Example of client send task and monitor task

Refs #1422

.circleci/config.yml

@@ -0,0 +1,201 @@
+version: 2
+
+defaults: &defaults
+  working_directory: /go/src/github.com/tendermint/tendermint
+  docker:
+    - image: circleci/golang:1.10.0
+  environment:
+    GOBIN: /tmp/workspace/bin
+
+jobs:
+  setup_dependencies:
+    <<: *defaults
+    steps:
+      - run: mkdir -p /tmp/workspace/bin
+      - run: mkdir -p /tmp/workspace/profiles
+      - checkout
+      - restore_cache:
+          keys:
+            - v1-pkg-cache
+      - run:
+          name: tools
+          command: |
+            export PATH="$GOBIN:$PATH"
+            make get_tools
+      - run:
+          name: dependencies
+          command: |
+            export PATH="$GOBIN:$PATH"
+            make get_vendor_deps
+      - run:
+          name: binaries
+          command: |
+            export PATH="$GOBIN:$PATH"
+            make install
+      - persist_to_workspace:
+          root: /tmp/workspace
+          paths:
+            - bin
+            - profiles
+      - save_cache:
+          key: v1-pkg-cache
+          paths:
+            - /go/pkg
+      - save_cache:
+          key: v1-tree-{{ .Environment.CIRCLE_SHA1 }}
+          paths:
+            - /go/src/github.com/tendermint/tendermint
+
+  setup_abci:
+    <<: *defaults
+    steps:
+      - attach_workspace:
+          at: /tmp/workspace
+      - restore_cache:
+          key: v1-pkg-cache
+      - restore_cache:
+          key: v1-tree-{{ .Environment.CIRCLE_SHA1 }}
+      - run:
+          name: Checkout abci
+          command: |
+            commit=$(bash scripts/dep_utils/parse.sh abci)
+            go get -v -u -d github.com/tendermint/abci/...
+            cd /go/src/github.com/tendermint/abci
+            git checkout "$commit"
+      - run:
+          working_directory: /go/src/github.com/tendermint/abci
+          name: Install abci
+          command: |
+            set -ex
+            export PATH="$GOBIN:$PATH"
+            make get_tools
+            make get_vendor_deps
+            make install
+      - run: ls -lah /tmp/workspace/bin
+      - persist_to_workspace:
+          root: /tmp/workspace
+          paths:
+            - "bin/abci*"
+
+  lint:
+    <<: *defaults
+    steps:
+      - attach_workspace:
+          at: /tmp/workspace
+      - restore_cache:
+          key: v1-pkg-cache
+      - restore_cache:
+          key: v1-tree-{{ .Environment.CIRCLE_SHA1 }}
+      - run:
+          name: metalinter
+          command: |
+            set -ex
+            export PATH="$GOBIN:$PATH"
+            make metalinter
+
+  test_apps:
+    <<: *defaults
+    steps:
+      - attach_workspace:
+          at: /tmp/workspace
+      - restore_cache:
+          key: v1-pkg-cache
+      - restore_cache:
+          key: v1-tree-{{ .Environment.CIRCLE_SHA1 }}
+      - run: sudo apt-get update && sudo apt-get install -y --no-install-recommends bsdmainutils
+      - run:
+          name: Run tests
+          command: bash test/app/test.sh
+
+  test_cover:
+    <<: *defaults
+    parallelism: 4
+    steps:
+      - attach_workspace:
+          at: /tmp/workspace
+      - restore_cache:
+          key: v1-pkg-cache
+      - restore_cache:
+          key: v1-tree-{{ .Environment.CIRCLE_SHA1 }}
+      - run:
+          name: Run tests
+          command: |
+            for pkg in $(go list github.com/tendermint/tendermint/... | grep -v /vendor/ | circleci tests split --split-by=timings); do
+              id=$(basename "$pkg")
+
+              go test -timeout 5m -race -coverprofile=/tmp/workspace/profiles/$id.out -covermode=atomic "$pkg"
+            done
+      - persist_to_workspace:
+          root: /tmp/workspace
+          paths:
+            - "profiles/*"
+
+  test_persistence:
+    <<: *defaults
+    steps:
+      - attach_workspace:
+          at: /tmp/workspace
+      - restore_cache:
+          key: v1-pkg-cache
+      - restore_cache:
+          key: v1-tree-{{ .Environment.CIRCLE_SHA1 }}
+      - run:
+          name: Run tests
+          command: bash test/persist/test_failure_indices.sh
+
+  test_p2p:
+    environment:
+      GOBIN: /home/circleci/.go_workspace/bin
+      GOPATH: /home/circleci/.go_workspace
+    machine:
+      image: circleci/classic:latest
+    steps:
+      - checkout
+      - run: mkdir -p $GOPATH/src/github.com/tendermint
+      - run: ln -sf /home/circleci/project $GOPATH/src/github.com/tendermint/tendermint
+      - run: bash test/circleci/p2p.sh
+
+  upload_coverage:
+    <<: *defaults
+    steps:
+      - attach_workspace:
+          at: /tmp/workspace
+      - restore_cache:
+          key: v1-tree-{{ .Environment.CIRCLE_SHA1 }}
+      - run:
+          name: gather
+          command: |
+            set -ex
+
+            echo "mode: atomic" > coverage.txt
+            for prof in $(ls /tmp/workspace/profiles/); do
+              tail -n +2 /tmp/workspace/profiles/"$prof" >> coverage.txt
+            done
+      - run:
+          name: upload
+          command: bash <(curl -s https://codecov.io/bash) -f coverage.txt
+
+workflows:
+  version: 2
+  test-suite:
+    jobs:
+      - setup_dependencies
+      - setup_abci:
+          requires:
+            - setup_dependencies
+      - lint:
+          requires:
+            - setup_dependencies
+      - test_apps:
+          requires:
+            - setup_abci
+      - test_cover:
+          requires:
+            - setup_dependencies
+      - test_persistence:
+          requires:
+            - setup_abci
+      - test_p2p
+      - upload_coverage:
+          requires:
+            - test_cover

.codecov.yml

@@ -1,21 +0,0 @@
-
-#
-# This codecov.yml is the default configuration for
-# all repositories on Codecov. You may adjust the settings
-# below in your own codecov.yml in your repository.
-#
-coverage:
-  precision: 2
-  round: down
-  range: 70...100
-
-  status:
-    # Learn more at https://codecov.io/docs#yaml_default_commit_status
-    project: 
-      default:
-        threshold: 1% # allow this much decrease on project
-    changes: false
-
-comment:
-  layout: "header, diff"
-  behavior: default  # update if exists else create new

.editorconfig

@@ -8,8 +8,9 @@ end_of_line = lf
 insert_final_newline = true
 trim_trailing_whitespace = true
 
-[Makefile]
+[*.{sh,Makefile}]
 indent_style = tab
 
-[*.sh]
-indent_style = tab
+[*.proto]
+indent_style = space
+indent_size = 2

.github/CODEOWNERS

@@ -0,0 +1,4 @@
+# CODEOWNERS: https://help.github.com/articles/about-codeowners/
+
+# Everything goes through Bucky and Anton. For now.
+*       @ebuchman @melekes

.github/ISSUE_TEMPLATE

@@ -37,5 +37,8 @@ in a case of bug.
 
 **How to reproduce it** (as minimally and precisely as possible):
 
+**Logs (you can paste a part showing an error or attach the whole file)**:
+
+**`/dump_consensus_state` output for consensus bugs**
 
 **Anything else do we need to know**:

.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,6 @@
+<!-- Thanks for filing a PR! Before hitting the button, please check the following items.-->
+
+* [ ] Updated all relevant documentation in docs
+* [ ] Updated all code comments where relevant
+* [ ] Wrote tests
+* [ ] Updated CHANGELOG.md

.gitignore

@@ -14,3 +14,14 @@ vendor
 test/p2p/data/
 test/logs
 .glide
+coverage.txt
+docs/_build
+docs/tools
+docs/abci-spec.rst
+*.log
+
+scripts/wal2json/wal2json
+scripts/cutWALUntil/cutWALUntil
+
+.idea/
+*.iml

CHANGELOG.md

@@ -1,5 +1,423 @@
 # Changelog
 
+## Roadmap
+
+BREAKING CHANGES:
+- Better support for injecting randomness
+- Upgrade consensus for more real-time use of evidence
+
+FEATURES:
+- Use the chain as its own CA for nodes and validators
+- Tooling to run multiple blockchains/apps, possibly in a single process
+- State syncing (without transaction replay)
+- Add authentication and rate-limitting to the RPC
+
+IMPROVEMENTS:
+- Improve subtleties around mempool caching and logic
+- Consensus optimizations:
+	- cache block parts for faster agreement after round changes
+	- propagate block parts rarest first
+- Better testing of the consensus state machine (ie. use a DSL)
+- Auto compiled serialization/deserialization code instead of go-wire reflection
+
+BUG FIXES:
+- Graceful handling/recovery for apps that have non-determinism or fail to halt
+- Graceful handling/recovery for violations of safety, or liveness
+
+## 0.19.0 (April 13th, 2018)
+
+BREAKING:
+- [cmd] improved `testnet` command; now it can fill in `persistent_peers` for you in the config file and much more (see `tendermint testnet --help` for details)
+- [cmd] `show_node_id` now returns an error if there is no node key
+- [rpc]: changed the output format for the `/status` endpoint (see https://godoc.org/github.com/tendermint/tendermint/rpc/core#Status)
+
+Upgrade from go-wire to go-amino. This is a sweeping change that breaks everything that is
+serialized to disk or over the network.
+
+See github.com/tendermint/go-amino for details on the new format.
+
+See `scripts/wire2amino.go` for a tool to upgrade
+genesis/priv_validator/node_key JSON files.
+
+FEATURES:
+- [cmd] added `gen_node_key` command
+
+## 0.18.0 (April 6th, 2018)
+
+BREAKING:
+
+- [types] Merkle tree uses different encoding for varints (see tmlibs v0.8.0)
+- [types] ValidtorSet.GetByAddress returns -1 if no validator found
+- [p2p] require all addresses come with an ID no matter what
+- [rpc] Listening address must contain tcp:// or unix:// prefix
+
+FEATURES:
+
+- [rpc] StartHTTPAndTLSServer (not used yet)
+- [rpc] Include validator's voting power in `/status`
+- [rpc] `/tx` and `/tx_search` responses now include the transaction hash
+- [rpc] Include peer NodeIDs in `/net_info`
+
+IMPROVEMENTS:
+- [config] trim whitespace from elements of lists (like `persistent_peers`)
+- [rpc] `/tx_search` results are sorted by height
+- [p2p] do not try to connect to ourselves (ok, maybe only once)
+- [p2p] seeds respond with a bias towards good peers
+
+BUG FIXES:
+- [rpc] fix subscribing using an abci.ResponseDeliverTx tag
+- [rpc] fix tx_indexers matchRange
+- [rpc] fix unsubscribing (see tmlibs v0.8.0)
+
+## 0.17.1 (March 27th, 2018)
+
+BUG FIXES:
+- [types] Actually support `app_state` in genesis as `AppStateJSON`
+
+## 0.17.0 (March 27th, 2018)
+
+BREAKING:
+- [types] WriteSignBytes -> SignBytes
+
+IMPROVEMENTS:
+- [all] renamed `dummy` (`persistent_dummy`) to `kvstore` (`persistent_kvstore`) (name "dummy" is deprecated and will not work in the next breaking release)
+- [docs] note on determinism (docs/determinism.rst)
+- [genesis] `app_options` field is deprecated. please rename it to `app_state` in your genesis file(s). `app_options` will not work in the next breaking release
+- [p2p] dial seeds directly without potential peers
+- [p2p] exponential backoff for addrs in the address book
+- [p2p] mark peer as good if it contributed enough votes or block parts
+- [p2p] stop peer if it sends incorrect data, msg to unknown channel, msg we did not expect
+- [p2p] when `auth_enc` is true, all dialed peers must have a node ID in their address
+- [spec] various improvements
+- switched from glide to dep internally for package management
+- [wire] prep work for upgrading to new go-wire (which is now called go-amino)
+
+FEATURES:
+- [config] exposed `auth_enc` flag to enable/disable encryption
+- [config] added the `--p2p.private_peer_ids` flag and `PrivatePeerIDs` config variable (see config for description)
+- [rpc] added `/health` endpoint, which returns empty result for now
+- [types/priv_validator] new format and socket client, allowing for remote signing
+
+BUG FIXES:
+- [consensus] fix liveness bug by introducing ValidBlock mechanism
+
+## 0.16.0 (February 20th, 2018)
+
+BREAKING CHANGES:
+- [config] use $TMHOME/config for all config and json files
+- [p2p] old `--p2p.seeds` is now `--p2p.persistent_peers` (persistent peers to which TM will always connect to)
+- [p2p] now `--p2p.seeds` only used for getting addresses (if addrbook is empty; not persistent)
+- [p2p] NodeInfo: remove RemoteAddr and add Channels
+    - we must have at least one overlapping channel with peer
+    - we only send msgs for channels the peer advertised
+- [p2p/conn] pong timeout
+- [lite] comment out IAVL related code
+
+FEATURES:
+- [p2p] added new `/dial_peers&persistent=_` **unsafe** endpoint
+- [p2p] persistent node key in `$THMHOME/config/node_key.json`
+- [p2p] introduce peer ID and authenticate peers by ID using addresses like `ID@IP:PORT`
+- [p2p/pex] new seed mode crawls the network and serves as a seed.
+- [config] MempoolConfig.CacheSize
+- [config] P2P.SeedMode (`--p2p.seed_mode`)
+
+IMPROVEMENT:
+- [p2p/pex] stricter rules in the PEX reactor for better handling of abuse
+- [p2p] various improvements to code structure including subpackages for `pex` and `conn`
+- [docs] new spec!
+- [all] speed up the tests!
+
+BUG FIX:
+- [blockchain] StopPeerForError on timeout
+- [consensus] StopPeerForError on a bad Maj23 message
+- [state] flush mempool conn before calling commit
+- [types] fix priv val signing things that only differ by timestamp
+- [mempool] fix memory leak causing zombie peers
+- [p2p/conn] fix potential deadlock
+
+## 0.15.0 (December 29, 2017)
+
+BREAKING CHANGES:
+- [p2p] enable the Peer Exchange reactor by default
+- [types] add Timestamp field to Proposal/Vote
+- [types] add new fields to Header: TotalTxs, ConsensusParamsHash, LastResultsHash, EvidenceHash
+- [types] add Evidence to Block
+- [types] simplify ValidateBasic
+- [state] updates to support changes to the header
+- [state] Enforce <1/3 of validator set can change at a time
+
+FEATURES:
+- [state] Send indices of absent validators and addresses of byzantine validators in BeginBlock
+- [state] Historical ConsensusParams and ABCIResponses
+- [docs] Specification for the base Tendermint data structures.
+- [evidence] New evidence reactor for gossiping and managing evidence
+- [rpc] `/block_results?height=X` returns the DeliverTx results for a given height.
+
+IMPROVEMENTS:
+- [consensus] Better handling of corrupt WAL file
+
+BUG FIXES:
+- [lite] fix race
+- [state] validate block.Header.ValidatorsHash
+- [p2p] allow seed addresses to be prefixed with eg. `tcp://`
+- [p2p] use consistent key to refer to peers so we dont try to connect to existing peers
+- [cmd] fix `tendermint init` to ignore files that are there and generate files that aren't.
+
+## 0.14.0 (December 11, 2017)
+
+BREAKING CHANGES:
+- consensus/wal: removed separator
+- rpc/client: changed Subscribe/Unsubscribe/UnsubscribeAll funcs signatures to be identical to event bus.
+
+FEATURES:
+- new `tendermint lite` command (and `lite/proxy` pkg) for running a light-client RPC proxy.
+    NOTE it is currently insecure and its APIs are not yet covered by semver
+
+IMPROVEMENTS:
+- rpc/client: can act as event bus subscriber (See https://github.com/tendermint/tendermint/issues/945).
+- p2p: use exponential backoff from seconds to hours when attempting to reconnect to persistent peer
+- config: moniker defaults to the machine's hostname instead of "anonymous"
+
+BUG FIXES:
+- p2p: no longer exit if one of the seed addresses is incorrect
+
+## 0.13.0 (December 6, 2017)
+
+BREAKING CHANGES:
+- abci: update to v0.8 using gogo/protobuf; includes tx tags, vote info in RequestBeginBlock, data.Bytes everywhere, use int64, etc.
+- types: block heights are now `int64` everywhere
+- types & node: EventSwitch and EventCache have been replaced by EventBus and EventBuffer; event types have been overhauled
+- node: EventSwitch methods now refer to EventBus
+- rpc/lib/types: RPCResponse is no longer a pointer; WSRPCConnection interface has been modified
+- rpc/client: WaitForOneEvent takes an EventsClient instead of types.EventSwitch
+- rpc/client: Add/RemoveListenerForEvent are now Subscribe/Unsubscribe
+- rpc/core/types: ResultABCIQuery wraps an abci.ResponseQuery
+- rpc: `/subscribe` and `/unsubscribe` take `query` arg instead of `event`
+- rpc: `/status` returns the LatestBlockTime in human readable form instead of in nanoseconds
+- mempool: cached transactions return an error instead of an ABCI response with BadNonce
+
+FEATURES:
+- rpc: new `/unsubscribe_all` WebSocket RPC endpoint
+- rpc: new `/tx_search` endpoint for filtering transactions by more complex queries
+- p2p/trust: new trust metric for tracking peers. See ADR-006
+- config: TxIndexConfig allows to set what DeliverTx tags to index
+
+IMPROVEMENTS:
+- New asynchronous events system using `tmlibs/pubsub`
+- logging: Various small improvements
+- consensus: Graceful shutdown when app crashes
+- tests: Fix various non-deterministic errors
+- p2p: more defensive programming
+
+BUG FIXES:
+- consensus: fix panic where prs.ProposalBlockParts is not initialized
+- p2p: fix panic on bad channel
+
+## 0.12.1 (November 27, 2017)
+
+BUG FIXES:
+- upgrade tmlibs dependency to enable Windows builds for Tendermint
+
+## 0.12.0 (October 27, 2017)
+
+BREAKING CHANGES:
+ - rpc/client: websocket ResultsCh and ErrorsCh unified in ResponsesCh.
+ - rpc/client: ABCIQuery no longer takes `prove`
+ - state: remove GenesisDoc from state.
+ - consensus: new binary WAL format provides efficiency and uses checksums to detect corruption
+    - use scripts/wal2json to convert to json for debugging
+
+FEATURES:
+ - new `certifiers` pkg contains the tendermint light-client library (name subject to change)!
+ - rpc: `/genesis` includes the `app_options` .
+ - rpc: `/abci_query` takes an additional `height` parameter to support historical queries.
+ - rpc/client: new ABCIQueryWithOptions supports options like `trusted` (set false to get a proof) and `height` to query a historical height.
+
+IMPROVEMENTS:
+ - rpc: `/genesis` result includes `app_options`
+ - rpc/lib/client: add jitter to reconnects.
+ - rpc/lib/types: `RPCError` satisfies the `error` interface.
+
+BUG FIXES:
+ - rpc/client: fix ws deadlock after stopping
+ - blockchain: fix panic on AddBlock when peer is nil
+ - mempool: fix sending on TxsAvailable when a tx has been invalidated
+ - consensus: dont run WAL catchup if we fast synced
+
+## 0.11.1 (October 10, 2017)
+
+IMPROVEMENTS:
+ - blockchain/reactor: respondWithNoResponseMessage for missing height
+
+BUG FIXES:
+ - rpc: fixed client WebSocket timeout
+ - rpc: client now resubscribes on reconnection
+ - rpc: fix panics on missing params
+ - rpc: fix `/dump_consensus_state` to have normal json output (NOTE: technically breaking, but worth a bug fix label)
+ - types: fixed out of range error in VoteSet.addVote
+ - consensus: fix wal autofile via https://github.com/tendermint/tmlibs/blob/master/CHANGELOG.md#032-october-2-2017
+
+## 0.11.0 (September 22, 2017)
+
+BREAKING:
+ - genesis file: validator `amount` is now `power`
+ - abci: Info, BeginBlock, InitChain all take structs
+ - rpc: various changes to match JSONRPC spec (http://www.jsonrpc.org/specification), including breaking ones:
+    - requests that previously returned HTTP code 4XX now return 200 with an error code in the JSONRPC.
+    - `rpctypes.RPCResponse` uses new `RPCError` type instead of `string`.
+
+ - cmd: if there is no genesis, exit immediately instead of waiting around for one to show.
+ - types: `Signer.Sign` returns an error.
+ - state: every validator set change is persisted to disk, which required some changes to the `State` structure.
+ - p2p: new `p2p.Peer` interface used for all reactor methods (instead of `*p2p.Peer` struct).
+
+FEATURES:
+ - rpc: `/validators?height=X` allows querying of validators at previous heights.
+ - rpc: Leaving the `height` param empty for `/block`, `/validators`, and `/commit` will return the value for the latest height.
+
+IMPROVEMENTS:
+ - docs: Moved all docs from the website and tools repo in, converted to `.rst`, and cleaned up for presentation on `tendermint.readthedocs.io`
+
+BUG FIXES:
+ - fix WAL openning issue on Windows
+
+## 0.10.4 (September 5, 2017)
+
+IMPROVEMENTS:
+- docs: Added Slate docs to each rpc function (see rpc/core)
+- docs: Ported all website docs to Read The Docs
+- config: expose some p2p params to tweak performance: RecvRate, SendRate, and MaxMsgPacketPayloadSize
+- rpc: Upgrade the websocket client and server, including improved auto reconnect, and proper ping/pong
+
+BUG FIXES:
+- consensus: fix panic on getVoteBitArray
+- consensus: hang instead of panicking on byzantine consensus failures
+- cmd: dont load config for version command
+
+## 0.10.3 (August 10, 2017)
+
+FEATURES:
+- control over empty block production:
+  - new flag, `--consensus.create_empty_blocks`; when set to false, blocks are only created when there are txs or when the AppHash changes.
+  - new config option, `consensus.create_empty_blocks_interval`; an empty block is created after this many seconds.
+  - in normal operation, `create_empty_blocks = true` and `create_empty_blocks_interval = 0`, so blocks are being created all the time (as in all previous versions of tendermint). The number of empty blocks can be reduced by increasing `create_empty_blocks_interval` or by setting `create_empty_blocks = false`.
+  - new `TxsAvailable()` method added to Mempool that returns a channel which fires when txs are available.
+  - new heartbeat message added to consensus reactor to notify peers that a node is waiting for txs before entering propose step.
+- rpc: Add `syncing` field to response returned by `/status`. Is `true` while in fast-sync mode.
+
+IMPROVEMENTS:
+- various improvements to documentation and code comments
+
+BUG FIXES:
+- mempool: pass height into constructor so it doesn't always start at 0
+
+## 0.10.2 (July 10, 2017)
+
+FEATURES:
+- Enable lower latency block commits by adding consensus reactor sleep durations and p2p flush throttle timeout to the config
+
+IMPROVEMENTS:
+- More detailed logging in the consensus reactor and state machine
+- More in-code documentation for many exposed functions, especially in consensus/reactor.go and p2p/switch.go
+- Improved readability for some function definitions and code blocks with long lines
+
+## 0.10.1 (June 28, 2017)
+
+FEATURES:
+- Use `--trace` to get stack traces for logged errors
+- types: GenesisDoc.ValidatorHash returns the hash of the genesis validator set
+- types: GenesisDocFromFile parses a GenesiDoc from a JSON file
+
+IMPROVEMENTS:
+- Add a Code of Conduct
+- Variety of improvements as suggested by `megacheck` tool
+- rpc: deduplicate tests between rpc/client and rpc/tests
+- rpc: addresses without a protocol prefix default to `tcp://`. `http://` is also accepted as an alias for `tcp://`
+- cmd: commands are more easily reuseable from other tools
+- DOCKER: automate build/push
+
+BUG FIXES:
+- Fix log statements using keys with spaces (logger does not currently support spaces)
+- rpc: set logger on websocket connection
+- rpc: fix ws connection stability by setting write deadline on pings
+
+## 0.10.0 (June 2, 2017)
+
+Includes major updates to configuration, logging, and json serialization.
+Also includes the Grand Repo-Merge of 2017.
+
+BREAKING CHANGES:
+
+- Config and Flags:
+  - The `config` map is replaced with a [`Config` struct](https://github.com/tendermint/tendermint/blob/master/config/config.go#L11),
+containing substructs: `BaseConfig`, `P2PConfig`, `MempoolConfig`, `ConsensusConfig`, `RPCConfig`
+  - This affects the following flags:
+    - `--seeds` is now `--p2p.seeds`
+    - `--node_laddr` is now `--p2p.laddr`
+    - `--pex` is now `--p2p.pex`
+    - `--skip_upnp` is now `--p2p.skip_upnp`
+    - `--rpc_laddr` is now `--rpc.laddr`
+    - `--grpc_laddr` is now `--rpc.grpc_laddr`
+  - Any configuration option now within a substract must come under that heading in the `config.toml`, for instance:
+    ```
+    [p2p]
+    laddr="tcp://1.2.3.4:46656"
+
+    [consensus]
+    timeout_propose=1000
+    ```
+  - Use viper and `DefaultConfig() / TestConfig()` functions to handle defaults, and remove `config/tendermint` and `config/tendermint_test`
+  - Change some function and method signatures to
+  - Change some [function and method signatures](https://gist.github.com/ebuchman/640d5fc6c2605f73497992fe107ebe0b) accomodate new config
+
+- Logger
+  - Replace static `log15` logger with a simple interface, and provide a new implementation using `go-kit`.
+See our new [logging library](https://github.com/tendermint/tmlibs/log) and [blog post](https://tendermint.com/blog/abstracting-the-logger-interface-in-go) for more details
+  - Levels `warn` and `notice` are removed (you may need to change them in your `config.toml`!)
+  - Change some [function and method signatures](https://gist.github.com/ebuchman/640d5fc6c2605f73497992fe107ebe0b) to accept a logger
+
+- JSON serialization:
+  - Replace `[TypeByte, Xxx]` with `{"type": "some-type", "data": Xxx}` in RPC and all `.json` files by using `go-wire/data`. For instance, a public key is now:
+    ```
+    "pub_key": {
+      "type": "ed25519",
+      "data": "83DDF8775937A4A12A2704269E2729FCFCD491B933C4B0A7FFE37FE41D7760D0"
+    }
+    ```
+  - Remove type information about RPC responses, so `[TypeByte, {"jsonrpc": "2.0", ... }]` is now just `{"jsonrpc": "2.0", ... }`
+  - Change `[]byte` to `data.Bytes` in all serialized types (for hex encoding)
+  - Lowercase the JSON tags in `ValidatorSet` fields
+  - Introduce `EventDataInner` for serializing events
+
+- Other:
+  - Send InitChain message in handshake if `appBlockHeight == 0`
+  - Do not include the `Accum` field when computing the validator hash. This makes the ValidatorSetHash unique for a given validator set, rather than changing with every block (as the Accum changes)
+  - Unsafe RPC calls are not enabled by default. This includes `/dial_seeds`, and all calls prefixed with `unsafe`. Use the `--rpc.unsafe` flag to enable.
+
+
+FEATURES:
+
+- Per-module log levels. For instance, the new default is `state:info,*:error`, which means the `state` package logs at `info` level, and everything else logs at `error` level
+- Log if a node is validator or not in every consensus round
+- Use ldflags to set git hash as part of the version
+- Ignore `address` and `pub_key` fields in `priv_validator.json` and overwrite them with the values derrived from the `priv_key`
+
+IMPROVEMENTS:
+
+- Merge `tendermint/go-p2p -> tendermint/tendermint/p2p` and `tendermint/go-rpc -> tendermint/tendermint/rpc/lib`
+- Update paths for grand repo merge:
+  - `go-common -> tmlibs/common`
+  - `go-data -> go-wire/data`
+  - All other `go-` libs, except `go-crypto` and `go-wire`, are merged under `tmlibs`
+- No global loggers (loggers are passed into constructors, or preferably set with a SetLogger method)
+- Return HTTP status codes with errors for RPC responses
+- Limit `/blockchain_info` call to return a maximum of 20 blocks
+- Use `.Wrap()` and `.Unwrap()` instead of eg. `PubKeyS` for `go-crypto` types
+- RPC JSON responses use pretty printing (via `json.MarshalIndent`)
+- Color code different instances of the consensus for tests
+- Isolate viper to `cmd/tendermint/commands` and do not read config from file for tests
+
+
 ## 0.9.2 (April 26, 2017)
 
 BUG FIXES:
@@ -24,7 +442,7 @@ IMPROVEMENTS:
 - WAL uses #ENDHEIGHT instead of #HEIGHT (#HEIGHT will stop working in 0.10.0)
 - Peers included via `--seeds`, under `seeds` in the config, or in `/dial_seeds` are now persistent, and will be reconnected to if the connection breaks
 
-BUG FIXES: 
+BUG FIXES:
 
 - Fix bug in fast-sync where we stop syncing after a peer is removed, even if they're re-added later
 - Fix handshake replay to handle validator set changes and results of DeliverTx when we crash after app.Commit but before state.Save()
@@ -40,7 +458,7 @@ message RequestQuery{
 	bytes data = 1;
 	string path = 2;
 	uint64 height = 3;
-	bool prove = 4; 
+	bool prove = 4;
 }
 
 message ResponseQuery{
@@ -64,7 +482,7 @@ type BlockMeta struct {
 }
 ```
 
-- `ValidatorSet.Proposer` is exposed as a field and persisted with the `State`. Use `GetProposer()` to initialize or update after validator-set changes. 
+- `ValidatorSet.Proposer` is exposed as a field and persisted with the `State`. Use `GetProposer()` to initialize or update after validator-set changes.
 
 - `tendermint gen_validator` command output is now pure JSON
 
@@ -107,7 +525,7 @@ type BlockID struct {
 }
 ```
 
-- `Vote` data type now includes validator address and index: 
+- `Vote` data type now includes validator address and index:
 
 ```
 type Vote struct {
@@ -127,7 +545,7 @@ type Vote struct {
 
 FEATURES:
 
-- New message type on the ConsensusReactor, `Maj23Msg`, for peers to alert others they've seen a Maj23, 
+- New message type on the ConsensusReactor, `Maj23Msg`, for peers to alert others they've seen a Maj23,
 in order to track and handle conflicting votes intelligently to prevent Byzantine faults from causing halts:
 
 ```
@@ -150,7 +568,7 @@ IMPROVEMENTS:
 - Less verbose logging
 - Better test coverage (37% -> 49%)
 - Canonical SignBytes for signable types
-- Write-Ahead Log for Mempool and Consensus via go-autofile 
+- Write-Ahead Log for Mempool and Consensus via tmlibs/autofile
 - Better in-process testing for the consensus reactor and byzantine faults
 - Better crash/restart testing for individual nodes at preset failure points, and of networks at arbitrary points
 - Better abstraction over timeout mechanics
@@ -230,7 +648,7 @@ FEATURES:
 - TMSP and RPC support TCP and UNIX sockets
 - Addition config options including block size and consensus parameters
 - New WAL mode `cswal_light`; logs only the validator's own votes
-- New RPC endpoints: 
+- New RPC endpoints:
 	- for starting/stopping profilers, and for updating config
 	- `/broadcast_tx_commit`, returns when tx is included in a block, else an error
 	- `/unsafe_flush_mempool`, empties the mempool
@@ -251,14 +669,14 @@ BUG FIXES:
 
 Strict versioning only began with the release of v0.7.0, in late summer 2016.
 The project itself began in early summer 2014 and was workable decentralized cryptocurrency software by the end of that year.
-Through the course of 2015, in collaboration with Eris Industries (now Monax Indsutries), 
+Through the course of 2015, in collaboration with Eris Industries (now Monax Indsutries),
 many additional features were integrated, including an implementation from scratch of the Ethereum Virtual Machine.
-That implementation now forms the heart of [ErisDB](https://github.com/eris-ltd/eris-db).
+That implementation now forms the heart of [Burrow](https://github.com/hyperledger/burrow).
 In the later half of 2015, the consensus algorithm was upgraded with a more asynchronous design and a more deterministic and robust implementation.
 
-By late 2015, frustration with the difficulty of forking a large monolithic stack to create alternative cryptocurrency designs led to the 
+By late 2015, frustration with the difficulty of forking a large monolithic stack to create alternative cryptocurrency designs led to the
 invention of the Application Blockchain Interface (ABCI), then called the Tendermint Socket Protocol (TMSP).
 The Ethereum Virtual Machine and various other transaction features were removed, and Tendermint was whittled down to a core consensus engine
-driving an application running in another process. 
+driving an application running in another process.
 The ABCI interface and implementation were iterated on and improved over the course of 2016,
 until versioned history kicked in with v0.7.0.

CODE_OF_CONDUCT.md

@@ -0,0 +1,56 @@
+# The Tendermint Code of Conduct
+This code of conduct applies to all projects run by the Tendermint/COSMOS team and hence to tendermint.
+
+
+----
+
+
+# Conduct
+## Contact: adrian@tendermint.com
+
+* We are committed to providing a friendly, safe and welcoming environment for all, regardless of level of experience, gender, gender identity and expression, sexual orientation, disability, personal appearance, body size, race, ethnicity, age, religion, nationality, or other similar characteristic.
+
+* On Slack, please avoid using overtly sexual nicknames or other nicknames that might detract from a friendly, safe and welcoming environment for all.
+
+* Please be kind and courteous. There’s no need to be mean or rude.
+
+* Respect that people have differences of opinion and that every design or implementation choice carries a trade-off and numerous costs. There is seldom a right answer.
+
+* Please keep unstructured critique to a minimum. If you have solid ideas you want to experiment with, make a fork and see how it works.
+
+* We will exclude you from interaction if you insult, demean or harass anyone. That is not welcome behaviour. We interpret the term “harassment” as including the definition in the [Citizen Code of Conduct](http://citizencodeofconduct.org/); if you have any lack of clarity about what might be included in that concept, please read their definition. In particular, we don’t tolerate behavior that excludes people in socially marginalized groups.
+
+* Private harassment is also unacceptable. No matter who you are, if you feel you have been or are being harassed or made uncomfortable by a community member, please contact one of the channel admins or the person mentioned above immediately. Whether you’re a regular contributor or a newcomer, we care about making this community a safe place for you and we’ve got your back.
+
+* Likewise any spamming, trolling, flaming, baiting or other attention-stealing behaviour is not welcome.
+
+
+----
+
+
+# Moderation
+These are the policies for upholding our community’s standards of conduct. If you feel that a thread needs moderation, please contact the above mentioned person.
+
+1. Remarks that violate the Tendermint/COSMOS standards of conduct, including hateful, hurtful, oppressive, or exclusionary remarks, are not allowed. (Cursing is allowed, but never targeting another user, and never in a hateful manner.)
+
+2. Remarks that moderators find inappropriate, whether listed in the code of conduct or not, are also not allowed.
+
+3. Moderators will first respond to such remarks with a warning.
+
+4. If the warning is unheeded, the user will be “kicked,” i.e., kicked out of the communication channel to cool off.
+
+5. If the user comes back and continues to make trouble, they will be banned, i.e., indefinitely excluded.
+
+6. Moderators may choose at their discretion to un-ban the user if it was a first offense and they offer the offended party a genuine apology.
+
+7. If a moderator bans someone and you think it was unjustified, please take it up with that moderator, or with a different moderator, in private. Complaints about bans in-channel are not allowed.
+
+8. Moderators are held to a higher standard than other community members. If a moderator creates an inappropriate situation, they should expect less leeway than others.
+
+In the Tendermint/COSMOS community we strive to go the extra step to look out for each other. Don’t just aim to be technically unimpeachable, try to be your best self. In particular, avoid flirting with offensive or sensitive issues, particularly if they’re off-topic; this all too often leads to unnecessary fights, hurt feelings, and damaged trust; worse, it can drive people away from the community entirely.
+
+And if someone takes issue with something you said or did, resist the urge to be defensive. Just stop doing what it was they complained about and apologize. Even if you feel you were misinterpreted or unfairly accused, chances are good there was something you could’ve communicated better — remember that it’s your responsibility to make your fellow Cosmonauts comfortable. Everyone wants to get along and we are all here first and foremost because we want to talk about cool technology. You will find that people will be eager to assume good intent and forgive as long as you earn their trust.
+
+The enforcement policies listed above apply to all official Tendermint/COSMOS venues.For other projects adopting the Tendermint/COSMOS Code of Conduct, please contact the maintainers of those projects for enforcement. If you wish to use this code of conduct for your own project, consider explicitly mentioning your moderation policy or making a copy with your own moderation policy so as to avoid confusion.
+
+*Adapted from the [Node.js Policy on Trolling](http://blog.izs.me/post/30036893703/policy-on-trolling), the [Contributor Covenant v1.3.0](http://contributor-covenant.org/version/1/3/0/) and the [Rust Code of Conduct](https://www.rust-lang.org/en-US/conduct.html).

CONTRIBUTING.md

@@ -1,16 +1,117 @@
-# Contributing guidelines
+# Contributing
 
-**Thanks for considering making contributions to Tendermint!**
+Thank you for considering making contributions to Tendermint and related repositories! Start by taking a look at the [coding repo](https://github.com/tendermint/coding) for overall information on repository workflow and standards.
 
-Please follow standard github best practices: fork the repo, **branch from the
-tip of develop**, make some commits, test your code changes with `make test`,
-and submit a pull request to develop.
+Please follow standard github best practices: fork the repo, branch from the tip of develop, make some commits, and submit a pull request to develop. See the [open issues](https://github.com/tendermint/tendermint/issues) for things we need help with!
 
-See the [open issues](https://github.com/tendermint/tendermint/issues) for
-things we need help with!
+Please make sure to use `gofmt` before every commit - the easiest way to do this is have your editor run it for you upon saving a file.
 
-Please make sure to use `gofmt` before every commit - the easiest way to do
-this is have your editor run it for you upon saving a file.
+## Forking
 
-You can read the full guide [on our
-site](https://tendermint.com/docs/guides/contributing).
+Please note that Go requires code to live under absolute paths, which complicates forking.
+While my fork lives at `https://github.com/ebuchman/tendermint`,
+the code should never exist at  `$GOPATH/src/github.com/ebuchman/tendermint`.
+Instead, we use `git remote` to add the fork as a new remote for the original repo,
+`$GOPATH/src/github.com/tendermint/tendermint `, and do all the work there.
+
+For instance, to create a fork and work on a branch of it, I would:
+
+  * Create the fork on github, using the fork button.
+  * Go to the original repo checked out locally (ie. `$GOPATH/src/github.com/tendermint/tendermint`)
+  * `git remote rename origin upstream`
+  * `git remote add origin git@github.com:ebuchman/basecoin.git`
+
+Now `origin` refers to my fork and `upstream` refers to the tendermint version.
+So I can `git push -u origin master` to update my fork, and make pull requests to tendermint from there.
+Of course, replace `ebuchman` with your git handle.
+
+To pull in updates from the origin repo, run
+
+    * `git fetch upstream`
+    * `git rebase upstream/master` (or whatever branch you want)
+
+Please don't make Pull Requests to `master`.
+
+## Dependencies
+
+We use [dep](https://github.com/golang/dep) to manage dependencies.
+
+That said, the master branch of every Tendermint repository should just build
+with `go get`, which means they should be kept up-to-date with their
+dependencies so we can get away with telling people they can just `go get` our
+software.
+
+Since some dependencies are not under our control, a third party may break our
+build, in which case we can fall back on `dep ensure` (or `make
+get_vendor_deps`). Even for dependencies under our control, dep helps us to
+keep multiple repos in sync as they evolve. Anything with an executable, such
+as apps, tools, and the core, should use dep.
+
+Run `dep status` to get a list of vendored dependencies that may not be
+up-to-date.
+
+## Vagrant
+
+If you are a [Vagrant](https://www.vagrantup.com/) user, you can get started
+hacking Tendermint with the commands below.
+
+NOTE: In case you installed Vagrant in 2017, you might need to run
+`vagrant box update` to upgrade to the latest `ubuntu/xenial64`.
+
+```
+vagrant up
+vagrant ssh
+make test
+```
+
+## Testing
+
+All repos should be hooked up to [CircleCI](https://circleci.com/).
+
+If they have `.go` files in the root directory, they will be automatically
+tested by circle using `go test -v -race ./...`. If not, they will need a
+`circle.yml`. Ideally, every repo has a `Makefile` that defines `make test` and
+includes its continuous integration status using a badge in the `README.md`.
+
+## Branching Model and Release
+
+User-facing repos should adhere to the branching model: http://nvie.com/posts/a-successful-git-branching-model/.
+That is, these repos should be well versioned, and any merge to master requires a version bump and tagged release.
+
+Libraries need not follow the model strictly, but would be wise to,
+especially `go-p2p` and `go-rpc`, as their versions are referenced in tendermint core.
+
+### Development Procedure:
+- the latest state of development is on `develop`
+- `develop` must never fail `make test`
+- no --force onto `develop` (except when reverting a broken commit, which should seldom happen)
+- create a development branch either on github.com/tendermint/tendermint, or your fork (using `git add origin`)
+- before submitting a pull request, begin `git rebase` on top of `develop`
+
+### Pull Merge Procedure:
+- ensure pull branch is rebased on develop
+- run `make test` to ensure that all tests pass
+- merge pull request
+- the `unstable` branch may be used to aggregate pull merges before testing once
+- push master may request that pull requests be rebased on top of `unstable`
+
+### Release Procedure:
+- start on `develop`
+- run integration tests (see `test_integrations` in Makefile)
+- prepare changelog/release issue
+- bump versions
+- push to release-vX.X.X to run the extended integration tests on the CI
+- merge to master
+- merge master back to develop
+
+### Hotfix Procedure:
+- start on `master`
+- checkout a new branch named hotfix-vX.X.X
+- make the required changes
+  - these changes should be small and an absolute necessity
+  - add a note to CHANGELOG.md
+- bumb versions
+- push to hotfix-vX.X.X to run the extended integration tests on the CI
+- merge hotfix-vX.X.X to master
+- merge hotfix-vX.X.X to develop
+- delete the hotfix-vX.X.X branch

DOCKER/Dockerfile

@@ -1,8 +1,8 @@
-FROM alpine:3.5
+FROM alpine:3.7
 
 # This is the release of tendermint to pull in.
-ENV TM_VERSION 0.9.0
-ENV TM_SHA256SUM 697033ea0f34f8b34a8a2b74c4dd730b47dd4efcfce65e53e953bdae8eb14364
+ENV TM_VERSION 0.17.1
+ENV TM_SHA256SUM d57008c63d2d9176861137e38ed203da486febf20ae7d388fb810a75afff8f24
 
 # Tendermint will be looking for genesis file in /tendermint (unless you change
 # `genesis_file` in config.toml). You can put your config.toml and private
@@ -26,7 +26,7 @@ RUN mkdir -p $DATA_ROOT && \
 RUN apk add --no-cache bash curl jq
 
 RUN apk add --no-cache openssl && \
-    wget https://s3-us-west-2.amazonaws.com/tendermint/${TM_VERSION}/tendermint_${TM_VERSION}_linux_amd64.zip && \
+    wget https://github.com/tendermint/tendermint/releases/download/v${TM_VERSION}/tendermint_${TM_VERSION}_linux_amd64.zip && \
     echo "${TM_SHA256SUM}  tendermint_${TM_VERSION}_linux_amd64.zip" | sha256sum -c && \
     unzip -d /bin tendermint_${TM_VERSION}_linux_amd64.zip && \
     apk del openssl && \
@@ -42,5 +42,4 @@ EXPOSE 46657
 
 ENTRYPOINT ["tendermint"]
 
-# By default you'll get the dummy app
-CMD ["node", "--moniker=`hostname`", "--proxy_app=dummy"]
+CMD ["node", "--moniker=`hostname`"]

DOCKER/Dockerfile.develop

@@ -1,4 +1,4 @@
-FROM alpine:3.5
+FROM alpine:3.7
 
 ENV DATA_ROOT /tendermint
 ENV TMHOME $DATA_ROOT
@@ -18,9 +18,9 @@ RUN mkdir -p /go/src/github.com/tendermint/tendermint && \
     cd /go/src/github.com/tendermint/tendermint && \
     git clone https://github.com/tendermint/tendermint . && \
     git checkout develop && \
+    make get_tools && \
     make get_vendor_deps && \
     make install && \
-    glide cc && \
     cd - && \
     rm -rf /go/src/github.com/tendermint/tendermint && \
     apk del go build-base git
@@ -32,4 +32,4 @@ EXPOSE 46657
 
 ENTRYPOINT ["tendermint"]
 
-CMD ["node", "--moniker=`hostname`", "--proxy_app=dummy"]
+CMD ["node", "--moniker=`hostname`", "--proxy_app=kvstore"]

DOCKER/Makefile

@@ -1,10 +1,8 @@
 build:
-	# TAG=0.8.0 TAG_NO_PATCH=0.8
-	docker build -t "tendermint/tendermint" -t "tendermint/tendermint:$TAG" -t "tendermint/tendermint:$TAG_NO_PATCH" .
+	@sh -c "'$(CURDIR)/build.sh'"
 
 push:
-	# TAG=0.8.0 TAG_NO_PATCH=0.8
-	docker push "tendermint/tendermint" "tendermint/tendermint:$TAG" "tendermint/tendermint:$TAG_NO_PATCH"
+	@sh -c "'$(CURDIR)/push.sh'"
 
 build_develop:
 	docker build -t "tendermint/tendermint:develop" -f Dockerfile.develop .

DOCKER/README.md

@@ -1,41 +1,52 @@
 # Supported tags and respective `Dockerfile` links
 
-- `0.9.0`, `0.9`, `latest` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/d474baeeea6c22b289e7402449572f7c89ee21da/DOCKER/Dockerfile)
+- `0.17.1`, `latest` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/208ac32fa266657bd6c304e84ec828aa252bb0b8/DOCKER/Dockerfile)
+- `0.15.0` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/170777300ea92dc21a8aec1abc16cb51812513a4/DOCKER/Dockerfile)
+- `0.13.0` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/a28b3fff49dce2fb31f90abb2fc693834e0029c2/DOCKER/Dockerfile)
+- `0.12.1` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/457c688346b565e90735431619ca3ca597ef9007/DOCKER/Dockerfile)
+- `0.12.0` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/70d8afa6e952e24c573ece345560a5971bf2cc0e/DOCKER/Dockerfile)
+- `0.11.0` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/9177cc1f64ca88a4a0243c5d1773d10fba67e201/DOCKER/Dockerfile)
+- `0.10.0` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/e5342f4054ab784b2cd6150e14f01053d7c8deb2/DOCKER/Dockerfile)
+- `0.9.1`, `0.9`, [(Dockerfile)](https://github.com/tendermint/tendermint/blob/809e0e8c5933604ba8b2d096803ada7c5ec4dfd3/DOCKER/Dockerfile)
+- `0.9.0` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/d474baeeea6c22b289e7402449572f7c89ee21da/DOCKER/Dockerfile)
 - `0.8.0`, `0.8` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/bf64dd21fdb193e54d8addaaaa2ecf7ac371de8c/DOCKER/Dockerfile)
 - `develop` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/master/DOCKER/Dockerfile.develop)
 
 `develop` tag points to the [develop](https://github.com/tendermint/tendermint/tree/develop) branch.
 
+# Quick reference
+
+* **Where to get help:**
+  https://tendermint.com/community
+
+* **Where to file issues:**
+  https://github.com/tendermint/tendermint/issues
+
+* **Supported Docker versions:**
+  [the latest release](https://github.com/moby/moby/releases) (down to 1.6 on a best-effort basis)
+
 # Tendermint
 
 Tendermint Core is Byzantine Fault Tolerant (BFT) middleware that takes a state transition machine, written in any programming language, and securely replicates it on many machines.
 
-For more background, see the [introduction](https://tendermint.com/intro).
+For more background, see the [introduction](https://tendermint.readthedocs.io/en/master/introduction.html).
 
-To get started developing applications, see the [application developers guide](https://tendermint.com/docs/guides/app-development).
+To get started developing applications, see the [application developers guide](https://tendermint.readthedocs.io/en/master/getting-started.html).
 
 # How to use this image
 
-## Start one instance of the Tendermint core with the `dummy` app
+## Start one instance of the Tendermint core with the `kvstore` app
 
 A very simple example of a built-in app and Tendermint core in one container.
 
 ```
 docker run -it --rm -v "/tmp:/tendermint" tendermint/tendermint init
-docker run -it --rm -v "/tmp:/tendermint" tendermint/tendermint
+docker run -it --rm -v "/tmp:/tendermint" tendermint/tendermint node --proxy_app=kvstore
 ```
 
 ## mintnet-kubernetes
 
-If you want to see many containers talking to each other, consider using [mintnet-kubernetes](https://github.com/tendermint/mintnet-kubernetes), which is a tool for running Tendermint-based applications on a Kubernetes cluster.
-
-# Supported Docker versions
-
-This image is officially supported on Docker version 1.13.1.
-
-Support for older versions (down to 1.6) is provided on a best-effort basis.
-
-Please see [the Docker installation documentation](https://docs.docker.com/installation/) for details on how to upgrade your Docker daemon.
+If you want to see many containers talking to each other, consider using [mintnet-kubernetes](https://github.com/tendermint/tools/tree/master/mintnet-kubernetes), which is a tool for running Tendermint-based applications on a Kubernetes cluster.
 
 # License
 
@@ -43,12 +54,6 @@ View [license information](https://raw.githubusercontent.com/tendermint/tendermi
 
 # User Feedback
 
-## Issues
-
-If you have any problems with or questions about this image, please contact us through a [GitHub](https://github.com/tendermint/tendermint/issues) issue. If the issue is related to a CVE, please check for [a `cve-tracker` issue on the `official-images` repository](https://github.com/docker-library/official-images/issues?q=label%3Acve-tracker) first.
-
-You can also reach the image maintainers via [Slack](http://forum.tendermint.com:3000/).
-
 ## Contributing
 
 You are invited to contribute new features, fixes, or updates, large or small; we are always thrilled to receive pull requests, and do our best to process them as fast as we can.

DOCKER/build.sh

@@ -0,0 +1,20 @@
+#!/usr/bin/env bash
+set -e
+
+# Get the tag from the version, or try to figure it out.
+if [ -z "$TAG" ]; then
+	TAG=$(awk -F\" '/Version =/ { print $2; exit }' < ../version/version.go)
+fi
+if [ -z "$TAG" ]; then
+		echo "Please specify a tag."
+		exit 1
+fi
+
+TAG_NO_PATCH=${TAG%.*}
+
+read -p "==> Build 3 docker images with the following tags (latest, $TAG, $TAG_NO_PATCH)? y/n" -n 1 -r
+echo
+if [[ $REPLY =~ ^[Yy]$ ]]
+then
+		docker build -t "tendermint/tendermint" -t "tendermint/tendermint:$TAG" -t "tendermint/tendermint:$TAG_NO_PATCH" .
+fi

DOCKER/push.sh

@@ -0,0 +1,22 @@
+#!/usr/bin/env bash
+set -e
+
+# Get the tag from the version, or try to figure it out.
+if [ -z "$TAG" ]; then
+	TAG=$(awk -F\" '/Version =/ { print $2; exit }' < ../version/version.go)
+fi
+if [ -z "$TAG" ]; then
+		echo "Please specify a tag."
+		exit 1
+fi
+
+TAG_NO_PATCH=${TAG%.*}
+
+read -p "==> Push 3 docker images with the following tags (latest, $TAG, $TAG_NO_PATCH)? y/n" -n 1 -r
+echo
+if [[ $REPLY =~ ^[Yy]$ ]]
+then
+	docker push "tendermint/tendermint:latest"
+	docker push "tendermint/tendermint:$TAG"
+	docker push "tendermint/tendermint:$TAG_NO_PATCH"
+fi

Gopkg.lock

@@ -0,0 +1,388 @@
+# This file is autogenerated, do not edit; changes may be undone by the next 'dep ensure'.
+
+
+[[projects]]
+  branch = "master"
+  name = "github.com/btcsuite/btcd"
+  packages = ["btcec"]
+  revision = "2be2f12b358dc57d70b8f501b00be450192efbc3"
+
+[[projects]]
+  name = "github.com/davecgh/go-spew"
+  packages = ["spew"]
+  revision = "346938d642f2ec3594ed81d874461961cd0faa76"
+  version = "v1.1.0"
+
+[[projects]]
+  branch = "master"
+  name = "github.com/ebuchman/fail-test"
+  packages = ["."]
+  revision = "95f809107225be108efcf10a3509e4ea6ceef3c4"
+
+[[projects]]
+  name = "github.com/fortytw2/leaktest"
+  packages = ["."]
+  revision = "a5ef70473c97b71626b9abeda80ee92ba2a7de9e"
+  version = "v1.2.0"
+
+[[projects]]
+  name = "github.com/fsnotify/fsnotify"
+  packages = ["."]
+  revision = "c2828203cd70a50dcccfb2761f8b1f8ceef9a8e9"
+  version = "v1.4.7"
+
+[[projects]]
+  name = "github.com/go-kit/kit"
+  packages = [
+    "log",
+    "log/level",
+    "log/term"
+  ]
+  revision = "4dc7be5d2d12881735283bcab7352178e190fc71"
+  version = "v0.6.0"
+
+[[projects]]
+  name = "github.com/go-logfmt/logfmt"
+  packages = ["."]
+  revision = "390ab7935ee28ec6b286364bba9b4dd6410cb3d5"
+  version = "v0.3.0"
+
+[[projects]]
+  name = "github.com/go-stack/stack"
+  packages = ["."]
+  revision = "259ab82a6cad3992b4e21ff5cac294ccb06474bc"
+  version = "v1.7.0"
+
+[[projects]]
+  name = "github.com/gogo/protobuf"
+  packages = [
+    "gogoproto",
+    "jsonpb",
+    "proto",
+    "protoc-gen-gogo/descriptor",
+    "sortkeys",
+    "types"
+  ]
+  revision = "1adfc126b41513cc696b209667c8656ea7aac67c"
+  version = "v1.0.0"
+
+[[projects]]
+  name = "github.com/golang/protobuf"
+  packages = [
+    "proto",
+    "ptypes",
+    "ptypes/any",
+    "ptypes/duration",
+    "ptypes/timestamp"
+  ]
+  revision = "925541529c1fa6821df4e44ce2723319eb2be768"
+  version = "v1.0.0"
+
+[[projects]]
+  branch = "master"
+  name = "github.com/golang/snappy"
+  packages = ["."]
+  revision = "553a641470496b2327abcac10b36396bd98e45c9"
+
+[[projects]]
+  name = "github.com/gorilla/websocket"
+  packages = ["."]
+  revision = "ea4d1f681babbce9545c9c5f3d5194a789c89f5b"
+  version = "v1.2.0"
+
+[[projects]]
+  branch = "master"
+  name = "github.com/hashicorp/hcl"
+  packages = [
+    ".",
+    "hcl/ast",
+    "hcl/parser",
+    "hcl/printer",
+    "hcl/scanner",
+    "hcl/strconv",
+    "hcl/token",
+    "json/parser",
+    "json/scanner",
+    "json/token"
+  ]
+  revision = "ef8a98b0bbce4a65b5aa4c368430a80ddc533168"
+
+[[projects]]
+  name = "github.com/inconshreveable/mousetrap"
+  packages = ["."]
+  revision = "76626ae9c91c4f2a10f34cad8ce83ea42c93bb75"
+  version = "v1.0"
+
+[[projects]]
+  branch = "master"
+  name = "github.com/jmhodges/levigo"
+  packages = ["."]
+  revision = "c42d9e0ca023e2198120196f842701bb4c55d7b9"
+
+[[projects]]
+  branch = "master"
+  name = "github.com/kr/logfmt"
+  packages = ["."]
+  revision = "b84e30acd515aadc4b783ad4ff83aff3299bdfe0"
+
+[[projects]]
+  name = "github.com/magiconair/properties"
+  packages = ["."]
+  revision = "c3beff4c2358b44d0493c7dda585e7db7ff28ae6"
+  version = "v1.7.6"
+
+[[projects]]
+  branch = "master"
+  name = "github.com/mitchellh/mapstructure"
+  packages = ["."]
+  revision = "00c29f56e2386353d58c599509e8dc3801b0d716"
+
+[[projects]]
+  name = "github.com/pelletier/go-toml"
+  packages = ["."]
+  revision = "acdc4509485b587f5e675510c4f2c63e90ff68a8"
+  version = "v1.1.0"
+
+[[projects]]
+  name = "github.com/pkg/errors"
+  packages = ["."]
+  revision = "645ef00459ed84a119197bfb8d8205042c6df63d"
+  version = "v0.8.0"
+
+[[projects]]
+  name = "github.com/pmezard/go-difflib"
+  packages = ["difflib"]
+  revision = "792786c7400a136282c1664665ae0a8db921c6c2"
+  version = "v1.0.0"
+
+[[projects]]
+  branch = "master"
+  name = "github.com/rcrowley/go-metrics"
+  packages = ["."]
+  revision = "d932a24a8ccb8fcadc993e5c6c58f93dac168294"
+
+[[projects]]
+  name = "github.com/spf13/afero"
+  packages = [
+    ".",
+    "mem"
+  ]
+  revision = "63644898a8da0bc22138abf860edaf5277b6102e"
+  version = "v1.1.0"
+
+[[projects]]
+  name = "github.com/spf13/cast"
+  packages = ["."]
+  revision = "8965335b8c7107321228e3e3702cab9832751bac"
+  version = "v1.2.0"
+
+[[projects]]
+  name = "github.com/spf13/cobra"
+  packages = ["."]
+  revision = "a1f051bc3eba734da4772d60e2d677f47cf93ef4"
+  version = "v0.0.2"
+
+[[projects]]
+  branch = "master"
+  name = "github.com/spf13/jwalterweatherman"
+  packages = ["."]
+  revision = "7c0cea34c8ece3fbeb2b27ab9b59511d360fb394"
+
+[[projects]]
+  name = "github.com/spf13/pflag"
+  packages = ["."]
+  revision = "583c0c0531f06d5278b7d917446061adc344b5cd"
+  version = "v1.0.1"
+
+[[projects]]
+  name = "github.com/spf13/viper"
+  packages = ["."]
+  revision = "b5e8006cbee93ec955a89ab31e0e3ce3204f3736"
+  version = "v1.0.2"
+
+[[projects]]
+  name = "github.com/stretchr/testify"
+  packages = [
+    "assert",
+    "require"
+  ]
+  revision = "12b6f73e6084dad08a7c6e575284b177ecafbc71"
+  version = "v1.2.1"
+
+[[projects]]
+  branch = "master"
+  name = "github.com/syndtr/goleveldb"
+  packages = [
+    "leveldb",
+    "leveldb/cache",
+    "leveldb/comparer",
+    "leveldb/errors",
+    "leveldb/filter",
+    "leveldb/iterator",
+    "leveldb/journal",
+    "leveldb/memdb",
+    "leveldb/opt",
+    "leveldb/storage",
+    "leveldb/table",
+    "leveldb/util"
+  ]
+  revision = "714f901b98fdb3aa954b4193d8cbd64a28d80cad"
+
+[[projects]]
+  name = "github.com/tendermint/abci"
+  packages = [
+    "client",
+    "example/code",
+    "example/counter",
+    "example/kvstore",
+    "server",
+    "types"
+  ]
+  revision = "78a8905690ef54f9d57e3b2b0ee7ad3a04ef3f1f"
+  version = "v0.10.3"
+
+[[projects]]
+  branch = "master"
+  name = "github.com/tendermint/ed25519"
+  packages = [
+    ".",
+    "edwards25519",
+    "extra25519"
+  ]
+  revision = "d8387025d2b9d158cf4efb07e7ebf814bcce2057"
+
+[[projects]]
+  name = "github.com/tendermint/go-amino"
+  packages = ["."]
+  revision = "42246108ff925a457fb709475070a03dfd3e2b5c"
+  version = "0.9.6"
+
+[[projects]]
+  name = "github.com/tendermint/go-crypto"
+  packages = ["."]
+  revision = "915416979bf70efa4bcbf1c6cd5d64c5fff9fc19"
+  version = "v0.6.2"
+
+[[projects]]
+  name = "github.com/tendermint/go-wire"
+  packages = ["."]
+  revision = "fa721242b042ecd4c6ed1a934ee740db4f74e45c"
+  version = "v0.7.3"
+
+[[projects]]
+  name = "github.com/tendermint/tmlibs"
+  packages = [
+    "autofile",
+    "cli",
+    "cli/flags",
+    "clist",
+    "common",
+    "db",
+    "flowrate",
+    "log",
+    "merkle",
+    "pubsub",
+    "pubsub/query",
+    "test"
+  ]
+  revision = "97e1f1ad3f510048929a51475811a18686c894df"
+  version = "0.8.2-rc0"
+
+[[projects]]
+  branch = "master"
+  name = "golang.org/x/crypto"
+  packages = [
+    "curve25519",
+    "nacl/box",
+    "nacl/secretbox",
+    "openpgp/armor",
+    "openpgp/errors",
+    "poly1305",
+    "ripemd160",
+    "salsa20/salsa"
+  ]
+  revision = "d6449816ce06963d9d136eee5a56fca5b0616e7e"
+
+[[projects]]
+  branch = "master"
+  name = "golang.org/x/net"
+  packages = [
+    "context",
+    "http2",
+    "http2/hpack",
+    "idna",
+    "internal/timeseries",
+    "lex/httplex",
+    "trace"
+  ]
+  revision = "61147c48b25b599e5b561d2e9c4f3e1ef489ca41"
+
+[[projects]]
+  branch = "master"
+  name = "golang.org/x/sys"
+  packages = ["unix"]
+  revision = "3b87a42e500a6dc65dae1a55d0b641295971163e"
+
+[[projects]]
+  name = "golang.org/x/text"
+  packages = [
+    "collate",
+    "collate/build",
+    "internal/colltab",
+    "internal/gen",
+    "internal/tag",
+    "internal/triegen",
+    "internal/ucd",
+    "language",
+    "secure/bidirule",
+    "transform",
+    "unicode/bidi",
+    "unicode/cldr",
+    "unicode/norm",
+    "unicode/rangetable"
+  ]
+  revision = "f21a4dfb5e38f5895301dc265a8def02365cc3d0"
+  version = "v0.3.0"
+
+[[projects]]
+  branch = "master"
+  name = "google.golang.org/genproto"
+  packages = ["googleapis/rpc/status"]
+  revision = "51d0944304c3cbce4afe9e5247e21100037bff78"
+
+[[projects]]
+  name = "google.golang.org/grpc"
+  packages = [
+    ".",
+    "balancer",
+    "codes",
+    "connectivity",
+    "credentials",
+    "grpclb/grpc_lb_v1/messages",
+    "grpclog",
+    "internal",
+    "keepalive",
+    "metadata",
+    "naming",
+    "peer",
+    "resolver",
+    "stats",
+    "status",
+    "tap",
+    "transport"
+  ]
+  revision = "5b3c4e850e90a4cf6a20ebd46c8b32a0a3afcb9e"
+  version = "v1.7.5"
+
+[[projects]]
+  name = "gopkg.in/yaml.v2"
+  packages = ["."]
+  revision = "5420a8b6744d3b0345ab293f6fcba19c978f1183"
+  version = "v2.2.1"
+
+[solve-meta]
+  analyzer-name = "dep"
+  analyzer-version = 1
+  inputs-digest = "e70f8692c825e80ae8510546e297840b9560d00e11b2272749a55cc2ffd147f0"
+  solver-name = "gps-cdcl"
+  solver-version = 1

Gopkg.toml

@@ -0,0 +1,94 @@
+# Gopkg.toml example
+#
+# Refer to https://github.com/golang/dep/blob/master/docs/Gopkg.toml.md
+# for detailed Gopkg.toml documentation.
+#
+# required = ["github.com/user/thing/cmd/thing"]
+# ignored = ["github.com/user/project/pkgX", "bitbucket.org/user/project/pkgA/pkgY"]
+#
+# [[constraint]]
+#   name = "github.com/user/project"
+#   version = "1.0.0"
+#
+# [[constraint]]
+#   name = "github.com/user/project2"
+#   branch = "dev"
+#   source = "github.com/myfork/project2"
+#
+# [[override]]
+#   name = "github.com/x/y"
+#   version = "2.4.0"
+#
+# [prune]
+#   non-go = false
+#   go-tests = true
+#   unused-packages = true
+
+
+[[constraint]]
+  name = "github.com/ebuchman/fail-test"
+  branch = "master"
+
+[[constraint]]
+  name = "github.com/fortytw2/leaktest"
+  branch = "master"
+
+[[constraint]]
+  name = "github.com/go-kit/kit"
+  version = "~0.6.0"
+
+[[constraint]]
+  name = "github.com/gogo/protobuf"
+  version = "~1.0.0"
+
+[[constraint]]
+  name = "github.com/golang/protobuf"
+  version = "~1.0.0"
+
+[[constraint]]
+  name = "github.com/gorilla/websocket"
+  version = "~1.2.0"
+
+[[constraint]]
+  name = "github.com/pkg/errors"
+  version = "~0.8.0"
+
+[[constraint]]
+  name = "github.com/rcrowley/go-metrics"
+  branch = "master"
+
+[[constraint]]
+  name = "github.com/spf13/cobra"
+  version = "~0.0.1"
+
+[[constraint]]
+  name = "github.com/spf13/viper"
+  version = "~1.0.0"
+
+[[constraint]]
+  name = "github.com/stretchr/testify"
+  version = "~1.2.1"
+
+[[constraint]]
+  name = "github.com/tendermint/abci"
+  version = "~0.10.3"
+
+[[constraint]]
+  name = "github.com/tendermint/go-crypto"
+  version = "~0.6.2"
+
+[[constraint]]
+  name = "github.com/tendermint/go-amino"
+  version = "~0.9.6"
+
+[[constraint]]
+  name = "github.com/tendermint/tmlibs"
+  version = "~0.8.2-rc0"
+
+[[constraint]]
+  name = "google.golang.org/grpc"
+  version = "~1.7.3"
+
+[prune]
+  go-tests = true
+  unused-packages = true

INSTALL.md

@@ -1,57 +0,0 @@
-# Install Go
-
-[Install Go, set the `GOPATH`, and put `GOPATH/bin` on your `PATH`](https://github.com/tendermint/tendermint/wiki/Setting-GOPATH).
-
-# Install Tendermint
-
-You should be able to install the latest with a simple `go get -u github.com/tendermint/tendermint/cmd/tendermint`.
-The `-u` makes sure all dependencies are updated as well. 
-
-Run `tendermint version` and `tendermint --help`.
-
-If the install falied, see [vendored dependencies below](#vendored-dependencies).
-
-To start a one-node blockchain with a simple in-process application: 
-
-```
-tendermint init
-tendermint node --proxy_app=dummy
-```
-
-See the [application developers guide](https://github.com/tendermint/tendermint/wiki/Application-Developers) for more details on building and running applications.
-
-
-## Vendored dependencies
-
-If the `go get` failed, updated dependencies may have broken the build.
-Install the correct version of each dependency using `glide`.
-
-Fist, install `glide`:
-
-```
-go get github.com/Masterminds/glide
-```
-
-Now, fetch the dependencies and install them with `glide` and `go`:
-
-```
-cd $GOPATH/src/github.com/tendermint/tendermint
-glide install
-go install ./cmd/tendermint
-```
-
-Sometimes `glide install` is painfully slow. Hang in there champ.
-
-The latest Tendermint Core version is now installed. Check by running `tendermint version`.
-
-## Troubleshooting
-
-If `go get` failing bothers you, fetch the code using `git`:
-
-```
-mkdir -p $GOPATH/src/github.com/tendermint
-git clone https://github.com/tendermint/tendermint $GOPATH/src/github.com/tendermint/tendermint
-cd $GOPATH/src/github.com/tendermint/tendermint
-glide install
-go install ./cmd/tendermint
-```

Makefile

@@ -1,25 +1,135 @@
 GOTOOLS = \
-					github.com/mitchellh/gox \
-					github.com/Masterminds/glide
+	github.com/golang/dep/cmd/dep \
+	gopkg.in/alecthomas/gometalinter.v2
 PACKAGES=$(shell go list ./... | grep -v '/vendor/')
 BUILD_TAGS?=tendermint
-TMHOME = $${TMHOME:-$$HOME/.tendermint}
+BUILD_FLAGS = -ldflags "-X github.com/tendermint/tendermint/version.GitCommit=`git rev-parse --short=8 HEAD`"
 
-all: install test
+all: check build test install
 
-install: get_vendor_deps
-	@go install ./cmd/tendermint
+check: check_tools ensure_deps
+
+
+########################################
+### Build
 
 build:
-	go build -o build/tendermint ./cmd/tendermint
+	CGO_ENABLED=0 go build $(BUILD_FLAGS) -tags '$(BUILD_TAGS)' -o build/tendermint ./cmd/tendermint/
 
 build_race:
-	go build -race -o build/tendermint ./cmd/tendermint
+	CGO_ENABLED=0 go build -race $(BUILD_FLAGS) -tags '$(BUILD_TAGS)' -o build/tendermint ./cmd/tendermint
+
+install:
+	CGO_ENABLED=0 go install $(BUILD_FLAGS) -tags '$(BUILD_TAGS)' ./cmd/tendermint
+
+########################################
+### Distribution
 
 # dist builds binaries for all platforms and packages them for distribution
 dist:
 	@BUILD_TAGS='$(BUILD_TAGS)' sh -c "'$(CURDIR)/scripts/dist.sh'"
 
+########################################
+### Tools & dependencies
+
+check_tools:
+	@# https://stackoverflow.com/a/25668869
+	@echo "Found tools: $(foreach tool,$(notdir $(GOTOOLS)),\
+        $(if $(shell which $(tool)),$(tool),$(error "No $(tool) in PATH")))"
+
+get_tools:
+	@echo "--> Installing tools"
+	go get -u -v $(GOTOOLS)
+	@gometalinter.v2 --install
+
+update_tools:
+	@echo "--> Updating tools"
+	@go get -u $(GOTOOLS)
+
+#Run this from CI
+get_vendor_deps:
+	@rm -rf vendor/
+	@echo "--> Running dep"
+	@dep ensure -vendor-only
+
+
+#Run this locally.
+ensure_deps:
+	@rm -rf vendor/
+	@echo "--> Running dep"
+	@dep ensure
+
+draw_deps:
+	@# requires brew install graphviz or apt-get install graphviz
+	go get github.com/RobotsAndPencils/goviz
+	@goviz -i github.com/tendermint/tendermint/cmd/tendermint -d 3 | dot -Tpng -o dependency-graph.png
+
+get_deps_bin_size:
+	@# Copy of build recipe with additional flags to perform binary size analysis
+	$(eval $(shell go build -work -a $(BUILD_FLAGS) -tags '$(BUILD_TAGS)' -o build/tendermint ./cmd/tendermint/ 2>&1))
+	@find $(WORK) -type f -name "*.a" | xargs -I{} du -hxs "{}" | sort -rh | sed -e s:${WORK}/::g > deps_bin_size.log
+	@echo "Results can be found here: $(CURDIR)/deps_bin_size.log"
+
+########################################
+### Testing
+
+## required to be run first by most tests
+build_docker_test_image:
+	docker build -t tester -f ./test/docker/Dockerfile .
+
+### coverage, app, persistence, and libs tests
+test_cover:
+	# run the go unit tests with coverage
+	bash test/test_cover.sh
+
+test_apps:
+	# run the app tests using bash
+	# requires `abci-cli` and `tendermint` binaries installed
+	bash test/app/test.sh
+
+test_persistence:
+	# run the persistence tests using bash
+	# requires `abci-cli` installed
+	docker run --name run_persistence -t tester bash test/persist/test_failure_indices.sh
+
+	# TODO undockerize
+	# bash test/persist/test_failure_indices.sh
+
+test_p2p:
+	docker rm -f rsyslog || true
+	rm -rf test/logs || true
+	mkdir test/logs
+	cd test/
+	docker run -d -v "logs:/var/log/" -p 127.0.0.1:5514:514/udp --name rsyslog voxxit/rsyslog
+	cd ..
+	# requires 'tester' the image from above
+	bash test/p2p/test.sh tester
+
+need_abci:
+	bash scripts/install_abci_apps.sh
+
+test_integrations:
+	make build_docker_test_image
+	make get_tools
+	make get_vendor_deps
+	make install
+	make need_abci
+	make test_cover
+	make test_apps
+	make test_persistence
+	make test_p2p
+
+test_release:
+	@go test -tags release $(PACKAGES)
+
+test100:
+	@for i in {1..100}; do make test; done
+
+vagrant_test:
+	vagrant up
+	vagrant ssh -c 'make test_integrations'
+
+### go tests
 test:
 	@echo "--> Running go test"
 	@go test $(PACKAGES)
@@ -28,47 +138,65 @@ test_race:
 	@echo "--> Running go test --race"
 	@go test -v -race $(PACKAGES)
 
-test_integrations:
-	@bash ./test/test.sh
 
-test100:
-	@for i in {1..100}; do make test; done
+########################################
+### Formatting, linting, and vetting
 
-draw_deps:
-	# requires brew install graphviz or apt-get install graphviz
-	go get github.com/RobotsAndPencils/goviz
-	@goviz -i github.com/tendermint/tendermint/cmd/tendermint -d 3 | dot -Tpng -o dependency-graph.png
+fmt:
+	@go fmt ./...
 
-list_deps:
-	@go list -f '{{join .Deps "\n"}}' ./... | \
-		grep -v /vendor/ | sort | uniq | \
-		xargs go list -f '{{if not .Standard}}{{.ImportPath}}{{end}}'
+metalinter:
+	@echo "--> Running linter"
+	@gometalinter.v2 --vendor --deadline=600s --disable-all  \
+		--enable=deadcode \
+		--enable=gosimple \
+	 	--enable=misspell \
+		--enable=safesql \
+		./...
+		#--enable=gas \
+		#--enable=maligned \
+		#--enable=dupl \
+		#--enable=errcheck \
+		#--enable=goconst \
+		#--enable=gocyclo \
+		#--enable=goimports \
+		#--enable=golint \ <== comments on anything exported
+		#--enable=gotype \
+	 	#--enable=ineffassign \
+	   	#--enable=interfacer \
+	   	#--enable=megacheck \
+	   	#--enable=staticcheck \
+	   	#--enable=structcheck \
+	   	#--enable=unconvert \
+	   	#--enable=unparam \
+		#--enable=unused \
+	   	#--enable=varcheck \
+		#--enable=vet \
+		#--enable=vetshadow \
 
-get_deps:
-	@echo "--> Running go get"
-	@go get -v -d $(PACKAGES)
-	@go list -f '{{join .TestImports "\n"}}' ./... | \
-		grep -v /vendor/ | sort | uniq | \
-		xargs go get -v -d
+metalinter_all:
+	@echo "--> Running linter (all)"
+	gometalinter.v2 --vendor --deadline=600s --enable-all --disable=lll ./...
 
-get_vendor_deps: ensure_tools
-	@rm -rf vendor/
-	@echo "--> Running glide install"
-	@glide install
+###########################################################
+### Local testnet using docker
 
-update_deps: tools
-	@echo "--> Updating dependencies"
-	@go get -d -u ./...
+# Build linux binary on other platforms
+build-linux:
+	GOOS=linux GOARCH=amd64 $(MAKE) build
 
-revision:
-	-echo `git rev-parse --verify HEAD` > $(TMHOME)/revision
-	-echo `git rev-parse --verify HEAD` >> $(TMHOME)/revision_history
+# Run a 4-node testnet locally
+docker-start:
+	@echo "Wait until 'Attaching to node0, node1, node2, node3' message appears"
+	@if ! [ -f build/node0/config/genesis.json ]; then docker run --rm -v `pwd`/build:/tendermint:Z tendermint/localnode testnet --v 4 --o . --populate-persistent-peers --starting-ip-address 192.167.10.2 ; fi
+	docker-compose up
 
-tools:
-	go get -u -v $(GOTOOLS)
+# Stop testnet
+docker-stop:
+	docker-compose down
 
-ensure_tools:
-	go get $(GOTOOLS)
+# To avoid unintended conflicts with file names, always add to .PHONY
+# unless there is a reason not to.
+# https://www.gnu.org/software/make/manual/html_node/Phony-Targets.html
+.PHONY: check build build_race dist install check_tools get_tools update_tools get_vendor_deps draw_deps test_cover test_apps test_persistence test_p2p test test_race test_integrations test_release test100 vagrant_test fmt build-linux docker-start docker-stop
 
-
-.PHONY: install build build_race dist test test_race test_integrations test100 draw_deps list_deps get_deps get_vendor_deps update_deps revision tools

README.md

@@ -1,71 +1,112 @@
 # Tendermint
 
 [Byzantine-Fault Tolerant](https://en.wikipedia.org/wiki/Byzantine_fault_tolerance)
-[State Machine Replication](https://en.wikipedia.org/wiki/State_machine_replication). 
+[State Machine Replication](https://en.wikipedia.org/wiki/State_machine_replication).
 Or [Blockchain](https://en.wikipedia.org/wiki/Blockchain_(database)) for short.
 
 [![version](https://img.shields.io/github/tag/tendermint/tendermint.svg)](https://github.com/tendermint/tendermint/releases/latest)
 [![API Reference](
 https://camo.githubusercontent.com/915b7be44ada53c290eb157634330494ebe3e30a/68747470733a2f2f676f646f632e6f72672f6769746875622e636f6d2f676f6c616e672f6764646f3f7374617475732e737667
 )](https://godoc.org/github.com/tendermint/tendermint)
-[![chat](https://img.shields.io/badge/slack-join%20chat-pink.svg)](http://forum.tendermint.com:3000/)
+[![Go version](https://img.shields.io/badge/go-1.9.2-blue.svg)](https://github.com/moovweb/gvm)
+[![Rocket.Chat](https://demo.rocket.chat/images/join-chat.svg)](https://cosmos.rocket.chat/)
 [![license](https://img.shields.io/github/license/tendermint/tendermint.svg)](https://github.com/tendermint/tendermint/blob/master/LICENSE)
 [![](https://tokei.rs/b1/github/tendermint/tendermint?category=lines)](https://github.com/tendermint/tendermint)
 
 
-Branch    | Tests | Coverage | Report Card
-----------|-------|----------|-------------
-develop   | [![CircleCI](https://circleci.com/gh/tendermint/tendermint/tree/develop.svg?style=shield)](https://circleci.com/gh/tendermint/tendermint/tree/develop) | [![codecov](https://codecov.io/gh/tendermint/tendermint/branch/develop/graph/badge.svg)](https://codecov.io/gh/tendermint/tendermint) | [![Go Report Card](https://goreportcard.com/badge/github.com/tendermint/tendermint/tree/develop)](https://goreportcard.com/report/github.com/tendermint/tendermint/tree/develop)
-master    | [![CircleCI](https://circleci.com/gh/tendermint/tendermint/tree/master.svg?style=shield)](https://circleci.com/gh/tendermint/tendermint/tree/master) | [![codecov](https://codecov.io/gh/tendermint/tendermint/branch/master/graph/badge.svg)](https://codecov.io/gh/tendermint/tendermint) | [![Go Report Card](https://goreportcard.com/badge/github.com/tendermint/tendermint/tree/master)](https://goreportcard.com/report/github.com/tendermint/tendermint/tree/master)
+Branch    | Tests | Coverage
+----------|-------|----------
+master    | [![CircleCI](https://circleci.com/gh/tendermint/tendermint/tree/master.svg?style=shield)](https://circleci.com/gh/tendermint/tendermint/tree/master) | [![codecov](https://codecov.io/gh/tendermint/tendermint/branch/master/graph/badge.svg)](https://codecov.io/gh/tendermint/tendermint)
+develop   | [![CircleCI](https://circleci.com/gh/tendermint/tendermint/tree/develop.svg?style=shield)](https://circleci.com/gh/tendermint/tendermint/tree/develop) | [![codecov](https://codecov.io/gh/tendermint/tendermint/branch/develop/graph/badge.svg)](https://codecov.io/gh/tendermint/tendermint)
 
 _NOTE: This is alpha software. Please contact us if you intend to run it in production._
 
-Tendermint Core is Byzantine Fault Tolerant (BFT) middleware that takes a state transition machine, written in any programming language,
+Tendermint Core is Byzantine Fault Tolerant (BFT) middleware that takes a state transition machine - written in any programming language -
 and securely replicates it on many machines.
 
-For more background, see the [introduction](https://tendermint.com/intro).
+For more information, from introduction to install to application development, [Read The Docs](https://tendermint.readthedocs.io/en/master/).
 
-To get started developing applications, see the [application developers guide](https://tendermint.com/docs/guides/app-development).
+## Minimum requirements
+
+Requirement|Notes
+---|---
+Go version | Go1.9 or higher
 
 ## Install
 
-To download pre-built binaries, see our [downloads page](https://tendermint.com/intro/getting-started/download).
+To download pre-built binaries, see our [downloads page](https://tendermint.com/downloads).
 
 To install from source, you should be able to:
 
 `go get -u github.com/tendermint/tendermint/cmd/tendermint`
 
-For more details (or if it fails), see the [install guide](https://tendermint.com/docs/guides/install).
-
-## Contributing
-
-Yay open source! Please see our [contributing guidelines](https://tendermint.com/docs/guides/contributing).
+For more details (or if it fails), [read the docs](https://tendermint.readthedocs.io/en/master/install.html).
 
 ## Resources
 
 ### Tendermint Core
 
-- [Introduction](https://tendermint.com/intro)
-- [Docs](https://tendermint.com/docs)
-- [Software using Tendermint](https://tendermint.com/ecosystem)
+All resources involving the use of, building application on, or developing for, tendermint, can be found at [Read The Docs](https://tendermint.readthedocs.io/en/master/). Additional information about some - and eventually all - of the sub-projects below, can be found at Read The Docs.
 
 ### Sub-projects
 
-* [ABCI](http://github.com/tendermint/abci)
-* [Mintnet](http://github.com/tendermint/mintnet)
-* [Go-Wire](http://github.com/tendermint/go-wire)
-* [Go-P2P](http://github.com/tendermint/go-p2p)
-* [Go-Merkle](http://github.com/tendermint/go-merkle)
+* [ABCI](http://github.com/tendermint/abci), the Application Blockchain Interface
+* [Go-Wire](http://github.com/tendermint/go-wire), a deterministic serialization library
+* [Go-Crypto](http://github.com/tendermint/go-crypto), an elliptic curve cryptography library
+* [TmLibs](http://github.com/tendermint/tmlibs), an assortment of Go libraries used internally
+* [IAVL](http://github.com/tendermint/iavl), Merkleized IAVL+ Tree implementation
+
+### Tools
+* [Deployment, Benchmarking, and Monitoring](http://tendermint.readthedocs.io/projects/tools/en/develop/index.html#tendermint-tools)
 
 ### Applications
 
-* [Ethermint](http://github.com/tendermint/ethermint)
-* [Basecoin](http://github.com/tendermint/basecoin)
+* [Ethermint](http://github.com/tendermint/ethermint); Ethereum on Tendermint
+* [Cosmos SDK](http://github.com/cosmos/cosmos-sdk); a cryptocurrency application framework
+* [Many more](https://tendermint.readthedocs.io/en/master/ecosystem.html#abci-applications)
 
-### More 
+### More
 
-* [Tendermint Blog](https://tendermint.com/blog)
-* [Cosmos Blog](https://cosmos.network/blog)
-* [Original Whitepaper (out-of-date)](http://www.the-blockchain.com/docs/Tendermint%20Consensus%20without%20Mining.pdf)
 * [Master's Thesis on Tendermint](https://atrium.lib.uoguelph.ca/xmlui/handle/10214/9769)
+* [Original Whitepaper](https://tendermint.com/static/docs/tendermint.pdf)
+* [Tendermint Blog](https://blog.cosmos.network/tendermint/home)
+* [Cosmos Blog](https://blog.cosmos.network)
 
+## Contributing
+
+Yay open source! Please see our [contributing guidelines](CONTRIBUTING.md).
+
+## Versioning
+
+### SemVer
+
+Tendermint uses [SemVer](http://semver.org/) to determine when and how the version changes.
+According to SemVer, anything in the public API can change at any time before version 1.0.0
+
+To provide some stability to Tendermint users in these 0.X.X days, the MINOR version is used
+to signal breaking changes across a subset of the total public API. This subset includes all
+interfaces exposed to other processes (cli, rpc, p2p, etc.), as well as parts of the following packages:
+
+- types
+- rpc/client
+- config
+- node
+
+Exported objects in these packages that are not covered by the versioning scheme
+are explicitly marked by `// UNSTABLE` in their go doc comment and may change at any time.
+Functions, types, and values in any other package may also change at any time.
+
+### Upgrades
+
+In an effort to avoid accumulating technical debt prior to 1.0.0,
+we do not guarantee that breaking changes (ie. bumps in the MINOR version)
+will work with existing tendermint blockchains. In these cases you will
+have to start a new blockchain, or write something custom to get the old
+data into the new chain.
+
+However, any bump in the PATCH version should be compatible with existing histories
+(if not please open an [issue](https://github.com/tendermint/tendermint/issues)).
+
+## Code of Conduct
+
+Please read, understand and adhere to our [code of conduct](CODE_OF_CONDUCT.md).

Vagrantfile

@@ -2,37 +2,51 @@
 # vi: set ft=ruby :
 
 Vagrant.configure("2") do |config|
-  config.vm.box = "ubuntu/trusty64"
+  config.vm.box = "ubuntu/xenial64"
 
   config.vm.provider "virtualbox" do |v|
-    v.memory = 3072
+    v.memory = 4096
     v.cpus = 2
   end
 
   config.vm.provision "shell", inline: <<-SHELL
-    apt-get update
-    apt-get install -y --no-install-recommends wget curl jq shellcheck bsdmainutils psmisc
+    # add docker repo
+    curl -fsSL https://download.docker.com/linux/ubuntu/gpg | apt-key add -
+    add-apt-repository "deb [arch=amd64] https://download.docker.com/linux/ubuntu xenial stable"
 
-    wget -qO- https://get.docker.com/ | sh
-    usermod -a -G docker vagrant
+    # and golang 1.9 support
+    # official repo doesn't have race detection runtime...
+    # add-apt-repository ppa:gophers/archive
+    add-apt-repository ppa:longsleep/golang-backports
+
+    # install base requirements
+    apt-get update
+    apt-get install -y --no-install-recommends wget curl jq zip \
+        make shellcheck bsdmainutils psmisc
+    apt-get install -y docker-ce golang-1.9-go
+    apt-get install -y language-pack-en
+
+    # cleanup
     apt-get autoremove -y
 
-    curl -O https://storage.googleapis.com/golang/go1.8.linux-amd64.tar.gz
-    tar -xvf go1.8.linux-amd64.tar.gz
-    rm -rf /usr/local/go
-    mv go /usr/local
-    rm -f go1.8.linux-amd64.tar.gz
-    mkdir -p /home/vagrant/go/bin
-    echo 'export PATH=$PATH:/usr/local/go/bin:/home/vagrant/go/bin' >> /home/vagrant/.bash_profile
+    # needed for docker
+    usermod -a -G docker vagrant
+
+    # set env variables
+    echo 'export PATH=$PATH:/usr/lib/go-1.9/bin:/home/vagrant/go/bin' >> /home/vagrant/.bash_profile
     echo 'export GOPATH=/home/vagrant/go' >> /home/vagrant/.bash_profile
-
     echo 'export LC_ALL=en_US.UTF-8' >> /home/vagrant/.bash_profile
+    echo 'cd go/src/github.com/tendermint/tendermint' >> /home/vagrant/.bash_profile
 
+    mkdir -p /home/vagrant/go/bin
     mkdir -p /home/vagrant/go/src/github.com/tendermint
     ln -s /vagrant /home/vagrant/go/src/github.com/tendermint/tendermint
 
     chown -R vagrant:vagrant /home/vagrant/go
+    chown vagrant:vagrant /home/vagrant/.bash_profile
 
-    su - vagrant -c 'cd /home/vagrant/go/src/github.com/tendermint/tendermint && make get_vendor_deps'
+    # get all deps and tools, ready to install/test
+    su - vagrant  -c 'source /home/vagrant/.bash_profile'
+    su - vagrant -c 'cd /home/vagrant/go/src/github.com/tendermint/tendermint && make get_tools && make get_vendor_deps'
   SHELL
 end

appveyor.yml

@@ -0,0 +1,13 @@
+version: 1.0.{build}
+configuration: Release
+platform:
+- x64
+- x86
+clone_folder: c:\go\path\src\github.com\tendermint\tendermint
+before_build:
+- cmd: set GOPATH=%GOROOT%\path
+- cmd: set PATH=%GOPATH%\bin;%PATH%
+- cmd: make get_vendor_deps
+build_script:
+- cmd: make test
+test: off

benchmarks/blockchain/.gitignore

@@ -0,0 +1,2 @@
+data
+

benchmarks/blockchain/localsync.sh

@@ -0,0 +1,80 @@
+#!/bin/bash
+
+DATA=$GOPATH/src/github.com/tendermint/tendermint/benchmarks/blockchain/data
+if [ ! -d $DATA ]; then
+  echo "no data found, generating a chain... (this only has to happen once)"
+
+  tendermint init --home $DATA
+  cp $DATA/config.toml $DATA/config2.toml
+  echo "
+  [consensus]
+  timeout_commit = 0
+  " >> $DATA/config.toml
+
+  echo "starting node"
+  tendermint node \
+    --home $DATA \
+    --proxy_app kvstore \
+    --p2p.laddr tcp://127.0.0.1:56656 \
+    --rpc.laddr tcp://127.0.0.1:56657 \
+    --log_level error &
+
+  echo "making blocks for 60s"
+  sleep 60
+
+  mv $DATA/config2.toml $DATA/config.toml
+
+  kill %1
+
+  echo "done generating chain."
+fi
+
+# validator node
+HOME1=$TMPDIR$RANDOM$RANDOM
+cp -R $DATA $HOME1
+echo "starting validator node"
+tendermint node \
+  --home $HOME1 \
+  --proxy_app kvstore \
+  --p2p.laddr tcp://127.0.0.1:56656 \
+  --rpc.laddr tcp://127.0.0.1:56657 \
+  --log_level error &
+sleep 1
+
+# downloader node
+HOME2=$TMPDIR$RANDOM$RANDOM
+tendermint init --home $HOME2
+cp $HOME1/genesis.json $HOME2
+printf "starting downloader node"
+tendermint node \
+  --home $HOME2 \
+  --proxy_app kvstore \
+  --p2p.laddr tcp://127.0.0.1:56666 \
+  --rpc.laddr tcp://127.0.0.1:56667 \
+  --p2p.persistent_peers 127.0.0.1:56656 \
+  --log_level error &
+
+# wait for node to start up so we only count time where we are actually syncing
+sleep 0.5
+while curl localhost:56667/status 2> /dev/null | grep "\"latest_block_height\": 0," > /dev/null
+do
+  printf '.'
+  sleep 0.2
+done
+echo
+
+echo "syncing blockchain for 10s"
+for i in {1..10}
+do
+  sleep 1
+  HEIGHT="$(curl localhost:56667/status 2> /dev/null \
+    | grep 'latest_block_height' \
+    | grep -o ' [0-9]*' \
+    | xargs)"
+  let 'RATE = HEIGHT / i'
+  echo "height: $HEIGHT, blocks/sec: $RATE"
+done
+
+kill %1
+kill %2
+rm -rf $HOME1 $HOME2

benchmarks/codec_test.go

@@ -2,37 +2,47 @@ package benchmarks
 
 import (
 	"testing"
+	"time"
 
+	amino "github.com/tendermint/go-amino"
 	"github.com/tendermint/go-crypto"
-	"github.com/tendermint/go-p2p"
-	"github.com/tendermint/go-wire"
+
 	proto "github.com/tendermint/tendermint/benchmarks/proto"
+	"github.com/tendermint/tendermint/p2p"
 	ctypes "github.com/tendermint/tendermint/rpc/core/types"
 )
 
 func BenchmarkEncodeStatusWire(b *testing.B) {
 	b.StopTimer()
-	pubKey := crypto.GenPrivKeyEd25519().PubKey().(crypto.PubKeyEd25519)
+	cdc := amino.NewCodec()
+	ctypes.RegisterAmino(cdc)
+	nodeKey := p2p.NodeKey{PrivKey: crypto.GenPrivKeyEd25519()}
 	status := &ctypes.ResultStatus{
-		NodeInfo: &p2p.NodeInfo{
-			PubKey:     pubKey,
+		NodeInfo: p2p.NodeInfo{
+			ID:         nodeKey.ID(),
 			Moniker:    "SOMENAME",
 			Network:    "SOMENAME",
-			RemoteAddr: "SOMEADDR",
 			ListenAddr: "SOMEADDR",
 			Version:    "SOMEVER",
 			Other:      []string{"SOMESTRING", "OTHERSTRING"},
 		},
-		PubKey:            pubKey,
-		LatestBlockHash:   []byte("SOMEBYTES"),
-		LatestBlockHeight: 123,
-		LatestBlockTime:   1234,
+		SyncInfo: ctypes.SyncInfo{
+			LatestBlockHash:   []byte("SOMEBYTES"),
+			LatestBlockHeight: 123,
+			LatestBlockTime:   time.Unix(0, 1234),
+		},
+		ValidatorInfo: ctypes.ValidatorInfo{
+			PubKey: nodeKey.PubKey(),
+		},
 	}
 	b.StartTimer()
 
 	counter := 0
 	for i := 0; i < b.N; i++ {
-		jsonBytes := wire.JSONBytes(status)
+		jsonBytes, err := cdc.MarshalJSON(status)
+		if err != nil {
+			panic(err)
+		}
 		counter += len(jsonBytes)
 	}
 
@@ -40,12 +50,13 @@ func BenchmarkEncodeStatusWire(b *testing.B) {
 
 func BenchmarkEncodeNodeInfoWire(b *testing.B) {
 	b.StopTimer()
-	pubKey := crypto.GenPrivKeyEd25519().PubKey().(crypto.PubKeyEd25519)
-	nodeInfo := &p2p.NodeInfo{
-		PubKey:     pubKey,
+	cdc := amino.NewCodec()
+	ctypes.RegisterAmino(cdc)
+	nodeKey := p2p.NodeKey{PrivKey: crypto.GenPrivKeyEd25519()}
+	nodeInfo := p2p.NodeInfo{
+		ID:         nodeKey.ID(),
 		Moniker:    "SOMENAME",
 		Network:    "SOMENAME",
-		RemoteAddr: "SOMEADDR",
 		ListenAddr: "SOMEADDR",
 		Version:    "SOMEVER",
 		Other:      []string{"SOMESTRING", "OTHERSTRING"},
@@ -54,19 +65,23 @@ func BenchmarkEncodeNodeInfoWire(b *testing.B) {
 
 	counter := 0
 	for i := 0; i < b.N; i++ {
-		jsonBytes := wire.JSONBytes(nodeInfo)
+		jsonBytes, err := cdc.MarshalJSON(nodeInfo)
+		if err != nil {
+			panic(err)
+		}
 		counter += len(jsonBytes)
 	}
 }
 
 func BenchmarkEncodeNodeInfoBinary(b *testing.B) {
 	b.StopTimer()
-	pubKey := crypto.GenPrivKeyEd25519().PubKey().(crypto.PubKeyEd25519)
-	nodeInfo := &p2p.NodeInfo{
-		PubKey:     pubKey,
+	cdc := amino.NewCodec()
+	ctypes.RegisterAmino(cdc)
+	nodeKey := p2p.NodeKey{PrivKey: crypto.GenPrivKeyEd25519()}
+	nodeInfo := p2p.NodeInfo{
+		ID:         nodeKey.ID(),
 		Moniker:    "SOMENAME",
 		Network:    "SOMENAME",
-		RemoteAddr: "SOMEADDR",
 		ListenAddr: "SOMEADDR",
 		Version:    "SOMEVER",
 		Other:      []string{"SOMESTRING", "OTHERSTRING"},
@@ -75,7 +90,7 @@ func BenchmarkEncodeNodeInfoBinary(b *testing.B) {
 
 	counter := 0
 	for i := 0; i < b.N; i++ {
-		jsonBytes := wire.BinaryBytes(nodeInfo)
+		jsonBytes := cdc.MustMarshalBinaryBare(nodeInfo)
 		counter += len(jsonBytes)
 	}
 
@@ -83,16 +98,20 @@ func BenchmarkEncodeNodeInfoBinary(b *testing.B) {
 
 func BenchmarkEncodeNodeInfoProto(b *testing.B) {
 	b.StopTimer()
-	pubKey := crypto.GenPrivKeyEd25519().PubKey().(crypto.PubKeyEd25519)
-	pubKey2 := &proto.PubKey{Ed25519: &proto.PubKeyEd25519{Bytes: pubKey[:]}}
-	nodeInfo := &proto.NodeInfo{
-		PubKey:     pubKey2,
-		Moniker:    "SOMENAME",
-		Network:    "SOMENAME",
-		RemoteAddr: "SOMEADDR",
-		ListenAddr: "SOMEADDR",
-		Version:    "SOMEVER",
-		Other:      []string{"SOMESTRING", "OTHERSTRING"},
+	nodeKey := p2p.NodeKey{PrivKey: crypto.GenPrivKeyEd25519()}
+	nodeID := string(nodeKey.ID())
+	someName := "SOMENAME"
+	someAddr := "SOMEADDR"
+	someVer := "SOMEVER"
+	someString := "SOMESTRING"
+	otherString := "OTHERSTRING"
+	nodeInfo := proto.NodeInfo{
+		Id:         &proto.ID{Id: &nodeID},
+		Moniker:    &someName,
+		Network:    &someName,
+		ListenAddr: &someAddr,
+		Version:    &someVer,
+		Other:      []string{someString, otherString},
 	}
 	b.StartTimer()
 

benchmarks/experiments/Makefile

@@ -0,0 +1,26 @@
+DIST_DIRS := find * -type d -exec
+VERSION := $(shell perl -ne '/^var version.*"([^"]+)".*$$/ && print "v$$1\n"' main.go)
+GOTOOLS = \
+					github.com/mitchellh/gox
+
+tools:
+	go get $(GOTOOLS)
+
+get_vendor_deps:
+	@hash glide 2>/dev/null || go get github.com/Masterminds/glide
+	glide install
+
+build:
+	go build
+
+install:
+	go install
+
+test:
+	go test -race
+
+clean:
+	rm -f ./experiments
+	rm -rf ./dist
+
+.PHONY: tools get_vendor_deps build install test clean

benchmarks/experiments/glide.yaml

@@ -0,0 +1,12 @@
+package: github.com/tendermint/tendermint/benchmarks/experiments
+import:
+- package: github.com/tendermint/tendermint
+  version: v0.16.0
+  subpackages:
+  - rpc/client
+  - rpc/lib/types
+  - types
+- package: github.com/tendermint/tmlibs
+  version: v0.7.0
+  subpackages:
+  - log

benchmarks/experiments/main.go

@@ -0,0 +1,126 @@
+package main
+
+import (
+	"encoding/binary"
+	"fmt"
+	"math/rand"
+	"os"
+	"sync"
+	"time"
+
+	"context"
+
+	"github.com/tendermint/tendermint/rpc/client"
+	"github.com/tendermint/tendermint/types"
+	"github.com/tendermint/tmlibs/log"
+)
+
+var logger = log.NewNopLogger()
+var finishedTasks = 0
+var mutex = &sync.Mutex{}
+
+func main() {
+
+	var endpoint = "tcp://0.0.0.0:46657"
+
+	var httpClient = getHTTPClient(endpoint)
+
+	var res, err = httpClient.Status()
+	if err != nil {
+		logger.Info("something wrong happens", err)
+	}
+	logger.Info("received status", res)
+
+	go monitorTask(endpoint)
+
+	txCount := 10
+	var clientNumber = 10
+	for i := 0; i < clientNumber; i++ {
+		go clientTask(i, txCount, endpoint)
+	}
+	for finishedTasks < clientNumber+1 {
+	}
+	fmt.Printf("Done: %d\n", finishedTasks)
+}
+
+func clientTask(id, txCount int, endpoint string) {
+	var httpClient = getHTTPClient(endpoint)
+	for i := 0; i < txCount; i++ {
+		var _, err = httpClient.BroadcastTxSync(generateTx(id, rand.Int()))
+		if err != nil {
+			fmt.Printf("Something wrong happened: %s\n", err)
+		}
+	}
+	fmt.Printf("Finished client task: %d\n", id)
+
+	mutex.Lock()
+	finishedTasks++
+	mutex.Unlock()
+}
+
+func getHTTPClient(rpcAddr string) *client.HTTP {
+	return client.NewHTTP(rpcAddr, "/websocket")
+}
+
+func generateTx(i, valI int) []byte {
+	// a tx encodes the validator index, the tx number, and some random junk
+	tx := make([]byte, 250)
+	binary.PutUvarint(tx[:32], uint64(valI))
+	binary.PutUvarint(tx[32:64], uint64(i))
+	if _, err := rand.Read(tx[65:]); err != nil {
+		fmt.Println("err reading from crypto/rand", err)
+		os.Exit(1)
+	}
+	return tx
+}
+
+func monitorTask(endpoint string) {
+	fmt.Println("Monitor task started...")
+	var duration = 5 * time.Second
+
+	const subscriber = "monitor"
+	ctx, cancel := context.WithTimeout(context.Background(), duration)
+	defer cancel()
+	evts := make(chan interface{})
+
+	var httpClient = getHTTPClient(endpoint)
+	httpClient.Start()
+
+	evtTyp := types.EventNewBlockHeader
+
+	// register for the next event of this type
+	query := types.QueryForEvent(evtTyp)
+	err := httpClient.Subscribe(ctx, subscriber, query, evts)
+	if err != nil {
+		fmt.Println("error when subscribing", err)
+	}
+
+	// make sure to unregister after the test is over
+	defer httpClient.UnsubscribeAll(ctx, subscriber)
+
+	totalNumOfCommittedTxs := int64(0)
+
+	for {
+		fmt.Println("Starting main loop", err)
+		select {
+		case evt := <-evts:
+			event := evt.(types.TMEventData)
+			header, ok := event.Unwrap().(types.EventDataNewBlockHeader)
+			if ok {
+				fmt.Println("received header\n", header.Header.StringIndented(""))
+			} else {
+				fmt.Println("not able to unwrap header")
+			}
+			// Do some metric computation with header
+			totalNumOfCommittedTxs += header.Header.NumTxs
+
+		case <-ctx.Done():
+			fmt.Printf("Finished monitor task. Received %d transactions \n", totalNumOfCommittedTxs)
+
+			mutex.Lock()
+			finishedTasks++
+			mutex.Unlock()
+			return
+		}
+	}
+}

benchmarks/map_test.go

@@ -1,8 +1,9 @@
 package benchmarks
 
 import (
-	. "github.com/tendermint/go-common"
 	"testing"
+
+	cmn "github.com/tendermint/tmlibs/common"
 )
 
 func BenchmarkSomething(b *testing.B) {
@@ -11,11 +12,11 @@ func BenchmarkSomething(b *testing.B) {
 	numChecks := 100000
 	keys := make([]string, numItems)
 	for i := 0; i < numItems; i++ {
-		keys[i] = RandStr(100)
+		keys[i] = cmn.RandStr(100)
 	}
 	txs := make([]string, numChecks)
 	for i := 0; i < numChecks; i++ {
-		txs[i] = RandStr(100)
+		txs[i] = cmn.RandStr(100)
 	}
 	b.StartTimer()
 

benchmarks/os_test.go

@@ -4,7 +4,7 @@ import (
 	"os"
 	"testing"
 
-	. "github.com/tendermint/go-common"
+	cmn "github.com/tendermint/tmlibs/common"
 )
 
 func BenchmarkFileWrite(b *testing.B) {
@@ -14,16 +14,20 @@ func BenchmarkFileWrite(b *testing.B) {
 	if err != nil {
 		b.Error(err)
 	}
-	testString := RandStr(200) + "\n"
+	testString := cmn.RandStr(200) + "\n"
 	b.StartTimer()
 
 	for i := 0; i < b.N; i++ {
-		file.Write([]byte(testString))
+		_, err := file.Write([]byte(testString))
+		if err != nil {
+			b.Error(err)
+		}
 	}
 
-	file.Close()
-	err = os.Remove("benchmark_file_write.out")
-	if err != nil {
+	if err := file.Close(); err != nil {
+		b.Error(err)
+	}
+	if err := os.Remove("benchmark_file_write.out"); err != nil {
 		b.Error(err)
 	}
 }

benchmarks/proto/test.proto

@@ -7,7 +7,7 @@ message ResultStatus {
 }
 
 message NodeInfo {
-  required PubKey pubKey = 1;
+  required ID id = 1;
   required string moniker = 2;
   required string network = 3;
   required string remoteAddr = 4;
@@ -16,6 +16,10 @@ message NodeInfo {
   repeated string other = 7;
 }
 
+message ID {
+  required string id = 1;
+}
+
 message PubKey {
   optional PubKeyEd25519 ed25519 = 1;
 }

benchmarks/simu/counter.go

@@ -1,30 +1,27 @@
 package main
 
 import (
+	"context"
 	"encoding/binary"
-	"time"
-	//"encoding/hex"
 	"fmt"
+	"time"
 
-	"github.com/gorilla/websocket"
-	. "github.com/tendermint/go-common"
-	"github.com/tendermint/go-rpc/client"
-	"github.com/tendermint/go-rpc/types"
-	"github.com/tendermint/go-wire"
-	_ "github.com/tendermint/tendermint/rpc/core/types" // Register RPCResponse > Result types
+	rpcclient "github.com/tendermint/tendermint/rpc/lib/client"
+	cmn "github.com/tendermint/tmlibs/common"
 )
 
 func main() {
-	ws := rpcclient.NewWSClient("127.0.0.1:46657", "/websocket")
-	_, err := ws.Start()
+	wsc := rpcclient.NewWSClient("127.0.0.1:46657", "/websocket")
+	err := wsc.Start()
 	if err != nil {
-		Exit(err.Error())
+		cmn.Exit(err.Error())
 	}
+	defer wsc.Stop()
 
 	// Read a bunch of responses
 	go func() {
 		for {
-			_, ok := <-ws.ResultsCh
+			_, ok := <-wsc.ResponsesCh
 			if !ok {
 				break
 			}
@@ -37,21 +34,14 @@ func main() {
 	for i := 0; ; i++ {
 		binary.BigEndian.PutUint64(buf, uint64(i))
 		//txBytes := hex.EncodeToString(buf[:n])
-		request := rpctypes.NewRPCRequest("fakeid",
-			"broadcast_tx",
-			map[string]interface{}{"tx": buf[:8]})
-		reqBytes := wire.JSONBytes(request)
-		//fmt.Println("!!", string(reqBytes))
 		fmt.Print(".")
-		err := ws.WriteMessage(websocket.TextMessage, reqBytes)
+		err = wsc.Call(context.TODO(), "broadcast_tx", map[string]interface{}{"tx": buf[:8]})
 		if err != nil {
-			Exit(err.Error())
+			cmn.Exit(err.Error())
 		}
 		if i%1000 == 0 {
 			fmt.Println(i)
 		}
 		time.Sleep(time.Microsecond * 1000)
 	}
-
-	ws.Stop()
 }

blockchain/log.go

@@ -1,7 +0,0 @@
-package blockchain
-
-import (
-	"github.com/tendermint/go-logger"
-)
-
-var log = logger.New("module", "blockchain")

blockchain/pool.go

@@ -1,24 +1,51 @@
 package blockchain
 
 import (
+	"errors"
+	"fmt"
 	"math"
 	"sync"
 	"time"
 
-	. "github.com/tendermint/go-common"
-	flow "github.com/tendermint/go-flowrate/flowrate"
+	cmn "github.com/tendermint/tmlibs/common"
+	flow "github.com/tendermint/tmlibs/flowrate"
+	"github.com/tendermint/tmlibs/log"
+
+	"github.com/tendermint/tendermint/p2p"
 	"github.com/tendermint/tendermint/types"
 )
 
+/*
+eg, L = latency = 0.1s
+	P = num peers = 10
+	FN = num full nodes
+	BS = 1kB block size
+	CB = 1 Mbit/s = 128 kB/s
+	CB/P = 12.8 kB
+	B/S = CB/P/BS = 12.8 blocks/s
+
+	12.8 * 0.1 = 1.28 blocks on conn
+*/
+
 const (
-	requestIntervalMS         = 250
-	maxTotalRequesters        = 300
+	requestIntervalMS         = 100
+	maxTotalRequesters        = 1000
 	maxPendingRequests        = maxTotalRequesters
-	maxPendingRequestsPerPeer = 75
-	minRecvRate               = 10240 // 10Kb/s
+	maxPendingRequestsPerPeer = 50
+
+	// Minimum recv rate to ensure we're receiving blocks from a peer fast
+	// enough. If a peer is not sending us data at at least that rate, we
+	// consider them to have timedout and we disconnect.
+	//
+	// Assuming a DSL connection (not a good choice) 128 Kbps (upload) ~ 15 KB/s,
+	// sending data across atlantic ~ 7.5 KB/s.
+	minRecvRate = 7680
+
+	// Maximum difference between current and new block's height.
+	maxDiffBetweenCurrentAndReceivedBlockHeight = 100
 )
 
-var peerTimeoutSeconds = time.Duration(15) // not const so we can override with tests
+var peerTimeout = 15 * time.Second // not const so we can override with tests
 
 /*
 	Peers self report their heights when we join the block pool.
@@ -27,38 +54,39 @@ var peerTimeoutSeconds = time.Duration(15) // not const so we can override with
 	Every so often we ask peers what height they're on so we can keep going.
 
 	Requests are continuously made for blocks of higher heights until
-	the limits. If most of the requests have no available peers, and we
+	the limit is reached. If most of the requests have no available peers, and we
 	are not at peer limits, we can probably switch to consensus reactor
 */
 
 type BlockPool struct {
-	BaseService
+	cmn.BaseService
 	startTime time.Time
 
 	mtx sync.Mutex
 	// block requests
-	requesters map[int]*bpRequester
-	height     int   // the lowest key in requesters.
+	requesters map[int64]*bpRequester
+	height     int64 // the lowest key in requesters.
 	numPending int32 // number of requests pending assignment or block response
 	// peers
-	peers map[string]*bpPeer
+	peers         map[p2p.ID]*bpPeer
+	maxPeerHeight int64
 
 	requestsCh chan<- BlockRequest
-	timeoutsCh chan<- string
+	errorsCh   chan<- peerError
 }
 
-func NewBlockPool(start int, requestsCh chan<- BlockRequest, timeoutsCh chan<- string) *BlockPool {
+func NewBlockPool(start int64, requestsCh chan<- BlockRequest, errorsCh chan<- peerError) *BlockPool {
 	bp := &BlockPool{
-		peers: make(map[string]*bpPeer),
+		peers: make(map[p2p.ID]*bpPeer),
 
-		requesters: make(map[int]*bpRequester),
+		requesters: make(map[int64]*bpRequester),
 		height:     start,
 		numPending: 0,
 
 		requestsCh: requestsCh,
-		timeoutsCh: timeoutsCh,
+		errorsCh:   errorsCh,
 	}
-	bp.BaseService = *NewBaseService(log, "BlockPool", bp)
+	bp.BaseService = *cmn.NewBaseService(nil, "BlockPool", bp)
 	return bp
 }
 
@@ -68,9 +96,7 @@ func (pool *BlockPool) OnStart() error {
 	return nil
 }
 
-func (pool *BlockPool) OnStop() {
-	pool.BaseService.OnStop()
-}
+func (pool *BlockPool) OnStop() {}
 
 // Run spawns requesters as needed.
 func (pool *BlockPool) makeRequestersRoutine() {
@@ -78,6 +104,7 @@ func (pool *BlockPool) makeRequestersRoutine() {
 		if !pool.IsRunning() {
 			break
 		}
+
 		_, numPending, lenRequesters := pool.GetStatus()
 		if numPending >= maxPendingRequests {
 			// sleep for a bit.
@@ -103,10 +130,14 @@ func (pool *BlockPool) removeTimedoutPeers() {
 	for _, peer := range pool.peers {
 		if !peer.didTimeout && peer.numPending > 0 {
 			curRate := peer.recvMonitor.Status().CurRate
-			// XXX remove curRate != 0
+			// curRate can be 0 on start
 			if curRate != 0 && curRate < minRecvRate {
-				pool.sendTimeout(peer.id)
-				log.Warn("SendTimeout", "peer", peer.id, "reason", "curRate too low")
+				err := errors.New("peer is not sending us data fast enough")
+				pool.sendError(err, peer.id)
+				pool.Logger.Error("SendTimeout", "peer", peer.id,
+					"reason", err,
+					"curRate", fmt.Sprintf("%d KB/s", curRate/1024),
+					"minRate", fmt.Sprintf("%d KB/s", minRecvRate/1024))
 				peer.didTimeout = true
 			}
 		}
@@ -116,7 +147,7 @@ func (pool *BlockPool) removeTimedoutPeers() {
 	}
 }
 
-func (pool *BlockPool) GetStatus() (height int, numPending int32, lenRequesters int) {
+func (pool *BlockPool) GetStatus() (height int64, numPending int32, lenRequesters int) {
 	pool.mtx.Lock()
 	defer pool.mtx.Unlock()
 
@@ -128,21 +159,16 @@ func (pool *BlockPool) IsCaughtUp() bool {
 	pool.mtx.Lock()
 	defer pool.mtx.Unlock()
 
-	height := pool.height
-
 	// Need at least 1 peer to be considered caught up.
 	if len(pool.peers) == 0 {
-		log.Debug("Blockpool has no peers")
+		pool.Logger.Debug("Blockpool has no peers")
 		return false
 	}
 
-	maxPeerHeight := 0
-	for _, peer := range pool.peers {
-		maxPeerHeight = MaxInt(maxPeerHeight, peer.height)
-	}
-
-	isCaughtUp := (height > 0 || time.Now().Sub(pool.startTime) > 5*time.Second) && (maxPeerHeight == 0 || height >= maxPeerHeight)
-	log.Notice(Fmt("IsCaughtUp: %v", isCaughtUp), "height", height, "maxPeerHeight", maxPeerHeight)
+	// some conditions to determine if we're caught up
+	receivedBlockOrTimedOut := (pool.height > 0 || time.Since(pool.startTime) > 5*time.Second)
+	ourChainIsLongestAmongPeers := pool.maxPeerHeight == 0 || pool.height >= pool.maxPeerHeight
+	isCaughtUp := receivedBlockOrTimedOut && ourChainIsLongestAmongPeers
 	return isCaughtUp
 }
 
@@ -178,46 +204,66 @@ func (pool *BlockPool) PopRequest() {
 		delete(pool.requesters, pool.height)
 		pool.height++
 	} else {
-		PanicSanity(Fmt("Expected requester to pop, got nothing at height %v", pool.height))
+		panic(fmt.Sprintf("Expected requester to pop, got nothing at height %v", pool.height))
 	}
 }
 
 // Invalidates the block at pool.height,
 // Remove the peer and redo request from others.
-func (pool *BlockPool) RedoRequest(height int) {
+// Returns the ID of the removed peer.
+func (pool *BlockPool) RedoRequest(height int64) p2p.ID {
 	pool.mtx.Lock()
+	defer pool.mtx.Unlock()
+
 	request := pool.requesters[height]
-	pool.mtx.Unlock()
 
 	if request.block == nil {
-		PanicSanity("Expected block to be non-nil")
+		panic("Expected block to be non-nil")
 	}
+
 	// RemovePeer will redo all requesters associated with this peer.
-	// TODO: record this malfeasance
-	pool.RemovePeer(request.peerID)
+	pool.removePeer(request.peerID)
+	return request.peerID
 }
 
 // TODO: ensure that blocks come in order for each peer.
-func (pool *BlockPool) AddBlock(peerID string, block *types.Block, blockSize int) {
+func (pool *BlockPool) AddBlock(peerID p2p.ID, block *types.Block, blockSize int) {
 	pool.mtx.Lock()
 	defer pool.mtx.Unlock()
 
 	requester := pool.requesters[block.Height]
 	if requester == nil {
+		pool.Logger.Info("peer sent us a block we didn't expect", "peer", peerID, "curHeight", pool.height, "blockHeight", block.Height)
+		diff := pool.height - block.Height
+		if diff < 0 {
+			diff *= -1
+		}
+		if diff > maxDiffBetweenCurrentAndReceivedBlockHeight {
+			pool.sendError(errors.New("peer sent us a block we didn't expect with a height too far ahead/behind"), peerID)
+		}
 		return
 	}
 
 	if requester.setBlock(block, peerID) {
 		pool.numPending--
 		peer := pool.peers[peerID]
-		peer.decrPending(blockSize)
+		if peer != nil {
+			peer.decrPending(blockSize)
+		}
 	} else {
 		// Bad peer?
 	}
 }
 
+// MaxPeerHeight returns the highest height reported by a peer.
+func (pool *BlockPool) MaxPeerHeight() int64 {
+	pool.mtx.Lock()
+	defer pool.mtx.Unlock()
+	return pool.maxPeerHeight
+}
+
 // Sets the peer's alleged blockchain height.
-func (pool *BlockPool) SetPeerHeight(peerID string, height int) {
+func (pool *BlockPool) SetPeerHeight(peerID p2p.ID, height int64) {
 	pool.mtx.Lock()
 	defer pool.mtx.Unlock()
 
@@ -226,18 +272,23 @@ func (pool *BlockPool) SetPeerHeight(peerID string, height int) {
 		peer.height = height
 	} else {
 		peer = newBPPeer(pool, peerID, height)
+		peer.setLogger(pool.Logger.With("peer", peerID))
 		pool.peers[peerID] = peer
 	}
+
+	if height > pool.maxPeerHeight {
+		pool.maxPeerHeight = height
+	}
 }
 
-func (pool *BlockPool) RemovePeer(peerID string) {
+func (pool *BlockPool) RemovePeer(peerID p2p.ID) {
 	pool.mtx.Lock()
 	defer pool.mtx.Unlock()
 
 	pool.removePeer(peerID)
 }
 
-func (pool *BlockPool) removePeer(peerID string) {
+func (pool *BlockPool) removePeer(peerID p2p.ID) {
 	for _, requester := range pool.requesters {
 		if requester.getPeerID() == peerID {
 			if requester.getBlock() != nil {
@@ -251,7 +302,7 @@ func (pool *BlockPool) removePeer(peerID string) {
 
 // Pick an available peer with at least the given minHeight.
 // If no peers are available, returns nil.
-func (pool *BlockPool) pickIncrAvailablePeer(minHeight int) *bpPeer {
+func (pool *BlockPool) pickIncrAvailablePeer(minHeight int64) *bpPeer {
 	pool.mtx.Lock()
 	defer pool.mtx.Unlock()
 
@@ -259,7 +310,6 @@ func (pool *BlockPool) pickIncrAvailablePeer(minHeight int) *bpPeer {
 		if peer.didTimeout {
 			pool.removePeer(peer.id)
 			continue
-		} else {
 		}
 		if peer.numPending >= maxPendingRequestsPerPeer {
 			continue
@@ -277,40 +327,50 @@ func (pool *BlockPool) makeNextRequester() {
 	pool.mtx.Lock()
 	defer pool.mtx.Unlock()
 
-	nextHeight := pool.height + len(pool.requesters)
+	nextHeight := pool.height + pool.requestersLen()
 	request := newBPRequester(pool, nextHeight)
+	// request.SetLogger(pool.Logger.With("height", nextHeight))
 
 	pool.requesters[nextHeight] = request
 	pool.numPending++
 
-	request.Start()
+	err := request.Start()
+	if err != nil {
+		request.Logger.Error("Error starting request", "err", err)
+	}
 }
 
-func (pool *BlockPool) sendRequest(height int, peerID string) {
+func (pool *BlockPool) requestersLen() int64 {
+	return int64(len(pool.requesters))
+}
+
+func (pool *BlockPool) sendRequest(height int64, peerID p2p.ID) {
 	if !pool.IsRunning() {
 		return
 	}
 	pool.requestsCh <- BlockRequest{height, peerID}
 }
 
-func (pool *BlockPool) sendTimeout(peerID string) {
+func (pool *BlockPool) sendError(err error, peerID p2p.ID) {
 	if !pool.IsRunning() {
 		return
 	}
-	pool.timeoutsCh <- peerID
+	pool.errorsCh <- peerError{err, peerID}
 }
 
+// unused by tendermint; left for debugging purposes
 func (pool *BlockPool) debug() string {
 	pool.mtx.Lock() // Lock
 	defer pool.mtx.Unlock()
 
 	str := ""
-	for h := pool.height; h < pool.height+len(pool.requesters); h++ {
+	nextHeight := pool.height + pool.requestersLen()
+	for h := pool.height; h < nextHeight; h++ {
 		if pool.requesters[h] == nil {
-			str += Fmt("H(%v):X ", h)
+			str += cmn.Fmt("H(%v):X ", h)
 		} else {
-			str += Fmt("H(%v):", h)
-			str += Fmt("B?(%v) ", pool.requesters[h].block != nil)
+			str += cmn.Fmt("H(%v):", h)
+			str += cmn.Fmt("B?(%v) ", pool.requesters[h].block != nil)
 		}
 	}
 	return str
@@ -320,37 +380,43 @@ func (pool *BlockPool) debug() string {
 
 type bpPeer struct {
 	pool        *BlockPool
-	id          string
+	id          p2p.ID
 	recvMonitor *flow.Monitor
 
-	mtx        sync.Mutex
-	height     int
+	height     int64
 	numPending int32
 	timeout    *time.Timer
 	didTimeout bool
+
+	logger log.Logger
 }
 
-func newBPPeer(pool *BlockPool, peerID string, height int) *bpPeer {
+func newBPPeer(pool *BlockPool, peerID p2p.ID, height int64) *bpPeer {
 	peer := &bpPeer{
 		pool:       pool,
 		id:         peerID,
 		height:     height,
 		numPending: 0,
+		logger:     log.NewNopLogger(),
 	}
 	return peer
 }
 
+func (peer *bpPeer) setLogger(l log.Logger) {
+	peer.logger = l
+}
+
 func (peer *bpPeer) resetMonitor() {
 	peer.recvMonitor = flow.New(time.Second, time.Second*40)
-	var initialValue = float64(minRecvRate) * math.E
+	initialValue := float64(minRecvRate) * math.E
 	peer.recvMonitor.SetREMA(initialValue)
 }
 
 func (peer *bpPeer) resetTimeout() {
 	if peer.timeout == nil {
-		peer.timeout = time.AfterFunc(time.Second*peerTimeoutSeconds, peer.onTimeout)
+		peer.timeout = time.AfterFunc(peerTimeout, peer.onTimeout)
 	} else {
-		peer.timeout.Reset(time.Second * peerTimeoutSeconds)
+		peer.timeout.Reset(peerTimeout)
 	}
 }
 
@@ -376,26 +442,27 @@ func (peer *bpPeer) onTimeout() {
 	peer.pool.mtx.Lock()
 	defer peer.pool.mtx.Unlock()
 
-	peer.pool.sendTimeout(peer.id)
-	log.Warn("SendTimeout", "peer", peer.id, "reason", "onTimeout")
+	err := errors.New("peer did not send us anything")
+	peer.pool.sendError(err, peer.id)
+	peer.logger.Error("SendTimeout", "reason", err, "timeout", peerTimeout)
 	peer.didTimeout = true
 }
 
 //-------------------------------------
 
 type bpRequester struct {
-	BaseService
+	cmn.BaseService
 	pool       *BlockPool
-	height     int
+	height     int64
 	gotBlockCh chan struct{}
 	redoCh     chan struct{}
 
 	mtx    sync.Mutex
-	peerID string
+	peerID p2p.ID
 	block  *types.Block
 }
 
-func newBPRequester(pool *BlockPool, height int) *bpRequester {
+func newBPRequester(pool *BlockPool, height int64) *bpRequester {
 	bpr := &bpRequester{
 		pool:       pool,
 		height:     height,
@@ -405,7 +472,7 @@ func newBPRequester(pool *BlockPool, height int) *bpRequester {
 		peerID: "",
 		block:  nil,
 	}
-	bpr.BaseService = *NewBaseService(nil, "bpRequester", bpr)
+	bpr.BaseService = *cmn.NewBaseService(nil, "bpRequester", bpr)
 	return bpr
 }
 
@@ -415,7 +482,7 @@ func (bpr *bpRequester) OnStart() error {
 }
 
 // Returns true if the peer matches
-func (bpr *bpRequester) setBlock(block *types.Block, peerID string) bool {
+func (bpr *bpRequester) setBlock(block *types.Block, peerID p2p.ID) bool {
 	bpr.mtx.Lock()
 	if bpr.block != nil || bpr.peerID != peerID {
 		bpr.mtx.Unlock()
@@ -434,7 +501,7 @@ func (bpr *bpRequester) getBlock() *types.Block {
 	return bpr.block
 }
 
-func (bpr *bpRequester) getPeerID() string {
+func (bpr *bpRequester) getPeerID() p2p.ID {
 	bpr.mtx.Lock()
 	defer bpr.mtx.Unlock()
 	return bpr.peerID
@@ -459,7 +526,7 @@ func (bpr *bpRequester) requestRoutine() {
 OUTER_LOOP:
 	for {
 		// Pick a peer to send request to.
-		var peer *bpPeer = nil
+		var peer *bpPeer
 	PICK_PEER_LOOP:
 		for {
 			if !bpr.IsRunning() || !bpr.pool.IsRunning() {
@@ -480,10 +547,10 @@ OUTER_LOOP:
 		// Send request and wait.
 		bpr.pool.sendRequest(bpr.height, peer.id)
 		select {
-		case <-bpr.pool.Quit:
+		case <-bpr.pool.Quit():
 			bpr.Stop()
 			return
-		case <-bpr.Quit:
+		case <-bpr.Quit():
 			return
 		case <-bpr.redoCh:
 			bpr.reset()
@@ -491,10 +558,10 @@ OUTER_LOOP:
 		case <-bpr.gotBlockCh:
 			// We got the block, now see if it's good.
 			select {
-			case <-bpr.pool.Quit:
+			case <-bpr.pool.Quit():
 				bpr.Stop()
 				return
-			case <-bpr.Quit:
+			case <-bpr.Quit():
 				return
 			case <-bpr.redoCh:
 				bpr.reset()
@@ -507,6 +574,6 @@ OUTER_LOOP:
 //-------------------------------------
 
 type BlockRequest struct {
-	Height int
-	PeerID string
+	Height int64
+	PeerID p2p.ID
 }

blockchain/pool_test.go

@@ -5,36 +5,45 @@ import (
 	"testing"
 	"time"
 
-	. "github.com/tendermint/go-common"
+	cmn "github.com/tendermint/tmlibs/common"
+	"github.com/tendermint/tmlibs/log"
+
+	"github.com/tendermint/tendermint/p2p"
 	"github.com/tendermint/tendermint/types"
 )
 
 func init() {
-	peerTimeoutSeconds = time.Duration(2)
+	peerTimeout = 2 * time.Second
 }
 
 type testPeer struct {
-	id     string
-	height int
+	id     p2p.ID
+	height int64
 }
 
-func makePeers(numPeers int, minHeight, maxHeight int) map[string]testPeer {
-	peers := make(map[string]testPeer, numPeers)
+func makePeers(numPeers int, minHeight, maxHeight int64) map[p2p.ID]testPeer {
+	peers := make(map[p2p.ID]testPeer, numPeers)
 	for i := 0; i < numPeers; i++ {
-		peerID := RandStr(12)
-		height := minHeight + rand.Intn(maxHeight-minHeight)
+		peerID := p2p.ID(cmn.RandStr(12))
+		height := minHeight + rand.Int63n(maxHeight-minHeight)
 		peers[peerID] = testPeer{peerID, height}
 	}
 	return peers
 }
 
 func TestBasic(t *testing.T) {
-	start := 42
+	start := int64(42)
 	peers := makePeers(10, start+1, 1000)
-	timeoutsCh := make(chan string, 100)
-	requestsCh := make(chan BlockRequest, 100)
-	pool := NewBlockPool(start, requestsCh, timeoutsCh)
-	pool.Start()
+	errorsCh := make(chan peerError, 1000)
+	requestsCh := make(chan BlockRequest, 1000)
+	pool := NewBlockPool(start, requestsCh, errorsCh)
+	pool.SetLogger(log.TestingLogger())
+
+	err := pool.Start()
+	if err != nil {
+		t.Error(err)
+	}
+
 	defer pool.Stop()
 
 	// Introduce each peer.
@@ -62,10 +71,10 @@ func TestBasic(t *testing.T) {
 	// Pull from channels
 	for {
 		select {
-		case peerID := <-timeoutsCh:
-			t.Errorf("timeout: %v", peerID)
+		case err := <-errorsCh:
+			t.Error(err)
 		case request := <-requestsCh:
-			log.Info("TEST: Pulled new BlockRequest", "request", request)
+			t.Logf("Pulled new BlockRequest %v", request)
 			if request.Height == 300 {
 				return // Done!
 			}
@@ -73,23 +82,27 @@ func TestBasic(t *testing.T) {
 			go func() {
 				block := &types.Block{Header: &types.Header{Height: request.Height}}
 				pool.AddBlock(request.PeerID, block, 123)
-				log.Info("TEST: Added block", "block", request.Height, "peer", request.PeerID)
+				t.Logf("Added block from peer %v (height: %v)", request.PeerID, request.Height)
 			}()
 		}
 	}
 }
 
 func TestTimeout(t *testing.T) {
-	start := 42
+	start := int64(42)
 	peers := makePeers(10, start+1, 1000)
-	timeoutsCh := make(chan string, 100)
-	requestsCh := make(chan BlockRequest, 100)
-	pool := NewBlockPool(start, requestsCh, timeoutsCh)
-	pool.Start()
+	errorsCh := make(chan peerError, 1000)
+	requestsCh := make(chan BlockRequest, 1000)
+	pool := NewBlockPool(start, requestsCh, errorsCh)
+	pool.SetLogger(log.TestingLogger())
+	err := pool.Start()
+	if err != nil {
+		t.Error(err)
+	}
 	defer pool.Stop()
 
 	for _, peer := range peers {
-		log.Info("Peer", "id", peer.id)
+		t.Logf("Peer %v", peer.id)
 	}
 
 	// Introduce each peer.
@@ -116,19 +129,20 @@ func TestTimeout(t *testing.T) {
 
 	// Pull from channels
 	counter := 0
-	timedOut := map[string]struct{}{}
+	timedOut := map[p2p.ID]struct{}{}
 	for {
 		select {
-		case peerID := <-timeoutsCh:
-			log.Info("Timeout", "peerID", peerID)
-			if _, ok := timedOut[peerID]; !ok {
+		case err := <-errorsCh:
+			t.Log(err)
+			// consider error to be always timeout here
+			if _, ok := timedOut[err.peerID]; !ok {
 				counter++
 				if counter == len(peers) {
 					return // Done!
 				}
 			}
 		case request := <-requestsCh:
-			log.Info("TEST: Pulled new BlockRequest", "request", request)
+			t.Logf("Pulled new BlockRequest %+v", request)
 		}
 	}
 }

blockchain/reactor.go

@@ -1,27 +1,23 @@
 package blockchain
 
 import (
-	"bytes"
-	"errors"
+	"fmt"
 	"reflect"
 	"time"
 
-	cmn "github.com/tendermint/go-common"
-	cfg "github.com/tendermint/go-config"
-	"github.com/tendermint/go-p2p"
-	"github.com/tendermint/go-wire"
-	"github.com/tendermint/tendermint/proxy"
+	amino "github.com/tendermint/go-amino"
+	"github.com/tendermint/tendermint/p2p"
 	sm "github.com/tendermint/tendermint/state"
 	"github.com/tendermint/tendermint/types"
+	cmn "github.com/tendermint/tmlibs/common"
+	"github.com/tendermint/tmlibs/log"
 )
 
 const (
 	// BlockchainChannel is a channel for blocks and status updates (`BlockStore` height)
 	BlockchainChannel = byte(0x40)
 
-	defaultChannelCapacity = 100
-	defaultSleepIntervalMS = 500
-	trySyncIntervalMS      = 100
+	trySyncIntervalMS = 50
 	// stop syncing when last block's time is
 	// within this much of the system time.
 	// stopSyncingDurationMinutes = 10
@@ -30,66 +26,91 @@ const (
 	statusUpdateIntervalSeconds = 10
 	// check if we should switch to consensus reactor
 	switchToConsensusIntervalSeconds = 1
-	maxBlockchainResponseSize        = types.MaxBlockSize + 2
+
+	// NOTE: keep up to date with bcBlockResponseMessage
+	bcBlockResponseMessagePrefixSize   = 4
+	bcBlockResponseMessageFieldKeySize = 1
+	maxMsgSize                         = types.MaxBlockSizeBytes +
+		bcBlockResponseMessagePrefixSize +
+		bcBlockResponseMessageFieldKeySize
 )
 
 type consensusReactor interface {
 	// for when we switch from blockchain reactor and fast sync to
 	// the consensus machine
-	SwitchToConsensus(*sm.State)
+	SwitchToConsensus(sm.State, int)
+}
+
+type peerError struct {
+	err    error
+	peerID p2p.ID
+}
+
+func (e peerError) Error() string {
+	return fmt.Sprintf("error with peer %v: %s", e.peerID, e.err.Error())
 }
 
 // BlockchainReactor handles long-term catchup syncing.
 type BlockchainReactor struct {
 	p2p.BaseReactor
 
-	config       cfg.Config
-	state        *sm.State
-	proxyAppConn proxy.AppConnConsensus // same as consensus.proxyAppConn
-	store        *BlockStore
-	pool         *BlockPool
-	fastSync     bool
-	requestsCh   chan BlockRequest
-	timeoutsCh   chan string
-	lastBlock    *types.Block
+	// immutable
+	initialState sm.State
 
-	evsw types.EventSwitch
+	blockExec *sm.BlockExecutor
+	store     *BlockStore
+	pool      *BlockPool
+	fastSync  bool
+
+	requestsCh <-chan BlockRequest
+	errorsCh   <-chan peerError
 }
 
 // NewBlockchainReactor returns new reactor instance.
-func NewBlockchainReactor(config cfg.Config, state *sm.State, proxyAppConn proxy.AppConnConsensus, store *BlockStore, fastSync bool) *BlockchainReactor {
-	if state.LastBlockHeight == store.Height()-1 {
-		store.height-- // XXX HACK, make this better
-	}
+func NewBlockchainReactor(state sm.State, blockExec *sm.BlockExecutor, store *BlockStore,
+	fastSync bool) *BlockchainReactor {
+
 	if state.LastBlockHeight != store.Height() {
-		cmn.PanicSanity(cmn.Fmt("state (%v) and store (%v) height mismatch", state.LastBlockHeight, store.Height()))
+		panic(fmt.Sprintf("state (%v) and store (%v) height mismatch", state.LastBlockHeight,
+			store.Height()))
 	}
-	requestsCh := make(chan BlockRequest, defaultChannelCapacity)
-	timeoutsCh := make(chan string, defaultChannelCapacity)
+
+	const capacity = 1000 // must be bigger than peers count
+	requestsCh := make(chan BlockRequest, capacity)
+	errorsCh := make(chan peerError, capacity) // so we don't block in #Receive#pool.AddBlock
+
 	pool := NewBlockPool(
 		store.Height()+1,
 		requestsCh,
-		timeoutsCh,
+		errorsCh,
 	)
+
 	bcR := &BlockchainReactor{
-		config:       config,
-		state:        state,
-		proxyAppConn: proxyAppConn,
+		initialState: state,
+		blockExec:    blockExec,
 		store:        store,
 		pool:         pool,
 		fastSync:     fastSync,
 		requestsCh:   requestsCh,
-		timeoutsCh:   timeoutsCh,
+		errorsCh:     errorsCh,
 	}
-	bcR.BaseReactor = *p2p.NewBaseReactor(log, "BlockchainReactor", bcR)
+	bcR.BaseReactor = *p2p.NewBaseReactor("BlockchainReactor", bcR)
 	return bcR
 }
 
-// OnStart implements BaseService
+// SetLogger implements cmn.Service by setting the logger on reactor and pool.
+func (bcR *BlockchainReactor) SetLogger(l log.Logger) {
+	bcR.BaseService.Logger = l
+	bcR.pool.Logger = l
+}
+
+// OnStart implements cmn.Service.
 func (bcR *BlockchainReactor) OnStart() error {
-	bcR.BaseReactor.OnStart()
+	if err := bcR.BaseReactor.OnStart(); err != nil {
+		return err
+	}
 	if bcR.fastSync {
-		_, err := bcR.pool.Start()
+		err := bcR.pool.Start()
 		if err != nil {
 			return err
 		}
@@ -98,7 +119,7 @@ func (bcR *BlockchainReactor) OnStart() error {
 	return nil
 }
 
-// OnStop implements BaseService
+// OnStop implements cmn.Service.
 func (bcR *BlockchainReactor) OnStop() {
 	bcR.BaseReactor.OnStop()
 	bcR.pool.Stop()
@@ -107,63 +128,81 @@ func (bcR *BlockchainReactor) OnStop() {
 // GetChannels implements Reactor
 func (bcR *BlockchainReactor) GetChannels() []*p2p.ChannelDescriptor {
 	return []*p2p.ChannelDescriptor{
-		&p2p.ChannelDescriptor{
-			ID:                BlockchainChannel,
-			Priority:          5,
-			SendQueueCapacity: 100,
+		{
+			ID:                  BlockchainChannel,
+			Priority:            10,
+			SendQueueCapacity:   1000,
+			RecvBufferCapacity:  50 * 4096,
+			RecvMessageCapacity: maxMsgSize,
 		},
 	}
 }
 
 // AddPeer implements Reactor by sending our state to peer.
-func (bcR *BlockchainReactor) AddPeer(peer *p2p.Peer) {
-	if !peer.Send(BlockchainChannel, struct{ BlockchainMessage }{&bcStatusResponseMessage{bcR.store.Height()}}) {
+func (bcR *BlockchainReactor) AddPeer(peer p2p.Peer) {
+	msgBytes := cdc.MustMarshalBinaryBare(&bcStatusResponseMessage{bcR.store.Height()})
+	if !peer.Send(BlockchainChannel, msgBytes) {
 		// doing nothing, will try later in `poolRoutine`
 	}
+	// peer is added to the pool once we receive the first
+	// bcStatusResponseMessage from the peer and call pool.SetPeerHeight
 }
 
 // RemovePeer implements Reactor by removing peer from the pool.
-func (bcR *BlockchainReactor) RemovePeer(peer *p2p.Peer, reason interface{}) {
-	bcR.pool.RemovePeer(peer.Key)
+func (bcR *BlockchainReactor) RemovePeer(peer p2p.Peer, reason interface{}) {
+	bcR.pool.RemovePeer(peer.ID())
+}
+
+// respondToPeer loads a block and sends it to the requesting peer,
+// if we have it. Otherwise, we'll respond saying we don't have it.
+// According to the Tendermint spec, if all nodes are honest,
+// no node should be requesting for a block that's non-existent.
+func (bcR *BlockchainReactor) respondToPeer(msg *bcBlockRequestMessage,
+	src p2p.Peer) (queued bool) {
+
+	block := bcR.store.LoadBlock(msg.Height)
+	if block != nil {
+		msgBytes := cdc.MustMarshalBinaryBare(&bcBlockResponseMessage{Block: block})
+		return src.TrySend(BlockchainChannel, msgBytes)
+	}
+
+	bcR.Logger.Info("Peer asking for a block we don't have", "src", src, "height", msg.Height)
+
+	msgBytes := cdc.MustMarshalBinaryBare(&bcNoBlockResponseMessage{Height: msg.Height})
+	return src.TrySend(BlockchainChannel, msgBytes)
 }
 
 // Receive implements Reactor by handling 4 types of messages (look below).
-func (bcR *BlockchainReactor) Receive(chID byte, src *p2p.Peer, msgBytes []byte) {
-	_, msg, err := DecodeMessage(msgBytes)
+func (bcR *BlockchainReactor) Receive(chID byte, src p2p.Peer, msgBytes []byte) {
+	msg, err := DecodeMessage(msgBytes)
 	if err != nil {
-		log.Warn("Error decoding message", "error", err)
+		bcR.Logger.Error("Error decoding message", "src", src, "chId", chID, "msg", msg, "err", err, "bytes", msgBytes)
+		bcR.Switch.StopPeerForError(src, err)
 		return
 	}
 
-	log.Debug("Receive", "src", src, "chID", chID, "msg", msg)
+	bcR.Logger.Debug("Receive", "src", src, "chID", chID, "msg", msg)
 
 	switch msg := msg.(type) {
 	case *bcBlockRequestMessage:
-		// Got a request for a block. Respond with block if we have it.
-		block := bcR.store.LoadBlock(msg.Height)
-		if block != nil {
-			msg := &bcBlockResponseMessage{Block: block}
-			queued := src.TrySend(BlockchainChannel, struct{ BlockchainMessage }{msg})
-			if !queued {
-				// queue is full, just ignore.
-			}
-		} else {
-			// TODO peer is asking for things we don't have.
+		if queued := bcR.respondToPeer(msg, src); !queued {
+			// Unfortunately not queued since the queue is full.
 		}
 	case *bcBlockResponseMessage:
 		// Got a block.
-		bcR.pool.AddBlock(src.Key, msg.Block, len(msgBytes))
+		bcR.pool.AddBlock(src.ID(), msg.Block, len(msgBytes))
 	case *bcStatusRequestMessage:
 		// Send peer our state.
-		queued := src.TrySend(BlockchainChannel, struct{ BlockchainMessage }{&bcStatusResponseMessage{bcR.store.Height()}})
+		msgBytes := cdc.MustMarshalBinaryBare(&bcStatusResponseMessage{bcR.store.Height()})
+		queued := src.TrySend(BlockchainChannel, msgBytes)
 		if !queued {
 			// sorry
 		}
 	case *bcStatusResponseMessage:
 		// Got a peer status. Unverified.
-		bcR.pool.SetPeerHeight(src.Key, msg.Height)
+		bcR.pool.SetPeerHeight(src.ID(), msg.Height)
 	default:
-		log.Warn(cmn.Fmt("Unknown message type %v", reflect.TypeOf(msg)))
+		bcR.Logger.Error(cmn.Fmt("Unknown message type %v", reflect.TypeOf(msg)))
 	}
 }
 
@@ -176,85 +215,106 @@ func (bcR *BlockchainReactor) poolRoutine() {
 	statusUpdateTicker := time.NewTicker(statusUpdateIntervalSeconds * time.Second)
 	switchToConsensusTicker := time.NewTicker(switchToConsensusIntervalSeconds * time.Second)
 
+	blocksSynced := 0
+
+	chainID := bcR.initialState.ChainID
+	state := bcR.initialState
+
+	lastHundred := time.Now()
+	lastRate := 0.0
+
 FOR_LOOP:
 	for {
 		select {
-		case request := <-bcR.requestsCh: // chan BlockRequest
+		case request := <-bcR.requestsCh:
 			peer := bcR.Switch.Peers().Get(request.PeerID)
 			if peer == nil {
 				continue FOR_LOOP // Peer has since been disconnected.
 			}
-			msg := &bcBlockRequestMessage{request.Height}
-			queued := peer.TrySend(BlockchainChannel, struct{ BlockchainMessage }{msg})
+			msgBytes := cdc.MustMarshalBinaryBare(&bcBlockRequestMessage{request.Height})
+			queued := peer.TrySend(BlockchainChannel, msgBytes)
 			if !queued {
 				// We couldn't make the request, send-queue full.
 				// The pool handles timeouts, just let it go.
 				continue FOR_LOOP
 			}
-		case peerID := <-bcR.timeoutsCh: // chan string
-			// Peer timed out.
-			peer := bcR.Switch.Peers().Get(peerID)
+		case err := <-bcR.errorsCh:
+			peer := bcR.Switch.Peers().Get(err.peerID)
 			if peer != nil {
-				bcR.Switch.StopPeerForError(peer, errors.New("BlockchainReactor Timeout"))
+				bcR.Switch.StopPeerForError(peer, err)
 			}
-		case _ = <-statusUpdateTicker.C:
+		case <-statusUpdateTicker.C:
 			// ask for status updates
-			go bcR.BroadcastStatusRequest()
-		case _ = <-switchToConsensusTicker.C:
-			height, numPending, _ := bcR.pool.GetStatus()
+			go bcR.BroadcastStatusRequest() // nolint: errcheck
+		case <-switchToConsensusTicker.C:
+			height, numPending, lenRequesters := bcR.pool.GetStatus()
 			outbound, inbound, _ := bcR.Switch.NumPeers()
-			log.Info("Consensus ticker", "numPending", numPending, "total", len(bcR.pool.requesters),
+			bcR.Logger.Debug("Consensus ticker", "numPending", numPending, "total", lenRequesters,
 				"outbound", outbound, "inbound", inbound)
 			if bcR.pool.IsCaughtUp() {
-				log.Notice("Time to switch to consensus reactor!", "height", height)
+				bcR.Logger.Info("Time to switch to consensus reactor!", "height", height)
 				bcR.pool.Stop()
 
 				conR := bcR.Switch.Reactor("CONSENSUS").(consensusReactor)
-				conR.SwitchToConsensus(bcR.state)
+				conR.SwitchToConsensus(state, blocksSynced)
 
 				break FOR_LOOP
 			}
-		case _ = <-trySyncTicker.C: // chan time
+		case <-trySyncTicker.C: // chan time
 			// This loop can be slow as long as it's doing syncing work.
 		SYNC_LOOP:
 			for i := 0; i < 10; i++ {
 				// See if there are any blocks to sync.
 				first, second := bcR.pool.PeekTwoBlocks()
-				//log.Info("TrySync peeked", "first", first, "second", second)
+				//bcR.Logger.Info("TrySync peeked", "first", first, "second", second)
 				if first == nil || second == nil {
 					// We need both to sync the first block.
 					break SYNC_LOOP
 				}
-				firstParts := first.MakePartSet(bcR.config.GetInt("block_part_size")) // TODO: put part size in parts header?
+				firstParts := first.MakePartSet(state.ConsensusParams.BlockPartSizeBytes)
 				firstPartsHeader := firstParts.Header()
+				firstID := types.BlockID{first.Hash(), firstPartsHeader}
 				// Finally, verify the first block using the second's commit
 				// NOTE: we can probably make this more efficient, but note that calling
 				// first.Hash() doesn't verify the tx contents, so MakePartSet() is
 				// currently necessary.
-				err := bcR.state.Validators.VerifyCommit(
-					bcR.state.ChainID, types.BlockID{first.Hash(), firstPartsHeader}, first.Height, second.LastCommit)
+				err := state.Validators.VerifyCommit(
+					chainID, firstID, first.Height, second.LastCommit)
 				if err != nil {
-					log.Info("error in validation", "error", err)
-					bcR.pool.RedoRequest(first.Height)
+					bcR.Logger.Error("Error in validation", "err", err)
+					peerID := bcR.pool.RedoRequest(first.Height)
+					peer := bcR.Switch.Peers().Get(peerID)
+					if peer != nil {
+						bcR.Switch.StopPeerForError(peer, fmt.Errorf("BlockchainReactor validation error: %v", err))
+					}
 					break SYNC_LOOP
 				} else {
 					bcR.pool.PopRequest()
 
+					// TODO: batch saves so we dont persist to disk every block
 					bcR.store.SaveBlock(first, firstParts, second.LastCommit)
 
-					// TODO: should we be firing events? need to fire NewBlock events manually ...
-					// NOTE: we could improve performance if we
-					// didn't make the app commit to disk every block
-					// ... but we would need a way to get the hash without it persisting
-					err := bcR.state.ApplyBlock(bcR.evsw, bcR.proxyAppConn, first, firstPartsHeader, types.MockMempool{})
+					// TODO: same thing for app - but we would need a way to
+					// get the hash without persisting the state
+					var err error
+					state, err = bcR.blockExec.ApplyBlock(state, firstID, first)
 					if err != nil {
 						// TODO This is bad, are we zombie?
-						cmn.PanicQ(cmn.Fmt("Failed to process committed block (%d:%X): %v", first.Height, first.Hash(), err))
+						cmn.PanicQ(cmn.Fmt("Failed to process committed block (%d:%X): %v",
+							first.Height, first.Hash(), err))
+					}
+					blocksSynced++
+
+					if blocksSynced%100 == 0 {
+						lastRate = 0.9*lastRate + 0.1*(100/time.Since(lastHundred).Seconds())
+						bcR.Logger.Info("Fast Sync Rate", "height", bcR.pool.height,
+							"max_peer_height", bcR.pool.MaxPeerHeight(), "blocks/s", lastRate)
+						lastHundred = time.Now()
 					}
 				}
 			}
 			continue FOR_LOOP
-		case <-bcR.Quit:
+		case <-bcR.Quit():
 			break FOR_LOOP
 		}
 	}
@@ -262,45 +322,36 @@ FOR_LOOP:
 
 // BroadcastStatusRequest broadcasts `BlockStore` height.
 func (bcR *BlockchainReactor) BroadcastStatusRequest() error {
-	bcR.Switch.Broadcast(BlockchainChannel, struct{ BlockchainMessage }{&bcStatusRequestMessage{bcR.store.Height()}})
+	msgBytes := cdc.MustMarshalBinaryBare(&bcStatusRequestMessage{bcR.store.Height()})
+	bcR.Switch.Broadcast(BlockchainChannel, msgBytes)
 	return nil
 }
 
-// SetEventSwitch implements events.Eventable
-func (bcR *BlockchainReactor) SetEventSwitch(evsw types.EventSwitch) {
-	bcR.evsw = evsw
-}
-
 //-----------------------------------------------------------------------------
 // Messages
 
-const (
-	msgTypeBlockRequest   = byte(0x10)
-	msgTypeBlockResponse  = byte(0x11)
-	msgTypeStatusResponse = byte(0x20)
-	msgTypeStatusRequest  = byte(0x21)
-)
-
 // BlockchainMessage is a generic message for this reactor.
 type BlockchainMessage interface{}
 
-var _ = wire.RegisterInterface(
-	struct{ BlockchainMessage }{},
-	wire.ConcreteType{&bcBlockRequestMessage{}, msgTypeBlockRequest},
-	wire.ConcreteType{&bcBlockResponseMessage{}, msgTypeBlockResponse},
-	wire.ConcreteType{&bcStatusResponseMessage{}, msgTypeStatusResponse},
-	wire.ConcreteType{&bcStatusRequestMessage{}, msgTypeStatusRequest},
-)
+func RegisterBlockchainMessages(cdc *amino.Codec) {
+	cdc.RegisterInterface((*BlockchainMessage)(nil), nil)
+	cdc.RegisterConcrete(&bcBlockRequestMessage{}, "tendermint/mempool/BlockRequest", nil)
+	cdc.RegisterConcrete(&bcBlockResponseMessage{}, "tendermint/mempool/BlockResponse", nil)
+	cdc.RegisterConcrete(&bcNoBlockResponseMessage{}, "tendermint/mempool/NoBlockResponse", nil)
+	cdc.RegisterConcrete(&bcStatusResponseMessage{}, "tendermint/mempool/StatusResponse", nil)
+	cdc.RegisterConcrete(&bcStatusRequestMessage{}, "tendermint/mempool/StatusRequest", nil)
+}
 
 // DecodeMessage decodes BlockchainMessage.
 // TODO: ensure that bz is completely read.
-func DecodeMessage(bz []byte) (msgType byte, msg BlockchainMessage, err error) {
-	msgType = bz[0]
-	n := int(0)
-	r := bytes.NewReader(bz)
-	msg = wire.ReadBinary(struct{ BlockchainMessage }{}, r, maxBlockchainResponseSize, &n, &err).(struct{ BlockchainMessage }).BlockchainMessage
-	if err != nil && n != len(bz) {
-		err = errors.New("DecodeMessage() had bytes left over")
+func DecodeMessage(bz []byte) (msg BlockchainMessage, err error) {
+	if len(bz) > maxMsgSize {
+		return msg, fmt.Errorf("Msg exceeds max size (%d > %d)",
+			len(bz), maxMsgSize)
+	}
+	err = cdc.UnmarshalBinaryBare(bz, &msg)
+	if err != nil {
+		err = cmn.ErrorWrap(err, "DecodeMessage() had bytes left over")
 	}
 	return
 }
@@ -308,16 +359,23 @@ func DecodeMessage(bz []byte) (msgType byte, msg BlockchainMessage, err error) {
 //-------------------------------------
 
 type bcBlockRequestMessage struct {
-	Height int
+	Height int64
 }
 
 func (m *bcBlockRequestMessage) String() string {
 	return cmn.Fmt("[bcBlockRequestMessage %v]", m.Height)
 }
 
+type bcNoBlockResponseMessage struct {
+	Height int64
+}
+
+func (brm *bcNoBlockResponseMessage) String() string {
+	return cmn.Fmt("[bcNoBlockResponseMessage %d]", brm.Height)
+}
+
 //-------------------------------------
 
-// NOTE: keep up-to-date with maxBlockchainResponseSize
 type bcBlockResponseMessage struct {
 	Block *types.Block
 }
@@ -329,7 +387,7 @@ func (m *bcBlockResponseMessage) String() string {
 //-------------------------------------
 
 type bcStatusRequestMessage struct {
-	Height int
+	Height int64
 }
 
 func (m *bcStatusRequestMessage) String() string {
@@ -339,7 +397,7 @@ func (m *bcStatusRequestMessage) String() string {
 //-------------------------------------
 
 type bcStatusResponseMessage struct {
-	Height int
+	Height int64
 }
 
 func (m *bcStatusResponseMessage) String() string {

blockchain/reactor_test.go

@@ -0,0 +1,206 @@
+package blockchain
+
+import (
+	"testing"
+
+	cmn "github.com/tendermint/tmlibs/common"
+	dbm "github.com/tendermint/tmlibs/db"
+	"github.com/tendermint/tmlibs/log"
+
+	cfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tendermint/p2p"
+	"github.com/tendermint/tendermint/proxy"
+	sm "github.com/tendermint/tendermint/state"
+	"github.com/tendermint/tendermint/types"
+)
+
+func makeStateAndBlockStore(logger log.Logger) (sm.State, *BlockStore) {
+	config := cfg.ResetTestRoot("blockchain_reactor_test")
+	// blockDB := dbm.NewDebugDB("blockDB", dbm.NewMemDB())
+	// stateDB := dbm.NewDebugDB("stateDB", dbm.NewMemDB())
+	blockDB := dbm.NewMemDB()
+	stateDB := dbm.NewMemDB()
+	blockStore := NewBlockStore(blockDB)
+	state, err := sm.LoadStateFromDBOrGenesisFile(stateDB, config.GenesisFile())
+	if err != nil {
+		panic(cmn.ErrorWrap(err, "error constructing state from genesis file"))
+	}
+	return state, blockStore
+}
+
+func newBlockchainReactor(logger log.Logger, maxBlockHeight int64) *BlockchainReactor {
+	state, blockStore := makeStateAndBlockStore(logger)
+
+	// Make the blockchainReactor itself
+	fastSync := true
+	var nilApp proxy.AppConnConsensus
+	blockExec := sm.NewBlockExecutor(dbm.NewMemDB(), log.TestingLogger(), nilApp,
+		types.MockMempool{}, types.MockEvidencePool{})
+
+	bcReactor := NewBlockchainReactor(state.Copy(), blockExec, blockStore, fastSync)
+	bcReactor.SetLogger(logger.With("module", "blockchain"))
+
+	// Next: we need to set a switch in order for peers to be added in
+	bcReactor.Switch = p2p.NewSwitch(cfg.DefaultP2PConfig())
+
+	// Lastly: let's add some blocks in
+	for blockHeight := int64(1); blockHeight <= maxBlockHeight; blockHeight++ {
+		firstBlock := makeBlock(blockHeight, state)
+		secondBlock := makeBlock(blockHeight+1, state)
+		firstParts := firstBlock.MakePartSet(state.ConsensusParams.BlockGossip.BlockPartSizeBytes)
+		blockStore.SaveBlock(firstBlock, firstParts, secondBlock.LastCommit)
+	}
+
+	return bcReactor
+}
+
+func TestNoBlockResponse(t *testing.T) {
+	maxBlockHeight := int64(20)
+
+	bcr := newBlockchainReactor(log.TestingLogger(), maxBlockHeight)
+	bcr.Start()
+	defer bcr.Stop()
+
+	// Add some peers in
+	peer := newbcrTestPeer(p2p.ID(cmn.RandStr(12)))
+	bcr.AddPeer(peer)
+
+	chID := byte(0x01)
+
+	tests := []struct {
+		height   int64
+		existent bool
+	}{
+		{maxBlockHeight + 2, false},
+		{10, true},
+		{1, true},
+		{100, false},
+	}
+
+	// receive a request message from peer,
+	// wait for our response to be received on the peer
+	for _, tt := range tests {
+		reqBlockMsg := &bcBlockRequestMessage{tt.height}
+		reqBlockBytes := cdc.MustMarshalBinaryBare(reqBlockMsg)
+		bcr.Receive(chID, peer, reqBlockBytes)
+		msg := peer.lastBlockchainMessage()
+
+		if tt.existent {
+			if blockMsg, ok := msg.(*bcBlockResponseMessage); !ok {
+				t.Fatalf("Expected to receive a block response for height %d", tt.height)
+			} else if blockMsg.Block.Height != tt.height {
+				t.Fatalf("Expected response to be for height %d, got %d", tt.height, blockMsg.Block.Height)
+			}
+		} else {
+			if noBlockMsg, ok := msg.(*bcNoBlockResponseMessage); !ok {
+				t.Fatalf("Expected to receive a no block response for height %d", tt.height)
+			} else if noBlockMsg.Height != tt.height {
+				t.Fatalf("Expected response to be for height %d, got %d", tt.height, noBlockMsg.Height)
+			}
+		}
+	}
+}
+
+/*
+// NOTE: This is too hard to test without
+// an easy way to add test peer to switch
+// or without significant refactoring of the module.
+// Alternatively we could actually dial a TCP conn but
+// that seems extreme.
+func TestBadBlockStopsPeer(t *testing.T) {
+	maxBlockHeight := int64(20)
+
+	bcr := newBlockchainReactor(log.TestingLogger(), maxBlockHeight)
+	bcr.Start()
+	defer bcr.Stop()
+
+	// Add some peers in
+	peer := newbcrTestPeer(p2p.ID(cmn.RandStr(12)))
+
+	// XXX: This doesn't add the peer to anything,
+	// so it's hard to check that it's later removed
+	bcr.AddPeer(peer)
+	assert.True(t, bcr.Switch.Peers().Size() > 0)
+
+	// send a bad block from the peer
+	// default blocks already dont have commits, so should fail
+	block := bcr.store.LoadBlock(3)
+	msg := &bcBlockResponseMessage{Block: block}
+	peer.Send(BlockchainChannel, struct{ BlockchainMessage }{msg})
+
+	ticker := time.NewTicker(time.Millisecond * 10)
+	timer := time.NewTimer(time.Second * 2)
+LOOP:
+	for {
+		select {
+		case <-ticker.C:
+			if bcr.Switch.Peers().Size() == 0 {
+				break LOOP
+			}
+		case <-timer.C:
+			t.Fatal("Timed out waiting to disconnect peer")
+		}
+	}
+}
+*/
+
+//----------------------------------------------
+// utility funcs
+
+func makeTxs(height int64) (txs []types.Tx) {
+	for i := 0; i < 10; i++ {
+		txs = append(txs, types.Tx([]byte{byte(height), byte(i)}))
+	}
+	return txs
+}
+
+func makeBlock(height int64, state sm.State) *types.Block {
+	block, _ := state.MakeBlock(height, makeTxs(height), new(types.Commit))
+	return block
+}
+
+// The Test peer
+type bcrTestPeer struct {
+	cmn.BaseService
+	id p2p.ID
+	ch chan interface{}
+}
+
+var _ p2p.Peer = (*bcrTestPeer)(nil)
+
+func newbcrTestPeer(id p2p.ID) *bcrTestPeer {
+	bcr := &bcrTestPeer{
+		id: id,
+		ch: make(chan interface{}, 2),
+	}
+	bcr.BaseService = *cmn.NewBaseService(nil, "bcrTestPeer", bcr)
+	return bcr
+}
+
+func (tp *bcrTestPeer) lastBlockchainMessage() interface{} { return <-tp.ch }
+
+func (tp *bcrTestPeer) TrySend(chID byte, msgBytes []byte) bool {
+	var msg BlockchainMessage
+	err := cdc.UnmarshalBinaryBare(msgBytes, &msg)
+	if err != nil {
+		panic(cmn.ErrorWrap(err, "Error while trying to parse a BlockchainMessage"))
+	}
+	if _, ok := msg.(*bcStatusResponseMessage); ok {
+		// Discard status response messages since they skew our results
+		// We only want to deal with:
+		// + bcBlockResponseMessage
+		// + bcNoBlockResponseMessage
+	} else {
+		tp.ch <- msg
+	}
+	return true
+}
+
+func (tp *bcrTestPeer) Send(chID byte, msgBytes []byte) bool { return tp.TrySend(chID, msgBytes) }
+func (tp *bcrTestPeer) NodeInfo() p2p.NodeInfo               { return p2p.NodeInfo{} }
+func (tp *bcrTestPeer) Status() p2p.ConnectionStatus         { return p2p.ConnectionStatus{} }
+func (tp *bcrTestPeer) ID() p2p.ID                           { return tp.id }
+func (tp *bcrTestPeer) IsOutbound() bool                     { return false }
+func (tp *bcrTestPeer) IsPersistent() bool                   { return true }
+func (tp *bcrTestPeer) Get(s string) interface{}             { return s }
+func (tp *bcrTestPeer) Set(string, interface{})              {}

blockchain/store.go

@@ -1,20 +1,17 @@
 package blockchain
 
 import (
-	"bytes"
-	"encoding/json"
 	"fmt"
-	"io"
 	"sync"
 
-	. "github.com/tendermint/go-common"
-	dbm "github.com/tendermint/go-db"
-	"github.com/tendermint/go-wire"
+	cmn "github.com/tendermint/tmlibs/common"
+	dbm "github.com/tendermint/tmlibs/db"
+
 	"github.com/tendermint/tendermint/types"
 )
 
 /*
-Simple low level store for blocks.
+BlockStore is a simple low level store for blocks.
 
 There are three types of information stored:
  - BlockMeta:   Meta information about each block
@@ -23,17 +20,20 @@ There are three types of information stored:
 
 Currently the precommit signatures are duplicated in the Block parts as
 well as the Commit.  In the future this may change, perhaps by moving
-the Commit data outside the Block.
+the Commit data outside the Block. (TODO)
 
-Panics indicate probable corruption in the data
+// NOTE: BlockStore methods will panic if they encounter errors
+// deserializing loaded data, indicating probable corruption on disk.
 */
 type BlockStore struct {
 	db dbm.DB
 
 	mtx    sync.RWMutex
-	height int
+	height int64
 }
 
+// NewBlockStore returns a new BlockStore with the given DB,
+// initialized to the last height that was committed to the DB.
 func NewBlockStore(db dbm.DB) *BlockStore {
 	bsjson := LoadBlockStoreStateJSON(db)
 	return &BlockStore{
@@ -42,134 +42,136 @@ func NewBlockStore(db dbm.DB) *BlockStore {
 	}
 }
 
-// Height() returns the last known contiguous block height.
-func (bs *BlockStore) Height() int {
+// Height returns the last known contiguous block height.
+func (bs *BlockStore) Height() int64 {
 	bs.mtx.RLock()
 	defer bs.mtx.RUnlock()
 	return bs.height
 }
 
-func (bs *BlockStore) GetReader(key []byte) io.Reader {
-	bytez := bs.db.Get(key)
-	if bytez == nil {
+// LoadBlock returns the block with the given height.
+// If no block is found for that height, it returns nil.
+func (bs *BlockStore) LoadBlock(height int64) *types.Block {
+	var blockMeta = bs.LoadBlockMeta(height)
+	if blockMeta == nil {
 		return nil
 	}
-	return bytes.NewReader(bytez)
-}
 
-func (bs *BlockStore) LoadBlock(height int) *types.Block {
-	var n int
-	var err error
-	r := bs.GetReader(calcBlockMetaKey(height))
-	if r == nil {
-		return nil
-	}
-	blockMeta := wire.ReadBinary(&types.BlockMeta{}, r, 0, &n, &err).(*types.BlockMeta)
-	if err != nil {
-		PanicCrisis(Fmt("Error reading block meta: %v", err))
-	}
-	bytez := []byte{}
+	var block = new(types.Block)
+	buf := []byte{}
 	for i := 0; i < blockMeta.BlockID.PartsHeader.Total; i++ {
 		part := bs.LoadBlockPart(height, i)
-		bytez = append(bytez, part.Bytes...)
+		buf = append(buf, part.Bytes...)
 	}
-	block := wire.ReadBinary(&types.Block{}, bytes.NewReader(bytez), 0, &n, &err).(*types.Block)
+	err := cdc.UnmarshalBinary(buf, block)
 	if err != nil {
-		PanicCrisis(Fmt("Error reading block: %v", err))
+		// NOTE: The existence of meta should imply the existence of the
+		// block. So, make sure meta is only saved after blocks are saved.
+		panic(cmn.ErrorWrap(err, "Error reading block"))
 	}
 	return block
 }
 
-func (bs *BlockStore) LoadBlockPart(height int, index int) *types.Part {
-	var n int
-	var err error
-	r := bs.GetReader(calcBlockPartKey(height, index))
-	if r == nil {
+// LoadBlockPart returns the Part at the given index
+// from the block at the given height.
+// If no part is found for the given height and index, it returns nil.
+func (bs *BlockStore) LoadBlockPart(height int64, index int) *types.Part {
+	var part = new(types.Part)
+	bz := bs.db.Get(calcBlockPartKey(height, index))
+	if len(bz) == 0 {
 		return nil
 	}
-	part := wire.ReadBinary(&types.Part{}, r, 0, &n, &err).(*types.Part)
+	err := cdc.UnmarshalBinaryBare(bz, part)
 	if err != nil {
-		PanicCrisis(Fmt("Error reading block part: %v", err))
+		panic(cmn.ErrorWrap(err, "Error reading block part"))
 	}
 	return part
 }
 
-func (bs *BlockStore) LoadBlockMeta(height int) *types.BlockMeta {
-	var n int
-	var err error
-	r := bs.GetReader(calcBlockMetaKey(height))
-	if r == nil {
+// LoadBlockMeta returns the BlockMeta for the given height.
+// If no block is found for the given height, it returns nil.
+func (bs *BlockStore) LoadBlockMeta(height int64) *types.BlockMeta {
+	var blockMeta = new(types.BlockMeta)
+	bz := bs.db.Get(calcBlockMetaKey(height))
+	if len(bz) == 0 {
 		return nil
 	}
-	blockMeta := wire.ReadBinary(&types.BlockMeta{}, r, 0, &n, &err).(*types.BlockMeta)
+	err := cdc.UnmarshalBinaryBare(bz, blockMeta)
 	if err != nil {
-		PanicCrisis(Fmt("Error reading block meta: %v", err))
+		panic(cmn.ErrorWrap(err, "Error reading block meta"))
 	}
 	return blockMeta
 }
 
-// The +2/3 and other Precommit-votes for block at `height`.
-// This Commit comes from block.LastCommit for `height+1`.
-func (bs *BlockStore) LoadBlockCommit(height int) *types.Commit {
-	var n int
-	var err error
-	r := bs.GetReader(calcBlockCommitKey(height))
-	if r == nil {
+// LoadBlockCommit returns the Commit for the given height.
+// This commit consists of the +2/3 and other Precommit-votes for block at `height`,
+// and it comes from the block.LastCommit for `height+1`.
+// If no commit is found for the given height, it returns nil.
+func (bs *BlockStore) LoadBlockCommit(height int64) *types.Commit {
+	var commit = new(types.Commit)
+	bz := bs.db.Get(calcBlockCommitKey(height))
+	if len(bz) == 0 {
 		return nil
 	}
-	commit := wire.ReadBinary(&types.Commit{}, r, 0, &n, &err).(*types.Commit)
+	err := cdc.UnmarshalBinaryBare(bz, commit)
 	if err != nil {
-		PanicCrisis(Fmt("Error reading commit: %v", err))
+		panic(cmn.ErrorWrap(err, "Error reading block commit"))
 	}
 	return commit
 }
 
-// NOTE: the Precommit-vote heights are for the block at `height`
-func (bs *BlockStore) LoadSeenCommit(height int) *types.Commit {
-	var n int
-	var err error
-	r := bs.GetReader(calcSeenCommitKey(height))
-	if r == nil {
+// LoadSeenCommit returns the locally seen Commit for the given height.
+// This is useful when we've seen a commit, but there has not yet been
+// a new block at `height + 1` that includes this commit in its block.LastCommit.
+func (bs *BlockStore) LoadSeenCommit(height int64) *types.Commit {
+	var commit = new(types.Commit)
+	bz := bs.db.Get(calcSeenCommitKey(height))
+	if len(bz) == 0 {
 		return nil
 	}
-	commit := wire.ReadBinary(&types.Commit{}, r, 0, &n, &err).(*types.Commit)
+	err := cdc.UnmarshalBinaryBare(bz, commit)
 	if err != nil {
-		PanicCrisis(Fmt("Error reading commit: %v", err))
+		panic(cmn.ErrorWrap(err, "Error reading block seen commit"))
 	}
 	return commit
 }
 
+// SaveBlock persists the given block, blockParts, and seenCommit to the underlying db.
 // blockParts: Must be parts of the block
 // seenCommit: The +2/3 precommits that were seen which committed at height.
 //             If all the nodes restart after committing a block,
 //             we need this to reload the precommits to catch-up nodes to the
 //             most recent height.  Otherwise they'd stall at H-1.
 func (bs *BlockStore) SaveBlock(block *types.Block, blockParts *types.PartSet, seenCommit *types.Commit) {
+	if block == nil {
+		cmn.PanicSanity("BlockStore can only save a non-nil block")
+	}
 	height := block.Height
-	if height != bs.Height()+1 {
-		PanicSanity(Fmt("BlockStore can only save contiguous blocks. Wanted %v, got %v", bs.Height()+1, height))
+	if g, w := height, bs.Height()+1; g != w {
+		cmn.PanicSanity(cmn.Fmt("BlockStore can only save contiguous blocks. Wanted %v, got %v", w, g))
 	}
 	if !blockParts.IsComplete() {
-		PanicSanity(Fmt("BlockStore can only save complete block part sets"))
+		cmn.PanicSanity(cmn.Fmt("BlockStore can only save complete block part sets"))
 	}
 
 	// Save block meta
 	blockMeta := types.NewBlockMeta(block, blockParts)
-	metaBytes := wire.BinaryBytes(blockMeta)
+	metaBytes := cdc.MustMarshalBinaryBare(blockMeta)
 	bs.db.Set(calcBlockMetaKey(height), metaBytes)
 
 	// Save block parts
 	for i := 0; i < blockParts.Total(); i++ {
-		bs.saveBlockPart(height, i, blockParts.GetPart(i))
+		part := blockParts.GetPart(i)
+		bs.saveBlockPart(height, i, part)
 	}
 
 	// Save block commit (duplicate and separate from the Block)
-	blockCommitBytes := wire.BinaryBytes(block.LastCommit)
+	blockCommitBytes := cdc.MustMarshalBinaryBare(block.LastCommit)
 	bs.db.Set(calcBlockCommitKey(height-1), blockCommitBytes)
 
 	// Save seen commit (seen +2/3 precommits for block)
 	// NOTE: we can delete this at a later height
-	seenCommitBytes := wire.BinaryBytes(seenCommit)
+	seenCommitBytes := cdc.MustMarshalBinaryBare(seenCommit)
 	bs.db.Set(calcSeenCommitKey(height), seenCommitBytes)
 
 	// Save new BlockStoreStateJSON descriptor
@@ -184,29 +186,29 @@ func (bs *BlockStore) SaveBlock(block *types.Block, blockParts *types.PartSet, s
 	bs.db.SetSync(nil, nil)
 }
 
-func (bs *BlockStore) saveBlockPart(height int, index int, part *types.Part) {
+func (bs *BlockStore) saveBlockPart(height int64, index int, part *types.Part) {
 	if height != bs.Height()+1 {
-		PanicSanity(Fmt("BlockStore can only save contiguous blocks. Wanted %v, got %v", bs.Height()+1, height))
+		cmn.PanicSanity(cmn.Fmt("BlockStore can only save contiguous blocks. Wanted %v, got %v", bs.Height()+1, height))
 	}
-	partBytes := wire.BinaryBytes(part)
+	partBytes := cdc.MustMarshalBinaryBare(part)
 	bs.db.Set(calcBlockPartKey(height, index), partBytes)
 }
 
 //-----------------------------------------------------------------------------
 
-func calcBlockMetaKey(height int) []byte {
+func calcBlockMetaKey(height int64) []byte {
 	return []byte(fmt.Sprintf("H:%v", height))
 }
 
-func calcBlockPartKey(height int, partIndex int) []byte {
+func calcBlockPartKey(height int64, partIndex int) []byte {
 	return []byte(fmt.Sprintf("P:%v:%v", height, partIndex))
 }
 
-func calcBlockCommitKey(height int) []byte {
+func calcBlockCommitKey(height int64) []byte {
 	return []byte(fmt.Sprintf("C:%v", height))
 }
 
-func calcSeenCommitKey(height int) []byte {
+func calcSeenCommitKey(height int64) []byte {
 	return []byte(fmt.Sprintf("SC:%v", height))
 }
 
@@ -215,28 +217,31 @@ func calcSeenCommitKey(height int) []byte {
 var blockStoreKey = []byte("blockStore")
 
 type BlockStoreStateJSON struct {
-	Height int
+	Height int64 `json:"height"`
 }
 
+// Save persists the blockStore state to the database as JSON.
 func (bsj BlockStoreStateJSON) Save(db dbm.DB) {
-	bytes, err := json.Marshal(bsj)
+	bytes, err := cdc.MarshalJSON(bsj)
 	if err != nil {
-		PanicSanity(Fmt("Could not marshal state bytes: %v", err))
+		cmn.PanicSanity(cmn.Fmt("Could not marshal state bytes: %v", err))
 	}
 	db.SetSync(blockStoreKey, bytes)
 }
 
+// LoadBlockStoreStateJSON returns the BlockStoreStateJSON as loaded from disk.
+// If no BlockStoreStateJSON was previously persisted, it returns the zero value.
 func LoadBlockStoreStateJSON(db dbm.DB) BlockStoreStateJSON {
 	bytes := db.Get(blockStoreKey)
-	if bytes == nil {
+	if len(bytes) == 0 {
 		return BlockStoreStateJSON{
 			Height: 0,
 		}
 	}
 	bsj := BlockStoreStateJSON{}
-	err := json.Unmarshal(bytes, &bsj)
+	err := cdc.UnmarshalJSON(bytes, &bsj)
 	if err != nil {
-		PanicCrisis(Fmt("Could not unmarshal bytes: %X", bytes))
+		panic(fmt.Sprintf("Could not unmarshal bytes: %X", bytes))
 	}
 	return bsj
 }

blockchain/store_test.go

@@ -0,0 +1,383 @@
+package blockchain
+
+import (
+	"bytes"
+	"fmt"
+	"runtime/debug"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"github.com/tendermint/tmlibs/db"
+	"github.com/tendermint/tmlibs/log"
+
+	"github.com/tendermint/tendermint/types"
+)
+
+func TestLoadBlockStoreStateJSON(t *testing.T) {
+	db := db.NewMemDB()
+
+	bsj := &BlockStoreStateJSON{Height: 1000}
+	bsj.Save(db)
+
+	retrBSJ := LoadBlockStoreStateJSON(db)
+
+	assert.Equal(t, *bsj, retrBSJ, "expected the retrieved DBs to match")
+}
+
+func TestNewBlockStore(t *testing.T) {
+	db := db.NewMemDB()
+	db.Set(blockStoreKey, []byte(`{"height": 10000}`))
+	bs := NewBlockStore(db)
+	require.Equal(t, int64(10000), bs.Height(), "failed to properly parse blockstore")
+
+	panicCausers := []struct {
+		data    []byte
+		wantErr string
+	}{
+		{[]byte("artful-doger"), "not unmarshal bytes"},
+		{[]byte(" "), "unmarshal bytes"},
+	}
+
+	for i, tt := range panicCausers {
+		// Expecting a panic here on trying to parse an invalid blockStore
+		_, _, panicErr := doFn(func() (interface{}, error) {
+			db.Set(blockStoreKey, tt.data)
+			_ = NewBlockStore(db)
+			return nil, nil
+		})
+		require.NotNil(t, panicErr, "#%d panicCauser: %q expected a panic", i, tt.data)
+		assert.Contains(t, panicErr.Error(), tt.wantErr, "#%d data: %q", i, tt.data)
+	}
+
+	db.Set(blockStoreKey, nil)
+	bs = NewBlockStore(db)
+	assert.Equal(t, bs.Height(), int64(0), "expecting nil bytes to be unmarshaled alright")
+}
+
+func freshBlockStore() (*BlockStore, db.DB) {
+	db := db.NewMemDB()
+	return NewBlockStore(db), db
+}
+
+var (
+	state, _ = makeStateAndBlockStore(log.NewTMLogger(new(bytes.Buffer)))
+
+	block       = makeBlock(1, state)
+	partSet     = block.MakePartSet(2)
+	part1       = partSet.GetPart(0)
+	part2       = partSet.GetPart(1)
+	seenCommit1 = &types.Commit{Precommits: []*types.Vote{{Height: 10,
+		Timestamp: time.Now().UTC()}}}
+)
+
+// TODO: This test should be simplified ...
+
+func TestBlockStoreSaveLoadBlock(t *testing.T) {
+	state, bs := makeStateAndBlockStore(log.NewTMLogger(new(bytes.Buffer)))
+	require.Equal(t, bs.Height(), int64(0), "initially the height should be zero")
+
+	// check there are no blocks at various heights
+	noBlockHeights := []int64{0, -1, 100, 1000, 2}
+	for i, height := range noBlockHeights {
+		if g := bs.LoadBlock(height); g != nil {
+			t.Errorf("#%d: height(%d) got a block; want nil", i, height)
+		}
+	}
+
+	// save a block
+	block := makeBlock(bs.Height()+1, state)
+	validPartSet := block.MakePartSet(2)
+	seenCommit := &types.Commit{Precommits: []*types.Vote{{Height: 10,
+		Timestamp: time.Now().UTC()}}}
+	bs.SaveBlock(block, partSet, seenCommit)
+	require.Equal(t, bs.Height(), block.Header.Height, "expecting the new height to be changed")
+
+	incompletePartSet := types.NewPartSetFromHeader(types.PartSetHeader{Total: 2})
+	uncontiguousPartSet := types.NewPartSetFromHeader(types.PartSetHeader{Total: 0})
+	uncontiguousPartSet.AddPart(part2, false)
+
+	header1 := types.Header{
+		Height:  1,
+		NumTxs:  100,
+		ChainID: "block_test",
+		Time:    time.Now(),
+	}
+	header2 := header1
+	header2.Height = 4
+
+	// End of setup, test data
+
+	commitAtH10 := &types.Commit{Precommits: []*types.Vote{{Height: 10,
+		Timestamp: time.Now().UTC()}}}
+	tuples := []struct {
+		block      *types.Block
+		parts      *types.PartSet
+		seenCommit *types.Commit
+		wantErr    bool
+		wantPanic  string
+
+		corruptBlockInDB      bool
+		corruptCommitInDB     bool
+		corruptSeenCommitInDB bool
+		eraseCommitInDB       bool
+		eraseSeenCommitInDB   bool
+	}{
+		{
+			block:      newBlock(&header1, commitAtH10),
+			parts:      validPartSet,
+			seenCommit: seenCommit1,
+		},
+
+		{
+			block:     nil,
+			wantPanic: "only save a non-nil block",
+		},
+
+		{
+			block:     newBlock(&header2, commitAtH10),
+			parts:     uncontiguousPartSet,
+			wantPanic: "only save contiguous blocks", // and incomplete and uncontiguous parts
+		},
+
+		{
+			block:     newBlock(&header1, commitAtH10),
+			parts:     incompletePartSet,
+			wantPanic: "only save complete block", // incomplete parts
+		},
+
+		{
+			block:             newBlock(&header1, commitAtH10),
+			parts:             validPartSet,
+			seenCommit:        seenCommit1,
+			corruptCommitInDB: true, // Corrupt the DB's commit entry
+			wantPanic:         "Error reading block commit",
+		},
+
+		{
+			block:            newBlock(&header1, commitAtH10),
+			parts:            validPartSet,
+			seenCommit:       seenCommit1,
+			wantPanic:        "Error reading block",
+			corruptBlockInDB: true, // Corrupt the DB's block entry
+		},
+
+		{
+			block:      newBlock(&header1, commitAtH10),
+			parts:      validPartSet,
+			seenCommit: seenCommit1,
+
+			// Expecting no error and we want a nil back
+			eraseSeenCommitInDB: true,
+		},
+
+		{
+			block:      newBlock(&header1, commitAtH10),
+			parts:      validPartSet,
+			seenCommit: seenCommit1,
+
+			corruptSeenCommitInDB: true,
+			wantPanic:             "Error reading block seen commit",
+		},
+
+		{
+			block:      newBlock(&header1, commitAtH10),
+			parts:      validPartSet,
+			seenCommit: seenCommit1,
+
+			// Expecting no error and we want a nil back
+			eraseCommitInDB: true,
+		},
+	}
+
+	type quad struct {
+		block  *types.Block
+		commit *types.Commit
+		meta   *types.BlockMeta
+
+		seenCommit *types.Commit
+	}
+
+	for i, tuple := range tuples {
+		bs, db := freshBlockStore()
+		// SaveBlock
+		res, err, panicErr := doFn(func() (interface{}, error) {
+			bs.SaveBlock(tuple.block, tuple.parts, tuple.seenCommit)
+			if tuple.block == nil {
+				return nil, nil
+			}
+
+			if tuple.corruptBlockInDB {
+				db.Set(calcBlockMetaKey(tuple.block.Height), []byte("block-bogus"))
+			}
+			bBlock := bs.LoadBlock(tuple.block.Height)
+			bBlockMeta := bs.LoadBlockMeta(tuple.block.Height)
+
+			if tuple.eraseSeenCommitInDB {
+				db.Delete(calcSeenCommitKey(tuple.block.Height))
+			}
+			if tuple.corruptSeenCommitInDB {
+				db.Set(calcSeenCommitKey(tuple.block.Height), []byte("bogus-seen-commit"))
+			}
+			bSeenCommit := bs.LoadSeenCommit(tuple.block.Height)
+
+			commitHeight := tuple.block.Height - 1
+			if tuple.eraseCommitInDB {
+				db.Delete(calcBlockCommitKey(commitHeight))
+			}
+			if tuple.corruptCommitInDB {
+				db.Set(calcBlockCommitKey(commitHeight), []byte("foo-bogus"))
+			}
+			bCommit := bs.LoadBlockCommit(commitHeight)
+			return &quad{block: bBlock, seenCommit: bSeenCommit, commit: bCommit,
+				meta: bBlockMeta}, nil
+		})
+
+		if subStr := tuple.wantPanic; subStr != "" {
+			if panicErr == nil {
+				t.Errorf("#%d: want a non-nil panic", i)
+			} else if got := panicErr.Error(); !strings.Contains(got, subStr) {
+				t.Errorf("#%d:\n\tgotErr: %q\nwant substring: %q", i, got, subStr)
+			}
+			continue
+		}
+
+		if tuple.wantErr {
+			if err == nil {
+				t.Errorf("#%d: got nil error", i)
+			}
+			continue
+		}
+
+		assert.Nil(t, panicErr, "#%d: unexpected panic", i)
+		assert.Nil(t, err, "#%d: expecting a non-nil error", i)
+		qua, ok := res.(*quad)
+		if !ok || qua == nil {
+			t.Errorf("#%d: got nil quad back; gotType=%T", i, res)
+			continue
+		}
+		if tuple.eraseSeenCommitInDB {
+			assert.Nil(t, qua.seenCommit,
+				"erased the seenCommit in the DB hence we should get back a nil seenCommit")
+		}
+		if tuple.eraseCommitInDB {
+			assert.Nil(t, qua.commit,
+				"erased the commit in the DB hence we should get back a nil commit")
+		}
+	}
+}
+
+func TestLoadBlockPart(t *testing.T) {
+	bs, db := freshBlockStore()
+	height, index := int64(10), 1
+	loadPart := func() (interface{}, error) {
+		part := bs.LoadBlockPart(height, index)
+		return part, nil
+	}
+
+	// Initially no contents.
+	// 1. Requesting for a non-existent block shouldn't fail
+	res, _, panicErr := doFn(loadPart)
+	require.Nil(t, panicErr, "a non-existent block part shouldn't cause a panic")
+	require.Nil(t, res, "a non-existent block part should return nil")
+
+	// 2. Next save a corrupted block then try to load it
+	db.Set(calcBlockPartKey(height, index), []byte("Tendermint"))
+	res, _, panicErr = doFn(loadPart)
+	require.NotNil(t, panicErr, "expecting a non-nil panic")
+	require.Contains(t, panicErr.Error(), "Error reading block part")
+
+	// 3. A good block serialized and saved to the DB should be retrievable
+	db.Set(calcBlockPartKey(height, index), cdc.MustMarshalBinaryBare(part1))
+	gotPart, _, panicErr := doFn(loadPart)
+	require.Nil(t, panicErr, "an existent and proper block should not panic")
+	require.Nil(t, res, "a properly saved block should return a proper block")
+	require.Equal(t, gotPart.(*types.Part).Hash(), part1.Hash(),
+		"expecting successful retrieval of previously saved block")
+}
+
+func TestLoadBlockMeta(t *testing.T) {
+	bs, db := freshBlockStore()
+	height := int64(10)
+	loadMeta := func() (interface{}, error) {
+		meta := bs.LoadBlockMeta(height)
+		return meta, nil
+	}
+
+	// Initially no contents.
+	// 1. Requesting for a non-existent blockMeta shouldn't fail
+	res, _, panicErr := doFn(loadMeta)
+	require.Nil(t, panicErr, "a non-existent blockMeta shouldn't cause a panic")
+	require.Nil(t, res, "a non-existent blockMeta should return nil")
+
+	// 2. Next save a corrupted blockMeta then try to load it
+	db.Set(calcBlockMetaKey(height), []byte("Tendermint-Meta"))
+	res, _, panicErr = doFn(loadMeta)
+	require.NotNil(t, panicErr, "expecting a non-nil panic")
+	require.Contains(t, panicErr.Error(), "Error reading block meta")
+
+	// 3. A good blockMeta serialized and saved to the DB should be retrievable
+	meta := &types.BlockMeta{}
+	db.Set(calcBlockMetaKey(height), cdc.MustMarshalBinaryBare(meta))
+	gotMeta, _, panicErr := doFn(loadMeta)
+	require.Nil(t, panicErr, "an existent and proper block should not panic")
+	require.Nil(t, res, "a properly saved blockMeta should return a proper blocMeta ")
+	require.Equal(t, cdc.MustMarshalBinaryBare(meta), cdc.MustMarshalBinaryBare(gotMeta),
+		"expecting successful retrieval of previously saved blockMeta")
+}
+
+func TestBlockFetchAtHeight(t *testing.T) {
+	state, bs := makeStateAndBlockStore(log.NewTMLogger(new(bytes.Buffer)))
+	require.Equal(t, bs.Height(), int64(0), "initially the height should be zero")
+	block := makeBlock(bs.Height()+1, state)
+
+	partSet := block.MakePartSet(2)
+	seenCommit := &types.Commit{Precommits: []*types.Vote{{Height: 10,
+		Timestamp: time.Now().UTC()}}}
+
+	bs.SaveBlock(block, partSet, seenCommit)
+	require.Equal(t, bs.Height(), block.Header.Height, "expecting the new height to be changed")
+
+	blockAtHeight := bs.LoadBlock(bs.Height())
+	bz1 := cdc.MustMarshalBinaryBare(block)
+	bz2 := cdc.MustMarshalBinaryBare(blockAtHeight)
+	require.Equal(t, bz1, bz2)
+	require.Equal(t, block.Hash(), blockAtHeight.Hash(),
+		"expecting a successful load of the last saved block")
+
+	blockAtHeightPlus1 := bs.LoadBlock(bs.Height() + 1)
+	require.Nil(t, blockAtHeightPlus1, "expecting an unsuccessful load of Height()+1")
+	blockAtHeightPlus2 := bs.LoadBlock(bs.Height() + 2)
+	require.Nil(t, blockAtHeightPlus2, "expecting an unsuccessful load of Height()+2")
+}
+
+func doFn(fn func() (interface{}, error)) (res interface{}, err error, panicErr error) {
+	defer func() {
+		if r := recover(); r != nil {
+			switch e := r.(type) {
+			case error:
+				panicErr = e
+			case string:
+				panicErr = fmt.Errorf("%s", e)
+			default:
+				if st, ok := r.(fmt.Stringer); ok {
+					panicErr = fmt.Errorf("%s", st)
+				} else {
+					panicErr = fmt.Errorf("%s", debug.Stack())
+				}
+			}
+		}
+	}()
+
+	res, err = fn()
+	return res, err, panicErr
+}
+
+func newBlock(hdr *types.Header, lastCommit *types.Commit) *types.Block {
+	return &types.Block{
+		Header:     hdr,
+		LastCommit: lastCommit,
+	}
+}

blockchain/wire.go

@@ -0,0 +1,13 @@
+package blockchain
+
+import (
+	amino "github.com/tendermint/go-amino"
+	"github.com/tendermint/go-crypto"
+)
+
+var cdc = amino.NewCodec()
+
+func init() {
+	RegisterBlockchainMessages(cdc)
+	crypto.RegisterAmino(cdc)
+}

circle.yml

@@ -1,33 +0,0 @@
----
-machine:
-  environment:
-    MACH_PREFIX: tendermint-test-mach
-    DOCKER_VERSION: 1.10.0
-    DOCKER_MACHINE_VERSION: 0.9.0
-    GOPATH: "$HOME/.go_project"
-    PROJECT_PARENT_PATH: "$GOPATH/src/github.com/$CIRCLE_PROJECT_USERNAME"
-    PROJECT_PATH: "$PROJECT_PARENT_PATH/$CIRCLE_PROJECT_REPONAME"
-  hosts:
-    localhost: 127.0.0.1
-
-dependencies:
-  override:
-    - curl -sSL https://s3.amazonaws.com/circle-downloads/install-circleci-docker.sh | sudo bash -s -- $DOCKER_VERSION
-    - sudo start docker
-    - sudo curl -sSL -o /usr/bin/docker-machine "https://github.com/docker/machine/releases/download/v$DOCKER_MACHINE_VERSION/docker-machine-`uname -s`-`uname -m`"; sudo chmod 0755 /usr/bin/docker-machine
-    - mkdir -p "$PROJECT_PARENT_PATH"
-    - ln -sf "$HOME/$CIRCLE_PROJECT_REPONAME/" "$PROJECT_PATH"
-  post:
-    - go version
-    - docker version
-    - docker-machine version
-
-test:
-  override:
-    - cd "$PROJECT_PATH" && set -o pipefail && make test_integrations 2>&1 | tee test_integrations.log:
-        timeout: 1800
-  post:
-    - cd "$PROJECT_PATH" && mv test_integrations.log "${CIRCLE_ARTIFACTS}"
-    - cd "$PROJECT_PATH" && bash <(curl -s https://codecov.io/bash) -f coverage.txt
-    - cd "$PROJECT_PATH" && mv coverage.txt "${CIRCLE_ARTIFACTS}"
-    - cd "$PROJECT_PATH" && cp test/logs/messages "${CIRCLE_ARTIFACTS}/docker_logs.txt"

cmd/priv_val_server/main.go

@@ -0,0 +1,53 @@
+package main
+
+import (
+	"flag"
+	"os"
+
+	crypto "github.com/tendermint/go-crypto"
+	cmn "github.com/tendermint/tmlibs/common"
+	"github.com/tendermint/tmlibs/log"
+
+	priv_val "github.com/tendermint/tendermint/types/priv_validator"
+)
+
+func main() {
+	var (
+		addr        = flag.String("addr", ":46659", "Address of client to connect to")
+		chainID     = flag.String("chain-id", "mychain", "chain id")
+		privValPath = flag.String("priv", "", "priv val file path")
+
+		logger = log.NewTMLogger(
+			log.NewSyncWriter(os.Stdout),
+		).With("module", "priv_val")
+	)
+	flag.Parse()
+
+	logger.Info(
+		"Starting private validator",
+		"addr", *addr,
+		"chainID", *chainID,
+		"privPath", *privValPath,
+	)
+
+	privVal := priv_val.LoadFilePV(*privValPath)
+
+	rs := priv_val.NewRemoteSigner(
+		logger,
+		*chainID,
+		*addr,
+		privVal,
+		crypto.GenPrivKeyEd25519(),
+	)
+	err := rs.Start()
+	if err != nil {
+		panic(err)
+	}
+
+	cmn.TrapSignal(func() {
+		err := rs.Stop()
+		if err != nil {
+			panic(err)
+		}
+	})
+}

cmd/tendermint/commands/gen_node_key.go

@@ -0,0 +1,32 @@
+package commands
+
+import (
+	"fmt"
+
+	"github.com/spf13/cobra"
+
+	"github.com/tendermint/tendermint/p2p"
+	cmn "github.com/tendermint/tmlibs/common"
+)
+
+// GenNodeKeyCmd allows the generation of a node key. It prints node's ID to
+// the standard output.
+var GenNodeKeyCmd = &cobra.Command{
+	Use:   "gen_node_key",
+	Short: "Generate a node key for this node and print its ID",
+	RunE:  genNodeKey,
+}
+
+func genNodeKey(cmd *cobra.Command, args []string) error {
+	nodeKeyFile := config.NodeKeyFile()
+	if cmn.FileExists(nodeKeyFile) {
+		return fmt.Errorf("node key at %s already exists", nodeKeyFile)
+	}
+
+	nodeKey, err := p2p.LoadOrGenNodeKey(nodeKeyFile)
+	if err != nil {
+		return err
+	}
+	fmt.Println(nodeKey.ID())
+	return nil
+}

cmd/tendermint/commands/gen_validator.go

@@ -5,23 +5,23 @@ import (
 
 	"github.com/spf13/cobra"
 
-	"github.com/tendermint/go-wire"
-	"github.com/tendermint/tendermint/types"
+	pvm "github.com/tendermint/tendermint/types/priv_validator"
 )
 
-var genValidatorCmd = &cobra.Command{
+// GenValidatorCmd allows the generation of a keypair for a
+// validator.
+var GenValidatorCmd = &cobra.Command{
 	Use:   "gen_validator",
 	Short: "Generate new validator keypair",
 	Run:   genValidator,
 }
 
-func init() {
-	RootCmd.AddCommand(genValidatorCmd)
-}
-
 func genValidator(cmd *cobra.Command, args []string) {
-	privValidator := types.GenPrivValidator()
-	privValidatorJSONBytes := wire.JSONBytesPretty(privValidator)
+	pv := pvm.GenFilePV("")
+	jsbz, err := cdc.MarshalJSON(pv)
+	if err != nil {
+		panic(err)
+	}
 	fmt.Printf(`%v
-`, string(privValidatorJSONBytes))
+`, string(jsbz))
 }

cmd/tendermint/commands/init.go

@@ -1,47 +1,67 @@
 package commands
 
 import (
-	"os"
-
 	"github.com/spf13/cobra"
 
-	cmn "github.com/tendermint/go-common"
+	cfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tendermint/p2p"
 	"github.com/tendermint/tendermint/types"
+	pvm "github.com/tendermint/tendermint/types/priv_validator"
+	cmn "github.com/tendermint/tmlibs/common"
 )
 
-var initFilesCmd = &cobra.Command{
+// InitFilesCmd initialises a fresh Tendermint Core instance.
+var InitFilesCmd = &cobra.Command{
 	Use:   "init",
 	Short: "Initialize Tendermint",
-	Run:   initFiles,
+	RunE:  initFiles,
 }
 
-func init() {
-	RootCmd.AddCommand(initFilesCmd)
+func initFiles(cmd *cobra.Command, args []string) error {
+	return initFilesWithConfig(config)
 }
 
-func initFiles(cmd *cobra.Command, args []string) {
-	privValFile := config.GetString("priv_validator_file")
-	if _, err := os.Stat(privValFile); os.IsNotExist(err) {
-		privValidator := types.GenPrivValidator()
-		privValidator.SetFile(privValFile)
-		privValidator.Save()
-
-		genFile := config.GetString("genesis_file")
-
-		if _, err := os.Stat(genFile); os.IsNotExist(err) {
-			genDoc := types.GenesisDoc{
-				ChainID: cmn.Fmt("test-chain-%v", cmn.RandStr(6)),
-			}
-			genDoc.Validators = []types.GenesisValidator{types.GenesisValidator{
-				PubKey: privValidator.PubKey,
-				Amount: 10,
-			}}
-
-			genDoc.SaveAs(genFile)
-		}
-
-		log.Notice("Initialized tendermint", "genesis", config.GetString("genesis_file"), "priv_validator", config.GetString("priv_validator_file"))
+func initFilesWithConfig(config *cfg.Config) error {
+	// private validator
+	privValFile := config.PrivValidatorFile()
+	var pv *pvm.FilePV
+	if cmn.FileExists(privValFile) {
+		pv = pvm.LoadFilePV(privValFile)
+		logger.Info("Found private validator", "path", privValFile)
 	} else {
-		log.Notice("Already initialized", "priv_validator", config.GetString("priv_validator_file"))
+		pv = pvm.GenFilePV(privValFile)
+		pv.Save()
+		logger.Info("Generated private validator", "path", privValFile)
 	}
+
+	nodeKeyFile := config.NodeKeyFile()
+	if cmn.FileExists(nodeKeyFile) {
+		logger.Info("Found node key", "path", nodeKeyFile)
+	} else {
+		if _, err := p2p.LoadOrGenNodeKey(nodeKeyFile); err != nil {
+			return err
+		}
+		logger.Info("Generated node key", "path", nodeKeyFile)
+	}
+
+	// genesis file
+	genFile := config.GenesisFile()
+	if cmn.FileExists(genFile) {
+		logger.Info("Found genesis file", "path", genFile)
+	} else {
+		genDoc := types.GenesisDoc{
+			ChainID: cmn.Fmt("test-chain-%v", cmn.RandStr(6)),
+		}
+		genDoc.Validators = []types.GenesisValidator{{
+			PubKey: pv.GetPubKey(),
+			Power:  10,
+		}}
+
+		if err := genDoc.SaveAs(genFile); err != nil {
+			return err
+		}
+		logger.Info("Generated genesis file", "path", genFile)
+	}
+
+	return nil
 }

cmd/tendermint/commands/lite.go

@@ -0,0 +1,87 @@
+package commands
+
+import (
+	"fmt"
+	"net/url"
+
+	"github.com/spf13/cobra"
+
+	cmn "github.com/tendermint/tmlibs/common"
+
+	"github.com/tendermint/tendermint/lite/proxy"
+	rpcclient "github.com/tendermint/tendermint/rpc/client"
+)
+
+// LiteCmd represents the base command when called without any subcommands
+var LiteCmd = &cobra.Command{
+	Use:   "lite",
+	Short: "Run lite-client proxy server, verifying tendermint rpc",
+	Long: `This node will run a secure proxy to a tendermint rpc server.
+
+All calls that can be tracked back to a block header by a proof
+will be verified before passing them back to the caller. Other that
+that it will present the same interface as a full tendermint node,
+just with added trust and running locally.`,
+	RunE:         runProxy,
+	SilenceUsage: true,
+}
+
+var (
+	listenAddr string
+	nodeAddr   string
+	chainID    string
+	home       string
+)
+
+func init() {
+	LiteCmd.Flags().StringVar(&listenAddr, "laddr", "tcp://localhost:8888", "Serve the proxy on the given address")
+	LiteCmd.Flags().StringVar(&nodeAddr, "node", "tcp://localhost:46657", "Connect to a Tendermint node at this address")
+	LiteCmd.Flags().StringVar(&chainID, "chain-id", "tendermint", "Specify the Tendermint chain ID")
+	LiteCmd.Flags().StringVar(&home, "home-dir", ".tendermint-lite", "Specify the home directory")
+}
+
+func ensureAddrHasSchemeOrDefaultToTCP(addr string) (string, error) {
+	u, err := url.Parse(addr)
+	if err != nil {
+		return "", err
+	}
+	switch u.Scheme {
+	case "tcp", "unix":
+	case "":
+		u.Scheme = "tcp"
+	default:
+		return "", fmt.Errorf("unknown scheme %q, use either tcp or unix", u.Scheme)
+	}
+	return u.String(), nil
+}
+
+func runProxy(cmd *cobra.Command, args []string) error {
+	nodeAddr, err := ensureAddrHasSchemeOrDefaultToTCP(nodeAddr)
+	if err != nil {
+		return err
+	}
+	listenAddr, err := ensureAddrHasSchemeOrDefaultToTCP(listenAddr)
+	if err != nil {
+		return err
+	}
+
+	// First, connect a client
+	node := rpcclient.NewHTTP(nodeAddr, "/websocket")
+
+	cert, err := proxy.GetCertifier(chainID, home, nodeAddr)
+	if err != nil {
+		return err
+	}
+	sc := proxy.SecureClient(node, cert)
+
+	err = proxy.StartProxy(sc, listenAddr, logger)
+	if err != nil {
+		return err
+	}
+
+	cmn.TrapSignal(func() {
+		// TODO: close up shop
+	})
+
+	return nil
+}

cmd/tendermint/commands/probe_upnp.go

@@ -1,36 +1,31 @@
 package commands
 
 import (
-	"encoding/json"
 	"fmt"
 
 	"github.com/spf13/cobra"
 
-	"github.com/tendermint/go-p2p/upnp"
+	"github.com/tendermint/tendermint/p2p/upnp"
 )
 
-var probeUpnpCmd = &cobra.Command{
+// ProbeUpnpCmd adds capabilities to test the UPnP functionality.
+var ProbeUpnpCmd = &cobra.Command{
 	Use:   "probe_upnp",
 	Short: "Test UPnP functionality",
-	Run:   probeUpnp,
+	RunE:  probeUpnp,
 }
 
-func init() {
-	RootCmd.AddCommand(probeUpnpCmd)
-}
-
-func probeUpnp(cmd *cobra.Command, args []string) {
-
-	capabilities, err := upnp.Probe()
+func probeUpnp(cmd *cobra.Command, args []string) error {
+	capabilities, err := upnp.Probe(logger)
 	if err != nil {
-		fmt.Println("Probe failed: %v", err)
+		fmt.Println("Probe failed: ", err)
 	} else {
 		fmt.Println("Probe success!")
-		jsonBytes, err := json.Marshal(capabilities)
+		jsonBytes, err := cdc.MarshalJSON(capabilities)
 		if err != nil {
-			panic(err)
+			return err
 		}
 		fmt.Println(string(jsonBytes))
 	}
-
+	return nil
 }

cmd/tendermint/commands/replay.go

@@ -1,40 +1,26 @@
 package commands
 
 import (
-	"fmt"
+	"github.com/spf13/cobra"
 
 	"github.com/tendermint/tendermint/consensus"
-
-	"github.com/spf13/cobra"
 )
 
-var replayCmd = &cobra.Command{
-	Use:   "replay [walfile]",
+// ReplayCmd allows replaying of messages from the WAL.
+var ReplayCmd = &cobra.Command{
+	Use:   "replay",
 	Short: "Replay messages from WAL",
 	Run: func(cmd *cobra.Command, args []string) {
-
-		if len(args) > 1 {
-			consensus.RunReplayFile(config, args[1], false)
-		} else {
-			fmt.Println("replay requires an argument (walfile)")
-		}
+		consensus.RunReplayFile(config.BaseConfig, config.Consensus, false)
 	},
 }
 
-var replayConsoleCmd = &cobra.Command{
-	Use:   "replay_console [walfile]",
+// ReplayConsoleCmd allows replaying of messages from the WAL in a
+// console.
+var ReplayConsoleCmd = &cobra.Command{
+	Use:   "replay_console",
 	Short: "Replay messages from WAL in a console",
 	Run: func(cmd *cobra.Command, args []string) {
-
-		if len(args) > 1 {
-			consensus.RunReplayFile(config, args[1], true)
-		} else {
-			fmt.Println("replay_console requires an argument (walfile)")
-		}
+		consensus.RunReplayFile(config.BaseConfig, config.Consensus, true)
 	},
 }
-
-func init() {
-	RootCmd.AddCommand(replayCmd)
-	RootCmd.AddCommand(replayConsoleCmd)
-}

cmd/tendermint/commands/reset_priv_validator.go

@@ -5,58 +5,57 @@ import (
 
 	"github.com/spf13/cobra"
 
-	cfg "github.com/tendermint/go-config"
-	"github.com/tendermint/log15"
-	"github.com/tendermint/tendermint/types"
+	pvm "github.com/tendermint/tendermint/types/priv_validator"
+	"github.com/tendermint/tmlibs/log"
 )
 
-var resetAllCmd = &cobra.Command{
+// ResetAllCmd removes the database of this Tendermint core
+// instance.
+var ResetAllCmd = &cobra.Command{
 	Use:   "unsafe_reset_all",
 	Short: "(unsafe) Remove all the data and WAL, reset this node's validator",
 	Run:   resetAll,
 }
 
-var resetPrivValidatorCmd = &cobra.Command{
+// ResetPrivValidatorCmd resets the private validator files.
+var ResetPrivValidatorCmd = &cobra.Command{
 	Use:   "unsafe_reset_priv_validator",
 	Short: "(unsafe) Reset this node's validator",
 	Run:   resetPrivValidator,
 }
 
-func init() {
-	RootCmd.AddCommand(resetAllCmd)
-	RootCmd.AddCommand(resetPrivValidatorCmd)
+// ResetAll removes the privValidator files.
+// Exported so other CLI tools can use it.
+func ResetAll(dbDir, privValFile string, logger log.Logger) {
+	resetFilePV(privValFile, logger)
+	if err := os.RemoveAll(dbDir); err != nil {
+		logger.Error("Error removing directory", "err", err)
+		return
+	}
+	logger.Info("Removed all data", "dir", dbDir)
 }
 
 // XXX: this is totally unsafe.
 // it's only suitable for testnets.
 func resetAll(cmd *cobra.Command, args []string) {
-	ResetAll(config, log)
+	ResetAll(config.DBDir(), config.PrivValidatorFile(), logger)
 }
 
 // XXX: this is totally unsafe.
 // it's only suitable for testnets.
 func resetPrivValidator(cmd *cobra.Command, args []string) {
-	ResetPrivValidator(config, log)
+	resetFilePV(config.PrivValidatorFile(), logger)
 }
 
-// Exported so other CLI tools can use  it
-func ResetAll(c cfg.Config, l log15.Logger) {
-	ResetPrivValidator(c, l)
-	os.RemoveAll(c.GetString("db_dir"))
-}
-
-func ResetPrivValidator(c cfg.Config, l log15.Logger) {
+func resetFilePV(privValFile string, logger log.Logger) {
 	// Get PrivValidator
-	var privValidator *types.PrivValidator
-	privValidatorFile := c.GetString("priv_validator_file")
-	if _, err := os.Stat(privValidatorFile); err == nil {
-		privValidator = types.LoadPrivValidator(privValidatorFile)
-		privValidator.Reset()
-		l.Notice("Reset PrivValidator", "file", privValidatorFile)
+	if _, err := os.Stat(privValFile); err == nil {
+		pv := pvm.LoadFilePV(privValFile)
+		pv.Reset()
+		logger.Info("Reset PrivValidator", "file", privValFile)
 	} else {
-		privValidator = types.GenPrivValidator()
-		privValidator.SetFile(privValidatorFile)
-		privValidator.Save()
-		l.Notice("Generated PrivValidator", "file", privValidatorFile)
+		pv := pvm.GenFilePV(privValFile)
+		pv.Save()
+		logger.Info("Generated PrivValidator", "file", privValFile)
 	}
 }

cmd/tendermint/commands/root.go

@@ -1,31 +1,63 @@
 package commands
 
 import (
-	"github.com/spf13/cobra"
+	"os"
 
-	"github.com/tendermint/go-logger"
-	tmcfg "github.com/tendermint/tendermint/config/tendermint"
+	"github.com/spf13/cobra"
+	"github.com/spf13/viper"
+
+	cfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tmlibs/cli"
+	tmflags "github.com/tendermint/tmlibs/cli/flags"
+	"github.com/tendermint/tmlibs/log"
 )
 
 var (
-	config = tmcfg.GetConfig("")
-	log    = logger.New("module", "main")
+	config = cfg.DefaultConfig()
+	logger = log.NewTMLogger(log.NewSyncWriter(os.Stdout))
 )
 
-//global flag
-var logLevel string
+func init() {
+	registerFlagsRootCmd(RootCmd)
+}
 
+func registerFlagsRootCmd(cmd *cobra.Command) {
+	cmd.PersistentFlags().String("log_level", config.LogLevel, "Log level")
+}
+
+// ParseConfig retrieves the default environment configuration,
+// sets up the Tendermint root and ensures that the root exists
+func ParseConfig() (*cfg.Config, error) {
+	conf := cfg.DefaultConfig()
+	err := viper.Unmarshal(conf)
+	if err != nil {
+		return nil, err
+	}
+	conf.SetRoot(conf.RootDir)
+	cfg.EnsureRoot(conf.RootDir)
+	return conf, err
+}
+
+// RootCmd is the root command for Tendermint core.
 var RootCmd = &cobra.Command{
 	Use:   "tendermint",
 	Short: "Tendermint Core (BFT Consensus) in Go",
-	PersistentPreRun: func(cmd *cobra.Command, args []string) {
-		// set the log level in the config and logger
-		config.Set("log_level", logLevel)
-		logger.SetLogLevel(logLevel)
+	PersistentPreRunE: func(cmd *cobra.Command, args []string) (err error) {
+		if cmd.Name() == VersionCmd.Name() {
+			return nil
+		}
+		config, err = ParseConfig()
+		if err != nil {
+			return err
+		}
+		logger, err = tmflags.ParseLogLevel(config.LogLevel, logger, cfg.DefaultLogLevel())
+		if err != nil {
+			return err
+		}
+		if viper.GetBool(cli.TraceFlag) {
+			logger = log.NewTracingLogger(logger)
+		}
+		logger = logger.With("module", "main")
+		return nil
 	},
 }
-
-func init() {
-	//parse flag and set config
-	RootCmd.PersistentFlags().StringVar(&logLevel, "log_level", config.GetString("log_level"), "Log level")
-}

cmd/tendermint/commands/root_test.go

@@ -0,0 +1,176 @@
+package commands
+
+import (
+	"fmt"
+	"io/ioutil"
+	"os"
+	"path/filepath"
+	"strconv"
+	"testing"
+
+	"github.com/spf13/cobra"
+	"github.com/spf13/viper"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	cfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tmlibs/cli"
+	cmn "github.com/tendermint/tmlibs/common"
+)
+
+var (
+	defaultRoot = os.ExpandEnv("$HOME/.some/test/dir")
+)
+
+const (
+	rootName = "root"
+)
+
+// clearConfig clears env vars, the given root dir, and resets viper.
+func clearConfig(dir string) {
+	if err := os.Unsetenv("TMHOME"); err != nil {
+		panic(err)
+	}
+	if err := os.Unsetenv("TM_HOME"); err != nil {
+		panic(err)
+	}
+
+	if err := os.RemoveAll(dir); err != nil {
+		panic(err)
+	}
+	viper.Reset()
+	config = cfg.DefaultConfig()
+}
+
+// prepare new rootCmd
+func testRootCmd() *cobra.Command {
+	rootCmd := &cobra.Command{
+		Use:               RootCmd.Use,
+		PersistentPreRunE: RootCmd.PersistentPreRunE,
+		Run:               func(cmd *cobra.Command, args []string) {},
+	}
+	registerFlagsRootCmd(rootCmd)
+	var l string
+	rootCmd.PersistentFlags().String("log", l, "Log")
+	return rootCmd
+}
+
+func testSetup(rootDir string, args []string, env map[string]string) error {
+	clearConfig(defaultRoot)
+
+	rootCmd := testRootCmd()
+	cmd := cli.PrepareBaseCmd(rootCmd, "TM", defaultRoot)
+
+	// run with the args and env
+	args = append([]string{rootCmd.Use}, args...)
+	return cli.RunWithArgs(cmd, args, env)
+}
+
+func TestRootHome(t *testing.T) {
+	newRoot := filepath.Join(defaultRoot, "something-else")
+	cases := []struct {
+		args []string
+		env  map[string]string
+		root string
+	}{
+		{nil, nil, defaultRoot},
+		{[]string{"--home", newRoot}, nil, newRoot},
+		{nil, map[string]string{"TMHOME": newRoot}, newRoot},
+	}
+
+	for i, tc := range cases {
+		idxString := strconv.Itoa(i)
+
+		err := testSetup(defaultRoot, tc.args, tc.env)
+		require.Nil(t, err, idxString)
+
+		assert.Equal(t, tc.root, config.RootDir, idxString)
+		assert.Equal(t, tc.root, config.P2P.RootDir, idxString)
+		assert.Equal(t, tc.root, config.Consensus.RootDir, idxString)
+		assert.Equal(t, tc.root, config.Mempool.RootDir, idxString)
+	}
+}
+
+func TestRootFlagsEnv(t *testing.T) {
+
+	// defaults
+	defaults := cfg.DefaultConfig()
+	defaultLogLvl := defaults.LogLevel
+
+	cases := []struct {
+		args     []string
+		env      map[string]string
+		logLevel string
+	}{
+		{[]string{"--log", "debug"}, nil, defaultLogLvl},                 // wrong flag
+		{[]string{"--log_level", "debug"}, nil, "debug"},                 // right flag
+		{nil, map[string]string{"TM_LOW": "debug"}, defaultLogLvl},       // wrong env flag
+		{nil, map[string]string{"MT_LOG_LEVEL": "debug"}, defaultLogLvl}, // wrong env prefix
+		{nil, map[string]string{"TM_LOG_LEVEL": "debug"}, "debug"},       // right env
+	}
+
+	for i, tc := range cases {
+		idxString := strconv.Itoa(i)
+
+		err := testSetup(defaultRoot, tc.args, tc.env)
+		require.Nil(t, err, idxString)
+
+		assert.Equal(t, tc.logLevel, config.LogLevel, idxString)
+	}
+}
+
+func TestRootConfig(t *testing.T) {
+
+	// write non-default config
+	nonDefaultLogLvl := "abc:debug"
+	cvals := map[string]string{
+		"log_level": nonDefaultLogLvl,
+	}
+
+	cases := []struct {
+		args []string
+		env  map[string]string
+
+		logLvl string
+	}{
+		{nil, nil, nonDefaultLogLvl},                                     // should load config
+		{[]string{"--log_level=abc:info"}, nil, "abc:info"},              // flag over rides
+		{nil, map[string]string{"TM_LOG_LEVEL": "abc:info"}, "abc:info"}, // env over rides
+	}
+
+	for i, tc := range cases {
+		idxString := strconv.Itoa(i)
+		clearConfig(defaultRoot)
+
+		// XXX: path must match cfg.defaultConfigPath
+		configFilePath := filepath.Join(defaultRoot, "config")
+		err := cmn.EnsureDir(configFilePath, 0700)
+		require.Nil(t, err)
+
+		// write the non-defaults to a different path
+		// TODO: support writing sub configs so we can test that too
+		err = WriteConfigVals(configFilePath, cvals)
+		require.Nil(t, err)
+
+		rootCmd := testRootCmd()
+		cmd := cli.PrepareBaseCmd(rootCmd, "TM", defaultRoot)
+
+		// run with the args and env
+		tc.args = append([]string{rootCmd.Use}, tc.args...)
+		err = cli.RunWithArgs(cmd, tc.args, tc.env)
+		require.Nil(t, err, idxString)
+
+		assert.Equal(t, tc.logLvl, config.LogLevel, idxString)
+	}
+}
+
+// WriteConfigVals writes a toml file with the given values.
+// It returns an error if writing was impossible.
+func WriteConfigVals(dir string, vals map[string]string) error {
+	data := ""
+	for k, v := range vals {
+		data = data + fmt.Sprintf("%s = \"%s\"\n", k, v)
+	}
+	cfile := filepath.Join(dir, "config.toml")
+	return ioutil.WriteFile(cfile, []byte(data), 0666)
+}

cmd/tendermint/commands/run_node.go

@@ -1,124 +1,72 @@
 package commands
 
 import (
-	"io/ioutil"
-	"time"
+	"fmt"
 
 	"github.com/spf13/cobra"
 
-	. "github.com/tendermint/go-common"
-	"github.com/tendermint/tendermint/node"
-	"github.com/tendermint/tendermint/types"
+	nm "github.com/tendermint/tendermint/node"
 )
 
-var runNodeCmd = &cobra.Command{
-	Use:    "node",
-	Short:  "Run the tendermint node",
-	PreRun: setConfigFlags,
-	Run:    runNode,
+// AddNodeFlags exposes some common configuration options on the command-line
+// These are exposed for convenience of commands embedding a tendermint node
+func AddNodeFlags(cmd *cobra.Command) {
+	// bind flags
+	cmd.Flags().String("moniker", config.Moniker, "Node Name")
+
+	// priv val flags
+	cmd.Flags().String("priv_validator_laddr", config.PrivValidatorListenAddr, "Socket address to listen on for connections from external priv_validator process")
+
+	// node flags
+	cmd.Flags().Bool("fast_sync", config.FastSync, "Fast blockchain syncing")
+
+	// abci flags
+	cmd.Flags().String("proxy_app", config.ProxyApp, "Proxy app address, or 'nilapp' or 'kvstore' for local testing.")
+	cmd.Flags().String("abci", config.ABCI, "Specify abci transport (socket | grpc)")
+
+	// rpc flags
+	cmd.Flags().String("rpc.laddr", config.RPC.ListenAddress, "RPC listen address. Port required")
+	cmd.Flags().String("rpc.grpc_laddr", config.RPC.GRPCListenAddress, "GRPC listen address (BroadcastTx only). Port required")
+	cmd.Flags().Bool("rpc.unsafe", config.RPC.Unsafe, "Enabled unsafe rpc methods")
+
+	// p2p flags
+	cmd.Flags().String("p2p.laddr", config.P2P.ListenAddress, "Node listen address. (0.0.0.0:0 means any interface, any port)")
+	cmd.Flags().String("p2p.seeds", config.P2P.Seeds, "Comma-delimited ID@host:port seed nodes")
+	cmd.Flags().String("p2p.persistent_peers", config.P2P.PersistentPeers, "Comma-delimited ID@host:port persistent peers")
+	cmd.Flags().Bool("p2p.skip_upnp", config.P2P.SkipUPNP, "Skip UPNP configuration")
+	cmd.Flags().Bool("p2p.pex", config.P2P.PexReactor, "Enable/disable Peer-Exchange")
+	cmd.Flags().Bool("p2p.seed_mode", config.P2P.SeedMode, "Enable/disable seed mode")
+	cmd.Flags().String("p2p.private_peer_ids", config.P2P.PrivatePeerIDs, "Comma-delimited private peer IDs")
+
+	// consensus flags
+	cmd.Flags().Bool("consensus.create_empty_blocks", config.Consensus.CreateEmptyBlocks, "Set this to false to only produce blocks when there are txs or when the AppHash changes")
 }
 
-//flags
-var (
-	moniker       string
-	nodeLaddr     string
-	seeds         string
-	fastSync      bool
-	skipUPNP      bool
-	rpcLaddr      string
-	grpcLaddr     string
-	proxyApp      string
-	abciTransport string
-	pex           bool
-)
-
-func init() {
-
-	// configuration options
-	runNodeCmd.Flags().StringVar(&moniker, "moniker", config.GetString("moniker"),
-		"Node Name")
-	runNodeCmd.Flags().StringVar(&nodeLaddr, "node_laddr", config.GetString("node_laddr"),
-		"Node listen address. (0.0.0.0:0 means any interface, any port)")
-	runNodeCmd.Flags().StringVar(&seeds, "seeds", config.GetString("seeds"),
-		"Comma delimited host:port seed nodes")
-	runNodeCmd.Flags().BoolVar(&fastSync, "fast_sync", config.GetBool("fast_sync"),
-		"Fast blockchain syncing")
-	runNodeCmd.Flags().BoolVar(&skipUPNP, "skip_upnp", config.GetBool("skip_upnp"),
-		"Skip UPNP configuration")
-	runNodeCmd.Flags().StringVar(&rpcLaddr, "rpc_laddr", config.GetString("rpc_laddr"),
-		"RPC listen address. Port required")
-	runNodeCmd.Flags().StringVar(&grpcLaddr, "grpc_laddr", config.GetString("grpc_laddr"),
-		"GRPC listen address (BroadcastTx only). Port required")
-	runNodeCmd.Flags().StringVar(&proxyApp, "proxy_app", config.GetString("proxy_app"),
-		"Proxy app address, or 'nilapp' or 'dummy' for local testing.")
-	runNodeCmd.Flags().StringVar(&abciTransport, "abci", config.GetString("abci"),
-		"Specify abci transport (socket | grpc)")
-
-	// feature flags
-	runNodeCmd.Flags().BoolVar(&pex, "pex", config.GetBool("pex_reactor"),
-		"Enable Peer-Exchange (dev feature)")
-
-	RootCmd.AddCommand(runNodeCmd)
-}
-
-func setConfigFlags(cmd *cobra.Command, args []string) {
-
-	// Merge parsed flag values onto config
-	config.Set("moniker", moniker)
-	config.Set("node_laddr", nodeLaddr)
-	config.Set("seeds", seeds)
-	config.Set("fast_sync", fastSync)
-	config.Set("skip_upnp", skipUPNP)
-	config.Set("rpc_laddr", rpcLaddr)
-	config.Set("grpc_laddr", grpcLaddr)
-	config.Set("proxy_app", proxyApp)
-	config.Set("abci", abciTransport)
-	config.Set("pex_reactor", pex)
-}
-
-// Users wishing to:
-//	* Use an external signer for their validators
-//	* Supply an in-proc abci app
-// should import github.com/tendermint/tendermint/node and implement
-// their own run_node to call node.NewNode (instead of node.NewNodeDefault)
-// with their custom priv validator and/or custom proxy.ClientCreator
-func runNode(cmd *cobra.Command, args []string) {
-
-	// Wait until the genesis doc becomes available
-	// This is for Mintnet compatibility.
-	// TODO: If Mintnet gets deprecated or genesis_file is
-	// always available, remove.
-	genDocFile := config.GetString("genesis_file")
-	if !FileExists(genDocFile) {
-		log.Notice(Fmt("Waiting for genesis file %v...", genDocFile))
-		for {
-			time.Sleep(time.Second)
-			if !FileExists(genDocFile) {
-				continue
-			}
-			jsonBlob, err := ioutil.ReadFile(genDocFile)
+// NewRunNodeCmd returns the command that allows the CLI to start a node.
+// It can be used with a custom PrivValidator and in-process ABCI application.
+func NewRunNodeCmd(nodeProvider nm.NodeProvider) *cobra.Command {
+	cmd := &cobra.Command{
+		Use:   "node",
+		Short: "Run the tendermint node",
+		RunE: func(cmd *cobra.Command, args []string) error {
+			// Create & start node
+			n, err := nodeProvider(config, logger)
 			if err != nil {
-				Exit(Fmt("Couldn't read GenesisDoc file: %v", err))
+				return fmt.Errorf("Failed to create node: %v", err)
 			}
-			genDoc, err := types.GenesisDocFromJSON(jsonBlob)
-			if err != nil {
-				Exit(Fmt("Error reading GenesisDoc: %v", err))
+
+			if err := n.Start(); err != nil {
+				return fmt.Errorf("Failed to start node: %v", err)
 			}
-			if genDoc.ChainID == "" {
-				Exit(Fmt("Genesis doc %v must include non-empty chain_id", genDocFile))
-			}
-			config.Set("chain_id", genDoc.ChainID)
-		}
+			logger.Info("Started node", "nodeInfo", n.Switch().NodeInfo())
+
+			// Trap signal, run forever.
+			n.RunForever()
+
+			return nil
+		},
 	}
 
-	// Create & start node
-	n := node.NewNodeDefault(config)
-	if _, err := n.Start(); err != nil {
-		Exit(Fmt("Failed to start node: %v", err))
-	} else {
-		log.Notice("Started node", "nodeInfo", n.Switch().NodeInfo())
-	}
-
-	// Trap signal, run forever.
-	n.RunForever()
+	AddNodeFlags(cmd)
+	return cmd
 }

cmd/tendermint/commands/show_node_id.go

@@ -0,0 +1,27 @@
+package commands
+
+import (
+	"fmt"
+
+	"github.com/spf13/cobra"
+
+	"github.com/tendermint/tendermint/p2p"
+)
+
+// ShowNodeIDCmd dumps node's ID to the standard output.
+var ShowNodeIDCmd = &cobra.Command{
+	Use:   "show_node_id",
+	Short: "Show this node's ID",
+	RunE:  showNodeID,
+}
+
+func showNodeID(cmd *cobra.Command, args []string) error {
+
+	nodeKey, err := p2p.LoadNodeKey(config.NodeKeyFile())
+	if err != nil {
+		return err
+	}
+	fmt.Println(nodeKey.ID())
+
+	return nil
+}

cmd/tendermint/commands/show_validator.go

@@ -5,22 +5,18 @@ import (
 
 	"github.com/spf13/cobra"
 
-	"github.com/tendermint/go-wire"
-	"github.com/tendermint/tendermint/types"
+	privval "github.com/tendermint/tendermint/types/priv_validator"
 )
 
-var showValidatorCmd = &cobra.Command{
+// ShowValidatorCmd adds capabilities for showing the validator info.
+var ShowValidatorCmd = &cobra.Command{
 	Use:   "show_validator",
 	Short: "Show this node's validator info",
 	Run:   showValidator,
 }
 
-func init() {
-	RootCmd.AddCommand(showValidatorCmd)
-}
-
 func showValidator(cmd *cobra.Command, args []string) {
-	privValidatorFile := config.GetString("priv_validator_file")
-	privValidator := types.LoadOrGenPrivValidator(privValidatorFile)
-	fmt.Println(string(wire.JSONBytesPretty(privValidator.PubKey)))
+	privValidator := privval.LoadOrGenFilePV(config.PrivValidatorFile())
+	pubKeyJSONBytes, _ := cdc.MarshalJSON(privValidator.GetPubKey())
+	fmt.Println(string(pubKeyJSONBytes))
 }

cmd/tendermint/commands/testnet.go

@@ -2,57 +2,103 @@ package commands
 
 import (
 	"fmt"
-	"path"
+	"net"
+	"os"
+	"path/filepath"
+	"strings"
 	"time"
 
 	"github.com/spf13/cobra"
 
-	cmn "github.com/tendermint/go-common"
+	cfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tendermint/p2p"
 	"github.com/tendermint/tendermint/types"
+	pvm "github.com/tendermint/tendermint/types/priv_validator"
+	cmn "github.com/tendermint/tmlibs/common"
 )
 
-var testnetFilesCmd = &cobra.Command{
-	Use:   "testnet",
-	Short: "Initialize files for a Tendermint testnet",
-	Run:   testnetFiles,
-}
-
-//flags
 var (
-	nValidators int
-	dataDir     string
+	nValidators    int
+	nNonValidators int
+	outputDir      string
+	nodeDirPrefix  string
+
+	populatePersistentPeers bool
+	hostnamePrefix          string
+	startingIPAddress       string
+	p2pPort                 int
+)
+
+const (
+	nodeDirPerm = 0755
 )
 
 func init() {
-	testnetFilesCmd.Flags().IntVar(&nValidators, "n", 4,
+	TestnetFilesCmd.Flags().IntVar(&nValidators, "v", 4,
 		"Number of validators to initialize the testnet with")
-	testnetFilesCmd.Flags().StringVar(&dataDir, "dir", "mytestnet",
+	TestnetFilesCmd.Flags().IntVar(&nNonValidators, "n", 0,
+		"Number of non-validators to initialize the testnet with")
+	TestnetFilesCmd.Flags().StringVar(&outputDir, "o", "./mytestnet",
 		"Directory to store initialization data for the testnet")
+	TestnetFilesCmd.Flags().StringVar(&nodeDirPrefix, "node-dir-prefix", "node",
+		"Prefix the directory name for each node with (node results in node0, node1, ...)")
 
-	RootCmd.AddCommand(testnetFilesCmd)
+	TestnetFilesCmd.Flags().BoolVar(&populatePersistentPeers, "populate-persistent-peers", true,
+		"Update config of each node with the list of persistent peers build using either hostname-prefix or starting-ip-address")
+	TestnetFilesCmd.Flags().StringVar(&hostnamePrefix, "hostname-prefix", "node",
+		"Hostname prefix (node results in persistent peers list ID0@node0:46656, ID1@node1:46656, ...)")
+	TestnetFilesCmd.Flags().StringVar(&startingIPAddress, "starting-ip-address", "",
+		"Starting IP address (192.168.0.1 results in persistent peers list ID0@192.168.0.1:46656, ID1@192.168.0.2:46656, ...)")
+	TestnetFilesCmd.Flags().IntVar(&p2pPort, "p2p-port", 46656,
+		"P2P Port")
 }
 
-func testnetFiles(cmd *cobra.Command, args []string) {
+// TestnetFilesCmd allows initialisation of files for a Tendermint testnet.
+var TestnetFilesCmd = &cobra.Command{
+	Use:   "testnet",
+	Short: "Initialize files for a Tendermint testnet",
+	RunE:  testnetFiles,
+}
 
+func testnetFiles(cmd *cobra.Command, args []string) error {
+	config := cfg.DefaultConfig()
 	genVals := make([]types.GenesisValidator, nValidators)
 
-	// Initialize core dir and priv_validator.json's
 	for i := 0; i < nValidators; i++ {
-		mach := cmn.Fmt("mach%d", i)
-		err := initMachCoreDirectory(dataDir, mach)
+		nodeDirName := cmn.Fmt("%s%d", nodeDirPrefix, i)
+		nodeDir := filepath.Join(outputDir, nodeDirName)
+		config.SetRoot(nodeDir)
+
+		err := os.MkdirAll(filepath.Join(nodeDir, "config"), nodeDirPerm)
 		if err != nil {
-			cmn.Exit(err.Error())
+			_ = os.RemoveAll(outputDir)
+			return err
 		}
-		// Read priv_validator.json to populate vals
-		privValFile := path.Join(dataDir, mach, "priv_validator.json")
-		privVal := types.LoadPrivValidator(privValFile)
+
+		initFilesWithConfig(config)
+
+		pvFile := filepath.Join(nodeDir, config.BaseConfig.PrivValidator)
+		pv := pvm.LoadFilePV(pvFile)
 		genVals[i] = types.GenesisValidator{
-			PubKey: privVal.PubKey,
-			Amount: 1,
-			Name:   mach,
+			PubKey: pv.GetPubKey(),
+			Power:  1,
+			Name:   nodeDirName,
 		}
 	}
 
+	for i := 0; i < nNonValidators; i++ {
+		nodeDir := filepath.Join(outputDir, cmn.Fmt("%s%d", nodeDirPrefix, i+nValidators))
+		config.SetRoot(nodeDir)
+
+		err := os.MkdirAll(filepath.Join(nodeDir, "config"), nodeDirPerm)
+		if err != nil {
+			_ = os.RemoveAll(outputDir)
+			return err
+		}
+
+		initFilesWithConfig(config)
+	}
+
 	// Generate genesis doc from generated validators
 	genDoc := &types.GenesisDoc{
 		GenesisTime: time.Now(),
@@ -61,33 +107,65 @@ func testnetFiles(cmd *cobra.Command, args []string) {
 	}
 
 	// Write genesis file.
-	for i := 0; i < nValidators; i++ {
-		mach := cmn.Fmt("mach%d", i)
-		genDoc.SaveAs(path.Join(dataDir, mach, "genesis.json"))
+	for i := 0; i < nValidators+nNonValidators; i++ {
+		nodeDir := filepath.Join(outputDir, cmn.Fmt("%s%d", nodeDirPrefix, i))
+		if err := genDoc.SaveAs(filepath.Join(nodeDir, config.BaseConfig.Genesis)); err != nil {
+			_ = os.RemoveAll(outputDir)
+			return err
+		}
 	}
 
-	fmt.Println(cmn.Fmt("Successfully initialized %v node directories", nValidators))
-}
-
-// Initialize per-machine core directory
-func initMachCoreDirectory(base, mach string) error {
-	dir := path.Join(base, mach)
-	err := cmn.EnsureDir(dir, 0777)
-	if err != nil {
-		return err
+	if populatePersistentPeers {
+		err := populatePersistentPeersInConfigAndWriteIt(config)
+		if err != nil {
+			_ = os.RemoveAll(outputDir)
+			return err
+		}
 	}
 
-	// Create priv_validator.json file if not present
-	ensurePrivValidator(path.Join(dir, "priv_validator.json"))
+	fmt.Printf("Successfully initialized %v node directories\n", nValidators+nNonValidators)
 	return nil
-
 }
 
-func ensurePrivValidator(file string) {
-	if cmn.FileExists(file) {
-		return
+func hostnameOrIP(i int) string {
+	if startingIPAddress != "" {
+		ip := net.ParseIP(startingIPAddress)
+		ip = ip.To4()
+		if ip == nil {
+			fmt.Printf("%v: non ipv4 address\n", startingIPAddress)
+			os.Exit(1)
+		}
+
+		for j := 0; j < i; j++ {
+			ip[3]++
+		}
+		return ip.String()
 	}
-	privValidator := types.GenPrivValidator()
-	privValidator.SetFile(file)
-	privValidator.Save()
+
+	return fmt.Sprintf("%s%d", hostnamePrefix, i)
+}
+
+func populatePersistentPeersInConfigAndWriteIt(config *cfg.Config) error {
+	persistentPeers := make([]string, nValidators+nNonValidators)
+	for i := 0; i < nValidators+nNonValidators; i++ {
+		nodeDir := filepath.Join(outputDir, cmn.Fmt("%s%d", nodeDirPrefix, i))
+		config.SetRoot(nodeDir)
+		nodeKey, err := p2p.LoadNodeKey(config.NodeKeyFile())
+		if err != nil {
+			return err
+		}
+		persistentPeers[i] = p2p.IDAddressString(nodeKey.ID(), fmt.Sprintf("%s:%d", hostnameOrIP(i), p2pPort))
+	}
+	persistentPeersList := strings.Join(persistentPeers, ",")
+
+	for i := 0; i < nValidators+nNonValidators; i++ {
+		nodeDir := filepath.Join(outputDir, cmn.Fmt("%s%d", nodeDirPrefix, i))
+		config.SetRoot(nodeDir)
+		config.P2P.PersistentPeers = persistentPeersList
+
+		// overwrite default config
+		cfg.WriteConfigFile(filepath.Join(nodeDir, "config", "config.toml"), config)
+	}
+
+	return nil
 }

cmd/tendermint/commands/version.go

@@ -8,14 +8,11 @@ import (
 	"github.com/tendermint/tendermint/version"
 )
 
-var versionCmd = &cobra.Command{
+// VersionCmd ...
+var VersionCmd = &cobra.Command{
 	Use:   "version",
 	Short: "Show version info",
 	Run: func(cmd *cobra.Command, args []string) {
 		fmt.Println(version.Version)
 	},
 }
-
-func init() {
-	RootCmd.AddCommand(versionCmd)
-}

cmd/tendermint/commands/wire.go

@@ -0,0 +1,12 @@
+package commands
+
+import (
+	amino "github.com/tendermint/go-amino"
+	"github.com/tendermint/go-crypto"
+)
+
+var cdc = amino.NewCodec()
+
+func init() {
+	crypto.RegisterAmino(cdc)
+}

cmd/tendermint/main.go

@@ -1,15 +1,48 @@
 package main
 
 import (
-	"fmt"
 	"os"
+	"path/filepath"
 
-	"github.com/tendermint/tendermint/cmd/tendermint/commands"
+	"github.com/tendermint/tmlibs/cli"
+
+	cmd "github.com/tendermint/tendermint/cmd/tendermint/commands"
+	cfg "github.com/tendermint/tendermint/config"
+	nm "github.com/tendermint/tendermint/node"
 )
 
 func main() {
-	if err := commands.RootCmd.Execute(); err != nil {
-		fmt.Println(err)
-		os.Exit(1)
+	rootCmd := cmd.RootCmd
+	rootCmd.AddCommand(
+		cmd.GenValidatorCmd,
+		cmd.InitFilesCmd,
+		cmd.ProbeUpnpCmd,
+		cmd.LiteCmd,
+		cmd.ReplayCmd,
+		cmd.ReplayConsoleCmd,
+		cmd.ResetAllCmd,
+		cmd.ResetPrivValidatorCmd,
+		cmd.ShowValidatorCmd,
+		cmd.TestnetFilesCmd,
+		cmd.ShowNodeIDCmd,
+		cmd.GenNodeKeyCmd,
+		cmd.VersionCmd)
+
+	// NOTE:
+	// Users wishing to:
+	//	* Use an external signer for their validators
+	//	* Supply an in-proc abci app
+	//	* Supply a genesis doc file from another source
+	//	* Provide their own DB implementation
+	// can copy this file and use something other than the
+	// DefaultNewNode function
+	nodeFunc := nm.DefaultNewNode
+
+	// Create & start node
+	rootCmd.AddCommand(cmd.NewRunNodeCmd(nodeFunc))
+
+	cmd := cli.PrepareBaseCmd(rootCmd, "TM", os.ExpandEnv(filepath.Join("$HOME", cfg.DefaultTendermintDir)))
+	if err := cmd.Execute(); err != nil {
+		panic(err)
 	}
 }

codecov.yml

@@ -0,0 +1,23 @@
+coverage:
+  precision: 2
+  round: down
+  range: "70...100"
+
+  status:
+    project:
+      default:
+        threshold: 1%
+    patch: on
+    changes: off
+
+comment:
+  layout: "diff, files"
+  behavior: default
+  require_changes: no
+  require_base: no
+  require_head: yes
+
+ignore:
+  - "docs"
+  - "DOCKER"
+  - "scripts"

config/config.go

@@ -0,0 +1,555 @@
+package config
+
+import (
+	"fmt"
+	"os"
+	"path/filepath"
+	"time"
+)
+
+// NOTE: Most of the structs & relevant comments + the
+// default configuration options were used to manually
+// generate the config.toml. Please reflect any changes
+// made here in the defaultConfigTemplate constant in
+// config/toml.go
+// NOTE: tmlibs/cli must know to look in the config dir!
+var (
+	DefaultTendermintDir = ".tendermint"
+	defaultConfigDir     = "config"
+	defaultDataDir       = "data"
+
+	defaultConfigFileName  = "config.toml"
+	defaultGenesisJSONName = "genesis.json"
+
+	defaultPrivValName  = "priv_validator.json"
+	defaultNodeKeyName  = "node_key.json"
+	defaultAddrBookName = "addrbook.json"
+
+	defaultConfigFilePath  = filepath.Join(defaultConfigDir, defaultConfigFileName)
+	defaultGenesisJSONPath = filepath.Join(defaultConfigDir, defaultGenesisJSONName)
+	defaultPrivValPath     = filepath.Join(defaultConfigDir, defaultPrivValName)
+	defaultNodeKeyPath     = filepath.Join(defaultConfigDir, defaultNodeKeyName)
+	defaultAddrBookPath    = filepath.Join(defaultConfigDir, defaultAddrBookName)
+)
+
+// Config defines the top level configuration for a Tendermint node
+type Config struct {
+	// Top level options use an anonymous struct
+	BaseConfig `mapstructure:",squash"`
+
+	// Options for services
+	RPC       *RPCConfig       `mapstructure:"rpc"`
+	P2P       *P2PConfig       `mapstructure:"p2p"`
+	Mempool   *MempoolConfig   `mapstructure:"mempool"`
+	Consensus *ConsensusConfig `mapstructure:"consensus"`
+	TxIndex   *TxIndexConfig   `mapstructure:"tx_index"`
+}
+
+// DefaultConfig returns a default configuration for a Tendermint node
+func DefaultConfig() *Config {
+	return &Config{
+		BaseConfig: DefaultBaseConfig(),
+		RPC:        DefaultRPCConfig(),
+		P2P:        DefaultP2PConfig(),
+		Mempool:    DefaultMempoolConfig(),
+		Consensus:  DefaultConsensusConfig(),
+		TxIndex:    DefaultTxIndexConfig(),
+	}
+}
+
+// TestConfig returns a configuration that can be used for testing
+func TestConfig() *Config {
+	return &Config{
+		BaseConfig: TestBaseConfig(),
+		RPC:        TestRPCConfig(),
+		P2P:        TestP2PConfig(),
+		Mempool:    TestMempoolConfig(),
+		Consensus:  TestConsensusConfig(),
+		TxIndex:    TestTxIndexConfig(),
+	}
+}
+
+// SetRoot sets the RootDir for all Config structs
+func (cfg *Config) SetRoot(root string) *Config {
+	cfg.BaseConfig.RootDir = root
+	cfg.RPC.RootDir = root
+	cfg.P2P.RootDir = root
+	cfg.Mempool.RootDir = root
+	cfg.Consensus.RootDir = root
+	return cfg
+}
+
+//-----------------------------------------------------------------------------
+// BaseConfig
+
+// BaseConfig defines the base configuration for a Tendermint node
+type BaseConfig struct {
+
+	// chainID is unexposed and immutable but here for convenience
+	chainID string
+
+	// The root directory for all data.
+	// This should be set in viper so it can unmarshal into this struct
+	RootDir string `mapstructure:"home"`
+
+	// Path to the JSON file containing the initial validator set and other meta data
+	Genesis string `mapstructure:"genesis_file"`
+
+	// Path to the JSON file containing the private key to use as a validator in the consensus protocol
+	PrivValidator string `mapstructure:"priv_validator_file"`
+
+	// A JSON file containing the private key to use for p2p authenticated encryption
+	NodeKey string `mapstructure:"node_key_file"`
+
+	// A custom human readable name for this node
+	Moniker string `mapstructure:"moniker"`
+
+	// TCP or UNIX socket address for Tendermint to listen on for
+	// connections from an external PrivValidator process
+	PrivValidatorListenAddr string `mapstructure:"priv_validator_laddr"`
+
+	// TCP or UNIX socket address of the ABCI application,
+	// or the name of an ABCI application compiled in with the Tendermint binary
+	ProxyApp string `mapstructure:"proxy_app"`
+
+	// Mechanism to connect to the ABCI application: socket | grpc
+	ABCI string `mapstructure:"abci"`
+
+	// Output level for logging
+	LogLevel string `mapstructure:"log_level"`
+
+	// TCP or UNIX socket address for the profiling server to listen on
+	ProfListenAddress string `mapstructure:"prof_laddr"`
+
+	// If this node is many blocks behind the tip of the chain, FastSync
+	// allows them to catchup quickly by downloading blocks in parallel
+	// and verifying their commits
+	FastSync bool `mapstructure:"fast_sync"`
+
+	// If true, query the ABCI app on connecting to a new peer
+	// so the app can decide if we should keep the connection or not
+	FilterPeers bool `mapstructure:"filter_peers"` // false
+
+	// Database backend: leveldb | memdb
+	DBBackend string `mapstructure:"db_backend"`
+
+	// Database directory
+	DBPath string `mapstructure:"db_dir"`
+}
+
+// DefaultBaseConfig returns a default base configuration for a Tendermint node
+func DefaultBaseConfig() BaseConfig {
+	return BaseConfig{
+		Genesis:           defaultGenesisJSONPath,
+		PrivValidator:     defaultPrivValPath,
+		NodeKey:           defaultNodeKeyPath,
+		Moniker:           defaultMoniker,
+		ProxyApp:          "tcp://127.0.0.1:46658",
+		ABCI:              "socket",
+		LogLevel:          DefaultPackageLogLevels(),
+		ProfListenAddress: "",
+		FastSync:          true,
+		FilterPeers:       false,
+		DBBackend:         "leveldb",
+		DBPath:            "data",
+	}
+}
+
+// TestBaseConfig returns a base configuration for testing a Tendermint node
+func TestBaseConfig() BaseConfig {
+	cfg := DefaultBaseConfig()
+	cfg.chainID = "tendermint_test"
+	cfg.ProxyApp = "kvstore"
+	cfg.FastSync = false
+	cfg.DBBackend = "memdb"
+	return cfg
+}
+
+func (cfg BaseConfig) ChainID() string {
+	return cfg.chainID
+}
+
+// GenesisFile returns the full path to the genesis.json file
+func (cfg BaseConfig) GenesisFile() string {
+	return rootify(cfg.Genesis, cfg.RootDir)
+}
+
+// PrivValidatorFile returns the full path to the priv_validator.json file
+func (cfg BaseConfig) PrivValidatorFile() string {
+	return rootify(cfg.PrivValidator, cfg.RootDir)
+}
+
+// NodeKeyFile returns the full path to the node_key.json file
+func (cfg BaseConfig) NodeKeyFile() string {
+	return rootify(cfg.NodeKey, cfg.RootDir)
+}
+
+// DBDir returns the full path to the database directory
+func (cfg BaseConfig) DBDir() string {
+	return rootify(cfg.DBPath, cfg.RootDir)
+}
+
+// DefaultLogLevel returns a default log level of "error"
+func DefaultLogLevel() string {
+	return "error"
+}
+
+// DefaultPackageLogLevels returns a default log level setting so all packages
+// log at "error", while the `state` and `main` packages log at "info"
+func DefaultPackageLogLevels() string {
+	return fmt.Sprintf("main:info,state:info,*:%s", DefaultLogLevel())
+}
+
+//-----------------------------------------------------------------------------
+// RPCConfig
+
+// RPCConfig defines the configuration options for the Tendermint RPC server
+type RPCConfig struct {
+	RootDir string `mapstructure:"home"`
+
+	// TCP or UNIX socket address for the RPC server to listen on
+	ListenAddress string `mapstructure:"laddr"`
+
+	// TCP or UNIX socket address for the gRPC server to listen on
+	// NOTE: This server only supports /broadcast_tx_commit
+	GRPCListenAddress string `mapstructure:"grpc_laddr"`
+
+	// Activate unsafe RPC commands like /dial_persistent_peers and /unsafe_flush_mempool
+	Unsafe bool `mapstructure:"unsafe"`
+}
+
+// DefaultRPCConfig returns a default configuration for the RPC server
+func DefaultRPCConfig() *RPCConfig {
+	return &RPCConfig{
+		ListenAddress:     "tcp://0.0.0.0:46657",
+		GRPCListenAddress: "",
+		Unsafe:            false,
+	}
+}
+
+// TestRPCConfig returns a configuration for testing the RPC server
+func TestRPCConfig() *RPCConfig {
+	cfg := DefaultRPCConfig()
+	cfg.ListenAddress = "tcp://0.0.0.0:36657"
+	cfg.GRPCListenAddress = "tcp://0.0.0.0:36658"
+	cfg.Unsafe = true
+	return cfg
+}
+
+//-----------------------------------------------------------------------------
+// P2PConfig
+
+// P2PConfig defines the configuration options for the Tendermint peer-to-peer networking layer
+type P2PConfig struct {
+	RootDir string `mapstructure:"home"`
+
+	// Address to listen for incoming connections
+	ListenAddress string `mapstructure:"laddr"`
+
+	// Comma separated list of seed nodes to connect to
+	// We only use these if we can’t connect to peers in the addrbook
+	Seeds string `mapstructure:"seeds"`
+
+	// Comma separated list of nodes to keep persistent connections to
+	// Do not add private peers to this list if you don't want them advertised
+	PersistentPeers string `mapstructure:"persistent_peers"`
+
+	// Skip UPNP port forwarding
+	SkipUPNP bool `mapstructure:"skip_upnp"`
+
+	// Path to address book
+	AddrBook string `mapstructure:"addr_book_file"`
+
+	// Set true for strict address routability rules
+	AddrBookStrict bool `mapstructure:"addr_book_strict"`
+
+	// Maximum number of peers to connect to
+	MaxNumPeers int `mapstructure:"max_num_peers"`
+
+	// Time to wait before flushing messages out on the connection, in ms
+	FlushThrottleTimeout int `mapstructure:"flush_throttle_timeout"`
+
+	// Maximum size of a message packet payload, in bytes
+	MaxPacketMsgPayloadSize int `mapstructure:"max_packet_msg_payload_size"`
+
+	// Rate at which packets can be sent, in bytes/second
+	SendRate int64 `mapstructure:"send_rate"`
+
+	// Rate at which packets can be received, in bytes/second
+	RecvRate int64 `mapstructure:"recv_rate"`
+
+	// Set true to enable the peer-exchange reactor
+	PexReactor bool `mapstructure:"pex"`
+
+	// Seed mode, in which node constantly crawls the network and looks for
+	// peers. If another node asks it for addresses, it responds and disconnects.
+	//
+	// Does not work if the peer-exchange reactor is disabled.
+	SeedMode bool `mapstructure:"seed_mode"`
+
+	// Authenticated encryption
+	AuthEnc bool `mapstructure:"auth_enc"`
+
+	// Comma separated list of peer IDs to keep private (will not be gossiped to other peers)
+	PrivatePeerIDs string `mapstructure:"private_peer_ids"`
+}
+
+// DefaultP2PConfig returns a default configuration for the peer-to-peer layer
+func DefaultP2PConfig() *P2PConfig {
+	return &P2PConfig{
+		ListenAddress:           "tcp://0.0.0.0:46656",
+		AddrBook:                defaultAddrBookPath,
+		AddrBookStrict:          true,
+		MaxNumPeers:             50,
+		FlushThrottleTimeout:    100,
+		MaxPacketMsgPayloadSize: 1024,   // 1 kB
+		SendRate:                512000, // 500 kB/s
+		RecvRate:                512000, // 500 kB/s
+		PexReactor:              true,
+		SeedMode:                false,
+		AuthEnc:                 true,
+	}
+}
+
+// TestP2PConfig returns a configuration for testing the peer-to-peer layer
+func TestP2PConfig() *P2PConfig {
+	cfg := DefaultP2PConfig()
+	cfg.ListenAddress = "tcp://0.0.0.0:36656"
+	cfg.SkipUPNP = true
+	cfg.FlushThrottleTimeout = 10
+	return cfg
+}
+
+// AddrBookFile returns the full path to the address book
+func (cfg *P2PConfig) AddrBookFile() string {
+	return rootify(cfg.AddrBook, cfg.RootDir)
+}
+
+//-----------------------------------------------------------------------------
+// MempoolConfig
+
+// MempoolConfig defines the configuration options for the Tendermint mempool
+type MempoolConfig struct {
+	RootDir      string `mapstructure:"home"`
+	Recheck      bool   `mapstructure:"recheck"`
+	RecheckEmpty bool   `mapstructure:"recheck_empty"`
+	Broadcast    bool   `mapstructure:"broadcast"`
+	WalPath      string `mapstructure:"wal_dir"`
+	CacheSize    int    `mapstructure:"cache_size"`
+}
+
+// DefaultMempoolConfig returns a default configuration for the Tendermint mempool
+func DefaultMempoolConfig() *MempoolConfig {
+	return &MempoolConfig{
+		Recheck:      true,
+		RecheckEmpty: true,
+		Broadcast:    true,
+		WalPath:      filepath.Join(defaultDataDir, "mempool.wal"),
+		CacheSize:    100000,
+	}
+}
+
+// TestMempoolConfig returns a configuration for testing the Tendermint mempool
+func TestMempoolConfig() *MempoolConfig {
+	cfg := DefaultMempoolConfig()
+	cfg.CacheSize = 1000
+	return cfg
+}
+
+// WalDir returns the full path to the mempool's write-ahead log
+func (cfg *MempoolConfig) WalDir() string {
+	return rootify(cfg.WalPath, cfg.RootDir)
+}
+
+//-----------------------------------------------------------------------------
+// ConsensusConfig
+
+// ConsensusConfig defines the confuguration for the Tendermint consensus service,
+// including timeouts and details about the WAL and the block structure.
+type ConsensusConfig struct {
+	RootDir  string `mapstructure:"home"`
+	WalPath  string `mapstructure:"wal_file"`
+	WalLight bool   `mapstructure:"wal_light"`
+	walFile  string // overrides WalPath if set
+
+	// All timeouts are in milliseconds
+	TimeoutPropose        int `mapstructure:"timeout_propose"`
+	TimeoutProposeDelta   int `mapstructure:"timeout_propose_delta"`
+	TimeoutPrevote        int `mapstructure:"timeout_prevote"`
+	TimeoutPrevoteDelta   int `mapstructure:"timeout_prevote_delta"`
+	TimeoutPrecommit      int `mapstructure:"timeout_precommit"`
+	TimeoutPrecommitDelta int `mapstructure:"timeout_precommit_delta"`
+	TimeoutCommit         int `mapstructure:"timeout_commit"`
+
+	// Make progress as soon as we have all the precommits (as if TimeoutCommit = 0)
+	SkipTimeoutCommit bool `mapstructure:"skip_timeout_commit"`
+
+	// BlockSize
+	MaxBlockSizeTxs   int `mapstructure:"max_block_size_txs"`
+	MaxBlockSizeBytes int `mapstructure:"max_block_size_bytes"`
+
+	// EmptyBlocks mode and possible interval between empty blocks in seconds
+	CreateEmptyBlocks         bool `mapstructure:"create_empty_blocks"`
+	CreateEmptyBlocksInterval int  `mapstructure:"create_empty_blocks_interval"`
+
+	// Reactor sleep duration parameters are in milliseconds
+	PeerGossipSleepDuration     int `mapstructure:"peer_gossip_sleep_duration"`
+	PeerQueryMaj23SleepDuration int `mapstructure:"peer_query_maj23_sleep_duration"`
+}
+
+// DefaultConsensusConfig returns a default configuration for the consensus service
+func DefaultConsensusConfig() *ConsensusConfig {
+	return &ConsensusConfig{
+		WalPath:                     filepath.Join(defaultDataDir, "cs.wal", "wal"),
+		WalLight:                    false,
+		TimeoutPropose:              3000,
+		TimeoutProposeDelta:         500,
+		TimeoutPrevote:              1000,
+		TimeoutPrevoteDelta:         500,
+		TimeoutPrecommit:            1000,
+		TimeoutPrecommitDelta:       500,
+		TimeoutCommit:               1000,
+		SkipTimeoutCommit:           false,
+		MaxBlockSizeTxs:             10000,
+		MaxBlockSizeBytes:           1, // TODO
+		CreateEmptyBlocks:           true,
+		CreateEmptyBlocksInterval:   0,
+		PeerGossipSleepDuration:     100,
+		PeerQueryMaj23SleepDuration: 2000,
+	}
+}
+
+// TestConsensusConfig returns a configuration for testing the consensus service
+func TestConsensusConfig() *ConsensusConfig {
+	cfg := DefaultConsensusConfig()
+	cfg.TimeoutPropose = 100
+	cfg.TimeoutProposeDelta = 1
+	cfg.TimeoutPrevote = 10
+	cfg.TimeoutPrevoteDelta = 1
+	cfg.TimeoutPrecommit = 10
+	cfg.TimeoutPrecommitDelta = 1
+	cfg.TimeoutCommit = 10
+	cfg.SkipTimeoutCommit = true
+	cfg.PeerGossipSleepDuration = 5
+	cfg.PeerQueryMaj23SleepDuration = 250
+	return cfg
+}
+
+// WaitForTxs returns true if the consensus should wait for transactions before entering the propose step
+func (cfg *ConsensusConfig) WaitForTxs() bool {
+	return !cfg.CreateEmptyBlocks || cfg.CreateEmptyBlocksInterval > 0
+}
+
+// EmptyBlocks returns the amount of time to wait before proposing an empty block or starting the propose timer if there are no txs available
+func (cfg *ConsensusConfig) EmptyBlocksInterval() time.Duration {
+	return time.Duration(cfg.CreateEmptyBlocksInterval) * time.Second
+}
+
+// Propose returns the amount of time to wait for a proposal
+func (cfg *ConsensusConfig) Propose(round int) time.Duration {
+	return time.Duration(cfg.TimeoutPropose+cfg.TimeoutProposeDelta*round) * time.Millisecond
+}
+
+// Prevote returns the amount of time to wait for straggler votes after receiving any +2/3 prevotes
+func (cfg *ConsensusConfig) Prevote(round int) time.Duration {
+	return time.Duration(cfg.TimeoutPrevote+cfg.TimeoutPrevoteDelta*round) * time.Millisecond
+}
+
+// Precommit returns the amount of time to wait for straggler votes after receiving any +2/3 precommits
+func (cfg *ConsensusConfig) Precommit(round int) time.Duration {
+	return time.Duration(cfg.TimeoutPrecommit+cfg.TimeoutPrecommitDelta*round) * time.Millisecond
+}
+
+// Commit returns the amount of time to wait for straggler votes after receiving +2/3 precommits for a single block (ie. a commit).
+func (cfg *ConsensusConfig) Commit(t time.Time) time.Time {
+	return t.Add(time.Duration(cfg.TimeoutCommit) * time.Millisecond)
+}
+
+// PeerGossipSleep returns the amount of time to sleep if there is nothing to send from the ConsensusReactor
+func (cfg *ConsensusConfig) PeerGossipSleep() time.Duration {
+	return time.Duration(cfg.PeerGossipSleepDuration) * time.Millisecond
+}
+
+// PeerQueryMaj23Sleep returns the amount of time to sleep after each VoteSetMaj23Message is sent in the ConsensusReactor
+func (cfg *ConsensusConfig) PeerQueryMaj23Sleep() time.Duration {
+	return time.Duration(cfg.PeerQueryMaj23SleepDuration) * time.Millisecond
+}
+
+// WalFile returns the full path to the write-ahead log file
+func (cfg *ConsensusConfig) WalFile() string {
+	if cfg.walFile != "" {
+		return cfg.walFile
+	}
+	return rootify(cfg.WalPath, cfg.RootDir)
+}
+
+// SetWalFile sets the path to the write-ahead log file
+func (cfg *ConsensusConfig) SetWalFile(walFile string) {
+	cfg.walFile = walFile
+}
+
+//-----------------------------------------------------------------------------
+// TxIndexConfig
+
+// TxIndexConfig defines the confuguration for the transaction
+// indexer, including tags to index.
+type TxIndexConfig struct {
+	// What indexer to use for transactions
+	//
+	// Options:
+	//   1) "null" (default)
+	//   2) "kv" - the simplest possible indexer, backed by key-value storage (defaults to levelDB; see DBBackend).
+	Indexer string `mapstructure:"indexer"`
+
+	// Comma-separated list of tags to index (by default the only tag is tx hash)
+	//
+	// It's recommended to index only a subset of tags due to possible memory
+	// bloat. This is, of course, depends on the indexer's DB and the volume of
+	// transactions.
+	IndexTags string `mapstructure:"index_tags"`
+
+	// When set to true, tells indexer to index all tags. Note this may be not
+	// desirable (see the comment above). IndexTags has a precedence over
+	// IndexAllTags (i.e. when given both, IndexTags will be indexed).
+	IndexAllTags bool `mapstructure:"index_all_tags"`
+}
+
+// DefaultTxIndexConfig returns a default configuration for the transaction indexer.
+func DefaultTxIndexConfig() *TxIndexConfig {
+	return &TxIndexConfig{
+		Indexer:      "kv",
+		IndexTags:    "",
+		IndexAllTags: false,
+	}
+}
+
+// TestTxIndexConfig returns a default configuration for the transaction indexer.
+func TestTxIndexConfig() *TxIndexConfig {
+	return DefaultTxIndexConfig()
+}
+
+//-----------------------------------------------------------------------------
+// Utils
+
+// helper function to make config creation independent of root dir
+func rootify(path, root string) string {
+	if filepath.IsAbs(path) {
+		return path
+	}
+	return filepath.Join(root, path)
+}
+
+//-----------------------------------------------------------------------------
+// Moniker
+
+var defaultMoniker = getDefaultMoniker()
+
+// getDefaultMoniker returns a default moniker, which is the host name. If runtime
+// fails to get the host name, "anonymous" will be returned.
+func getDefaultMoniker() string {
+	moniker, err := os.Hostname()
+	if err != nil {
+		moniker = "anonymous"
+	}
+	return moniker
+}

config/config_test.go

@@ -0,0 +1,28 @@
+package config
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestDefaultConfig(t *testing.T) {
+	assert := assert.New(t)
+
+	// set up some defaults
+	cfg := DefaultConfig()
+	assert.NotNil(cfg.P2P)
+	assert.NotNil(cfg.Mempool)
+	assert.NotNil(cfg.Consensus)
+
+	// check the root dir stuff...
+	cfg.SetRoot("/foo")
+	cfg.Genesis = "bar"
+	cfg.DBPath = "/opt/data"
+	cfg.Mempool.WalPath = "wal/mem/"
+
+	assert.Equal("/foo/bar", cfg.GenesisFile())
+	assert.Equal("/opt/data", cfg.DBDir())
+	assert.Equal("/foo/wal/mem", cfg.Mempool.WalDir())
+
+}

config/tendermint/config.go

@@ -1,125 +0,0 @@
-package tendermint
-
-import (
-	"os"
-	"path"
-	"strings"
-
-	. "github.com/tendermint/go-common"
-	cfg "github.com/tendermint/go-config"
-)
-
-func getTMRoot(rootDir string) string {
-	if rootDir == "" {
-		rootDir = os.Getenv("TMHOME")
-	}
-	if rootDir == "" {
-		// deprecated, use TMHOME (TODO: remove in TM 0.11.0)
-		rootDir = os.Getenv("TMROOT")
-	}
-	if rootDir == "" {
-		rootDir = os.Getenv("HOME") + "/.tendermint"
-	}
-	return rootDir
-}
-
-func initTMRoot(rootDir string) {
-	rootDir = getTMRoot(rootDir)
-	EnsureDir(rootDir, 0700)
-	EnsureDir(rootDir+"/data", 0700)
-
-	configFilePath := path.Join(rootDir, "config.toml")
-
-	// Write default config file if missing.
-	if !FileExists(configFilePath) {
-		// Ask user for moniker
-		// moniker := cfg.Prompt("Type hostname: ", "anonymous")
-		MustWriteFile(configFilePath, []byte(defaultConfig("anonymous")), 0644)
-	}
-}
-
-func GetConfig(rootDir string) cfg.Config {
-	rootDir = getTMRoot(rootDir)
-	initTMRoot(rootDir)
-
-	configFilePath := path.Join(rootDir, "config.toml")
-	mapConfig, err := cfg.ReadMapConfigFromFile(configFilePath)
-	if err != nil {
-		Exit(Fmt("Could not read config: %v", err))
-	}
-
-	// Set defaults or panic
-	if mapConfig.IsSet("chain_id") {
-		Exit("Cannot set 'chain_id' via config.toml")
-	}
-	if mapConfig.IsSet("revision_file") {
-		Exit("Cannot set 'revision_file' via config.toml. It must match what's in the Makefile")
-	}
-	mapConfig.SetRequired("chain_id") // blows up if you try to use it before setting.
-	mapConfig.SetDefault("genesis_file", rootDir+"/genesis.json")
-	mapConfig.SetDefault("proxy_app", "tcp://127.0.0.1:46658")
-	mapConfig.SetDefault("abci", "socket")
-	mapConfig.SetDefault("moniker", "anonymous")
-	mapConfig.SetDefault("node_laddr", "tcp://0.0.0.0:46656")
-	mapConfig.SetDefault("seeds", "")
-	// mapConfig.SetDefault("seeds", "goldenalchemist.chaintest.net:46656")
-	mapConfig.SetDefault("fast_sync", true)
-	mapConfig.SetDefault("skip_upnp", false)
-	mapConfig.SetDefault("addrbook_file", rootDir+"/addrbook.json")
-	mapConfig.SetDefault("addrbook_strict", true) // disable to allow connections locally
-	mapConfig.SetDefault("pex_reactor", false)    // enable for peer exchange
-	mapConfig.SetDefault("priv_validator_file", rootDir+"/priv_validator.json")
-	mapConfig.SetDefault("db_backend", "leveldb")
-	mapConfig.SetDefault("db_dir", rootDir+"/data")
-	mapConfig.SetDefault("log_level", "info")
-	mapConfig.SetDefault("rpc_laddr", "tcp://0.0.0.0:46657")
-	mapConfig.SetDefault("grpc_laddr", "")
-	mapConfig.SetDefault("prof_laddr", "")
-	mapConfig.SetDefault("revision_file", rootDir+"/revision")
-	mapConfig.SetDefault("cs_wal_file", rootDir+"/data/cs.wal/wal")
-	mapConfig.SetDefault("cs_wal_light", false)
-	mapConfig.SetDefault("filter_peers", false)
-
-	mapConfig.SetDefault("block_size", 10000)      // max number of txs
-	mapConfig.SetDefault("block_part_size", 65536) // part size 64K
-	mapConfig.SetDefault("disable_data_hash", false)
-
-	// all timeouts are in ms
-	mapConfig.SetDefault("timeout_handshake", 10000)
-	mapConfig.SetDefault("timeout_propose", 3000)
-	mapConfig.SetDefault("timeout_propose_delta", 500)
-	mapConfig.SetDefault("timeout_prevote", 1000)
-	mapConfig.SetDefault("timeout_prevote_delta", 500)
-	mapConfig.SetDefault("timeout_precommit", 1000)
-	mapConfig.SetDefault("timeout_precommit_delta", 500)
-	mapConfig.SetDefault("timeout_commit", 1000)
-
-	// make progress asap (no `timeout_commit`) on full precommit votes
-	mapConfig.SetDefault("skip_timeout_commit", false)
-	mapConfig.SetDefault("mempool_recheck", true)
-	mapConfig.SetDefault("mempool_recheck_empty", true)
-	mapConfig.SetDefault("mempool_broadcast", true)
-	mapConfig.SetDefault("mempool_wal_dir", rootDir+"/data/mempool.wal")
-
-	mapConfig.SetDefault("tx_index", "kv")
-
-	return mapConfig
-}
-
-var defaultConfigTmpl = `# This is a TOML config file.
-# For more information, see https://github.com/toml-lang/toml
-
-proxy_app = "tcp://127.0.0.1:46658"
-moniker = "__MONIKER__"
-node_laddr = "tcp://0.0.0.0:46656"
-seeds = ""
-fast_sync = true
-db_backend = "leveldb"
-log_level = "notice"
-rpc_laddr = "tcp://0.0.0.0:46657"
-`
-
-func defaultConfig(moniker string) (defaultConfig string) {
-	defaultConfig = strings.Replace(defaultConfigTmpl, "__MONIKER__", moniker, -1)
-	return
-}

config/tendermint/logrotate.config

@@ -1,22 +0,0 @@
-// If you wanted to use logrotate, I suppose this might be the config you want.
-// Instead, I'll just write our own, that way we don't need sudo to install.
-
-$HOME/.tendermint/logs/tendermint.log {
-  missingok
-  notifempty
-  rotate 12
-  daily
-  size 10M
-  compress
-  delaycompress
-}
-
-$HOME/.barak/logs/barak.log {
-  missingok
-  notifempty
-  rotate 12
-  weekly
-  size 10M
-  compress
-  delaycompress
-}

config/tendermint_test/config.go

@@ -1,164 +0,0 @@
-// Import this in all *_test.go files to initialize ~/.tendermint_test.
-
-package tendermint_test
-
-import (
-	"os"
-	"path"
-	"strings"
-
-	. "github.com/tendermint/go-common"
-	cfg "github.com/tendermint/go-config"
-	"github.com/tendermint/go-logger"
-)
-
-func init() {
-	// Creates ~/.tendermint_test
-	EnsureDir(os.Getenv("HOME")+"/.tendermint_test", 0700)
-}
-
-func initTMRoot(rootDir string) {
-	// Remove ~/.tendermint_test_bak
-	if FileExists(rootDir + "_bak") {
-		err := os.RemoveAll(rootDir + "_bak")
-		if err != nil {
-			PanicSanity(err.Error())
-		}
-	}
-	// Move ~/.tendermint_test to ~/.tendermint_test_bak
-	if FileExists(rootDir) {
-		err := os.Rename(rootDir, rootDir+"_bak")
-		if err != nil {
-			PanicSanity(err.Error())
-		}
-	}
-	// Create new dir
-	EnsureDir(rootDir, 0700)
-	EnsureDir(rootDir+"/data", 0700)
-
-	configFilePath := path.Join(rootDir, "config.toml")
-	genesisFilePath := path.Join(rootDir, "genesis.json")
-	privFilePath := path.Join(rootDir, "priv_validator.json")
-
-	// Write default config file if missing.
-	if !FileExists(configFilePath) {
-		// Ask user for moniker
-		// moniker := cfg.Prompt("Type hostname: ", "anonymous")
-		MustWriteFile(configFilePath, []byte(defaultConfig("anonymous")), 0644)
-	}
-	if !FileExists(genesisFilePath) {
-		MustWriteFile(genesisFilePath, []byte(defaultGenesis), 0644)
-	}
-	// we always overwrite the priv val
-	MustWriteFile(privFilePath, []byte(defaultPrivValidator), 0644)
-}
-
-func ResetConfig(localPath string) cfg.Config {
-	rootDir := os.Getenv("HOME") + "/.tendermint_test/" + localPath
-	initTMRoot(rootDir)
-
-	configFilePath := path.Join(rootDir, "config.toml")
-	mapConfig, err := cfg.ReadMapConfigFromFile(configFilePath)
-	if err != nil {
-		Exit(Fmt("Could not read config: %v", err))
-	}
-
-	// Set defaults or panic
-	if mapConfig.IsSet("chain_id") {
-		Exit("Cannot set 'chain_id' via config.toml")
-	}
-	mapConfig.SetDefault("chain_id", "tendermint_test")
-	mapConfig.SetDefault("genesis_file", rootDir+"/genesis.json")
-	mapConfig.SetDefault("proxy_app", "dummy")
-	mapConfig.SetDefault("abci", "socket")
-	mapConfig.SetDefault("moniker", "anonymous")
-	mapConfig.SetDefault("node_laddr", "tcp://0.0.0.0:36656")
-	mapConfig.SetDefault("fast_sync", false)
-	mapConfig.SetDefault("skip_upnp", true)
-	mapConfig.SetDefault("addrbook_file", rootDir+"/addrbook.json")
-	mapConfig.SetDefault("addrbook_strict", true) // disable to allow connections locally
-	mapConfig.SetDefault("pex_reactor", false)    // enable for peer exchange
-	mapConfig.SetDefault("priv_validator_file", rootDir+"/priv_validator.json")
-	mapConfig.SetDefault("db_backend", "memdb")
-	mapConfig.SetDefault("db_dir", rootDir+"/data")
-	mapConfig.SetDefault("log_level", "info")
-	mapConfig.SetDefault("rpc_laddr", "tcp://0.0.0.0:36657")
-	mapConfig.SetDefault("grpc_laddr", "tcp://0.0.0.0:36658")
-	mapConfig.SetDefault("prof_laddr", "")
-	mapConfig.SetDefault("revision_file", rootDir+"/revision")
-	mapConfig.SetDefault("cs_wal_file", rootDir+"/data/cs.wal/wal")
-	mapConfig.SetDefault("cs_wal_light", false)
-	mapConfig.SetDefault("filter_peers", false)
-
-	mapConfig.SetDefault("block_size", 10000)
-	mapConfig.SetDefault("block_part_size", 65536) // part size 64K
-	mapConfig.SetDefault("disable_data_hash", false)
-	mapConfig.SetDefault("timeout_handshake", 10000)
-	mapConfig.SetDefault("timeout_propose", 2000)
-	mapConfig.SetDefault("timeout_propose_delta", 1)
-	mapConfig.SetDefault("timeout_prevote", 10)
-	mapConfig.SetDefault("timeout_prevote_delta", 1)
-	mapConfig.SetDefault("timeout_precommit", 10)
-	mapConfig.SetDefault("timeout_precommit_delta", 1)
-	mapConfig.SetDefault("timeout_commit", 10)
-	mapConfig.SetDefault("skip_timeout_commit", true)
-	mapConfig.SetDefault("mempool_recheck", true)
-	mapConfig.SetDefault("mempool_recheck_empty", true)
-	mapConfig.SetDefault("mempool_broadcast", true)
-	mapConfig.SetDefault("mempool_wal_dir", "")
-
-	mapConfig.SetDefault("tx_index", "kv")
-
-	logger.SetLogLevel(mapConfig.GetString("log_level"))
-
-	return mapConfig
-}
-
-var defaultConfigTmpl = `# This is a TOML config file.
-# For more information, see https://github.com/toml-lang/toml
-
-proxy_app = "dummy"
-moniker = "__MONIKER__"
-node_laddr = "tcp://0.0.0.0:36656"
-seeds = ""
-fast_sync = false
-db_backend = "memdb"
-log_level = "info"
-rpc_laddr = "tcp://0.0.0.0:36657"
-`
-
-func defaultConfig(moniker string) (defaultConfig string) {
-	defaultConfig = strings.Replace(defaultConfigTmpl, "__MONIKER__", moniker, -1)
-	return
-}
-
-var defaultGenesis = `{
-  "genesis_time": "0001-01-01T00:00:00.000Z",
-  "chain_id": "tendermint_test",
-  "validators": [
-    {
-      "pub_key": [
-        1,
-        "3B3069C422E19688B45CBFAE7BB009FC0FA1B1EA86593519318B7214853803C8"
-      ],
-      "amount": 10,
-      "name": ""
-    }
-  ],
-  "app_hash": ""
-}`
-
-var defaultPrivValidator = `{
-  "address": "D028C9981F7A87F3093672BF0D5B0E2A1B3ED456",
-  "pub_key": [
-    1,
-    "3B3069C422E19688B45CBFAE7BB009FC0FA1B1EA86593519318B7214853803C8"
-  ],
-  "priv_key": [
-    1,
-    "27F82582AEFAE7AB151CFB01C48BB6C1A0DA78F9BDDA979A9F70A84D074EB07D3B3069C422E19688B45CBFAE7BB009FC0FA1B1EA86593519318B7214853803C8"
-  ],
-  "last_height": 0,
-  "last_round": 0,
-  "last_step": 0
-}`

config/toml.go

@@ -0,0 +1,311 @@
+package config
+
+import (
+	"bytes"
+	"os"
+	"path/filepath"
+	"text/template"
+
+	cmn "github.com/tendermint/tmlibs/common"
+)
+
+var configTemplate *template.Template
+
+func init() {
+	var err error
+	if configTemplate, err = template.New("configFileTemplate").Parse(defaultConfigTemplate); err != nil {
+		panic(err)
+	}
+}
+
+/****** these are for production settings ***********/
+
+// EnsureRoot creates the root, config, and data directories if they don't exist,
+// and panics if it fails.
+func EnsureRoot(rootDir string) {
+	if err := cmn.EnsureDir(rootDir, 0700); err != nil {
+		cmn.PanicSanity(err.Error())
+	}
+	if err := cmn.EnsureDir(filepath.Join(rootDir, defaultConfigDir), 0700); err != nil {
+		cmn.PanicSanity(err.Error())
+	}
+	if err := cmn.EnsureDir(filepath.Join(rootDir, defaultDataDir), 0700); err != nil {
+		cmn.PanicSanity(err.Error())
+	}
+
+	configFilePath := filepath.Join(rootDir, defaultConfigFilePath)
+
+	// Write default config file if missing.
+	if !cmn.FileExists(configFilePath) {
+		writeDefaultCondigFile(configFilePath)
+	}
+}
+
+// XXX: this func should probably be called by cmd/tendermint/commands/init.go
+// alongside the writing of the genesis.json and priv_validator.json
+func writeDefaultCondigFile(configFilePath string) {
+	WriteConfigFile(configFilePath, DefaultConfig())
+}
+
+// WriteConfigFile renders config using the template and writes it to configFilePath.
+func WriteConfigFile(configFilePath string, config *Config) {
+	var buffer bytes.Buffer
+
+	if err := configTemplate.Execute(&buffer, config); err != nil {
+		panic(err)
+	}
+
+	cmn.MustWriteFile(configFilePath, buffer.Bytes(), 0644)
+}
+
+// Note: any changes to the comments/variables/mapstructure
+// must be reflected in the appropriate struct in config/config.go
+const defaultConfigTemplate = `# This is a TOML config file.
+# For more information, see https://github.com/toml-lang/toml
+
+##### main base config options #####
+
+# TCP or UNIX socket address of the ABCI application,
+# or the name of an ABCI application compiled in with the Tendermint binary
+proxy_app = "{{ .BaseConfig.ProxyApp }}"
+
+# A custom human readable name for this node
+moniker = "{{ .BaseConfig.Moniker }}"
+
+# If this node is many blocks behind the tip of the chain, FastSync
+# allows them to catchup quickly by downloading blocks in parallel
+# and verifying their commits
+fast_sync = {{ .BaseConfig.FastSync }}
+
+# Database backend: leveldb | memdb
+db_backend = "{{ .BaseConfig.DBBackend }}"
+
+# Database directory
+db_path = "{{ .BaseConfig.DBPath }}"
+
+# Output level for logging, including package level options
+log_level = "{{ .BaseConfig.LogLevel }}"
+
+##### additional base config options #####
+
+# Path to the JSON file containing the initial validator set and other meta data
+genesis_file = "{{ .BaseConfig.Genesis }}"
+
+# Path to the JSON file containing the private key to use as a validator in the consensus protocol
+priv_validator_file = "{{ .BaseConfig.PrivValidator }}"
+
+# Path to the JSON file containing the private key to use for node authentication in the p2p protocol
+node_key_file = "{{ .BaseConfig.NodeKey}}"
+
+# Mechanism to connect to the ABCI application: socket | grpc
+abci = "{{ .BaseConfig.ABCI }}"
+
+# TCP or UNIX socket address for the profiling server to listen on
+prof_laddr = "{{ .BaseConfig.ProfListenAddress }}"
+
+# If true, query the ABCI app on connecting to a new peer
+# so the app can decide if we should keep the connection or not
+filter_peers = {{ .BaseConfig.FilterPeers }}
+
+##### advanced configuration options #####
+
+##### rpc server configuration options #####
+[rpc]
+
+# TCP or UNIX socket address for the RPC server to listen on
+laddr = "{{ .RPC.ListenAddress }}"
+
+# TCP or UNIX socket address for the gRPC server to listen on
+# NOTE: This server only supports /broadcast_tx_commit
+grpc_laddr = "{{ .RPC.GRPCListenAddress }}"
+
+# Activate unsafe RPC commands like /dial_seeds and /unsafe_flush_mempool
+unsafe = {{ .RPC.Unsafe }}
+
+##### peer to peer configuration options #####
+[p2p]
+
+# Address to listen for incoming connections
+laddr = "{{ .P2P.ListenAddress }}"
+
+# Comma separated list of seed nodes to connect to
+seeds = "{{ .P2P.Seeds }}"
+
+# Comma separated list of nodes to keep persistent connections to
+# Do not add private peers to this list if you don't want them advertised
+persistent_peers = "{{ .P2P.PersistentPeers }}"
+
+# Path to address book
+addr_book_file = "{{ .P2P.AddrBook }}"
+
+# Set true for strict address routability rules
+addr_book_strict = {{ .P2P.AddrBookStrict }}
+
+# Time to wait before flushing messages out on the connection, in ms
+flush_throttle_timeout = {{ .P2P.FlushThrottleTimeout }}
+
+# Maximum number of peers to connect to
+max_num_peers = {{ .P2P.MaxNumPeers }}
+
+# Maximum size of a message packet payload, in bytes
+max_packet_msg_payload_size = {{ .P2P.MaxPacketMsgPayloadSize }}
+
+# Rate at which packets can be sent, in bytes/second
+send_rate = {{ .P2P.SendRate }}
+
+# Rate at which packets can be received, in bytes/second
+recv_rate = {{ .P2P.RecvRate }}
+
+# Set true to enable the peer-exchange reactor
+pex = {{ .P2P.PexReactor }}
+
+# Seed mode, in which node constantly crawls the network and looks for
+# peers. If another node asks it for addresses, it responds and disconnects.
+#
+# Does not work if the peer-exchange reactor is disabled.
+seed_mode = {{ .P2P.SeedMode }}
+
+# Authenticated encryption
+auth_enc = {{ .P2P.AuthEnc }}
+
+# Comma separated list of peer IDs to keep private (will not be gossiped to other peers)
+private_peer_ids = "{{ .P2P.PrivatePeerIDs }}"
+
+##### mempool configuration options #####
+[mempool]
+
+recheck = {{ .Mempool.Recheck }}
+recheck_empty = {{ .Mempool.RecheckEmpty }}
+broadcast = {{ .Mempool.Broadcast }}
+wal_dir = "{{ .Mempool.WalPath }}"
+
+##### consensus configuration options #####
+[consensus]
+
+wal_file = "{{ .Consensus.WalPath }}"
+wal_light = {{ .Consensus.WalLight }}
+
+# All timeouts are in milliseconds
+timeout_propose = {{ .Consensus.TimeoutPropose }}
+timeout_propose_delta = {{ .Consensus.TimeoutProposeDelta }}
+timeout_prevote = {{ .Consensus.TimeoutPrevote }}
+timeout_prevote_delta = {{ .Consensus.TimeoutPrevoteDelta }}
+timeout_precommit = {{ .Consensus.TimeoutPrecommit }}
+timeout_precommit_delta = {{ .Consensus.TimeoutPrecommitDelta }}
+timeout_commit = {{ .Consensus.TimeoutCommit }}
+
+# Make progress as soon as we have all the precommits (as if TimeoutCommit = 0)
+skip_timeout_commit = {{ .Consensus.SkipTimeoutCommit }}
+
+# BlockSize
+max_block_size_txs = {{ .Consensus.MaxBlockSizeTxs }}
+max_block_size_bytes = {{ .Consensus.MaxBlockSizeBytes }}
+
+# EmptyBlocks mode and possible interval between empty blocks in seconds
+create_empty_blocks = {{ .Consensus.CreateEmptyBlocks }}
+create_empty_blocks_interval = {{ .Consensus.CreateEmptyBlocksInterval }}
+
+# Reactor sleep duration parameters are in milliseconds
+peer_gossip_sleep_duration = {{ .Consensus.PeerGossipSleepDuration }}
+peer_query_maj23_sleep_duration = {{ .Consensus.PeerQueryMaj23SleepDuration }}
+
+##### transactions indexer configuration options #####
+[tx_index]
+
+# What indexer to use for transactions
+#
+# Options:
+#   1) "null" (default)
+#   2) "kv" - the simplest possible indexer, backed by key-value storage (defaults to levelDB; see DBBackend).
+indexer = "{{ .TxIndex.Indexer }}"
+
+# Comma-separated list of tags to index (by default the only tag is tx hash)
+#
+# It's recommended to index only a subset of tags due to possible memory
+# bloat. This is, of course, depends on the indexer's DB and the volume of
+# transactions.
+index_tags = "{{ .TxIndex.IndexTags }}"
+
+# When set to true, tells indexer to index all tags. Note this may be not
+# desirable (see the comment above). IndexTags has a precedence over
+# IndexAllTags (i.e. when given both, IndexTags will be indexed).
+index_all_tags = {{ .TxIndex.IndexAllTags }}
+`
+
+/****** these are for test settings ***********/
+
+func ResetTestRoot(testName string) *Config {
+	rootDir := os.ExpandEnv("$HOME/.tendermint_test")
+	rootDir = filepath.Join(rootDir, testName)
+	// Remove ~/.tendermint_test_bak
+	if cmn.FileExists(rootDir + "_bak") {
+		if err := os.RemoveAll(rootDir + "_bak"); err != nil {
+			cmn.PanicSanity(err.Error())
+		}
+	}
+	// Move ~/.tendermint_test to ~/.tendermint_test_bak
+	if cmn.FileExists(rootDir) {
+		if err := os.Rename(rootDir, rootDir+"_bak"); err != nil {
+			cmn.PanicSanity(err.Error())
+		}
+	}
+	// Create new dir
+	if err := cmn.EnsureDir(rootDir, 0700); err != nil {
+		cmn.PanicSanity(err.Error())
+	}
+	if err := cmn.EnsureDir(filepath.Join(rootDir, defaultConfigDir), 0700); err != nil {
+		cmn.PanicSanity(err.Error())
+	}
+	if err := cmn.EnsureDir(filepath.Join(rootDir, defaultDataDir), 0700); err != nil {
+		cmn.PanicSanity(err.Error())
+	}
+
+	baseConfig := DefaultBaseConfig()
+	configFilePath := filepath.Join(rootDir, defaultConfigFilePath)
+	genesisFilePath := filepath.Join(rootDir, baseConfig.Genesis)
+	privFilePath := filepath.Join(rootDir, baseConfig.PrivValidator)
+
+	// Write default config file if missing.
+	if !cmn.FileExists(configFilePath) {
+		writeDefaultCondigFile(configFilePath)
+	}
+	if !cmn.FileExists(genesisFilePath) {
+		cmn.MustWriteFile(genesisFilePath, []byte(testGenesis), 0644)
+	}
+	// we always overwrite the priv val
+	cmn.MustWriteFile(privFilePath, []byte(testPrivValidator), 0644)
+
+	config := TestConfig().SetRoot(rootDir)
+	return config
+}
+
+var testGenesis = `{
+  "genesis_time": "0001-01-01T00:00:00.000Z",
+  "chain_id": "tendermint_test",
+  "validators": [
+    {
+      "pub_key": {
+        "type": "AC26791624DE60",
+        "value":"AT/+aaL1eB0477Mud9JMm8Sh8BIvOYlPGC9KkIUmFaE="
+      },
+      "power": 10,
+      "name": ""
+    }
+  ],
+  "app_hash": ""
+}`
+
+var testPrivValidator = `{
+  "address": "849CB2C877F87A20925F35D00AE6688342D25B47",
+  "pub_key": {
+    "type": "AC26791624DE60",
+    "value": "AT/+aaL1eB0477Mud9JMm8Sh8BIvOYlPGC9KkIUmFaE="
+  },
+  "priv_key": {
+    "type": "954568A3288910",
+    "value": "EVkqJO/jIXp3rkASXfh9YnyToYXRXhBr6g9cQVxPFnQBP/5povV4HTjvsy530kybxKHwEi85iU8YL0qQhSYVoQ=="
+  },
+  "last_height": 0,
+  "last_round": 0,
+  "last_step": 0
+}`

config/toml_test.go

@@ -0,0 +1,94 @@
+package config
+
+import (
+	"io/ioutil"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func ensureFiles(t *testing.T, rootDir string, files ...string) {
+	for _, f := range files {
+		p := rootify(rootDir, f)
+		_, err := os.Stat(p)
+		assert.Nil(t, err, p)
+	}
+}
+
+func TestEnsureRoot(t *testing.T) {
+	require := require.New(t)
+
+	// setup temp dir for test
+	tmpDir, err := ioutil.TempDir("", "config-test")
+	require.Nil(err)
+	defer os.RemoveAll(tmpDir) // nolint: errcheck
+
+	// create root dir
+	EnsureRoot(tmpDir)
+
+	// make sure config is set properly
+	data, err := ioutil.ReadFile(filepath.Join(tmpDir, defaultConfigFilePath))
+	require.Nil(err)
+
+	if !checkConfig(string(data)) {
+		t.Fatalf("config file missing some information")
+	}
+
+	ensureFiles(t, tmpDir, "data")
+}
+
+func TestEnsureTestRoot(t *testing.T) {
+	require := require.New(t)
+
+	testName := "ensureTestRoot"
+
+	// create root dir
+	cfg := ResetTestRoot(testName)
+	rootDir := cfg.RootDir
+
+	// make sure config is set properly
+	data, err := ioutil.ReadFile(filepath.Join(rootDir, defaultConfigFilePath))
+	require.Nil(err)
+
+	if !checkConfig(string(data)) {
+		t.Fatalf("config file missing some information")
+	}
+
+	// TODO: make sure the cfg returned and testconfig are the same!
+	baseConfig := DefaultBaseConfig()
+	ensureFiles(t, rootDir, defaultDataDir, baseConfig.Genesis, baseConfig.PrivValidator)
+}
+
+func checkConfig(configFile string) bool {
+	var valid bool
+
+	// list of words we expect in the config
+	var elems = []string{
+		"moniker",
+		"seeds",
+		"proxy_app",
+		"fast_sync",
+		"create_empty_blocks",
+		"peer",
+		"timeout",
+		"broadcast",
+		"send",
+		"addr",
+		"wal",
+		"propose",
+		"max",
+		"genesis",
+	}
+	for _, e := range elems {
+		if !strings.Contains(configFile, e) {
+			valid = false
+		} else {
+			valid = true
+		}
+	}
+	return valid
+}

consensus/byzantine_test.go

@@ -1,21 +1,19 @@
 package consensus
 
 import (
+	"context"
 	"sync"
 	"testing"
 	"time"
 
-	"github.com/tendermint/tendermint/config/tendermint_test"
-
-	. "github.com/tendermint/go-common"
-	cfg "github.com/tendermint/go-config"
-	"github.com/tendermint/go-events"
-	"github.com/tendermint/go-p2p"
+	"github.com/stretchr/testify/require"
+	"github.com/tendermint/tendermint/p2p"
 	"github.com/tendermint/tendermint/types"
+	cmn "github.com/tendermint/tmlibs/common"
 )
 
 func init() {
-	config = tendermint_test.ResetConfig("consensus_byzantine_test")
+	config = ResetConfig("consensus_byzantine_test")
 }
 
 //----------------------------------------------
@@ -29,17 +27,62 @@ func init() {
 // Heal partition and ensure A sees the commit
 func TestByzantine(t *testing.T) {
 	N := 4
+	logger := consensusLogger()
 	css := randConsensusNet(N, "consensus_byzantine_test", newMockTickerFunc(false), newCounter)
 
 	// give the byzantine validator a normal ticker
-	css[0].SetTimeoutTicker(NewTimeoutTicker())
+	ticker := NewTimeoutTicker()
+	ticker.SetLogger(css[0].Logger)
+	css[0].SetTimeoutTicker(ticker)
 
 	switches := make([]*p2p.Switch, N)
+	p2pLogger := logger.With("module", "p2p")
 	for i := 0; i < N; i++ {
-		switches[i] = p2p.NewSwitch(cfg.NewMapConfig(nil))
+		switches[i] = p2p.NewSwitch(config.P2P)
+		switches[i].SetLogger(p2pLogger.With("validator", i))
 	}
 
+	eventChans := make([]chan interface{}, N)
 	reactors := make([]p2p.Reactor, N)
+	for i := 0; i < N; i++ {
+		// make first val byzantine
+		if i == 0 {
+			// NOTE: Now, test validators are MockPV, which by default doesn't
+			// do any safety checks.
+			css[i].privValidator.(*types.MockPV).DisableChecks()
+			css[i].decideProposal = func(j int) func(int64, int) {
+				return func(height int64, round int) {
+					byzantineDecideProposalFunc(t, height, round, css[j], switches[j])
+				}
+			}(i)
+			css[i].doPrevote = func(height int64, round int) {}
+		}
+
+		eventBus := types.NewEventBus()
+		eventBus.SetLogger(logger.With("module", "events", "validator", i))
+		err := eventBus.Start()
+		require.NoError(t, err)
+		defer eventBus.Stop()
+
+		eventChans[i] = make(chan interface{}, 1)
+		err = eventBus.Subscribe(context.Background(), testSubscriber, types.EventQueryNewBlock, eventChans[i])
+		require.NoError(t, err)
+
+		conR := NewConsensusReactor(css[i], true) // so we dont start the consensus states
+		conR.SetLogger(logger.With("validator", i))
+		conR.SetEventBus(eventBus)
+
+		var conRI p2p.Reactor // nolint: gotype, gosimple
+		conRI = conR
+
+		// make first val byzantine
+		if i == 0 {
+			conRI = NewByzantineReactor(conR)
+		}
+
+		reactors[i] = conRI
+	}
+
 	defer func() {
 		for _, r := range reactors {
 			if rr, ok := r.(*ByzantineReactor); ok {
@@ -49,38 +92,8 @@ func TestByzantine(t *testing.T) {
 			}
 		}
 	}()
-	eventChans := make([]chan interface{}, N)
-	for i := 0; i < N; i++ {
-		if i == 0 {
-			css[i].privValidator = NewByzantinePrivValidator(css[i].privValidator.(*types.PrivValidator))
-			// make byzantine
-			css[i].decideProposal = func(j int) func(int, int) {
-				return func(height, round int) {
-					byzantineDecideProposalFunc(height, round, css[j], switches[j])
-				}
-			}(i)
-			css[i].doPrevote = func(height, round int) {}
-		}
 
-		eventSwitch := events.NewEventSwitch()
-		_, err := eventSwitch.Start()
-		if err != nil {
-			t.Fatalf("Failed to start switch: %v", err)
-		}
-		eventChans[i] = subscribeToEvent(eventSwitch, "tester", types.EventStringNewBlock(), 1)
-
-		conR := NewConsensusReactor(css[i], true) // so we dont start the consensus states
-		conR.SetEventSwitch(eventSwitch)
-
-		var conRI p2p.Reactor
-		conRI = conR
-		if i == 0 {
-			conRI = NewByzantineReactor(conR)
-		}
-		reactors[i] = conRI
-	}
-
-	p2p.MakeConnectedSwitches(N, func(i int, s *p2p.Switch) *p2p.Switch {
+	p2p.MakeConnectedSwitches(config.P2P, N, func(i int, s *p2p.Switch) *p2p.Switch {
 		// ignore new switch s, we already made ours
 		switches[i].AddReactor("CONSENSUS", reactors[i])
 		return switches[i]
@@ -95,32 +108,29 @@ func TestByzantine(t *testing.T) {
 	// start the state machines
 	byzR := reactors[0].(*ByzantineReactor)
 	s := byzR.reactor.conS.GetState()
-	byzR.reactor.SwitchToConsensus(s)
+	byzR.reactor.SwitchToConsensus(s, 0)
 	for i := 1; i < N; i++ {
 		cr := reactors[i].(*ConsensusReactor)
-		cr.SwitchToConsensus(cr.conS.GetState())
+		cr.SwitchToConsensus(cr.conS.GetState(), 0)
 	}
 
 	// byz proposer sends one block to peers[0]
 	// and the other block to peers[1] and peers[2].
 	// note peers and switches order don't match.
 	peers := switches[0].Peers().List()
+
+	// partition A
 	ind0 := getSwitchIndex(switches, peers[0])
+
+	// partition B
 	ind1 := getSwitchIndex(switches, peers[1])
 	ind2 := getSwitchIndex(switches, peers[2])
-
-	// connect the 2 peers in the larger partition
 	p2p.Connect2Switches(switches, ind1, ind2)
 
-	// wait for someone in the big partition to make a block
+	// wait for someone in the big partition (B) to make a block
+	<-eventChans[ind2]
 
-	select {
-	case <-eventChans[ind2]:
-	}
-
-	log.Notice("A block has been committed. Healing partition")
-
-	// connect the partitions
+	t.Log("A block has been committed. Healing partition")
 	p2p.Connect2Switches(switches, ind0, ind1)
 	p2p.Connect2Switches(switches, ind0, ind2)
 
@@ -146,8 +156,8 @@ func TestByzantine(t *testing.T) {
 	case <-done:
 	case <-tick.C:
 		for i, reactor := range reactors {
-			t.Log(Fmt("Consensus Reactor %v", i))
-			t.Log(Fmt("%v", reactor))
+			t.Log(cmn.Fmt("Consensus Reactor %v", i))
+			t.Log(cmn.Fmt("%v", reactor))
 		}
 		t.Fatalf("Timed out waiting for all validators to commit first block")
 	}
@@ -156,7 +166,7 @@ func TestByzantine(t *testing.T) {
 //-------------------------------
 // byzantine consensus functions
 
-func byzantineDecideProposalFunc(height, round int, cs *ConsensusState, sw *p2p.Switch) {
+func byzantineDecideProposalFunc(t *testing.T, height int64, round int, cs *ConsensusState, sw *p2p.Switch) {
 	// byzantine user should create two proposals and try to split the vote.
 	// Avoid sending on internalMsgQueue and running consensus state.
 
@@ -164,20 +174,24 @@ func byzantineDecideProposalFunc(height, round int, cs *ConsensusState, sw *p2p.
 	block1, blockParts1 := cs.createProposalBlock()
 	polRound, polBlockID := cs.Votes.POLInfo()
 	proposal1 := types.NewProposal(height, round, blockParts1.Header(), polRound, polBlockID)
-	cs.privValidator.SignProposal(cs.state.ChainID, proposal1) // byzantine doesnt err
+	if err := cs.privValidator.SignProposal(cs.state.ChainID, proposal1); err != nil {
+		t.Error(err)
+	}
 
 	// Create a new proposal block from state/txs from the mempool.
 	block2, blockParts2 := cs.createProposalBlock()
 	polRound, polBlockID = cs.Votes.POLInfo()
 	proposal2 := types.NewProposal(height, round, blockParts2.Header(), polRound, polBlockID)
-	cs.privValidator.SignProposal(cs.state.ChainID, proposal2) // byzantine doesnt err
+	if err := cs.privValidator.SignProposal(cs.state.ChainID, proposal2); err != nil {
+		t.Error(err)
+	}
 
 	block1Hash := block1.Hash()
 	block2Hash := block2.Hash()
 
 	// broadcast conflicting proposals/block parts to peers
 	peers := sw.Peers().List()
-	log.Notice("Byzantine: broadcasting conflicting proposals", "peers", len(peers))
+	t.Logf("Byzantine: broadcasting conflicting proposals to %d peers", len(peers))
 	for i, peer := range peers {
 		if i < len(peers)/2 {
 			go sendProposalAndParts(height, round, cs, peer, proposal1, block1Hash, blockParts1)
@@ -187,10 +201,10 @@ func byzantineDecideProposalFunc(height, round int, cs *ConsensusState, sw *p2p.
 	}
 }
 
-func sendProposalAndParts(height, round int, cs *ConsensusState, peer *p2p.Peer, proposal *types.Proposal, blockHash []byte, parts *types.PartSet) {
+func sendProposalAndParts(height int64, round int, cs *ConsensusState, peer p2p.Peer, proposal *types.Proposal, blockHash []byte, parts *types.PartSet) {
 	// proposal
 	msg := &ProposalMessage{Proposal: proposal}
-	peer.Send(DataChannel, struct{ ConsensusMessage }{msg})
+	peer.Send(DataChannel, cdc.MustMarshalBinaryBare(msg))
 
 	// parts
 	for i := 0; i < parts.Total(); i++ {
@@ -200,7 +214,7 @@ func sendProposalAndParts(height, round int, cs *ConsensusState, peer *p2p.Peer,
 			Round:  round,  // This tells peer that this part applies to us.
 			Part:   part,
 		}
-		peer.Send(DataChannel, struct{ ConsensusMessage }{msg})
+		peer.Send(DataChannel, cdc.MustMarshalBinaryBare(msg))
 	}
 
 	// votes
@@ -209,15 +223,15 @@ func sendProposalAndParts(height, round int, cs *ConsensusState, peer *p2p.Peer,
 	precommit, _ := cs.signVote(types.VoteTypePrecommit, blockHash, parts.Header())
 	cs.mtx.Unlock()
 
-	peer.Send(VoteChannel, struct{ ConsensusMessage }{&VoteMessage{prevote}})
-	peer.Send(VoteChannel, struct{ ConsensusMessage }{&VoteMessage{precommit}})
+	peer.Send(VoteChannel, cdc.MustMarshalBinaryBare(&VoteMessage{prevote}))
+	peer.Send(VoteChannel, cdc.MustMarshalBinaryBare(&VoteMessage{precommit}))
 }
 
 //----------------------------------------
 // byzantine consensus reactor
 
 type ByzantineReactor struct {
-	Service
+	cmn.Service
 	reactor *ConsensusReactor
 }
 
@@ -230,14 +244,14 @@ func NewByzantineReactor(conR *ConsensusReactor) *ByzantineReactor {
 
 func (br *ByzantineReactor) SetSwitch(s *p2p.Switch)               { br.reactor.SetSwitch(s) }
 func (br *ByzantineReactor) GetChannels() []*p2p.ChannelDescriptor { return br.reactor.GetChannels() }
-func (br *ByzantineReactor) AddPeer(peer *p2p.Peer) {
+func (br *ByzantineReactor) AddPeer(peer p2p.Peer) {
 	if !br.reactor.IsRunning() {
 		return
 	}
 
 	// Create peerState for peer
-	peerState := NewPeerState(peer)
-	peer.Data.Set(types.PeerStateKey, peerState)
+	peerState := NewPeerState(peer).SetLogger(br.reactor.Logger)
+	peer.Set(types.PeerStateKey, peerState)
 
 	// Send our state to peer.
 	// If we're fast_syncing, broadcast a RoundStepMessage later upon SwitchToConsensus().
@@ -245,53 +259,9 @@ func (br *ByzantineReactor) AddPeer(peer *p2p.Peer) {
 		br.reactor.sendNewRoundStepMessages(peer)
 	}
 }
-func (br *ByzantineReactor) RemovePeer(peer *p2p.Peer, reason interface{}) {
+func (br *ByzantineReactor) RemovePeer(peer p2p.Peer, reason interface{}) {
 	br.reactor.RemovePeer(peer, reason)
 }
-func (br *ByzantineReactor) Receive(chID byte, peer *p2p.Peer, msgBytes []byte) {
+func (br *ByzantineReactor) Receive(chID byte, peer p2p.Peer, msgBytes []byte) {
 	br.reactor.Receive(chID, peer, msgBytes)
 }
-
-//----------------------------------------
-// byzantine privValidator
-
-type ByzantinePrivValidator struct {
-	Address      []byte `json:"address"`
-	types.Signer `json:"-"`
-
-	mtx sync.Mutex
-}
-
-// Return a priv validator that will sign anything
-func NewByzantinePrivValidator(pv *types.PrivValidator) *ByzantinePrivValidator {
-	return &ByzantinePrivValidator{
-		Address: pv.Address,
-		Signer:  pv.Signer,
-	}
-}
-
-func (privVal *ByzantinePrivValidator) GetAddress() []byte {
-	return privVal.Address
-}
-
-func (privVal *ByzantinePrivValidator) SignVote(chainID string, vote *types.Vote) error {
-	privVal.mtx.Lock()
-	defer privVal.mtx.Unlock()
-
-	// Sign
-	vote.Signature = privVal.Sign(types.SignBytes(chainID, vote))
-	return nil
-}
-
-func (privVal *ByzantinePrivValidator) SignProposal(chainID string, proposal *types.Proposal) error {
-	privVal.mtx.Lock()
-	defer privVal.mtx.Unlock()
-
-	// Sign
-	proposal.Signature = privVal.Sign(types.SignBytes(chainID, proposal))
-	return nil
-}
-
-func (privVal *ByzantinePrivValidator) String() string {
-	return Fmt("PrivValidator{%X}", privVal.Address)
-}

consensus/common.go

@@ -1,29 +0,0 @@
-package consensus
-
-import (
-	"github.com/tendermint/tendermint/types"
-)
-
-// XXX: WARNING: these functions can halt the consensus as firing events is synchronous.
-// Make sure to read off the channels, and in the case of subscribeToEventRespond, to write back on it
-
-// NOTE: if chanCap=0, this blocks on the event being consumed
-func subscribeToEvent(evsw types.EventSwitch, receiver, eventID string, chanCap int) chan interface{} {
-	// listen for event
-	ch := make(chan interface{}, chanCap)
-	types.AddListenerForEvent(evsw, receiver, eventID, func(data types.TMEventData) {
-		ch <- data
-	})
-	return ch
-}
-
-// NOTE: this blocks on receiving a response after the event is consumed
-func subscribeToEventRespond(evsw types.EventSwitch, receiver, eventID string) chan interface{} {
-	// listen for event
-	ch := make(chan interface{})
-	types.AddListenerForEvent(evsw, receiver, eventID, func(data types.TMEventData) {
-		ch <- data
-		<-ch
-	})
-	return ch
-}

consensus/common_test.go

@@ -2,6 +2,7 @@ package consensus
 
 import (
 	"bytes"
+	"context"
 	"fmt"
 	"io/ioutil"
 	"os"
@@ -13,42 +14,55 @@ import (
 
 	abcicli "github.com/tendermint/abci/client"
 	abci "github.com/tendermint/abci/types"
-	. "github.com/tendermint/go-common"
-	cfg "github.com/tendermint/go-config"
-	dbm "github.com/tendermint/go-db"
-	"github.com/tendermint/go-p2p"
 	bc "github.com/tendermint/tendermint/blockchain"
-	"github.com/tendermint/tendermint/config/tendermint_test"
+	cfg "github.com/tendermint/tendermint/config"
+	cstypes "github.com/tendermint/tendermint/consensus/types"
 	mempl "github.com/tendermint/tendermint/mempool"
+	"github.com/tendermint/tendermint/p2p"
 	sm "github.com/tendermint/tendermint/state"
 	"github.com/tendermint/tendermint/types"
+	pvm "github.com/tendermint/tendermint/types/priv_validator"
+	cmn "github.com/tendermint/tmlibs/common"
+	dbm "github.com/tendermint/tmlibs/db"
+	"github.com/tendermint/tmlibs/log"
 
 	"github.com/tendermint/abci/example/counter"
-	"github.com/tendermint/abci/example/dummy"
+	"github.com/tendermint/abci/example/kvstore"
+
+	"github.com/go-kit/kit/log/term"
 )
 
-var config cfg.Config // NOTE: must be reset for each _test.go file
-var ensureTimeout = time.Duration(2)
+const (
+	testSubscriber = "test-client"
+)
+
+// genesis, chain_id, priv_val
+var config *cfg.Config              // NOTE: must be reset for each _test.go file
+var ensureTimeout = time.Second * 1 // must be in seconds because CreateEmptyBlocksInterval is
 
 func ensureDir(dir string, mode os.FileMode) {
-	if err := EnsureDir(dir, mode); err != nil {
+	if err := cmn.EnsureDir(dir, mode); err != nil {
 		panic(err)
 	}
 }
 
+func ResetConfig(name string) *cfg.Config {
+	return cfg.ResetTestRoot(name)
+}
+
 //-------------------------------------------------------------------------------
-// validator stub (a dummy consensus peer we control)
+// validator stub (a kvstore consensus peer we control)
 
 type validatorStub struct {
 	Index  int // Validator index. NOTE: we don't assume validator set changes.
-	Height int
+	Height int64
 	Round  int
-	*types.PrivValidator
+	types.PrivValidator
 }
 
-var testMinPower = 10
+var testMinPower int64 = 10
 
-func NewValidatorStub(privValidator *types.PrivValidator, valIndex int) *validatorStub {
+func NewValidatorStub(privValidator types.PrivValidator, valIndex int) *validatorStub {
 	return &validatorStub{
 		Index:         valIndex,
 		PrivValidator: privValidator,
@@ -58,13 +72,14 @@ func NewValidatorStub(privValidator *types.PrivValidator, valIndex int) *validat
 func (vs *validatorStub) signVote(voteType byte, hash []byte, header types.PartSetHeader) (*types.Vote, error) {
 	vote := &types.Vote{
 		ValidatorIndex:   vs.Index,
-		ValidatorAddress: vs.PrivValidator.Address,
+		ValidatorAddress: vs.PrivValidator.GetAddress(),
 		Height:           vs.Height,
 		Round:            vs.Round,
+		Timestamp:        time.Now().UTC(),
 		Type:             voteType,
 		BlockID:          types.BlockID{hash, header},
 	}
-	err := vs.PrivValidator.SignVote(config.GetString("chain_id"), vote)
+	err := vs.PrivValidator.SignVote(config.ChainID(), vote)
 	return vote, err
 }
 
@@ -87,26 +102,26 @@ func signVotes(voteType byte, hash []byte, header types.PartSetHeader, vss ...*v
 
 func incrementHeight(vss ...*validatorStub) {
 	for _, vs := range vss {
-		vs.Height += 1
+		vs.Height++
 	}
 }
 
 func incrementRound(vss ...*validatorStub) {
 	for _, vs := range vss {
-		vs.Round += 1
+		vs.Round++
 	}
 }
 
 //-------------------------------------------------------------------------------
 // Functions for transitioning the consensus state
 
-func startTestRound(cs *ConsensusState, height, round int) {
+func startTestRound(cs *ConsensusState, height int64, round int) {
 	cs.enterNewRound(height, round)
 	cs.startRoutines(0)
 }
 
 // Create proposal block from cs1 but sign it with vs
-func decideProposal(cs1 *ConsensusState, vs *validatorStub, height, round int) (proposal *types.Proposal, block *types.Block) {
+func decideProposal(cs1 *ConsensusState, vs *validatorStub, height int64, round int) (proposal *types.Proposal, block *types.Block) {
 	block, blockParts := cs1.createProposalBlock()
 	if block == nil { // on error
 		panic("error creating proposal block")
@@ -115,7 +130,7 @@ func decideProposal(cs1 *ConsensusState, vs *validatorStub, height, round int) (
 	// Make proposal
 	polRound, polBlockID := cs1.Votes.POLInfo()
 	proposal = types.NewProposal(height, round, blockParts.Header(), polRound, polBlockID)
-	if err := vs.SignProposal(config.GetString("chain_id"), proposal); err != nil {
+	if err := vs.SignProposal(cs1.state.ChainID, proposal); err != nil {
 		panic(err)
 	}
 	return
@@ -135,7 +150,7 @@ func signAddVotes(to *ConsensusState, voteType byte, hash []byte, header types.P
 func validatePrevote(t *testing.T, cs *ConsensusState, round int, privVal *validatorStub, blockHash []byte) {
 	prevotes := cs.Votes.Prevotes(round)
 	var vote *types.Vote
-	if vote = prevotes.GetByAddress(privVal.Address); vote == nil {
+	if vote = prevotes.GetByAddress(privVal.GetAddress()); vote == nil {
 		panic("Failed to find prevote from validator")
 	}
 	if blockHash == nil {
@@ -152,7 +167,7 @@ func validatePrevote(t *testing.T, cs *ConsensusState, round int, privVal *valid
 func validateLastPrecommit(t *testing.T, cs *ConsensusState, privVal *validatorStub, blockHash []byte) {
 	votes := cs.LastCommit
 	var vote *types.Vote
-	if vote = votes.GetByAddress(privVal.Address); vote == nil {
+	if vote = votes.GetByAddress(privVal.GetAddress()); vote == nil {
 		panic("Failed to find precommit from validator")
 	}
 	if !bytes.Equal(vote.BlockID.Hash, blockHash) {
@@ -163,7 +178,7 @@ func validateLastPrecommit(t *testing.T, cs *ConsensusState, privVal *validatorS
 func validatePrecommit(t *testing.T, cs *ConsensusState, thisRound, lockRound int, privVal *validatorStub, votedBlockHash, lockedBlockHash []byte) {
 	precommits := cs.Votes.Precommits(thisRound)
 	var vote *types.Vote
-	if vote = precommits.GetByAddress(privVal.Address); vote == nil {
+	if vote = precommits.GetByAddress(privVal.GetAddress()); vote == nil {
 		panic("Failed to find precommit from validator")
 	}
 
@@ -200,11 +215,14 @@ func validatePrevoteAndPrecommit(t *testing.T, cs *ConsensusState, thisRound, lo
 
 // genesis
 func subscribeToVoter(cs *ConsensusState, addr []byte) chan interface{} {
-	voteCh0 := subscribeToEvent(cs.evsw, "tester", types.EventStringVote(), 1)
+	voteCh0 := make(chan interface{})
+	err := cs.eventBus.Subscribe(context.Background(), testSubscriber, types.EventQueryVote, voteCh0)
+	if err != nil {
+		panic(fmt.Sprintf("failed to subscribe %s to %v", testSubscriber, types.EventQueryVote))
+	}
 	voteCh := make(chan interface{})
 	go func() {
-		for {
-			v := <-voteCh0
+		for v := range voteCh0 {
 			vote := v.(types.EventDataVote)
 			// we only fire for our own votes
 			if bytes.Equal(addr, vote.Vote.ValidatorAddress) {
@@ -215,27 +233,20 @@ func subscribeToVoter(cs *ConsensusState, addr []byte) chan interface{} {
 	return voteCh
 }
 
-func readVotes(ch chan interface{}, reads int) chan struct{} {
-	wg := make(chan struct{})
-	go func() {
-		for i := 0; i < reads; i++ {
-			<-ch // read the precommit event
-		}
-		close(wg)
-	}()
-	return wg
-}
-
 //-------------------------------------------------------------------------------
 // consensus states
 
-func newConsensusState(state *sm.State, pv *types.PrivValidator, app abci.Application) *ConsensusState {
+func newConsensusState(state sm.State, pv types.PrivValidator, app abci.Application) *ConsensusState {
 	return newConsensusStateWithConfig(config, state, pv, app)
 }
 
-func newConsensusStateWithConfig(thisConfig cfg.Config, state *sm.State, pv *types.PrivValidator, app abci.Application) *ConsensusState {
-	// Get BlockStore
+func newConsensusStateWithConfig(thisConfig *cfg.Config, state sm.State, pv types.PrivValidator, app abci.Application) *ConsensusState {
 	blockDB := dbm.NewMemDB()
+	return newConsensusStateWithConfigAndBlockStore(thisConfig, state, pv, app, blockDB)
+}
+
+func newConsensusStateWithConfigAndBlockStore(thisConfig *cfg.Config, state sm.State, pv types.PrivValidator, app abci.Application, blockDB dbm.DB) *ConsensusState {
+	// Get BlockStore
 	blockStore := bc.NewBlockStore(blockDB)
 
 	// one for mempool, one for consensus
@@ -244,42 +255,37 @@ func newConsensusStateWithConfig(thisConfig cfg.Config, state *sm.State, pv *typ
 	proxyAppConnCon := abcicli.NewLocalClient(mtx, app)
 
 	// Make Mempool
-	mempool := mempl.NewMempool(thisConfig, proxyAppConnMem)
+	mempool := mempl.NewMempool(thisConfig.Mempool, proxyAppConnMem, 0)
+	mempool.SetLogger(log.TestingLogger().With("module", "mempool"))
+	if thisConfig.Consensus.WaitForTxs() {
+		mempool.EnableTxsAvailable()
+	}
+
+	// mock the evidence pool
+	evpool := types.MockEvidencePool{}
 
 	// Make ConsensusReactor
-	cs := NewConsensusState(thisConfig, state, proxyAppConnCon, blockStore, mempool)
+	stateDB := dbm.NewMemDB()
+	blockExec := sm.NewBlockExecutor(stateDB, log.TestingLogger(), proxyAppConnCon, mempool, evpool)
+	cs := NewConsensusState(thisConfig.Consensus, state, blockExec, blockStore, mempool, evpool)
+	cs.SetLogger(log.TestingLogger().With("module", "consensus"))
 	cs.SetPrivValidator(pv)
 
-	evsw := types.NewEventSwitch()
-	cs.SetEventSwitch(evsw)
-	evsw.Start()
+	eventBus := types.NewEventBus()
+	eventBus.SetLogger(log.TestingLogger().With("module", "events"))
+	eventBus.Start()
+	cs.SetEventBus(eventBus)
 	return cs
 }
 
-func loadPrivValidator(conf cfg.Config) *types.PrivValidator {
-	privValidatorFile := conf.GetString("priv_validator_file")
+func loadPrivValidator(config *cfg.Config) *pvm.FilePV {
+	privValidatorFile := config.PrivValidatorFile()
 	ensureDir(path.Dir(privValidatorFile), 0700)
-	privValidator := types.LoadOrGenPrivValidator(privValidatorFile)
+	privValidator := pvm.LoadOrGenFilePV(privValidatorFile)
 	privValidator.Reset()
 	return privValidator
 }
 
-func fixedConsensusState() *ConsensusState {
-	stateDB := dbm.NewMemDB()
-	state := sm.MakeGenesisStateFromFile(stateDB, config.GetString("genesis_file"))
-	privValidator := loadPrivValidator(config)
-	cs := newConsensusState(state, privValidator, counter.NewCounterApplication(true))
-	return cs
-}
-
-func fixedConsensusStateDummy() *ConsensusState {
-	stateDB := dbm.NewMemDB()
-	state := sm.MakeGenesisStateFromFile(stateDB, config.GetString("genesis_file"))
-	privValidator := loadPrivValidator(config)
-	cs := newConsensusState(state, privValidator, dummy.NewDummyApplication())
-	return cs
-}
-
 func randConsensusState(nValidators int) (*ConsensusState, []*validatorStub) {
 	// Get State
 	state, privVals := randGenesisState(nValidators, false, 10)
@@ -299,62 +305,97 @@ func randConsensusState(nValidators int) (*ConsensusState, []*validatorStub) {
 
 //-------------------------------------------------------------------------------
 
-func ensureNoNewStep(stepCh chan interface{}) {
-	timeout := time.NewTicker(ensureTimeout * time.Second)
+func ensureNoNewStep(stepCh <-chan interface{}) {
+	timer := time.NewTimer(ensureTimeout)
 	select {
-	case <-timeout.C:
+	case <-timer.C:
 		break
 	case <-stepCh:
-		panic("We should be stuck waiting for more votes, not moving to the next step")
+		panic("We should be stuck waiting, not moving to the next step")
+	}
+}
+
+func ensureNewStep(stepCh <-chan interface{}) {
+	timer := time.NewTimer(ensureTimeout)
+	select {
+	case <-timer.C:
+		panic("We shouldnt be stuck waiting")
+	case <-stepCh:
+		break
 	}
 }
 
 //-------------------------------------------------------------------------------
 // consensus nets
 
-func randConsensusNet(nValidators int, testName string, tickerFunc func() TimeoutTicker, appFunc func() abci.Application) []*ConsensusState {
-	genDoc, privVals := randGenesisDoc(nValidators, false, 10)
+// consensusLogger is a TestingLogger which uses a different
+// color for each validator ("validator" key must exist).
+func consensusLogger() log.Logger {
+	return log.TestingLoggerWithColorFn(func(keyvals ...interface{}) term.FgBgColor {
+		for i := 0; i < len(keyvals)-1; i += 2 {
+			if keyvals[i] == "validator" {
+				return term.FgBgColor{Fg: term.Color(uint8(keyvals[i+1].(int) + 1))}
+			}
+		}
+		return term.FgBgColor{}
+	}).With("module", "consensus")
+}
+
+func randConsensusNet(nValidators int, testName string, tickerFunc func() TimeoutTicker, appFunc func() abci.Application, configOpts ...func(*cfg.Config)) []*ConsensusState {
+	genDoc, privVals := randGenesisDoc(nValidators, false, 30)
 	css := make([]*ConsensusState, nValidators)
+	logger := consensusLogger()
 	for i := 0; i < nValidators; i++ {
-		db := dbm.NewMemDB() // each state needs its own db
-		state := sm.MakeGenesisState(db, genDoc)
-		state.Save()
-		thisConfig := tendermint_test.ResetConfig(Fmt("%s_%d", testName, i))
-		ensureDir(path.Dir(thisConfig.GetString("cs_wal_file")), 0700) // dir for wal
-		css[i] = newConsensusStateWithConfig(thisConfig, state, privVals[i], appFunc())
+		stateDB := dbm.NewMemDB() // each state needs its own db
+		state, _ := sm.LoadStateFromDBOrGenesisDoc(stateDB, genDoc)
+		thisConfig := ResetConfig(cmn.Fmt("%s_%d", testName, i))
+		for _, opt := range configOpts {
+			opt(thisConfig)
+		}
+		ensureDir(path.Dir(thisConfig.Consensus.WalFile()), 0700) // dir for wal
+		app := appFunc()
+		vals := types.TM2PB.Validators(state.Validators)
+		app.InitChain(abci.RequestInitChain{Validators: vals})
+
+		css[i] = newConsensusStateWithConfig(thisConfig, state, privVals[i], app)
 		css[i].SetTimeoutTicker(tickerFunc())
+		css[i].SetLogger(logger.With("validator", i, "module", "consensus"))
 	}
 	return css
 }
 
 // nPeers = nValidators + nNotValidator
 func randConsensusNetWithPeers(nValidators, nPeers int, testName string, tickerFunc func() TimeoutTicker, appFunc func() abci.Application) []*ConsensusState {
-	genDoc, privVals := randGenesisDoc(nValidators, false, int64(testMinPower))
+	genDoc, privVals := randGenesisDoc(nValidators, false, testMinPower)
 	css := make([]*ConsensusState, nPeers)
+	logger := consensusLogger()
 	for i := 0; i < nPeers; i++ {
-		db := dbm.NewMemDB() // each state needs its own db
-		state := sm.MakeGenesisState(db, genDoc)
-		state.Save()
-		thisConfig := tendermint_test.ResetConfig(Fmt("%s_%d", testName, i))
-		ensureDir(path.Dir(thisConfig.GetString("cs_wal_file")), 0700) // dir for wal
-		var privVal *types.PrivValidator
+		stateDB := dbm.NewMemDB() // each state needs its own db
+		state, _ := sm.LoadStateFromDBOrGenesisDoc(stateDB, genDoc)
+		thisConfig := ResetConfig(cmn.Fmt("%s_%d", testName, i))
+		ensureDir(path.Dir(thisConfig.Consensus.WalFile()), 0700) // dir for wal
+		var privVal types.PrivValidator
 		if i < nValidators {
 			privVal = privVals[i]
 		} else {
-			privVal = types.GenPrivValidator()
-			_, tempFilePath := Tempfile("priv_validator_")
-			privVal.SetFile(tempFilePath)
+			_, tempFilePath := cmn.Tempfile("priv_validator_")
+			privVal = pvm.GenFilePV(tempFilePath)
 		}
 
-		css[i] = newConsensusStateWithConfig(thisConfig, state, privVal, appFunc())
+		app := appFunc()
+		vals := types.TM2PB.Validators(state.Validators)
+		app.InitChain(abci.RequestInitChain{Validators: vals})
+
+		css[i] = newConsensusStateWithConfig(thisConfig, state, privVal, app)
 		css[i].SetTimeoutTicker(tickerFunc())
+		css[i].SetLogger(logger.With("validator", i, "module", "consensus"))
 	}
 	return css
 }
 
-func getSwitchIndex(switches []*p2p.Switch, peer *p2p.Peer) int {
+func getSwitchIndex(switches []*p2p.Switch, peer p2p.Peer) int {
 	for i, s := range switches {
-		if bytes.Equal(peer.NodeInfo.PubKey.Address(), s.NodeInfo().PubKey.Address()) {
+		if peer.NodeInfo().ID == s.NodeInfo().ID {
 			return i
 		}
 	}
@@ -365,30 +406,31 @@ func getSwitchIndex(switches []*p2p.Switch, peer *p2p.Peer) int {
 //-------------------------------------------------------------------------------
 // genesis
 
-func randGenesisDoc(numValidators int, randPower bool, minPower int64) (*types.GenesisDoc, []*types.PrivValidator) {
+func randGenesisDoc(numValidators int, randPower bool, minPower int64) (*types.GenesisDoc, []types.PrivValidator) {
 	validators := make([]types.GenesisValidator, numValidators)
-	privValidators := make([]*types.PrivValidator, numValidators)
+	privValidators := make([]types.PrivValidator, numValidators)
 	for i := 0; i < numValidators; i++ {
 		val, privVal := types.RandValidator(randPower, minPower)
 		validators[i] = types.GenesisValidator{
 			PubKey: val.PubKey,
-			Amount: val.VotingPower,
+			Power:  val.VotingPower,
 		}
 		privValidators[i] = privVal
 	}
 	sort.Sort(types.PrivValidatorsByAddress(privValidators))
+
 	return &types.GenesisDoc{
 		GenesisTime: time.Now(),
-		ChainID:     config.GetString("chain_id"),
+		ChainID:     config.ChainID(),
 		Validators:  validators,
 	}, privValidators
 }
 
-func randGenesisState(numValidators int, randPower bool, minPower int64) (*sm.State, []*types.PrivValidator) {
+func randGenesisState(numValidators int, randPower bool, minPower int64) (sm.State, []types.PrivValidator) {
 	genDoc, privValidators := randGenesisDoc(numValidators, randPower, minPower)
+	s0, _ := sm.MakeGenesisState(genDoc)
 	db := dbm.NewMemDB()
-	s0 := sm.MakeGenesisState(db, genDoc)
-	s0.Save()
+	sm.SaveState(db, s0)
 	return s0, privValidators
 }
 
@@ -414,12 +456,12 @@ type mockTicker struct {
 	fired    bool
 }
 
-func (m *mockTicker) Start() (bool, error) {
-	return true, nil
+func (m *mockTicker) Start() error {
+	return nil
 }
 
-func (m *mockTicker) Stop() bool {
-	return true
+func (m *mockTicker) Stop() error {
+	return nil
 }
 
 func (m *mockTicker) ScheduleTimeout(ti timeoutInfo) {
@@ -428,7 +470,7 @@ func (m *mockTicker) ScheduleTimeout(ti timeoutInfo) {
 	if m.onlyOnce && m.fired {
 		return
 	}
-	if ti.Step == RoundStepNewHeight {
+	if ti.Step == cstypes.RoundStepNewHeight {
 		m.c <- ti
 		m.fired = true
 	}
@@ -438,13 +480,16 @@ func (m *mockTicker) Chan() <-chan timeoutInfo {
 	return m.c
 }
 
+func (mockTicker) SetLogger(log.Logger) {
+}
+
 //------------------------------------
 
 func newCounter() abci.Application {
 	return counter.NewCounterApplication(true)
 }
 
-func newPersistentDummy() abci.Application {
-	dir, _ := ioutil.TempDir("/tmp", "persistent-dummy")
-	return dummy.NewPersistentDummyApplication(dir)
+func newPersistentKVStore() abci.Application {
+	dir, _ := ioutil.TempDir("/tmp", "persistent-kvstore")
+	return kvstore.NewPersistentKVStoreApplication(dir)
 }

consensus/log.go

@@ -1,18 +0,0 @@
-package consensus
-
-import (
-	"github.com/tendermint/go-logger"
-)
-
-var log = logger.New("module", "consensus")
-
-/*
-func init() {
-	log.SetHandler(
-		logger.LvlFilterHandler(
-			logger.LvlDebug,
-			logger.BypassHandler(),
-		),
-	)
-}
-*/

consensus/mempool_test.go

@@ -2,56 +2,121 @@ package consensus
 
 import (
 	"encoding/binary"
+	"fmt"
 	"testing"
 	"time"
 
-	abci "github.com/tendermint/abci/types"
-	"github.com/tendermint/tendermint/config/tendermint_test"
-	"github.com/tendermint/tendermint/types"
+	"github.com/stretchr/testify/assert"
 
-	. "github.com/tendermint/go-common"
+	"github.com/tendermint/abci/example/code"
+	abci "github.com/tendermint/abci/types"
+	cmn "github.com/tendermint/tmlibs/common"
+
+	"github.com/tendermint/tendermint/types"
 )
 
 func init() {
-	config = tendermint_test.ResetConfig("consensus_mempool_test")
+	config = ResetConfig("consensus_mempool_test")
 }
 
-func TestTxConcurrentWithCommit(t *testing.T) {
+func TestMempoolNoProgressUntilTxsAvailable(t *testing.T) {
+	config := ResetConfig("consensus_mempool_txs_available_test")
+	config.Consensus.CreateEmptyBlocks = false
+	state, privVals := randGenesisState(1, false, 10)
+	cs := newConsensusStateWithConfig(config, state, privVals[0], NewCounterApplication())
+	cs.mempool.EnableTxsAvailable()
+	height, round := cs.Height, cs.Round
+	newBlockCh := subscribe(cs.eventBus, types.EventQueryNewBlock)
+	startTestRound(cs, height, round)
 
+	ensureNewStep(newBlockCh) // first block gets committed
+	ensureNoNewStep(newBlockCh)
+	deliverTxsRange(cs, 0, 1)
+	ensureNewStep(newBlockCh) // commit txs
+	ensureNewStep(newBlockCh) // commit updated app hash
+	ensureNoNewStep(newBlockCh)
+}
+
+func TestMempoolProgressAfterCreateEmptyBlocksInterval(t *testing.T) {
+	config := ResetConfig("consensus_mempool_txs_available_test")
+	config.Consensus.CreateEmptyBlocksInterval = int(ensureTimeout.Seconds())
+	state, privVals := randGenesisState(1, false, 10)
+	cs := newConsensusStateWithConfig(config, state, privVals[0], NewCounterApplication())
+	cs.mempool.EnableTxsAvailable()
+	height, round := cs.Height, cs.Round
+	newBlockCh := subscribe(cs.eventBus, types.EventQueryNewBlock)
+	startTestRound(cs, height, round)
+
+	ensureNewStep(newBlockCh)   // first block gets committed
+	ensureNoNewStep(newBlockCh) // then we dont make a block ...
+	ensureNewStep(newBlockCh)   // until the CreateEmptyBlocksInterval has passed
+}
+
+func TestMempoolProgressInHigherRound(t *testing.T) {
+	config := ResetConfig("consensus_mempool_txs_available_test")
+	config.Consensus.CreateEmptyBlocks = false
+	state, privVals := randGenesisState(1, false, 10)
+	cs := newConsensusStateWithConfig(config, state, privVals[0], NewCounterApplication())
+	cs.mempool.EnableTxsAvailable()
+	height, round := cs.Height, cs.Round
+	newBlockCh := subscribe(cs.eventBus, types.EventQueryNewBlock)
+	newRoundCh := subscribe(cs.eventBus, types.EventQueryNewRound)
+	timeoutCh := subscribe(cs.eventBus, types.EventQueryTimeoutPropose)
+	cs.setProposal = func(proposal *types.Proposal) error {
+		if cs.Height == 2 && cs.Round == 0 {
+			// dont set the proposal in round 0 so we timeout and
+			// go to next round
+			cs.Logger.Info("Ignoring set proposal at height 2, round 0")
+			return nil
+		}
+		return cs.defaultSetProposal(proposal)
+	}
+	startTestRound(cs, height, round)
+
+	ensureNewStep(newRoundCh) // first round at first height
+	ensureNewStep(newBlockCh) // first block gets committed
+	ensureNewStep(newRoundCh) // first round at next height
+	deliverTxsRange(cs, 0, 1) // we deliver txs, but dont set a proposal so we get the next round
+	<-timeoutCh
+	ensureNewStep(newRoundCh) // wait for the next round
+	ensureNewStep(newBlockCh) // now we can commit the block
+}
+
+func deliverTxsRange(cs *ConsensusState, start, end int) {
+	// Deliver some txs.
+	for i := start; i < end; i++ {
+		txBytes := make([]byte, 8)
+		binary.BigEndian.PutUint64(txBytes, uint64(i))
+		err := cs.mempool.CheckTx(txBytes, nil)
+		if err != nil {
+			panic(cmn.Fmt("Error after CheckTx: %v", err))
+		}
+	}
+}
+
+func TestMempoolTxConcurrentWithCommit(t *testing.T) {
 	state, privVals := randGenesisState(1, false, 10)
 	cs := newConsensusState(state, privVals[0], NewCounterApplication())
 	height, round := cs.Height, cs.Round
-	newBlockCh := subscribeToEvent(cs.evsw, "tester", types.EventStringNewBlock(), 1)
-
-	deliverTxsRange := func(start, end int) {
-		// Deliver some txs.
-		for i := start; i < end; i++ {
-			txBytes := make([]byte, 8)
-			binary.BigEndian.PutUint64(txBytes, uint64(i))
-			err := cs.mempool.CheckTx(txBytes, nil)
-			if err != nil {
-				panic(Fmt("Error after CheckTx: %v", err))
-			}
-			//	time.Sleep(time.Microsecond * time.Duration(rand.Int63n(3000)))
-		}
-	}
+	newBlockCh := subscribe(cs.eventBus, types.EventQueryNewBlock)
 
 	NTxs := 10000
-	go deliverTxsRange(0, NTxs)
+	go deliverTxsRange(cs, 0, NTxs)
 
 	startTestRound(cs, height, round)
-	ticker := time.NewTicker(time.Second * 20)
 	for nTxs := 0; nTxs < NTxs; {
+		ticker := time.NewTicker(time.Second * 30)
 		select {
 		case b := <-newBlockCh:
-			nTxs += b.(types.EventDataNewBlock).Block.Header.NumTxs
+			evt := b.(types.EventDataNewBlock)
+			nTxs += int(evt.Block.Header.NumTxs)
 		case <-ticker.C:
 			panic("Timed out waiting to commit blocks with transactions")
 		}
 	}
 }
 
-func TestRmBadTx(t *testing.T) {
+func TestMempoolRmBadTx(t *testing.T) {
 	state, privVals := randGenesisState(1, false, 10)
 	app := NewCounterApplication()
 	cs := newConsensusState(state, privVals[0], app)
@@ -59,41 +124,44 @@ func TestRmBadTx(t *testing.T) {
 	// increment the counter by 1
 	txBytes := make([]byte, 8)
 	binary.BigEndian.PutUint64(txBytes, uint64(0))
-	app.DeliverTx(txBytes)
-	app.Commit()
 
-	ch := make(chan struct{})
-	cbCh := make(chan struct{})
+	resDeliver := app.DeliverTx(txBytes)
+	assert.False(t, resDeliver.IsErr(), cmn.Fmt("expected no error. got %v", resDeliver))
+
+	resCommit := app.Commit()
+	assert.True(t, len(resCommit.Data) > 0)
+
+	emptyMempoolCh := make(chan struct{})
+	checkTxRespCh := make(chan struct{})
 	go func() {
 		// Try to send the tx through the mempool.
 		// CheckTx should not err, but the app should return a bad abci code
 		// and the tx should get removed from the pool
 		err := cs.mempool.CheckTx(txBytes, func(r *abci.Response) {
-			if r.GetCheckTx().Code != abci.CodeType_BadNonce {
+			if r.GetCheckTx().Code != code.CodeTypeBadNonce {
 				t.Fatalf("expected checktx to return bad nonce, got %v", r)
 			}
-			cbCh <- struct{}{}
+			checkTxRespCh <- struct{}{}
 		})
 		if err != nil {
-			t.Fatal("Error after CheckTx: %v", err)
+			t.Fatalf("Error after CheckTx: %v", err)
 		}
 
 		// check for the tx
 		for {
-			time.Sleep(time.Second)
 			txs := cs.mempool.Reap(1)
 			if len(txs) == 0 {
-				ch <- struct{}{}
+				emptyMempoolCh <- struct{}{}
 				return
 			}
-
+			time.Sleep(10 * time.Millisecond)
 		}
 	}()
 
 	// Wait until the tx returns
 	ticker := time.After(time.Second * 5)
 	select {
-	case <-cbCh:
+	case <-checkTxRespCh:
 		// success
 	case <-ticker:
 		t.Fatalf("Timed out waiting for tx to return")
@@ -102,7 +170,7 @@ func TestRmBadTx(t *testing.T) {
 	// Wait until the tx is removed
 	ticker = time.After(time.Second * 5)
 	select {
-	case <-ch:
+	case <-emptyMempoolCh:
 		// success
 	case <-ticker:
 		t.Fatalf("Timed out waiting for tx to be removed")
@@ -121,37 +189,44 @@ func NewCounterApplication() *CounterApplication {
 	return &CounterApplication{}
 }
 
-func (app *CounterApplication) Info() abci.ResponseInfo {
-	return abci.ResponseInfo{Data: Fmt("txs:%v", app.txCount)}
+func (app *CounterApplication) Info(req abci.RequestInfo) abci.ResponseInfo {
+	return abci.ResponseInfo{Data: cmn.Fmt("txs:%v", app.txCount)}
 }
 
-func (app *CounterApplication) DeliverTx(tx []byte) abci.Result {
-	return runTx(tx, &app.txCount)
+func (app *CounterApplication) DeliverTx(tx []byte) abci.ResponseDeliverTx {
+	txValue := txAsUint64(tx)
+	if txValue != uint64(app.txCount) {
+		return abci.ResponseDeliverTx{
+			Code: code.CodeTypeBadNonce,
+			Log:  fmt.Sprintf("Invalid nonce. Expected %v, got %v", app.txCount, txValue)}
+	}
+	app.txCount++
+	return abci.ResponseDeliverTx{Code: code.CodeTypeOK}
 }
 
-func (app *CounterApplication) CheckTx(tx []byte) abci.Result {
-	return runTx(tx, &app.mempoolTxCount)
+func (app *CounterApplication) CheckTx(tx []byte) abci.ResponseCheckTx {
+	txValue := txAsUint64(tx)
+	if txValue != uint64(app.mempoolTxCount) {
+		return abci.ResponseCheckTx{
+			Code: code.CodeTypeBadNonce,
+			Log:  fmt.Sprintf("Invalid nonce. Expected %v, got %v", app.mempoolTxCount, txValue)}
+	}
+	app.mempoolTxCount++
+	return abci.ResponseCheckTx{Code: code.CodeTypeOK}
 }
 
-func runTx(tx []byte, countPtr *int) abci.Result {
-	count := *countPtr
+func txAsUint64(tx []byte) uint64 {
 	tx8 := make([]byte, 8)
 	copy(tx8[len(tx8)-len(tx):], tx)
-	txValue := binary.BigEndian.Uint64(tx8)
-	if txValue != uint64(count) {
-		return abci.ErrBadNonce.AppendLog(Fmt("Invalid nonce. Expected %v, got %v", count, txValue))
-	}
-	*countPtr += 1
-	return abci.OK
+	return binary.BigEndian.Uint64(tx8)
 }
 
-func (app *CounterApplication) Commit() abci.Result {
+func (app *CounterApplication) Commit() abci.ResponseCommit {
 	app.mempoolTxCount = app.txCount
 	if app.txCount == 0 {
-		return abci.OK
-	} else {
-		hash := make([]byte, 8)
-		binary.BigEndian.PutUint64(hash, uint64(app.txCount))
-		return abci.NewResultOK(hash, "")
+		return abci.ResponseCommit{}
 	}
+	hash := make([]byte, 8)
+	binary.BigEndian.PutUint64(hash, uint64(app.txCount))
+	return abci.ResponseCommit{Data: hash}
 }

consensus/reactor_test.go

@@ -1,88 +1,243 @@
 package consensus
 
 import (
+	"context"
 	"fmt"
+	"os"
+	"runtime"
+	"runtime/pprof"
 	"sync"
 	"testing"
 	"time"
 
-	"github.com/tendermint/tendermint/config/tendermint_test"
+	"github.com/tendermint/abci/example/kvstore"
+	cmn "github.com/tendermint/tmlibs/common"
+	"github.com/tendermint/tmlibs/log"
 
-	"github.com/tendermint/go-events"
-	"github.com/tendermint/go-p2p"
+	cfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tendermint/p2p"
+	p2pdummy "github.com/tendermint/tendermint/p2p/dummy"
 	"github.com/tendermint/tendermint/types"
-	"github.com/tendermint/abci/example/dummy"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
 )
 
 func init() {
-	config = tendermint_test.ResetConfig("consensus_reactor_test")
+	config = ResetConfig("consensus_reactor_test")
 }
 
 //----------------------------------------------
 // in-process testnets
 
-func startConsensusNet(t *testing.T, css []*ConsensusState, N int, subscribeEventRespond bool) ([]*ConsensusReactor, []chan interface{}) {
+func startConsensusNet(t *testing.T, css []*ConsensusState, N int) ([]*ConsensusReactor, []chan interface{}, []*types.EventBus) {
 	reactors := make([]*ConsensusReactor, N)
 	eventChans := make([]chan interface{}, N)
+	eventBuses := make([]*types.EventBus, N)
 	for i := 0; i < N; i++ {
+		/*logger, err := tmflags.ParseLogLevel("consensus:info,*:error", logger, "info")
+		if err != nil {	t.Fatal(err)}*/
 		reactors[i] = NewConsensusReactor(css[i], true) // so we dont start the consensus states
+		reactors[i].SetLogger(css[i].Logger)
 
-		eventSwitch := events.NewEventSwitch()
-		_, err := eventSwitch.Start()
-		if err != nil {
-			t.Fatalf("Failed to start switch: %v", err)
-		}
+		// eventBus is already started with the cs
+		eventBuses[i] = css[i].eventBus
+		reactors[i].SetEventBus(eventBuses[i])
 
-		reactors[i].SetEventSwitch(eventSwitch)
-		if subscribeEventRespond {
-			eventChans[i] = subscribeToEventRespond(eventSwitch, "tester", types.EventStringNewBlock())
-		} else {
-			eventChans[i] = subscribeToEvent(eventSwitch, "tester", types.EventStringNewBlock(), 1)
-		}
+		eventChans[i] = make(chan interface{}, 1)
+		err := eventBuses[i].Subscribe(context.Background(), testSubscriber, types.EventQueryNewBlock, eventChans[i])
+		require.NoError(t, err)
 	}
 	// make connected switches and start all reactors
-	p2p.MakeConnectedSwitches(N, func(i int, s *p2p.Switch) *p2p.Switch {
+	p2p.MakeConnectedSwitches(config.P2P, N, func(i int, s *p2p.Switch) *p2p.Switch {
 		s.AddReactor("CONSENSUS", reactors[i])
+		s.SetLogger(reactors[i].conS.Logger.With("module", "p2p"))
 		return s
 	}, p2p.Connect2Switches)
 
 	// now that everyone is connected,  start the state machines
 	// If we started the state machines before everyone was connected,
 	// we'd block when the cs fires NewBlockEvent and the peers are trying to start their reactors
+	// TODO: is this still true with new pubsub?
 	for i := 0; i < N; i++ {
 		s := reactors[i].conS.GetState()
-		reactors[i].SwitchToConsensus(s)
+		reactors[i].SwitchToConsensus(s, 0)
 	}
-	return reactors, eventChans
+	return reactors, eventChans, eventBuses
 }
 
-func stopConsensusNet(reactors []*ConsensusReactor) {
-	for _, r := range reactors {
+func stopConsensusNet(logger log.Logger, reactors []*ConsensusReactor, eventBuses []*types.EventBus) {
+	logger.Info("stopConsensusNet", "n", len(reactors))
+	for i, r := range reactors {
+		logger.Info("stopConsensusNet: Stopping ConsensusReactor", "i", i)
 		r.Switch.Stop()
 	}
+	for i, b := range eventBuses {
+		logger.Info("stopConsensusNet: Stopping eventBus", "i", i)
+		b.Stop()
+	}
+	logger.Info("stopConsensusNet: DONE", "n", len(reactors))
 }
 
 // Ensure a testnet makes blocks
-func TestReactor(t *testing.T) {
+func TestReactorBasic(t *testing.T) {
 	N := 4
 	css := randConsensusNet(N, "consensus_reactor_test", newMockTickerFunc(true), newCounter)
-	reactors, eventChans := startConsensusNet(t, css, N, false)
-	defer stopConsensusNet(reactors)
+	reactors, eventChans, eventBuses := startConsensusNet(t, css, N)
+	defer stopConsensusNet(log.TestingLogger(), reactors, eventBuses)
 	// wait till everyone makes the first new block
-	timeoutWaitGroup(t, N, func(wg *sync.WaitGroup, j int) {
+	timeoutWaitGroup(t, N, func(j int) {
 		<-eventChans[j]
-		wg.Done()
 	}, css)
 }
 
+// Ensure a testnet sends proposal heartbeats and makes blocks when there are txs
+func TestReactorProposalHeartbeats(t *testing.T) {
+	N := 4
+	css := randConsensusNet(N, "consensus_reactor_test", newMockTickerFunc(true), newCounter,
+		func(c *cfg.Config) {
+			c.Consensus.CreateEmptyBlocks = false
+		})
+	reactors, eventChans, eventBuses := startConsensusNet(t, css, N)
+	defer stopConsensusNet(log.TestingLogger(), reactors, eventBuses)
+	heartbeatChans := make([]chan interface{}, N)
+	var err error
+	for i := 0; i < N; i++ {
+		heartbeatChans[i] = make(chan interface{}, 1)
+		err = eventBuses[i].Subscribe(context.Background(), testSubscriber, types.EventQueryProposalHeartbeat, heartbeatChans[i])
+		require.NoError(t, err)
+	}
+	// wait till everyone sends a proposal heartbeat
+	timeoutWaitGroup(t, N, func(j int) {
+		<-heartbeatChans[j]
+	}, css)
+
+	// send a tx
+	if err := css[3].mempool.CheckTx([]byte{1, 2, 3}, nil); err != nil {
+		//t.Fatal(err)
+	}
+
+	// wait till everyone makes the first new block
+	timeoutWaitGroup(t, N, func(j int) {
+		<-eventChans[j]
+	}, css)
+}
+
+// Test we record block parts from other peers
+func TestReactorRecordsBlockParts(t *testing.T) {
+	// create dummy peer
+	peer := p2pdummy.NewPeer()
+	ps := NewPeerState(peer).SetLogger(log.TestingLogger())
+	peer.Set(types.PeerStateKey, ps)
+
+	// create reactor
+	css := randConsensusNet(1, "consensus_reactor_records_block_parts_test", newMockTickerFunc(true), newPersistentKVStore)
+	reactor := NewConsensusReactor(css[0], false) // so we dont start the consensus states
+	reactor.SetEventBus(css[0].eventBus)
+	reactor.SetLogger(log.TestingLogger())
+	sw := p2p.MakeSwitch(cfg.DefaultP2PConfig(), 1, "testing", "123.123.123", func(i int, sw *p2p.Switch) *p2p.Switch { return sw })
+	reactor.SetSwitch(sw)
+	err := reactor.Start()
+	require.NoError(t, err)
+	defer reactor.Stop()
+
+	// 1) new block part
+	parts := types.NewPartSetFromData(cmn.RandBytes(100), 10)
+	msg := &BlockPartMessage{
+		Height: 2,
+		Round:  0,
+		Part:   parts.GetPart(0),
+	}
+	bz, err := cdc.MarshalBinaryBare(msg)
+	require.NoError(t, err)
+
+	reactor.Receive(DataChannel, peer, bz)
+	require.Equal(t, 1, ps.BlockPartsSent(), "number of block parts sent should have increased by 1")
+
+	// 2) block part with the same height, but different round
+	msg.Round = 1
+
+	bz, err = cdc.MarshalBinaryBare(msg)
+	require.NoError(t, err)
+
+	reactor.Receive(DataChannel, peer, bz)
+	require.Equal(t, 1, ps.BlockPartsSent(), "number of block parts sent should stay the same")
+
+	// 3) block part from earlier height
+	msg.Height = 1
+	msg.Round = 0
+
+	bz, err = cdc.MarshalBinaryBare(msg)
+	require.NoError(t, err)
+
+	reactor.Receive(DataChannel, peer, bz)
+	require.Equal(t, 1, ps.BlockPartsSent(), "number of block parts sent should stay the same")
+}
+
+// Test we record votes from other peers
+func TestReactorRecordsVotes(t *testing.T) {
+	// create dummy peer
+	peer := p2pdummy.NewPeer()
+	ps := NewPeerState(peer).SetLogger(log.TestingLogger())
+	peer.Set(types.PeerStateKey, ps)
+
+	// create reactor
+	css := randConsensusNet(1, "consensus_reactor_records_votes_test", newMockTickerFunc(true), newPersistentKVStore)
+	reactor := NewConsensusReactor(css[0], false) // so we dont start the consensus states
+	reactor.SetEventBus(css[0].eventBus)
+	reactor.SetLogger(log.TestingLogger())
+	sw := p2p.MakeSwitch(cfg.DefaultP2PConfig(), 1, "testing", "123.123.123", func(i int, sw *p2p.Switch) *p2p.Switch { return sw })
+	reactor.SetSwitch(sw)
+	err := reactor.Start()
+	require.NoError(t, err)
+	defer reactor.Stop()
+	_, val := css[0].state.Validators.GetByIndex(0)
+
+	// 1) new vote
+	vote := &types.Vote{
+		ValidatorIndex:   0,
+		ValidatorAddress: val.Address,
+		Height:           2,
+		Round:            0,
+		Timestamp:        time.Now().UTC(),
+		Type:             types.VoteTypePrevote,
+		BlockID:          types.BlockID{},
+	}
+	bz, err := cdc.MarshalBinaryBare(&VoteMessage{vote})
+	require.NoError(t, err)
+
+	reactor.Receive(VoteChannel, peer, bz)
+	assert.Equal(t, 1, ps.VotesSent(), "number of votes sent should have increased by 1")
+
+	// 2) vote with the same height, but different round
+	vote.Round = 1
+
+	bz, err = cdc.MarshalBinaryBare(&VoteMessage{vote})
+	require.NoError(t, err)
+
+	reactor.Receive(VoteChannel, peer, bz)
+	assert.Equal(t, 1, ps.VotesSent(), "number of votes sent should stay the same")
+
+	// 3) vote from earlier height
+	vote.Height = 1
+	vote.Round = 0
+
+	bz, err = cdc.MarshalBinaryBare(&VoteMessage{vote})
+	require.NoError(t, err)
+
+	reactor.Receive(VoteChannel, peer, bz)
+	assert.Equal(t, 1, ps.VotesSent(), "number of votes sent should stay the same")
+}
+
 //-------------------------------------------------------------
 // ensure we can make blocks despite cycling a validator set
 
-func TestVotingPowerChange(t *testing.T) {
+func TestReactorVotingPowerChange(t *testing.T) {
 	nVals := 4
-	css := randConsensusNet(nVals, "consensus_voting_power_changes_test", newMockTickerFunc(true), newPersistentDummy)
-	reactors, eventChans := startConsensusNet(t, css, nVals, true)
-	defer stopConsensusNet(reactors)
+	logger := log.TestingLogger()
+	css := randConsensusNet(nVals, "consensus_voting_power_changes_test", newMockTickerFunc(true), newPersistentKVStore)
+	reactors, eventChans, eventBuses := startConsensusNet(t, css, nVals)
+	defer stopConsensusNet(logger, reactors, eventBuses)
 
 	// map of active validators
 	activeVals := make(map[string]struct{})
@@ -91,21 +246,19 @@ func TestVotingPowerChange(t *testing.T) {
 	}
 
 	// wait till everyone makes block 1
-	timeoutWaitGroup(t, nVals, func(wg *sync.WaitGroup, j int) {
+	timeoutWaitGroup(t, nVals, func(j int) {
 		<-eventChans[j]
-		eventChans[j] <- struct{}{}
-		wg.Done()
 	}, css)
 
 	//---------------------------------------------------------------------------
-	log.Info("---------------------------- Testing changing the voting power of one validator a few times")
+	logger.Debug("---------------------------- Testing changing the voting power of one validator a few times")
 
-	val1PubKey := css[0].privValidator.(*types.PrivValidator).PubKey
-	updateValidatorTx := dummy.MakeValSetChangeTx(val1PubKey.Bytes(), 25)
+	val1PubKey := css[0].privValidator.GetPubKey()
+	updateValidatorTx := kvstore.MakeValSetChangeTx(val1PubKey.Bytes(), 25)
 	previousTotalVotingPower := css[0].GetRoundState().LastValidators.TotalVotingPower()
 
 	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css, updateValidatorTx)
-	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
+	waitForAndValidateBlockWithTx(t, nVals, activeVals, eventChans, css, updateValidatorTx)
 	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
 	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
 
@@ -113,11 +266,11 @@ func TestVotingPowerChange(t *testing.T) {
 		t.Fatalf("expected voting power to change (before: %d, after: %d)", previousTotalVotingPower, css[0].GetRoundState().LastValidators.TotalVotingPower())
 	}
 
-	updateValidatorTx = dummy.MakeValSetChangeTx(val1PubKey.Bytes(), 2)
+	updateValidatorTx = kvstore.MakeValSetChangeTx(val1PubKey.Bytes(), 2)
 	previousTotalVotingPower = css[0].GetRoundState().LastValidators.TotalVotingPower()
 
 	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css, updateValidatorTx)
-	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
+	waitForAndValidateBlockWithTx(t, nVals, activeVals, eventChans, css, updateValidatorTx)
 	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
 	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
 
@@ -125,11 +278,11 @@ func TestVotingPowerChange(t *testing.T) {
 		t.Fatalf("expected voting power to change (before: %d, after: %d)", previousTotalVotingPower, css[0].GetRoundState().LastValidators.TotalVotingPower())
 	}
 
-	updateValidatorTx = dummy.MakeValSetChangeTx(val1PubKey.Bytes(), 100)
+	updateValidatorTx = kvstore.MakeValSetChangeTx(val1PubKey.Bytes(), 26)
 	previousTotalVotingPower = css[0].GetRoundState().LastValidators.TotalVotingPower()
 
 	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css, updateValidatorTx)
-	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
+	waitForAndValidateBlockWithTx(t, nVals, activeVals, eventChans, css, updateValidatorTx)
 	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
 	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
 
@@ -138,12 +291,15 @@ func TestVotingPowerChange(t *testing.T) {
 	}
 }
 
-func TestValidatorSetChanges(t *testing.T) {
+func TestReactorValidatorSetChanges(t *testing.T) {
 	nPeers := 7
 	nVals := 4
-	css := randConsensusNetWithPeers(nVals, nPeers, "consensus_val_set_changes_test", newMockTickerFunc(true), newPersistentDummy)
-	reactors, eventChans := startConsensusNet(t, css, nPeers, true)
-	defer stopConsensusNet(reactors)
+	css := randConsensusNetWithPeers(nVals, nPeers, "consensus_val_set_changes_test", newMockTickerFunc(true), newPersistentKVStore)
+
+	logger := log.TestingLogger()
+
+	reactors, eventChans, eventBuses := startConsensusNet(t, css, nPeers)
+	defer stopConsensusNet(logger, reactors, eventBuses)
 
 	// map of active validators
 	activeVals := make(map[string]struct{})
@@ -152,17 +308,15 @@ func TestValidatorSetChanges(t *testing.T) {
 	}
 
 	// wait till everyone makes block 1
-	timeoutWaitGroup(t, nPeers, func(wg *sync.WaitGroup, j int) {
+	timeoutWaitGroup(t, nPeers, func(j int) {
 		<-eventChans[j]
-		eventChans[j] <- struct{}{}
-		wg.Done()
 	}, css)
 
 	//---------------------------------------------------------------------------
-	log.Info("---------------------------- Testing adding one validator")
+	logger.Info("---------------------------- Testing adding one validator")
 
-	newValidatorPubKey1 := css[nVals].privValidator.(*types.PrivValidator).PubKey
-	newValidatorTx1 := dummy.MakeValSetChangeTx(newValidatorPubKey1.Bytes(), uint64(testMinPower))
+	newValidatorPubKey1 := css[nVals].privValidator.GetPubKey()
+	newValidatorTx1 := kvstore.MakeValSetChangeTx(newValidatorPubKey1.Bytes(), testMinPower)
 
 	// wait till everyone makes block 2
 	// ensure the commit includes all validators
@@ -171,7 +325,7 @@ func TestValidatorSetChanges(t *testing.T) {
 
 	// wait till everyone makes block 3.
 	// it includes the commit for block 2, which is by the original validator set
-	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
+	waitForAndValidateBlockWithTx(t, nPeers, activeVals, eventChans, css, newValidatorTx1)
 
 	// wait till everyone makes block 4.
 	// it includes the commit for block 3, which is by the original validator set
@@ -182,52 +336,52 @@ func TestValidatorSetChanges(t *testing.T) {
 
 	// wait till everyone makes block 5
 	// it includes the commit for block 4, which should have the updated validator set
-	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
+	waitForBlockWithUpdatedValsAndValidateIt(t, nPeers, activeVals, eventChans, css)
 
 	//---------------------------------------------------------------------------
-	log.Info("---------------------------- Testing changing the voting power of one validator")
+	logger.Info("---------------------------- Testing changing the voting power of one validator")
 
-	updateValidatorPubKey1 := css[nVals].privValidator.(*types.PrivValidator).PubKey
-	updateValidatorTx1 := dummy.MakeValSetChangeTx(updateValidatorPubKey1.Bytes(), 25)
+	updateValidatorPubKey1 := css[nVals].privValidator.GetPubKey()
+	updateValidatorTx1 := kvstore.MakeValSetChangeTx(updateValidatorPubKey1.Bytes(), 25)
 	previousTotalVotingPower := css[nVals].GetRoundState().LastValidators.TotalVotingPower()
 
 	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css, updateValidatorTx1)
+	waitForAndValidateBlockWithTx(t, nPeers, activeVals, eventChans, css, updateValidatorTx1)
 	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
-	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
-	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
+	waitForBlockWithUpdatedValsAndValidateIt(t, nPeers, activeVals, eventChans, css)
 
 	if css[nVals].GetRoundState().LastValidators.TotalVotingPower() == previousTotalVotingPower {
 		t.Errorf("expected voting power to change (before: %d, after: %d)", previousTotalVotingPower, css[nVals].GetRoundState().LastValidators.TotalVotingPower())
 	}
 
 	//---------------------------------------------------------------------------
-	log.Info("---------------------------- Testing adding two validators at once")
+	logger.Info("---------------------------- Testing adding two validators at once")
 
-	newValidatorPubKey2 := css[nVals+1].privValidator.(*types.PrivValidator).PubKey
-	newValidatorTx2 := dummy.MakeValSetChangeTx(newValidatorPubKey2.Bytes(), uint64(testMinPower))
+	newValidatorPubKey2 := css[nVals+1].privValidator.GetPubKey()
+	newValidatorTx2 := kvstore.MakeValSetChangeTx(newValidatorPubKey2.Bytes(), testMinPower)
 
-	newValidatorPubKey3 := css[nVals+2].privValidator.(*types.PrivValidator).PubKey
-	newValidatorTx3 := dummy.MakeValSetChangeTx(newValidatorPubKey3.Bytes(), uint64(testMinPower))
+	newValidatorPubKey3 := css[nVals+2].privValidator.GetPubKey()
+	newValidatorTx3 := kvstore.MakeValSetChangeTx(newValidatorPubKey3.Bytes(), testMinPower)
 
 	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css, newValidatorTx2, newValidatorTx3)
-	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
+	waitForAndValidateBlockWithTx(t, nPeers, activeVals, eventChans, css, newValidatorTx2, newValidatorTx3)
 	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
 	activeVals[string(newValidatorPubKey2.Address())] = struct{}{}
 	activeVals[string(newValidatorPubKey3.Address())] = struct{}{}
-	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
+	waitForBlockWithUpdatedValsAndValidateIt(t, nPeers, activeVals, eventChans, css)
 
 	//---------------------------------------------------------------------------
-	log.Info("---------------------------- Testing removing two validators at once")
+	logger.Info("---------------------------- Testing removing two validators at once")
 
-	removeValidatorTx2 := dummy.MakeValSetChangeTx(newValidatorPubKey2.Bytes(), 0)
-	removeValidatorTx3 := dummy.MakeValSetChangeTx(newValidatorPubKey3.Bytes(), 0)
+	removeValidatorTx2 := kvstore.MakeValSetChangeTx(newValidatorPubKey2.Bytes(), 0)
+	removeValidatorTx3 := kvstore.MakeValSetChangeTx(newValidatorPubKey3.Bytes(), 0)
 
 	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css, removeValidatorTx2, removeValidatorTx3)
-	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
+	waitForAndValidateBlockWithTx(t, nPeers, activeVals, eventChans, css, removeValidatorTx2, removeValidatorTx3)
 	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
 	delete(activeVals, string(newValidatorPubKey2.Address()))
 	delete(activeVals, string(newValidatorPubKey3.Address()))
-	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
+	waitForBlockWithUpdatedValsAndValidateIt(t, nPeers, activeVals, eventChans, css)
 }
 
 // Check we can make blocks with skip_timeout_commit=false
@@ -236,35 +390,89 @@ func TestReactorWithTimeoutCommit(t *testing.T) {
 	css := randConsensusNet(N, "consensus_reactor_with_timeout_commit_test", newMockTickerFunc(false), newCounter)
 	// override default SkipTimeoutCommit == true for tests
 	for i := 0; i < N; i++ {
-		css[i].timeoutParams.SkipTimeoutCommit = false
+		css[i].config.SkipTimeoutCommit = false
 	}
 
-	reactors, eventChans := startConsensusNet(t, css, N-1, false)
-	defer stopConsensusNet(reactors)
+	reactors, eventChans, eventBuses := startConsensusNet(t, css, N-1)
+	defer stopConsensusNet(log.TestingLogger(), reactors, eventBuses)
 
 	// wait till everyone makes the first new block
-	timeoutWaitGroup(t, N-1, func(wg *sync.WaitGroup, j int) {
+	timeoutWaitGroup(t, N-1, func(j int) {
 		<-eventChans[j]
-		wg.Done()
 	}, css)
 }
 
 func waitForAndValidateBlock(t *testing.T, n int, activeVals map[string]struct{}, eventChans []chan interface{}, css []*ConsensusState, txs ...[]byte) {
-	timeoutWaitGroup(t, n, func(wg *sync.WaitGroup, j int) {
-		newBlockI := <-eventChans[j]
-		newBlock := newBlockI.(types.EventDataNewBlock).Block
-		log.Warn("Got block", "height", newBlock.Height, "validator", j)
-		err := validateBlock(newBlock, activeVals)
-		if err != nil {
-			t.Fatal(err)
+	timeoutWaitGroup(t, n, func(j int) {
+		css[j].Logger.Debug("waitForAndValidateBlock")
+		newBlockI, ok := <-eventChans[j]
+		if !ok {
+			return
 		}
+		newBlock := newBlockI.(types.EventDataNewBlock).Block
+		css[j].Logger.Debug("waitForAndValidateBlock: Got block", "height", newBlock.Height)
+		err := validateBlock(newBlock, activeVals)
+		assert.Nil(t, err)
 		for _, tx := range txs {
 			css[j].mempool.CheckTx(tx, nil)
+			assert.Nil(t, err)
+		}
+	}, css)
+}
+
+func waitForAndValidateBlockWithTx(t *testing.T, n int, activeVals map[string]struct{}, eventChans []chan interface{}, css []*ConsensusState, txs ...[]byte) {
+	timeoutWaitGroup(t, n, func(j int) {
+		ntxs := 0
+	BLOCK_TX_LOOP:
+		for {
+			css[j].Logger.Debug("waitForAndValidateBlockWithTx", "ntxs", ntxs)
+			newBlockI, ok := <-eventChans[j]
+			if !ok {
+				return
+			}
+			newBlock := newBlockI.(types.EventDataNewBlock).Block
+			css[j].Logger.Debug("waitForAndValidateBlockWithTx: Got block", "height", newBlock.Height)
+			err := validateBlock(newBlock, activeVals)
+			assert.Nil(t, err)
+
+			// check that txs match the txs we're waiting for.
+			// note they could be spread over multiple blocks,
+			// but they should be in order.
+			for _, tx := range newBlock.Data.Txs {
+				assert.EqualValues(t, txs[ntxs], tx)
+				ntxs++
+			}
+
+			if ntxs == len(txs) {
+				break BLOCK_TX_LOOP
+			}
 		}
 
-		eventChans[j] <- struct{}{}
-		wg.Done()
-		log.Warn("Done wait group", "height", newBlock.Height, "validator", j)
+	}, css)
+}
+
+func waitForBlockWithUpdatedValsAndValidateIt(t *testing.T, n int, updatedVals map[string]struct{}, eventChans []chan interface{}, css []*ConsensusState) {
+	timeoutWaitGroup(t, n, func(j int) {
+
+		var newBlock *types.Block
+	LOOP:
+		for {
+			css[j].Logger.Debug("waitForBlockWithUpdatedValsAndValidateIt")
+			newBlockI, ok := <-eventChans[j]
+			if !ok {
+				return
+			}
+			newBlock = newBlockI.(types.EventDataNewBlock).Block
+			if newBlock.LastCommit.Size() == len(updatedVals) {
+				css[j].Logger.Debug("waitForBlockWithUpdatedValsAndValidateIt: Got block", "height", newBlock.Height)
+				break LOOP
+			} else {
+				css[j].Logger.Debug("waitForBlockWithUpdatedValsAndValidateIt: Got block with no new validators. Skipping", "height", newBlock.Height)
+			}
+		}
+
+		err := validateBlock(newBlock, updatedVals)
+		assert.Nil(t, err)
 	}, css)
 }
 
@@ -282,11 +490,14 @@ func validateBlock(block *types.Block, activeVals map[string]struct{}) error {
 	return nil
 }
 
-func timeoutWaitGroup(t *testing.T, n int, f func(*sync.WaitGroup, int), css []*ConsensusState) {
+func timeoutWaitGroup(t *testing.T, n int, f func(int), css []*ConsensusState) {
 	wg := new(sync.WaitGroup)
 	wg.Add(n)
 	for i := 0; i < n; i++ {
-		go f(wg, i)
+		go func(j int) {
+			f(j)
+			wg.Done()
+		}(i)
 	}
 
 	done := make(chan struct{})
@@ -295,15 +506,28 @@ func timeoutWaitGroup(t *testing.T, n int, f func(*sync.WaitGroup, int), css []*
 		close(done)
 	}()
 
+	// we're running many nodes in-process, possibly in in a virtual machine,
+	// and spewing debug messages - making a block could take a while,
+	timeout := time.Second * 300
+
 	select {
 	case <-done:
-	case <-time.After(time.Second * 10):
+	case <-time.After(timeout):
 		for i, cs := range css {
-			fmt.Println("#################")
-			fmt.Println("Validator", i)
-			fmt.Println(cs.GetRoundState())
-			fmt.Println("")
+			t.Log("#################")
+			t.Log("Validator", i)
+			t.Log(cs.GetRoundState())
+			t.Log("")
 		}
+		os.Stdout.Write([]byte("pprof.Lookup('goroutine'):\n"))
+		pprof.Lookup("goroutine").WriteTo(os.Stdout, 1)
+		capture()
 		panic("Timed out waiting for all validators to commit a block")
 	}
 }
+
+func capture() {
+	trace := make([]byte, 10240000)
+	count := runtime.Stack(trace, true)
+	fmt.Printf("Stack of %d bytes: %s\n", count, trace)
+}

consensus/replay.go

@@ -2,25 +2,29 @@ package consensus
 
 import (
 	"bytes"
-	"errors"
+	"encoding/json"
 	"fmt"
+	"hash/crc32"
 	"io"
 	"reflect"
-	"strconv"
-	"strings"
+	//"strconv"
+	//"strings"
 	"time"
 
 	abci "github.com/tendermint/abci/types"
-	auto "github.com/tendermint/go-autofile"
-	. "github.com/tendermint/go-common"
-	cfg "github.com/tendermint/go-config"
-	"github.com/tendermint/go-wire"
+	//auto "github.com/tendermint/tmlibs/autofile"
+	cmn "github.com/tendermint/tmlibs/common"
+	dbm "github.com/tendermint/tmlibs/db"
+	"github.com/tendermint/tmlibs/log"
 
 	"github.com/tendermint/tendermint/proxy"
 	sm "github.com/tendermint/tendermint/state"
 	"github.com/tendermint/tendermint/types"
+	"github.com/tendermint/tendermint/version"
 )
 
+var crc32c = crc32.MakeTable(crc32.Castagnoli)
+
 // Functionality to replay blocks and messages on recovery from a crash.
 // There are two general failure scenarios: failure during consensus, and failure while applying the block.
 // The former is handled by the WAL, the latter by the proxyApp Handshake on restart,
@@ -34,23 +38,16 @@ import (
 // as if it were received in receiveRoutine
 // Lines that start with "#" are ignored.
 // NOTE: receiveRoutine should not be running
-func (cs *ConsensusState) readReplayMessage(msgBytes []byte, newStepCh chan interface{}) error {
-	// Skip over empty and meta lines
-	if len(msgBytes) == 0 || msgBytes[0] == '#' {
+func (cs *ConsensusState) readReplayMessage(msg *TimedWALMessage, newStepCh chan interface{}) error {
+	// skip meta messages
+	if _, ok := msg.Msg.(EndHeightMessage); ok {
 		return nil
 	}
-	var err error
-	var msg TimedWALMessage
-	wire.ReadJSON(&msg, msgBytes, &err)
-	if err != nil {
-		fmt.Println("MsgBytes:", msgBytes, string(msgBytes))
-		return fmt.Errorf("Error reading json data: %v", err)
-	}
 
 	// for logging
 	switch m := msg.Msg.(type) {
 	case types.EventDataRoundState:
-		log.Notice("Replay: New Step", "height", m.Height, "round", m.Round, "step", m.Step)
+		cs.Logger.Info("Replay: New Step", "height", m.Height, "round", m.Round, "step", m.Step)
 		// these are playback checks
 		ticker := time.After(time.Second * 2)
 		if newStepCh != nil {
@@ -65,26 +62,26 @@ func (cs *ConsensusState) readReplayMessage(msgBytes []byte, newStepCh chan inte
 			}
 		}
 	case msgInfo:
-		peerKey := m.PeerKey
-		if peerKey == "" {
-			peerKey = "local"
+		peerID := m.PeerID
+		if peerID == "" {
+			peerID = "local"
 		}
 		switch msg := m.Msg.(type) {
 		case *ProposalMessage:
 			p := msg.Proposal
-			log.Notice("Replay: Proposal", "height", p.Height, "round", p.Round, "header",
-				p.BlockPartsHeader, "pol", p.POLRound, "peer", peerKey)
+			cs.Logger.Info("Replay: Proposal", "height", p.Height, "round", p.Round, "header",
+				p.BlockPartsHeader, "pol", p.POLRound, "peer", peerID)
 		case *BlockPartMessage:
-			log.Notice("Replay: BlockPart", "height", msg.Height, "round", msg.Round, "peer", peerKey)
+			cs.Logger.Info("Replay: BlockPart", "height", msg.Height, "round", msg.Round, "peer", peerID)
 		case *VoteMessage:
 			v := msg.Vote
-			log.Notice("Replay: Vote", "height", v.Height, "round", v.Round, "type", v.Type,
-				"blockID", v.BlockID, "peer", peerKey)
+			cs.Logger.Info("Replay: Vote", "height", v.Height, "round", v.Round, "type", v.Type,
+				"blockID", v.BlockID, "peer", peerID)
 		}
 
-		cs.handleMsg(m, cs.RoundState)
+		cs.handleMsg(m)
 	case timeoutInfo:
-		log.Notice("Replay: Timeout", "height", m.Height, "round", m.Round, "step", m.Step, "dur", m.Duration)
+		cs.Logger.Info("Replay: Timeout", "height", m.Height, "round", m.Round, "step", m.Step, "dur", m.Duration)
 		cs.handleTimeout(m, cs.RoundState)
 	default:
 		return fmt.Errorf("Replay: Unknown TimedWALMessage type: %v", reflect.TypeOf(msg.Msg))
@@ -94,77 +91,68 @@ func (cs *ConsensusState) readReplayMessage(msgBytes []byte, newStepCh chan inte
 
 // replay only those messages since the last block.
 // timeoutRoutine should run concurrently to read off tickChan
-func (cs *ConsensusState) catchupReplay(csHeight int) error {
-
+func (cs *ConsensusState) catchupReplay(csHeight int64) error {
 	// set replayMode
 	cs.replayMode = true
 	defer func() { cs.replayMode = false }()
 
-	// Ensure that ENDHEIGHT for this height doesn't exist
-	// NOTE: This is just a sanity check. As far as we know things work fine without it,
-	// and Handshake could reuse ConsensusState if it weren't for this check (since we can crash after writing ENDHEIGHT).
-	gr, found, err := cs.wal.group.Search("#ENDHEIGHT: ", makeHeightSearchFunc(csHeight))
+	// Ensure that ENDHEIGHT for this height doesn't exist.
+	// NOTE: This is just a sanity check. As far as we know things work fine
+	// without it, and Handshake could reuse ConsensusState if it weren't for
+	// this check (since we can crash after writing ENDHEIGHT).
+	//
+	// Ignore data corruption errors since this is a sanity check.
+	gr, found, err := cs.wal.SearchForEndHeight(csHeight, &WALSearchOptions{IgnoreDataCorruptionErrors: true})
+	if err != nil {
+		return err
+	}
 	if gr != nil {
-		gr.Close()
+		if err := gr.Close(); err != nil {
+			return err
+		}
 	}
 	if found {
-		return errors.New(Fmt("WAL should not contain #ENDHEIGHT %d.", csHeight))
+		return fmt.Errorf("WAL should not contain #ENDHEIGHT %d", csHeight)
 	}
 
 	// Search for last height marker
-	gr, found, err = cs.wal.group.Search("#ENDHEIGHT: ", makeHeightSearchFunc(csHeight-1))
+	//
+	// Ignore data corruption errors in previous heights because we only care about last height
+	gr, found, err = cs.wal.SearchForEndHeight(csHeight-1, &WALSearchOptions{IgnoreDataCorruptionErrors: true})
 	if err == io.EOF {
-		log.Warn("Replay: wal.group.Search returned EOF", "#ENDHEIGHT", csHeight-1)
-		// if we upgraded from 0.9 to 0.9.1, we may have #HEIGHT instead
-		// TODO (0.10.0): remove this
-		gr, found, err = cs.wal.group.Search("#HEIGHT: ", makeHeightSearchFunc(csHeight))
-		if err == io.EOF {
-			log.Warn("Replay: wal.group.Search returned EOF", "#HEIGHT", csHeight)
-			return nil
-		} else if err != nil {
-			return err
-		}
+		cs.Logger.Error("Replay: wal.group.Search returned EOF", "#ENDHEIGHT", csHeight-1)
 	} else if err != nil {
 		return err
-	} else {
-		defer gr.Close()
 	}
 	if !found {
-		// if we upgraded from 0.9 to 0.9.1, we may have #HEIGHT instead
-		// TODO (0.10.0): remove this
-		gr, found, err = cs.wal.group.Search("#HEIGHT: ", makeHeightSearchFunc(csHeight))
-		if err == io.EOF {
-			log.Warn("Replay: wal.group.Search returned EOF", "#HEIGHT", csHeight)
-			return nil
-		} else if err != nil {
-			return err
-		} else {
-			defer gr.Close()
-		}
-
-		// TODO (0.10.0): uncomment
-		// return errors.New(Fmt("Cannot replay height %d. WAL does not contain #ENDHEIGHT for %d.", csHeight, csHeight-1))
+		return fmt.Errorf("Cannot replay height %d. WAL does not contain #ENDHEIGHT for %d", csHeight, csHeight-1)
 	}
+	defer gr.Close() // nolint: errcheck
 
-	log.Notice("Catchup by replaying consensus messages", "height", csHeight)
+	cs.Logger.Info("Catchup by replaying consensus messages", "height", csHeight)
+
+	var msg *TimedWALMessage
+	dec := WALDecoder{gr}
 
 	for {
-		line, err := gr.ReadLine()
-		if err != nil {
-			if err == io.EOF {
-				break
-			} else {
-				return err
-			}
+		msg, err = dec.Decode()
+		if err == io.EOF {
+			break
+		} else if IsDataCorruptionError(err) {
+			cs.Logger.Debug("data has been corrupted in last height of consensus WAL", "err", err, "height", csHeight)
+			panic(fmt.Sprintf("data has been corrupted (%v) in last height %d of consensus WAL", err, csHeight))
+		} else if err != nil {
+			return err
 		}
+
 		// NOTE: since the priv key is set when the msgs are received
 		// it will attempt to eg double sign but we can just ignore it
 		// since the votes will be replayed and we'll get to the next step
-		if err := cs.readReplayMessage([]byte(line), nil); err != nil {
+		if err := cs.readReplayMessage(msg, nil); err != nil {
 			return err
 		}
 	}
-	log.Notice("Replay: Done")
+	cs.Logger.Info("Replay: Done")
 	return nil
 }
 
@@ -172,7 +160,8 @@ func (cs *ConsensusState) catchupReplay(csHeight int) error {
 
 // Parses marker lines of the form:
 // #ENDHEIGHT: 12345
-func makeHeightSearchFunc(height int) auto.SearchFunc {
+/*
+func makeHeightSearchFunc(height int64) auto.SearchFunc {
 	return func(line string) (int, error) {
 		line = strings.TrimRight(line, "\n")
 		parts := strings.Split(line, " ")
@@ -191,7 +180,7 @@ func makeHeightSearchFunc(height int) auto.SearchFunc {
 			return -1, nil
 		}
 	}
-}
+}*/
 
 //----------------------------------------------
 // Recover from failure during block processing
@@ -199,49 +188,61 @@ func makeHeightSearchFunc(height int) auto.SearchFunc {
 // we were last and using the WAL to recover there
 
 type Handshaker struct {
-	config cfg.Config
-	state  *sm.State
-	store  types.BlockStore
+	stateDB      dbm.DB
+	initialState sm.State
+	store        types.BlockStore
+	appState     json.RawMessage
+	logger       log.Logger
 
 	nBlocks int // number of blocks applied to the state
 }
 
-func NewHandshaker(config cfg.Config, state *sm.State, store types.BlockStore) *Handshaker {
-	return &Handshaker{config, state, store, 0}
+func NewHandshaker(stateDB dbm.DB, state sm.State,
+	store types.BlockStore, appState json.RawMessage) *Handshaker {
+
+	return &Handshaker{
+		stateDB:      stateDB,
+		initialState: state,
+		store:        store,
+		appState:     appState,
+		logger:       log.NewNopLogger(),
+		nBlocks:      0,
+	}
+}
+
+func (h *Handshaker) SetLogger(l log.Logger) {
+	h.logger = l
 }
 
 func (h *Handshaker) NBlocks() int {
 	return h.nBlocks
 }
 
-var ErrReplayLastBlockTimeout = errors.New("Timed out waiting for last block to be replayed")
-
 // TODO: retry the handshake/replay if it fails ?
 func (h *Handshaker) Handshake(proxyApp proxy.AppConns) error {
 	// handshake is done via info request on the query conn
-	res, err := proxyApp.Query().InfoSync()
+	res, err := proxyApp.Query().InfoSync(abci.RequestInfo{version.Version})
 	if err != nil {
-		return errors.New(Fmt("Error calling Info: %v", err))
+		return fmt.Errorf("Error calling Info: %v", err)
 	}
 
-	blockHeight := int(res.LastBlockHeight) // XXX: beware overflow
+	blockHeight := int64(res.LastBlockHeight)
+	if blockHeight < 0 {
+		return fmt.Errorf("Got a negative last block height (%d) from the app", blockHeight)
+	}
 	appHash := res.LastBlockAppHash
 
-	log.Notice("ABCI Handshake", "appHeight", blockHeight, "appHash", appHash)
+	h.logger.Info("ABCI Handshake", "appHeight", blockHeight, "appHash", fmt.Sprintf("%X", appHash))
 
 	// TODO: check version
 
 	// replay blocks up to the latest in the blockstore
-	_, err = h.ReplayBlocks(appHash, blockHeight, proxyApp)
-	if err == ErrReplayLastBlockTimeout {
-		log.Warn("Failed to sync via handshake. Trying other means. If they fail, please increase the timeout_handshake parameter")
-		return nil
-
-	} else if err != nil {
-		return errors.New(Fmt("Error on replay: %v", err))
+	_, err = h.ReplayBlocks(h.initialState, appHash, blockHeight, proxyApp)
+	if err != nil {
+		return fmt.Errorf("Error on replay: %v", err)
 	}
 
-	log.Notice("Completed ABCI Handshake - Tendermint and App are synced", "appHeight", blockHeight, "appHash", appHash)
+	h.logger.Info("Completed ABCI Handshake - Tendermint and App are synced", "appHeight", blockHeight, "appHash", fmt.Sprintf("%X", appHash))
 
 	// TODO: (on restart) replay mempool
 
@@ -250,15 +251,28 @@ func (h *Handshaker) Handshake(proxyApp proxy.AppConns) error {
 
 // Replay all blocks since appBlockHeight and ensure the result matches the current state.
 // Returns the final AppHash or an error
-func (h *Handshaker) ReplayBlocks(appHash []byte, appBlockHeight int, proxyApp proxy.AppConns) ([]byte, error) {
+func (h *Handshaker) ReplayBlocks(state sm.State, appHash []byte, appBlockHeight int64, proxyApp proxy.AppConns) ([]byte, error) {
 
 	storeBlockHeight := h.store.Height()
-	stateBlockHeight := h.state.LastBlockHeight
-	log.Notice("ABCI Replay Blocks", "appHeight", appBlockHeight, "storeHeight", storeBlockHeight, "stateHeight", stateBlockHeight)
+	stateBlockHeight := state.LastBlockHeight
+	h.logger.Info("ABCI Replay Blocks", "appHeight", appBlockHeight, "storeHeight", storeBlockHeight, "stateHeight", stateBlockHeight)
+
+	// If appBlockHeight == 0 it means that we are at genesis and hence should send InitChain
+	if appBlockHeight == 0 {
+		validators := types.TM2PB.Validators(state.Validators)
+		req := abci.RequestInitChain{
+			Validators:    validators,
+			AppStateBytes: h.appState,
+		}
+		_, err := proxyApp.Consensus().InitChainSync(req)
+		if err != nil {
+			return nil, err
+		}
+	}
 
 	// First handle edge cases and constraints on the storeBlockHeight
 	if storeBlockHeight == 0 {
-		return appHash, h.checkAppHash(appHash)
+		return appHash, checkAppHash(state, appHash)
 
 	} else if storeBlockHeight < appBlockHeight {
 		// the app should never be ahead of the store (but this is under app's control)
@@ -266,13 +280,14 @@ func (h *Handshaker) ReplayBlocks(appHash []byte, appBlockHeight int, proxyApp p
 
 	} else if storeBlockHeight < stateBlockHeight {
 		// the state should never be ahead of the store (this is under tendermint's control)
-		PanicSanity(Fmt("StateBlockHeight (%d) > StoreBlockHeight (%d)", stateBlockHeight, storeBlockHeight))
+		cmn.PanicSanity(cmn.Fmt("StateBlockHeight (%d) > StoreBlockHeight (%d)", stateBlockHeight, storeBlockHeight))
 
 	} else if storeBlockHeight > stateBlockHeight+1 {
 		// store should be at most one ahead of the state (this is under tendermint's control)
-		PanicSanity(Fmt("StoreBlockHeight (%d) > StateBlockHeight + 1 (%d)", storeBlockHeight, stateBlockHeight+1))
+		cmn.PanicSanity(cmn.Fmt("StoreBlockHeight (%d) > StateBlockHeight + 1 (%d)", storeBlockHeight, stateBlockHeight+1))
 	}
 
+	var err error
 	// Now either store is equal to state, or one ahead.
 	// For each, consider all cases of where the app could be, given app <= store
 	if storeBlockHeight == stateBlockHeight {
@@ -280,11 +295,11 @@ func (h *Handshaker) ReplayBlocks(appHash []byte, appBlockHeight int, proxyApp p
 		// Either the app is asking for replay, or we're all synced up.
 		if appBlockHeight < storeBlockHeight {
 			// the app is behind, so replay blocks, but no need to go through WAL (state is already synced to store)
-			return h.replayBlocks(proxyApp, appBlockHeight, storeBlockHeight, false)
+			return h.replayBlocks(state, proxyApp, appBlockHeight, storeBlockHeight, false)
 
 		} else if appBlockHeight == storeBlockHeight {
 			// We're good!
-			return appHash, h.checkAppHash(appHash)
+			return appHash, checkAppHash(state, appHash)
 		}
 
 	} else if storeBlockHeight == stateBlockHeight+1 {
@@ -293,83 +308,96 @@ func (h *Handshaker) ReplayBlocks(appHash []byte, appBlockHeight int, proxyApp p
 		if appBlockHeight < stateBlockHeight {
 			// the app is further behind than it should be, so replay blocks
 			// but leave the last block to go through the WAL
-			return h.replayBlocks(proxyApp, appBlockHeight, storeBlockHeight, true)
+			return h.replayBlocks(state, proxyApp, appBlockHeight, storeBlockHeight, true)
 
 		} else if appBlockHeight == stateBlockHeight {
 			// We haven't run Commit (both the state and app are one block behind),
 			// so replayBlock with the real app.
 			// NOTE: We could instead use the cs.WAL on cs.Start,
 			// but we'd have to allow the WAL to replay a block that wrote it's ENDHEIGHT
-			log.Info("Replay last block using real app")
-			return h.replayBlock(storeBlockHeight, proxyApp.Consensus())
+			h.logger.Info("Replay last block using real app")
+			state, err = h.replayBlock(state, storeBlockHeight, proxyApp.Consensus())
+			return state.AppHash, err
 
 		} else if appBlockHeight == storeBlockHeight {
 			// We ran Commit, but didn't save the state, so replayBlock with mock app
-			abciResponses := h.state.LoadABCIResponses()
+			abciResponses, err := sm.LoadABCIResponses(h.stateDB, storeBlockHeight)
+			if err != nil {
+				return nil, err
+			}
 			mockApp := newMockProxyApp(appHash, abciResponses)
-			log.Info("Replay last block using mock app")
-			return h.replayBlock(storeBlockHeight, mockApp)
+			h.logger.Info("Replay last block using mock app")
+			state, err = h.replayBlock(state, storeBlockHeight, mockApp)
+			return state.AppHash, err
 		}
 
 	}
 
-	PanicSanity("Should never happen")
+	cmn.PanicSanity("Should never happen")
 	return nil, nil
 }
 
-func (h *Handshaker) replayBlocks(proxyApp proxy.AppConns, appBlockHeight, storeBlockHeight int, mutateState bool) ([]byte, error) {
+func (h *Handshaker) replayBlocks(state sm.State, proxyApp proxy.AppConns, appBlockHeight, storeBlockHeight int64, mutateState bool) ([]byte, error) {
 	// App is further behind than it should be, so we need to replay blocks.
 	// We replay all blocks from appBlockHeight+1.
+	//
 	// Note that we don't have an old version of the state,
 	// so we by-pass state validation/mutation using sm.ExecCommitBlock.
+	// This also means we won't be saving validator sets if they change during this period.
+	// TODO: Load the historical information to fix this and just use state.ApplyBlock
+	//
 	// If mutateState == true, the final block is replayed with h.replayBlock()
 
 	var appHash []byte
 	var err error
 	finalBlock := storeBlockHeight
 	if mutateState {
-		finalBlock -= 1
+		finalBlock--
 	}
 	for i := appBlockHeight + 1; i <= finalBlock; i++ {
-		log.Info("Applying block", "height", i)
+		h.logger.Info("Applying block", "height", i)
 		block := h.store.LoadBlock(i)
-		appHash, err = sm.ExecCommitBlock(proxyApp.Consensus(), block)
+		appHash, err = sm.ExecCommitBlock(proxyApp.Consensus(), block, h.logger)
 		if err != nil {
 			return nil, err
 		}
 
-		h.nBlocks += 1
+		h.nBlocks++
 	}
 
 	if mutateState {
 		// sync the final block
-		return h.replayBlock(storeBlockHeight, proxyApp.Consensus())
+		state, err = h.replayBlock(state, storeBlockHeight, proxyApp.Consensus())
+		if err != nil {
+			return nil, err
+		}
+		appHash = state.AppHash
 	}
 
-	return appHash, h.checkAppHash(appHash)
+	return appHash, checkAppHash(state, appHash)
 }
 
 // ApplyBlock on the proxyApp with the last block.
-func (h *Handshaker) replayBlock(height int, proxyApp proxy.AppConnConsensus) ([]byte, error) {
-	mempool := types.MockMempool{}
-
-	var eventCache types.Fireable // nil
+func (h *Handshaker) replayBlock(state sm.State, height int64, proxyApp proxy.AppConnConsensus) (sm.State, error) {
 	block := h.store.LoadBlock(height)
 	meta := h.store.LoadBlockMeta(height)
 
-	if err := h.state.ApplyBlock(eventCache, proxyApp, block, meta.BlockID.PartsHeader, mempool); err != nil {
-		return nil, err
+	blockExec := sm.NewBlockExecutor(h.stateDB, h.logger, proxyApp, types.MockMempool{}, types.MockEvidencePool{})
+
+	var err error
+	state, err = blockExec.ApplyBlock(state, meta.BlockID, block)
+	if err != nil {
+		return sm.State{}, err
 	}
 
-	h.nBlocks += 1
+	h.nBlocks++
 
-	return h.state.AppHash, nil
+	return state, nil
 }
 
-func (h *Handshaker) checkAppHash(appHash []byte) error {
-	if !bytes.Equal(h.state.AppHash, appHash) {
-		panic(errors.New(Fmt("Tendermint state.AppHash does not match AppHash after replay. Got %X, expected %X", appHash, h.state.AppHash)).Error())
-		return nil
+func checkAppHash(state sm.State, appHash []byte) error {
+	if !bytes.Equal(state.AppHash, appHash) {
+		panic(fmt.Errorf("Tendermint state.AppHash does not match AppHash after replay. Got %X, expected %X", appHash, state.AppHash).Error())
 	}
 	return nil
 }
@@ -384,6 +412,10 @@ func newMockProxyApp(appHash []byte, abciResponses *sm.ABCIResponses) proxy.AppC
 		abciResponses: abciResponses,
 	})
 	cli, _ := clientCreator.NewABCIClient()
+	err := cli.Start()
+	if err != nil {
+		panic(err)
+	}
 	return proxy.NewAppConnConsensus(cli)
 }
 
@@ -395,21 +427,17 @@ type mockProxyApp struct {
 	abciResponses *sm.ABCIResponses
 }
 
-func (mock *mockProxyApp) DeliverTx(tx []byte) abci.Result {
+func (mock *mockProxyApp) DeliverTx(tx []byte) abci.ResponseDeliverTx {
 	r := mock.abciResponses.DeliverTx[mock.txCount]
-	mock.txCount += 1
-	return abci.Result{
-		r.Code,
-		r.Data,
-		r.Log,
-	}
+	mock.txCount++
+	return *r
 }
 
-func (mock *mockProxyApp) EndBlock(height uint64) abci.ResponseEndBlock {
+func (mock *mockProxyApp) EndBlock(req abci.RequestEndBlock) abci.ResponseEndBlock {
 	mock.txCount = 0
-	return mock.abciResponses.EndBlock
+	return *mock.abciResponses.EndBlock
 }
 
-func (mock *mockProxyApp) Commit() abci.Result {
-	return abci.NewResultOK(mock.appHash, "")
+func (mock *mockProxyApp) Commit() abci.ResponseCommit {
+	return abci.ResponseCommit{Data: mock.appHash}
 }

consensus/replay_file.go

@@ -2,30 +2,38 @@ package consensus
 
 import (
 	"bufio"
-	"errors"
+	"context"
 	"fmt"
+	"io"
 	"os"
 	"strconv"
 	"strings"
 
-	. "github.com/tendermint/go-common"
-	cfg "github.com/tendermint/go-config"
-	dbm "github.com/tendermint/go-db"
+	"github.com/pkg/errors"
+
 	bc "github.com/tendermint/tendermint/blockchain"
-	mempl "github.com/tendermint/tendermint/mempool"
+	cfg "github.com/tendermint/tendermint/config"
 	"github.com/tendermint/tendermint/proxy"
 	sm "github.com/tendermint/tendermint/state"
 	"github.com/tendermint/tendermint/types"
+	cmn "github.com/tendermint/tmlibs/common"
+	dbm "github.com/tendermint/tmlibs/db"
+	"github.com/tendermint/tmlibs/log"
+)
+
+const (
+	// event bus subscriber
+	subscriber = "replay-file"
 )
 
 //--------------------------------------------------------
 // replay messages interactively or all at once
 
-func RunReplayFile(config cfg.Config, walFile string, console bool) {
-	consensusState := newConsensusStateForReplay(config)
+func RunReplayFile(config cfg.BaseConfig, csConfig *cfg.ConsensusConfig, console bool) {
+	consensusState := newConsensusStateForReplay(config, csConfig)
 
-	if err := consensusState.ReplayFile(walFile, console); err != nil {
-		Exit(Fmt("Error during consensus replay: %v", err))
+	if err := consensusState.ReplayFile(csConfig.WalFile(), console); err != nil {
+		cmn.Exit(cmn.Fmt("Error during consensus replay: %v", err))
 	}
 }
 
@@ -42,31 +50,46 @@ func (cs *ConsensusState) ReplayFile(file string, console bool) error {
 	cs.startForReplay()
 
 	// ensure all new step events are regenerated as expected
-	newStepCh := subscribeToEvent(cs.evsw, "replay-test", types.EventStringNewRoundStep(), 1)
+	newStepCh := make(chan interface{}, 1)
+
+	ctx := context.Background()
+	err := cs.eventBus.Subscribe(ctx, subscriber, types.EventQueryNewRoundStep, newStepCh)
+	if err != nil {
+		return errors.Errorf("failed to subscribe %s to %v", subscriber, types.EventQueryNewRoundStep)
+	}
+	defer cs.eventBus.Unsubscribe(ctx, subscriber, types.EventQueryNewRoundStep)
 
 	// just open the file for reading, no need to use wal
-	fp, err := os.OpenFile(file, os.O_RDONLY, 0666)
+	fp, err := os.OpenFile(file, os.O_RDONLY, 0600)
 	if err != nil {
 		return err
 	}
 
 	pb := newPlayback(file, fp, cs, cs.state.Copy())
-	defer pb.fp.Close()
+	defer pb.fp.Close() // nolint: errcheck
 
 	var nextN int // apply N msgs in a row
-	for pb.scanner.Scan() {
+	var msg *TimedWALMessage
+	for {
 		if nextN == 0 && console {
 			nextN = pb.replayConsoleLoop()
 		}
 
-		if err := pb.cs.readReplayMessage(pb.scanner.Bytes(), newStepCh); err != nil {
+		msg, err = pb.dec.Decode()
+		if err == io.EOF {
+			return nil
+		} else if err != nil {
+			return err
+		}
+
+		if err := pb.cs.readReplayMessage(msg, newStepCh); err != nil {
 			return err
 		}
 
 		if nextN > 0 {
-			nextN -= 1
+			nextN--
 		}
-		pb.count += 1
+		pb.count++
 	}
 	return nil
 }
@@ -77,58 +100,66 @@ func (cs *ConsensusState) ReplayFile(file string, console bool) error {
 type playback struct {
 	cs *ConsensusState
 
-	fp      *os.File
-	scanner *bufio.Scanner
-	count   int // how many lines/msgs into the file are we
+	fp    *os.File
+	dec   *WALDecoder
+	count int // how many lines/msgs into the file are we
 
 	// replays can be reset to beginning
-	fileName     string    // so we can close/reopen the file
-	genesisState *sm.State // so the replay session knows where to restart from
+	fileName     string   // so we can close/reopen the file
+	genesisState sm.State // so the replay session knows where to restart from
 }
 
-func newPlayback(fileName string, fp *os.File, cs *ConsensusState, genState *sm.State) *playback {
+func newPlayback(fileName string, fp *os.File, cs *ConsensusState, genState sm.State) *playback {
 	return &playback{
 		cs:           cs,
 		fp:           fp,
 		fileName:     fileName,
 		genesisState: genState,
-		scanner:      bufio.NewScanner(fp),
+		dec:          NewWALDecoder(fp),
 	}
 }
 
 // go back count steps by resetting the state and running (pb.count - count) steps
 func (pb *playback) replayReset(count int, newStepCh chan interface{}) error {
-
 	pb.cs.Stop()
 	pb.cs.Wait()
 
-	newCS := NewConsensusState(pb.cs.config, pb.genesisState.Copy(), pb.cs.proxyAppConn, pb.cs.blockStore, pb.cs.mempool)
-	newCS.SetEventSwitch(pb.cs.evsw)
+	newCS := NewConsensusState(pb.cs.config, pb.genesisState.Copy(), pb.cs.blockExec,
+		pb.cs.blockStore, pb.cs.mempool, pb.cs.evpool)
+	newCS.SetEventBus(pb.cs.eventBus)
 	newCS.startForReplay()
 
-	pb.fp.Close()
-	fp, err := os.OpenFile(pb.fileName, os.O_RDONLY, 0666)
+	if err := pb.fp.Close(); err != nil {
+		return err
+	}
+	fp, err := os.OpenFile(pb.fileName, os.O_RDONLY, 0600)
 	if err != nil {
 		return err
 	}
 	pb.fp = fp
-	pb.scanner = bufio.NewScanner(fp)
+	pb.dec = NewWALDecoder(fp)
 	count = pb.count - count
-	log.Notice(Fmt("Reseting from %d to %d", pb.count, count))
+	fmt.Printf("Reseting from %d to %d\n", pb.count, count)
 	pb.count = 0
 	pb.cs = newCS
-	for i := 0; pb.scanner.Scan() && i < count; i++ {
-		if err := pb.cs.readReplayMessage(pb.scanner.Bytes(), newStepCh); err != nil {
+	var msg *TimedWALMessage
+	for i := 0; i < count; i++ {
+		msg, err = pb.dec.Decode()
+		if err == io.EOF {
+			return nil
+		} else if err != nil {
 			return err
 		}
-		pb.count += 1
+		if err := pb.cs.readReplayMessage(msg, newStepCh); err != nil {
+			return err
+		}
+		pb.count++
 	}
 	return nil
 }
 
 func (cs *ConsensusState) startForReplay() {
-
-	log.Warn("Replay commands are disabled until someone updates them and writes tests")
+	cs.Logger.Error("Replay commands are disabled until someone updates them and writes tests")
 	/* TODO:!
 	// since we replay tocks we just ignore ticks
 		go func() {
@@ -149,9 +180,9 @@ func (pb *playback) replayConsoleLoop() int {
 		bufReader := bufio.NewReader(os.Stdin)
 		line, more, err := bufReader.ReadLine()
 		if more {
-			Exit("input is too long")
+			cmn.Exit("input is too long")
 		} else if err != nil {
-			Exit(err.Error())
+			cmn.Exit(err.Error())
 		}
 
 		tokens := strings.Split(string(line), " ")
@@ -166,13 +197,12 @@ func (pb *playback) replayConsoleLoop() int {
 
 			if len(tokens) == 1 {
 				return 0
+			}
+			i, err := strconv.Atoi(tokens[1])
+			if err != nil {
+				fmt.Println("next takes an integer argument")
 			} else {
-				i, err := strconv.Atoi(tokens[1])
-				if err != nil {
-					fmt.Println("next takes an integer argument")
-				} else {
-					return i
-				}
+				return i
 			}
 
 		case "back":
@@ -182,10 +212,20 @@ func (pb *playback) replayConsoleLoop() int {
 			// NOTE: "back" is not supported in the state machine design,
 			// so we restart and replay up to
 
+			ctx := context.Background()
 			// ensure all new step events are regenerated as expected
-			newStepCh := subscribeToEvent(pb.cs.evsw, "replay-test", types.EventStringNewRoundStep(), 1)
+			newStepCh := make(chan interface{}, 1)
+
+			err := pb.cs.eventBus.Subscribe(ctx, subscriber, types.EventQueryNewRoundStep, newStepCh)
+			if err != nil {
+				cmn.Exit(fmt.Sprintf("failed to subscribe %s to %v", subscriber, types.EventQueryNewRoundStep))
+			}
+			defer pb.cs.eventBus.Unsubscribe(ctx, subscriber, types.EventQueryNewRoundStep)
+
 			if len(tokens) == 1 {
-				pb.replayReset(1, newStepCh)
+				if err := pb.replayReset(1, newStepCh); err != nil {
+					pb.cs.Logger.Error("Replay reset error", "err", err)
+				}
 			} else {
 				i, err := strconv.Atoi(tokens[1])
 				if err != nil {
@@ -193,7 +233,9 @@ func (pb *playback) replayConsoleLoop() int {
 				} else if i > pb.count {
 					fmt.Printf("argument to back must not be larger than the current count (%d)\n", pb.count)
 				} else {
-					pb.replayReset(i, newStepCh)
+					if err := pb.replayReset(i, newStepCh); err != nil {
+						pb.cs.Logger.Error("Replay reset error", "err", err)
+					}
 				}
 			}
 
@@ -236,34 +278,43 @@ func (pb *playback) replayConsoleLoop() int {
 //--------------------------------------------------------------------------------
 
 // convenience for replay mode
-func newConsensusStateForReplay(config cfg.Config) *ConsensusState {
+func newConsensusStateForReplay(config cfg.BaseConfig, csConfig *cfg.ConsensusConfig) *ConsensusState {
+	dbType := dbm.DBBackendType(config.DBBackend)
 	// Get BlockStore
-	blockStoreDB := dbm.NewDB("blockstore", config.GetString("db_backend"), config.GetString("db_dir"))
+	blockStoreDB := dbm.NewDB("blockstore", dbType, config.DBDir())
 	blockStore := bc.NewBlockStore(blockStoreDB)
 
 	// Get State
-	stateDB := dbm.NewDB("state", config.GetString("db_backend"), config.GetString("db_dir"))
-	state := sm.MakeGenesisStateFromFile(stateDB, config.GetString("genesis_file"))
+	stateDB := dbm.NewDB("state", dbType, config.DBDir())
+	gdoc, err := sm.MakeGenesisDocFromFile(config.GenesisFile())
+	if err != nil {
+		cmn.Exit(err.Error())
+	}
+	state, err := sm.MakeGenesisState(gdoc)
+	if err != nil {
+		cmn.Exit(err.Error())
+	}
 
 	// Create proxyAppConn connection (consensus, mempool, query)
-	proxyApp := proxy.NewAppConns(config, proxy.DefaultClientCreator(config), NewHandshaker(config, state, blockStore))
-	_, err := proxyApp.Start()
+	clientCreator := proxy.DefaultClientCreator(config.ProxyApp, config.ABCI, config.DBDir())
+	proxyApp := proxy.NewAppConns(clientCreator,
+		NewHandshaker(stateDB, state, blockStore, gdoc.AppState()))
+	err = proxyApp.Start()
 	if err != nil {
-		Exit(Fmt("Error starting proxy app conns: %v", err))
+		cmn.Exit(cmn.Fmt("Error starting proxy app conns: %v", err))
 	}
 
-	// add the chainid to the global config
-	config.Set("chain_id", state.ChainID)
-
-	// Make event switch
-	eventSwitch := types.NewEventSwitch()
-	if _, err := eventSwitch.Start(); err != nil {
-		Exit(Fmt("Failed to start event switch: %v", err))
+	eventBus := types.NewEventBus()
+	if err := eventBus.Start(); err != nil {
+		cmn.Exit(cmn.Fmt("Failed to start event bus: %v", err))
 	}
 
-	mempool := mempl.NewMempool(config, proxyApp.Mempool())
+	mempool, evpool := types.MockMempool{}, types.MockEvidencePool{}
+	blockExec := sm.NewBlockExecutor(stateDB, log.TestingLogger(), proxyApp.Consensus(), mempool, evpool)
 
-	consensusState := NewConsensusState(config, state.Copy(), proxyApp.Consensus(), blockStore, mempool)
-	consensusState.SetEventSwitch(eventSwitch)
+	consensusState := NewConsensusState(csConfig, state.Copy(), blockExec,
+		blockStore, mempool, evpool)
+
+	consensusState.SetEventBus(eventBus)
 	return consensusState
 }

consensus/replay_test.go

@@ -2,31 +2,38 @@ package consensus
 
 import (
 	"bytes"
+	"context"
 	"errors"
 	"fmt"
 	"io"
 	"io/ioutil"
 	"os"
 	"path"
-	"strings"
+	"runtime"
 	"testing"
 	"time"
 
-	"github.com/tendermint/tendermint/config/tendermint_test"
+	"github.com/stretchr/testify/require"
 
-	"github.com/tendermint/abci/example/dummy"
-	cmn "github.com/tendermint/go-common"
-	cfg "github.com/tendermint/go-config"
+	"github.com/tendermint/abci/example/kvstore"
+	abci "github.com/tendermint/abci/types"
 	"github.com/tendermint/go-crypto"
-	dbm "github.com/tendermint/go-db"
-	"github.com/tendermint/go-wire"
+	auto "github.com/tendermint/tmlibs/autofile"
+	cmn "github.com/tendermint/tmlibs/common"
+	dbm "github.com/tendermint/tmlibs/db"
+
+	cfg "github.com/tendermint/tendermint/config"
 	"github.com/tendermint/tendermint/proxy"
 	sm "github.com/tendermint/tendermint/state"
 	"github.com/tendermint/tendermint/types"
+	pvm "github.com/tendermint/tendermint/types/priv_validator"
+	"github.com/tendermint/tmlibs/log"
 )
 
+var consensusReplayConfig *cfg.Config
+
 func init() {
-	config = tendermint_test.ResetConfig("consensus_replay_test")
+	consensusReplayConfig = ResetConfig("consensus_replay_test")
 }
 
 // These tests ensure we can always recover from failure at any part of the consensus process.
@@ -37,8 +44,6 @@ func init() {
 // the `Handshake Tests` are for failures in applying the block.
 // With the help of the WAL, we can recover from it all!
 
-var data_dir = path.Join(cmn.GoPath, "src/github.com/tendermint/tendermint/consensus", "test_data")
-
 //------------------------------------------------------------------------------------------
 // WAL Tests
 
@@ -46,217 +51,216 @@ var data_dir = path.Join(cmn.GoPath, "src/github.com/tendermint/tendermint/conse
 // and which ones we need the wal for - then we'd also be able to only flush the
 // wal writer when we need to, instead of with every message.
 
-// the priv validator changes step at these lines for a block with 1 val and 1 part
-var baseStepChanges = []int{3, 6, 8}
+func startNewConsensusStateAndWaitForBlock(t *testing.T, lastBlockHeight int64, blockDB dbm.DB, stateDB dbm.DB) {
+	logger := log.TestingLogger()
+	state, _ := sm.LoadStateFromDBOrGenesisFile(stateDB, consensusReplayConfig.GenesisFile())
+	privValidator := loadPrivValidator(consensusReplayConfig)
+	cs := newConsensusStateWithConfigAndBlockStore(consensusReplayConfig, state, privValidator, kvstore.NewKVStoreApplication(), blockDB)
+	cs.SetLogger(logger)
 
-// test recovery from each line in each testCase
-var testCases = []*testCase{
-	newTestCase("empty_block", baseStepChanges),   // empty block (has 1 block part)
-	newTestCase("small_block1", baseStepChanges),  // small block with txs in 1 block part
-	newTestCase("small_block2", []int{3, 10, 12}), // small block with txs across 5 smaller block parts
-}
+	bytes, _ := ioutil.ReadFile(cs.config.WalFile())
+	// fmt.Printf("====== WAL: \n\r%s\n", bytes)
+	t.Logf("====== WAL: \n\r%X\n", bytes)
 
-type testCase struct {
-	name    string
-	log     string       //full cs wal
-	stepMap map[int]int8 // map lines of log to privval step
+	err := cs.Start()
+	require.NoError(t, err)
+	defer cs.Stop()
 
-	proposeLine   int
-	prevoteLine   int
-	precommitLine int
-}
-
-func newTestCase(name string, stepChanges []int) *testCase {
-	if len(stepChanges) != 3 {
-		panic(cmn.Fmt("a full wal has 3 step changes! Got array %v", stepChanges))
-	}
-	return &testCase{
-		name:    name,
-		log:     readWAL(path.Join(data_dir, name+".cswal")),
-		stepMap: newMapFromChanges(stepChanges),
-
-		proposeLine:   stepChanges[0],
-		prevoteLine:   stepChanges[1],
-		precommitLine: stepChanges[2],
-	}
-}
-
-func newMapFromChanges(changes []int) map[int]int8 {
-	changes = append(changes, changes[2]+1) // so we add the last step change to the map
-	m := make(map[int]int8)
-	var count int
-	for changeNum, nextChange := range changes {
-		for ; count < nextChange; count++ {
-			m[count] = int8(changeNum)
-		}
-	}
-	return m
-}
-
-func readWAL(p string) string {
-	b, err := ioutil.ReadFile(p)
-	if err != nil {
-		panic(err)
-	}
-	return string(b)
-}
-
-func writeWAL(walMsgs string) string {
-	tempDir := os.TempDir()
-	walDir := path.Join(tempDir, "/wal"+cmn.RandStr(12))
-	walFile := path.Join(walDir, "wal")
-	// Create WAL directory
-	err := cmn.EnsureDir(walDir, 0700)
-	if err != nil {
-		panic(err)
-	}
-	// Write the needed WAL to file
-	err = cmn.WriteFile(walFile, []byte(walMsgs), 0600)
-	if err != nil {
-		panic(err)
-	}
-	return walFile
-}
-
-func waitForBlock(newBlockCh chan interface{}, thisCase *testCase, i int) {
-	after := time.After(time.Second * 10)
+	// This is just a signal that we haven't halted; its not something contained
+	// in the WAL itself. Assuming the consensus state is running, replay of any
+	// WAL, including the empty one, should eventually be followed by a new
+	// block, or else something is wrong.
+	newBlockCh := make(chan interface{}, 1)
+	err = cs.eventBus.Subscribe(context.Background(), testSubscriber, types.EventQueryNewBlock, newBlockCh)
+	require.NoError(t, err)
 	select {
 	case <-newBlockCh:
-	case <-after:
-		panic(cmn.Fmt("Timed out waiting for new block for case '%s' line %d", thisCase.name, i))
+	case <-time.After(60 * time.Second):
+		t.Fatalf("Timed out waiting for new block (see trace above)")
 	}
 }
 
-func runReplayTest(t *testing.T, cs *ConsensusState, walFile string, newBlockCh chan interface{},
-	thisCase *testCase, i int) {
+func sendTxs(cs *ConsensusState, ctx context.Context) {
+	for i := 0; i < 256; i++ {
+		select {
+		case <-ctx.Done():
+			return
+		default:
+			tx := []byte{byte(i)}
+			cs.mempool.CheckTx(tx, nil)
+			i++
+		}
+	}
+}
 
-	cs.config.Set("cs_wal_file", walFile)
-	cs.Start()
-	// Wait to make a new block.
-	// This is just a signal that we haven't halted; its not something contained in the WAL itself.
-	// Assuming the consensus state is running, replay of any WAL, including the empty one,
-	// should eventually be followed by a new block, or else something is wrong
-	waitForBlock(newBlockCh, thisCase, i)
-	cs.evsw.Stop()
-	cs.Stop()
+// TestWALCrash uses crashing WAL to test we can recover from any WAL failure.
+func TestWALCrash(t *testing.T) {
+	testCases := []struct {
+		name         string
+		initFn       func(dbm.DB, *ConsensusState, context.Context)
+		heightToStop int64
+	}{
+		{"empty block",
+			func(stateDB dbm.DB, cs *ConsensusState, ctx context.Context) {},
+			1},
+		{"block with a smaller part size",
+			func(stateDB dbm.DB, cs *ConsensusState, ctx context.Context) {
+				// XXX: is there a better way to change BlockPartSizeBytes?
+				cs.state.ConsensusParams.BlockPartSizeBytes = 512
+				sm.SaveState(stateDB, cs.state)
+				go sendTxs(cs, ctx)
+			},
+			1},
+		{"many non-empty blocks",
+			func(stateDB dbm.DB, cs *ConsensusState, ctx context.Context) {
+				go sendTxs(cs, ctx)
+			},
+			3},
+	}
+
+	for _, tc := range testCases {
+		t.Run(tc.name, func(t *testing.T) {
+			crashWALandCheckLiveness(t, tc.initFn, tc.heightToStop)
+		})
+	}
+}
+
+func crashWALandCheckLiveness(t *testing.T, initFn func(dbm.DB, *ConsensusState, context.Context), heightToStop int64) {
+	walPaniced := make(chan error)
+	crashingWal := &crashingWAL{panicCh: walPaniced, heightToStop: heightToStop}
+
+	i := 1
 LOOP:
 	for {
+		// fmt.Printf("====== LOOP %d\n", i)
+		t.Logf("====== LOOP %d\n", i)
+
+		// create consensus state from a clean slate
+		logger := log.NewNopLogger()
+		stateDB := dbm.NewMemDB()
+		state, _ := sm.MakeGenesisStateFromFile(consensusReplayConfig.GenesisFile())
+		privValidator := loadPrivValidator(consensusReplayConfig)
+		blockDB := dbm.NewMemDB()
+		cs := newConsensusStateWithConfigAndBlockStore(consensusReplayConfig, state, privValidator, kvstore.NewKVStoreApplication(), blockDB)
+		cs.SetLogger(logger)
+
+		// start sending transactions
+		ctx, cancel := context.WithCancel(context.Background())
+		initFn(stateDB, cs, ctx)
+
+		// clean up WAL file from the previous iteration
+		walFile := cs.config.WalFile()
+		os.Remove(walFile)
+
+		// set crashing WAL
+		csWal, err := cs.OpenWAL(walFile)
+		require.NoError(t, err)
+		crashingWal.next = csWal
+		// reset the message counter
+		crashingWal.msgIndex = 1
+		cs.wal = crashingWal
+
+		// start consensus state
+		err = cs.Start()
+		require.NoError(t, err)
+
+		i++
+
 		select {
-		case <-newBlockCh:
-		default:
-			break LOOP
-		}
-	}
-	cs.Wait()
-}
+		case err := <-walPaniced:
+			t.Logf("WAL paniced: %v", err)
 
-func toPV(pv PrivValidator) *types.PrivValidator {
-	return pv.(*types.PrivValidator)
-}
+			// make sure we can make blocks after a crash
+			startNewConsensusStateAndWaitForBlock(t, cs.Height, blockDB, stateDB)
 
-func setupReplayTest(thisCase *testCase, nLines int, crashAfter bool) (*ConsensusState, chan interface{}, string, string) {
-	fmt.Println("-------------------------------------")
-	log.Notice(cmn.Fmt("Starting replay test %v (of %d lines of WAL). Crash after = %v", thisCase.name, nLines, crashAfter))
+			// stop consensus state and transactions sender (initFn)
+			cs.Stop()
+			cancel()
 
-	lineStep := nLines
-	if crashAfter {
-		lineStep -= 1
-	}
-
-	split := strings.Split(thisCase.log, "\n")
-	lastMsg := split[nLines]
-
-	// we write those lines up to (not including) one with the signature
-	walFile := writeWAL(strings.Join(split[:nLines], "\n") + "\n")
-
-	cs := fixedConsensusStateDummy()
-
-	// set the last step according to when we crashed vs the wal
-	toPV(cs.privValidator).LastHeight = 1 // first block
-	toPV(cs.privValidator).LastStep = thisCase.stepMap[lineStep]
-
-	log.Warn("setupReplayTest", "LastStep", toPV(cs.privValidator).LastStep)
-
-	newBlockCh := subscribeToEvent(cs.evsw, "tester", types.EventStringNewBlock(), 1)
-
-	return cs, newBlockCh, lastMsg, walFile
-}
-
-func readTimedWALMessage(t *testing.T, walMsg string) TimedWALMessage {
-	var err error
-	var msg TimedWALMessage
-	wire.ReadJSON(&msg, []byte(walMsg), &err)
-	if err != nil {
-		t.Fatalf("Error reading json data: %v", err)
-	}
-	return msg
-}
-
-//-----------------------------------------------
-// Test the log at every iteration, and set the privVal last step
-// as if the log was written after signing, before the crash
-
-func TestWALCrashAfterWrite(t *testing.T) {
-	for _, thisCase := range testCases {
-		split := strings.Split(thisCase.log, "\n")
-		for i := 0; i < len(split)-1; i++ {
-			cs, newBlockCh, _, walFile := setupReplayTest(thisCase, i+1, true)
-			runReplayTest(t, cs, walFile, newBlockCh, thisCase, i+1)
+			// if we reached the required height, exit
+			if _, ok := err.(ReachedHeightToStopError); ok {
+				break LOOP
+			}
+		case <-time.After(10 * time.Second):
+			t.Fatal("WAL did not panic for 10 seconds (check the log)")
 		}
 	}
 }
 
-//-----------------------------------------------
-// Test the log as if we crashed after signing but before writing.
-// This relies on privValidator.LastSignature being set
+// crashingWAL is a WAL which crashes or rather simulates a crash during Save
+// (before and after). It remembers a message for which we last panicked
+// (lastPanicedForMsgIndex), so we don't panic for it in subsequent iterations.
+type crashingWAL struct {
+	next         WAL
+	panicCh      chan error
+	heightToStop int64
 
-func TestWALCrashBeforeWritePropose(t *testing.T) {
-	for _, thisCase := range testCases {
-		lineNum := thisCase.proposeLine
-		// setup replay test where last message is a proposal
-		cs, newBlockCh, proposalMsg, walFile := setupReplayTest(thisCase, lineNum, false)
-		msg := readTimedWALMessage(t, proposalMsg)
-		proposal := msg.Msg.(msgInfo).Msg.(*ProposalMessage)
-		// Set LastSig
-		toPV(cs.privValidator).LastSignBytes = types.SignBytes(cs.state.ChainID, proposal.Proposal)
-		toPV(cs.privValidator).LastSignature = proposal.Proposal.Signature
-		runReplayTest(t, cs, walFile, newBlockCh, thisCase, lineNum)
+	msgIndex               int // current message index
+	lastPanicedForMsgIndex int // last message for which we panicked
+}
+
+// WALWriteError indicates a WAL crash.
+type WALWriteError struct {
+	msg string
+}
+
+func (e WALWriteError) Error() string {
+	return e.msg
+}
+
+// ReachedHeightToStopError indicates we've reached the required consensus
+// height and may exit.
+type ReachedHeightToStopError struct {
+	height int64
+}
+
+func (e ReachedHeightToStopError) Error() string {
+	return fmt.Sprintf("reached height to stop %d", e.height)
+}
+
+// Save simulate WAL's crashing by sending an error to the panicCh and then
+// exiting the cs.receiveRoutine.
+func (w *crashingWAL) Save(m WALMessage) {
+	if endMsg, ok := m.(EndHeightMessage); ok {
+		if endMsg.Height == w.heightToStop {
+			w.panicCh <- ReachedHeightToStopError{endMsg.Height}
+			runtime.Goexit()
+		} else {
+			w.next.Save(m)
+		}
+		return
+	}
+
+	if w.msgIndex > w.lastPanicedForMsgIndex {
+		w.lastPanicedForMsgIndex = w.msgIndex
+		_, file, line, _ := runtime.Caller(1)
+		w.panicCh <- WALWriteError{fmt.Sprintf("failed to write %T to WAL (fileline: %s:%d)", m, file, line)}
+		runtime.Goexit()
+	} else {
+		w.msgIndex++
+		w.next.Save(m)
 	}
 }
 
-func TestWALCrashBeforeWritePrevote(t *testing.T) {
-	for _, thisCase := range testCases {
-		testReplayCrashBeforeWriteVote(t, thisCase, thisCase.prevoteLine, types.EventStringCompleteProposal())
-	}
+func (w *crashingWAL) Group() *auto.Group { return w.next.Group() }
+func (w *crashingWAL) SearchForEndHeight(height int64, options *WALSearchOptions) (gr *auto.GroupReader, found bool, err error) {
+	return w.next.SearchForEndHeight(height, options)
 }
 
-func TestWALCrashBeforeWritePrecommit(t *testing.T) {
-	for _, thisCase := range testCases {
-		testReplayCrashBeforeWriteVote(t, thisCase, thisCase.precommitLine, types.EventStringPolka())
-	}
-}
-
-func testReplayCrashBeforeWriteVote(t *testing.T, thisCase *testCase, lineNum int, eventString string) {
-	// setup replay test where last message is a vote
-	cs, newBlockCh, voteMsg, walFile := setupReplayTest(thisCase, lineNum, false)
-	types.AddListenerForEvent(cs.evsw, "tester", eventString, func(data types.TMEventData) {
-		msg := readTimedWALMessage(t, voteMsg)
-		vote := msg.Msg.(msgInfo).Msg.(*VoteMessage)
-		// Set LastSig
-		toPV(cs.privValidator).LastSignBytes = types.SignBytes(cs.state.ChainID, vote.Vote)
-		toPV(cs.privValidator).LastSignature = vote.Vote.Signature
-	})
-	runReplayTest(t, cs, walFile, newBlockCh, thisCase, lineNum)
-}
+func (w *crashingWAL) Start() error { return w.next.Start() }
+func (w *crashingWAL) Stop() error  { return w.next.Stop() }
+func (w *crashingWAL) Wait()        { w.next.Wait() }
 
 //------------------------------------------------------------------------------------------
 // Handshake Tests
 
-var (
-	NUM_BLOCKS = 6 // number of blocks in the test_data/many_blocks.cswal
-	mempool    = types.MockMempool{}
+const (
+	NUM_BLOCKS = 6
+)
 
-	testPartSize int
+var (
+	mempool = types.MockMempool{}
+	evpool  = types.MockEvidencePool{}
 )
 
 //---------------------------------------
@@ -295,57 +299,78 @@ func TestHandshakeReplayNone(t *testing.T) {
 	}
 }
 
+func tempWALWithData(data []byte) string {
+	walFile, err := ioutil.TempFile("", "wal")
+	if err != nil {
+		panic(fmt.Errorf("failed to create temp WAL file: %v", err))
+	}
+	_, err = walFile.Write(data)
+	if err != nil {
+		panic(fmt.Errorf("failed to write to temp WAL file: %v", err))
+	}
+	if err := walFile.Close(); err != nil {
+		panic(fmt.Errorf("failed to close temp WAL file: %v", err))
+	}
+	return walFile.Name()
+}
+
 // Make some blocks. Start a fresh app and apply nBlocks blocks. Then restart the app and sync it up with the remaining blocks
 func testHandshakeReplay(t *testing.T, nBlocks int, mode uint) {
-	config := tendermint_test.ResetConfig("proxy_test_")
+	config := ResetConfig("proxy_test_")
 
-	// copy the many_blocks file
-	walBody, err := cmn.ReadFile(path.Join(data_dir, "many_blocks.cswal"))
+	walBody, err := WALWithNBlocks(NUM_BLOCKS)
 	if err != nil {
 		t.Fatal(err)
 	}
-	walFile := writeWAL(string(walBody))
-	config.Set("cs_wal_file", walFile)
+	walFile := tempWALWithData(walBody)
+	config.Consensus.SetWalFile(walFile)
 
-	privVal := types.LoadPrivValidator(config.GetString("priv_validator_file"))
-	testPartSize = config.GetInt("block_part_size")
+	privVal := pvm.LoadFilePV(config.PrivValidatorFile())
 
 	wal, err := NewWAL(walFile, false)
 	if err != nil {
 		t.Fatal(err)
 	}
+	wal.SetLogger(log.TestingLogger())
+	if err := wal.Start(); err != nil {
+		t.Fatal(err)
+	}
+	defer wal.Stop()
+
 	chain, commits, err := makeBlockchainFromWAL(wal)
 	if err != nil {
 		t.Fatalf(err.Error())
 	}
 
-	state, store := stateAndStore(config, privVal.PubKey)
+	stateDB, state, store := stateAndStore(config, privVal.GetPubKey())
 	store.chain = chain
 	store.commits = commits
 
 	// run the chain through state.ApplyBlock to build up the tendermint state
-	latestAppHash := buildTMStateFromChain(config, state, chain, mode)
+	state = buildTMStateFromChain(config, stateDB, state, chain, mode)
+	latestAppHash := state.AppHash
 
 	// make a new client creator
-	dummyApp := dummy.NewPersistentDummyApplication(path.Join(config.GetString("db_dir"), "2"))
-	clientCreator2 := proxy.NewLocalClientCreator(dummyApp)
+	kvstoreApp := kvstore.NewPersistentKVStoreApplication(path.Join(config.DBDir(), "2"))
+	clientCreator2 := proxy.NewLocalClientCreator(kvstoreApp)
 	if nBlocks > 0 {
 		// run nBlocks against a new client to build up the app state.
 		// use a throwaway tendermint state
-		proxyApp := proxy.NewAppConns(config, clientCreator2, nil)
-		state, _ := stateAndStore(config, privVal.PubKey)
-		buildAppStateFromChain(proxyApp, state, chain, nBlocks, mode)
+		proxyApp := proxy.NewAppConns(clientCreator2, nil)
+		stateDB, state, _ := stateAndStore(config, privVal.GetPubKey())
+		buildAppStateFromChain(proxyApp, stateDB, state, chain, nBlocks, mode)
 	}
 
 	// now start the app using the handshake - it should sync
-	handshaker := NewHandshaker(config, state, store)
-	proxyApp := proxy.NewAppConns(config, clientCreator2, handshaker)
-	if _, err := proxyApp.Start(); err != nil {
+	handshaker := NewHandshaker(stateDB, state, store, nil)
+	proxyApp := proxy.NewAppConns(clientCreator2, handshaker)
+	if err := proxyApp.Start(); err != nil {
 		t.Fatalf("Error starting proxy app connections: %v", err)
 	}
+	defer proxyApp.Stop()
 
 	// get the latest app hash from the app
-	res, err := proxyApp.Query().InfoSync()
+	res, err := proxyApp.Query().InfoSync(abci.RequestInfo{""})
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -357,9 +382,9 @@ func testHandshakeReplay(t *testing.T, nBlocks int, mode uint) {
 
 	expectedBlocksToSync := NUM_BLOCKS - nBlocks
 	if nBlocks == NUM_BLOCKS && mode > 0 {
-		expectedBlocksToSync += 1
+		expectedBlocksToSync++
 	} else if nBlocks > 0 && mode == 1 {
-		expectedBlocksToSync += 1
+		expectedBlocksToSync++
 	}
 
 	if handshaker.NBlocks() != expectedBlocksToSync {
@@ -367,275 +392,240 @@ func testHandshakeReplay(t *testing.T, nBlocks int, mode uint) {
 	}
 }
 
-func applyBlock(st *sm.State, blk *types.Block, proxyApp proxy.AppConns) {
-	err := st.ApplyBlock(nil, proxyApp.Consensus(), blk, blk.MakePartSet(testPartSize).Header(), mempool)
+func applyBlock(stateDB dbm.DB, st sm.State, blk *types.Block, proxyApp proxy.AppConns) sm.State {
+	testPartSize := st.ConsensusParams.BlockPartSizeBytes
+	blockExec := sm.NewBlockExecutor(stateDB, log.TestingLogger(), proxyApp.Consensus(), mempool, evpool)
+
+	blkID := types.BlockID{blk.Hash(), blk.MakePartSet(testPartSize).Header()}
+	newState, err := blockExec.ApplyBlock(st, blkID, blk)
 	if err != nil {
 		panic(err)
 	}
+	return newState
 }
 
-func buildAppStateFromChain(proxyApp proxy.AppConns,
-	state *sm.State, chain []*types.Block, nBlocks int, mode uint) {
+func buildAppStateFromChain(proxyApp proxy.AppConns, stateDB dbm.DB,
+	state sm.State, chain []*types.Block, nBlocks int, mode uint) {
 	// start a new app without handshake, play nBlocks blocks
-	if _, err := proxyApp.Start(); err != nil {
+	if err := proxyApp.Start(); err != nil {
 		panic(err)
 	}
 	defer proxyApp.Stop()
+
+	// TODO: get the genesis bytes (https://github.com/tendermint/tendermint/issues/1224)
+	var genesisBytes []byte
+	validators := types.TM2PB.Validators(state.Validators)
+	if _, err := proxyApp.Consensus().InitChainSync(abci.RequestInitChain{validators, genesisBytes}); err != nil {
+		panic(err)
+	}
+
 	switch mode {
 	case 0:
 		for i := 0; i < nBlocks; i++ {
 			block := chain[i]
-			applyBlock(state, block, proxyApp)
+			state = applyBlock(stateDB, state, block, proxyApp)
 		}
 	case 1, 2:
 		for i := 0; i < nBlocks-1; i++ {
 			block := chain[i]
-			applyBlock(state, block, proxyApp)
+			state = applyBlock(stateDB, state, block, proxyApp)
 		}
 
 		if mode == 2 {
-			// update the dummy height and apphash
+			// update the kvstore height and apphash
 			// as if we ran commit but not
-			applyBlock(state, chain[nBlocks-1], proxyApp)
+			state = applyBlock(stateDB, state, chain[nBlocks-1], proxyApp)
 		}
 	}
 
 }
 
-func buildTMStateFromChain(config cfg.Config, state *sm.State, chain []*types.Block, mode uint) []byte {
+func buildTMStateFromChain(config *cfg.Config, stateDB dbm.DB, state sm.State, chain []*types.Block, mode uint) sm.State {
 	// run the whole chain against this client to build up the tendermint state
-	clientCreator := proxy.NewLocalClientCreator(dummy.NewPersistentDummyApplication(path.Join(config.GetString("db_dir"), "1")))
-	proxyApp := proxy.NewAppConns(config, clientCreator, nil) // sm.NewHandshaker(config, state, store, ReplayLastBlock))
-	if _, err := proxyApp.Start(); err != nil {
+	clientCreator := proxy.NewLocalClientCreator(kvstore.NewPersistentKVStoreApplication(path.Join(config.DBDir(), "1")))
+	proxyApp := proxy.NewAppConns(clientCreator, nil) // sm.NewHandshaker(config, state, store, ReplayLastBlock))
+	if err := proxyApp.Start(); err != nil {
 		panic(err)
 	}
 	defer proxyApp.Stop()
 
-	var latestAppHash []byte
+	// TODO: get the genesis bytes (https://github.com/tendermint/tendermint/issues/1224)
+	var genesisBytes []byte
+	validators := types.TM2PB.Validators(state.Validators)
+	if _, err := proxyApp.Consensus().InitChainSync(abci.RequestInitChain{validators, genesisBytes}); err != nil {
+		panic(err)
+	}
 
 	switch mode {
 	case 0:
 		// sync right up
 		for _, block := range chain {
-			applyBlock(state, block, proxyApp)
+			state = applyBlock(stateDB, state, block, proxyApp)
 		}
 
-		latestAppHash = state.AppHash
 	case 1, 2:
 		// sync up to the penultimate as if we stored the block.
 		// whether we commit or not depends on the appHash
 		for _, block := range chain[:len(chain)-1] {
-			applyBlock(state, block, proxyApp)
+			state = applyBlock(stateDB, state, block, proxyApp)
 		}
 
 		// apply the final block to a state copy so we can
 		// get the right next appHash but keep the state back
-		stateCopy := state.Copy()
-		applyBlock(stateCopy, chain[len(chain)-1], proxyApp)
-		latestAppHash = stateCopy.AppHash
+		applyBlock(stateDB, state, chain[len(chain)-1], proxyApp)
 	}
 
-	return latestAppHash
+	return state
 }
 
 //--------------------------
 // utils for making blocks
 
-func makeBlockchainFromWAL(wal *WAL) ([]*types.Block, []*types.Commit, error) {
+func makeBlockchainFromWAL(wal WAL) ([]*types.Block, []*types.Commit, error) {
 	// Search for height marker
-	gr, found, err := wal.group.Search("#ENDHEIGHT: ", makeHeightSearchFunc(0))
+	gr, found, err := wal.SearchForEndHeight(0, &WALSearchOptions{})
 	if err != nil {
 		return nil, nil, err
 	}
 	if !found {
 		return nil, nil, errors.New(cmn.Fmt("WAL does not contain height %d.", 1))
 	}
-	defer gr.Close()
+	defer gr.Close() // nolint: errcheck
 
-	log.Notice("Build a blockchain by reading from the WAL")
+	// log.Notice("Build a blockchain by reading from the WAL")
 
-	var blockParts *types.PartSet
 	var blocks []*types.Block
 	var commits []*types.Commit
-	for {
-		line, err := gr.ReadLine()
-		if err != nil {
-			if err == io.EOF {
-				break
-			} else {
-				return nil, nil, err
-			}
-		}
 
-		piece, err := readPieceFromWAL([]byte(line))
-		if err != nil {
+	var thisBlockParts *types.PartSet
+	var thisBlockCommit *types.Commit
+	var height int64
+
+	dec := NewWALDecoder(gr)
+	for {
+		msg, err := dec.Decode()
+		if err == io.EOF {
+			break
+		} else if err != nil {
 			return nil, nil, err
 		}
+
+		piece := readPieceFromWAL(msg)
 		if piece == nil {
 			continue
 		}
 
 		switch p := piece.(type) {
-		case *types.PartSetHeader:
+		case EndHeightMessage:
 			// if its not the first one, we have a full block
-			if blockParts != nil {
-				var n int
-				block := wire.ReadBinary(&types.Block{}, blockParts.GetReader(), types.MaxBlockSize, &n, &err).(*types.Block)
+			if thisBlockParts != nil {
+				var block = new(types.Block)
+				_, err = cdc.UnmarshalBinaryReader(thisBlockParts.GetReader(), block, 0)
+				if err != nil {
+					panic(err)
+				}
+				if block.Height != height+1 {
+					panic(cmn.Fmt("read bad block from wal. got height %d, expected %d", block.Height, height+1))
+				}
+				commitHeight := thisBlockCommit.Precommits[0].Height
+				if commitHeight != height+1 {
+					panic(cmn.Fmt("commit doesnt match. got height %d, expected %d", commitHeight, height+1))
+				}
 				blocks = append(blocks, block)
+				commits = append(commits, thisBlockCommit)
+				height++
 			}
-			blockParts = types.NewPartSetFromHeader(*p)
+		case *types.PartSetHeader:
+			thisBlockParts = types.NewPartSetFromHeader(*p)
 		case *types.Part:
-			_, err := blockParts.AddPart(p, false)
+			_, err := thisBlockParts.AddPart(p, false)
 			if err != nil {
 				return nil, nil, err
 			}
 		case *types.Vote:
 			if p.Type == types.VoteTypePrecommit {
-				commit := &types.Commit{
+				thisBlockCommit = &types.Commit{
 					BlockID:    p.BlockID,
 					Precommits: []*types.Vote{p},
 				}
-				commits = append(commits, commit)
 			}
 		}
 	}
 	// grab the last block too
-	var n int
-	block := wire.ReadBinary(&types.Block{}, blockParts.GetReader(), types.MaxBlockSize, &n, &err).(*types.Block)
+	var block = new(types.Block)
+	_, err = cdc.UnmarshalBinaryReader(thisBlockParts.GetReader(), block, 0)
+	if err != nil {
+		panic(err)
+	}
+	if block.Height != height+1 {
+		panic(cmn.Fmt("read bad block from wal. got height %d, expected %d", block.Height, height+1))
+	}
+	commitHeight := thisBlockCommit.Precommits[0].Height
+	if commitHeight != height+1 {
+		panic(cmn.Fmt("commit doesnt match. got height %d, expected %d", commitHeight, height+1))
+	}
 	blocks = append(blocks, block)
+	commits = append(commits, thisBlockCommit)
 	return blocks, commits, nil
 }
 
-func readPieceFromWAL(msgBytes []byte) (interface{}, error) {
-	// Skip over empty and meta lines
-	if len(msgBytes) == 0 || msgBytes[0] == '#' {
-		return nil, nil
-	}
-	var err error
-	var msg TimedWALMessage
-	wire.ReadJSON(&msg, msgBytes, &err)
-	if err != nil {
-		fmt.Println("MsgBytes:", msgBytes, string(msgBytes))
-		return nil, fmt.Errorf("Error reading json data: %v", err)
-	}
-
+func readPieceFromWAL(msg *TimedWALMessage) interface{} {
 	// for logging
 	switch m := msg.Msg.(type) {
 	case msgInfo:
 		switch msg := m.Msg.(type) {
 		case *ProposalMessage:
-			return &msg.Proposal.BlockPartsHeader, nil
+			return &msg.Proposal.BlockPartsHeader
 		case *BlockPartMessage:
-			return msg.Part, nil
+			return msg.Part
 		case *VoteMessage:
-			return msg.Vote, nil
+			return msg.Vote
 		}
-	}
-	return nil, nil
-}
-
-// make some bogus txs
-func txsFunc(blockNum int) (txs []types.Tx) {
-	for i := 0; i < 10; i++ {
-		txs = append(txs, types.Tx([]byte{byte(blockNum), byte(i)}))
-	}
-	return txs
-}
-
-// sign a commit vote
-func signCommit(chainID string, privVal *types.PrivValidator, height, round int, hash []byte, header types.PartSetHeader) *types.Vote {
-	vote := &types.Vote{
-		ValidatorIndex:   0,
-		ValidatorAddress: privVal.Address,
-		Height:           height,
-		Round:            round,
-		Type:             types.VoteTypePrecommit,
-		BlockID:          types.BlockID{hash, header},
+	case EndHeightMessage:
+		return m
 	}
 
-	sig := privVal.Sign(types.SignBytes(chainID, vote))
-	vote.Signature = sig
-	return vote
-}
-
-// make a blockchain with one validator
-func makeBlockchain(t *testing.T, chainID string, nBlocks int, privVal *types.PrivValidator, proxyApp proxy.AppConns, state *sm.State) (blockchain []*types.Block, commits []*types.Commit) {
-
-	prevHash := state.LastBlockID.Hash
-	lastCommit := new(types.Commit)
-	prevParts := types.PartSetHeader{}
-	valHash := state.Validators.Hash()
-	prevBlockID := types.BlockID{prevHash, prevParts}
-
-	for i := 1; i < nBlocks+1; i++ {
-		block, parts := types.MakeBlock(i, chainID, txsFunc(i), lastCommit,
-			prevBlockID, valHash, state.AppHash, testPartSize)
-		fmt.Println(i)
-		fmt.Println(block.LastBlockID)
-		err := state.ApplyBlock(nil, proxyApp.Consensus(), block, block.MakePartSet(testPartSize).Header(), mempool)
-		if err != nil {
-			t.Fatal(i, err)
-		}
-
-		voteSet := types.NewVoteSet(chainID, i, 0, types.VoteTypePrecommit, state.Validators)
-		vote := signCommit(chainID, privVal, i, 0, block.Hash(), parts.Header())
-		_, err = voteSet.AddVote(vote)
-		if err != nil {
-			t.Fatal(err)
-		}
-
-		prevHash = block.Hash()
-		prevParts = parts.Header()
-		lastCommit = voteSet.MakeCommit()
-		prevBlockID = types.BlockID{prevHash, prevParts}
-
-		blockchain = append(blockchain, block)
-		commits = append(commits, lastCommit)
-	}
-	return blockchain, commits
+	return nil
 }
 
 // fresh state and mock store
-func stateAndStore(config cfg.Config, pubKey crypto.PubKey) (*sm.State, *mockBlockStore) {
+func stateAndStore(config *cfg.Config, pubKey crypto.PubKey) (dbm.DB, sm.State, *mockBlockStore) {
 	stateDB := dbm.NewMemDB()
-	return sm.MakeGenesisState(stateDB, &types.GenesisDoc{
-		ChainID: config.GetString("chain_id"),
-		Validators: []types.GenesisValidator{
-			types.GenesisValidator{pubKey, 10000, "test"},
-		},
-		AppHash: nil,
-	}), NewMockBlockStore(config)
+	state, _ := sm.MakeGenesisStateFromFile(config.GenesisFile())
+	store := NewMockBlockStore(config, state.ConsensusParams)
+	return stateDB, state, store
 }
 
 //----------------------------------
 // mock block store
 
 type mockBlockStore struct {
-	config  cfg.Config
+	config  *cfg.Config
+	params  types.ConsensusParams
 	chain   []*types.Block
 	commits []*types.Commit
 }
 
 // TODO: NewBlockStore(db.NewMemDB) ...
-func NewMockBlockStore(config cfg.Config) *mockBlockStore {
-	return &mockBlockStore{config, nil, nil}
+func NewMockBlockStore(config *cfg.Config, params types.ConsensusParams) *mockBlockStore {
+	return &mockBlockStore{config, params, nil, nil}
 }
 
-func (bs *mockBlockStore) Height() int                       { return len(bs.chain) }
-func (bs *mockBlockStore) LoadBlock(height int) *types.Block { return bs.chain[height-1] }
-func (bs *mockBlockStore) LoadBlockMeta(height int) *types.BlockMeta {
+func (bs *mockBlockStore) Height() int64                       { return int64(len(bs.chain)) }
+func (bs *mockBlockStore) LoadBlock(height int64) *types.Block { return bs.chain[height-1] }
+func (bs *mockBlockStore) LoadBlockMeta(height int64) *types.BlockMeta {
 	block := bs.chain[height-1]
 	return &types.BlockMeta{
-		BlockID: types.BlockID{block.Hash(), block.MakePartSet(bs.config.GetInt("block_part_size")).Header()},
+		BlockID: types.BlockID{block.Hash(), block.MakePartSet(bs.params.BlockPartSizeBytes).Header()},
 		Header:  block.Header,
 	}
 }
-func (bs *mockBlockStore) LoadBlockPart(height int, index int) *types.Part { return nil }
+func (bs *mockBlockStore) LoadBlockPart(height int64, index int) *types.Part { return nil }
 func (bs *mockBlockStore) SaveBlock(block *types.Block, blockParts *types.PartSet, seenCommit *types.Commit) {
 }
-func (bs *mockBlockStore) LoadBlockCommit(height int) *types.Commit {
+func (bs *mockBlockStore) LoadBlockCommit(height int64) *types.Commit {
 	return bs.commits[height-1]
 }
-func (bs *mockBlockStore) LoadSeenCommit(height int) *types.Commit {
+func (bs *mockBlockStore) LoadSeenCommit(height int64) *types.Commit {
 	return bs.commits[height-1]
 }

consensus/state_test.go

@@ -2,21 +2,24 @@ package consensus
 
 import (
 	"bytes"
+	"context"
 	"fmt"
 	"testing"
 	"time"
 
-	. "github.com/tendermint/go-common"
-	"github.com/tendermint/tendermint/config/tendermint_test"
+	cstypes "github.com/tendermint/tendermint/consensus/types"
 	"github.com/tendermint/tendermint/types"
+	cmn "github.com/tendermint/tmlibs/common"
+	"github.com/tendermint/tmlibs/log"
+	tmpubsub "github.com/tendermint/tmlibs/pubsub"
 )
 
 func init() {
-	config = tendermint_test.ResetConfig("consensus_state_test")
+	config = ResetConfig("consensus_state_test")
 }
 
-func (tp *TimeoutParams) ensureProposeTimeout() time.Duration {
-	return time.Duration(tp.Propose0*2) * time.Millisecond
+func ensureProposeTimeout(timeoutPropose int) time.Duration {
+	return time.Duration(timeoutPropose*2) * time.Millisecond
 }
 
 /*
@@ -52,12 +55,12 @@ x * TestHalt1 - if we see +2/3 precommits after timing out into new round, we sh
 //----------------------------------------------------------------------------------------------------
 // ProposeSuite
 
-func TestProposerSelection0(t *testing.T) {
+func TestStateProposerSelection0(t *testing.T) {
 	cs1, vss := randConsensusState(4)
 	height, round := cs1.Height, cs1.Round
 
-	newRoundCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringNewRound(), 1)
-	proposalCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringCompleteProposal(), 1)
+	newRoundCh := subscribe(cs1.eventBus, types.EventQueryNewRound)
+	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
 
 	startTestRound(cs1, height, round)
 
@@ -80,16 +83,16 @@ func TestProposerSelection0(t *testing.T) {
 	<-newRoundCh
 
 	prop = cs1.GetRoundState().Validators.GetProposer()
-	if !bytes.Equal(prop.Address, vss[1].Address) {
-		panic(Fmt("expected proposer to be validator %d. Got %X", 1, prop.Address))
+	if !bytes.Equal(prop.Address, vss[1].GetAddress()) {
+		panic(cmn.Fmt("expected proposer to be validator %d. Got %X", 1, prop.Address))
 	}
 }
 
 // Now let's do it all again, but starting from round 2 instead of 0
-func TestProposerSelection2(t *testing.T) {
+func TestStateProposerSelection2(t *testing.T) {
 	cs1, vss := randConsensusState(4) // test needs more work for more than 3 validators
 
-	newRoundCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringNewRound(), 1)
+	newRoundCh := subscribe(cs1.eventBus, types.EventQueryNewRound)
 
 	// this time we jump in at round 2
 	incrementRound(vss[1:]...)
@@ -101,8 +104,8 @@ func TestProposerSelection2(t *testing.T) {
 	// everyone just votes nil. we get a new proposer each round
 	for i := 0; i < len(vss); i++ {
 		prop := cs1.GetRoundState().Validators.GetProposer()
-		if !bytes.Equal(prop.Address, vss[(i+2)%len(vss)].Address) {
-			panic(Fmt("expected proposer to be validator %d. Got %X", (i+2)%len(vss), prop.Address))
+		if !bytes.Equal(prop.Address, vss[(i+2)%len(vss)].GetAddress()) {
+			panic(cmn.Fmt("expected proposer to be validator %d. Got %X", (i+2)%len(vss), prop.Address))
 		}
 
 		rs := cs1.GetRoundState()
@@ -115,18 +118,18 @@ func TestProposerSelection2(t *testing.T) {
 }
 
 // a non-validator should timeout into the prevote round
-func TestEnterProposeNoPrivValidator(t *testing.T) {
+func TestStateEnterProposeNoPrivValidator(t *testing.T) {
 	cs, _ := randConsensusState(1)
 	cs.SetPrivValidator(nil)
 	height, round := cs.Height, cs.Round
 
 	// Listen for propose timeout event
-	timeoutCh := subscribeToEvent(cs.evsw, "tester", types.EventStringTimeoutPropose(), 1)
+	timeoutCh := subscribe(cs.eventBus, types.EventQueryTimeoutPropose)
 
 	startTestRound(cs, height, round)
 
 	// if we're not a validator, EnterPropose should timeout
-	ticker := time.NewTicker(cs.timeoutParams.ensureProposeTimeout())
+	ticker := time.NewTicker(ensureProposeTimeout(cs.config.TimeoutPropose))
 	select {
 	case <-timeoutCh:
 	case <-ticker.C:
@@ -140,14 +143,14 @@ func TestEnterProposeNoPrivValidator(t *testing.T) {
 }
 
 // a validator should not timeout of the prevote round (TODO: unless the block is really big!)
-func TestEnterProposeYesPrivValidator(t *testing.T) {
+func TestStateEnterProposeYesPrivValidator(t *testing.T) {
 	cs, _ := randConsensusState(1)
 	height, round := cs.Height, cs.Round
 
 	// Listen for propose timeout event
 
-	timeoutCh := subscribeToEvent(cs.evsw, "tester", types.EventStringTimeoutPropose(), 1)
-	proposalCh := subscribeToEvent(cs.evsw, "tester", types.EventStringCompleteProposal(), 1)
+	timeoutCh := subscribe(cs.eventBus, types.EventQueryTimeoutPropose)
+	proposalCh := subscribe(cs.eventBus, types.EventQueryCompleteProposal)
 
 	cs.enterNewRound(height, round)
 	cs.startRoutines(3)
@@ -167,7 +170,7 @@ func TestEnterProposeYesPrivValidator(t *testing.T) {
 	}
 
 	// if we're a validator, enterPropose should not timeout
-	ticker := time.NewTicker(cs.timeoutParams.ensureProposeTimeout())
+	ticker := time.NewTicker(ensureProposeTimeout(cs.config.TimeoutPropose))
 	select {
 	case <-timeoutCh:
 		panic("Expected EnterPropose not to timeout")
@@ -176,15 +179,15 @@ func TestEnterProposeYesPrivValidator(t *testing.T) {
 	}
 }
 
-func TestBadProposal(t *testing.T) {
+func TestStateBadProposal(t *testing.T) {
 	cs1, vss := randConsensusState(2)
 	height, round := cs1.Height, cs1.Round
 	vs2 := vss[1]
 
-	partSize := config.GetInt("block_part_size")
+	partSize := cs1.state.ConsensusParams.BlockPartSizeBytes
 
-	proposalCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringCompleteProposal(), 1)
-	voteCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringVote(), 1)
+	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
+	voteCh := subscribe(cs1.eventBus, types.EventQueryVote)
 
 	propBlock, _ := cs1.createProposalBlock() //changeProposer(t, cs1, vs2)
 
@@ -201,12 +204,14 @@ func TestBadProposal(t *testing.T) {
 	propBlock.AppHash = stateHash
 	propBlockParts := propBlock.MakePartSet(partSize)
 	proposal := types.NewProposal(vs2.Height, round, propBlockParts.Header(), -1, types.BlockID{})
-	if err := vs2.SignProposal(config.GetString("chain_id"), proposal); err != nil {
+	if err := vs2.SignProposal(config.ChainID(), proposal); err != nil {
 		t.Fatal("failed to sign bad proposal", err)
 	}
 
 	// set the proposal block
-	cs1.SetProposalAndBlock(proposal, propBlock, propBlockParts, "some peer")
+	if err := cs1.SetProposalAndBlock(proposal, propBlock, propBlockParts, "some peer"); err != nil {
+		t.Fatal(err)
+	}
 
 	// start the machine
 	startTestRound(cs1, height, round)
@@ -234,13 +239,21 @@ func TestBadProposal(t *testing.T) {
 // FullRoundSuite
 
 // propose, prevote, and precommit a block
-func TestFullRound1(t *testing.T) {
+func TestStateFullRound1(t *testing.T) {
 	cs, vss := randConsensusState(1)
 	height, round := cs.Height, cs.Round
 
-	voteCh := subscribeToEvent(cs.evsw, "tester", types.EventStringVote(), 0)
-	propCh := subscribeToEvent(cs.evsw, "tester", types.EventStringCompleteProposal(), 1)
-	newRoundCh := subscribeToEvent(cs.evsw, "tester", types.EventStringNewRound(), 1)
+	// NOTE: buffer capacity of 0 ensures we can validate prevote and last commit
+	// before consensus can move to the next height (and cause a race condition)
+	cs.eventBus.Stop()
+	eventBus := types.NewEventBusWithBufferCapacity(0)
+	eventBus.SetLogger(log.TestingLogger().With("module", "events"))
+	cs.SetEventBus(eventBus)
+	eventBus.Start()
+
+	voteCh := subscribe(cs.eventBus, types.EventQueryVote)
+	propCh := subscribe(cs.eventBus, types.EventQueryCompleteProposal)
+	newRoundCh := subscribe(cs.eventBus, types.EventQueryNewRound)
 
 	startTestRound(cs, height, round)
 
@@ -248,11 +261,9 @@ func TestFullRound1(t *testing.T) {
 
 	// grab proposal
 	re := <-propCh
-	propBlockHash := re.(types.EventDataRoundState).RoundState.(*RoundState).ProposalBlock.Hash()
+	propBlockHash := re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState).ProposalBlock.Hash()
 
 	<-voteCh // wait for prevote
-	// NOTE: voteChan cap of 0 ensures we can complete this
-	// before consensus can move to the next height (and cause a race condition)
 	validatePrevote(t, cs, round, vss[0], propBlockHash)
 
 	<-voteCh // wait for precommit
@@ -264,11 +275,11 @@ func TestFullRound1(t *testing.T) {
 }
 
 // nil is proposed, so prevote and precommit nil
-func TestFullRoundNil(t *testing.T) {
+func TestStateFullRoundNil(t *testing.T) {
 	cs, vss := randConsensusState(1)
 	height, round := cs.Height, cs.Round
 
-	voteCh := subscribeToEvent(cs.evsw, "tester", types.EventStringVote(), 1)
+	voteCh := subscribe(cs.eventBus, types.EventQueryVote)
 
 	cs.enterPrevote(height, round)
 	cs.startRoutines(4)
@@ -282,13 +293,13 @@ func TestFullRoundNil(t *testing.T) {
 
 // run through propose, prevote, precommit commit with two validators
 // where the first validator has to wait for votes from the second
-func TestFullRound2(t *testing.T) {
+func TestStateFullRound2(t *testing.T) {
 	cs1, vss := randConsensusState(2)
 	vs2 := vss[1]
 	height, round := cs1.Height, cs1.Round
 
-	voteCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringVote(), 1)
-	newBlockCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringNewBlock(), 1)
+	voteCh := subscribe(cs1.eventBus, types.EventQueryVote)
+	newBlockCh := subscribe(cs1.eventBus, types.EventQueryNewBlock)
 
 	// start round and wait for propose and prevote
 	startTestRound(cs1, height, round)
@@ -323,18 +334,18 @@ func TestFullRound2(t *testing.T) {
 
 // two validators, 4 rounds.
 // two vals take turns proposing. val1 locks on first one, precommits nil on everything else
-func TestLockNoPOL(t *testing.T) {
+func TestStateLockNoPOL(t *testing.T) {
 	cs1, vss := randConsensusState(2)
 	vs2 := vss[1]
 	height := cs1.Height
 
-	partSize := config.GetInt("block_part_size")
+	partSize := cs1.state.ConsensusParams.BlockPartSizeBytes
 
-	timeoutProposeCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringTimeoutPropose(), 1)
-	timeoutWaitCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringTimeoutWait(), 1)
-	voteCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringVote(), 1)
-	proposalCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringCompleteProposal(), 1)
-	newRoundCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringNewRound(), 1)
+	timeoutProposeCh := subscribe(cs1.eventBus, types.EventQueryTimeoutPropose)
+	timeoutWaitCh := subscribe(cs1.eventBus, types.EventQueryTimeoutWait)
+	voteCh := subscribe(cs1.eventBus, types.EventQueryVote)
+	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
+	newRoundCh := subscribe(cs1.eventBus, types.EventQueryNewRound)
 
 	/*
 		Round1 (cs1, B) // B B // B B2
@@ -345,7 +356,7 @@ func TestLockNoPOL(t *testing.T) {
 	cs1.startRoutines(0)
 
 	re := <-proposalCh
-	rs := re.(types.EventDataRoundState).RoundState.(*RoundState)
+	rs := re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 	theBlockHash := rs.ProposalBlock.Hash()
 
 	<-voteCh // prevote
@@ -376,7 +387,7 @@ func TestLockNoPOL(t *testing.T) {
 	///
 
 	<-newRoundCh
-	log.Notice("#### ONTO ROUND 1")
+	t.Log("#### ONTO ROUND 1")
 	/*
 		Round2 (cs1, B) // B B2
 	*/
@@ -385,7 +396,7 @@ func TestLockNoPOL(t *testing.T) {
 
 	// now we're on a new round and not the proposer, so wait for timeout
 	re = <-timeoutProposeCh
-	rs = re.(types.EventDataRoundState).RoundState.(*RoundState)
+	rs = re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 
 	if rs.ProposalBlock != nil {
 		panic("Expected proposal block to be nil")
@@ -398,7 +409,7 @@ func TestLockNoPOL(t *testing.T) {
 	validatePrevote(t, cs1, 1, vss[0], rs.LockedBlock.Hash())
 
 	// add a conflicting prevote from the other validator
-	signAddVotes(cs1, types.VoteTypePrevote, hash, rs.ProposalBlock.MakePartSet(partSize).Header(), vs2)
+	signAddVotes(cs1, types.VoteTypePrevote, hash, rs.LockedBlock.MakePartSet(partSize).Header(), vs2)
 	<-voteCh
 
 	// now we're going to enter prevote again, but with invalid args
@@ -413,7 +424,7 @@ func TestLockNoPOL(t *testing.T) {
 
 	// add conflicting precommit from vs2
 	// NOTE: in practice we should never get to a point where there are precommits for different blocks at the same round
-	signAddVotes(cs1, types.VoteTypePrecommit, hash, rs.ProposalBlock.MakePartSet(partSize).Header(), vs2)
+	signAddVotes(cs1, types.VoteTypePrecommit, hash, rs.LockedBlock.MakePartSet(partSize).Header(), vs2)
 	<-voteCh
 
 	// (note we're entering precommit for a second time this round, but with invalid args
@@ -421,7 +432,7 @@ func TestLockNoPOL(t *testing.T) {
 	<-timeoutWaitCh
 
 	<-newRoundCh
-	log.Notice("#### ONTO ROUND 2")
+	t.Log("#### ONTO ROUND 2")
 	/*
 		Round3 (vs2, _) // B, B2
 	*/
@@ -429,11 +440,11 @@ func TestLockNoPOL(t *testing.T) {
 	incrementRound(vs2)
 
 	re = <-proposalCh
-	rs = re.(types.EventDataRoundState).RoundState.(*RoundState)
+	rs = re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 
 	// now we're on a new round and are the proposer
 	if !bytes.Equal(rs.ProposalBlock.Hash(), rs.LockedBlock.Hash()) {
-		panic(Fmt("Expected proposal block to be locked block. Got %v, Expected %v", rs.ProposalBlock, rs.LockedBlock))
+		panic(cmn.Fmt("Expected proposal block to be locked block. Got %v, Expected %v", rs.ProposalBlock, rs.LockedBlock))
 	}
 
 	<-voteCh // prevote
@@ -462,14 +473,16 @@ func TestLockNoPOL(t *testing.T) {
 	incrementRound(vs2)
 
 	<-newRoundCh
-	log.Notice("#### ONTO ROUND 3")
+	t.Log("#### ONTO ROUND 3")
 	/*
 		Round4 (vs2, C) // B C // B C
 	*/
 
 	// now we're on a new round and not the proposer
 	// so set the proposal block
-	cs1.SetProposalAndBlock(prop, propBlock, propBlock.MakePartSet(partSize), "")
+	if err := cs1.SetProposalAndBlock(prop, propBlock, propBlock.MakePartSet(partSize), ""); err != nil {
+		t.Fatal(err)
+	}
 
 	<-proposalCh
 	<-voteCh // prevote
@@ -490,20 +503,18 @@ func TestLockNoPOL(t *testing.T) {
 }
 
 // 4 vals, one precommits, other 3 polka at next round, so we unlock and precomit the polka
-func TestLockPOLRelock(t *testing.T) {
+func TestStateLockPOLRelock(t *testing.T) {
 	cs1, vss := randConsensusState(4)
 	vs2, vs3, vs4 := vss[1], vss[2], vss[3]
 
-	partSize := config.GetInt("block_part_size")
+	partSize := cs1.state.ConsensusParams.BlockPartSizeBytes
 
-	timeoutProposeCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringTimeoutPropose(), 1)
-	timeoutWaitCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringTimeoutWait(), 1)
-	proposalCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringCompleteProposal(), 1)
-	voteCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringVote(), 1)
-	newRoundCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringNewRound(), 1)
-	newBlockCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringNewBlockHeader(), 1)
-
-	log.Debug("vs2 last round", "lr", vs2.PrivValidator.LastRound)
+	timeoutProposeCh := subscribe(cs1.eventBus, types.EventQueryTimeoutPropose)
+	timeoutWaitCh := subscribe(cs1.eventBus, types.EventQueryTimeoutWait)
+	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
+	voteCh := subscribe(cs1.eventBus, types.EventQueryVote)
+	newRoundCh := subscribe(cs1.eventBus, types.EventQueryNewRound)
+	newBlockCh := subscribe(cs1.eventBus, types.EventQueryNewBlockHeader)
 
 	// everything done from perspective of cs1
 
@@ -518,13 +529,14 @@ func TestLockPOLRelock(t *testing.T) {
 
 	<-newRoundCh
 	re := <-proposalCh
-	rs := re.(types.EventDataRoundState).RoundState.(*RoundState)
+	rs := re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 	theBlockHash := rs.ProposalBlock.Hash()
 
 	<-voteCh // prevote
 
 	signAddVotes(cs1, types.VoteTypePrevote, cs1.ProposalBlock.Hash(), cs1.ProposalBlockParts.Header(), vs2, vs3, vs4)
-	_, _, _ = <-voteCh, <-voteCh, <-voteCh // prevotes
+	// prevotes
+	discardFromChan(voteCh, 3)
 
 	<-voteCh // our precommit
 	// the proposed block should now be locked and our precommit added
@@ -533,7 +545,8 @@ func TestLockPOLRelock(t *testing.T) {
 	// add precommits from the rest
 	signAddVotes(cs1, types.VoteTypePrecommit, nil, types.PartSetHeader{}, vs2, vs4)
 	signAddVotes(cs1, types.VoteTypePrecommit, cs1.ProposalBlock.Hash(), cs1.ProposalBlockParts.Header(), vs3)
-	_, _, _ = <-voteCh, <-voteCh, <-voteCh // precommits
+	// precommites
+	discardFromChan(voteCh, 3)
 
 	// before we timeout to the new round set the new proposal
 	prop, propBlock := decideProposal(cs1, vs2, vs2.Height, vs2.Round+1)
@@ -545,11 +558,13 @@ func TestLockPOLRelock(t *testing.T) {
 	// timeout to new round
 	<-timeoutWaitCh
 
-	//XXX: this isnt gauranteed to get there before the timeoutPropose ...
-	cs1.SetProposalAndBlock(prop, propBlock, propBlockParts, "some peer")
+	//XXX: this isnt guaranteed to get there before the timeoutPropose ...
+	if err := cs1.SetProposalAndBlock(prop, propBlock, propBlockParts, "some peer"); err != nil {
+		t.Fatal(err)
+	}
 
 	<-newRoundCh
-	log.Notice("### ONTO ROUND 1")
+	t.Log("### ONTO ROUND 1")
 
 	/*
 		Round2 (vs2, C) // B C C C // C C C _)
@@ -571,7 +586,8 @@ func TestLockPOLRelock(t *testing.T) {
 
 	// now lets add prevotes from everyone else for the new block
 	signAddVotes(cs1, types.VoteTypePrevote, propBlockHash, propBlockParts.Header(), vs2, vs3, vs4)
-	_, _, _ = <-voteCh, <-voteCh, <-voteCh // prevotes
+	// prevotes
+	discardFromChan(voteCh, 3)
 
 	// now either we go to PrevoteWait or Precommit
 	select {
@@ -586,12 +602,12 @@ func TestLockPOLRelock(t *testing.T) {
 	validatePrecommit(t, cs1, 1, 1, vss[0], propBlockHash, propBlockHash)
 
 	signAddVotes(cs1, types.VoteTypePrecommit, propBlockHash, propBlockParts.Header(), vs2, vs3)
-	_, _ = <-voteCh, <-voteCh
+	discardFromChan(voteCh, 2)
 
 	be := <-newBlockCh
 	b := be.(types.EventDataNewBlockHeader)
 	re = <-newRoundCh
-	rs = re.(types.EventDataRoundState).RoundState.(*RoundState)
+	rs = re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 	if rs.Height != 2 {
 		panic("Expected height to increment")
 	}
@@ -602,17 +618,17 @@ func TestLockPOLRelock(t *testing.T) {
 }
 
 // 4 vals, one precommits, other 3 polka at next round, so we unlock and precomit the polka
-func TestLockPOLUnlock(t *testing.T) {
+func TestStateLockPOLUnlock(t *testing.T) {
 	cs1, vss := randConsensusState(4)
 	vs2, vs3, vs4 := vss[1], vss[2], vss[3]
 
-	partSize := config.GetInt("block_part_size")
+	partSize := cs1.state.ConsensusParams.BlockPartSizeBytes
 
-	proposalCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringCompleteProposal(), 1)
-	timeoutProposeCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringTimeoutPropose(), 1)
-	timeoutWaitCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringTimeoutWait(), 1)
-	newRoundCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringNewRound(), 1)
-	unlockCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringUnlock(), 1)
+	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
+	timeoutProposeCh := subscribe(cs1.eventBus, types.EventQueryTimeoutPropose)
+	timeoutWaitCh := subscribe(cs1.eventBus, types.EventQueryTimeoutWait)
+	newRoundCh := subscribe(cs1.eventBus, types.EventQueryNewRound)
+	unlockCh := subscribe(cs1.eventBus, types.EventQueryUnlock)
 	voteCh := subscribeToVoter(cs1, cs1.privValidator.GetAddress())
 
 	// everything done from perspective of cs1
@@ -627,7 +643,7 @@ func TestLockPOLUnlock(t *testing.T) {
 	startTestRound(cs1, cs1.Height, 0)
 	<-newRoundCh
 	re := <-proposalCh
-	rs := re.(types.EventDataRoundState).RoundState.(*RoundState)
+	rs := re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 	theBlockHash := rs.ProposalBlock.Hash()
 
 	<-voteCh // prevote
@@ -653,14 +669,16 @@ func TestLockPOLUnlock(t *testing.T) {
 
 	// timeout to new round
 	re = <-timeoutWaitCh
-	rs = re.(types.EventDataRoundState).RoundState.(*RoundState)
+	rs = re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 	lockedBlockHash := rs.LockedBlock.Hash()
 
-	//XXX: this isnt gauranteed to get there before the timeoutPropose ...
-	cs1.SetProposalAndBlock(prop, propBlock, propBlockParts, "some peer")
+	//XXX: this isnt guaranteed to get there before the timeoutPropose ...
+	if err := cs1.SetProposalAndBlock(prop, propBlock, propBlockParts, "some peer"); err != nil {
+		t.Fatal(err)
+	}
 
 	<-newRoundCh
-	log.Notice("#### ONTO ROUND 1")
+	t.Log("#### ONTO ROUND 1")
 	/*
 		Round2 (vs2, C) // B nil nil nil // nil nil nil _
 
@@ -697,23 +715,23 @@ func TestLockPOLUnlock(t *testing.T) {
 // a polka at round 1 but we miss it
 // then a polka at round 2 that we lock on
 // then we see the polka from round 1 but shouldn't unlock
-func TestLockPOLSafety1(t *testing.T) {
+func TestStateLockPOLSafety1(t *testing.T) {
 	cs1, vss := randConsensusState(4)
 	vs2, vs3, vs4 := vss[1], vss[2], vss[3]
 
-	partSize := config.GetInt("block_part_size")
+	partSize := cs1.state.ConsensusParams.BlockPartSizeBytes
 
-	proposalCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringCompleteProposal(), 1)
-	timeoutProposeCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringTimeoutPropose(), 1)
-	timeoutWaitCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringTimeoutWait(), 1)
-	newRoundCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringNewRound(), 1)
+	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
+	timeoutProposeCh := subscribe(cs1.eventBus, types.EventQueryTimeoutPropose)
+	timeoutWaitCh := subscribe(cs1.eventBus, types.EventQueryTimeoutWait)
+	newRoundCh := subscribe(cs1.eventBus, types.EventQueryNewRound)
 	voteCh := subscribeToVoter(cs1, cs1.privValidator.GetAddress())
 
 	// start round and wait for propose and prevote
 	startTestRound(cs1, cs1.Height, 0)
 	<-newRoundCh
 	re := <-proposalCh
-	rs := re.(types.EventDataRoundState).RoundState.(*RoundState)
+	rs := re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 	propBlock := rs.ProposalBlock
 
 	<-voteCh // prevote
@@ -732,7 +750,7 @@ func TestLockPOLSafety1(t *testing.T) {
 			panic("failed to update validator")
 		}*/
 
-	log.Warn("old prop", "hash", fmt.Sprintf("%X", propBlock.Hash()))
+	t.Logf("old prop hash %v", fmt.Sprintf("%X", propBlock.Hash()))
 
 	// we do see them precommit nil
 	signAddVotes(cs1, types.VoteTypePrecommit, nil, types.PartSetHeader{}, vs2, vs3, vs4)
@@ -743,11 +761,13 @@ func TestLockPOLSafety1(t *testing.T) {
 
 	incrementRound(vs2, vs3, vs4)
 
-	//XXX: this isnt gauranteed to get there before the timeoutPropose ...
-	cs1.SetProposalAndBlock(prop, propBlock, propBlockParts, "some peer")
+	//XXX: this isnt guaranteed to get there before the timeoutPropose ...
+	if err := cs1.SetProposalAndBlock(prop, propBlock, propBlockParts, "some peer"); err != nil {
+		t.Fatal(err)
+	}
 
 	<-newRoundCh
-	log.Notice("### ONTO ROUND 1")
+	t.Log("### ONTO ROUND 1")
 	/*Round2
 	// we timeout and prevote our lock
 	// a polka happened but we didn't see it!
@@ -761,12 +781,12 @@ func TestLockPOLSafety1(t *testing.T) {
 		re = <-proposalCh
 	}
 
-	rs = re.(types.EventDataRoundState).RoundState.(*RoundState)
+	rs = re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 
 	if rs.LockedBlock != nil {
 		panic("we should not be locked!")
 	}
-	log.Warn("new prop", "hash", fmt.Sprintf("%X", propBlockHash))
+	t.Logf("new prop hash %v", fmt.Sprintf("%X", propBlockHash))
 	// go to prevote, prevote for proposal block
 	<-voteCh
 	validatePrevote(t, cs1, 1, vss[0], propBlockHash)
@@ -787,7 +807,7 @@ func TestLockPOLSafety1(t *testing.T) {
 
 	<-newRoundCh
 
-	log.Notice("### ONTO ROUND 2")
+	t.Log("### ONTO ROUND 2")
 	/*Round3
 	we see the polka from round 1 but we shouldn't unlock!
 	*/
@@ -801,12 +821,12 @@ func TestLockPOLSafety1(t *testing.T) {
 	// we should prevote what we're locked on
 	validatePrevote(t, cs1, 2, vss[0], propBlockHash)
 
-	newStepCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringNewRoundStep(), 1)
+	newStepCh := subscribe(cs1.eventBus, types.EventQueryNewRoundStep)
 
 	// add prevotes from the earlier round
 	addVotes(cs1, prevotes...)
 
-	log.Warn("Done adding prevotes!")
+	t.Log("Done adding prevotes!")
 
 	ensureNoNewStep(newStepCh)
 }
@@ -818,17 +838,17 @@ func TestLockPOLSafety1(t *testing.T) {
 
 // What we want:
 // dont see P0, lock on P1 at R1, dont unlock using P0 at R2
-func TestLockPOLSafety2(t *testing.T) {
+func TestStateLockPOLSafety2(t *testing.T) {
 	cs1, vss := randConsensusState(4)
 	vs2, vs3, vs4 := vss[1], vss[2], vss[3]
 
-	partSize := config.GetInt("block_part_size")
+	partSize := cs1.state.ConsensusParams.BlockPartSizeBytes
 
-	proposalCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringCompleteProposal(), 1)
-	timeoutProposeCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringTimeoutPropose(), 1)
-	timeoutWaitCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringTimeoutWait(), 1)
-	newRoundCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringNewRound(), 1)
-	unlockCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringUnlock(), 1)
+	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
+	timeoutProposeCh := subscribe(cs1.eventBus, types.EventQueryTimeoutPropose)
+	timeoutWaitCh := subscribe(cs1.eventBus, types.EventQueryTimeoutWait)
+	newRoundCh := subscribe(cs1.eventBus, types.EventQueryNewRound)
+	unlockCh := subscribe(cs1.eventBus, types.EventQueryUnlock)
 	voteCh := subscribeToVoter(cs1, cs1.privValidator.GetAddress())
 
 	// the block for R0: gets polkad but we miss it
@@ -848,15 +868,17 @@ func TestLockPOLSafety2(t *testing.T) {
 
 	incrementRound(vs2, vs3, vs4)
 
-	cs1.updateRoundStep(0, RoundStepPrecommitWait)
+	cs1.updateRoundStep(0, cstypes.RoundStepPrecommitWait)
 
-	log.Notice("### ONTO Round 1")
+	t.Log("### ONTO Round 1")
 	// jump in at round 1
 	height := cs1.Height
 	startTestRound(cs1, height, 1)
 	<-newRoundCh
 
-	cs1.SetProposalAndBlock(prop1, propBlock1, propBlockParts1, "some peer")
+	if err := cs1.SetProposalAndBlock(prop1, propBlock1, propBlockParts1, "some peer"); err != nil {
+		t.Fatal(err)
+	}
 	<-proposalCh
 
 	<-voteCh // prevote
@@ -878,16 +900,18 @@ func TestLockPOLSafety2(t *testing.T) {
 
 	// in round 2 we see the polkad block from round 0
 	newProp := types.NewProposal(height, 2, propBlockParts0.Header(), 0, propBlockID1)
-	if err := vs3.SignProposal(config.GetString("chain_id"), newProp); err != nil {
+	if err := vs3.SignProposal(config.ChainID(), newProp); err != nil {
+		t.Fatal(err)
+	}
+	if err := cs1.SetProposalAndBlock(newProp, propBlock0, propBlockParts0, "some peer"); err != nil {
 		t.Fatal(err)
 	}
-	cs1.SetProposalAndBlock(newProp, propBlock0, propBlockParts0, "some peer")
 
 	// Add the pol votes
 	addVotes(cs1, prevotes...)
 
 	<-newRoundCh
-	log.Notice("### ONTO Round 2")
+	t.Log("### ONTO Round 2")
 	/*Round2
 	// now we see the polka from round 1, but we shouldnt unlock
 	*/
@@ -913,14 +937,14 @@ func TestLockPOLSafety2(t *testing.T) {
 // TODO: Slashing
 
 /*
-func TestSlashingPrevotes(t *testing.T) {
+func TestStateSlashingPrevotes(t *testing.T) {
 	cs1, vss := randConsensusState(2)
 	vs2 := vss[1]
 
 
-	proposalCh := subscribeToEvent(cs1.evsw,"tester",types.EventStringCompleteProposal() , 1)
-	timeoutWaitCh := subscribeToEvent(cs1.evsw,"tester",types.EventStringTimeoutWait() , 1)
-	newRoundCh := subscribeToEvent(cs1.evsw,"tester",types.EventStringNewRound() , 1)
+	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
+	timeoutWaitCh := subscribe(cs1.eventBus, types.EventQueryTimeoutWait)
+	newRoundCh := subscribe(cs1.eventBus, types.EventQueryNewRound)
 	voteCh := subscribeToVoter(cs1, cs1.privValidator.GetAddress())
 
 	// start round and wait for propose and prevote
@@ -929,7 +953,7 @@ func TestSlashingPrevotes(t *testing.T) {
 	re := <-proposalCh
 	<-voteCh // prevote
 
-	rs := re.(types.EventDataRoundState).RoundState.(*RoundState)
+	rs := re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 
 	// we should now be stuck in limbo forever, waiting for more prevotes
 	// add one for a different block should cause us to go into prevote wait
@@ -948,14 +972,14 @@ func TestSlashingPrevotes(t *testing.T) {
 	// XXX: Check for existence of Dupeout info
 }
 
-func TestSlashingPrecommits(t *testing.T) {
+func TestStateSlashingPrecommits(t *testing.T) {
 	cs1, vss := randConsensusState(2)
 	vs2 := vss[1]
 
 
-	proposalCh := subscribeToEvent(cs1.evsw,"tester",types.EventStringCompleteProposal() , 1)
-	timeoutWaitCh := subscribeToEvent(cs1.evsw,"tester",types.EventStringTimeoutWait() , 1)
-	newRoundCh := subscribeToEvent(cs1.evsw,"tester",types.EventStringNewRound() , 1)
+	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
+	timeoutWaitCh := subscribe(cs1.eventBus, types.EventQueryTimeoutWait)
+	newRoundCh := subscribe(cs1.eventBus, types.EventQueryNewRound)
 	voteCh := subscribeToVoter(cs1, cs1.privValidator.GetAddress())
 
 	// start round and wait for propose and prevote
@@ -993,23 +1017,23 @@ func TestSlashingPrecommits(t *testing.T) {
 
 // 4 vals.
 // we receive a final precommit after going into next round, but others might have gone to commit already!
-func TestHalt1(t *testing.T) {
+func TestStateHalt1(t *testing.T) {
 	cs1, vss := randConsensusState(4)
 	vs2, vs3, vs4 := vss[1], vss[2], vss[3]
 
-	partSize := config.GetInt("block_part_size")
+	partSize := cs1.state.ConsensusParams.BlockPartSizeBytes
 
-	proposalCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringCompleteProposal(), 1)
-	timeoutWaitCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringTimeoutWait(), 1)
-	newRoundCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringNewRound(), 1)
-	newBlockCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringNewBlock(), 1)
+	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
+	timeoutWaitCh := subscribe(cs1.eventBus, types.EventQueryTimeoutWait)
+	newRoundCh := subscribe(cs1.eventBus, types.EventQueryNewRound)
+	newBlockCh := subscribe(cs1.eventBus, types.EventQueryNewBlock)
 	voteCh := subscribeToVoter(cs1, cs1.privValidator.GetAddress())
 
 	// start round and wait for propose and prevote
 	startTestRound(cs1, cs1.Height, 0)
 	<-newRoundCh
 	re := <-proposalCh
-	rs := re.(types.EventDataRoundState).RoundState.(*RoundState)
+	rs := re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 	propBlock := rs.ProposalBlock
 	propBlockParts := propBlock.MakePartSet(partSize)
 
@@ -1032,9 +1056,9 @@ func TestHalt1(t *testing.T) {
 	// timeout to new round
 	<-timeoutWaitCh
 	re = <-newRoundCh
-	rs = re.(types.EventDataRoundState).RoundState.(*RoundState)
+	rs = re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 
-	log.Notice("### ONTO ROUND 1")
+	t.Log("### ONTO ROUND 1")
 	/*Round2
 	// we timeout and prevote our lock
 	// a polka happened but we didn't see it!
@@ -1050,9 +1074,26 @@ func TestHalt1(t *testing.T) {
 	// receiving that precommit should take us straight to commit
 	<-newBlockCh
 	re = <-newRoundCh
-	rs = re.(types.EventDataRoundState).RoundState.(*RoundState)
+	rs = re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 
 	if rs.Height != 2 {
 		panic("expected height to increment")
 	}
 }
+
+// subscribe subscribes test client to the given query and returns a channel with cap = 1.
+func subscribe(eventBus *types.EventBus, q tmpubsub.Query) <-chan interface{} {
+	out := make(chan interface{}, 1)
+	err := eventBus.Subscribe(context.Background(), testSubscriber, q, out)
+	if err != nil {
+		panic(fmt.Sprintf("failed to subscribe %s to %v", testSubscriber, q))
+	}
+	return out
+}
+
+// discardFromChan reads n values from the channel.
+func discardFromChan(ch <-chan interface{}, n int) {
+	for i := 0; i < n; i++ {
+		<-ch
+	}
+}

consensus/test_data/README.md

@@ -1,36 +0,0 @@
-# Generating test data
-
-To generate the data, run `build.sh`. See that script for more details.
-
-Make sure to adjust the stepChanges in the testCases if the number of messages changes.
-This sometimes happens for the `small_block2.cswal`, where the number of block parts changes between 4 and 5.
-
-If you need to change the signatures, you can use a script as follows:
-The privBytes comes from `config/tendermint_test/...`:
-
-```
-package main
-
-import (
-	"encoding/hex"
-	"fmt"
-
-	"github.com/tendermint/go-crypto"
-)
-
-func main() {
-	signBytes, err := hex.DecodeString("7B22636861696E5F6964223A2274656E6465726D696E745F74657374222C22766F7465223A7B22626C6F636B5F68617368223A2242453544373939433846353044354645383533364334333932464443384537423342313830373638222C22626C6F636B5F70617274735F686561646572223A506172745365747B543A31204236323237323535464632307D2C22686569676874223A312C22726F756E64223A302C2274797065223A327D7D")
-	if err != nil {
-		panic(err)
-	}
-	privBytes, err := hex.DecodeString("27F82582AEFAE7AB151CFB01C48BB6C1A0DA78F9BDDA979A9F70A84D074EB07D3B3069C422E19688B45CBFAE7BB009FC0FA1B1EA86593519318B7214853803C8")
-	if err != nil {
-		panic(err)
-	}
-	privKey := crypto.PrivKeyEd25519{}
-	copy(privKey[:], privBytes)
-	signature := privKey.Sign(signBytes)
-	fmt.Printf("Signature Bytes: %X\n", signature.Bytes())
-}
-```
-

consensus/test_data/build.sh

@@ -1,103 +0,0 @@
-#! /bin/bash
-
-# XXX: removes tendermint dir
-
-cd $GOPATH/src/github.com/tendermint/tendermint
-
-# specify a dir to copy
-# TODO: eventually we should replace with `tendermint init --test`
-DIR=$HOME/.tendermint_test/consensus_state_test
-
-rm -rf $HOME/.tendermint
-cp -r $DIR $HOME/.tendermint
-
-function reset(){
-	rm -rf $HOME/.tendermint/data
-	tendermint unsafe_reset_priv_validator
-}
-
-reset
-
-# empty block
-function empty_block(){
-tendermint node --proxy_app=dummy &> /dev/null &
-sleep 5
-killall tendermint
-
-# /q would print up to and including the match, then quit. 
-# /Q doesn't include the match. 
-# http://unix.stackexchange.com/questions/11305/grep-show-all-the-file-up-to-the-match
-sed '/ENDHEIGHT: 1/Q' ~/.tendermint/data/cs.wal/wal  > consensus/test_data/empty_block.cswal
-
-reset
-}
-
-# many blocks
-function many_blocks(){
-bash scripts/txs/random.sh 1000 36657 &> /dev/null &
-PID=$!
-tendermint node --proxy_app=dummy &> /dev/null &
-sleep 7
-killall tendermint
-kill -9 $PID
-
-sed '/ENDHEIGHT: 6/Q' ~/.tendermint/data/cs.wal/wal  > consensus/test_data/many_blocks.cswal
-
-reset
-}
-
-
-# small block 1
-function small_block1(){
-bash scripts/txs/random.sh 1000 36657 &> /dev/null &
-PID=$!
-tendermint node --proxy_app=dummy &> /dev/null &
-sleep 10
-killall tendermint
-kill -9 $PID
-
-sed '/ENDHEIGHT: 1/Q' ~/.tendermint/data/cs.wal/wal  > consensus/test_data/small_block1.cswal
-
-reset
-}
-
-
-# small block 2 (part size = 512)
-function small_block2(){
-echo "" >> ~/.tendermint/config.toml
-echo "block_part_size = 512" >> ~/.tendermint/config.toml
-bash scripts/txs/random.sh 1000 36657 &> /dev/null &
-PID=$!
-tendermint node --proxy_app=dummy &> /dev/null &
-sleep 5
-killall tendermint
-kill -9 $PID
-
-sed '/ENDHEIGHT: 1/Q' ~/.tendermint/data/cs.wal/wal  > consensus/test_data/small_block2.cswal
-
-reset
-}
-
-
-
-case "$1" in 
-	"small_block1")
-		small_block1
-		;;
-	"small_block2")
-		small_block2
-		;;
-	"empty_block")
-		empty_block
-		;;
-	"many_blocks")
-		many_blocks
-		;;
-	*)
-		small_block1
-		small_block2
-		empty_block
-		many_blocks
-esac
-
-

consensus/test_data/empty_block.cswal

@@ -1,10 +0,0 @@
-#ENDHEIGHT: 0
-{"time":"2016-12-18T05:05:33.502Z","msg":[3,{"duration":974084551,"height":1,"round":0,"step":1}]}
-{"time":"2016-12-18T05:05:33.505Z","msg":[1,{"height":1,"round":0,"step":"RoundStepPropose"}]}
-{"time":"2016-12-18T05:05:33.505Z","msg":[2,{"msg":[17,{"Proposal":{"height":1,"round":0,"block_parts_header":{"total":1,"hash":"71D2DA2336A9F84C22A28FF6C67F35F3478FC0AF"},"pol_round":-1,"pol_block_id":{"hash":"","parts":{"total":0,"hash":""}},"signature":[1,"62C0F2BCCB491399EEDAF8E85837ADDD4E25BAB7A84BFC4F0E88594531FBC6D4755DEC7E6427F04AD7EB8BB89502762AB4380C7BBA93A4C297E6180EC78E3504"]}}],"peer_key":""}]}
-{"time":"2016-12-18T05:05:33.506Z","msg":[2,{"msg":[19,{"Height":1,"Round":0,"Part":{"index":0,"bytes":"0101010F74656E6465726D696E745F74657374010114914148D83E0DC00000000000000114354594CBFC1A7BCA1AD0050ED6AA010023EADA390001000100000000","proof":{"aunts":[]}}}],"peer_key":""}]}
-{"time":"2016-12-18T05:05:33.508Z","msg":[1,{"height":1,"round":0,"step":"RoundStepPrevote"}]}
-{"time":"2016-12-18T05:05:33.508Z","msg":[2,{"msg":[20,{"Vote":{"validator_address":"D028C9981F7A87F3093672BF0D5B0E2A1B3ED456","validator_index":0,"height":1,"round":0,"type":1,"block_id":{"hash":"3E83DF89A01C5F104912E095F32451C202F34717","parts":{"total":1,"hash":"71D2DA2336A9F84C22A28FF6C67F35F3478FC0AF"}},"signature":[1,"B64D0BB64B2E9AAFDD4EBEA679644F77AE774D69E3E2E1B042AB15FE4F84B1427AC6C8A25AFF58EA22011AE567FEA49D2EE7354382E915AD85BF40C58FA6130C"]}}],"peer_key":""}]}
-{"time":"2016-12-18T05:05:33.509Z","msg":[1,{"height":1,"round":0,"step":"RoundStepPrecommit"}]}
-{"time":"2016-12-18T05:05:33.509Z","msg":[2,{"msg":[20,{"Vote":{"validator_address":"D028C9981F7A87F3093672BF0D5B0E2A1B3ED456","validator_index":0,"height":1,"round":0,"type":2,"block_id":{"hash":"3E83DF89A01C5F104912E095F32451C202F34717","parts":{"total":1,"hash":"71D2DA2336A9F84C22A28FF6C67F35F3478FC0AF"}},"signature":[1,"D83E968392D1BF09821E0D05079DAB5491CABD89BE128BD1CF573ED87148BA84667A56C0A069EFC90760F25EDAC62BC324DBB12EA63F44E6CB2D3500FE5E640F"]}}],"peer_key":""}]}
-{"time":"2016-12-18T05:05:33.509Z","msg":[1,{"height":1,"round":0,"step":"RoundStepCommit"}]}

consensus/test_data/small_block2.cswal

@@ -1,14 +0,0 @@
-#ENDHEIGHT: 0
-{"time":"2016-12-18T05:05:43.641Z","msg":[3,{"duration":969409681,"height":1,"round":0,"step":1}]}
-{"time":"2016-12-18T05:05:43.643Z","msg":[1,{"height":1,"round":0,"step":"RoundStepPropose"}]}
-{"time":"2016-12-18T05:05:43.643Z","msg":[2,{"msg":[17,{"Proposal":{"height":1,"round":0,"block_parts_header":{"total":5,"hash":"C916905C3C444501DDDAA1BF52E959B7531E762E"},"pol_round":-1,"pol_block_id":{"hash":"","parts":{"total":0,"hash":""}},"signature":[1,"F1A8E9928889C68FD393F3983B5362AECA4A95AA13FE3C78569B2515EC046893CB718071CAF54F3F1507DCD851B37CD5557EA17BB5471D2DC6FB5AC5FBB72E02"]}}],"peer_key":""}]}
-{"time":"2016-12-18T05:05:43.643Z","msg":[2,{"msg":[19,{"Height":1,"Round":0,"Part":{"index":0,"bytes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proof":{"aunts":["C9FBD66B63A976638196323F5B93494BDDFC9EED","47FD83BB7607E679EE5CF0783372D13C5A264056","FEEC97078A26B7F6057821C0660855170CC6F1D7"]}}}],"peer_key":""}]}
-{"time":"2016-12-18T05:05:43.643Z","msg":[2,{"msg":[19,{"Height":1,"Round":0,"Part":{"index":1,"bytes":"646362613430010D6162636434313D646362613431010D6162636434323D646362613432010D6162636434333D646362613433010D6162636434343D646362613434010D6162636434353D646362613435010D6162636434363D646362613436010D6162636434373D646362613437010D6162636434383D646362613438010D6162636434393D646362613439010D6162636435303D646362613530010D6162636435313D646362613531010D6162636435323D646362613532010D6162636435333D646362613533010D6162636435343D646362613534010D6162636435353D646362613535010D6162636435363D646362613536010D6162636435373D646362613537010D6162636435383D646362613538010D6162636435393D646362613539010D6162636436303D646362613630010D6162636436313D646362613631010D6162636436323D646362613632010D6162636436333D646362613633010D6162636436343D646362613634010D6162636436353D646362613635010D6162636436363D646362613636010D6162636436373D646362613637010D6162636436383D646362613638010D6162636436393D646362613639010D6162636437303D646362613730010D6162636437313D646362613731010D6162636437323D646362613732010D6162636437333D646362613733010D6162636437343D6463","proof":{"aunts":["D7FB03B935B77C322064F8277823CDB5C7018597","47FD83BB7607E679EE5CF0783372D13C5A264056","FEEC97078A26B7F6057821C0660855170CC6F1D7"]}}}],"peer_key":""}]}
-{"time":"2016-12-18T05:05:43.644Z","msg":[2,{"msg":[19,{"Height":1,"Round":0,"Part":{"index":2,"bytes":"62613734010D6162636437353D646362613735010D6162636437363D646362613736010D6162636437373D646362613737010D6162636437383D646362613738010D6162636437393D646362613739010D6162636438303D646362613830010D6162636438313D646362613831010D6162636438323D646362613832010D6162636438333D646362613833010D6162636438343D646362613834010D6162636438353D646362613835010D6162636438363D646362613836010D6162636438373D646362613837010D6162636438383D646362613838010D6162636438393D646362613839010D6162636439303D646362613930010D6162636439313D646362613931010D6162636439323D646362613932010D6162636439333D646362613933010D6162636439343D646362613934010D6162636439353D646362613935010D6162636439363D646362613936010D6162636439373D646362613937010D6162636439383D646362613938010D6162636439393D646362613939010F616263643130303D64636261313030010F616263643130313D64636261313031010F616263643130323D64636261313032010F616263643130333D64636261313033010F616263643130343D64636261313034010F616263643130353D64636261313035010F616263643130363D64636261313036010F616263643130373D64636261","proof":{"aunts":["A607D9BF5107E6C9FD19B6928D9CC7714B0730E4","FEEC97078A26B7F6057821C0660855170CC6F1D7"]}}}],"peer_key":""}]}
-{"time":"2016-12-18T05:05:43.644Z","msg":[2,{"msg":[19,{"Height":1,"Round":0,"Part":{"index":3,"bytes":"313037010F616263643130383D64636261313038010F616263643130393D64636261313039010F616263643131303D64636261313130010F616263643131313D64636261313131010F616263643131323D64636261313132010F616263643131333D64636261313133010F616263643131343D64636261313134010F616263643131353D64636261313135010F616263643131363D64636261313136010F616263643131373D64636261313137010F616263643131383D64636261313138010F616263643131393D64636261313139010F616263643132303D64636261313230010F616263643132313D64636261313231010F616263643132323D64636261313232010F616263643132333D64636261313233010F616263643132343D64636261313234010F616263643132353D64636261313235010F616263643132363D64636261313236010F616263643132373D64636261313237010F616263643132383D64636261313238010F616263643132393D64636261313239010F616263643133303D64636261313330010F616263643133313D64636261313331010F616263643133323D64636261313332010F616263643133333D64636261313333010F616263643133343D64636261313334010F616263643133353D64636261313335010F616263643133363D64636261313336010F616263643133373D646362613133","proof":{"aunts":["0FD794B3506B9E92CDE3703F7189D42167E77095","86D455F542DA79F5A764B9DABDEABF01F4BAB2AB"]}}}],"peer_key":""}]}
-{"time":"2016-12-18T05:05:43.644Z","msg":[2,{"msg":[19,{"Height":1,"Round":0,"Part":{"index":4,"bytes":"37010F616263643133383D64636261313338010F616263643133393D64636261313339010F616263643134303D64636261313430010F616263643134313D64636261313431010F616263643134323D64636261313432010F616263643134333D64636261313433010F616263643134343D64636261313434010F616263643134353D64636261313435010F616263643134363D64636261313436010F616263643134373D64636261313437010F616263643134383D64636261313438010F616263643134393D64636261313439010F616263643135303D64636261313530010F616263643135313D64636261313531010F616263643135323D64636261313532010F616263643135333D64636261313533010F616263643135343D64636261313534010F616263643135353D646362613135350100000000","proof":{"aunts":["50CBDC078A660EAE3442BA355BE10EE0D04408D1","86D455F542DA79F5A764B9DABDEABF01F4BAB2AB"]}}}],"peer_key":""}]}
-{"time":"2016-12-18T05:05:43.645Z","msg":[1,{"height":1,"round":0,"step":"RoundStepPrevote"}]}
-{"time":"2016-12-18T05:05:43.645Z","msg":[2,{"msg":[20,{"Vote":{"validator_address":"D028C9981F7A87F3093672BF0D5B0E2A1B3ED456","validator_index":0,"height":1,"round":0,"type":1,"block_id":{"hash":"6ADACDC2871C59A67337DAFD5045A982ED070C51","parts":{"total":5,"hash":"C916905C3C444501DDDAA1BF52E959B7531E762E"}},"signature":[1,"E815E0A63B7EEE7894DE2D72372A7C393434AC8ACCC46B60C628910F73351806D55A59994F08B454BFD71EDAA0CA95733CA47E37FFDAF9AAA2431A8160176E01"]}}],"peer_key":""}]}
-{"time":"2016-12-18T05:05:43.647Z","msg":[1,{"height":1,"round":0,"step":"RoundStepPrecommit"}]}
-{"time":"2016-12-18T05:05:43.647Z","msg":[2,{"msg":[20,{"Vote":{"validator_address":"D028C9981F7A87F3093672BF0D5B0E2A1B3ED456","validator_index":0,"height":1,"round":0,"type":2,"block_id":{"hash":"6ADACDC2871C59A67337DAFD5045A982ED070C51","parts":{"total":5,"hash":"C916905C3C444501DDDAA1BF52E959B7531E762E"}},"signature":[1,"9AAC3F3A118EE039EB460E9E5308D490D671C7490309BD5D62B5F392205C7E420DFDAF90F08294FF36BE8A9AA5CC203C1F2088B42D2BB8EE40A45F2BB5C54D0A"]}}],"peer_key":""}]}
-{"time":"2016-12-18T05:05:43.648Z","msg":[1,{"height":1,"round":0,"step":"RoundStepCommit"}]}

consensus/ticker.go

@@ -3,7 +3,8 @@ package consensus
 import (
 	"time"
 
-	. "github.com/tendermint/go-common"
+	cmn "github.com/tendermint/tmlibs/common"
+	"github.com/tendermint/tmlibs/log"
 )
 
 var (
@@ -14,10 +15,12 @@ var (
 // conditional on the height/round/step in the timeoutInfo.
 // The timeoutInfo.Duration may be non-positive.
 type TimeoutTicker interface {
-	Start() (bool, error)
-	Stop() bool
+	Start() error
+	Stop() error
 	Chan() <-chan timeoutInfo       // on which to receive a timeout
 	ScheduleTimeout(ti timeoutInfo) // reset the timer
+
+	SetLogger(log.Logger)
 }
 
 // timeoutTicker wraps time.Timer,
@@ -26,24 +29,26 @@ type TimeoutTicker interface {
 // Timeouts are scheduled along the tickChan,
 // and fired on the tockChan.
 type timeoutTicker struct {
-	BaseService
+	cmn.BaseService
 
 	timer    *time.Timer
-	tickChan chan timeoutInfo
-	tockChan chan timeoutInfo
+	tickChan chan timeoutInfo // for scheduling timeouts
+	tockChan chan timeoutInfo // for notifying about them
 }
 
+// NewTimeoutTicker returns a new TimeoutTicker.
 func NewTimeoutTicker() TimeoutTicker {
 	tt := &timeoutTicker{
 		timer:    time.NewTimer(0),
 		tickChan: make(chan timeoutInfo, tickTockBufferSize),
 		tockChan: make(chan timeoutInfo, tickTockBufferSize),
 	}
+	tt.BaseService = *cmn.NewBaseService(nil, "TimeoutTicker", tt)
 	tt.stopTimer() // don't want to fire until the first scheduled timeout
-	tt.BaseService = *NewBaseService(log, "TimeoutTicker", tt)
 	return tt
 }
 
+// OnStart implements cmn.Service. It starts the timeout routine.
 func (t *timeoutTicker) OnStart() error {
 
 	go t.timeoutRoutine()
@@ -51,16 +56,19 @@ func (t *timeoutTicker) OnStart() error {
 	return nil
 }
 
+// OnStop implements cmn.Service. It stops the timeout routine.
 func (t *timeoutTicker) OnStop() {
 	t.BaseService.OnStop()
 	t.stopTimer()
 }
 
+// Chan returns a channel on which timeouts are sent.
 func (t *timeoutTicker) Chan() <-chan timeoutInfo {
 	return t.tockChan
 }
 
-// The timeoutRoutine is alwaya available to read from tickChan (it won't block).
+// ScheduleTimeout schedules a new timeout by sending on the internal tickChan.
+// The timeoutRoutine is always available to read from tickChan, so this won't block.
 // The scheduling may fail if the timeoutRoutine has already scheduled a timeout for a later height/round/step.
 func (t *timeoutTicker) ScheduleTimeout(ti timeoutInfo) {
 	t.tickChan <- ti
@@ -75,7 +83,7 @@ func (t *timeoutTicker) stopTimer() {
 		select {
 		case <-t.timer.C:
 		default:
-			log.Debug("Timer already stopped")
+			t.Logger.Debug("Timer already stopped")
 		}
 	}
 }
@@ -84,12 +92,12 @@ func (t *timeoutTicker) stopTimer() {
 // timers are interupted and replaced by new ticks from later steps
 // timeouts of 0 on the tickChan will be immediately relayed to the tockChan
 func (t *timeoutTicker) timeoutRoutine() {
-	log.Debug("Starting timeout routine")
+	t.Logger.Debug("Starting timeout routine")
 	var ti timeoutInfo
 	for {
 		select {
 		case newti := <-t.tickChan:
-			log.Debug("Received tick", "old_ti", ti, "new_ti", newti)
+			t.Logger.Debug("Received tick", "old_ti", ti, "new_ti", newti)
 
 			// ignore tickers for old height/round/step
 			if newti.Height < ti.Height {
@@ -111,15 +119,15 @@ func (t *timeoutTicker) timeoutRoutine() {
 			// NOTE time.Timer allows duration to be non-positive
 			ti = newti
 			t.timer.Reset(ti.Duration)
-			log.Debug("Scheduled timeout", "dur", ti.Duration, "height", ti.Height, "round", ti.Round, "step", ti.Step)
+			t.Logger.Debug("Scheduled timeout", "dur", ti.Duration, "height", ti.Height, "round", ti.Round, "step", ti.Step)
 		case <-t.timer.C:
-			log.Info("Timed out", "dur", ti.Duration, "height", ti.Height, "round", ti.Round, "step", ti.Step)
-			// go routine here gaurantees timeoutRoutine doesn't block.
+			t.Logger.Info("Timed out", "dur", ti.Duration, "height", ti.Height, "round", ti.Round, "step", ti.Step)
+			// go routine here guarantees timeoutRoutine doesn't block.
 			// Determinism comes from playback in the receiveRoutine.
 			// We can eliminate it by merging the timeoutRoutine into receiveRoutine
 			//  and managing the timeouts ourselves with a millisecond ticker
 			go func(toi timeoutInfo) { t.tockChan <- toi }(ti)
-		case <-t.Quit:
+		case <-t.Quit():
 			return
 		}
 	}

consensus/types/height_vote_set.go

@@ -1,11 +1,14 @@
-package consensus
+package types
 
 import (
+	"errors"
+	"fmt"
 	"strings"
 	"sync"
 
-	. "github.com/tendermint/go-common"
+	"github.com/tendermint/tendermint/p2p"
 	"github.com/tendermint/tendermint/types"
+	cmn "github.com/tendermint/tmlibs/common"
 )
 
 type RoundVoteSet struct {
@@ -13,6 +16,10 @@ type RoundVoteSet struct {
 	Precommits *types.VoteSet
 }
 
+var (
+	GotVoteFromUnwantedRoundError = errors.New("Peer has sent a vote that does not match our round for more than one round")
+)
+
 /*
 Keeps track of all VoteSets from round 0 to round 'round'.
 
@@ -29,16 +36,16 @@ One for their LastCommit round, and another for the official commit round.
 */
 type HeightVoteSet struct {
 	chainID string
-	height  int
+	height  int64
 	valSet  *types.ValidatorSet
 
 	mtx               sync.Mutex
 	round             int                  // max tracked round
 	roundVoteSets     map[int]RoundVoteSet // keys: [0...round]
-	peerCatchupRounds map[string][]int     // keys: peer.Key; values: at most 2 rounds
+	peerCatchupRounds map[p2p.ID][]int     // keys: peer.ID; values: at most 2 rounds
 }
 
-func NewHeightVoteSet(chainID string, height int, valSet *types.ValidatorSet) *HeightVoteSet {
+func NewHeightVoteSet(chainID string, height int64, valSet *types.ValidatorSet) *HeightVoteSet {
 	hvs := &HeightVoteSet{
 		chainID: chainID,
 	}
@@ -46,20 +53,20 @@ func NewHeightVoteSet(chainID string, height int, valSet *types.ValidatorSet) *H
 	return hvs
 }
 
-func (hvs *HeightVoteSet) Reset(height int, valSet *types.ValidatorSet) {
+func (hvs *HeightVoteSet) Reset(height int64, valSet *types.ValidatorSet) {
 	hvs.mtx.Lock()
 	defer hvs.mtx.Unlock()
 
 	hvs.height = height
 	hvs.valSet = valSet
 	hvs.roundVoteSets = make(map[int]RoundVoteSet)
-	hvs.peerCatchupRounds = make(map[string][]int)
+	hvs.peerCatchupRounds = make(map[p2p.ID][]int)
 
 	hvs.addRound(0)
 	hvs.round = 0
 }
 
-func (hvs *HeightVoteSet) Height() int {
+func (hvs *HeightVoteSet) Height() int64 {
 	hvs.mtx.Lock()
 	defer hvs.mtx.Unlock()
 	return hvs.height
@@ -76,7 +83,7 @@ func (hvs *HeightVoteSet) SetRound(round int) {
 	hvs.mtx.Lock()
 	defer hvs.mtx.Unlock()
 	if hvs.round != 0 && (round < hvs.round+1) {
-		PanicSanity("SetRound() must increment hvs.round")
+		cmn.PanicSanity("SetRound() must increment hvs.round")
 	}
 	for r := hvs.round + 1; r <= round; r++ {
 		if _, ok := hvs.roundVoteSets[r]; ok {
@@ -89,9 +96,9 @@ func (hvs *HeightVoteSet) SetRound(round int) {
 
 func (hvs *HeightVoteSet) addRound(round int) {
 	if _, ok := hvs.roundVoteSets[round]; ok {
-		PanicSanity("addRound() for an existing round")
+		cmn.PanicSanity("addRound() for an existing round")
 	}
-	log.Debug("addRound(round)", "round", round)
+	// log.Debug("addRound(round)", "round", round)
 	prevotes := types.NewVoteSet(hvs.chainID, hvs.height, round, types.VoteTypePrevote, hvs.valSet)
 	precommits := types.NewVoteSet(hvs.chainID, hvs.height, round, types.VoteTypePrecommit, hvs.valSet)
 	hvs.roundVoteSets[round] = RoundVoteSet{
@@ -101,8 +108,8 @@ func (hvs *HeightVoteSet) addRound(round int) {
 }
 
 // Duplicate votes return added=false, err=nil.
-// By convention, peerKey is "" if origin is self.
-func (hvs *HeightVoteSet) AddVote(vote *types.Vote, peerKey string) (added bool, err error) {
+// By convention, peerID is "" if origin is self.
+func (hvs *HeightVoteSet) AddVote(vote *types.Vote, peerID p2p.ID) (added bool, err error) {
 	hvs.mtx.Lock()
 	defer hvs.mtx.Unlock()
 	if !types.IsVoteTypeValid(vote.Type) {
@@ -110,15 +117,13 @@ func (hvs *HeightVoteSet) AddVote(vote *types.Vote, peerKey string) (added bool,
 	}
 	voteSet := hvs.getVoteSet(vote.Round, vote.Type)
 	if voteSet == nil {
-		if rndz := hvs.peerCatchupRounds[peerKey]; len(rndz) < 2 {
+		if rndz := hvs.peerCatchupRounds[peerID]; len(rndz) < 2 {
 			hvs.addRound(vote.Round)
 			voteSet = hvs.getVoteSet(vote.Round, vote.Type)
-			hvs.peerCatchupRounds[peerKey] = append(rndz, vote.Round)
+			hvs.peerCatchupRounds[peerID] = append(rndz, vote.Round)
 		} else {
-			// Peer has sent a vote that does not match our round,
-			// for more than one round.  Bad peer!
-			// TODO punish peer.
-			log.Warn("Deal with peer giving votes from unwanted rounds")
+			// punish peer
+			err = GotVoteFromUnwantedRoundError
 			return
 		}
 	}
@@ -164,7 +169,7 @@ func (hvs *HeightVoteSet) getVoteSet(round int, type_ byte) *types.VoteSet {
 	case types.VoteTypePrecommit:
 		return rvs.Precommits
 	default:
-		PanicSanity(Fmt("Unexpected vote type %X", type_))
+		cmn.PanicSanity(cmn.Fmt("Unexpected vote type %X", type_))
 		return nil
 	}
 }
@@ -194,7 +199,7 @@ func (hvs *HeightVoteSet) StringIndented(indent string) string {
 		voteSetString = roundVoteSet.Precommits.StringShort()
 		vsStrings = append(vsStrings, voteSetString)
 	}
-	return Fmt(`HeightVoteSet{H:%v R:0~%v
+	return cmn.Fmt(`HeightVoteSet{H:%v R:0~%v
 %s  %v
 %s}`,
 		hvs.height, hvs.round,
@@ -206,15 +211,15 @@ func (hvs *HeightVoteSet) StringIndented(indent string) string {
 // NOTE: if there are too many peers, or too much peer churn,
 // this can cause memory issues.
 // TODO: implement ability to remove peers too
-func (hvs *HeightVoteSet) SetPeerMaj23(round int, type_ byte, peerID string, blockID types.BlockID) {
+func (hvs *HeightVoteSet) SetPeerMaj23(round int, type_ byte, peerID p2p.ID, blockID types.BlockID) error {
 	hvs.mtx.Lock()
 	defer hvs.mtx.Unlock()
 	if !types.IsVoteTypeValid(type_) {
-		return
+		return fmt.Errorf("SetPeerMaj23: Invalid vote type %v", type_)
 	}
 	voteSet := hvs.getVoteSet(round, type_)
 	if voteSet == nil {
-		return
+		return nil // something we don't know about yet
 	}
-	voteSet.SetPeerMaj23(peerID, blockID)
+	return voteSet.SetPeerMaj23(types.P2PID(peerID), blockID)
 }

consensus/types/height_vote_set_test.go

@@ -1,21 +1,24 @@
-package consensus
+package types
 
 import (
 	"testing"
+	"time"
 
-	. "github.com/tendermint/go-common"
-	"github.com/tendermint/tendermint/config/tendermint_test"
+	cfg "github.com/tendermint/tendermint/config"
 	"github.com/tendermint/tendermint/types"
+	cmn "github.com/tendermint/tmlibs/common"
 )
 
+var config *cfg.Config // NOTE: must be reset for each _test.go file
+
 func init() {
-	config = tendermint_test.ResetConfig("consensus_height_vote_set_test")
+	config = cfg.ResetTestRoot("consensus_height_vote_set_test")
 }
 
 func TestPeerCatchupRounds(t *testing.T) {
 	valSet, privVals := types.RandValidatorSet(10, 1)
 
-	hvs := NewHeightVoteSet(config.GetString("chain_id"), 1, valSet)
+	hvs := NewHeightVoteSet(config.ChainID(), 1, valSet)
 
 	vote999_0 := makeVoteHR(t, 1, 999, privVals, 0)
 	added, err := hvs.AddVote(vote999_0, "peer1")
@@ -31,6 +34,9 @@ func TestPeerCatchupRounds(t *testing.T) {
 
 	vote1001_0 := makeVoteHR(t, 1, 1001, privVals, 0)
 	added, err = hvs.AddVote(vote1001_0, "peer1")
+	if err != GotVoteFromUnwantedRoundError {
+		t.Errorf("Expected GotVoteFromUnwantedRoundError, but got %v", err)
+	}
 	if added {
 		t.Error("Expected to *not* add vote from peer, too many catchup rounds.")
 	}
@@ -42,20 +48,21 @@ func TestPeerCatchupRounds(t *testing.T) {
 
 }
 
-func makeVoteHR(t *testing.T, height, round int, privVals []*types.PrivValidator, valIndex int) *types.Vote {
+func makeVoteHR(t *testing.T, height int64, round int, privVals []types.PrivValidator, valIndex int) *types.Vote {
 	privVal := privVals[valIndex]
 	vote := &types.Vote{
-		ValidatorAddress: privVal.Address,
+		ValidatorAddress: privVal.GetAddress(),
 		ValidatorIndex:   valIndex,
 		Height:           height,
 		Round:            round,
+		Timestamp:        time.Now().UTC(),
 		Type:             types.VoteTypePrecommit,
 		BlockID:          types.BlockID{[]byte("fakehash"), types.PartSetHeader{}},
 	}
-	chainID := config.GetString("chain_id")
+	chainID := config.ChainID()
 	err := privVal.SignVote(chainID, vote)
 	if err != nil {
-		panic(Fmt("Error signing vote: %v", err))
+		panic(cmn.Fmt("Error signing vote: %v", err))
 		return nil
 	}
 	return vote

consensus/types/reactor.go

@@ -0,0 +1,57 @@
+package types
+
+import (
+	"fmt"
+	"time"
+
+	"github.com/tendermint/tendermint/types"
+	cmn "github.com/tendermint/tmlibs/common"
+)
+
+//-----------------------------------------------------------------------------
+
+// PeerRoundState contains the known state of a peer.
+// NOTE: Read-only when returned by PeerState.GetRoundState().
+type PeerRoundState struct {
+	Height                   int64               // Height peer is at
+	Round                    int                 // Round peer is at, -1 if unknown.
+	Step                     RoundStepType       // Step peer is at
+	StartTime                time.Time           // Estimated start of round 0 at this height
+	Proposal                 bool                // True if peer has proposal for this round
+	ProposalBlockPartsHeader types.PartSetHeader //
+	ProposalBlockParts       *cmn.BitArray       //
+	ProposalPOLRound         int                 // Proposal's POL round. -1 if none.
+	ProposalPOL              *cmn.BitArray       // nil until ProposalPOLMessage received.
+	Prevotes                 *cmn.BitArray       // All votes peer has for this round
+	Precommits               *cmn.BitArray       // All precommits peer has for this round
+	LastCommitRound          int                 // Round of commit for last height. -1 if none.
+	LastCommit               *cmn.BitArray       // All commit precommits of commit for last height.
+	CatchupCommitRound       int                 // Round that we have commit for. Not necessarily unique. -1 if none.
+	CatchupCommit            *cmn.BitArray       // All commit precommits peer has for this height & CatchupCommitRound
+}
+
+// String returns a string representation of the PeerRoundState
+func (prs PeerRoundState) String() string {
+	return prs.StringIndented("")
+}
+
+// StringIndented returns a string representation of the PeerRoundState
+func (prs PeerRoundState) StringIndented(indent string) string {
+	return fmt.Sprintf(`PeerRoundState{
+%s  %v/%v/%v @%v
+%s  Proposal %v -> %v
+%s  POL      %v (round %v)
+%s  Prevotes   %v
+%s  Precommits %v
+%s  LastCommit %v (round %v)
+%s  Catchup    %v (round %v)
+%s}`,
+		indent, prs.Height, prs.Round, prs.Step, prs.StartTime,
+		indent, prs.ProposalBlockPartsHeader, prs.ProposalBlockParts,
+		indent, prs.ProposalPOL, prs.ProposalPOLRound,
+		indent, prs.Prevotes,
+		indent, prs.Precommits,
+		indent, prs.LastCommit, prs.LastCommitRound,
+		indent, prs.CatchupCommit, prs.CatchupCommitRound,
+		indent)
+}

consensus/types/state.go

@@ -0,0 +1,135 @@
+package types
+
+import (
+	"fmt"
+	"time"
+
+	"github.com/tendermint/tendermint/types"
+)
+
+//-----------------------------------------------------------------------------
+// RoundStepType enum type
+
+// RoundStepType enumerates the state of the consensus state machine
+type RoundStepType uint8 // These must be numeric, ordered.
+
+const (
+	RoundStepNewHeight     = RoundStepType(0x01) // Wait til CommitTime + timeoutCommit
+	RoundStepNewRound      = RoundStepType(0x02) // Setup new round and go to RoundStepPropose
+	RoundStepPropose       = RoundStepType(0x03) // Did propose, gossip proposal
+	RoundStepPrevote       = RoundStepType(0x04) // Did prevote, gossip prevotes
+	RoundStepPrevoteWait   = RoundStepType(0x05) // Did receive any +2/3 prevotes, start timeout
+	RoundStepPrecommit     = RoundStepType(0x06) // Did precommit, gossip precommits
+	RoundStepPrecommitWait = RoundStepType(0x07) // Did receive any +2/3 precommits, start timeout
+	RoundStepCommit        = RoundStepType(0x08) // Entered commit state machine
+	// NOTE: RoundStepNewHeight acts as RoundStepCommitWait.
+)
+
+// String returns a string
+func (rs RoundStepType) String() string {
+	switch rs {
+	case RoundStepNewHeight:
+		return "RoundStepNewHeight"
+	case RoundStepNewRound:
+		return "RoundStepNewRound"
+	case RoundStepPropose:
+		return "RoundStepPropose"
+	case RoundStepPrevote:
+		return "RoundStepPrevote"
+	case RoundStepPrevoteWait:
+		return "RoundStepPrevoteWait"
+	case RoundStepPrecommit:
+		return "RoundStepPrecommit"
+	case RoundStepPrecommitWait:
+		return "RoundStepPrecommitWait"
+	case RoundStepCommit:
+		return "RoundStepCommit"
+	default:
+		return "RoundStepUnknown" // Cannot panic.
+	}
+}
+
+//-----------------------------------------------------------------------------
+
+// RoundState defines the internal consensus state.
+// NOTE: Not thread safe. Should only be manipulated by functions downstream
+// of the cs.receiveRoutine
+type RoundState struct {
+	Height             int64 // Height we are working on
+	Round              int
+	Step               RoundStepType
+	StartTime          time.Time
+	CommitTime         time.Time // Subjective time when +2/3 precommits for Block at Round were found
+	Validators         *types.ValidatorSet
+	Proposal           *types.Proposal
+	ProposalBlock      *types.Block
+	ProposalBlockParts *types.PartSet
+	LockedRound        int
+	LockedBlock        *types.Block
+	LockedBlockParts   *types.PartSet
+	ValidRound         int
+	ValidBlock         *types.Block
+	ValidBlockParts    *types.PartSet
+	Votes              *HeightVoteSet
+	CommitRound        int            //
+	LastCommit         *types.VoteSet // Last precommits at Height-1
+	LastValidators     *types.ValidatorSet
+}
+
+// RoundStateEvent returns the H/R/S of the RoundState as an event.
+func (rs *RoundState) RoundStateEvent() types.EventDataRoundState {
+	// XXX: copy the RoundState
+	// if we want to avoid this, we may need synchronous events after all
+	rs_ := *rs
+	edrs := types.EventDataRoundState{
+		Height:     rs.Height,
+		Round:      rs.Round,
+		Step:       rs.Step.String(),
+		RoundState: &rs_,
+	}
+	return edrs
+}
+
+// String returns a string
+func (rs *RoundState) String() string {
+	return rs.StringIndented("")
+}
+
+// StringIndented returns a string
+func (rs *RoundState) StringIndented(indent string) string {
+	return fmt.Sprintf(`RoundState{
+%s  H:%v R:%v S:%v
+%s  StartTime:     %v
+%s  CommitTime:    %v
+%s  Validators:    %v
+%s  Proposal:      %v
+%s  ProposalBlock: %v %v
+%s  LockedRound:   %v
+%s  LockedBlock:   %v %v
+%s  ValidRound:   %v
+%s  ValidBlock:   %v %v
+%s  Votes:         %v
+%s  LastCommit:    %v
+%s  LastValidators:%v
+%s}`,
+		indent, rs.Height, rs.Round, rs.Step,
+		indent, rs.StartTime,
+		indent, rs.CommitTime,
+		indent, rs.Validators.StringIndented(indent+"    "),
+		indent, rs.Proposal,
+		indent, rs.ProposalBlockParts.StringShort(), rs.ProposalBlock.StringShort(),
+		indent, rs.LockedRound,
+		indent, rs.LockedBlockParts.StringShort(), rs.LockedBlock.StringShort(),
+		indent, rs.ValidRound,
+		indent, rs.ValidBlockParts.StringShort(), rs.ValidBlock.StringShort(),
+		indent, rs.Votes.StringIndented(indent+"    "),
+		indent, rs.LastCommit.StringShort(),
+		indent, rs.LastValidators.StringIndented(indent+"    "),
+		indent)
+}
+
+// StringShort returns a string
+func (rs *RoundState) StringShort() string {
+	return fmt.Sprintf(`RoundState{H:%v R:%v S:%v ST:%v}`,
+		rs.Height, rs.Round, rs.Step, rs.StartTime)
+}

consensus/version.go

@@ -1,7 +1,7 @@
 package consensus
 
 import (
-	. "github.com/tendermint/go-common"
+	cmn "github.com/tendermint/tmlibs/common"
 )
 
 // kind of arbitrary
@@ -10,4 +10,4 @@ var Major = "0"    //
 var Minor = "2"    // replay refactor
 var Revision = "2" // validation -> commit
 
-var Version = Fmt("v%s/%s.%s.%s", Spec, Major, Minor, Revision)
+var Version = cmn.Fmt("v%s/%s.%s.%s", Spec, Major, Minor, Revision)

consensus/wal.go

@@ -1,105 +1,318 @@
 package consensus
 
 import (
+	"encoding/binary"
+	"fmt"
+	"hash/crc32"
+	"io"
+	"path/filepath"
 	"time"
 
-	auto "github.com/tendermint/go-autofile"
-	. "github.com/tendermint/go-common"
-	"github.com/tendermint/go-wire"
+	"github.com/pkg/errors"
+
+	amino "github.com/tendermint/go-amino"
 	"github.com/tendermint/tendermint/types"
+	auto "github.com/tendermint/tmlibs/autofile"
+	cmn "github.com/tendermint/tmlibs/common"
+)
+
+const (
+	// must be greater than params.BlockGossip.BlockPartSizeBytes + a few bytes
+	maxMsgSizeBytes = 1024 * 1024 // 1MB
 )
 
 //--------------------------------------------------------
 // types and functions for savings consensus messages
 
 type TimedWALMessage struct {
-	Time time.Time  `json:"time"`
+	Time time.Time  `json:"time"` // for debugging purposes
 	Msg  WALMessage `json:"msg"`
 }
 
+// EndHeightMessage marks the end of the given height inside WAL.
+// @internal used by scripts/wal2json util.
+type EndHeightMessage struct {
+	Height int64 `json:"height"`
+}
+
 type WALMessage interface{}
 
-var _ = wire.RegisterInterface(
-	struct{ WALMessage }{},
-	wire.ConcreteType{types.EventDataRoundState{}, 0x01},
-	wire.ConcreteType{msgInfo{}, 0x02},
-	wire.ConcreteType{timeoutInfo{}, 0x03},
-)
+func RegisterWALMessages(cdc *amino.Codec) {
+	cdc.RegisterInterface((*WALMessage)(nil), nil)
+	cdc.RegisterConcrete(types.EventDataRoundState{}, "tendermint/wal/EventDataRoundState", nil)
+	cdc.RegisterConcrete(msgInfo{}, "tendermint/wal/MsgInfo", nil)
+	cdc.RegisterConcrete(timeoutInfo{}, "tendermint/wal/TimeoutInfo", nil)
+	cdc.RegisterConcrete(EndHeightMessage{}, "tendermint/wal/EndHeightMessage", nil)
+}
 
 //--------------------------------------------------------
 // Simple write-ahead logger
 
+// WAL is an interface for any write-ahead logger.
+type WAL interface {
+	Save(WALMessage)
+	Group() *auto.Group
+	SearchForEndHeight(height int64, options *WALSearchOptions) (gr *auto.GroupReader, found bool, err error)
+
+	Start() error
+	Stop() error
+	Wait()
+}
+
 // Write ahead logger writes msgs to disk before they are processed.
 // Can be used for crash-recovery and deterministic replay
 // TODO: currently the wal is overwritten during replay catchup
 //   give it a mode so it's either reading or appending - must read to end to start appending again
-type WAL struct {
-	BaseService
+type baseWAL struct {
+	cmn.BaseService
 
 	group *auto.Group
 	light bool // ignore block parts
+
+	enc *WALEncoder
 }
 
-func NewWAL(walFile string, light bool) (*WAL, error) {
+func NewWAL(walFile string, light bool) (*baseWAL, error) {
+	err := cmn.EnsureDir(filepath.Dir(walFile), 0700)
+	if err != nil {
+		return nil, errors.Wrap(err, "failed to ensure WAL directory is in place")
+	}
+
 	group, err := auto.OpenGroup(walFile)
 	if err != nil {
 		return nil, err
 	}
-	wal := &WAL{
+	wal := &baseWAL{
 		group: group,
 		light: light,
+		enc:   NewWALEncoder(group),
 	}
-	wal.BaseService = *NewBaseService(log, "WAL", wal)
-	_, err = wal.Start()
-	return wal, err
+	wal.BaseService = *cmn.NewBaseService(nil, "baseWAL", wal)
+	return wal, nil
 }
 
-func (wal *WAL) OnStart() error {
+func (wal *baseWAL) Group() *auto.Group {
+	return wal.group
+}
+
+func (wal *baseWAL) OnStart() error {
 	size, err := wal.group.Head.Size()
 	if err != nil {
 		return err
 	} else if size == 0 {
-		wal.writeEndHeight(0)
+		wal.Save(EndHeightMessage{0})
 	}
-	_, err = wal.group.Start()
+	err = wal.group.Start()
 	return err
 }
 
-func (wal *WAL) OnStop() {
+func (wal *baseWAL) OnStop() {
 	wal.BaseService.OnStop()
 	wal.group.Stop()
 }
 
 // called in newStep and for each pass in receiveRoutine
-func (wal *WAL) Save(wmsg WALMessage) {
+func (wal *baseWAL) Save(msg WALMessage) {
 	if wal == nil {
 		return
 	}
+
 	if wal.light {
 		// in light mode we only write new steps, timeouts, and our own votes (no proposals, block parts)
-		if mi, ok := wmsg.(msgInfo); ok {
-			if mi.PeerKey != "" {
+		if mi, ok := msg.(msgInfo); ok {
+			if mi.PeerID != "" {
 				return
 			}
 		}
 	}
+
 	// Write the wal message
-	var wmsgBytes = wire.JSONBytes(TimedWALMessage{time.Now(), wmsg})
-	err := wal.group.WriteLine(string(wmsgBytes))
+	if err := wal.enc.Encode(&TimedWALMessage{time.Now(), msg}); err != nil {
+		cmn.PanicQ(cmn.Fmt("Error writing msg to consensus wal: %v \n\nMessage: %v", err, msg))
+	}
+
+	// TODO: only flush when necessary
+	if err := wal.group.Flush(); err != nil {
+		cmn.PanicQ(cmn.Fmt("Error flushing consensus wal buf to file. Error: %v \n", err))
+	}
+}
+
+// WALSearchOptions are optional arguments to SearchForEndHeight.
+type WALSearchOptions struct {
+	// IgnoreDataCorruptionErrors set to true will result in skipping data corruption errors.
+	IgnoreDataCorruptionErrors bool
+}
+
+// SearchForEndHeight searches for the EndHeightMessage with the height and
+// returns an auto.GroupReader, whenever it was found or not and an error.
+// Group reader will be nil if found equals false.
+//
+// CONTRACT: caller must close group reader.
+func (wal *baseWAL) SearchForEndHeight(height int64, options *WALSearchOptions) (gr *auto.GroupReader, found bool, err error) {
+	var msg *TimedWALMessage
+
+	// NOTE: starting from the last file in the group because we're usually
+	// searching for the last height. See replay.go
+	min, max := wal.group.MinIndex(), wal.group.MaxIndex()
+	wal.Logger.Debug("Searching for height", "height", height, "min", min, "max", max)
+	for index := max; index >= min; index-- {
+		gr, err = wal.group.NewReader(index)
+		if err != nil {
+			return nil, false, err
+		}
+
+		dec := NewWALDecoder(gr)
+		for {
+			msg, err = dec.Decode()
+			if err == io.EOF {
+				// check next file
+				break
+			}
+			if options.IgnoreDataCorruptionErrors && IsDataCorruptionError(err) {
+				// do nothing
+			} else if err != nil {
+				gr.Close()
+				return nil, false, err
+			}
+
+			if m, ok := msg.Msg.(EndHeightMessage); ok {
+				if m.Height == height { // found
+					wal.Logger.Debug("Found", "height", height, "index", index)
+					return gr, true, nil
+				}
+			}
+		}
+		gr.Close()
+	}
+
+	return nil, false, nil
+}
+
+///////////////////////////////////////////////////////////////////////////////
+
+// A WALEncoder writes custom-encoded WAL messages to an output stream.
+//
+// Format: 4 bytes CRC sum + 4 bytes length + arbitrary-length value (go-amino encoded)
+type WALEncoder struct {
+	wr io.Writer
+}
+
+// NewWALEncoder returns a new encoder that writes to wr.
+func NewWALEncoder(wr io.Writer) *WALEncoder {
+	return &WALEncoder{wr}
+}
+
+// Encode writes the custom encoding of v to the stream.
+func (enc *WALEncoder) Encode(v *TimedWALMessage) error {
+	data := cdc.MustMarshalBinaryBare(v)
+
+	crc := crc32.Checksum(data, crc32c)
+	length := uint32(len(data))
+	totalLength := 8 + int(length)
+
+	msg := make([]byte, totalLength)
+	binary.BigEndian.PutUint32(msg[0:4], crc)
+	binary.BigEndian.PutUint32(msg[4:8], length)
+	copy(msg[8:], data)
+
+	_, err := enc.wr.Write(msg)
+
+	return err
+}
+
+///////////////////////////////////////////////////////////////////////////////
+
+// IsDataCorruptionError returns true if data has been corrupted inside WAL.
+func IsDataCorruptionError(err error) bool {
+	_, ok := err.(DataCorruptionError)
+	return ok
+}
+
+// DataCorruptionError is an error that occures if data on disk was corrupted.
+type DataCorruptionError struct {
+	cause error
+}
+
+func (e DataCorruptionError) Error() string {
+	return fmt.Sprintf("DataCorruptionError[%v]", e.cause)
+}
+
+func (e DataCorruptionError) Cause() error {
+	return e.cause
+}
+
+// A WALDecoder reads and decodes custom-encoded WAL messages from an input
+// stream. See WALEncoder for the format used.
+//
+// It will also compare the checksums and make sure data size is equal to the
+// length from the header. If that is not the case, error will be returned.
+type WALDecoder struct {
+	rd io.Reader
+}
+
+// NewWALDecoder returns a new decoder that reads from rd.
+func NewWALDecoder(rd io.Reader) *WALDecoder {
+	return &WALDecoder{rd}
+}
+
+// Decode reads the next custom-encoded value from its reader and returns it.
+func (dec *WALDecoder) Decode() (*TimedWALMessage, error) {
+	b := make([]byte, 4)
+
+	_, err := dec.rd.Read(b)
+	if err == io.EOF {
+		return nil, err
+	}
 	if err != nil {
-		PanicQ(Fmt("Error writing msg to consensus wal. Error: %v \n\nMessage: %v", err, wmsg))
+		return nil, fmt.Errorf("failed to read checksum: %v", err)
 	}
-	// TODO: only flush when necessary
-	if err := wal.group.Flush(); err != nil {
-		PanicQ(Fmt("Error flushing consensus wal buf to file. Error: %v \n", err))
+	crc := binary.BigEndian.Uint32(b)
+
+	b = make([]byte, 4)
+	_, err = dec.rd.Read(b)
+	if err == io.EOF {
+		return nil, err
 	}
+	if err != nil {
+		return nil, fmt.Errorf("failed to read length: %v", err)
+	}
+	length := binary.BigEndian.Uint32(b)
+
+	if length > maxMsgSizeBytes {
+		return nil, DataCorruptionError{fmt.Errorf("length %d exceeded maximum possible value of %d bytes", length, maxMsgSizeBytes)}
+	}
+
+	data := make([]byte, length)
+	_, err = dec.rd.Read(data)
+	if err == io.EOF {
+		return nil, err
+	}
+	if err != nil {
+		return nil, fmt.Errorf("failed to read data: %v", err)
+	}
+
+	// check checksum before decoding data
+	actualCRC := crc32.Checksum(data, crc32c)
+	if actualCRC != crc {
+		return nil, DataCorruptionError{fmt.Errorf("checksums do not match: (read: %v, actual: %v)", crc, actualCRC)}
+	}
+
+	var res = new(TimedWALMessage) // nolint: gosimple
+	err = cdc.UnmarshalBinaryBare(data, res)
+	if err != nil {
+		return nil, DataCorruptionError{fmt.Errorf("failed to decode data: %v", err)}
+	}
+
+	return res, err
 }
 
-func (wal *WAL) writeEndHeight(height int) {
-	wal.group.WriteLine(Fmt("#ENDHEIGHT: %v", height))
+type nilWAL struct{}
 
-	// TODO: only flush when necessary
-	if err := wal.group.Flush(); err != nil {
-		PanicQ(Fmt("Error flushing consensus wal buf to file. Error: %v \n", err))
-	}
+func (nilWAL) Save(m WALMessage)  {}
+func (nilWAL) Group() *auto.Group { return nil }
+func (nilWAL) SearchForEndHeight(height int64, options *WALSearchOptions) (gr *auto.GroupReader, found bool, err error) {
+	return nil, false, nil
 }
+func (nilWAL) Start() error { return nil }
+func (nilWAL) Stop() error  { return nil }
+func (nilWAL) Wait()        {}

consensus/wal_fuzz.go

@@ -0,0 +1,31 @@
+// +build gofuzz
+
+package consensus
+
+import (
+	"bytes"
+	"io"
+)
+
+func Fuzz(data []byte) int {
+	dec := NewWALDecoder(bytes.NewReader(data))
+	for {
+		msg, err := dec.Decode()
+		if err == io.EOF {
+			break
+		}
+		if err != nil {
+			if msg != nil {
+				panic("msg != nil on error")
+			}
+			return 0
+		}
+		var w bytes.Buffer
+		enc := NewWALEncoder(&w)
+		err = enc.Encode(msg)
+		if err != nil {
+			panic(err)
+		}
+	}
+	return 1
+}

consensus/wal_generator.go

@@ -0,0 +1,201 @@
+package consensus
+
+import (
+	"bufio"
+	"bytes"
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+	"time"
+
+	"github.com/pkg/errors"
+	"github.com/tendermint/abci/example/kvstore"
+	bc "github.com/tendermint/tendermint/blockchain"
+	cfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tendermint/proxy"
+	sm "github.com/tendermint/tendermint/state"
+	"github.com/tendermint/tendermint/types"
+	pvm "github.com/tendermint/tendermint/types/priv_validator"
+	auto "github.com/tendermint/tmlibs/autofile"
+	cmn "github.com/tendermint/tmlibs/common"
+	"github.com/tendermint/tmlibs/db"
+	"github.com/tendermint/tmlibs/log"
+)
+
+// WALWithNBlocks generates a consensus WAL. It does this by spining up a
+// stripped down version of node (proxy app, event bus, consensus state) with a
+// persistent kvstore application and special consensus wal instance
+// (byteBufferWAL) and waits until numBlocks are created. Then it returns a WAL
+// content.
+func WALWithNBlocks(numBlocks int) (data []byte, err error) {
+	config := getConfig()
+
+	app := kvstore.NewPersistentKVStoreApplication(filepath.Join(config.DBDir(), "wal_generator"))
+
+	logger := log.TestingLogger().With("wal_generator", "wal_generator")
+	logger.Info("generating WAL (last height msg excluded)", "numBlocks", numBlocks)
+
+	/////////////////////////////////////////////////////////////////////////////
+	// COPY PASTE FROM node.go WITH A FEW MODIFICATIONS
+	// NOTE: we can't import node package because of circular dependency
+	privValidatorFile := config.PrivValidatorFile()
+	privValidator := pvm.LoadOrGenFilePV(privValidatorFile)
+	genDoc, err := types.GenesisDocFromFile(config.GenesisFile())
+	if err != nil {
+		return nil, errors.Wrap(err, "failed to read genesis file")
+	}
+	stateDB := db.NewMemDB()
+	blockStoreDB := db.NewMemDB()
+	state, err := sm.MakeGenesisState(genDoc)
+	if err != nil {
+		return nil, errors.Wrap(err, "failed to make genesis state")
+	}
+	blockStore := bc.NewBlockStore(blockStoreDB)
+	handshaker := NewHandshaker(stateDB, state, blockStore, genDoc.AppState())
+	proxyApp := proxy.NewAppConns(proxy.NewLocalClientCreator(app), handshaker)
+	proxyApp.SetLogger(logger.With("module", "proxy"))
+	if err := proxyApp.Start(); err != nil {
+		return nil, errors.Wrap(err, "failed to start proxy app connections")
+	}
+	defer proxyApp.Stop()
+	eventBus := types.NewEventBus()
+	eventBus.SetLogger(logger.With("module", "events"))
+	if err := eventBus.Start(); err != nil {
+		return nil, errors.Wrap(err, "failed to start event bus")
+	}
+	defer eventBus.Stop()
+	mempool := types.MockMempool{}
+	evpool := types.MockEvidencePool{}
+	blockExec := sm.NewBlockExecutor(stateDB, log.TestingLogger(), proxyApp.Consensus(), mempool, evpool)
+	consensusState := NewConsensusState(config.Consensus, state.Copy(), blockExec, blockStore, mempool, evpool)
+	consensusState.SetLogger(logger)
+	consensusState.SetEventBus(eventBus)
+	if privValidator != nil {
+		consensusState.SetPrivValidator(privValidator)
+	}
+	// END OF COPY PASTE
+	/////////////////////////////////////////////////////////////////////////////
+
+	// set consensus wal to buffered WAL, which will write all incoming msgs to buffer
+	var b bytes.Buffer
+	wr := bufio.NewWriter(&b)
+	numBlocksWritten := make(chan struct{})
+	wal := newByteBufferWAL(logger, NewWALEncoder(wr), int64(numBlocks), numBlocksWritten)
+	// see wal.go#103
+	wal.Save(EndHeightMessage{0})
+	consensusState.wal = wal
+
+	if err := consensusState.Start(); err != nil {
+		return nil, errors.Wrap(err, "failed to start consensus state")
+	}
+	defer consensusState.Stop()
+
+	select {
+	case <-numBlocksWritten:
+		wr.Flush()
+		return b.Bytes(), nil
+	case <-time.After(1 * time.Minute):
+		wr.Flush()
+		return b.Bytes(), fmt.Errorf("waited too long for tendermint to produce %d blocks (grep logs for `wal_generator`)", numBlocks)
+	}
+}
+
+// f**ing long, but unique for each test
+func makePathname() string {
+	// get path
+	p, err := os.Getwd()
+	if err != nil {
+		panic(err)
+	}
+	// fmt.Println(p)
+	sep := string(filepath.Separator)
+	return strings.Replace(p, sep, "_", -1)
+}
+
+func randPort() int {
+	// returns between base and base + spread
+	base, spread := 20000, 20000
+	return base + cmn.RandIntn(spread)
+}
+
+func makeAddrs() (string, string, string) {
+	start := randPort()
+	return fmt.Sprintf("tcp://0.0.0.0:%d", start),
+		fmt.Sprintf("tcp://0.0.0.0:%d", start+1),
+		fmt.Sprintf("tcp://0.0.0.0:%d", start+2)
+}
+
+// getConfig returns a config for test cases
+func getConfig() *cfg.Config {
+	pathname := makePathname()
+	c := cfg.ResetTestRoot(fmt.Sprintf("%s_%d", pathname, cmn.RandInt()))
+
+	// and we use random ports to run in parallel
+	tm, rpc, grpc := makeAddrs()
+	c.P2P.ListenAddress = tm
+	c.RPC.ListenAddress = rpc
+	c.RPC.GRPCListenAddress = grpc
+	return c
+}
+
+// byteBufferWAL is a WAL which writes all msgs to a byte buffer. Writing stops
+// when the heightToStop is reached. Client will be notified via
+// signalWhenStopsTo channel.
+type byteBufferWAL struct {
+	enc               *WALEncoder
+	stopped           bool
+	heightToStop      int64
+	signalWhenStopsTo chan<- struct{}
+
+	logger log.Logger
+}
+
+// needed for determinism
+var fixedTime, _ = time.Parse(time.RFC3339, "2017-01-02T15:04:05Z")
+
+func newByteBufferWAL(logger log.Logger, enc *WALEncoder, nBlocks int64, signalStop chan<- struct{}) *byteBufferWAL {
+	return &byteBufferWAL{
+		enc:               enc,
+		heightToStop:      nBlocks,
+		signalWhenStopsTo: signalStop,
+		logger:            logger,
+	}
+}
+
+// Save writes message to the internal buffer except when heightToStop is
+// reached, in which case it will signal the caller via signalWhenStopsTo and
+// skip writing.
+func (w *byteBufferWAL) Save(m WALMessage) {
+	if w.stopped {
+		w.logger.Debug("WAL already stopped. Not writing message", "msg", m)
+		return
+	}
+
+	if endMsg, ok := m.(EndHeightMessage); ok {
+		w.logger.Debug("WAL write end height message", "height", endMsg.Height, "stopHeight", w.heightToStop)
+		if endMsg.Height == w.heightToStop {
+			w.logger.Debug("Stopping WAL at height", "height", endMsg.Height)
+			w.signalWhenStopsTo <- struct{}{}
+			w.stopped = true
+			return
+		}
+	}
+
+	w.logger.Debug("WAL Write Message", "msg", m)
+	err := w.enc.Encode(&TimedWALMessage{fixedTime, m})
+	if err != nil {
+		panic(fmt.Sprintf("failed to encode the msg %v", m))
+	}
+}
+
+func (w *byteBufferWAL) Group() *auto.Group {
+	panic("not implemented")
+}
+func (w *byteBufferWAL) SearchForEndHeight(height int64, options *WALSearchOptions) (gr *auto.GroupReader, found bool, err error) {
+	return nil, false, nil
+}
+
+func (w *byteBufferWAL) Start() error { return nil }
+func (w *byteBufferWAL) Stop() error  { return nil }
+func (w *byteBufferWAL) Wait()        {}

consensus/wal_test.go

@@ -0,0 +1,133 @@
+package consensus
+
+import (
+	"bytes"
+	"crypto/rand"
+	// "sync"
+	"testing"
+	"time"
+
+	"github.com/tendermint/tendermint/consensus/types"
+	tmtypes "github.com/tendermint/tendermint/types"
+	cmn "github.com/tendermint/tmlibs/common"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestWALEncoderDecoder(t *testing.T) {
+	now := time.Now()
+	msgs := []TimedWALMessage{
+		TimedWALMessage{Time: now, Msg: EndHeightMessage{0}},
+		TimedWALMessage{Time: now, Msg: timeoutInfo{Duration: time.Second, Height: 1, Round: 1, Step: types.RoundStepPropose}},
+	}
+
+	b := new(bytes.Buffer)
+
+	for _, msg := range msgs {
+		b.Reset()
+
+		enc := NewWALEncoder(b)
+		err := enc.Encode(&msg)
+		require.NoError(t, err)
+
+		dec := NewWALDecoder(b)
+		decoded, err := dec.Decode()
+		require.NoError(t, err)
+
+		assert.Equal(t, msg.Time.UTC(), decoded.Time)
+		assert.Equal(t, msg.Msg, decoded.Msg)
+	}
+}
+
+func TestWALSearchForEndHeight(t *testing.T) {
+	walBody, err := WALWithNBlocks(6)
+	if err != nil {
+		t.Fatal(err)
+	}
+	walFile := tempWALWithData(walBody)
+
+	wal, err := NewWAL(walFile, false)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	h := int64(3)
+	gr, found, err := wal.SearchForEndHeight(h, &WALSearchOptions{})
+	assert.NoError(t, err, cmn.Fmt("expected not to err on height %d", h))
+	assert.True(t, found, cmn.Fmt("expected to find end height for %d", h))
+	assert.NotNil(t, gr, "expected group not to be nil")
+	defer gr.Close()
+
+	dec := NewWALDecoder(gr)
+	msg, err := dec.Decode()
+	assert.NoError(t, err, "expected to decode a message")
+	rs, ok := msg.Msg.(tmtypes.EventDataRoundState)
+	assert.True(t, ok, "expected message of type EventDataRoundState")
+	assert.Equal(t, rs.Height, h+1, cmn.Fmt("wrong height"))
+}
+
+/*
+var initOnce sync.Once
+
+func registerInterfacesOnce() {
+	initOnce.Do(func() {
+		var _ = wire.RegisterInterface(
+			struct{ WALMessage }{},
+			wire.ConcreteType{[]byte{}, 0x10},
+		)
+	})
+}
+*/
+
+func nBytes(n int) []byte {
+	buf := make([]byte, n)
+	n, _ = rand.Read(buf)
+	return buf[:n]
+}
+
+func benchmarkWalDecode(b *testing.B, n int) {
+	// registerInterfacesOnce()
+
+	buf := new(bytes.Buffer)
+	enc := NewWALEncoder(buf)
+
+	data := nBytes(n)
+	enc.Encode(&TimedWALMessage{Msg: data, Time: time.Now().Round(time.Second)})
+
+	encoded := buf.Bytes()
+
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		buf.Reset()
+		buf.Write(encoded)
+		dec := NewWALDecoder(buf)
+		if _, err := dec.Decode(); err != nil {
+			b.Fatal(err)
+		}
+	}
+	b.ReportAllocs()
+}
+
+func BenchmarkWalDecode512B(b *testing.B) {
+	benchmarkWalDecode(b, 512)
+}
+
+func BenchmarkWalDecode10KB(b *testing.B) {
+	benchmarkWalDecode(b, 10*1024)
+}
+func BenchmarkWalDecode100KB(b *testing.B) {
+	benchmarkWalDecode(b, 100*1024)
+}
+func BenchmarkWalDecode1MB(b *testing.B) {
+	benchmarkWalDecode(b, 1024*1024)
+}
+func BenchmarkWalDecode10MB(b *testing.B) {
+	benchmarkWalDecode(b, 10*1024*1024)
+}
+func BenchmarkWalDecode100MB(b *testing.B) {
+	benchmarkWalDecode(b, 100*1024*1024)
+}
+func BenchmarkWalDecode1GB(b *testing.B) {
+	benchmarkWalDecode(b, 1024*1024*1024)
+}

consensus/wire.go

@@ -0,0 +1,14 @@
+package consensus
+
+import (
+	amino "github.com/tendermint/go-amino"
+	"github.com/tendermint/go-crypto"
+)
+
+var cdc = amino.NewCodec()
+
+func init() {
+	RegisterConsensusMessages(cdc)
+	RegisterWALMessages(cdc)
+	crypto.RegisterAmino(cdc)
+}

docker-compose.yml

@@ -0,0 +1,68 @@
+version: '3'
+
+services:
+  node0:
+    container_name: node0
+    image: "tendermint/localnode"
+    ports:
+      - "46656-46657:46656-46657"
+    environment:
+      - ID=0
+      - LOG=${LOG:-tendermint.log}
+    volumes:
+      - ${FOLDER:-./build}:/tendermint:Z
+    networks:
+      localnet:
+        ipv4_address: 192.167.10.2
+
+  node1:
+    container_name: node1
+    image: "tendermint/localnode"
+    ports:
+      - "46659-46660:46656-46657"
+    environment:
+      - ID=1
+      - LOG=${LOG:-tendermint.log}
+    volumes:
+      - ${FOLDER:-./build}:/tendermint:Z
+    networks:
+      localnet:
+        ipv4_address: 192.167.10.3
+
+  node2:
+    container_name: node2
+    image: "tendermint/localnode"
+    environment:
+      - ID=2
+      - LOG=${LOG:-tendermint.log}
+    ports:
+      - "46661-46662:46656-46657"
+    volumes:
+      - ${FOLDER:-./build}:/tendermint:Z
+    networks:
+      localnet:
+        ipv4_address: 192.167.10.4
+
+  node3:
+    container_name: node3
+    image: "tendermint/localnode"
+    environment:
+      - ID=3
+      - LOG=${LOG:-tendermint.log}
+    ports:
+      - "46663-46664:46656-46657"
+    volumes:
+      - ${FOLDER:-./build}:/tendermint:Z
+    networks:
+      localnet:
+        ipv4_address: 192.167.10.5
+
+networks:
+  localnet:
+    driver: bridge
+    ipam:
+      driver: default
+      config:
+      -
+        subnet: 192.167.10.0/16
+

docker-compose/Makefile

@@ -0,0 +1,7 @@
+# Makefile for the "localnode" docker image.
+
+all:
+	docker build --tag tendermint/localnode localnode
+
+.PHONY: all
+

docker-compose/README.rst

@@ -0,0 +1,40 @@
+localnode
+=========
+
+It is assumed that you have already `setup docker <https://docs.docker.com/engine/installation/>`__.
+
+Description
+-----------
+Image for local testnets.
+
+Add the tendermint binary to the image by attaching it in a folder to the `/tendermint` mount point.
+
+It assumes that the configuration was created by the `tendermint testnet` command and it is also attached to the `/tendermint` mount point.
+
+Example:
+This example builds a linux tendermint binary under the `build/` folder, creates tendermint configuration for a single-node validator and runs the node:
+```
+cd $GOPATH/src/github.com/tendermint/tendermint
+
+#Build binary
+make build-linux
+
+#Create configuration
+docker run -e LOG="stdout" -v `pwd`/build:/tendermint tendermint/localnode testnet --o . --v 1
+
+#Run the node
+docker run -v `pwd`/build:/tendermint tendermint/localnode
+```
+
+Logging
+-------
+Log is saved under the attached volume, in the `tendermint.log` file. If the `LOG` environment variable is set to `stdout` at start, the log is not saved, but printed on the screen.
+
+Special binaries
+----------------
+If you have multiple binaries with different names, you can specify which one to run with the BINARY environment variable. The path of the binary is relative to the attached volume.
+
+docker-compose.yml
+==================
+This file creates a 4-node network using the localnode image. The nodes of the network are exposed to the host machine on ports 46656-46657, 46659-46660, 46661-46662, 46663-46664 respectively.
+