Merge pull request #1779 from tendermint/release/v0.21.0

Release/v0.21.0

.circleci/config.yml

@@ -0,0 +1,220 @@
+version: 2
+
+defaults: &defaults
+  working_directory: /go/src/github.com/tendermint/tendermint
+  docker:
+    - image: circleci/golang:1.10.3
+  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:
+            - v2-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: v2-pkg-cache
+          paths:
+            - /go/pkg
+      - save_cache:
+          key: v2-tree-{{ .Environment.CIRCLE_SHA1 }}
+          paths:
+            - /go/src/github.com/tendermint/tendermint
+
+  setup_abci:
+    <<: *defaults
+    steps:
+      - attach_workspace:
+          at: /tmp/workspace
+      - restore_cache:
+          key: v2-pkg-cache
+      - restore_cache:
+          key: v2-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*"
+
+  build_slate:
+    <<: *defaults
+    steps:
+      - attach_workspace:
+          at: /tmp/workspace
+      - restore_cache:
+          key: v2-pkg-cache
+      - restore_cache:
+          key: v2-tree-{{ .Environment.CIRCLE_SHA1 }}
+      - run:
+          name: slate docs
+          command: |
+            set -ex
+            export PATH="$GOBIN:$PATH"
+            make build-slate
+
+  lint:
+    <<: *defaults
+    steps:
+      - attach_workspace:
+          at: /tmp/workspace
+      - restore_cache:
+          key: v2-pkg-cache
+      - restore_cache:
+          key: v2-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: v2-pkg-cache
+      - restore_cache:
+          key: v2-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: v2-pkg-cache
+      - restore_cache:
+          key: v2-tree-{{ .Environment.CIRCLE_SHA1 }}
+      - run: mkdir -p /tmp/logs
+      - 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 "$pkg")
+
+              GOCACHE=off go test -v -timeout 5m -race -coverprofile=/tmp/workspace/profiles/$id.out -covermode=atomic "$pkg" | tee "/tmp/logs/$id-$RANDOM.log"
+            done
+      - persist_to_workspace:
+          root: /tmp/workspace
+          paths:
+            - "profiles/*"
+      - store_artifacts:
+          path: /tmp/logs
+
+  test_persistence:
+    <<: *defaults
+    steps:
+      - attach_workspace:
+          at: /tmp/workspace
+      - restore_cache:
+          key: v2-pkg-cache
+      - restore_cache:
+          key: v2-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/p2p/circleci.sh
+
+  upload_coverage:
+    <<: *defaults
+    steps:
+      - attach_workspace:
+          at: /tmp/workspace
+      - restore_cache:
+          key: v2-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

@@ -1,26 +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
-
-ignore:
-  - "docs"
-  - "*.md"
-  - "*.rst"

.github/CODEOWNERS

@@ -1,5 +1,4 @@
 # CODEOWNERS: https://help.github.com/articles/about-codeowners/
 
-# Everything goes through Bucky. For now.
-*       @ebuchman
-
+# Everything goes through Bucky, Anton, Alex. For now.
+*       @ebuchman @melekes @xla

.github/ISSUE_TEMPLATE

@@ -19,10 +19,6 @@ in a case of bug.
 
 **ABCI app** (name for built-in, URL for self-written if it's publicly available):
 
-
-**Merkleeyes version** (use `git rev-parse --verify HEAD`, skip if you don't use it):
-
-
 **Environment**:
 - **OS** (e.g. from /etc/os-release):
 - **Install tools**:
@@ -37,5 +33,10 @@ 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)**:
+
+**Config (you can paste only the changes you've made)**:
+
+**`/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

@@ -5,7 +5,6 @@
 .DS_Store
 build/*
 rpc/test/.tendermint
-.debora
 .tendermint
 remote_dump
 .revision
@@ -13,10 +12,16 @@ vendor
 .vagrant
 test/p2p/data/
 test/logs
-.glide
 coverage.txt
 docs/_build
 docs/tools
+docs/abci-spec.md
+*.log
 
 scripts/wal2json/wal2json
 scripts/cutWALUntil/cutWALUntil
+
+.idea/
+*.iml
+
+libs/pubsub/query/fuzz_test/output

CHANGELOG.md

@@ -1,31 +1,382 @@
 # Changelog
 
-## Roadmap
+## 0.21.0
 
-BREAKING CHANGES:
-- Upgrade the header to support better proofs on validtors, results, evidence, and possibly more
-- Better support for injecting randomness
-- Pass evidence/voteInfo through ABCI
-- Upgrade consensus for more real-time use of evidence
+*June 21th, 2018*
 
-FEATURES:
-- Peer reputation management
-- 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
+BREAKING CHANGES
+
+- [config] Change default ports from 4665X to 2665X. Ports over 32768 are
+  ephemeral and reserved for use by the kernel.
+- [cmd] `unsafe_reset_all` removes the addrbook.json
+
+IMPROVEMENT
+
+- [pubsub] Set default capacity to 0
+- [docs] Various improvements
+
+BUG FIXES
+
+- [consensus] Fix an issue where we don't make blocks after `fast_sync` when `create_empty_blocks=false`
+- [mempool] Fix #1761 where we don't process txs if `cache_size=0`
+- [rpc] Fix memory leak in Websocket (when using `/subscribe` method)
+- [config] Escape paths in config - fixes config paths on Windows
+
+## 0.20.0
+
+*June 6th, 2018*
+
+This is the first in a series of breaking releases coming to Tendermint after
+soliciting developer feedback and conducting security audits.
+
+This release does not break any blockchain data structures or
+protocols other than the ABCI messages between Tendermint and the application.
+
+Applications that upgrade for ABCI v0.11.0 should be able to continue running Tendermint
+v0.20.0 on blockchains created with v0.19.X
+
+BREAKING CHANGES
+
+- [abci] Upgrade to
+  [v0.11.0](https://github.com/tendermint/abci/blob/master/CHANGELOG.md#0110)
+- [abci] Change Query path for filtering peers by node ID from
+  `p2p/filter/pubkey/<id>` to `p2p/filter/id/<id>`
+
+## 0.19.9
+
+*June 5th, 2018*
+
+BREAKING CHANGES
+
+- [types/priv_validator] Moved to top level `privval` package
+
+FEATURES
+
+- [config] Collapse PeerConfig into P2PConfig
+- [docs] Add quick-install script
+- [docs/spec] Add table of Amino prefixes
+
+BUG FIXES
+
+- [rpc] Return 404 for unknown endpoints
+- [consensus] Flush WAL on stop
+- [evidence] Don't send evidence to peers that are behind
+- [p2p] Fix memory leak on peer disconnects
+- [rpc] Fix panic when `per_page=0`
+
+## 0.19.8
+
+*June 4th, 2018*
+
+BREAKING:
+
+- [p2p] Remove `auth_enc` config option, peer connections are always auth
+  encrypted. Technically a breaking change but seems no one was using it and
+  arguably a bug fix :)
+
+BUG FIXES
+
+- [mempool] Fix deadlock under high load when `skip_timeout_commit=true` and
+  `create_empty_blocks=false`
+
+## 0.19.7
+
+*May 31st, 2018*
+
+BREAKING:
+
+- [libs/pubsub] TagMap#Get returns a string value
+- [libs/pubsub] NewTagMap accepts a map of strings
+
+FEATURES
+
+- [rpc] the RPC documentation is now published to https://tendermint.github.io/slate
+- [p2p] AllowDuplicateIP config option to refuse connections from same IP.
+    - true by default for now, false by default in next breaking release
+- [docs] Add docs for query, tx indexing, events, pubsub
+- [docs] Add some notes about running Tendermint in production
 
 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
+
+- [consensus] Consensus reactor now receives events from a separate synchronous event bus,
+  which is not dependant on external RPC load
+- [consensus/wal] do not look for height in older files if we've seen height - 1
+- [docs] Various cleanup and link fixes
+
+## 0.19.6
+
+*May 29th, 2018*
+
+BUG FIXES
+
+- [blockchain] Fix fast-sync deadlock during high peer turnover
+
+BUG FIX:
+
+- [evidence] Dont send peers evidence from heights they haven't synced to yet
+- [p2p] Refuse connections to more than one peer with the same IP
+- [docs] Various fixes
+
+## 0.19.5
+
+*May 20th, 2018*
+
+BREAKING CHANGES
+
+- [rpc/client] TxSearch and UnconfirmedTxs have new arguments (see below)
+- [rpc/client] TxSearch returns ResultTxSearch
+- [version] Breaking changes to Go APIs will not be reflected in breaking
+  version change, but will be included in changelog.
+
+FEATURES
+
+- [rpc] `/tx_search` takes `page` (starts at 1) and `per_page` (max 100, default 30) args to paginate results
+- [rpc] `/unconfirmed_txs` takes `limit` (max 100, default 30) arg to limit the output
+- [config] `mempool.size` and `mempool.cache_size` options
+
+IMPROVEMENTS
+
+- [docs] Lots of updates
+- [consensus] Only Fsync() the WAL before executing msgs from ourselves
+
+BUG FIXES
+
+- [mempool] Enforce upper bound on number of transactions
+
+## 0.19.4 (May 17th, 2018)
+
+IMPROVEMENTS
+
+- [state] Improve tx indexing by using batches
+- [consensus, state] Improve logging (more consensus logs, fewer tx logs)
+- [spec] Moved to `docs/spec` (TODO cleanup the rest of the docs ...)
+
+BUG FIXES
+
+- [consensus] Fix issue #1575 where a late proposer can get stuck
+
+## 0.19.3 (May 14th, 2018)
+
+FEATURES
+
+- [rpc] New `/consensus_state` returns just the votes seen at the current height
+
+IMPROVEMENTS
+
+- [rpc] Add stringified votes and fraction of power voted to `/dump_consensus_state`
+- [rpc] Add PeerStateStats to `/dump_consensus_state`
+
+BUG FIXES
+
+- [cmd] Set GenesisTime during `tendermint init`
+- [consensus] fix ValidBlock rules
+
+## 0.19.2 (April 30th, 2018)
+
+FEATURES:
+
+- [p2p] Allow peers with different Minor versions to connect
+- [rpc] `/net_info` includes `n_peers`
+
+IMPROVEMENTS:
+
+- [p2p] Various code comments, cleanup, error types
+- [p2p] Change some Error logs to Debug
 
 BUG FIXES:
-- Graceful handling/recovery for apps that have non-determinism or fail to halt
-- Graceful handling/recovery for violations of safety, or liveness
+
+- [p2p] Fix reconnect to persistent peer when first dial fails
+- [p2p] Validate NodeInfo.ListenAddr
+- [p2p] Only allow (MaxNumPeers - MaxNumOutboundPeers) inbound peers
+- [p2p/pex] Limit max msg size to 64kB
+- [p2p] Fix panic when pex=false
+- [p2p] Allow multiple IPs per ID in AddrBook
+- [p2p] Fix before/after bugs in addrbook isBad()
+
+## 0.19.1 (April 27th, 2018)
+
+Note this release includes some small breaking changes in the RPC and one in the
+config that are really bug fixes. v0.19.1 will work with existing chains, and make Tendermint
+easier to use and debug. With <3
+
+BREAKING (MINOR)
+
+- [config] Removed `wal_light` setting. If you really needed this, let us know
+
+FEATURES:
+
+- [networks] moved in tooling from devops repo: terraform and ansible scripts for deploying testnets !
+- [cmd] Added `gen_node_key` command
+
+BUG FIXES
+
+Some of these are breaking in the RPC response, but they're really bugs!
+
+- [spec] Document address format and pubkey encoding pre and post Amino
+- [rpc] Lower case JSON field names
+- [rpc] Fix missing entries, improve, and lower case the fields in `/dump_consensus_state`
+- [rpc] Fix NodeInfo.Channels format to hex
+- [rpc] Add Validator address to `/status`
+- [rpc] Fix `prove` in ABCIQuery
+- [cmd] MarshalJSONIndent on init
+
+## 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
+
+- [test] docker-compose for local testnet setup (thanks Greg!)
+
+## 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)
 

CONTRIBUTING.md

@@ -34,27 +34,44 @@ Please don't make Pull Requests to `master`.
 
 ## Dependencies
 
-We use [glide](https://github.com/masterminds/glide) 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 `glide install`. Even for dependencies under our control, glide helps us keeps multiple repos in sync as they evolve. Anything with an executable, such as apps, tools, and the core, should use glide.
+We use [dep](https://github.com/golang/dep) to manage dependencies.
 
-Run `bash scripts/glide/status.sh` to get a list of vendored dependencies that may not be up-to-date.
+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, all you have to do to get started hacking Tendermint is:
+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
-cd ~/go/src/github.com/tendermint/tendermint
 make test
 ```
 
 ## Testing
 
-All repos should be hooked up to circle.
-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`.
+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
 
@@ -97,4 +114,4 @@ especially `go-p2p` and `go-rpc`, as their versions are referenced in tendermint
 - 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
+- delete the hotfix-vX.X.X branch

DOCKER/.gitignore

@@ -0,0 +1 @@
+tendermint

DOCKER/Dockerfile

@@ -1,45 +1,39 @@
-FROM alpine:3.6
+FROM alpine:3.7
+MAINTAINER Greg Szabo <greg@tendermint.com>
 
-# This is the release of tendermint to pull in.
-ENV TM_VERSION 0.12.0
-ENV TM_SHA256SUM be17469e92f04fc2a3663f891da28edbaa6c37c4d2f746736571887f4790555a
-
-# 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
-# validator file into /tendermint.
+# Tendermint will be looking for the genesis file in /tendermint/config/genesis.json
+# (unless you change `genesis_file` in config.toml). You can put your config.toml and
+# private validator file into /tendermint/config.
 #
 # The /tendermint/data dir is used by tendermint to store state.
-ENV DATA_ROOT /tendermint
-ENV TMHOME $DATA_ROOT
-
-# Set user right away for determinism
-RUN addgroup tmuser && \
-    adduser -S -G tmuser tmuser
-
-# Create directory for persistence and give our user ownership
-RUN mkdir -p $DATA_ROOT && \
-    chown -R tmuser:tmuser $DATA_ROOT
+ENV TMHOME /tendermint
 
+# OS environment setup
+# Set user right away for determinism, create directory for persistence and give our user ownership
 # jq and curl used for extracting `pub_key` from private validator while
 # deploying tendermint with Kubernetes. It is nice to have bash so the users
 # could execute bash commands.
-RUN apk add --no-cache bash curl jq
+RUN apk update && \
+    apk upgrade && \
+    apk --no-cache add curl jq bash && \
+    addgroup tmuser && \
+    adduser -S -G tmuser tmuser -h "$TMHOME"
 
-RUN apk add --no-cache openssl && \
-    wget https://s3-us-west-2.amazonaws.com/tendermint/binaries/tendermint/v${TM_VERSION}/tendermint_${TM_VERSION}_linux_amd64.zip && \
-    echo "${TM_SHA256SUM}  tendermint_${TM_VERSION}_linux_amd64.zip" | sha256sum -c && \
-    unzip -d /bin tendermint_${TM_VERSION}_linux_amd64.zip && \
-    apk del openssl && \
-    rm -f tendermint_${TM_VERSION}_linux_amd64.zip
+# Run the container with tmuser by default. (UID=100, GID=1000)
+USER tmuser
 
 # Expose the data directory as a volume since there's mutable state in there
-VOLUME $DATA_ROOT
+VOLUME [ $TMHOME ]
 
-# p2p port
-EXPOSE 46656
-# rpc port
-EXPOSE 46657
+WORKDIR $TMHOME
 
-ENTRYPOINT ["tendermint"]
+# p2p and rpc port
+EXPOSE 26656 26657
 
+ENTRYPOINT ["/usr/bin/tendermint"]
 CMD ["node", "--moniker=`hostname`"]
+STOPSIGNAL SIGTERM
+
+ARG BINARY=tendermint
+COPY $BINARY /usr/bin/tendermint
+

DOCKER/Dockerfile.develop

@@ -1,4 +1,4 @@
-FROM alpine:3.6
+FROM alpine:3.7
 
 ENV DATA_ROOT /tendermint
 ENV TMHOME $DATA_ROOT
@@ -18,18 +18,18 @@ 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
 
 VOLUME $DATA_ROOT
 
-EXPOSE 46656
-EXPOSE 46657
+EXPOSE 26656
+EXPOSE 26657
 
 ENTRYPOINT ["tendermint"]
 
-CMD ["node", "--moniker=`hostname`", "--proxy_app=dummy"]
+CMD ["node", "--moniker=`hostname`", "--proxy_app=kvstore"]

DOCKER/Dockerfile.testing

@@ -0,0 +1,18 @@
+FROM golang:1.10.1
+
+
+# Grab deps (jq, hexdump, xxd, killall)
+RUN apt-get update && \
+  apt-get install -y --no-install-recommends \
+  jq bsdmainutils vim-common psmisc netcat
+
+# Add testing deps for curl
+RUN echo 'deb http://httpredir.debian.org/debian testing main non-free contrib' >> /etc/apt/sources.list && \
+  apt-get update && \
+  apt-get install -y --no-install-recommends curl
+
+VOLUME /go
+
+EXPOSE 26656
+EXPOSE 26657
+

DOCKER/Makefile

@@ -7,6 +7,9 @@ push:
 build_develop:
 	docker build -t "tendermint/tendermint:develop" -f Dockerfile.develop .
 
+build_testing:
+	docker build --tag tendermint/testing -f ./Dockerfile.testing .
+
 push_develop:
 	docker push "tendermint/tendermint:develop"
 

DOCKER/README.md

@@ -1,6 +1,12 @@
-# Supported tags and respective `Dockerfile` links
+# Docker
 
-- `0.12.0`, `latest` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/70d8afa6e952e24c573ece345560a5971bf2cc0e/DOCKER/Dockerfile)
+## Supported tags and respective `Dockerfile` links
+
+- `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)
@@ -10,10 +16,10 @@
 
 `develop` tag points to the [develop](https://github.com/tendermint/tendermint/tree/develop) branch.
 
-# Quick reference
+## Quick reference
 
 * **Where to get help:**
-  https://tendermint.com/community
+  https://cosmos.network/community
 
 * **Where to file issues:**
   https://github.com/tendermint/tendermint/issues
@@ -21,7 +27,7 @@
 * **Supported Docker versions:**
   [the latest release](https://github.com/moby/moby/releases) (down to 1.6 on a best-effort basis)
 
-# Tendermint
+## 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.
 
@@ -29,29 +35,33 @@ For more background, see the [introduction](https://tendermint.readthedocs.io/en
 
 To get started developing applications, see the [application developers guide](https://tendermint.readthedocs.io/en/master/getting-started.html).
 
-# How to use this image
+## 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.
+A quick 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 node --proxy_app=dummy
+docker run -it --rm -v "/tmp:/tendermint" tendermint/tendermint node --proxy_app=kvstore
 ```
 
-## mintnet-kubernetes
+## Local cluster
 
-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.
+To run a 4-node network, see the `Makefile` in the root of [the repo](https://github.com/tendermint/tendermint/master/Makefile) and run:
 
-# License
+```
+make build-linux
+make build-docker-localnode
+make localnet-start
+```
 
-View [license information](https://raw.githubusercontent.com/tendermint/tendermint/master/LICENSE) for the software contained in this image.
+Note that this will build and use a different image than the ones provided here.
 
-# User Feedback
+## License
+
+- Tendermint's license is [Apache 2.0](https://github.com/tendermint/tendermint/master/LICENSE).
 
 ## 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.
-
-Before you start to code, we recommend discussing your plans through a [GitHub](https://github.com/tendermint/tendermint/issues) issue, especially for more ambitious contributions. This gives other contributors a chance to point you in the right direction, give you feedback on your design, and help you find out if someone else is working on the same thing.
+Contributions are most welcome! See the [contributing file](https://github.com/tendermint/tendermint/blob/master/CONTRIBUTING.md) for more information.

Gopkg.lock

@@ -0,0 +1,379 @@
+# 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 = "86fed781132ac890ee03e906e4ecd5d6fa180c64"
+
+[[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 = "2e65f85255dbc3072edf28d6b5b8efc472979f5a"
+
+[[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 = "c2353362d570a7bfa228149c62842019201cfb71"
+  version = "v1.8.0"
+
+[[projects]]
+  branch = "master"
+  name = "github.com/mitchellh/mapstructure"
+  packages = ["."]
+  revision = "bb74f1db0675b241733089d5a1faa5dd8b0ef57b"
+
+[[projects]]
+  name = "github.com/pelletier/go-toml"
+  packages = ["."]
+  revision = "c01d1270ff3e442a8a57cddc1c92dc1138598194"
+  version = "v1.2.0"
+
+[[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 = "e2704e165165ec55d062f5919b4b29494e9fa790"
+
+[[projects]]
+  name = "github.com/spf13/afero"
+  packages = [
+    ".",
+    "mem"
+  ]
+  revision = "787d034dfe70e44075ccc060d346146ef53270ad"
+  version = "v1.1.1"
+
+[[projects]]
+  name = "github.com/spf13/cast"
+  packages = ["."]
+  revision = "8965335b8c7107321228e3e3702cab9832751bac"
+  version = "v1.2.0"
+
+[[projects]]
+  name = "github.com/spf13/cobra"
+  packages = ["."]
+  revision = "ef82de70bb3f60c65fb8eebacbb2d122ef517385"
+  version = "v0.0.3"
+
+[[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 = "f35b8ab0b5a2cef36673838d662e249dd9c94686"
+  version = "v1.2.2"
+
+[[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 = "e2150783cd35f5b607daca48afd8c57ec54cc995"
+
+[[projects]]
+  name = "github.com/tendermint/abci"
+  packages = [
+    "client",
+    "example/code",
+    "example/counter",
+    "example/kvstore",
+    "server",
+    "types"
+  ]
+  revision = "198dccf0ddfd1bb176f87657e3286a05a6ed9540"
+  version = "v0.12.0"
+
+[[projects]]
+  branch = "master"
+  name = "github.com/tendermint/ed25519"
+  packages = [
+    ".",
+    "edwards25519",
+    "extra25519"
+  ]
+  revision = "d8387025d2b9d158cf4efb07e7ebf814bcce2057"
+
+[[projects]]
+  name = "github.com/tendermint/go-amino"
+  packages = ["."]
+  revision = "ed62928576cfcaf887209dc96142cd79cdfff389"
+  version = "0.9.9"
+
+[[projects]]
+  name = "github.com/tendermint/go-crypto"
+  packages = ["."]
+  revision = "915416979bf70efa4bcbf1c6cd5d64c5fff9fc19"
+  version = "v0.6.2"
+
+[[projects]]
+  name = "github.com/tendermint/tmlibs"
+  packages = [
+    "autofile",
+    "cli",
+    "cli/flags",
+    "clist",
+    "common",
+    "db",
+    "flowrate",
+    "log",
+    "merkle",
+    "test"
+  ]
+  revision = "692f1d86a6e2c0efa698fd1e4541b68c74ffaf38"
+  version = "v0.8.4"
+
+[[projects]]
+  branch = "master"
+  name = "golang.org/x/crypto"
+  packages = [
+    "curve25519",
+    "nacl/box",
+    "nacl/secretbox",
+    "openpgp/armor",
+    "openpgp/errors",
+    "poly1305",
+    "ripemd160",
+    "salsa20/salsa"
+  ]
+  revision = "8ac0e0d97ce45cd83d1d7243c060cb8461dda5e9"
+
+[[projects]]
+  branch = "master"
+  name = "golang.org/x/net"
+  packages = [
+    "context",
+    "http/httpguts",
+    "http2",
+    "http2/hpack",
+    "idna",
+    "internal/timeseries",
+    "trace"
+  ]
+  revision = "db08ff08e8622530d9ed3a0e8ac279f6d4c02196"
+
+[[projects]]
+  branch = "master"
+  name = "golang.org/x/sys"
+  packages = ["unix"]
+  revision = "a9e25c09b96b8870693763211309e213c6ef299d"
+
+[[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]]
+  name = "google.golang.org/genproto"
+  packages = ["googleapis/rpc/status"]
+  revision = "7fd901a49ba6a7f87732eb344f6e3c5b19d1b200"
+
+[[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 = "62d0626fa963b25411234da915fb3b8bfc7aefffd76824d27ac1647ca2b5d489"
+  solver-name = "gps-cdcl"
+  solver-version = 1

Gopkg.toml

@@ -0,0 +1,99 @@
+# 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 = "~0.12.0"
+
+[[constraint]]
+  name = "github.com/tendermint/go-crypto"
+  version = "~0.6.2"
+
+[[constraint]]
+  name = "github.com/tendermint/go-amino"
+  version = "=0.9.9"
+
+[[override]]
+  name = "github.com/tendermint/tmlibs"
+  version = "~0.8.4"
+
+[[constraint]]
+  name = "google.golang.org/grpc"
+  version = "~1.7.3"
+
+# this got updated and broke, so locked to an old working commit ...
+[[override]]
+  name = "google.golang.org/genproto"
+  revision = "7fd901a49ba6a7f87732eb344f6e3c5b19d1b200"
+
+[prune]
+  go-tests = true
+  unused-packages = true

Makefile

@@ -1,41 +1,123 @@
 GOTOOLS = \
-					github.com/mitchellh/gox \
-					github.com/tcnksm/ghr \
-					github.com/alecthomas/gometalinter
-
+	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`"
 
-BUILD_FLAGS = -ldflags "-X github.com/tendermint/tendermint/version.GitCommit=`git rev-parse --short HEAD`"
+all: check build test install
 
-all: get_vendor_deps install test
+check: check_tools ensure_deps
 
-install:
-	CGO_ENABLED=0 go install $(BUILD_FLAGS) ./cmd/tendermint
+
+########################################
+### Build
 
 build:
-	CGO_ENABLED=0 go build $(BUILD_FLAGS) -o build/tendermint ./cmd/tendermint/
+	CGO_ENABLED=0 go build $(BUILD_FLAGS) -tags '$(BUILD_TAGS)' -o build/tendermint ./cmd/tendermint/
 
 build_race:
-	CGO_ENABLED=0 go build -race $(BUILD_FLAGS) -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'"
 
-test:
-	@echo "--> Running linter"
-	@make metalinter_test
-	@echo "--> Running go test"
-	@go test $(PACKAGES)
+########################################
+### Tools & dependencies
 
-test_race:
-	@echo "--> Running go test --race"
-	@go test -v -race $(PACKAGES)
+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:
-	@bash ./test/test.sh
+	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)
@@ -43,55 +125,35 @@ test_release:
 test100:
 	@for i in {1..100}; do make test; done
 
-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
+vagrant_test:
+	vagrant up
+	vagrant ssh -c 'make test_integrations'
 
-list_deps:
-	@go list -f '{{join .Deps "\n"}}' ./... | \
-		grep -v /vendor/ | sort | uniq | \
-		xargs go list -f '{{if not .Standard}}{{.ImportPath}}{{end}}'
+### go tests
+test:
+	@echo "--> Running go test"
+	@go test $(PACKAGES)
 
-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
+test_race:
+	@echo "--> Running go test --race"
+	@go test -v -race $(PACKAGES)
 
-update_deps:
-	@echo "--> Updating dependencies"
-	@go get -d -u ./...
-
-get_vendor_deps:
-	@hash glide 2>/dev/null || go get github.com/Masterminds/glide
-	@rm -rf vendor/
-	@echo "--> Running glide install"
-	@glide install
-
-update_tools:
-	@echo "--> Updating tools"
-	@go get -u $(GOTOOLS)
-
-tools:
-	@echo "--> Installing tools"
-	@go get $(GOTOOLS)
-	@gometalinter --install
 
+########################################
 ### Formatting, linting, and vetting
 
-metalinter:
-	@gometalinter --vendor --deadline=600s --enable-all --disable=lll ./...
+fmt:
+	@go fmt ./...
 
-metalinter_test:
-	@gometalinter --vendor --deadline=600s --disable-all  \
+metalinter:
+	@echo "--> Running linter"
+	@gometalinter.v2 --vendor --deadline=600s --disable-all  \
 		--enable=deadcode \
+		--enable=gosimple \
 	 	--enable=misspell \
 		--enable=safesql \
 		./...
-
-		# --enable=gas \
+		#--enable=gas \
 		#--enable=maligned \
 		#--enable=dupl \
 		#--enable=errcheck \
@@ -99,7 +161,6 @@ metalinter_test:
 		#--enable=gocyclo \
 		#--enable=goimports \
 		#--enable=golint \ <== comments on anything exported
-		#--enable=gosimple \
 		#--enable=gotype \
 	 	#--enable=ineffassign \
 	   	#--enable=interfacer \
@@ -113,4 +174,63 @@ metalinter_test:
 		#--enable=vet \
 		#--enable=vetshadow \
 
-.PHONY: install build build_race dist test test_race test_integrations test100 draw_deps list_deps get_deps get_vendor_deps update_deps update_tools tools test_release
+metalinter_all:
+	@echo "--> Running linter (all)"
+	gometalinter.v2 --vendor --deadline=600s --enable-all --disable=lll ./...
+
+###########################################################
+### Docker image
+
+build-docker:
+	cp build/tendermint DOCKER/tendermint
+	docker build --label=tendermint --tag="tendermint/tendermint" DOCKER
+	rm -rf DOCKER/tendermint
+
+###########################################################
+### Local testnet using docker
+
+# Build linux binary on other platforms
+build-linux:
+	GOOS=linux GOARCH=amd64 $(MAKE) build
+
+build-docker-localnode:
+	cd networks/local
+	make
+
+# Run a 4-node testnet locally
+localnet-start: localnet-stop
+	@if ! [ -f build/node0/config/genesis.json ]; then docker run --rm -v $(CURDIR)/build:/tendermint:Z tendermint/localnode testnet --v 4 --o . --populate-persistent-peers --starting-ip-address 192.167.10.2 ; fi
+	docker-compose up
+
+# Stop testnet
+localnet-stop:
+	docker-compose down
+
+###########################################################
+### Remote full-nodes (sentry) using terraform and ansible
+
+# Server management
+sentry-start:
+	@if [ -z "$(DO_API_TOKEN)" ]; then echo "DO_API_TOKEN environment variable not set." ; false ; fi
+	@if ! [ -f $(HOME)/.ssh/id_rsa.pub ]; then ssh-keygen ; fi
+	cd networks/remote/terraform && terraform init && terraform apply -var DO_API_TOKEN="$(DO_API_TOKEN)" -var SSH_KEY_FILE="$(HOME)/.ssh/id_rsa.pub"
+	@if ! [ -f $(CURDIR)/build/node0/config/genesis.json ]; then docker run --rm -v $(CURDIR)/build:/tendermint:Z tendermint/localnode testnet --v 0 --n 4 --o . ; fi
+	cd networks/remote/ansible && ANSIBLE_HOST_KEY_CHECKING=False ansible-playbook -i inventory/digital_ocean.py -l sentrynet install.yml
+	@echo "Next step: Add your validator setup in the genesis.json and config.tml files and run \"make sentry-config\". (Public key of validator, chain ID, peer IP and node ID.)"
+
+# Configuration management
+sentry-config:
+	cd networks/remote/ansible && ansible-playbook -i inventory/digital_ocean.py -l sentrynet config.yml -e BINARY=$(CURDIR)/build/tendermint -e CONFIGDIR=$(CURDIR)/build
+
+sentry-stop:
+	@if [ -z "$(DO_API_TOKEN)" ]; then echo "DO_API_TOKEN environment variable not set." ; false ; fi
+	cd networks/remote/terraform && terraform destroy -var DO_API_TOKEN="$(DO_API_TOKEN)" -var SSH_KEY_FILE="$(HOME)/.ssh/id_rsa.pub"
+
+# meant for the CI, inspect script & adapt accordingly
+build-slate:
+	bash scripts/slate.sh
+
+# 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 localnet-start localnet-stop build-docker build-docker-localnode sentry-start sentry-config sentry-stop build-slate

README.md

@@ -9,7 +9,7 @@ Or [Blockchain](https://en.wikipedia.org/wiki/Blockchain_(database)) for short.
 https://camo.githubusercontent.com/915b7be44ada53c290eb157634330494ebe3e30a/68747470733a2f2f676f646f632e6f72672f6769746875622e636f6d2f676f6c616e672f6764646f3f7374617475732e737667
 )](https://godoc.org/github.com/tendermint/tendermint)
 [![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/)
+[![riot.im](https://img.shields.io/badge/riot.im-JOIN%20CHAT-green.svg)](https://riot.im/app/#/room/#tendermint:matrix.org)
 [![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)
 
@@ -19,28 +19,56 @@ 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 -
 and securely replicates it on many machines.
 
-For more information, from introduction to install to application development, [Read The Docs](https://tendermint.readthedocs.io/en/master/).
+For protocol details, see [the specification](/docs/spec).
+
+## A Note on Production Readiness
+
+While Tendermint is being used in production in private, permissioned
+environments, we are still working actively to harden and audit it in preparation
+for use in public blockchains, such as the [Cosmos Network](https://cosmos.network/).
+We are also still making breaking changes to the protocol and the APIs.
+Thus we tag the releases as *alpha software*.
+
+In any case, if you intend to run Tendermint in production,
+please [contact us](https://riot.im/app/#/room/#tendermint:matrix.org) :)
+
+## Security
+
+To report a security vulnerability, see our [bug bounty
+program](https://tendermint.com/security).
+
+For examples of the kinds of bugs we're looking for, see [SECURITY.md](SECURITY.md)
+
+## Minimum requirements
+
+Requirement|Notes
+---|---
+Go version | Go1.9 or higher
 
 ## Install
 
-To download pre-built binaries, see our [downloads page](https://tendermint.com/downloads).
+See the [install instructions](/docs/install.rst)
 
-To install from source, you should be able to:
+## Quick Start
 
-`go get -u github.com/tendermint/tendermint/cmd/tendermint`
-
-For more details (or if it fails), [read the docs](https://tendermint.readthedocs.io/en/master/install.html).
+- [Single node](/docs/using-tendermint.rst)
+- [Local cluster using docker-compose](/networks/local)
+- [Remote cluster using terraform and ansible](/docs/terraform-and-ansible.rst)
+- [Join the public testnet](https://cosmos.network/testnet)
 
 ## Resources
 
 ### Tendermint Core
 
-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.
+For details about the blockchain data structures and the p2p protocols, see the
+the [Tendermint specification](/docs/spec).
+
+For details on using the software, [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
 
@@ -55,8 +83,8 @@ All resources involving the use of, building application on, or developing for,
 
 ### Applications
 
-* [Ethermint](http://github.com/tendermint/ethermint); Ethereum on Tendermint
 * [Cosmos SDK](http://github.com/cosmos/cosmos-sdk); a cryptocurrency application framework
+* [Ethermint](http://github.com/tendermint/ethermint); Ethereum on Tendermint
 * [Many more](https://tendermint.readthedocs.io/en/master/ecosystem.html#abci-applications)
 
 ### More
@@ -79,7 +107,11 @@ According to SemVer, anything in the public API can change at any time before ve
 
 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:
+interfaces exposed to other processes (cli, rpc, p2p, etc.), but does not
+include the in-process Go APIs.
+
+That said, breaking changes in the following packages will be documented in the
+CHANGELOG even if they don't lead to MINOR version bumps:
 
 - types
 - rpc/client

ROADMAP.md

@@ -0,0 +1,23 @@
+# 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

SECURITY.md

@@ -0,0 +1,71 @@
+# Security
+
+As part of our [Coordinated Vulnerability Disclosure
+Policy](https://tendermint.com/security), we operate a bug bounty.
+See the policy for more details on submissions and rewards.
+
+Here is a list of examples of the kinds of bugs we're most interested in:
+
+## Specification
+
+- Conceptual flaws
+- Ambiguities, inconsistencies, or incorrect statements
+- Mis-match between specification and implementation of any component
+
+## Consensus
+
+Assuming less than 1/3 of the voting power is Byzantine (malicious):
+
+- Validation of blockchain data structures, including blocks, block parts,
+  votes, and so on
+- Execution of blocks
+- Validator set changes
+- Proposer round robin
+- Two nodes committing conflicting blocks for the same height (safety failure)
+- A correct node signing conflicting votes
+- A node halting (liveness failure)
+- Syncing new and old nodes
+
+## Networking
+
+- Authenticated encryption (MITM, information leakage)
+- Eclipse attacks
+- Sybil attacks
+- Long-range attacks
+- Denial-of-Service
+
+## RPC
+
+- Write-access to anything besides sending transactions
+- Denial-of-Service
+- Leakage of secrets
+
+## Denial-of-Service
+
+Attacks may come through the P2P network or the RPC:
+
+- Amplification attacks
+- Resource abuse
+- Deadlocks and race conditions
+- Panics and unhandled errors
+
+## Libraries
+
+- Serialization (Amino)
+- Reading/Writing files and databases
+- Logging and monitoring
+
+## Cryptography
+
+- Elliptic curves for validator signatures
+- Hash algorithms and Merkle trees for block validation
+- Authenticated encryption for P2P connections
+
+## Light Client
+
+- Validation of blockchain data structures
+- Correctly validating an incorrect proof
+- Incorrectly validating a correct proof
+- Syncing validator set changes
+
+

Vagrantfile

@@ -2,7 +2,7 @@
 # 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 = 4096
@@ -11,29 +11,48 @@ Vagrant.configure("2") do |config|
 
   config.vm.provision "shell", inline: <<-SHELL
     apt-get update
-    apt-get install -y --no-install-recommends wget curl jq shellcheck bsdmainutils psmisc
 
-    wget -qO- https://get.docker.com/ | sh
+    # install base requirements
+    apt-get install -y --no-install-recommends wget curl jq zip \
+        make shellcheck bsdmainutils psmisc
+    apt-get install -y language-pack-en
+
+    # install docker
+    apt-get install -y --no-install-recommends apt-transport-https \
+      ca-certificates curl software-properties-common
+    curl -fsSL https://download.docker.com/linux/ubuntu/gpg | apt-key add -
+    add-apt-repository \
+      "deb [arch=amd64] https://download.docker.com/linux/ubuntu \
+      $(lsb_release -cs) \
+      stable"
+    apt-get install -y docker-ce
     usermod -a -G docker vagrant
+
+    # install go
+    wget -q https://dl.google.com/go/go1.10.1.linux-amd64.tar.gz
+    tar -xvf go1.10.1.linux-amd64.tar.gz
+    mv go /usr/local
+    rm -f go1.10.1.linux-amd64.tar.gz
+
+    # cleanup
     apt-get autoremove -y
 
-    apt-get install -y --no-install-recommends git
-    curl -O https://storage.googleapis.com/golang/go1.9.linux-amd64.tar.gz
-    tar -xvf go1.9.linux-amd64.tar.gz
-    rm -rf /usr/local/go
-    mv go /usr/local
-    rm -f go1.9.linux-amd64.tar.gz
-    mkdir -p /home/vagrant/go/bin
-    echo 'export PATH=$PATH:/usr/local/go/bin:/home/vagrant/go/bin' >> /home/vagrant/.bash_profile
+    # set env variables
+    echo 'export GOROOT=/usr/local/go' >> /home/vagrant/.bash_profile
     echo 'export GOPATH=/home/vagrant/go' >> /home/vagrant/.bash_profile
-
+    echo 'export PATH=$PATH:$GOROOT/bin:$GOPATH/bin' >> /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/localsync.sh

@@ -14,7 +14,7 @@ if [ ! -d $DATA ]; then
   echo "starting node"
   tendermint node \
     --home $DATA \
-    --proxy_app dummy \
+    --proxy_app kvstore \
     --p2p.laddr tcp://127.0.0.1:56656 \
     --rpc.laddr tcp://127.0.0.1:56657 \
     --log_level error &
@@ -35,7 +35,7 @@ cp -R $DATA $HOME1
 echo "starting validator node"
 tendermint node \
   --home $HOME1 \
-  --proxy_app dummy \
+  --proxy_app kvstore \
   --p2p.laddr tcp://127.0.0.1:56656 \
   --rpc.laddr tcp://127.0.0.1:56657 \
   --log_level error &
@@ -48,10 +48,10 @@ cp $HOME1/genesis.json $HOME2
 printf "starting downloader node"
 tendermint node \
   --home $HOME2 \
-  --proxy_app dummy \
+  --proxy_app kvstore \
   --p2p.laddr tcp://127.0.0.1:56666 \
   --rpc.laddr tcp://127.0.0.1:56667 \
-  --p2p.seeds 127.0.0.1:56656 \
+  --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

benchmarks/codec_test.go

@@ -4,8 +4,8 @@ import (
 	"testing"
 	"time"
 
+	"github.com/tendermint/go-amino"
 	"github.com/tendermint/go-crypto"
-	"github.com/tendermint/go-wire"
 
 	proto "github.com/tendermint/tendermint/benchmarks/proto"
 	"github.com/tendermint/tendermint/p2p"
@@ -14,27 +14,35 @@ import (
 
 func BenchmarkEncodeStatusWire(b *testing.B) {
 	b.StopTimer()
-	pubKey := crypto.GenPrivKeyEd25519().PubKey()
+	cdc := amino.NewCodec()
+	ctypes.RegisterAmino(cdc)
+	nodeKey := p2p.NodeKey{PrivKey: crypto.GenPrivKeyEd25519()}
 	status := &ctypes.ResultStatus{
-		NodeInfo: &p2p.NodeInfo{
-			PubKey:     pubKey.Unwrap().(crypto.PubKeyEd25519),
+		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:   time.Unix(0, 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)
 	}
 
@@ -42,12 +50,13 @@ func BenchmarkEncodeStatusWire(b *testing.B) {
 
 func BenchmarkEncodeNodeInfoWire(b *testing.B) {
 	b.StopTimer()
-	pubKey := crypto.GenPrivKeyEd25519().PubKey().Unwrap().(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"},
@@ -56,19 +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().Unwrap().(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"},
@@ -77,7 +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)
 	}
 
@@ -85,16 +98,20 @@ func BenchmarkEncodeNodeInfoBinary(b *testing.B) {
 
 func BenchmarkEncodeNodeInfoProto(b *testing.B) {
 	b.StopTimer()
-	pubKey := crypto.GenPrivKeyEd25519().PubKey().Unwrap().(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/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

@@ -11,7 +11,7 @@ import (
 )
 
 func main() {
-	wsc := rpcclient.NewWSClient("127.0.0.1:46657", "/websocket")
+	wsc := rpcclient.NewWSClient("127.0.0.1:26657", "/websocket")
 	err := wsc.Start()
 	if err != nil {
 		cmn.Exit(err.Error())

blockchain/pool.go

@@ -1,18 +1,22 @@
 package blockchain
 
 import (
+	"errors"
+	"fmt"
 	"math"
 	"sync"
+	"sync/atomic"
 	"time"
 
-	"github.com/tendermint/tendermint/types"
 	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
@@ -22,7 +26,6 @@ eg, L = latency = 0.1s
 	B/S = CB/P/BS = 12.8 blocks/s
 
 	12.8 * 0.1 = 1.28 blocks on conn
-
 */
 
 const (
@@ -30,10 +33,20 @@ const (
 	maxTotalRequesters        = 1000
 	maxPendingRequests        = maxTotalRequesters
 	maxPendingRequestsPerPeer = 50
-	minRecvRate               = 10240 // 10Kb/s
+
+	// 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.
@@ -54,25 +67,27 @@ type BlockPool struct {
 	// block requests
 	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
 
+	// atomic
+	numPending int32 // number of requests pending assignment or block response
+
 	requestsCh chan<- BlockRequest
-	timeoutsCh chan<- string
+	errorsCh   chan<- peerError
 }
 
-func NewBlockPool(start int64, 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[int64]*bpRequester),
 		height:     start,
 		numPending: 0,
 
 		requestsCh: requestsCh,
-		timeoutsCh: timeoutsCh,
+		errorsCh:   errorsCh,
 	}
 	bp.BaseService = *cmn.NewBaseService(nil, "BlockPool", bp)
 	return bp
@@ -88,7 +103,6 @@ func (pool *BlockPool) OnStop() {}
 
 // Run spawns requesters as needed.
 func (pool *BlockPool) makeRequestersRoutine() {
-
 	for {
 		if !pool.IsRunning() {
 			break
@@ -119,10 +133,14 @@ 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)
-				pool.Logger.Error("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
 			}
 		}
@@ -136,7 +154,7 @@ func (pool *BlockPool) GetStatus() (height int64, numPending int32, lenRequester
 	pool.mtx.Lock()
 	defer pool.mtx.Unlock()
 
-	return pool.height, pool.numPending, len(pool.requesters)
+	return pool.height, atomic.LoadInt32(&pool.numPending), len(pool.requesters)
 }
 
 // TODO: relax conditions, prevent abuse.
@@ -189,40 +207,48 @@ func (pool *BlockPool) PopRequest() {
 		delete(pool.requesters, pool.height)
 		pool.height++
 	} else {
-		cmn.PanicSanity(cmn.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 int64) {
+// 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]
 
 	if request.block == nil {
-		cmn.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)
+	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 {
-		// a block we didn't expect.
-		// TODO:if height is too far ahead, punish peer
+		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--
+		atomic.AddInt32(&pool.numPending, -1)
 		peer := pool.peers[peerID]
 		if peer != nil {
 			peer.decrPending(blockSize)
@@ -240,7 +266,7 @@ func (pool *BlockPool) MaxPeerHeight() int64 {
 }
 
 // Sets the peer's alleged blockchain height.
-func (pool *BlockPool) SetPeerHeight(peerID string, height int64) {
+func (pool *BlockPool) SetPeerHeight(peerID p2p.ID, height int64) {
 	pool.mtx.Lock()
 	defer pool.mtx.Unlock()
 
@@ -258,20 +284,17 @@ func (pool *BlockPool) SetPeerHeight(peerID string, height int64) {
 	}
 }
 
-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 {
-				pool.numPending++
-			}
-			go requester.redo() // pick another peer and ...
+			requester.redo()
 		}
 	}
 	delete(pool.peers, peerID)
@@ -309,7 +332,7 @@ func (pool *BlockPool) makeNextRequester() {
 	// request.SetLogger(pool.Logger.With("height", nextHeight))
 
 	pool.requesters[nextHeight] = request
-	pool.numPending++
+	atomic.AddInt32(&pool.numPending, 1)
 
 	err := request.Start()
 	if err != nil {
@@ -321,23 +344,23 @@ func (pool *BlockPool) requestersLen() int64 {
 	return int64(len(pool.requesters))
 }
 
-func (pool *BlockPool) sendRequest(height int64, peerID string) {
+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
+	pool.mtx.Lock()
 	defer pool.mtx.Unlock()
 
 	str := ""
@@ -357,7 +380,7 @@ func (pool *BlockPool) debug() string {
 
 type bpPeer struct {
 	pool        *BlockPool
-	id          string
+	id          p2p.ID
 	recvMonitor *flow.Monitor
 
 	height     int64
@@ -368,7 +391,7 @@ type bpPeer struct {
 	logger log.Logger
 }
 
-func newBPPeer(pool *BlockPool, peerID string, height int64) *bpPeer {
+func newBPPeer(pool *BlockPool, peerID p2p.ID, height int64) *bpPeer {
 	peer := &bpPeer{
 		pool:       pool,
 		id:         peerID,
@@ -391,9 +414,9 @@ func (peer *bpPeer) resetMonitor() {
 
 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)
 	}
 }
 
@@ -419,8 +442,9 @@ func (peer *bpPeer) onTimeout() {
 	peer.pool.mtx.Lock()
 	defer peer.pool.mtx.Unlock()
 
-	peer.pool.sendTimeout(peer.id)
-	peer.logger.Error("SendTimeout", "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
 }
 
@@ -434,7 +458,7 @@ type bpRequester struct {
 	redoCh     chan struct{}
 
 	mtx    sync.Mutex
-	peerID string
+	peerID p2p.ID
 	block  *types.Block
 }
 
@@ -442,8 +466,8 @@ func newBPRequester(pool *BlockPool, height int64) *bpRequester {
 	bpr := &bpRequester{
 		pool:       pool,
 		height:     height,
-		gotBlockCh: make(chan struct{}),
-		redoCh:     make(chan struct{}),
+		gotBlockCh: make(chan struct{}, 1),
+		redoCh:     make(chan struct{}, 1),
 
 		peerID: "",
 		block:  nil,
@@ -457,8 +481,8 @@ func (bpr *bpRequester) OnStart() error {
 	return nil
 }
 
-// Returns true if the peer matches
-func (bpr *bpRequester) setBlock(block *types.Block, peerID string) bool {
+// Returns true if the peer matches and block doesn't already exist.
+func (bpr *bpRequester) setBlock(block *types.Block, peerID p2p.ID) bool {
 	bpr.mtx.Lock()
 	if bpr.block != nil || bpr.peerID != peerID {
 		bpr.mtx.Unlock()
@@ -467,7 +491,10 @@ func (bpr *bpRequester) setBlock(block *types.Block, peerID string) bool {
 	bpr.block = block
 	bpr.mtx.Unlock()
 
-	bpr.gotBlockCh <- struct{}{}
+	select {
+	case bpr.gotBlockCh <- struct{}{}:
+	default:
+	}
 	return true
 }
 
@@ -477,23 +504,33 @@ 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
 }
 
+// This is called from the requestRoutine, upon redo().
 func (bpr *bpRequester) reset() {
 	bpr.mtx.Lock()
+	defer bpr.mtx.Unlock()
+
+	if bpr.block != nil {
+		atomic.AddInt32(&bpr.pool.numPending, 1)
+	}
+
 	bpr.peerID = ""
 	bpr.block = nil
-	bpr.mtx.Unlock()
 }
 
 // Tells bpRequester to pick another peer and try again.
-// NOTE: blocking
+// NOTE: Nonblocking, and does nothing if another redo
+// was already requested.
 func (bpr *bpRequester) redo() {
-	bpr.redoCh <- struct{}{}
+	select {
+	case bpr.redoCh <- struct{}{}:
+	default:
+	}
 }
 
 // Responsible for making more requests as necessary
@@ -502,7 +539,7 @@ 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() {
@@ -522,26 +559,21 @@ OUTER_LOOP:
 
 		// Send request and wait.
 		bpr.pool.sendRequest(bpr.height, peer.id)
-		select {
-		case <-bpr.pool.Quit:
-			bpr.Stop()
-			return
-		case <-bpr.Quit:
-			return
-		case <-bpr.redoCh:
-			bpr.reset()
-			continue OUTER_LOOP // When peer is removed
-		case <-bpr.gotBlockCh:
-			// We got the block, now see if it's good.
+	WAIT_LOOP:
+		for {
 			select {
-			case <-bpr.pool.Quit:
+			case <-bpr.pool.Quit():
 				bpr.Stop()
 				return
-			case <-bpr.Quit:
+			case <-bpr.Quit():
 				return
 			case <-bpr.redoCh:
 				bpr.reset()
 				continue OUTER_LOOP
+			case <-bpr.gotBlockCh:
+				// We got a block!
+				// Continue the for-loop and wait til Quit.
+				continue WAIT_LOOP
 			}
 		}
 	}
@@ -551,5 +583,5 @@ OUTER_LOOP:
 
 type BlockRequest struct {
 	Height int64
-	PeerID string
+	PeerID p2p.ID
 }

blockchain/pool_test.go

@@ -5,24 +5,26 @@ import (
 	"testing"
 	"time"
 
-	"github.com/tendermint/tendermint/types"
 	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
+	id     p2p.ID
 	height int64
 }
 
-func makePeers(numPeers int, minHeight, maxHeight int64) 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 := cmn.RandStr(12)
+		peerID := p2p.ID(cmn.RandStr(12))
 		height := minHeight + rand.Int63n(maxHeight-minHeight)
 		peers[peerID] = testPeer{peerID, height}
 	}
@@ -32,9 +34,9 @@ func makePeers(numPeers int, minHeight, maxHeight int64) map[string]testPeer {
 func TestBasic(t *testing.T) {
 	start := int64(42)
 	peers := makePeers(10, start+1, 1000)
-	timeoutsCh := make(chan string, 100)
-	requestsCh := make(chan BlockRequest, 100)
-	pool := NewBlockPool(start, requestsCh, timeoutsCh)
+	errorsCh := make(chan peerError, 1000)
+	requestsCh := make(chan BlockRequest, 1000)
+	pool := NewBlockPool(start, requestsCh, errorsCh)
 	pool.SetLogger(log.TestingLogger())
 
 	err := pool.Start()
@@ -69,8 +71,8 @@ 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:
 			t.Logf("Pulled new BlockRequest %v", request)
 			if request.Height == 300 {
@@ -89,9 +91,9 @@ func TestBasic(t *testing.T) {
 func TestTimeout(t *testing.T) {
 	start := int64(42)
 	peers := makePeers(10, start+1, 1000)
-	timeoutsCh := make(chan string, 100)
-	requestsCh := make(chan BlockRequest, 100)
-	pool := NewBlockPool(start, requestsCh, timeoutsCh)
+	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 {
@@ -127,12 +129,13 @@ func TestTimeout(t *testing.T) {
 
 	// Pull from channels
 	counter := 0
-	timedOut := map[string]struct{}{}
+	timedOut := map[p2p.ID]struct{}{}
 	for {
 		select {
-		case peerID := <-timeoutsCh:
-			t.Logf("Peer %v timeouted", 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!

blockchain/reactor.go

@@ -1,14 +1,12 @@
 package blockchain
 
 import (
-	"bytes"
-	"errors"
+	"fmt"
 	"reflect"
 	"time"
 
-	wire "github.com/tendermint/go-wire"
+	"github.com/tendermint/go-amino"
 	"github.com/tendermint/tendermint/p2p"
-	"github.com/tendermint/tendermint/proxy"
 	sm "github.com/tendermint/tendermint/state"
 	"github.com/tendermint/tendermint/types"
 	cmn "github.com/tendermint/tmlibs/common"
@@ -19,8 +17,7 @@ const (
 	// BlockchainChannel is a channel for blocks and status updates (`BlockStore` height)
 	BlockchainChannel = byte(0x40)
 
-	defaultChannelCapacity = 1000
-	trySyncIntervalMS      = 50
+	trySyncIntervalMS = 50
 	// stop syncing when last block's time is
 	// within this much of the system time.
 	// stopSyncingDurationMinutes = 10
@@ -29,49 +26,73 @@ const (
 	statusUpdateIntervalSeconds = 10
 	// check if we should switch to consensus reactor
 	switchToConsensusIntervalSeconds = 1
+
+	// 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, int)
+	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
 
-	state        *sm.State
-	proxyAppConn proxy.AppConnConsensus // same as consensus.proxyAppConn
-	store        *BlockStore
-	pool         *BlockPool
-	fastSync     bool
-	requestsCh   chan BlockRequest
-	timeoutsCh   chan string
+	// immutable
+	initialState sm.State
 
-	eventBus *types.EventBus
+	blockExec *sm.BlockExecutor
+	store     *BlockStore
+	pool      *BlockPool
+	fastSync  bool
+
+	requestsCh <-chan BlockRequest
+	errorsCh   <-chan peerError
 }
 
 // NewBlockchainReactor returns new reactor instance.
-func NewBlockchainReactor(state *sm.State, proxyAppConn proxy.AppConnConsensus, store *BlockStore, fastSync bool) *BlockchainReactor {
+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{
-		state:        state,
-		proxyAppConn: proxyAppConn,
+		initialState: state,
+		blockExec:    blockExec,
 		store:        store,
 		pool:         pool,
 		fastSync:     fastSync,
 		requestsCh:   requestsCh,
-		timeoutsCh:   timeoutsCh,
+		errorsCh:     errorsCh,
 	}
 	bcR.BaseReactor = *p2p.NewBaseReactor("BlockchainReactor", bcR)
 	return bcR
@@ -108,16 +129,19 @@ func (bcR *BlockchainReactor) OnStop() {
 func (bcR *BlockchainReactor) GetChannels() []*p2p.ChannelDescriptor {
 	return []*p2p.ChannelDescriptor{
 		{
-			ID:                BlockchainChannel,
-			Priority:          10,
-			SendQueueCapacity: 1000,
+			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()}}) {
+	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
@@ -126,38 +150,39 @@ func (bcR *BlockchainReactor) AddPeer(peer p2p.Peer) {
 
 // RemovePeer implements Reactor by removing peer from the pool.
 func (bcR *BlockchainReactor) RemovePeer(peer p2p.Peer, reason interface{}) {
-	bcR.pool.RemovePeer(peer.Key())
+	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) {
+func (bcR *BlockchainReactor) respondToPeer(msg *bcBlockRequestMessage,
+	src p2p.Peer) (queued bool) {
+
 	block := bcR.store.LoadBlock(msg.Height)
 	if block != nil {
-		msg := &bcBlockResponseMessage{Block: block}
-		return src.TrySend(BlockchainChannel, struct{ BlockchainMessage }{msg})
+		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)
 
-	return src.TrySend(BlockchainChannel, struct{ BlockchainMessage }{
-		&bcNoBlockResponseMessage{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, bcR.maxMsgSize())
+	msg, err := DecodeMessage(msgBytes)
 	if err != nil {
-		bcR.Logger.Error("Error decoding message", "err", err)
+		bcR.Logger.Error("Error decoding message", "src", src, "chId", chID, "msg", msg, "err", err, "bytes", msgBytes)
+		bcR.Switch.StopPeerForError(src, err)
 		return
 	}
 
 	bcR.Logger.Debug("Receive", "src", src, "chID", chID, "msg", msg)
 
-	// TODO: improve logic to satisfy megacheck
 	switch msg := msg.(type) {
 	case *bcBlockRequestMessage:
 		if queued := bcR.respondToPeer(msg, src); !queued {
@@ -165,27 +190,22 @@ func (bcR *BlockchainReactor) Receive(chID byte, src p2p.Peer, msgBytes []byte)
 		}
 	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:
 		bcR.Logger.Error(cmn.Fmt("Unknown message type %v", reflect.TypeOf(msg)))
 	}
 }
 
-// maxMsgSize returns the maximum allowable size of a
-// message on the blockchain reactor.
-func (bcR *BlockchainReactor) maxMsgSize() int {
-	return bcR.state.Params.BlockSizeParams.MaxBytes + 2
-}
-
 // Handle messages from the poolReactor telling the reactor what to do.
 // NOTE: Don't sleep in the FOR_LOOP or otherwise slow it down!
 // (Except for the SYNC_LOOP, which is the primary purpose and must be synchronous.)
@@ -197,7 +217,8 @@ func (bcR *BlockchainReactor) poolRoutine() {
 
 	blocksSynced := 0
 
-	chainID := bcR.state.ChainID
+	chainID := bcR.initialState.ChainID
+	state := bcR.initialState
 
 	lastHundred := time.Now()
 	lastRate := 0.0
@@ -205,23 +226,22 @@ func (bcR *BlockchainReactor) poolRoutine() {
 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:
 			// ask for status updates
@@ -236,7 +256,7 @@ FOR_LOOP:
 				bcR.pool.Stop()
 
 				conR := bcR.Switch.Reactor("CONSENSUS").(consensusReactor)
-				conR.SwitchToConsensus(bcR.state, blocksSynced)
+				conR.SwitchToConsensus(state, blocksSynced)
 
 				break FOR_LOOP
 			}
@@ -251,33 +271,39 @@ FOR_LOOP:
 					// We need both to sync the first block.
 					break SYNC_LOOP
 				}
-				firstParts := first.MakePartSet(bcR.state.Params.BlockPartSizeBytes)
+				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(
-					chainID, types.BlockID{first.Hash(), firstPartsHeader}, first.Height, second.LastCommit)
+				err := state.Validators.VerifyCommit(
+					chainID, firstID, first.Height, second.LastCommit)
 				if err != nil {
 					bcR.Logger.Error("Error in validation", "err", err)
-					bcR.pool.RedoRequest(first.Height)
+					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.eventBus, 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 += 1
+					blocksSynced++
 
 					if blocksSynced%100 == 0 {
 						lastRate = 0.9*lastRate + 0.1*(100/time.Since(lastHundred).Seconds())
@@ -288,7 +314,7 @@ FOR_LOOP:
 				}
 			}
 			continue FOR_LOOP
-		case <-bcR.Quit:
+		case <-bcR.Quit():
 			break FOR_LOOP
 		}
 	}
@@ -296,47 +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
 }
 
-// SetEventBus sets event bus.
-func (bcR *BlockchainReactor) SetEventBus(b *types.EventBus) {
-	bcR.eventBus = b
-}
-
 //-----------------------------------------------------------------------------
 // Messages
 
-const (
-	msgTypeBlockRequest    = byte(0x10)
-	msgTypeBlockResponse   = byte(0x11)
-	msgTypeNoBlockResponse = byte(0x12)
-	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{&bcNoBlockResponseMessage{}, msgTypeNoBlockResponse},
-	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, maxSize int) (msgType byte, msg BlockchainMessage, err error) {
-	msgType = bz[0]
-	n := int(0)
-	r := bytes.NewReader(bz)
-	msg = wire.ReadBinary(struct{ BlockchainMessage }{}, r, maxSize, &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
 }
@@ -361,7 +376,6 @@ func (brm *bcNoBlockResponseMessage) String() string {
 
 //-------------------------------------
 
-// NOTE: keep up-to-date with maxBlockchainResponseSize
 type bcBlockResponseMessage struct {
 	Block *types.Block
 }

blockchain/reactor_test.go

@@ -1,33 +1,44 @@
 package blockchain
 
 import (
+	"net"
 	"testing"
 
-	wire "github.com/tendermint/go-wire"
 	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 newBlockchainReactor(maxBlockHeight int64) *BlockchainReactor {
-	logger := log.TestingLogger()
+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
+}
 
-	blockStore := NewBlockStore(dbm.NewMemDB())
-
-	// Get State
-	state, _ := sm.GetState(dbm.NewMemDB(), config.GenesisFile())
-	state.SetLogger(logger.With("module", "state"))
-	state.Save()
+func newBlockchainReactor(logger log.Logger, maxBlockHeight int64) *BlockchainReactor {
+	state, blockStore := makeStateAndBlockStore(logger)
 
 	// Make the blockchainReactor itself
 	fastSync := true
-	bcReactor := NewBlockchainReactor(state.Copy(), nil, blockStore, fastSync)
+	var nilApp proxy.AppConnConsensus
+	blockExec := sm.NewBlockExecutor(dbm.NewMemDB(), log.TestingLogger(), nilApp,
+		sm.MockMempool{}, sm.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
@@ -37,22 +48,22 @@ func newBlockchainReactor(maxBlockHeight int64) *BlockchainReactor {
 	for blockHeight := int64(1); blockHeight <= maxBlockHeight; blockHeight++ {
 		firstBlock := makeBlock(blockHeight, state)
 		secondBlock := makeBlock(blockHeight+1, state)
-		firstParts := firstBlock.MakePartSet(state.Params.BlockGossipParams.BlockPartSizeBytes)
+		firstParts := firstBlock.MakePartSet(state.ConsensusParams.BlockGossip.BlockPartSizeBytes)
 		blockStore.SaveBlock(firstBlock, firstParts, secondBlock.LastCommit)
 	}
 
 	return bcReactor
 }
 
-func TestNoBlockMessageResponse(t *testing.T) {
+func TestNoBlockResponse(t *testing.T) {
 	maxBlockHeight := int64(20)
 
-	bcr := newBlockchainReactor(maxBlockHeight)
+	bcr := newBlockchainReactor(log.TestingLogger(), maxBlockHeight)
 	bcr.Start()
 	defer bcr.Stop()
 
 	// Add some peers in
-	peer := newbcrTestPeer(cmn.RandStr(12))
+	peer := newbcrTestPeer(p2p.ID(cmn.RandStr(12)))
 	bcr.AddPeer(peer)
 
 	chID := byte(0x01)
@@ -67,12 +78,13 @@ func TestNoBlockMessageResponse(t *testing.T) {
 		{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 := wire.BinaryBytes(struct{ BlockchainMessage }{reqBlockMsg})
+		reqBlockBytes := cdc.MustMarshalBinaryBare(reqBlockMsg)
 		bcr.Receive(chID, peer, reqBlockBytes)
-		value := peer.lastValue()
-		msg := value.(struct{ BlockchainMessage }).BlockchainMessage
+		msg := peer.lastBlockchainMessage()
 
 		if tt.existent {
 			if blockMsg, ok := msg.(*bcBlockResponseMessage); !ok {
@@ -90,6 +102,49 @@ func TestNoBlockMessageResponse(t *testing.T) {
 	}
 }
 
+/*
+// 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
 
@@ -100,52 +155,54 @@ func makeTxs(height int64) (txs []types.Tx) {
 	return txs
 }
 
-func makeBlock(height int64, state *sm.State) *types.Block {
-	prevHash := state.LastBlockID.Hash
-	prevParts := types.PartSetHeader{}
-	valHash := state.Validators.Hash()
-	prevBlockID := types.BlockID{prevHash, prevParts}
-	block, _ := types.MakeBlock(height, "test_chain", makeTxs(height),
-		new(types.Commit), prevBlockID, valHash, state.AppHash, state.Params.BlockGossipParams.BlockPartSizeBytes)
+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.Service
-	key string
-	ch  chan interface{}
+	cmn.BaseService
+	id p2p.ID
+	ch chan interface{}
 }
 
 var _ p2p.Peer = (*bcrTestPeer)(nil)
 
-func newbcrTestPeer(key string) *bcrTestPeer {
-	return &bcrTestPeer{
-		Service: cmn.NewBaseService(nil, "bcrTestPeer", nil),
-		key:     key,
-		ch:      make(chan interface{}, 2),
+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) lastValue() interface{} { return <-tp.ch }
+func (tp *bcrTestPeer) lastBlockchainMessage() interface{} { return <-tp.ch }
 
-func (tp *bcrTestPeer) TrySend(chID byte, value interface{}) bool {
-	if _, ok := value.(struct{ BlockchainMessage }).BlockchainMessage.(*bcStatusResponseMessage); ok {
+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 <- value
+		tp.ch <- msg
 	}
 	return true
 }
 
-func (tp *bcrTestPeer) Send(chID byte, data interface{}) bool { return tp.TrySend(chID, data) }
-func (tp *bcrTestPeer) NodeInfo() *p2p.NodeInfo               { return nil }
-func (tp *bcrTestPeer) Status() p2p.ConnectionStatus          { return p2p.ConnectionStatus{} }
-func (tp *bcrTestPeer) Key() string                           { return tp.key }
-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{})               {}
+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{})              {}
+func (tp *bcrTestPeer) RemoteIP() net.IP                     { return []byte{127, 0, 0, 1} }

blockchain/store.go

@@ -1,20 +1,17 @@
 package blockchain
 
 import (
-	"bytes"
-	"encoding/json"
 	"fmt"
-	"io"
 	"sync"
 
-	wire "github.com/tendermint/go-wire"
-	"github.com/tendermint/tendermint/types"
 	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
@@ -23,7 +20,7 @@ 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)
 
 // NOTE: BlockStore methods will panic if they encounter errors
 // deserializing loaded data, indicating probable corruption on disk.
@@ -35,6 +32,8 @@ type BlockStore struct {
 	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{
@@ -43,112 +42,113 @@ func NewBlockStore(db dbm.DB) *BlockStore {
 	}
 }
 
-// Height() returns the last known contiguous block height.
+// 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 {
-		return nil
-	}
-	return bytes.NewReader(bytez)
-}
-
+// 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 n int
-	var err error
-	r := bs.GetReader(calcBlockMetaKey(height))
-	if r == nil {
+	var blockMeta = bs.LoadBlockMeta(height)
+	if blockMeta == nil {
 		return nil
 	}
-	blockMeta := wire.ReadBinary(&types.BlockMeta{}, r, 0, &n, &err).(*types.BlockMeta)
-	if err != nil {
-		cmn.PanicCrisis(cmn.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 {
-		cmn.PanicCrisis(cmn.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
 }
 
+// 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 n int
-	var err error
-	r := bs.GetReader(calcBlockPartKey(height, index))
-	if r == nil {
+	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 {
-		cmn.PanicCrisis(cmn.Fmt("Error reading block part: %v", err))
+		panic(cmn.ErrorWrap(err, "Error reading block part"))
 	}
 	return part
 }
 
+// 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 n int
-	var err error
-	r := bs.GetReader(calcBlockMetaKey(height))
-	if r == nil {
+	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 {
-		cmn.PanicCrisis(cmn.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`.
+// 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 n int
-	var err error
-	r := bs.GetReader(calcBlockCommitKey(height))
-	if r == nil {
+	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 {
-		cmn.PanicCrisis(cmn.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`
+// 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 n int
-	var err error
-	r := bs.GetReader(calcSeenCommitKey(height))
-	if r == nil {
+	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 {
-		cmn.PanicCrisis(cmn.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 {
-		cmn.PanicSanity(cmn.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() {
 		cmn.PanicSanity(cmn.Fmt("BlockStore can only save complete block part sets"))
@@ -156,21 +156,22 @@ func (bs *BlockStore) SaveBlock(block *types.Block, blockParts *types.PartSet, s
 
 	// 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
@@ -189,7 +190,7 @@ func (bs *BlockStore) saveBlockPart(height int64, index int, part *types.Part) {
 	if height != bs.Height()+1 {
 		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)
 }
 
@@ -216,28 +217,31 @@ func calcSeenCommitKey(height int64) []byte {
 var blockStoreKey = []byte("blockStore")
 
 type BlockStoreStateJSON struct {
-	Height int64
+	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 {
 		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 {
-		cmn.PanicCrisis(cmn.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)
+
+	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 (
+	"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"
+
+	"github.com/tendermint/tendermint/privval"
+)
+
+func main() {
+	var (
+		addr        = flag.String("addr", ":26659", "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,
+	)
+
+	pv := privval.LoadFilePV(*privValPath)
+
+	rs := privval.NewRemoteSigner(
+		logger,
+		*chainID,
+		*addr,
+		pv,
+		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

@@ -1,12 +1,11 @@
 package commands
 
 import (
-	"encoding/json"
 	"fmt"
 
 	"github.com/spf13/cobra"
 
-	"github.com/tendermint/tendermint/types"
+	"github.com/tendermint/tendermint/privval"
 )
 
 // GenValidatorCmd allows the generation of a keypair for a
@@ -18,11 +17,11 @@ var GenValidatorCmd = &cobra.Command{
 }
 
 func genValidator(cmd *cobra.Command, args []string) {
-	privValidator := types.GenPrivValidatorFS("")
-	privValidatorJSONBytes, err := json.MarshalIndent(privValidator, "", "\t")
+	pv := privval.GenFilePV("")
+	jsbz, err := cdc.MarshalJSON(pv)
 	if err != nil {
 		panic(err)
 	}
 	fmt.Printf(`%v
-`, string(privValidatorJSONBytes))
+`, string(jsbz))
 }

cmd/tendermint/commands/init.go

@@ -1,10 +1,13 @@
 package commands
 
 import (
-	"os"
+	"time"
 
 	"github.com/spf13/cobra"
 
+	cfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tendermint/p2p"
+	"github.com/tendermint/tendermint/privval"
 	"github.com/tendermint/tendermint/types"
 	cmn "github.com/tendermint/tmlibs/common"
 )
@@ -13,33 +16,55 @@ import (
 var InitFilesCmd = &cobra.Command{
 	Use:   "init",
 	Short: "Initialize Tendermint",
-	Run:   initFiles,
+	RunE:  initFiles,
 }
 
-func initFiles(cmd *cobra.Command, args []string) {
+func initFiles(cmd *cobra.Command, args []string) error {
+	return initFilesWithConfig(config)
+}
+
+func initFilesWithConfig(config *cfg.Config) error {
+	// private validator
 	privValFile := config.PrivValidatorFile()
-	if _, err := os.Stat(privValFile); os.IsNotExist(err) {
-		privValidator := types.GenPrivValidatorFS(privValFile)
-		privValidator.Save()
-
-		genFile := config.GenesisFile()
-
-		if _, err := os.Stat(genFile); os.IsNotExist(err) {
-			genDoc := types.GenesisDoc{
-				ChainID: cmn.Fmt("test-chain-%v", cmn.RandStr(6)),
-			}
-			genDoc.Validators = []types.GenesisValidator{{
-				PubKey: privValidator.GetPubKey(),
-				Power:  10,
-			}}
-
-			if err := genDoc.SaveAs(genFile); err != nil {
-				panic(err)
-			}
-		}
-
-		logger.Info("Initialized tendermint", "genesis", config.GenesisFile(), "priv_validator", config.PrivValidatorFile())
+	var pv *privval.FilePV
+	if cmn.FileExists(privValFile) {
+		pv = privval.LoadFilePV(privValFile)
+		logger.Info("Found private validator", "path", privValFile)
 	} else {
-		logger.Info("Already initialized", "priv_validator", config.PrivValidatorFile())
+		pv = privval.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)),
+			GenesisTime: time.Now(),
+		}
+		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:26657", "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

@@ -1,7 +1,6 @@
 package commands
 
 import (
-	"encoding/json"
 	"fmt"
 
 	"github.com/spf13/cobra"
@@ -19,10 +18,10 @@ var ProbeUpnpCmd = &cobra.Command{
 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 {
 			return err
 		}

cmd/tendermint/commands/reset_priv_validator.go

@@ -5,7 +5,7 @@ import (
 
 	"github.com/spf13/cobra"
 
-	"github.com/tendermint/tendermint/types"
+	"github.com/tendermint/tendermint/privval"
 	"github.com/tendermint/tmlibs/log"
 )
 
@@ -13,49 +13,57 @@ import (
 // instance.
 var ResetAllCmd = &cobra.Command{
 	Use:   "unsafe_reset_all",
-	Short: "(unsafe) Remove all the data and WAL, reset this node's validator",
+	Short: "(unsafe) Remove all the data and WAL, reset this node's validator to genesis state",
 	Run:   resetAll,
 }
 
 // ResetPrivValidatorCmd resets the private validator files.
 var ResetPrivValidatorCmd = &cobra.Command{
 	Use:   "unsafe_reset_priv_validator",
-	Short: "(unsafe) Reset this node's validator",
+	Short: "(unsafe) Reset this node's validator to genesis state",
 	Run:   resetPrivValidator,
 }
 
-// ResetAll removes the privValidator files.
-// Exported so other CLI tools can use it.
-func ResetAll(dbDir, privValFile string, logger log.Logger) {
-	resetPrivValidatorFS(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.DBDir(), config.PrivValidatorFile(), logger)
+	ResetAll(config.DBDir(), config.P2P.AddrBookFile(), config.PrivValidatorFile(), logger)
 }
 
 // XXX: this is totally unsafe.
 // it's only suitable for testnets.
 func resetPrivValidator(cmd *cobra.Command, args []string) {
-	resetPrivValidatorFS(config.PrivValidatorFile(), logger)
+	resetFilePV(config.PrivValidatorFile(), logger)
 }
 
-func resetPrivValidatorFS(privValFile string, logger log.Logger) {
-	// Get PrivValidator
-	if _, err := os.Stat(privValFile); err == nil {
-		privValidator := types.LoadPrivValidatorFS(privValFile)
-		privValidator.Reset()
-		logger.Info("Reset PrivValidator", "file", privValFile)
+// ResetAll removes the privValidator and address book files plus all data.
+// Exported so other CLI tools can use it.
+func ResetAll(dbDir, addrBookFile, privValFile string, logger log.Logger) {
+	resetFilePV(privValFile, logger)
+	removeAddrBook(addrBookFile, logger)
+	if err := os.RemoveAll(dbDir); err == nil {
+		logger.Info("Removed all blockchain history", "dir", dbDir)
 	} else {
-		privValidator := types.GenPrivValidatorFS(privValFile)
-		privValidator.Save()
-		logger.Info("Generated PrivValidator", "file", privValFile)
+		logger.Error("Error removing all blockchain history", "dir", dbDir, "err", err)
+	}
+}
+
+func resetFilePV(privValFile string, logger log.Logger) {
+	if _, err := os.Stat(privValFile); err == nil {
+		pv := privval.LoadFilePV(privValFile)
+		pv.Reset()
+		logger.Info("Reset private validator file to genesis state", "file", privValFile)
+	} else {
+		pv := privval.GenFilePV(privValFile)
+		pv.Save()
+		logger.Info("Generated private validator file", "file", privValFile)
+	}
+}
+
+func removeAddrBook(addrBookFile string, logger log.Logger) {
+	if err := os.Remove(addrBookFile); err == nil {
+		logger.Info("Removed existing address book", "file", addrBookFile)
+	} else if !os.IsNotExist(err) {
+		logger.Info("Error removing address book", "file", addrBookFile, "err", err)
 	}
 }

cmd/tendermint/commands/root.go

@@ -14,11 +14,15 @@ import (
 
 var (
 	config = cfg.DefaultConfig()
-	logger = log.NewTMLogger(log.NewSyncWriter(os.Stdout)).With("module", "main")
+	logger = log.NewTMLogger(log.NewSyncWriter(os.Stdout))
 )
 
 func init() {
-	RootCmd.PersistentFlags().String("log_level", config.LogLevel, "Log level")
+	registerFlagsRootCmd(RootCmd)
+}
+
+func registerFlagsRootCmd(cmd *cobra.Command) {
+	cmd.PersistentFlags().String("log_level", config.LogLevel, "Log level")
 }
 
 // ParseConfig retrieves the default environment configuration,
@@ -53,6 +57,7 @@ var RootCmd = &cobra.Command{
 		if viper.GetBool(cli.TraceFlag) {
 			logger = log.NewTracingLogger(logger)
 		}
+		logger = logger.With("module", "main")
 		return nil
 	},
 }

cmd/tendermint/commands/root_test.go

@@ -1,7 +1,10 @@
 package commands
 
 import (
+	"fmt"
+	"io/ioutil"
 	"os"
+	"path/filepath"
 	"strconv"
 	"testing"
 
@@ -12,6 +15,7 @@ import (
 
 	cfg "github.com/tendermint/tendermint/config"
 	"github.com/tendermint/tmlibs/cli"
+	cmn "github.com/tendermint/tmlibs/common"
 )
 
 var (
@@ -22,10 +26,8 @@ const (
 	rootName = "root"
 )
 
-// isolate provides a clean setup and returns a copy of RootCmd you can
-// modify in the test cases.
-// NOTE: it unsets all TM* env variables.
-func isolate(cmds ...*cobra.Command) cli.Executable {
+// clearConfig clears env vars, the given root dir, and resets viper.
+func clearConfig(dir string) {
 	if err := os.Unsetenv("TMHOME"); err != nil {
 		panic(err)
 	}
@@ -33,75 +35,142 @@ func isolate(cmds ...*cobra.Command) cli.Executable {
 		panic(err)
 	}
 
+	if err := os.RemoveAll(dir); err != nil {
+		panic(err)
+	}
 	viper.Reset()
 	config = cfg.DefaultConfig()
-	r := &cobra.Command{
-		Use:               rootName,
-		PersistentPreRunE: RootCmd.PersistentPreRunE,
-	}
-	r.AddCommand(cmds...)
-	wr := cli.PrepareBaseCmd(r, "TM", defaultRoot)
-	return wr
 }
 
-func TestRootConfig(t *testing.T) {
-	assert, require := assert.New(t), require.New(t)
-
-	// we pre-create a config file we can refer to in the rest of
-	// the test cases.
-	cvals := map[string]string{
-		"moniker":   "monkey",
-		"fast_sync": "false",
+// prepare new rootCmd
+func testRootCmd() *cobra.Command {
+	rootCmd := &cobra.Command{
+		Use:               RootCmd.Use,
+		PersistentPreRunE: RootCmd.PersistentPreRunE,
+		Run:               func(cmd *cobra.Command, args []string) {},
 	}
-	// proper types of the above settings
-	cfast := false
-	conf, err := cli.WriteDemoConfig(cvals)
-	require.Nil(err)
+	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()
-	dmax := defaults.P2P.MaxNumPeers
+	defaultLogLvl := defaults.LogLevel
 
 	cases := []struct {
 		args     []string
 		env      map[string]string
-		root     string
-		moniker  string
-		fastSync bool
-		maxPeer  int
+		logLevel string
 	}{
-		{nil, nil, defaultRoot, defaults.Moniker, defaults.FastSync, dmax},
-		// try multiple ways of setting root (two flags, cli vs. env)
-		{[]string{"--home", conf}, nil, conf, cvals["moniker"], cfast, dmax},
-		{nil, map[string]string{"TMHOME": conf}, conf, cvals["moniker"], cfast, dmax},
-		// check setting p2p subflags two different ways
-		{[]string{"--p2p.max_num_peers", "420"}, nil, defaultRoot, defaults.Moniker, defaults.FastSync, 420},
-		{nil, map[string]string{"TM_P2P_MAX_NUM_PEERS": "17"}, defaultRoot, defaults.Moniker, defaults.FastSync, 17},
-		// try to set env that have no flags attached...
-		{[]string{"--home", conf}, map[string]string{"TM_MONIKER": "funny"}, conf, "funny", cfast, dmax},
+		{[]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 idx, tc := range cases {
-		i := strconv.Itoa(idx)
-		// test command that does nothing, except trigger unmarshalling in root
-		noop := &cobra.Command{
-			Use: "noop",
-			RunE: func(cmd *cobra.Command, args []string) error {
-				return nil
-			},
-		}
-		noop.Flags().Int("p2p.max_num_peers", defaults.P2P.MaxNumPeers, "")
-		cmd := isolate(noop)
+	for i, tc := range cases {
+		idxString := strconv.Itoa(i)
 
-		args := append([]string{rootName, noop.Use}, tc.args...)
-		err := cli.RunWithArgs(cmd, args, tc.env)
-		require.Nil(err, i)
-		assert.Equal(tc.root, config.RootDir, i)
-		assert.Equal(tc.root, config.P2P.RootDir, i)
-		assert.Equal(tc.root, config.Consensus.RootDir, i)
-		assert.Equal(tc.root, config.Mempool.RootDir, i)
-		assert.Equal(tc.moniker, config.Moniker, i)
-		assert.Equal(tc.fastSync, config.FastSync, i)
-		assert.Equal(tc.maxPeer, config.P2P.MaxNumPeers, 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

@@ -14,11 +14,14 @@ 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 'dummy' for local testing.")
+	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
@@ -28,16 +31,19 @@ func AddNodeFlags(cmd *cobra.Command) {
 
 	// 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 host:port seed nodes")
+	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 Peer-Exchange (dev feature)")
+	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")
 }
 
-// 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.
+// 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",
@@ -51,9 +57,8 @@ func NewRunNodeCmd(nodeProvider nm.NodeProvider) *cobra.Command {
 
 			if err := n.Start(); err != nil {
 				return fmt.Errorf("Failed to start node: %v", err)
-			} else {
-				logger.Info("Started node", "nodeInfo", n.Switch().NodeInfo())
 			}
+			logger.Info("Started node", "nodeInfo", n.Switch().NodeInfo())
 
 			// Trap signal, run forever.
 			n.RunForever()

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

@@ -5,8 +5,7 @@ import (
 
 	"github.com/spf13/cobra"
 
-	"github.com/tendermint/go-wire/data"
-	"github.com/tendermint/tendermint/types"
+	"github.com/tendermint/tendermint/privval"
 )
 
 // ShowValidatorCmd adds capabilities for showing the validator info.
@@ -17,7 +16,7 @@ var ShowValidatorCmd = &cobra.Command{
 }
 
 func showValidator(cmd *cobra.Command, args []string) {
-	privValidator := types.LoadOrGenPrivValidatorFS(config.PrivValidatorFile())
-	pubKeyJSONBytes, _ := data.ToJSON(privValidator.PubKey)
+	privValidator := privval.LoadOrGenFilePV(config.PrivValidatorFile())
+	pubKeyJSONBytes, _ := cdc.MarshalJSON(privValidator.GetPubKey())
 	fmt.Println(string(pubKeyJSONBytes))
 }

cmd/tendermint/commands/testnet.go

@@ -2,57 +2,114 @@ package commands
 
 import (
 	"fmt"
-	"path"
+	"net"
+	"os"
+	"path/filepath"
+	"strings"
 	"time"
 
 	"github.com/spf13/cobra"
 
+	cfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tendermint/p2p"
+	"github.com/tendermint/tendermint/privval"
 	"github.com/tendermint/tendermint/types"
 	cmn "github.com/tendermint/tmlibs/common"
 )
 
-//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, ...)")
+
+	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@node0:26656, ID1@node1:26656, ...)")
+	TestnetFilesCmd.Flags().StringVar(&startingIPAddress, "starting-ip-address", "",
+		"Starting IP address (192.168.0.1 results in persistent peers list ID0@192.168.0.1:26656, ID1@192.168.0.2:26656, ...)")
+	TestnetFilesCmd.Flags().IntVar(&p2pPort, "p2p-port", 26656,
+		"P2P Port")
 }
 
-// TestnetFilesCmd allows initialisation of files for a
-// Tendermint testnet.
+// TestnetFilesCmd allows initialisation of files for a Tendermint testnet.
 var TestnetFilesCmd = &cobra.Command{
 	Use:   "testnet",
 	Short: "Initialize files for a Tendermint testnet",
-	Run:   testnetFiles,
+	Long: `testnet will create "v" + "n" number of directories and populate each with
+necessary files (private validator, genesis, config, etc.).
+
+Note, strict routability for addresses is turned off in the config file.
+
+Optionally, it will fill in persistent_peers list in config file using either hostnames or IPs.
+
+Example:
+
+	tendermint testnet --v 4 --o ./output --populate-persistent-peers --starting-ip-address 192.168.10.2
+	`,
+	RunE: testnetFiles,
 }
 
-func testnetFiles(cmd *cobra.Command, args []string) {
-
+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.LoadPrivValidatorFS(privValFile)
+
+		initFilesWithConfig(config)
+
+		pvFile := filepath.Join(nodeDir, config.BaseConfig.PrivValidator)
+		pv := privval.LoadFilePV(pvFile)
 		genVals[i] = types.GenesisValidator{
-			PubKey: privVal.GetPubKey(),
+			PubKey: pv.GetPubKey(),
 			Power:  1,
-			Name:   mach,
+			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(),
@@ -61,34 +118,66 @@ func testnetFiles(cmd *cobra.Command, args []string) {
 	}
 
 	// Write genesis file.
-	for i := 0; i < nValidators; i++ {
-		mach := cmn.Fmt("mach%d", i)
-		if err := genDoc.SaveAs(path.Join(dataDir, mach, "genesis.json")); err != nil {
-			panic(err)
+	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.GenPrivValidatorFS(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
+		config.P2P.AddrBookStrict = false
+
+		// overwrite default config
+		cfg.WriteConfigFile(filepath.Join(nodeDir, "config", "config.toml"), config)
+	}
+
+	return nil
 }

cmd/tendermint/commands/wire.go

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

cmd/tendermint/main.go

@@ -2,10 +2,12 @@ package main
 
 import (
 	"os"
+	"path/filepath"
 
 	"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"
 )
 
@@ -15,12 +17,15 @@ func main() {
 		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:
@@ -36,7 +41,7 @@ func main() {
 	// Create & start node
 	rootCmd.AddCommand(cmd.NewRunNodeCmd(nodeFunc))
 
-	cmd := cli.PrepareBaseCmd(rootCmd, "TM", os.ExpandEnv("$HOME/.tendermint"))
+	cmd := cli.PrepareBaseCmd(rootCmd, "TM", os.ExpandEnv(filepath.Join("$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

@@ -2,10 +2,43 @@ package config
 
 import (
 	"fmt"
+	"os"
 	"path/filepath"
 	"time"
 )
 
+const (
+	// FuzzModeDrop is a mode in which we randomly drop reads/writes, connections or sleep
+	FuzzModeDrop = iota
+	// FuzzModeDelay is a mode in which we randomly sleep
+	FuzzModeDelay
+)
+
+// 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
@@ -37,9 +70,9 @@ func TestConfig() *Config {
 		BaseConfig: TestBaseConfig(),
 		RPC:        TestRPCConfig(),
 		P2P:        TestP2PConfig(),
-		Mempool:    DefaultMempoolConfig(),
+		Mempool:    TestMempoolConfig(),
 		Consensus:  TestConsensusConfig(),
-		TxIndex:    DefaultTxIndexConfig(),
+		TxIndex:    TestTxIndexConfig(),
 	}
 }
 
@@ -58,22 +91,30 @@ func (cfg *Config) SetRoot(root string) *Config {
 
 // 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"`
 
-	// The ID of the chain to join (should be signed with every transaction and vote)
-	ChainID string `mapstructure:"chain_id"`
-
-	// A JSON file containing the initial validator set and other meta data
+	// Path to the JSON file containing the initial validator set and other meta data
 	Genesis string `mapstructure:"genesis_file"`
 
-	// A JSON file containing the private key to use as a validator in the consensus protocol
+	// 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"`
@@ -106,10 +147,11 @@ type BaseConfig struct {
 // DefaultBaseConfig returns a default base configuration for a Tendermint node
 func DefaultBaseConfig() BaseConfig {
 	return BaseConfig{
-		Genesis:           "genesis.json",
-		PrivValidator:     "priv_validator.json",
-		Moniker:           "anonymous",
-		ProxyApp:          "tcp://127.0.0.1:46658",
+		Genesis:           defaultGenesisJSONPath,
+		PrivValidator:     defaultPrivValPath,
+		NodeKey:           defaultNodeKeyPath,
+		Moniker:           defaultMoniker,
+		ProxyApp:          "tcp://127.0.0.1:26658",
 		ABCI:              "socket",
 		LogLevel:          DefaultPackageLogLevels(),
 		ProfListenAddress: "",
@@ -122,27 +164,36 @@ func DefaultBaseConfig() BaseConfig {
 
 // TestBaseConfig returns a base configuration for testing a Tendermint node
 func TestBaseConfig() BaseConfig {
-	conf := DefaultBaseConfig()
-	conf.ChainID = "tendermint_test"
-	conf.ProxyApp = "dummy"
-	conf.FastSync = false
-	conf.DBBackend = "memdb"
-	return conf
+	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 (b BaseConfig) GenesisFile() string {
-	return rootify(b.Genesis, b.RootDir)
+func (cfg BaseConfig) GenesisFile() string {
+	return rootify(cfg.Genesis, cfg.RootDir)
 }
 
 // PrivValidatorFile returns the full path to the priv_validator.json file
-func (b BaseConfig) PrivValidatorFile() string {
-	return rootify(b.PrivValidator, b.RootDir)
+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 (b BaseConfig) DBDir() string {
-	return rootify(b.DBPath, b.RootDir)
+func (cfg BaseConfig) DBDir() string {
+	return rootify(cfg.DBPath, cfg.RootDir)
 }
 
 // DefaultLogLevel returns a default log level of "error"
@@ -150,9 +201,10 @@ func DefaultLogLevel() string {
 	return "error"
 }
 
-// DefaultPackageLogLevels returns a default log level setting so all packages log at "error", while the `state` package logs at "info"
+// 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("state:info,*:%s", DefaultLogLevel())
+	return fmt.Sprintf("main:info,state:info,*:%s", DefaultLogLevel())
 }
 
 //-----------------------------------------------------------------------------
@@ -169,14 +221,14 @@ type RPCConfig struct {
 	// NOTE: This server only supports /broadcast_tx_commit
 	GRPCListenAddress string `mapstructure:"grpc_laddr"`
 
-	// Activate unsafe RPC commands like /dial_seeds and /unsafe_flush_mempool
+	// 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",
+		ListenAddress:     "tcp://0.0.0.0:26657",
 		GRPCListenAddress: "",
 		Unsafe:            false,
 	}
@@ -184,11 +236,11 @@ func DefaultRPCConfig() *RPCConfig {
 
 // TestRPCConfig returns a configuration for testing the RPC server
 func TestRPCConfig() *RPCConfig {
-	conf := DefaultRPCConfig()
-	conf.ListenAddress = "tcp://0.0.0.0:36657"
-	conf.GRPCListenAddress = "tcp://0.0.0.0:36658"
-	conf.Unsafe = true
-	return conf
+	cfg := DefaultRPCConfig()
+	cfg.ListenAddress = "tcp://0.0.0.0:36657"
+	cfg.GRPCListenAddress = "tcp://0.0.0.0:36658"
+	cfg.Unsafe = true
+	return cfg
 }
 
 //-----------------------------------------------------------------------------
@@ -202,8 +254,13 @@ type P2PConfig struct {
 	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"`
 
@@ -213,9 +270,6 @@ type P2PConfig struct {
 	// Set true for strict address routability rules
 	AddrBookStrict bool `mapstructure:"addr_book_strict"`
 
-	// Set true to enable the peer-exchange reactor
-	PexReactor bool `mapstructure:"pex"`
-
 	// Maximum number of peers to connect to
 	MaxNumPeers int `mapstructure:"max_num_peers"`
 
@@ -223,40 +277,97 @@ type P2PConfig struct {
 	FlushThrottleTimeout int `mapstructure:"flush_throttle_timeout"`
 
 	// Maximum size of a message packet payload, in bytes
-	MaxMsgPacketPayloadSize int `mapstructure:"max_msg_packet_payload_size"`
+	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"`
+
+	// Comma separated list of peer IDs to keep private (will not be gossiped to
+	// other peers)
+	PrivatePeerIDs string `mapstructure:"private_peer_ids"`
+
+	// Toggle to disable guard against peers connecting from the same ip.
+	AllowDuplicateIP bool `mapstructure:"allow_duplicate_ip"`
+
+	// Peer connection configuration.
+	HandshakeTimeout time.Duration `mapstructure:"handshake_timeout"`
+	DialTimeout      time.Duration `mapstructure:"dial_timeout"`
+
+	// Testing params.
+	// Force dial to fail
+	TestDialFail bool `mapstructure:"test_dial_fail"`
+	// FUzz connection
+	TestFuzz       bool            `mapstructure:"test_fuzz"`
+	TestFuzzConfig *FuzzConnConfig `mapstructure:"test_fuzz_config"`
 }
 
 // DefaultP2PConfig returns a default configuration for the peer-to-peer layer
 func DefaultP2PConfig() *P2PConfig {
 	return &P2PConfig{
-		ListenAddress:           "tcp://0.0.0.0:46656",
-		AddrBook:                "addrbook.json",
+		ListenAddress:           "tcp://0.0.0.0:26656",
+		AddrBook:                defaultAddrBookPath,
 		AddrBookStrict:          true,
 		MaxNumPeers:             50,
 		FlushThrottleTimeout:    100,
-		MaxMsgPacketPayloadSize: 1024,   // 1 kB
+		MaxPacketMsgPayloadSize: 1024,   // 1 kB
 		SendRate:                512000, // 500 kB/s
 		RecvRate:                512000, // 500 kB/s
+		PexReactor:              true,
+		SeedMode:                false,
+		AllowDuplicateIP:        true, // so non-breaking yet
+		HandshakeTimeout:        20 * time.Second,
+		DialTimeout:             3 * time.Second,
+		TestDialFail:            false,
+		TestFuzz:                false,
+		TestFuzzConfig:          DefaultFuzzConnConfig(),
 	}
 }
 
 // TestP2PConfig returns a configuration for testing the peer-to-peer layer
 func TestP2PConfig() *P2PConfig {
-	conf := DefaultP2PConfig()
-	conf.ListenAddress = "tcp://0.0.0.0:36656"
-	conf.SkipUPNP = true
-	return conf
+	cfg := DefaultP2PConfig()
+	cfg.ListenAddress = "tcp://0.0.0.0:36656"
+	cfg.SkipUPNP = true
+	cfg.FlushThrottleTimeout = 10
+	cfg.AllowDuplicateIP = true
+	return cfg
 }
 
 // AddrBookFile returns the full path to the address book
-func (p *P2PConfig) AddrBookFile() string {
-	return rootify(p.AddrBook, p.RootDir)
+func (cfg *P2PConfig) AddrBookFile() string {
+	return rootify(cfg.AddrBook, cfg.RootDir)
+}
+
+// FuzzConnConfig is a FuzzedConnection configuration.
+type FuzzConnConfig struct {
+	Mode         int
+	MaxDelay     time.Duration
+	ProbDropRW   float64
+	ProbDropConn float64
+	ProbSleep    float64
+}
+
+// DefaultFuzzConnConfig returns the default config.
+func DefaultFuzzConnConfig() *FuzzConnConfig {
+	return &FuzzConnConfig{
+		Mode:         FuzzModeDrop,
+		MaxDelay:     3 * time.Second,
+		ProbDropRW:   0.2,
+		ProbDropConn: 0.00,
+		ProbSleep:    0.00,
+	}
 }
 
 //-----------------------------------------------------------------------------
@@ -269,6 +380,8 @@ type MempoolConfig struct {
 	RecheckEmpty bool   `mapstructure:"recheck_empty"`
 	Broadcast    bool   `mapstructure:"broadcast"`
 	WalPath      string `mapstructure:"wal_dir"`
+	Size         int    `mapstructure:"size"`
+	CacheSize    int    `mapstructure:"cache_size"`
 }
 
 // DefaultMempoolConfig returns a default configuration for the Tendermint mempool
@@ -277,13 +390,22 @@ func DefaultMempoolConfig() *MempoolConfig {
 		Recheck:      true,
 		RecheckEmpty: true,
 		Broadcast:    true,
-		WalPath:      "data/mempool.wal",
+		WalPath:      filepath.Join(defaultDataDir, "mempool.wal"),
+		Size:         100000,
+		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 (m *MempoolConfig) WalDir() string {
-	return rootify(m.WalPath, m.RootDir)
+func (cfg *MempoolConfig) WalDir() string {
+	return rootify(cfg.WalPath, cfg.RootDir)
 }
 
 //-----------------------------------------------------------------------------
@@ -292,12 +414,11 @@ func (m *MempoolConfig) WalDir() string {
 // 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
+	RootDir string `mapstructure:"home"`
+	WalPath string `mapstructure:"wal_file"`
+	walFile string // overrides WalPath if set
 
-	// All timeouts are in ms
+	// All timeouts are in milliseconds
 	TimeoutPropose        int `mapstructure:"timeout_propose"`
 	TimeoutProposeDelta   int `mapstructure:"timeout_propose_delta"`
 	TimeoutPrevote        int `mapstructure:"timeout_prevote"`
@@ -317,11 +438,48 @@ type ConsensusConfig struct {
 	CreateEmptyBlocks         bool `mapstructure:"create_empty_blocks"`
 	CreateEmptyBlocksInterval int  `mapstructure:"create_empty_blocks_interval"`
 
-	// Reactor sleep duration parameters are in ms
+	// 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"),
+		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
@@ -362,53 +520,17 @@ func (cfg *ConsensusConfig) PeerQueryMaj23Sleep() time.Duration {
 	return time.Duration(cfg.PeerQueryMaj23SleepDuration) * time.Millisecond
 }
 
-// DefaultConsensusConfig returns a default configuration for the consensus service
-func DefaultConsensusConfig() *ConsensusConfig {
-	return &ConsensusConfig{
-		WalPath:                     "data/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 {
-	config := DefaultConsensusConfig()
-	config.TimeoutPropose = 2000
-	config.TimeoutProposeDelta = 1
-	config.TimeoutPrevote = 10
-	config.TimeoutPrevoteDelta = 1
-	config.TimeoutPrecommit = 10
-	config.TimeoutPrecommitDelta = 1
-	config.TimeoutCommit = 10
-	config.SkipTimeoutCommit = true
-	return config
-}
-
 // WalFile returns the full path to the write-ahead log file
-func (c *ConsensusConfig) WalFile() string {
-	if c.walFile != "" {
-		return c.walFile
+func (cfg *ConsensusConfig) WalFile() string {
+	if cfg.walFile != "" {
+		return cfg.walFile
 	}
-	return rootify(c.WalPath, c.RootDir)
+	return rootify(cfg.WalPath, cfg.RootDir)
 }
 
 // SetWalFile sets the path to the write-ahead log file
-func (c *ConsensusConfig) SetWalFile(walFile string) {
-	c.walFile = walFile
+func (cfg *ConsensusConfig) SetWalFile(walFile string) {
+	cfg.walFile = walFile
 }
 
 //-----------------------------------------------------------------------------
@@ -446,6 +568,11 @@ func DefaultTxIndexConfig() *TxIndexConfig {
 	}
 }
 
+// TestTxIndexConfig returns a default configuration for the transaction indexer.
+func TestTxIndexConfig() *TxIndexConfig {
+	return DefaultTxIndexConfig()
+}
+
 //-----------------------------------------------------------------------------
 // Utils
 
@@ -456,3 +583,18 @@ func rootify(path, root string) string {
 	}
 	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/toml.go

@@ -1,54 +1,238 @@
 package config
 
 import (
+	"bytes"
 	"os"
-	"path"
 	"path/filepath"
-	"strings"
+	"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(rootDir+"/data", 0700); err != nil {
+	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 := path.Join(rootDir, "config.toml")
+	configFilePath := filepath.Join(rootDir, defaultConfigFilePath)
 
 	// Write default config file if missing.
 	if !cmn.FileExists(configFilePath) {
-		// Ask user for moniker
-		// moniker := cfg.Prompt("Type hostname: ", "anonymous")
-		cmn.MustWriteFile(configFilePath, []byte(defaultConfig("anonymous")), 0644)
+		writeDefaultConfigFile(configFilePath)
 	}
 }
 
-var defaultConfigTmpl = `# This is a TOML config file.
+// 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 writeDefaultConfigFile(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
 
-proxy_app = "tcp://127.0.0.1:46658"
-moniker = "__MONIKER__"
-fast_sync = true
-db_backend = "leveldb"
-log_level = "state:info,*:error"
+##### 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 = "{{ js .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 = "{{ js .BaseConfig.Genesis }}"
+
+# Path to the JSON file containing the private key to use as a validator in the consensus protocol
+priv_validator_file = "{{ js .BaseConfig.PrivValidator }}"
+
+# Path to the JSON file containing the private key to use for node authentication in the p2p protocol
+node_key_file = "{{ js .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]
-laddr = "tcp://0.0.0.0:46657"
 
+# 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]
-laddr = "tcp://0.0.0.0:46656"
-seeds = ""
-`
 
-func defaultConfig(moniker string) string {
-	return strings.Replace(defaultConfigTmpl, "__MONIKER__", moniker, -1)
-}
+# 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 = "{{ js .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 }}
+
+# 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 = "{{ js .Mempool.WalPath }}"
+
+# size of the mempool
+size = {{ .Mempool.Size }}
+
+# size of the cache (used to filter transactions we saw earlier)
+cache_size = {{ .Mempool.CacheSize }}
+
+##### consensus configuration options #####
+[consensus]
+
+wal_file = "{{ js .Consensus.WalPath }}"
+
+# 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 ***********/
 
@@ -71,18 +255,21 @@ func ResetTestRoot(testName string) *Config {
 	if err := cmn.EnsureDir(rootDir, 0700); err != nil {
 		cmn.PanicSanity(err.Error())
 	}
-	if err := cmn.EnsureDir(rootDir+"/data", 0700); err != nil {
+	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 := path.Join(rootDir, "config.toml")
-	genesisFilePath := path.Join(rootDir, "genesis.json")
-	privFilePath := path.Join(rootDir, "priv_validator.json")
+	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) {
-		// Ask user for moniker
-		cmn.MustWriteFile(configFilePath, []byte(testConfig("anonymous")), 0644)
+		writeDefaultConfigFile(configFilePath)
 	}
 	if !cmn.FileExists(genesisFilePath) {
 		cmn.MustWriteFile(genesisFilePath, []byte(testGenesis), 0644)
@@ -94,36 +281,14 @@ func ResetTestRoot(testName string) *Config {
 	return config
 }
 
-var testConfigTmpl = `# This is a TOML config file.
-# For more information, see https://github.com/toml-lang/toml
-
-proxy_app = "dummy"
-moniker = "__MONIKER__"
-fast_sync = false
-db_backend = "memdb"
-log_level = "info"
-
-[rpc]
-laddr = "tcp://0.0.0.0:36657"
-
-[p2p]
-laddr = "tcp://0.0.0.0:36656"
-seeds = ""
-`
-
-func testConfig(moniker string) (testConfig string) {
-	testConfig = strings.Replace(testConfigTmpl, "__MONIKER__", moniker, -1)
-	return
-}
-
 var testGenesis = `{
   "genesis_time": "0001-01-01T00:00:00.000Z",
   "chain_id": "tendermint_test",
   "validators": [
     {
       "pub_key": {
-        "type": "ed25519",
-        "data":"3B3069C422E19688B45CBFAE7BB009FC0FA1B1EA86593519318B7214853803C8"
+        "type": "AC26791624DE60",
+        "value":"AT/+aaL1eB0477Mud9JMm8Sh8BIvOYlPGC9KkIUmFaE="
       },
       "power": 10,
       "name": ""
@@ -133,14 +298,14 @@ var testGenesis = `{
 }`
 
 var testPrivValidator = `{
-  "address": "D028C9981F7A87F3093672BF0D5B0E2A1B3ED456",
+  "address": "849CB2C877F87A20925F35D00AE6688342D25B47",
   "pub_key": {
-    "type": "ed25519",
-    "data": "3B3069C422E19688B45CBFAE7BB009FC0FA1B1EA86593519318B7214853803C8"
+    "type": "AC26791624DE60",
+    "value": "AT/+aaL1eB0477Mud9JMm8Sh8BIvOYlPGC9KkIUmFaE="
   },
   "priv_key": {
-    "type": "ed25519",
-    "data": "27F82582AEFAE7AB151CFB01C48BB6C1A0DA78F9BDDA979A9F70A84D074EB07D3B3069C422E19688B45CBFAE7BB009FC0FA1B1EA86593519318B7214853803C8"
+    "type": "954568A3288910",
+    "value": "EVkqJO/jIXp3rkASXfh9YnyToYXRXhBr6g9cQVxPFnQBP/5povV4HTjvsy530kybxKHwEi85iU8YL0qQhSYVoQ=="
   },
   "last_height": 0,
   "last_round": 0,

config/toml_test.go

@@ -4,6 +4,7 @@ import (
 	"io/ioutil"
 	"os"
 	"path/filepath"
+	"strings"
 	"testing"
 
 	"github.com/stretchr/testify/assert"
@@ -19,7 +20,7 @@ func ensureFiles(t *testing.T, rootDir string, files ...string) {
 }
 
 func TestEnsureRoot(t *testing.T) {
-	assert, require := assert.New(t), require.New(t)
+	require := require.New(t)
 
 	// setup temp dir for test
 	tmpDir, err := ioutil.TempDir("", "config-test")
@@ -30,15 +31,18 @@ func TestEnsureRoot(t *testing.T) {
 	EnsureRoot(tmpDir)
 
 	// make sure config is set properly
-	data, err := ioutil.ReadFile(filepath.Join(tmpDir, "config.toml"))
+	data, err := ioutil.ReadFile(filepath.Join(tmpDir, defaultConfigFilePath))
 	require.Nil(err)
-	assert.Equal([]byte(defaultConfig("anonymous")), data)
+
+	if !checkConfig(string(data)) {
+		t.Fatalf("config file missing some information")
+	}
 
 	ensureFiles(t, tmpDir, "data")
 }
 
 func TestEnsureTestRoot(t *testing.T) {
-	assert, require := assert.New(t), require.New(t)
+	require := require.New(t)
 
 	testName := "ensureTestRoot"
 
@@ -47,11 +51,44 @@ func TestEnsureTestRoot(t *testing.T) {
 	rootDir := cfg.RootDir
 
 	// make sure config is set properly
-	data, err := ioutil.ReadFile(filepath.Join(rootDir, "config.toml"))
+	data, err := ioutil.ReadFile(filepath.Join(rootDir, defaultConfigFilePath))
 	require.Nil(err)
-	assert.Equal([]byte(testConfig("anonymous")), data)
+
+	if !checkConfig(string(data)) {
+		t.Fatalf("config file missing some information")
+	}
 
 	// TODO: make sure the cfg returned and testconfig are the same!
-
-	ensureFiles(t, rootDir, "data", "genesis.json", "priv_validator.json")
+	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/README.md

@@ -1,18 +1 @@
-# The core consensus algorithm.
-
-* state.go - The state machine as detailed in the whitepaper
-* reactor.go - A reactor that connects the state machine to the gossip network
-
-# Go-routine summary
-
-The reactor runs 2 go-routines for each added peer: gossipDataRoutine and gossipVotesRoutine.
-
-The consensus state runs two persistent go-routines: timeoutRoutine and receiveRoutine.
-Go-routines are also started to trigger timeouts and to avoid blocking when the internalMsgQueue is really backed up.
-
-# Replay/WAL
-
-A write-ahead log is used to record all messages processed by the receiveRoutine,
-which amounts to all inputs to the consensus state machine:
-messages from peers, messages from ourselves, and timeouts.
-They can be played back deterministically at startup or using the replay console. 
+See the [consensus spec](https://github.com/tendermint/tendermint/tree/master/docs/spec/consensus) and the [reactor consensus spec](https://github.com/tendermint/tendermint/tree/master/docs/spec/reactors/consensus) for more information.

consensus/byzantine_test.go

@@ -7,8 +7,6 @@ import (
 	"time"
 
 	"github.com/stretchr/testify/require"
-	crypto "github.com/tendermint/go-crypto"
-	data "github.com/tendermint/go-wire/data"
 	"github.com/tendermint/tendermint/p2p"
 	"github.com/tendermint/tendermint/types"
 	cmn "github.com/tendermint/tmlibs/common"
@@ -29,11 +27,13 @@ func init() {
 // Heal partition and ensure A sees the commit
 func TestByzantine(t *testing.T) {
 	N := 4
-	logger := consensusLogger()
+	logger := consensusLogger().With("test", "byzantine")
 	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")
@@ -45,9 +45,11 @@ func TestByzantine(t *testing.T) {
 	eventChans := make([]chan interface{}, N)
 	reactors := make([]p2p.Reactor, N)
 	for i := 0; i < N; i++ {
+		// make first val byzantine
 		if i == 0 {
-			css[i].privValidator = NewByzantinePrivValidator(css[i].privValidator)
-			// make byzantine
+			// 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])
@@ -56,14 +58,11 @@ func TestByzantine(t *testing.T) {
 			css[i].doPrevote = func(height int64, round int) {}
 		}
 
-		eventBus := types.NewEventBus()
+		eventBus := css[i].eventBus
 		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])
+		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
@@ -73,9 +72,11 @@ func TestByzantine(t *testing.T) {
 		var conRI p2p.Reactor // nolint: gotype, gosimple
 		conRI = conR
 
+		// make first val byzantine
 		if i == 0 {
 			conRI = NewByzantineReactor(conR)
 		}
+
 		reactors[i] = conRI
 	}
 
@@ -101,32 +102,35 @@ func TestByzantine(t *testing.T) {
 		p2p.Connect2Switches(sws, i, j)
 	})
 
-	// start the state machines
-	byzR := reactors[0].(*ByzantineReactor)
-	s := byzR.reactor.conS.GetState()
-	byzR.reactor.SwitchToConsensus(s, 0)
+	// start the non-byz state machines.
+	// note these must be started before the byz
 	for i := 1; i < N; i++ {
 		cr := reactors[i].(*ConsensusReactor)
 		cr.SwitchToConsensus(cr.conS.GetState(), 0)
 	}
 
+	// start the byzantine state machine
+	byzR := reactors[0].(*ByzantineReactor)
+	s := byzR.reactor.conS.GetState()
+	byzR.reactor.SwitchToConsensus(s, 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]
 
 	t.Log("A block has been committed. Healing partition")
-
-	// connect the partitions
 	p2p.Connect2Switches(switches, ind0, ind1)
 	p2p.Connect2Switches(switches, ind0, ind2)
 
@@ -200,7 +204,7 @@ func byzantineDecideProposalFunc(t *testing.T, height int64, round int, cs *Cons
 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++ {
@@ -210,7 +214,7 @@ func sendProposalAndParts(height int64, round int, cs *ConsensusState, peer p2p.
 			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
@@ -219,8 +223,8 @@ func sendProposalAndParts(height int64, round int, cs *ConsensusState, peer p2p.
 	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}))
 }
 
 //----------------------------------------
@@ -261,47 +265,3 @@ func (br *ByzantineReactor) RemovePeer(peer p2p.Peer, reason interface{}) {
 func (br *ByzantineReactor) Receive(chID byte, peer p2p.Peer, msgBytes []byte) {
 	br.reactor.Receive(chID, peer, msgBytes)
 }
-
-//----------------------------------------
-// byzantine privValidator
-
-type ByzantinePrivValidator struct {
-	types.Signer
-
-	pv types.PrivValidator
-}
-
-// Return a priv validator that will sign anything
-func NewByzantinePrivValidator(pv types.PrivValidator) *ByzantinePrivValidator {
-	return &ByzantinePrivValidator{
-		Signer: pv.(*types.PrivValidatorFS).Signer,
-		pv:     pv,
-	}
-}
-
-func (privVal *ByzantinePrivValidator) GetAddress() data.Bytes {
-	return privVal.pv.GetAddress()
-}
-
-func (privVal *ByzantinePrivValidator) GetPubKey() crypto.PubKey {
-	return privVal.pv.GetPubKey()
-}
-
-func (privVal *ByzantinePrivValidator) SignVote(chainID string, vote *types.Vote) (err error) {
-	vote.Signature, err = privVal.Sign(types.SignBytes(chainID, vote))
-	return err
-}
-
-func (privVal *ByzantinePrivValidator) SignProposal(chainID string, proposal *types.Proposal) (err error) {
-	proposal.Signature, _ = privVal.Sign(types.SignBytes(chainID, proposal))
-	return nil
-}
-
-func (privVal *ByzantinePrivValidator) SignHeartbeat(chainID string, heartbeat *types.Heartbeat) (err error) {
-	heartbeat.Signature, _ = privVal.Sign(types.SignBytes(chainID, heartbeat))
-	return nil
-}
-
-func (privVal *ByzantinePrivValidator) String() string {
-	return cmn.Fmt("PrivValidator{%X}", privVal.GetAddress())
-}

consensus/common_test.go

@@ -19,6 +19,7 @@ import (
 	cstypes "github.com/tendermint/tendermint/consensus/types"
 	mempl "github.com/tendermint/tendermint/mempool"
 	"github.com/tendermint/tendermint/p2p"
+	"github.com/tendermint/tendermint/privval"
 	sm "github.com/tendermint/tendermint/state"
 	"github.com/tendermint/tendermint/types"
 	cmn "github.com/tendermint/tmlibs/common"
@@ -26,7 +27,7 @@ import (
 	"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"
 )
@@ -36,8 +37,8 @@ const (
 )
 
 // genesis, chain_id, priv_val
-var config *cfg.Config // NOTE: must be reset for each _test.go file
-var ensureTimeout = time.Second * 2
+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 := cmn.EnsureDir(dir, mode); err != nil {
@@ -50,7 +51,7 @@ func ResetConfig(name string) *cfg.Config {
 }
 
 //-------------------------------------------------------------------------------
-// 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.
@@ -74,10 +75,11 @@ func (vs *validatorStub) signVote(voteType byte, hash []byte, header types.PartS
 		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.ChainID, vote)
+	err := vs.PrivValidator.SignVote(config.ChainID(), vote)
 	return vote, err
 }
 
@@ -100,13 +102,13 @@ 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++
 	}
 }
 
@@ -128,7 +130,7 @@ func decideProposal(cs1 *ConsensusState, vs *validatorStub, height int64, round
 	// Make proposal
 	polRound, polBlockID := cs1.Votes.POLInfo()
 	proposal = types.NewProposal(height, round, blockParts.Header(), polRound, polBlockID)
-	if err := vs.SignProposal(config.ChainID, proposal); err != nil {
+	if err := vs.SignProposal(cs1.state.ChainID, proposal); err != nil {
 		panic(err)
 	}
 	return
@@ -221,7 +223,7 @@ func subscribeToVoter(cs *ConsensusState, addr []byte) chan interface{} {
 	voteCh := make(chan interface{})
 	go func() {
 		for v := range voteCh0 {
-			vote := v.(types.TMEventData).Unwrap().(types.EventDataVote)
+			vote := v.(types.EventDataVote)
 			// we only fire for our own votes
 			if bytes.Equal(addr, vote.Vote.ValidatorAddress) {
 				voteCh <- v
@@ -234,16 +236,16 @@ func subscribeToVoter(cs *ConsensusState, addr []byte) chan interface{} {
 //-------------------------------------------------------------------------------
 // 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 {
+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 {
+func newConsensusStateWithConfigAndBlockStore(thisConfig *cfg.Config, state sm.State, pv types.PrivValidator, app abci.Application, blockDB dbm.DB) *ConsensusState {
 	// Get BlockStore
 	blockStore := bc.NewBlockStore(blockDB)
 
@@ -259,9 +261,14 @@ func newConsensusStateWithConfigAndBlockStore(thisConfig *cfg.Config, state *sm.
 		mempool.EnableTxsAvailable()
 	}
 
-	// Make ConsensusReactor
-	cs := NewConsensusState(thisConfig.Consensus, state, proxyAppConnCon, blockStore, mempool)
-	cs.SetLogger(log.TestingLogger())
+	// mock the evidence pool
+	evpool := sm.MockEvidencePool{}
+
+	// Make ConsensusState
+	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)
 
 	eventBus := types.NewEventBus()
@@ -271,24 +278,14 @@ func newConsensusStateWithConfigAndBlockStore(thisConfig *cfg.Config, state *sm.
 	return cs
 }
 
-func loadPrivValidator(config *cfg.Config) *types.PrivValidatorFS {
+func loadPrivValidator(config *cfg.Config) *privval.FilePV {
 	privValidatorFile := config.PrivValidatorFile()
 	ensureDir(path.Dir(privValidatorFile), 0700)
-	privValidator := types.LoadOrGenPrivValidatorFS(privValidatorFile)
+	privValidator := privval.LoadOrGenFilePV(privValidatorFile)
 	privValidator.Reset()
 	return privValidator
 }
 
-func fixedConsensusStateDummy(config *cfg.Config, logger log.Logger) *ConsensusState {
-	stateDB := dbm.NewMemDB()
-	state, _ := sm.MakeGenesisStateFromFile(stateDB, config.GenesisFile())
-	state.SetLogger(logger.With("module", "state"))
-	privValidator := loadPrivValidator(config)
-	cs := newConsensusState(state, privValidator, dummy.NewDummyApplication())
-	cs.SetLogger(logger)
-	return cs
-}
-
 func randConsensusState(nValidators int) (*ConsensusState, []*validatorStub) {
 	// Get State
 	state, privVals := randGenesisState(nValidators, false, 10)
@@ -296,7 +293,6 @@ func randConsensusState(nValidators int) (*ConsensusState, []*validatorStub) {
 	vss := make([]*validatorStub, nValidators)
 
 	cs := newConsensusState(state, privVals[0], counter.NewCounterApplication(true))
-	cs.SetLogger(log.TestingLogger())
 
 	for i := 0; i < nValidators; i++ {
 		vss[i] = NewValidatorStub(privVals[i], i)
@@ -342,18 +338,16 @@ func consensusLogger() log.Logger {
 			}
 		}
 		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, 10)
+	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.SetLogger(logger.With("module", "state", "validator", i))
-		state.Save()
+		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)
@@ -364,8 +358,8 @@ func randConsensusNet(nValidators int, testName string, tickerFunc func() Timeou
 		app.InitChain(abci.RequestInitChain{Validators: vals})
 
 		css[i] = newConsensusStateWithConfig(thisConfig, state, privVals[i], app)
-		css[i].SetLogger(logger.With("validator", i))
 		css[i].SetTimeoutTicker(tickerFunc())
+		css[i].SetLogger(logger.With("validator", i, "module", "consensus"))
 	}
 	return css
 }
@@ -376,10 +370,8 @@ func randConsensusNetWithPeers(nValidators, nPeers int, testName string, tickerF
 	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.SetLogger(logger.With("module", "state", "validator", i))
-		state.Save()
+		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
@@ -387,7 +379,7 @@ func randConsensusNetWithPeers(nValidators, nPeers int, testName string, tickerF
 			privVal = privVals[i]
 		} else {
 			_, tempFilePath := cmn.Tempfile("priv_validator_")
-			privVal = types.GenPrivValidatorFS(tempFilePath)
+			privVal = privval.GenFilePV(tempFilePath)
 		}
 
 		app := appFunc()
@@ -395,15 +387,15 @@ func randConsensusNetWithPeers(nValidators, nPeers int, testName string, tickerF
 		app.InitChain(abci.RequestInitChain{Validators: vals})
 
 		css[i] = newConsensusStateWithConfig(thisConfig, state, privVal, app)
-		css[i].SetLogger(logger.With("validator", i))
 		css[i].SetTimeoutTicker(tickerFunc())
+		css[i].SetLogger(logger.With("validator", i, "module", "consensus"))
 	}
 	return css
 }
 
 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
 		}
 	}
@@ -414,9 +406,9 @@ func getSwitchIndex(switches []*p2p.Switch, peer p2p.Peer) int {
 //-------------------------------------------------------------------------------
 // genesis
 
-func randGenesisDoc(numValidators int, randPower bool, minPower int64) (*types.GenesisDoc, []*types.PrivValidatorFS) {
+func randGenesisDoc(numValidators int, randPower bool, minPower int64) (*types.GenesisDoc, []types.PrivValidator) {
 	validators := make([]types.GenesisValidator, numValidators)
-	privValidators := make([]*types.PrivValidatorFS, numValidators)
+	privValidators := make([]types.PrivValidator, numValidators)
 	for i := 0; i < numValidators; i++ {
 		val, privVal := types.RandValidator(randPower, minPower)
 		validators[i] = types.GenesisValidator{
@@ -426,19 +418,19 @@ func randGenesisDoc(numValidators int, randPower bool, minPower int64) (*types.G
 		privValidators[i] = privVal
 	}
 	sort.Sort(types.PrivValidatorsByAddress(privValidators))
+
 	return &types.GenesisDoc{
 		GenesisTime: time.Now(),
-		ChainID:     config.ChainID,
+		ChainID:     config.ChainID(),
 		Validators:  validators,
 	}, privValidators
 }
 
-func randGenesisState(numValidators int, randPower bool, minPower int64) (*sm.State, []*types.PrivValidatorFS) {
+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.SetLogger(log.TestingLogger().With("module", "state"))
-	s0.Save()
+	sm.SaveState(db, s0)
 	return s0, privValidators
 }
 
@@ -497,7 +489,7 @@ 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/mempool_test.go

@@ -19,7 +19,7 @@ func init() {
 	config = ResetConfig("consensus_mempool_test")
 }
 
-func TestNoProgressUntilTxsAvailable(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)
@@ -37,7 +37,7 @@ func TestNoProgressUntilTxsAvailable(t *testing.T) {
 	ensureNoNewStep(newBlockCh)
 }
 
-func TestProgressAfterCreateEmptyBlocksInterval(t *testing.T) {
+func TestMempoolProgressAfterCreateEmptyBlocksInterval(t *testing.T) {
 	config := ResetConfig("consensus_mempool_txs_available_test")
 	config.Consensus.CreateEmptyBlocksInterval = int(ensureTimeout.Seconds())
 	state, privVals := randGenesisState(1, false, 10)
@@ -52,7 +52,7 @@ func TestProgressAfterCreateEmptyBlocksInterval(t *testing.T) {
 	ensureNewStep(newBlockCh)   // until the CreateEmptyBlocksInterval has passed
 }
 
-func TestProgressInHigherRound(t *testing.T) {
+func TestMempoolProgressInHigherRound(t *testing.T) {
 	config := ResetConfig("consensus_mempool_txs_available_test")
 	config.Consensus.CreateEmptyBlocks = false
 	state, privVals := randGenesisState(1, false, 10)
@@ -94,7 +94,7 @@ func deliverTxsRange(cs *ConsensusState, start, end int) {
 	}
 }
 
-func TestTxConcurrentWithCommit(t *testing.T) {
+func TestMempoolTxConcurrentWithCommit(t *testing.T) {
 	state, privVals := randGenesisState(1, false, 10)
 	cs := newConsensusState(state, privVals[0], NewCounterApplication())
 	height, round := cs.Height, cs.Round
@@ -104,18 +104,19 @@ func TestTxConcurrentWithCommit(t *testing.T) {
 	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.TMEventData).Unwrap().(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)
@@ -128,7 +129,7 @@ func TestRmBadTx(t *testing.T) {
 	assert.False(t, resDeliver.IsErr(), cmn.Fmt("expected no error. got %v", resDeliver))
 
 	resCommit := app.Commit()
-	assert.False(t, resCommit.IsErr(), cmn.Fmt("expected no error. got %v", resCommit))
+	assert.True(t, len(resCommit.Data) > 0)
 
 	emptyMempoolCh := make(chan struct{})
 	checkTxRespCh := make(chan struct{})
@@ -151,6 +152,7 @@ func TestRmBadTx(t *testing.T) {
 			txs := cs.mempool.Reap(1)
 			if len(txs) == 0 {
 				emptyMempoolCh <- struct{}{}
+				return
 			}
 			time.Sleep(10 * time.Millisecond)
 		}
@@ -198,7 +200,7 @@ func (app *CounterApplication) DeliverTx(tx []byte) abci.ResponseDeliverTx {
 			Code: code.CodeTypeBadNonce,
 			Log:  fmt.Sprintf("Invalid nonce. Expected %v, got %v", app.txCount, txValue)}
 	}
-	app.txCount += 1
+	app.txCount++
 	return abci.ResponseDeliverTx{Code: code.CodeTypeOK}
 }
 
@@ -209,7 +211,7 @@ func (app *CounterApplication) CheckTx(tx []byte) abci.ResponseCheckTx {
 			Code: code.CodeTypeBadNonce,
 			Log:  fmt.Sprintf("Invalid nonce. Expected %v, got %v", app.mempoolTxCount, txValue)}
 	}
-	app.mempoolTxCount += 1
+	app.mempoolTxCount++
 	return abci.ResponseCheckTx{Code: code.CodeTypeOK}
 }
 
@@ -222,10 +224,9 @@ func txAsUint64(tx []byte) uint64 {
 func (app *CounterApplication) Commit() abci.ResponseCommit {
 	app.mempoolTxCount = app.txCount
 	if app.txCount == 0 {
-		return abci.ResponseCommit{Code: code.CodeTypeOK}
-	} else {
-		hash := make([]byte, 8)
-		binary.BigEndian.PutUint64(hash, uint64(app.txCount))
-		return abci.ResponseCommit{Code: code.CodeTypeOK, Data: hash}
+		return abci.ResponseCommit{}
 	}
+	hash := make([]byte, 8)
+	binary.BigEndian.PutUint64(hash, uint64(app.txCount))
+	return abci.ResponseCommit{Data: hash}
 }

consensus/reactor_test.go

@@ -4,17 +4,22 @@ import (
 	"context"
 	"fmt"
 	"os"
+	"runtime"
 	"runtime/pprof"
 	"sync"
 	"testing"
 	"time"
 
-	"github.com/tendermint/abci/example/dummy"
+	"github.com/tendermint/abci/example/kvstore"
+	cmn "github.com/tendermint/tmlibs/common"
+	"github.com/tendermint/tmlibs/log"
 
 	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/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 )
 
@@ -29,30 +34,24 @@ func startConsensusNet(t *testing.T, css []*ConsensusState, N int) ([]*Consensus
 	reactors := make([]*ConsensusReactor, N)
 	eventChans := make([]chan interface{}, N)
 	eventBuses := make([]*types.EventBus, N)
-	logger := consensusLogger()
 	for i := 0; i < N; i++ {
-		/*thisLogger, err := tmflags.ParseLogLevel("consensus:info,*:error", logger, "info")
+		/*logger, err := tmflags.ParseLogLevel("consensus:info,*:error", logger, "info")
 		if err != nil {	t.Fatal(err)}*/
-		thisLogger := logger
-
 		reactors[i] = NewConsensusReactor(css[i], true) // so we dont start the consensus states
-		reactors[i].conS.SetLogger(thisLogger.With("validator", i))
-		reactors[i].SetLogger(thisLogger.With("validator", i))
-
-		eventBuses[i] = types.NewEventBus()
-		eventBuses[i].SetLogger(thisLogger.With("module", "events", "validator", i))
-		err := eventBuses[i].Start()
-		require.NoError(t, err)
+		reactors[i].SetLogger(css[i].Logger)
 
+		// eventBus is already started with the cs
+		eventBuses[i] = css[i].eventBus
 		reactors[i].SetEventBus(eventBuses[i])
 
 		eventChans[i] = make(chan interface{}, 1)
-		err = eventBuses[i].Subscribe(context.Background(), testSubscriber, types.EventQueryNewBlock, eventChans[i])
+		err := eventBuses[i].Subscribe(context.Background(), testSubscriber, types.EventQueryNewBlock, eventChans[i])
 		require.NoError(t, err)
 	}
 	// make connected switches and start all reactors
 	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)
 
@@ -67,25 +66,28 @@ func startConsensusNet(t *testing.T, css []*ConsensusState, N int) ([]*Consensus
 	return reactors, eventChans, eventBuses
 }
 
-func stopConsensusNet(reactors []*ConsensusReactor, eventBuses []*types.EventBus) {
-	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 _, b := range eventBuses {
+	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, eventBuses := startConsensusNet(t, css, N)
-	defer stopConsensusNet(reactors, eventBuses)
+	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)
 }
 
@@ -97,7 +99,7 @@ func TestReactorProposalHeartbeats(t *testing.T) {
 			c.Consensus.CreateEmptyBlocks = false
 		})
 	reactors, eventChans, eventBuses := startConsensusNet(t, css, N)
-	defer stopConsensusNet(reactors, eventBuses)
+	defer stopConsensusNet(log.TestingLogger(), reactors, eventBuses)
 	heartbeatChans := make([]chan interface{}, N)
 	var err error
 	for i := 0; i < N; i++ {
@@ -106,9 +108,8 @@ func TestReactorProposalHeartbeats(t *testing.T) {
 		require.NoError(t, err)
 	}
 	// wait till everyone sends a proposal heartbeat
-	timeoutWaitGroup(t, N, func(wg *sync.WaitGroup, j int) {
+	timeoutWaitGroup(t, N, func(j int) {
 		<-heartbeatChans[j]
-		wg.Done()
 	}, css)
 
 	// send a tx
@@ -117,20 +118,126 @@ func TestReactorProposalHeartbeats(t *testing.T) {
 	}
 
 	// 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)
 }
 
+// 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)
+	logger := log.TestingLogger()
+	css := randConsensusNet(nVals, "consensus_voting_power_changes_test", newMockTickerFunc(true), newPersistentKVStore)
 	reactors, eventChans, eventBuses := startConsensusNet(t, css, nVals)
-	defer stopConsensusNet(reactors, eventBuses)
+	defer stopConsensusNet(logger, reactors, eventBuses)
 
 	// map of active validators
 	activeVals := make(map[string]struct{})
@@ -139,20 +246,20 @@ 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]
-		wg.Done()
 	}, css)
 
 	//---------------------------------------------------------------------------
-	t.Log("---------------------------- 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.GetPubKey()
-	updateValidatorTx := dummy.MakeValSetChangeTx(val1PubKey.Bytes(), 25)
+	val1PubKeyABCI := types.TM2PB.PubKey(val1PubKey)
+	updateValidatorTx := kvstore.MakeValSetChangeTx(val1PubKeyABCI, 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)
 
@@ -160,11 +267,11 @@ 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(val1PubKeyABCI, 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)
 
@@ -172,11 +279,11 @@ 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(val1PubKeyABCI, 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)
 
@@ -185,13 +292,15 @@ 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)
+	css := randConsensusNetWithPeers(nVals, nPeers, "consensus_val_set_changes_test", newMockTickerFunc(true), newPersistentKVStore)
+
+	logger := log.TestingLogger()
 
 	reactors, eventChans, eventBuses := startConsensusNet(t, css, nPeers)
-	defer stopConsensusNet(reactors, eventBuses)
+	defer stopConsensusNet(logger, reactors, eventBuses)
 
 	// map of active validators
 	activeVals := make(map[string]struct{})
@@ -200,16 +309,16 @@ 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]
-		wg.Done()
 	}, css)
 
 	//---------------------------------------------------------------------------
-	t.Log("---------------------------- Testing adding one validator")
+	logger.Info("---------------------------- Testing adding one validator")
 
 	newValidatorPubKey1 := css[nVals].privValidator.GetPubKey()
-	newValidatorTx1 := dummy.MakeValSetChangeTx(newValidatorPubKey1.Bytes(), testMinPower)
+	valPubKey1ABCI := types.TM2PB.PubKey(newValidatorPubKey1)
+	newValidatorTx1 := kvstore.MakeValSetChangeTx(valPubKey1ABCI, testMinPower)
 
 	// wait till everyone makes block 2
 	// ensure the commit includes all validators
@@ -218,7 +327,7 @@ 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
@@ -232,14 +341,15 @@ func TestValidatorSetChanges(t *testing.T) {
 	waitForBlockWithUpdatedValsAndValidateIt(t, nPeers, activeVals, eventChans, css)
 
 	//---------------------------------------------------------------------------
-	t.Log("---------------------------- Testing changing the voting power of one validator")
+	logger.Info("---------------------------- Testing changing the voting power of one validator")
 
 	updateValidatorPubKey1 := css[nVals].privValidator.GetPubKey()
-	updateValidatorTx1 := dummy.MakeValSetChangeTx(updateValidatorPubKey1.Bytes(), 25)
+	updatePubKey1ABCI := types.TM2PB.PubKey(updateValidatorPubKey1)
+	updateValidatorTx1 := kvstore.MakeValSetChangeTx(updatePubKey1ABCI, 25)
 	previousTotalVotingPower := css[nVals].GetRoundState().LastValidators.TotalVotingPower()
 
 	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css, updateValidatorTx1)
-	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
+	waitForAndValidateBlockWithTx(t, nPeers, activeVals, eventChans, css, updateValidatorTx1)
 	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
 	waitForBlockWithUpdatedValsAndValidateIt(t, nPeers, activeVals, eventChans, css)
 
@@ -248,29 +358,31 @@ func TestValidatorSetChanges(t *testing.T) {
 	}
 
 	//---------------------------------------------------------------------------
-	t.Log("---------------------------- Testing adding two validators at once")
+	logger.Info("---------------------------- Testing adding two validators at once")
 
 	newValidatorPubKey2 := css[nVals+1].privValidator.GetPubKey()
-	newValidatorTx2 := dummy.MakeValSetChangeTx(newValidatorPubKey2.Bytes(), testMinPower)
+	newVal2ABCI := types.TM2PB.PubKey(newValidatorPubKey2)
+	newValidatorTx2 := kvstore.MakeValSetChangeTx(newVal2ABCI, testMinPower)
 
 	newValidatorPubKey3 := css[nVals+2].privValidator.GetPubKey()
-	newValidatorTx3 := dummy.MakeValSetChangeTx(newValidatorPubKey3.Bytes(), testMinPower)
+	newVal3ABCI := types.TM2PB.PubKey(newValidatorPubKey3)
+	newValidatorTx3 := kvstore.MakeValSetChangeTx(newVal3ABCI, 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{}{}
 	waitForBlockWithUpdatedValsAndValidateIt(t, nPeers, activeVals, eventChans, css)
 
 	//---------------------------------------------------------------------------
-	t.Log("---------------------------- 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(newVal2ABCI, 0)
+	removeValidatorTx3 := kvstore.MakeValSetChangeTx(newVal3ABCI, 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()))
@@ -287,61 +399,85 @@ func TestReactorWithTimeoutCommit(t *testing.T) {
 	}
 
 	reactors, eventChans, eventBuses := startConsensusNet(t, css, N-1)
-	defer stopConsensusNet(reactors, eventBuses)
+	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) {
-		defer wg.Done()
-
+	timeoutWaitGroup(t, n, func(j int) {
+		css[j].Logger.Debug("waitForAndValidateBlock")
 		newBlockI, ok := <-eventChans[j]
 		if !ok {
 			return
 		}
-		newBlock := newBlockI.(types.TMEventData).Unwrap().(types.EventDataNewBlock).Block
-		t.Logf("Got block height=%v validator=%v", newBlock.Height, j)
+		newBlock := newBlockI.(types.EventDataNewBlock).Block
+		css[j].Logger.Debug("waitForAndValidateBlock: Got block", "height", newBlock.Height)
 		err := validateBlock(newBlock, activeVals)
-		if err != nil {
-			t.Fatal(err)
-		}
+		assert.Nil(t, err)
 		for _, tx := range txs {
-			if err = css[j].mempool.CheckTx(tx, nil); err != nil {
-				t.Fatal(err)
-			}
+			css[j].mempool.CheckTx(tx, nil)
+			assert.Nil(t, err)
 		}
 	}, css)
 }
 
-func waitForBlockWithUpdatedValsAndValidateIt(t *testing.T, n int, updatedVals map[string]struct{}, eventChans []chan interface{}, css []*ConsensusState) {
-	timeoutWaitGroup(t, n, func(wg *sync.WaitGroup, j int) {
-		defer wg.Done()
-
-		var newBlock *types.Block
-	LOOP:
+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.TMEventData).Unwrap().(types.EventDataNewBlock).Block
+			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
+			}
+		}
+
+	}, 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) {
-				t.Logf("Block with new validators height=%v validator=%v", newBlock.Height, j)
+				css[j].Logger.Debug("waitForBlockWithUpdatedValsAndValidateIt: Got block", "height", newBlock.Height)
 				break LOOP
 			} else {
-				t.Logf("Block with no new validators height=%v validator=%v. Skipping...", newBlock.Height, j)
+				css[j].Logger.Debug("waitForBlockWithUpdatedValsAndValidateIt: Got block with no new validators. Skipping", "height", newBlock.Height)
 			}
 		}
 
 		err := validateBlock(newBlock, updatedVals)
-		if err != nil {
-			t.Fatal(err)
-		}
+		assert.Nil(t, err)
 	}, css)
 }
 
@@ -359,11 +495,14 @@ 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{})
@@ -374,7 +513,7 @@ func timeoutWaitGroup(t *testing.T, n int, f func(*sync.WaitGroup, int), css []*
 
 	// 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 * 60
+	timeout := time.Second * 300
 
 	select {
 	case <-done:
@@ -385,7 +524,15 @@ func timeoutWaitGroup(t *testing.T, n int, f func(*sync.WaitGroup, int), css []*
 			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

@@ -2,7 +2,6 @@ package consensus
 
 import (
 	"bytes"
-	"errors"
 	"fmt"
 	"hash/crc32"
 	"io"
@@ -14,6 +13,7 @@ import (
 	abci "github.com/tendermint/abci/types"
 	//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"
@@ -25,20 +25,24 @@ import (
 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,
-// which ultimately hands off the work to the WAL.
+// There are two general failure scenarios:
+//
+//  1. failure during consensus
+//  2. failure while applying the block
+//
+// The former is handled by the WAL, the latter by the proxyApp Handshake on
+// restart, which ultimately hands off the work to the WAL.
 
 //-----------------------------------------
-// recover from failure during consensus
-// by replaying messages from the WAL
+// 1. Recover from failure during consensus
+// (by replaying messages from the WAL)
+//-----------------------------------------
 
-// Unmarshal and apply a single message to the consensus state
-// as if it were received in receiveRoutine
-// Lines that start with "#" are ignored.
-// NOTE: receiveRoutine should not be running
+// Unmarshal and apply a single message to the consensus state as if it were
+// received in receiveRoutine.  Lines that start with "#" are ignored.
+// NOTE: receiveRoutine should not be running.
 func (cs *ConsensusState) readReplayMessage(msg *TimedWALMessage, newStepCh chan interface{}) error {
-	// skip meta messages
+	// Skip meta messages which exist for demarcating boundaries.
 	if _, ok := msg.Msg.(EndHeightMessage); ok {
 		return nil
 	}
@@ -61,21 +65,21 @@ func (cs *ConsensusState) readReplayMessage(msg *TimedWALMessage, newStepCh chan
 			}
 		}
 	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
 			cs.Logger.Info("Replay: Proposal", "height", p.Height, "round", p.Round, "header",
-				p.BlockPartsHeader, "pol", p.POLRound, "peer", peerKey)
+				p.BlockPartsHeader, "pol", p.POLRound, "peer", peerID)
 		case *BlockPartMessage:
-			cs.Logger.Info("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
 			cs.Logger.Info("Replay: Vote", "height", v.Height, "round", v.Round, "type", v.Type,
-				"blockID", v.BlockID, "peer", peerKey)
+				"blockID", v.BlockID, "peer", peerID)
 		}
 
 		cs.handleMsg(m)
@@ -88,17 +92,21 @@ func (cs *ConsensusState) readReplayMessage(msg *TimedWALMessage, newStepCh chan
 	return nil
 }
 
-// replay only those messages since the last block.
-// timeoutRoutine should run concurrently to read off tickChan
+// Replay only those messages since the last block.  `timeoutRoutine` should
+// run concurrently to read off tickChan.
 func (cs *ConsensusState) catchupReplay(csHeight int64) error {
-	// set replayMode
+
+	// Set replayMode to true so we don't log signing errors.
 	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.SearchForEndHeight(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
 	}
@@ -108,18 +116,20 @@ func (cs *ConsensusState) catchupReplay(csHeight int64) error {
 		}
 	}
 	if found {
-		return fmt.Errorf("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.SearchForEndHeight(csHeight - 1)
+	// Search for last height marker.
+	//
+	// 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 {
 		cs.Logger.Error("Replay: wal.group.Search returned EOF", "#ENDHEIGHT", csHeight-1)
 	} else if err != nil {
 		return err
 	}
 	if !found {
-		return errors.New(cmn.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
 
@@ -132,9 +142,13 @@ func (cs *ConsensusState) catchupReplay(csHeight int64) error {
 		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
@@ -172,21 +186,33 @@ func makeHeightSearchFunc(height int64) auto.SearchFunc {
 	}
 }*/
 
-//----------------------------------------------
-// Recover from failure during block processing
-// by handshaking with the app to figure out where
-// we were last and using the WAL to recover there
+//---------------------------------------------------
+// 2. Recover from failure while applying the block.
+// (by handshaking with the app to figure out where
+// we were last, and using the WAL to recover there.)
+//---------------------------------------------------
 
 type Handshaker struct {
-	state  *sm.State
-	store  types.BlockStore
-	logger log.Logger
+	stateDB      dbm.DB
+	initialState sm.State
+	store        sm.BlockStore
+	genDoc       *types.GenesisDoc
+	logger       log.Logger
 
 	nBlocks int // number of blocks applied to the state
 }
 
-func NewHandshaker(state *sm.State, store types.BlockStore) *Handshaker {
-	return &Handshaker{state, store, log.NewNopLogger(), 0}
+func NewHandshaker(stateDB dbm.DB, state sm.State,
+	store sm.BlockStore, genDoc *types.GenesisDoc) *Handshaker {
+
+	return &Handshaker{
+		stateDB:      stateDB,
+		initialState: state,
+		store:        store,
+		genDoc:       genDoc,
+		logger:       log.NewNopLogger(),
+		nBlocks:      0,
+	}
 }
 
 func (h *Handshaker) SetLogger(l log.Logger) {
@@ -199,10 +225,11 @@ func (h *Handshaker) NBlocks() int {
 
 // 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
+
+	// Handshake is done via ABCI Info on the query conn.
 	res, err := proxyApp.Query().InfoSync(abci.RequestInfo{version.Version})
 	if err != nil {
-		return errors.New(cmn.Fmt("Error calling Info: %v", err))
+		return fmt.Errorf("Error calling Info: %v", err)
 	}
 
 	blockHeight := int64(res.LastBlockHeight)
@@ -213,15 +240,16 @@ func (h *Handshaker) Handshake(proxyApp proxy.AppConns) error {
 
 	h.logger.Info("ABCI Handshake", "appHeight", blockHeight, "appHash", fmt.Sprintf("%X", appHash))
 
-	// TODO: check version
+	// TODO: check app version.
 
-	// replay blocks up to the latest in the blockstore
-	_, err = h.ReplayBlocks(appHash, blockHeight, proxyApp)
+	// Replay blocks up to the latest in the blockstore.
+	_, err = h.ReplayBlocks(h.initialState, appHash, blockHeight, proxyApp)
 	if err != nil {
-		return errors.New(cmn.Fmt("Error on replay: %v", err))
+		return fmt.Errorf("Error on replay: %v", err)
 	}
 
-	h.logger.Info("Completed ABCI Handshake - Tendermint and App are synced", "appHeight", blockHeight, "appHash", fmt.Sprintf("%X", appHash))
+	h.logger.Info("Completed ABCI Handshake - Tendermint and App are synced",
+		"appHeight", blockHeight, "appHash", fmt.Sprintf("%X", appHash))
 
 	// TODO: (on restart) replay mempool
 
@@ -229,24 +257,48 @@ 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 int64, proxyApp proxy.AppConns) ([]byte, error) {
+// Returns the final AppHash or an 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
+	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(h.state.Validators)
-		if _, err := proxyApp.Consensus().InitChainSync(abci.RequestInitChain{validators}); err != nil {
+		validators := types.TM2PB.Validators(state.Validators)
+		csParams := types.TM2PB.ConsensusParams(h.genDoc.ConsensusParams)
+		req := abci.RequestInitChain{
+			Time:            h.genDoc.GenesisTime.Unix(), // TODO
+			ChainId:         h.genDoc.ChainID,
+			ConsensusParams: csParams,
+			Validators:      validators,
+			AppStateBytes:   h.genDoc.AppStateJSON,
+		}
+		res, err := proxyApp.Consensus().InitChainSync(req)
+		if err != nil {
 			return nil, err
 		}
+
+		// if the app returned validators
+		// or consensus params, update the state
+		// with the them
+		if len(res.Validators) > 0 {
+			vals, err := types.PB2TM.Validators(res.Validators)
+			if err != nil {
+				return nil, err
+			}
+			state.Validators = types.NewValidatorSet(vals)
+		}
+		if res.ConsensusParams != nil {
+			state.ConsensusParams = types.PB2TM.ConsensusParams(res.ConsensusParams)
+		}
+		sm.SaveState(h.stateDB, state)
 	}
 
 	// 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)
@@ -261,6 +313,7 @@ func (h *Handshaker) ReplayBlocks(appHash []byte, appBlockHeight int64, proxyApp
 		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 {
@@ -268,11 +321,11 @@ func (h *Handshaker) ReplayBlocks(appHash []byte, appBlockHeight int64, proxyApp
 		// 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 {
@@ -281,22 +334,27 @@ func (h *Handshaker) ReplayBlocks(appHash []byte, appBlockHeight int64, proxyApp
 		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
+			// but we'd have to allow the WAL to replay a block that wrote it's #ENDHEIGHT
 			h.logger.Info("Replay last block using real app")
-			return h.replayBlock(storeBlockHeight, proxyApp.Consensus())
+			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)
 			h.logger.Info("Replay last block using mock app")
-			return h.replayBlock(storeBlockHeight, mockApp)
+			state, err = h.replayBlock(state, storeBlockHeight, mockApp)
+			return state.AppHash, err
 		}
 
 	}
@@ -305,13 +363,14 @@ func (h *Handshaker) ReplayBlocks(appHash []byte, appBlockHeight int64, proxyApp
 	return nil, nil
 }
 
-func (h *Handshaker) replayBlocks(proxyApp proxy.AppConns, appBlockHeight, storeBlockHeight int64, 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()
 
@@ -319,46 +378,52 @@ func (h *Handshaker) replayBlocks(proxyApp proxy.AppConns, appBlockHeight, store
 	var err error
 	finalBlock := storeBlockHeight
 	if mutateState {
-		finalBlock -= 1
+		finalBlock--
 	}
 	for i := appBlockHeight + 1; i <= finalBlock; i++ {
 		h.logger.Info("Applying block", "height", i)
 		block := h.store.LoadBlock(i)
-		appHash, err = sm.ExecCommitBlock(proxyApp.Consensus(), block, h.logger)
+		appHash, err = sm.ExecCommitBlock(proxyApp.Consensus(), block, h.logger, state.LastValidators, h.stateDB)
 		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 int64, proxyApp proxy.AppConnConsensus) ([]byte, error) {
-	mempool := types.MockMempool{}
-
+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(types.NopEventBus{}, proxyApp, block, meta.BlockID.PartsHeader, mempool); err != nil {
-		return nil, err
+	blockExec := sm.NewBlockExecutor(h.stateDB, h.logger, proxyApp, sm.MockMempool{}, sm.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(cmn.Fmt("Tendermint state.AppHash does not match AppHash after replay. Got %X, expected %X", appHash, h.state.AppHash)).Error())
+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
 }
@@ -390,7 +455,7 @@ type mockProxyApp struct {
 
 func (mock *mockProxyApp) DeliverTx(tx []byte) abci.ResponseDeliverTx {
 	r := mock.abciResponses.DeliverTx[mock.txCount]
-	mock.txCount += 1
+	mock.txCount++
 	return *r
 }
 
@@ -400,5 +465,5 @@ func (mock *mockProxyApp) EndBlock(req abci.RequestEndBlock) abci.ResponseEndBlo
 }
 
 func (mock *mockProxyApp) Commit() abci.ResponseCommit {
-	return abci.ResponseCommit{Code: abci.CodeTypeOK, Data: mock.appHash}
+	return abci.ResponseCommit{Data: mock.appHash}
 }

consensus/replay_file.go

@@ -18,6 +18,7 @@ import (
 	"github.com/tendermint/tendermint/types"
 	cmn "github.com/tendermint/tmlibs/common"
 	dbm "github.com/tendermint/tmlibs/db"
+	"github.com/tendermint/tmlibs/log"
 )
 
 const (
@@ -28,6 +29,7 @@ const (
 //--------------------------------------------------------
 // replay messages interactively or all at once
 
+// replay the wal file
 func RunReplayFile(config cfg.BaseConfig, csConfig *cfg.ConsensusConfig, console bool) {
 	consensusState := newConsensusStateForReplay(config, csConfig)
 
@@ -86,9 +88,9 @@ func (cs *ConsensusState) ReplayFile(file string, console bool) error {
 		}
 
 		if nextN > 0 {
-			nextN -= 1
+			nextN--
 		}
-		pb.count += 1
+		pb.count++
 	}
 	return nil
 }
@@ -104,11 +106,11 @@ type playback struct {
 	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,
@@ -123,7 +125,8 @@ 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 := 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()
 
@@ -151,7 +154,7 @@ func (pb *playback) replayReset(count int, newStepCh chan interface{}) error {
 		if err := pb.cs.readReplayMessage(msg, newStepCh); err != nil {
 			return err
 		}
-		pb.count += 1
+		pb.count++
 	}
 	return nil
 }
@@ -195,13 +198,12 @@ 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":
@@ -261,7 +263,7 @@ func (pb *playback) replayConsoleLoop() int {
 				case "locked_block":
 					fmt.Printf("%v %v\n", rs.LockedBlockParts.StringShort(), rs.LockedBlock.StringShort())
 				case "votes":
-					fmt.Println(rs.Votes.StringIndented("    "))
+					fmt.Println(rs.Votes.StringIndented("  "))
 
 				default:
 					fmt.Println("Unknown option", tokens[1])
@@ -278,20 +280,26 @@ func (pb *playback) replayConsoleLoop() int {
 
 // convenience for replay mode
 func newConsensusStateForReplay(config cfg.BaseConfig, csConfig *cfg.ConsensusConfig) *ConsensusState {
+	dbType := dbm.DBBackendType(config.DBBackend)
 	// Get BlockStore
-	blockStoreDB := dbm.NewDB("blockstore", config.DBBackend, config.DBDir())
+	blockStoreDB := dbm.NewDB("blockstore", dbType, config.DBDir())
 	blockStore := bc.NewBlockStore(blockStoreDB)
 
 	// Get State
-	stateDB := dbm.NewDB("state", config.DBBackend, config.DBDir())
-	state, err := sm.MakeGenesisStateFromFile(stateDB, config.GenesisFile())
+	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)
 	clientCreator := proxy.DefaultClientCreator(config.ProxyApp, config.ABCI, config.DBDir())
-	proxyApp := proxy.NewAppConns(clientCreator, NewHandshaker(state, blockStore))
+	proxyApp := proxy.NewAppConns(clientCreator,
+		NewHandshaker(stateDB, state, blockStore, gdoc))
 	err = proxyApp.Start()
 	if err != nil {
 		cmn.Exit(cmn.Fmt("Error starting proxy app conns: %v", err))
@@ -302,7 +310,11 @@ func newConsensusStateForReplay(config cfg.BaseConfig, csConfig *cfg.ConsensusCo
 		cmn.Exit(cmn.Fmt("Failed to start event bus: %v", err))
 	}
 
-	consensusState := NewConsensusState(csConfig, state.Copy(), proxyApp.Consensus(), blockStore, types.MockMempool{})
+	mempool, evpool := sm.MockMempool{}, sm.MockEvidencePool{}
+	blockExec := sm.NewBlockExecutor(stateDB, log.TestingLogger(), proxyApp.Consensus(), mempool, evpool)
+
+	consensusState := NewConsensusState(csConfig, state.Copy(), blockExec,
+		blockStore, mempool, evpool)
 
 	consensusState.SetEventBus(eventBus)
 	return consensusState

consensus/replay_test.go

@@ -13,17 +13,18 @@ import (
 	"testing"
 	"time"
 
+	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 
-	"github.com/tendermint/abci/example/dummy"
+	"github.com/tendermint/abci/example/kvstore"
 	abci "github.com/tendermint/abci/types"
 	crypto "github.com/tendermint/go-crypto"
-	wire "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/privval"
 	"github.com/tendermint/tendermint/proxy"
 	sm "github.com/tendermint/tendermint/state"
 	"github.com/tendermint/tendermint/types"
@@ -44,13 +45,6 @@ func init() {
 // the `Handshake Tests` are for failures in applying the block.
 // With the help of the WAL, we can recover from it all!
 
-// NOTE: Files in this dir are generated by running the `build.sh` therein.
-// It's a simple way to generate wals for a single block, or multiple blocks, with random transactions,
-// and different part sizes. The output is not deterministic.
-// It should only have to be re-run if there is some breaking change to the consensus data structures (eg. blocks, votes)
-// or to the behaviour of the app (eg. computes app hash differently)
-var data_dir = path.Join(cmn.GoPath(), "src/github.com/tendermint/tendermint/consensus", "test_data")
-
 //------------------------------------------------------------------------------------------
 // WAL Tests
 
@@ -60,21 +54,18 @@ var data_dir = path.Join(cmn.GoPath(), "src/github.com/tendermint/tendermint/con
 
 func startNewConsensusStateAndWaitForBlock(t *testing.T, lastBlockHeight int64, blockDB dbm.DB, stateDB dbm.DB) {
 	logger := log.TestingLogger()
-	state, _ := sm.GetState(stateDB, consensusReplayConfig.GenesisFile())
-	state.SetLogger(logger.With("module", "state"))
+	state, _ := sm.LoadStateFromDBOrGenesisFile(stateDB, consensusReplayConfig.GenesisFile())
 	privValidator := loadPrivValidator(consensusReplayConfig)
-	cs := newConsensusStateWithConfigAndBlockStore(consensusReplayConfig, state, privValidator, dummy.NewDummyApplication(), blockDB)
+	cs := newConsensusStateWithConfigAndBlockStore(consensusReplayConfig, state, privValidator, kvstore.NewKVStoreApplication(), blockDB)
 	cs.SetLogger(logger)
 
 	bytes, _ := ioutil.ReadFile(cs.config.WalFile())
 	// fmt.Printf("====== WAL: \n\r%s\n", bytes)
-	t.Logf("====== WAL: \n\r%s\n", bytes)
+	t.Logf("====== WAL: \n\r%X\n", bytes)
 
 	err := cs.Start()
 	require.NoError(t, err)
-	defer func() {
-		cs.Stop()
-	}()
+	defer cs.Stop()
 
 	// 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
@@ -85,19 +76,19 @@ func startNewConsensusStateAndWaitForBlock(t *testing.T, lastBlockHeight int64,
 	require.NoError(t, err)
 	select {
 	case <-newBlockCh:
-	case <-time.After(10 * time.Second):
+	case <-time.After(60 * time.Second):
 		t.Fatalf("Timed out waiting for new block (see trace above)")
 	}
 }
 
 func sendTxs(cs *ConsensusState, ctx context.Context) {
-	i := 0
-	for {
+	for i := 0; i < 256; i++ {
 		select {
 		case <-ctx.Done():
 			return
 		default:
-			cs.mempool.CheckTx([]byte{byte(i)}, nil)
+			tx := []byte{byte(i)}
+			cs.mempool.CheckTx(tx, nil)
 			i++
 		}
 	}
@@ -107,23 +98,24 @@ func sendTxs(cs *ConsensusState, ctx context.Context) {
 func TestWALCrash(t *testing.T) {
 	testCases := []struct {
 		name         string
-		initFn       func(*ConsensusState, context.Context)
+		initFn       func(dbm.DB, *ConsensusState, context.Context)
 		heightToStop int64
 	}{
 		{"empty block",
-			func(cs *ConsensusState, ctx context.Context) {},
+			func(stateDB dbm.DB, cs *ConsensusState, ctx context.Context) {},
 			1},
 		{"block with a smaller part size",
-			func(cs *ConsensusState, ctx context.Context) {
+			func(stateDB dbm.DB, cs *ConsensusState, ctx context.Context) {
 				// XXX: is there a better way to change BlockPartSizeBytes?
-				params := cs.state.Params
-				params.BlockPartSizeBytes = 512
-				cs.state.Params = params
-				sendTxs(cs, ctx)
+				cs.state.ConsensusParams.BlockPartSizeBytes = 512
+				sm.SaveState(stateDB, cs.state)
+				go sendTxs(cs, ctx)
 			},
 			1},
 		{"many non-empty blocks",
-			sendTxs,
+			func(stateDB dbm.DB, cs *ConsensusState, ctx context.Context) {
+				go sendTxs(cs, ctx)
+			},
 			3},
 	}
 
@@ -134,7 +126,7 @@ func TestWALCrash(t *testing.T) {
 	}
 }
 
-func crashWALandCheckLiveness(t *testing.T, initFn func(*ConsensusState, context.Context), heightToStop int64) {
+func crashWALandCheckLiveness(t *testing.T, initFn func(dbm.DB, *ConsensusState, context.Context), heightToStop int64) {
 	walPaniced := make(chan error)
 	crashingWal := &crashingWAL{panicCh: walPaniced, heightToStop: heightToStop}
 
@@ -147,16 +139,15 @@ LOOP:
 		// create consensus state from a clean slate
 		logger := log.NewNopLogger()
 		stateDB := dbm.NewMemDB()
-		state, _ := sm.MakeGenesisStateFromFile(stateDB, consensusReplayConfig.GenesisFile())
-		state.SetLogger(logger.With("module", "state"))
+		state, _ := sm.MakeGenesisStateFromFile(consensusReplayConfig.GenesisFile())
 		privValidator := loadPrivValidator(consensusReplayConfig)
 		blockDB := dbm.NewMemDB()
-		cs := newConsensusStateWithConfigAndBlockStore(consensusReplayConfig, state, privValidator, dummy.NewDummyApplication(), blockDB)
+		cs := newConsensusStateWithConfigAndBlockStore(consensusReplayConfig, state, privValidator, kvstore.NewKVStoreApplication(), blockDB)
 		cs.SetLogger(logger)
 
 		// start sending transactions
 		ctx, cancel := context.WithCancel(context.Background())
-		go initFn(cs, ctx)
+		initFn(stateDB, cs, ctx)
 
 		// clean up WAL file from the previous iteration
 		walFile := cs.config.WalFile()
@@ -228,15 +219,15 @@ 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
+// Write simulate WAL's crashing by sending an error to the panicCh and then
 // exiting the cs.receiveRoutine.
-func (w *crashingWAL) Save(m WALMessage) {
+func (w *crashingWAL) Write(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)
+			w.next.Write(m)
 		}
 		return
 	}
@@ -248,13 +239,17 @@ func (w *crashingWAL) Save(m WALMessage) {
 		runtime.Goexit()
 	} else {
 		w.msgIndex++
-		w.next.Save(m)
+		w.next.Write(m)
 	}
 }
 
+func (w *crashingWAL) WriteSync(m WALMessage) {
+	w.Write(m)
+}
+
 func (w *crashingWAL) Group() *auto.Group { return w.next.Group() }
-func (w *crashingWAL) SearchForEndHeight(height int64) (gr *auto.GroupReader, found bool, err error) {
-	return w.next.SearchForEndHeight(height)
+func (w *crashingWAL) SearchForEndHeight(height int64, options *WALSearchOptions) (gr *auto.GroupReader, found bool, err error) {
+	return w.next.SearchForEndHeight(height, options)
 }
 
 func (w *crashingWAL) Start() error { return w.next.Start() }
@@ -264,9 +259,13 @@ func (w *crashingWAL) Wait()        { w.next.Wait() }
 //------------------------------------------------------------------------------------------
 // Handshake Tests
 
+const (
+	NUM_BLOCKS = 6
+)
+
 var (
-	NUM_BLOCKS = 6 // number of blocks in the test_data/many_blocks.cswal
-	mempool    = types.MockMempool{}
+	mempool = sm.MockMempool{}
+	evpool  = sm.MockEvidencePool{}
 )
 
 //---------------------------------------
@@ -305,12 +304,12 @@ func TestHandshakeReplayNone(t *testing.T) {
 	}
 }
 
-func writeWAL(walMsgs []byte) string {
+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(walMsgs)
+	_, err = walFile.Write(data)
 	if err != nil {
 		panic(fmt.Errorf("failed to write to temp WAL file: %v", err))
 	}
@@ -324,17 +323,16 @@ func writeWAL(walMsgs []byte) string {
 func testHandshakeReplay(t *testing.T, nBlocks int, mode uint) {
 	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(walBody)
+	walFile := tempWALWithData(walBody)
 	config.Consensus.SetWalFile(walFile)
 
-	privVal := types.LoadPrivValidatorFS(config.PrivValidatorFile())
+	privVal := privval.LoadFilePV(config.PrivValidatorFile())
 
-	wal, err := NewWAL(walFile, false)
+	wal, err := NewWAL(walFile)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -342,35 +340,40 @@ func testHandshakeReplay(t *testing.T, nBlocks int, mode uint) {
 	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.GetPubKey())
+	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.DBDir(), "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(clientCreator2, nil)
-		state, _ := stateAndStore(config, privVal.GetPubKey())
-		buildAppStateFromChain(proxyApp, state, chain, nBlocks, mode)
+		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(state, store)
+	genDoc, _ := sm.MakeGenesisDocFromFile(config.GenesisFile())
+	handshaker := NewHandshaker(stateDB, state, store, genDoc)
 	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(abci.RequestInfo{""})
@@ -385,9 +388,9 @@ 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 {
@@ -395,51 +398,57 @@ func testHandshakeReplay(t *testing.T, nBlocks int, mode uint) {
 	}
 }
 
-func applyBlock(st *sm.State, blk *types.Block, proxyApp proxy.AppConns) {
-	testPartSize := st.Params.BlockPartSizeBytes
-	err := st.ApplyBlock(types.NopEventBus{}, 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 {
 		panic(err)
 	}
+	defer proxyApp.Stop()
 
 	validators := types.TM2PB.Validators(state.Validators)
-	if _, err := proxyApp.Consensus().InitChainSync(abci.RequestInitChain{validators}); err != nil {
+	if _, err := proxyApp.Consensus().InitChainSync(abci.RequestInitChain{
+		Validators: validators,
+	}); err != nil {
 		panic(err)
 	}
 
-	defer proxyApp.Stop()
 	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.DBDir(), "1")))
+	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)
@@ -447,35 +456,32 @@ func buildTMStateFromChain(config *cfg.Config, state *sm.State, chain []*types.B
 	defer proxyApp.Stop()
 
 	validators := types.TM2PB.Validators(state.Validators)
-	if _, err := proxyApp.Consensus().InitChainSync(abci.RequestInitChain{validators}); err != nil {
+	if _, err := proxyApp.Consensus().InitChainSync(abci.RequestInitChain{
+		Validators: validators,
+	}); err != nil {
 		panic(err)
 	}
 
-	var latestAppHash []byte
-
 	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
 }
 
 //--------------------------
@@ -483,7 +489,7 @@ func buildTMStateFromChain(config *cfg.Config, state *sm.State, chain []*types.B
 
 func makeBlockchainFromWAL(wal WAL) ([]*types.Block, []*types.Commit, error) {
 	// Search for height marker
-	gr, found, err := wal.SearchForEndHeight(0)
+	gr, found, err := wal.SearchForEndHeight(0, &WALSearchOptions{})
 	if err != nil {
 		return nil, nil, err
 	}
@@ -494,10 +500,13 @@ func makeBlockchainFromWAL(wal WAL) ([]*types.Block, []*types.Commit, error) {
 
 	// log.Notice("Build a blockchain by reading from the WAL")
 
-	var blockParts *types.PartSet
 	var blocks []*types.Block
 	var commits []*types.Commit
 
+	var thisBlockParts *types.PartSet
+	var thisBlockCommit *types.Commit
+	var height int64
+
 	dec := NewWALDecoder(gr)
 	for {
 		msg, err := dec.Decode()
@@ -513,42 +522,60 @@ func makeBlockchainFromWAL(wal WAL) ([]*types.Block, []*types.Commit, error) {
 		}
 
 		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(), 0, &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)
 			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(), 0, &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(msg *TimedWALMessage) interface{} {
-	// skip meta messages
-	if _, ok := msg.Msg.(EndHeightMessage); ok {
-		return nil
-	}
-
 	// for logging
 	switch m := msg.Msg.(type) {
 	case msgInfo:
@@ -560,19 +587,19 @@ func readPieceFromWAL(msg *TimedWALMessage) interface{} {
 		case *VoteMessage:
 			return msg.Vote
 		}
+	case EndHeightMessage:
+		return m
 	}
 
 	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()
-	state, _ := sm.MakeGenesisStateFromFile(stateDB, config.GenesisFile())
-	state.SetLogger(log.TestingLogger().With("module", "state"))
-
-	store := NewMockBlockStore(config, state.Params)
-	return state, store
+	state, _ := sm.MakeGenesisStateFromFile(config.GenesisFile())
+	store := NewMockBlockStore(config, state.ConsensusParams)
+	return stateDB, state, store
 }
 
 //----------------------------------
@@ -608,3 +635,53 @@ func (bs *mockBlockStore) LoadBlockCommit(height int64) *types.Commit {
 func (bs *mockBlockStore) LoadSeenCommit(height int64) *types.Commit {
 	return bs.commits[height-1]
 }
+
+//----------------------------------------
+
+func TestInitChainUpdateValidators(t *testing.T) {
+	val, _ := types.RandValidator(true, 10)
+	vals := types.NewValidatorSet([]*types.Validator{val})
+	app := &initChainApp{vals: types.TM2PB.Validators(vals)}
+	clientCreator := proxy.NewLocalClientCreator(app)
+
+	config := ResetConfig("proxy_test_")
+	privVal := privval.LoadFilePV(config.PrivValidatorFile())
+	stateDB, state, store := stateAndStore(config, privVal.GetPubKey())
+
+	oldValAddr := state.Validators.Validators[0].Address
+
+	// now start the app using the handshake - it should sync
+	genDoc, _ := sm.MakeGenesisDocFromFile(config.GenesisFile())
+	handshaker := NewHandshaker(stateDB, state, store, genDoc)
+	proxyApp := proxy.NewAppConns(clientCreator, handshaker)
+	if err := proxyApp.Start(); err != nil {
+		t.Fatalf("Error starting proxy app connections: %v", err)
+	}
+	defer proxyApp.Stop()
+
+	// reload the state, check the validator set was updated
+	state = sm.LoadState(stateDB)
+
+	newValAddr := state.Validators.Validators[0].Address
+	expectValAddr := val.Address
+	assert.NotEqual(t, oldValAddr, newValAddr)
+	assert.Equal(t, newValAddr, expectValAddr)
+}
+
+func newInitChainApp(vals []abci.Validator) *initChainApp {
+	return &initChainApp{
+		vals: vals,
+	}
+}
+
+// returns the vals on InitChain
+type initChainApp struct {
+	abci.BaseApplication
+	vals []abci.Validator
+}
+
+func (ica *initChainApp) InitChain(req abci.RequestInitChain) abci.ResponseInitChain {
+	return abci.ResponseInitChain{
+		Validators: ica.vals,
+	}
+}

consensus/state_test.go

@@ -8,10 +8,10 @@ import (
 	"time"
 
 	cstypes "github.com/tendermint/tendermint/consensus/types"
+	tmpubsub "github.com/tendermint/tendermint/libs/pubsub"
 	"github.com/tendermint/tendermint/types"
 	cmn "github.com/tendermint/tmlibs/common"
 	"github.com/tendermint/tmlibs/log"
-	tmpubsub "github.com/tendermint/tmlibs/pubsub"
 )
 
 func init() {
@@ -55,7 +55,7 @@ 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
 
@@ -89,7 +89,7 @@ func TestProposerSelection0(t *testing.T) {
 }
 
 // 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 := subscribe(cs1.eventBus, types.EventQueryNewRound)
@@ -118,7 +118,7 @@ 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
@@ -143,7 +143,7 @@ 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
 
@@ -179,12 +179,12 @@ 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 := cs1.state.Params.BlockPartSizeBytes
+	partSize := cs1.state.ConsensusParams.BlockPartSizeBytes
 
 	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
 	voteCh := subscribe(cs1.eventBus, types.EventQueryVote)
@@ -204,7 +204,7 @@ 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.ChainID, proposal); err != nil {
+	if err := vs2.SignProposal(config.ChainID(), proposal); err != nil {
 		t.Fatal("failed to sign bad proposal", err)
 	}
 
@@ -239,7 +239,7 @@ 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
 
@@ -261,7 +261,7 @@ func TestFullRound1(t *testing.T) {
 
 	// grab proposal
 	re := <-propCh
-	propBlockHash := re.(types.TMEventData).Unwrap().(types.EventDataRoundState).RoundState.(*cstypes.RoundState).ProposalBlock.Hash()
+	propBlockHash := re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState).ProposalBlock.Hash()
 
 	<-voteCh // wait for prevote
 	validatePrevote(t, cs, round, vss[0], propBlockHash)
@@ -275,7 +275,7 @@ 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
 
@@ -293,7 +293,7 @@ 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
@@ -334,12 +334,12 @@ 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 := cs1.state.Params.BlockPartSizeBytes
+	partSize := cs1.state.ConsensusParams.BlockPartSizeBytes
 
 	timeoutProposeCh := subscribe(cs1.eventBus, types.EventQueryTimeoutPropose)
 	timeoutWaitCh := subscribe(cs1.eventBus, types.EventQueryTimeoutWait)
@@ -356,7 +356,7 @@ func TestLockNoPOL(t *testing.T) {
 	cs1.startRoutines(0)
 
 	re := <-proposalCh
-	rs := re.(types.TMEventData).Unwrap().(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
+	rs := re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 	theBlockHash := rs.ProposalBlock.Hash()
 
 	<-voteCh // prevote
@@ -396,7 +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.TMEventData).Unwrap().(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
+	rs = re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 
 	if rs.ProposalBlock != nil {
 		panic("Expected proposal block to be nil")
@@ -409,7 +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
@@ -424,7 +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
@@ -440,7 +440,7 @@ func TestLockNoPOL(t *testing.T) {
 	incrementRound(vs2)
 
 	re = <-proposalCh
-	rs = re.(types.TMEventData).Unwrap().(types.EventDataRoundState).RoundState.(*cstypes.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()) {
@@ -503,11 +503,11 @@ 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 := cs1.state.Params.BlockPartSizeBytes
+	partSize := cs1.state.ConsensusParams.BlockPartSizeBytes
 
 	timeoutProposeCh := subscribe(cs1.eventBus, types.EventQueryTimeoutPropose)
 	timeoutWaitCh := subscribe(cs1.eventBus, types.EventQueryTimeoutWait)
@@ -529,7 +529,7 @@ func TestLockPOLRelock(t *testing.T) {
 
 	<-newRoundCh
 	re := <-proposalCh
-	rs := re.(types.TMEventData).Unwrap().(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
+	rs := re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 	theBlockHash := rs.ProposalBlock.Hash()
 
 	<-voteCh // prevote
@@ -605,9 +605,9 @@ func TestLockPOLRelock(t *testing.T) {
 	discardFromChan(voteCh, 2)
 
 	be := <-newBlockCh
-	b := be.(types.TMEventData).Unwrap().(types.EventDataNewBlockHeader)
+	b := be.(types.EventDataNewBlockHeader)
 	re = <-newRoundCh
-	rs = re.(types.TMEventData).Unwrap().(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
+	rs = re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 	if rs.Height != 2 {
 		panic("Expected height to increment")
 	}
@@ -618,11 +618,11 @@ 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 := cs1.state.Params.BlockPartSizeBytes
+	partSize := cs1.state.ConsensusParams.BlockPartSizeBytes
 
 	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
 	timeoutProposeCh := subscribe(cs1.eventBus, types.EventQueryTimeoutPropose)
@@ -643,7 +643,7 @@ func TestLockPOLUnlock(t *testing.T) {
 	startTestRound(cs1, cs1.Height, 0)
 	<-newRoundCh
 	re := <-proposalCh
-	rs := re.(types.TMEventData).Unwrap().(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
+	rs := re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 	theBlockHash := rs.ProposalBlock.Hash()
 
 	<-voteCh // prevote
@@ -669,7 +669,7 @@ func TestLockPOLUnlock(t *testing.T) {
 
 	// timeout to new round
 	re = <-timeoutWaitCh
-	rs = re.(types.TMEventData).Unwrap().(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
+	rs = re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 	lockedBlockHash := rs.LockedBlock.Hash()
 
 	//XXX: this isnt guaranteed to get there before the timeoutPropose ...
@@ -715,11 +715,11 @@ 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 := cs1.state.Params.BlockPartSizeBytes
+	partSize := cs1.state.ConsensusParams.BlockPartSizeBytes
 
 	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
 	timeoutProposeCh := subscribe(cs1.eventBus, types.EventQueryTimeoutPropose)
@@ -731,7 +731,7 @@ func TestLockPOLSafety1(t *testing.T) {
 	startTestRound(cs1, cs1.Height, 0)
 	<-newRoundCh
 	re := <-proposalCh
-	rs := re.(types.TMEventData).Unwrap().(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
+	rs := re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 	propBlock := rs.ProposalBlock
 
 	<-voteCh // prevote
@@ -781,7 +781,7 @@ func TestLockPOLSafety1(t *testing.T) {
 		re = <-proposalCh
 	}
 
-	rs = re.(types.TMEventData).Unwrap().(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
+	rs = re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 
 	if rs.LockedBlock != nil {
 		panic("we should not be locked!")
@@ -838,11 +838,11 @@ 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 := cs1.state.Params.BlockPartSizeBytes
+	partSize := cs1.state.ConsensusParams.BlockPartSizeBytes
 
 	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
 	timeoutProposeCh := subscribe(cs1.eventBus, types.EventQueryTimeoutPropose)
@@ -900,7 +900,7 @@ 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.ChainID, 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 {
@@ -937,7 +937,7 @@ func TestLockPOLSafety2(t *testing.T) {
 // TODO: Slashing
 
 /*
-func TestSlashingPrevotes(t *testing.T) {
+func TestStateSlashingPrevotes(t *testing.T) {
 	cs1, vss := randConsensusState(2)
 	vs2 := vss[1]
 
@@ -972,7 +972,7 @@ 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]
 
@@ -1017,11 +1017,11 @@ 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 := cs1.state.Params.BlockPartSizeBytes
+	partSize := cs1.state.ConsensusParams.BlockPartSizeBytes
 
 	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
 	timeoutWaitCh := subscribe(cs1.eventBus, types.EventQueryTimeoutWait)
@@ -1033,7 +1033,7 @@ func TestHalt1(t *testing.T) {
 	startTestRound(cs1, cs1.Height, 0)
 	<-newRoundCh
 	re := <-proposalCh
-	rs := re.(types.TMEventData).Unwrap().(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
+	rs := re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 	propBlock := rs.ProposalBlock
 	propBlockParts := propBlock.MakePartSet(partSize)
 
@@ -1056,7 +1056,7 @@ func TestHalt1(t *testing.T) {
 	// timeout to new round
 	<-timeoutWaitCh
 	re = <-newRoundCh
-	rs = re.(types.TMEventData).Unwrap().(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
+	rs = re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 
 	t.Log("### ONTO ROUND 1")
 	/*Round2
@@ -1074,7 +1074,7 @@ func TestHalt1(t *testing.T) {
 	// receiving that precommit should take us straight to commit
 	<-newBlockCh
 	re = <-newRoundCh
-	rs = re.(types.TMEventData).Unwrap().(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
+	rs = re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 
 	if rs.Height != 2 {
 		panic("expected height to increment")

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

@@ -1,148 +0,0 @@
-#!/usr/bin/env bash
-
-# Requires: killall command and jq JSON processor.
-
-# Get the parent directory of where this script is.
-SOURCE="${BASH_SOURCE[0]}"
-while [ -h "$SOURCE" ] ; do SOURCE="$(readlink "$SOURCE")"; done
-DIR="$( cd -P "$( dirname "$SOURCE" )/../.." && pwd )"
-
-# Change into that dir because we expect that.
-cd "$DIR" || exit 1
-
-# Make sure we have a tendermint command.
-if ! hash tendermint 2>/dev/null; then
-	make install
-fi
-
-# Make sure we have a cutWALUntil binary.
-cutWALUntil=./scripts/cutWALUntil/cutWALUntil
-cutWALUntilDir=$(dirname $cutWALUntil)
-if ! hash $cutWALUntil 2>/dev/null; then
-	cd "$cutWALUntilDir" && go build && cd - || exit 1
-fi
-
-TMHOME=$(mktemp -d)
-export TMHOME="$TMHOME"
-
-if [[ ! -d "$TMHOME" ]]; then
-	echo "Could not create temp directory"
-  exit 1
-else
-	echo "TMHOME: ${TMHOME}"
-fi
-
-# TODO: eventually we should replace with `tendermint init --test`
-DIR_TO_COPY=$HOME/.tendermint_test/consensus_state_test
-if [ ! -d "$DIR_TO_COPY" ]; then
-    echo "$DIR_TO_COPY does not exist. Please run: go test ./consensus"
-    exit 1
-fi
-echo "==> Copying ${DIR_TO_COPY} to ${TMHOME} directory..."
-cp -r "$DIR_TO_COPY"/* "$TMHOME"
-
-# preserve original genesis file because later it will be modified (see small_block2)
-cp "$TMHOME/genesis.json" "$TMHOME/genesis.json.bak"
-
-function reset(){
-	echo "==> Resetting tendermint..."
-	tendermint unsafe_reset_all
-	cp "$TMHOME/genesis.json.bak" "$TMHOME/genesis.json"
-}
-
-reset
-
-# function empty_block(){
-# 	echo "==> Starting tendermint..."
-# 	tendermint node --proxy_app=persistent_dummy &> /dev/null &
-# 	sleep 5
-# 	echo "==> Killing tendermint..."
-# 	killall tendermint
-
-# 	echo "==> Copying WAL log..."
-# 	$cutWALUntil "$TMHOME/data/cs.wal/wal" 1 consensus/test_data/new_empty_block.cswal
-# 	mv consensus/test_data/new_empty_block.cswal consensus/test_data/empty_block.cswal
-
-# 	reset
-# }
-
-function many_blocks(){
-	bash scripts/txs/random.sh 1000 36657 &> /dev/null &
-	PID=$!
-	echo "==> Starting tendermint..."
-	tendermint node --proxy_app=persistent_dummy &> /dev/null &
-	sleep 10
-	echo "==> Killing tendermint..."
-	kill -9 $PID
-	killall tendermint
-
-	echo "==> Copying WAL log..."
-	$cutWALUntil "$TMHOME/data/cs.wal/wal" 6 consensus/test_data/new_many_blocks.cswal
-	mv consensus/test_data/new_many_blocks.cswal consensus/test_data/many_blocks.cswal
-
-	reset
-}
-
-
-# function small_block1(){
-# 	bash scripts/txs/random.sh 1000 36657 &> /dev/null &
-# 	PID=$!
-# 	echo "==> Starting tendermint..."
-# 	tendermint node --proxy_app=persistent_dummy &> /dev/null &
-# 	sleep 10
-# 	echo "==> Killing tendermint..."
-# 	kill -9 $PID
-# 	killall tendermint
-
-# 	echo "==> Copying WAL log..."
-# 	$cutWALUntil "$TMHOME/data/cs.wal/wal" 1 consensus/test_data/new_small_block1.cswal
-# 	mv consensus/test_data/new_small_block1.cswal consensus/test_data/small_block1.cswal
-
-# 	reset
-# }
-
-
-# # block part size = 512
-# function small_block2(){
-# 	cat "$TMHOME/genesis.json" | jq '. + {consensus_params: {block_size_params: {max_bytes: 22020096}, block_gossip_params: {block_part_size_bytes: 512}}}' > "$TMHOME/new_genesis.json"
-# 	mv "$TMHOME/new_genesis.json" "$TMHOME/genesis.json"
-# 	bash scripts/txs/random.sh 1000 36657 &> /dev/null &
-# 	PID=$!
-# 	echo "==> Starting tendermint..."
-# 	tendermint node --proxy_app=persistent_dummy &> /dev/null &
-# 	sleep 5
-# 	echo "==> Killing tendermint..."
-# 	kill -9 $PID
-# 	killall tendermint
-
-# 	echo "==> Copying WAL log..."
-# 	$cutWALUntil "$TMHOME/data/cs.wal/wal" 1 consensus/test_data/new_small_block2.cswal
-# 	mv consensus/test_data/new_small_block2.cswal consensus/test_data/small_block2.cswal
-
-# 	reset
-# }
-
-
-
-case "$1" in
-	# "small_block1")
-	# 	small_block1
-	# 	;;
-	# "small_block2")
-	# 	small_block2
-	# 	;;
-	# "empty_block")
-	# 	empty_block
-	# 	;;
-	"many_blocks")
-		many_blocks
-		;;
-	*)
-		# small_block1
-		# small_block2
-		# empty_block
-		many_blocks
-esac
-
-echo "==> Cleaning up..."
-rm -rf "$TMHOME"

consensus/ticker.go

@@ -68,7 +68,7 @@ func (t *timeoutTicker) Chan() <-chan timeoutInfo {
 }
 
 // ScheduleTimeout schedules a new timeout by sending on the internal tickChan.
-// The timeoutRoutine is alwaya available to read from tickChan, so this won't block.
+// 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
@@ -127,7 +127,7 @@ func (t *timeoutTicker) timeoutRoutine() {
 			// 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

@@ -1,9 +1,12 @@
 package types
 
 import (
+	"errors"
+	"fmt"
 	"strings"
 	"sync"
 
+	"github.com/tendermint/tendermint/p2p"
 	"github.com/tendermint/tendermint/types"
 	cmn "github.com/tendermint/tmlibs/common"
 )
@@ -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'.
 
@@ -35,7 +42,7 @@ type HeightVoteSet struct {
 	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 int64, valSet *types.ValidatorSet) *HeightVoteSet {
@@ -53,7 +60,7 @@ func (hvs *HeightVoteSet) Reset(height int64, valSet *types.ValidatorSet) {
 	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
@@ -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
 		}
 	}
@@ -169,6 +174,26 @@ func (hvs *HeightVoteSet) getVoteSet(round int, type_ byte) *types.VoteSet {
 	}
 }
 
+// If a peer claims that it has 2/3 majority for given blockKey, call this.
+// 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 p2p.ID, blockID types.BlockID) error {
+	hvs.mtx.Lock()
+	defer hvs.mtx.Unlock()
+	if !types.IsVoteTypeValid(type_) {
+		return fmt.Errorf("SetPeerMaj23: Invalid vote type %v", type_)
+	}
+	voteSet := hvs.getVoteSet(round, type_)
+	if voteSet == nil {
+		return nil // something we don't know about yet
+	}
+	return voteSet.SetPeerMaj23(types.P2PID(peerID), blockID)
+}
+
+//---------------------------------------------------------
+// string and json
+
 func (hvs *HeightVoteSet) String() string {
 	return hvs.StringIndented("")
 }
@@ -202,19 +227,35 @@ func (hvs *HeightVoteSet) StringIndented(indent string) string {
 		indent)
 }
 
-// If a peer claims that it has 2/3 majority for given blockKey, call this.
-// 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) MarshalJSON() ([]byte, error) {
 	hvs.mtx.Lock()
 	defer hvs.mtx.Unlock()
-	if !types.IsVoteTypeValid(type_) {
-		return
-	}
-	voteSet := hvs.getVoteSet(round, type_)
-	if voteSet == nil {
-		return
-	}
-	voteSet.SetPeerMaj23(peerID, blockID)
+
+	allVotes := hvs.toAllRoundVotes()
+	return cdc.MarshalJSON(allVotes)
+}
+
+func (hvs *HeightVoteSet) toAllRoundVotes() []roundVotes {
+	totalRounds := hvs.round + 1
+	allVotes := make([]roundVotes, totalRounds)
+	// rounds 0 ~ hvs.round inclusive
+	for round := 0; round < totalRounds; round++ {
+		allVotes[round] = roundVotes{
+			Round:              round,
+			Prevotes:           hvs.roundVoteSets[round].Prevotes.VoteStrings(),
+			PrevotesBitArray:   hvs.roundVoteSets[round].Prevotes.BitArrayString(),
+			Precommits:         hvs.roundVoteSets[round].Precommits.VoteStrings(),
+			PrecommitsBitArray: hvs.roundVoteSets[round].Precommits.BitArrayString(),
+		}
+	}
+	// TODO: all other peer catchup rounds
+	return allVotes
+}
+
+type roundVotes struct {
+	Round              int      `json:"round"`
+	Prevotes           []string `json:"prevotes"`
+	PrevotesBitArray   string   `json:"prevotes_bit_array"`
+	Precommits         []string `json:"precommits"`
+	PrecommitsBitArray string   `json:"precommits_bit_array"`
 }

consensus/types/height_vote_set_test.go

@@ -2,6 +2,7 @@ package types
 
 import (
 	"testing"
+	"time"
 
 	cfg "github.com/tendermint/tendermint/config"
 	"github.com/tendermint/tendermint/types"
@@ -17,7 +18,7 @@ func init() {
 func TestPeerCatchupRounds(t *testing.T) {
 	valSet, privVals := types.RandValidatorSet(10, 1)
 
-	hvs := NewHeightVoteSet(config.ChainID, 1, valSet)
+	hvs := NewHeightVoteSet(config.ChainID(), 1, valSet)
 
 	vote999_0 := makeVoteHR(t, 1, 999, privVals, 0)
 	added, err := hvs.AddVote(vote999_0, "peer1")
@@ -33,8 +34,8 @@ func TestPeerCatchupRounds(t *testing.T) {
 
 	vote1001_0 := makeVoteHR(t, 1, 1001, privVals, 0)
 	added, err = hvs.AddVote(vote1001_0, "peer1")
-	if err != nil {
-		t.Error("AddVote error", err)
+	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.")
@@ -47,17 +48,18 @@ func TestPeerCatchupRounds(t *testing.T) {
 
 }
 
-func makeVoteHR(t *testing.T, height int64, round int, privVals []*types.PrivValidatorFS, 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.GetAddress(),
 		ValidatorIndex:   valIndex,
 		Height:           height,
 		Round:            round,
+		Timestamp:        time.Now().UTC(),
 		Type:             types.VoteTypePrecommit,
 		BlockID:          types.BlockID{[]byte("fakehash"), types.PartSetHeader{}},
 	}
-	chainID := config.ChainID
+	chainID := config.ChainID()
 	err := privVal.SignVote(chainID, vote)
 	if err != nil {
 		panic(cmn.Fmt("Error signing vote: %v", err))

consensus/types/peer_round_state.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               `json:"height"`                      // Height peer is at
+	Round                    int                 `json:"round"`                       // Round peer is at, -1 if unknown.
+	Step                     RoundStepType       `json:"step"`                        // Step peer is at
+	StartTime                time.Time           `json:"start_time"`                  // Estimated start of round 0 at this height
+	Proposal                 bool                `json:"proposal"`                    // True if peer has proposal for this round
+	ProposalBlockPartsHeader types.PartSetHeader `json:"proposal_block_parts_header"` //
+	ProposalBlockParts       *cmn.BitArray       `json:"proposal_block_parts"`        //
+	ProposalPOLRound         int                 `json:"proposal_pol_round"`          // Proposal's POL round. -1 if none.
+	ProposalPOL              *cmn.BitArray       `json:"proposal_pol"`                // nil until ProposalPOLMessage received.
+	Prevotes                 *cmn.BitArray       `json:"prevotes"`                    // All votes peer has for this round
+	Precommits               *cmn.BitArray       `json:"precommits"`                  // All precommits peer has for this round
+	LastCommitRound          int                 `json:"last_commit_round"`           // Round of commit for last height. -1 if none.
+	LastCommit               *cmn.BitArray       `json:"last_commit"`                 // All commit precommits of commit for last height.
+	CatchupCommitRound       int                 `json:"catchup_commit_round"`        // Round that we have commit for. Not necessarily unique. -1 if none.
+	CatchupCommit            *cmn.BitArray       `json:"catchup_commit"`              // 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/reactor.go

@@ -1,57 +0,0 @@
-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/round_state.go

@@ -1,10 +1,12 @@
 package types
 
 import (
+	"encoding/json"
 	"fmt"
 	"time"
 
 	"github.com/tendermint/tendermint/types"
+	cmn "github.com/tendermint/tmlibs/common"
 )
 
 //-----------------------------------------------------------------------------
@@ -13,6 +15,7 @@ import (
 // RoundStepType enumerates the state of the consensus state machine
 type RoundStepType uint8 // These must be numeric, ordered.
 
+// RoundStepType
 const (
 	RoundStepNewHeight     = RoundStepType(0x01) // Wait til CommitTime + timeoutCommit
 	RoundStepNewRound      = RoundStepType(0x02) // Setup new round and go to RoundStepPropose
@@ -52,40 +55,66 @@ func (rs RoundStepType) String() string {
 //-----------------------------------------------------------------------------
 
 // RoundState defines the internal consensus state.
-// It is Immutable when returned from ConsensusState.GetRoundState()
-// TODO: Actually, only the top pointer is copied,
-// so access to field pointers is still racey
 // 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
-	Votes              *HeightVoteSet
-	CommitRound        int            //
-	LastCommit         *types.VoteSet // Last precommits at Height-1
-	LastValidators     *types.ValidatorSet
+	Height             int64               `json:"height"` // Height we are working on
+	Round              int                 `json:"round"`
+	Step               RoundStepType       `json:"step"`
+	StartTime          time.Time           `json:"start_time"`
+	CommitTime         time.Time           `json:"commit_time"` // Subjective time when +2/3 precommits for Block at Round were found
+	Validators         *types.ValidatorSet `json:"validators"`
+	Proposal           *types.Proposal     `json:"proposal"`
+	ProposalBlock      *types.Block        `json:"proposal_block"`
+	ProposalBlockParts *types.PartSet      `json:"proposal_block_parts"`
+	LockedRound        int                 `json:"locked_round"`
+	LockedBlock        *types.Block        `json:"locked_block"`
+	LockedBlockParts   *types.PartSet      `json:"locked_block_parts"`
+	ValidRound         int                 `json:"valid_round"`       // Last known round with POL for non-nil valid block.
+	ValidBlock         *types.Block        `json:"valid_block"`       // Last known block of POL mentioned above.
+	ValidBlockParts    *types.PartSet      `json:"valid_block_parts"` // Last known block parts of POL metnioned above.
+	Votes              *HeightVoteSet      `json:"votes"`
+	CommitRound        int                 `json:"commit_round"` //
+	LastCommit         *types.VoteSet      `json:"last_commit"`  // Last precommits at Height-1
+	LastValidators     *types.ValidatorSet `json:"last_validators"`
+}
+
+// Compressed version of the RoundState for use in RPC
+type RoundStateSimple struct {
+	HeightRoundStep   string          `json:"height/round/step"`
+	StartTime         time.Time       `json:"start_time"`
+	ProposalBlockHash cmn.HexBytes    `json:"proposal_block_hash"`
+	LockedBlockHash   cmn.HexBytes    `json:"locked_block_hash"`
+	ValidBlockHash    cmn.HexBytes    `json:"valid_block_hash"`
+	Votes             json.RawMessage `json:"height_vote_set"`
+}
+
+// Compress the RoundState to RoundStateSimple
+func (rs *RoundState) RoundStateSimple() RoundStateSimple {
+	votesJSON, err := rs.Votes.MarshalJSON()
+	if err != nil {
+		panic(err)
+	}
+	return RoundStateSimple{
+		HeightRoundStep:   fmt.Sprintf("%d/%d/%d", rs.Height, rs.Round, rs.Step),
+		StartTime:         rs.StartTime,
+		ProposalBlockHash: rs.ProposalBlock.Hash(),
+		LockedBlockHash:   rs.LockedBlock.Hash(),
+		ValidBlockHash:    rs.ValidBlock.Hash(),
+		Votes:             votesJSON,
+	}
 }
 
 // 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
+	rsCopy := *rs
 	edrs := types.EventDataRoundState{
 		Height:     rs.Height,
 		Round:      rs.Round,
 		Step:       rs.Step.String(),
-		RoundState: &rs_,
+		RoundState: &rsCopy,
 	}
 	return edrs
 }
@@ -106,21 +135,25 @@ func (rs *RoundState) StringIndented(indent string) string {
 %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  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.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.Votes.StringIndented(indent+"    "),
+		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, rs.LastValidators.StringIndented(indent+"  "),
 		indent)
 }
 

consensus/types/round_state_test.go

@@ -0,0 +1,95 @@
+package types
+
+import (
+	"testing"
+	"time"
+
+	"github.com/tendermint/go-amino"
+	"github.com/tendermint/go-crypto"
+	"github.com/tendermint/tendermint/types"
+	cmn "github.com/tendermint/tmlibs/common"
+)
+
+func BenchmarkRoundStateDeepCopy(b *testing.B) {
+	b.StopTimer()
+
+	// Random validators
+	nval, ntxs := 100, 100
+	vset, _ := types.RandValidatorSet(nval, 1)
+	precommits := make([]*types.Vote, nval)
+	blockID := types.BlockID{
+		Hash: cmn.RandBytes(20),
+		PartsHeader: types.PartSetHeader{
+			Hash: cmn.RandBytes(20),
+		},
+	}
+	sig := crypto.SignatureEd25519{}
+	for i := 0; i < nval; i++ {
+		precommits[i] = &types.Vote{
+			ValidatorAddress: types.Address(cmn.RandBytes(20)),
+			Timestamp:        time.Now(),
+			BlockID:          blockID,
+			Signature:        sig,
+		}
+	}
+	txs := make([]types.Tx, ntxs)
+	for i := 0; i < ntxs; i++ {
+		txs[i] = cmn.RandBytes(100)
+	}
+	// Random block
+	block := &types.Block{
+		Header: &types.Header{
+			ChainID:         cmn.RandStr(12),
+			Time:            time.Now(),
+			LastBlockID:     blockID,
+			LastCommitHash:  cmn.RandBytes(20),
+			DataHash:        cmn.RandBytes(20),
+			ValidatorsHash:  cmn.RandBytes(20),
+			ConsensusHash:   cmn.RandBytes(20),
+			AppHash:         cmn.RandBytes(20),
+			LastResultsHash: cmn.RandBytes(20),
+			EvidenceHash:    cmn.RandBytes(20),
+		},
+		Data: &types.Data{
+			Txs: txs,
+		},
+		Evidence: types.EvidenceData{},
+		LastCommit: &types.Commit{
+			BlockID:    blockID,
+			Precommits: precommits,
+		},
+	}
+	parts := block.MakePartSet(4096)
+	// Random Proposal
+	proposal := &types.Proposal{
+		Timestamp: time.Now(),
+		BlockPartsHeader: types.PartSetHeader{
+			Hash: cmn.RandBytes(20),
+		},
+		POLBlockID: blockID,
+		Signature:  sig,
+	}
+	// Random HeightVoteSet
+	// TODO: hvs :=
+
+	rs := &RoundState{
+		StartTime:          time.Now(),
+		CommitTime:         time.Now(),
+		Validators:         vset,
+		Proposal:           proposal,
+		ProposalBlock:      block,
+		ProposalBlockParts: parts,
+		LockedBlock:        block,
+		LockedBlockParts:   parts,
+		ValidBlock:         block,
+		ValidBlockParts:    parts,
+		Votes:              nil, // TODO
+		LastCommit:         nil, // TODO
+		LastValidators:     vset,
+	}
+	b.StartTimer()
+
+	for i := 0; i < b.N; i++ {
+		amino.DeepCopy(rs)
+	}
+}

consensus/types/wire.go

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

consensus/wal.go

@@ -1,7 +1,6 @@
 package consensus
 
 import (
-	"bytes"
 	"encoding/binary"
 	"fmt"
 	"hash/crc32"
@@ -11,48 +10,50 @@ import (
 
 	"github.com/pkg/errors"
 
-	wire "github.com/tendermint/go-wire"
+	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
 
-var (
-	walSeparator = []byte{55, 127, 6, 130} // 0x377f0682 - magic number
-)
-
 type TimedWALMessage struct {
 	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/cutWALUntil util.
+// @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},
-	wire.ConcreteType{EndHeightMessage{}, 0x04},
-)
+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)
+	Write(WALMessage)
+	WriteSync(WALMessage)
 	Group() *auto.Group
-	SearchForEndHeight(height int64) (gr *auto.GroupReader, found bool, err error)
+	SearchForEndHeight(height int64, options *WALSearchOptions) (gr *auto.GroupReader, found bool, err error)
 
 	Start() error
 	Stop() error
@@ -67,12 +68,11 @@ type baseWAL struct {
 	cmn.BaseService
 
 	group *auto.Group
-	light bool // ignore block parts
 
 	enc *WALEncoder
 }
 
-func NewWAL(walFile string, light bool) (*baseWAL, error) {
+func NewWAL(walFile string) (*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")
@@ -84,7 +84,6 @@ func NewWAL(walFile string, light bool) (*baseWAL, error) {
 	}
 	wal := &baseWAL{
 		group: group,
-		light: light,
 		enc:   NewWALEncoder(group),
 	}
 	wal.BaseService = *cmn.NewBaseService(nil, "baseWAL", wal)
@@ -100,50 +99,59 @@ func (wal *baseWAL) OnStart() error {
 	if err != nil {
 		return err
 	} else if size == 0 {
-		wal.Save(EndHeightMessage{0})
+		wal.WriteSync(EndHeightMessage{0})
 	}
 	err = wal.group.Start()
 	return err
 }
 
 func (wal *baseWAL) OnStop() {
-	wal.BaseService.OnStop()
 	wal.group.Stop()
+	wal.group.Close()
 }
 
-// called in newStep and for each pass in receiveRoutine
-func (wal *baseWAL) Save(msg WALMessage) {
+// Write is called in newStep and for each receive on the
+// peerMsgQueue and the timeoutTicker.
+// NOTE: does not call fsync()
+func (wal *baseWAL) Write(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 := msg.(msgInfo); ok {
-			if mi.PeerKey != "" {
-				return
-			}
-		}
-	}
-
 	// Write the wal message
 	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))
+		panic(cmn.Fmt("Error writing msg to consensus wal: %v \n\nMessage: %v", err, msg))
 	}
 }
 
-// SearchForEndHeight searches for the EndHeightMessage with the height and
-// returns an auto.GroupReader, whenever it was found or not and an error.
+// WriteSync is called when we receive a msg from ourselves
+// so that we write to disk before sending signed messages.
+// NOTE: calls fsync()
+func (wal *baseWAL) WriteSync(msg WALMessage) {
+	if wal == nil {
+		return
+	}
+
+	wal.Write(msg)
+	if err := wal.group.Flush(); err != nil {
+		panic(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 given 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) (gr *auto.GroupReader, found bool, err error) {
+func (wal *baseWAL) SearchForEndHeight(height int64, options *WALSearchOptions) (gr *auto.GroupReader, found bool, err error) {
 	var msg *TimedWALMessage
+	lastHeightFound := int64(-1)
 
 	// NOTE: starting from the last file in the group because we're usually
 	// searching for the last height. See replay.go
@@ -159,15 +167,25 @@ func (wal *baseWAL) SearchForEndHeight(height int64) (gr *auto.GroupReader, foun
 		for {
 			msg, err = dec.Decode()
 			if err == io.EOF {
+				// OPTIMISATION: no need to look for height in older files if we've seen h < height
+				if lastHeightFound > 0 && lastHeightFound < height {
+					gr.Close()
+					return nil, false, nil
+				}
 				// check next file
 				break
 			}
-			if err != nil {
+			if options.IgnoreDataCorruptionErrors && IsDataCorruptionError(err) {
+				wal.Logger.Debug("Corrupted entry. Skipping...", "err", err)
+				// do nothing
+				continue
+			} else if err != nil {
 				gr.Close()
 				return nil, false, err
 			}
 
 			if m, ok := msg.Msg.(EndHeightMessage); ok {
+				lastHeightFound = m.Height
 				if m.Height == height { // found
 					wal.Logger.Debug("Found", "height", height, "index", index)
 					return gr, true, nil
@@ -184,7 +202,7 @@ func (wal *baseWAL) SearchForEndHeight(height int64) (gr *auto.GroupReader, foun
 
 // A WALEncoder writes custom-encoded WAL messages to an output stream.
 //
-// Format: 4 bytes CRC sum + 4 bytes length + arbitrary-length value (go-wire encoded)
+// Format: 4 bytes CRC sum + 4 bytes length + arbitrary-length value (go-amino encoded)
 type WALEncoder struct {
 	wr io.Writer
 }
@@ -195,8 +213,8 @@ func NewWALEncoder(wr io.Writer) *WALEncoder {
 }
 
 // Encode writes the custom encoding of v to the stream.
-func (enc *WALEncoder) Encode(v interface{}) error {
-	data := wire.BinaryBytes(v)
+func (enc *WALEncoder) Encode(v *TimedWALMessage) error {
+	data := cdc.MustMarshalBinaryBare(v)
 
 	crc := crc32.Checksum(data, crc32c)
 	length := uint32(len(data))
@@ -209,16 +227,30 @@ func (enc *WALEncoder) Encode(v interface{}) error {
 
 	_, err := enc.wr.Write(msg)
 
-	if err == nil {
-		// TODO [Anton Kaliaev 23 Oct 2017]: remove separator
-		_, err = enc.wr.Write(walSeparator)
-	}
-
 	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.
 //
@@ -237,7 +269,7 @@ func NewWALDecoder(rd io.Reader) *WALDecoder {
 func (dec *WALDecoder) Decode() (*TimedWALMessage, error) {
 	b := make([]byte, 4)
 
-	n, err := dec.rd.Read(b)
+	_, err := dec.rd.Read(b)
 	if err == io.EOF {
 		return nil, err
 	}
@@ -247,64 +279,43 @@ func (dec *WALDecoder) Decode() (*TimedWALMessage, error) {
 	crc := binary.BigEndian.Uint32(b)
 
 	b = make([]byte, 4)
-	n, err = dec.rd.Read(b)
-	if err == io.EOF {
-		return nil, err
-	}
+	_, err = dec.rd.Read(b)
 	if err != nil {
 		return nil, fmt.Errorf("failed to read length: %v", err)
 	}
 	length := binary.BigEndian.Uint32(b)
 
-	data := make([]byte, length)
-	n, err = dec.rd.Read(data)
-	if err == io.EOF {
-		return nil, err
+	if length > maxMsgSizeBytes {
+		return nil, fmt.Errorf("length %d exceeded maximum possible value of %d bytes", length, maxMsgSizeBytes)
 	}
+
+	data := make([]byte, length)
+	_, err = dec.rd.Read(data)
 	if err != nil {
-		return nil, fmt.Errorf("not enough bytes for data: %v (want: %d, read: %v)", err, length, n)
+		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, fmt.Errorf("checksums do not match: (read: %v, actual: %v)", crc, actualCRC)
+		return nil, DataCorruptionError{fmt.Errorf("checksums do not match: (read: %v, actual: %v)", crc, actualCRC)}
 	}
 
-	var nn int
-	var res *TimedWALMessage // nolint: gosimple
-	res = wire.ReadBinary(&TimedWALMessage{}, bytes.NewBuffer(data), int(length), &nn, &err).(*TimedWALMessage)
+	var res = new(TimedWALMessage) // nolint: gosimple
+	err = cdc.UnmarshalBinaryBare(data, res)
 	if err != nil {
-		return nil, fmt.Errorf("failed to decode data: %v", err)
-	}
-
-	// TODO [Anton Kaliaev 23 Oct 2017]: remove separator
-	if err = readSeparator(dec.rd); err != nil {
-		return nil, err
+		return nil, DataCorruptionError{fmt.Errorf("failed to decode data: %v", err)}
 	}
 
 	return res, err
 }
 
-// readSeparator reads a separator from r. It returns any error from underlying
-// reader or if it's not a separator.
-func readSeparator(r io.Reader) error {
-	b := make([]byte, len(walSeparator))
-	_, err := r.Read(b)
-	if err != nil {
-		return fmt.Errorf("failed to read separator: %v", err)
-	}
-	if !bytes.Equal(b, walSeparator) {
-		return fmt.Errorf("not a separator: %v", b)
-	}
-	return nil
-}
-
 type nilWAL struct{}
 
-func (nilWAL) Save(m WALMessage)  {}
-func (nilWAL) Group() *auto.Group { return nil }
-func (nilWAL) SearchForEndHeight(height int64) (gr *auto.GroupReader, found bool, err error) {
+func (nilWAL) Write(m WALMessage)     {}
+func (nilWAL) WriteSync(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 }

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 +1,205 @@
+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/privval"
+	"github.com/tendermint/tendermint/proxy"
+	sm "github.com/tendermint/tendermint/state"
+	"github.com/tendermint/tendermint/types"
+	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 := privval.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)
+	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 := sm.MockMempool{}
+	evpool := sm.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.Write(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) Write(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) WriteSync(m WALMessage) {
+	w.Write(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

@@ -3,12 +3,10 @@ package consensus
 import (
 	"bytes"
 	"crypto/rand"
-	"path"
-	"sync"
+	// "sync"
 	"testing"
 	"time"
 
-	wire "github.com/tendermint/go-wire"
 	"github.com/tendermint/tendermint/consensus/types"
 	tmtypes "github.com/tendermint/tendermint/types"
 	cmn "github.com/tendermint/tmlibs/common"
@@ -37,19 +35,25 @@ func TestWALEncoderDecoder(t *testing.T) {
 		decoded, err := dec.Decode()
 		require.NoError(t, err)
 
-		assert.Equal(t, msg.Time.Truncate(time.Millisecond), decoded.Time)
+		assert.Equal(t, msg.Time.UTC(), decoded.Time)
 		assert.Equal(t, msg.Msg, decoded.Msg)
 	}
 }
 
-func TestSearchForEndHeight(t *testing.T) {
-	wal, err := NewWAL(path.Join(data_dir, "many_blocks.cswal"), false)
+func TestWALSearchForEndHeight(t *testing.T) {
+	walBody, err := WALWithNBlocks(6)
+	if err != nil {
+		t.Fatal(err)
+	}
+	walFile := tempWALWithData(walBody)
+
+	wal, err := NewWAL(walFile)
 	if err != nil {
 		t.Fatal(err)
 	}
 
 	h := int64(3)
-	gr, found, err := wal.SearchForEndHeight(h)
+	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")
@@ -63,6 +67,7 @@ func TestSearchForEndHeight(t *testing.T) {
 	assert.Equal(t, rs.Height, h+1, cmn.Fmt("wrong height"))
 }
 
+/*
 var initOnce sync.Once
 
 func registerInterfacesOnce() {
@@ -73,6 +78,7 @@ func registerInterfacesOnce() {
 		)
 	})
 }
+*/
 
 func nBytes(n int) []byte {
 	buf := make([]byte, n)
@@ -81,7 +87,7 @@ func nBytes(n int) []byte {
 }
 
 func benchmarkWalDecode(b *testing.B, n int) {
-	registerInterfacesOnce()
+	// registerInterfacesOnce()
 
 	buf := new(bytes.Buffer)
 	enc := NewWALEncoder(buf)

consensus/wire.go

@@ -0,0 +1,14 @@
+package consensus
+
+import (
+	"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:
+      - "26656-26657:26656-26657"
+    environment:
+      - ID=0
+      - LOG=$${LOG:-tendermint.log}
+    volumes:
+      - ./build:/tendermint:Z
+    networks:
+      localnet:
+        ipv4_address: 192.167.10.2
+
+  node1:
+    container_name: node1
+    image: "tendermint/localnode"
+    ports:
+      - "26659-26660:26656-26657"
+    environment:
+      - ID=1
+      - LOG=$${LOG:-tendermint.log}
+    volumes:
+      - ./build:/tendermint:Z
+    networks:
+      localnet:
+        ipv4_address: 192.167.10.3
+
+  node2:
+    container_name: node2
+    image: "tendermint/localnode"
+    environment:
+      - ID=2
+      - LOG=$${LOG:-tendermint.log}
+    ports:
+      - "26661-26662:26656-26657"
+    volumes:
+      - ./build:/tendermint:Z
+    networks:
+      localnet:
+        ipv4_address: 192.167.10.4
+
+  node3:
+    container_name: node3
+    image: "tendermint/localnode"
+    environment:
+      - ID=3
+      - LOG=$${LOG:-tendermint.log}
+    ports:
+      - "26663-26664:26656-26657"
+    volumes:
+      - ./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
+

docs/.python-version

@@ -0,0 +1 @@
+2.7.14

docs/Makefile

@@ -12,6 +12,9 @@ BUILDDIR      = _build
 help:
 	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
 
+install:
+	@pip install -r requirements.txt
+
 .PHONY: help Makefile
 
 # Catch-all target: route all unknown targets to Sphinx using the new

docs/abci-cli.md

@@ -0,0 +1,329 @@
+# Using ABCI-CLI
+
+To facilitate testing and debugging of ABCI servers and simple apps, we
+built a CLI, the `abci-cli`, for sending ABCI messages from the command
+line.
+
+## Install
+
+Make sure you [have Go installed](https://golang.org/doc/install).
+
+Next, install the `abci-cli` tool and example applications:
+
+    go get -u github.com/tendermint/abci/cmd/abci-cli
+
+If this fails, you may need to use [dep](https://github.com/golang/dep)
+to get vendored dependencies:
+
+    cd $GOPATH/src/github.com/tendermint/abci
+    make get_tools
+    make get_vendor_deps
+    make install
+
+Now run `abci-cli` to see the list of commands:
+
+    Usage:
+      abci-cli [command]
+
+    Available Commands:
+      batch       Run a batch of abci commands against an application
+      check_tx    Validate a tx
+      commit      Commit the application state and return the Merkle root hash
+      console     Start an interactive abci console for multiple commands
+      counter     ABCI demo example
+      deliver_tx  Deliver a new tx to the application
+      kvstore       ABCI demo example
+      echo        Have the application echo a message
+      help        Help about any command
+      info        Get some info about the application
+      query       Query the application state
+      set_option  Set an options on the application
+
+    Flags:
+          --abci string      socket or grpc (default "socket")
+          --address string   address of application socket (default "tcp://127.0.0.1:26658")
+      -h, --help             help for abci-cli
+      -v, --verbose          print the command and results as if it were a console session
+
+    Use "abci-cli [command] --help" for more information about a command.
+
+## KVStore - First Example
+
+The `abci-cli` tool lets us send ABCI messages to our application, to
+help build and debug them.
+
+The most important messages are `deliver_tx`, `check_tx`, and `commit`,
+but there are others for convenience, configuration, and information
+purposes.
+
+We'll start a kvstore application, which was installed at the same time
+as `abci-cli` above. The kvstore just stores transactions in a merkle
+tree.
+
+Its code can be found
+[here](https://github.com/tendermint/abci/blob/master/cmd/abci-cli/abci-cli.go)
+and looks like:
+
+    func cmdKVStore(cmd *cobra.Command, args []string) error {
+        logger := log.NewTMLogger(log.NewSyncWriter(os.Stdout))
+    
+        // Create the application - in memory or persisted to disk
+        var app types.Application
+        if flagPersist == "" {
+            app = kvstore.NewKVStoreApplication()
+        } else {
+            app = kvstore.NewPersistentKVStoreApplication(flagPersist)
+            app.(*kvstore.PersistentKVStoreApplication).SetLogger(logger.With("module", "kvstore"))
+        }
+    
+        // Start the listener
+        srv, err := server.NewServer(flagAddrD, flagAbci, app)
+        if err != nil {
+            return err
+        }
+        srv.SetLogger(logger.With("module", "abci-server"))
+        if err := srv.Start(); err != nil {
+            return err
+        }
+    
+        // Wait forever
+        cmn.TrapSignal(func() {
+            // Cleanup
+            srv.Stop()
+        })
+        return nil
+    }
+
+Start by running:
+
+    abci-cli kvstore
+
+And in another terminal, run
+
+    abci-cli echo hello
+    abci-cli info
+
+You'll see something like:
+
+    -> data: hello
+    -> data.hex: 68656C6C6F
+
+and:
+
+    -> data: {"size":0}
+    -> data.hex: 7B2273697A65223A307D
+
+An ABCI application must provide two things:
+
+-   a socket server
+-   a handler for ABCI messages
+
+When we run the `abci-cli` tool we open a new connection to the
+application's socket server, send the given ABCI message, and wait for a
+response.
+
+The server may be generic for a particular language, and we provide a
+[reference implementation in
+Golang](https://github.com/tendermint/abci/tree/master/server). See the
+[list of other ABCI implementations](./ecosystem.html) for servers in
+other languages.
+
+The handler is specific to the application, and may be arbitrary, so
+long as it is deterministic and conforms to the ABCI interface
+specification.
+
+So when we run `abci-cli info`, we open a new connection to the ABCI
+server, which calls the `Info()` method on the application, which tells
+us the number of transactions in our Merkle tree.
+
+Now, since every command opens a new connection, we provide the
+`abci-cli console` and `abci-cli batch` commands, to allow multiple ABCI
+messages to be sent over a single connection.
+
+Running `abci-cli console` should drop you in an interactive console for
+speaking ABCI messages to your application.
+
+Try running these commands:
+
+    > echo hello
+    -> code: OK
+    -> data: hello
+    -> data.hex: 0x68656C6C6F
+
+    > info
+    -> code: OK
+    -> data: {"size":0}
+    -> data.hex: 0x7B2273697A65223A307D
+
+    > commit
+    -> code: OK
+    -> data.hex: 0x0000000000000000
+
+    > deliver_tx "abc"
+    -> code: OK
+
+    > info
+    -> code: OK
+    -> data: {"size":1}
+    -> data.hex: 0x7B2273697A65223A317D
+
+    > commit
+    -> code: OK
+    -> data.hex: 0x0200000000000000
+
+    > query "abc"
+    -> code: OK
+    -> log: exists
+    -> height: 0
+    -> value: abc
+    -> value.hex: 616263
+
+    > deliver_tx "def=xyz"
+    -> code: OK
+
+    > commit
+    -> code: OK
+    -> data.hex: 0x0400000000000000
+
+    > query "def"
+    -> code: OK
+    -> log: exists
+    -> height: 0
+    -> value: xyz
+    -> value.hex: 78797A
+
+Note that if we do `deliver_tx "abc"` it will store `(abc, abc)`, but if
+we do `deliver_tx "abc=efg"` it will store `(abc, efg)`.
+
+Similarly, you could put the commands in a file and run
+`abci-cli --verbose batch < myfile`.
+
+## Counter - Another Example
+
+Now that we've got the hang of it, let's try another application, the
+"counter" app.
+
+Like the kvstore app, its code can be found
+[here](https://github.com/tendermint/abci/blob/master/cmd/abci-cli/abci-cli.go)
+and looks like:
+
+    func cmdCounter(cmd *cobra.Command, args []string) error {
+    
+        app := counter.NewCounterApplication(flagSerial)
+    
+        logger := log.NewTMLogger(log.NewSyncWriter(os.Stdout))
+    
+        // Start the listener
+        srv, err := server.NewServer(flagAddrC, flagAbci, app)
+        if err != nil {
+            return err
+        }
+        srv.SetLogger(logger.With("module", "abci-server"))
+        if err := srv.Start(); err != nil {
+            return err
+        }
+    
+        // Wait forever
+        cmn.TrapSignal(func() {
+            // Cleanup
+            srv.Stop()
+        })
+        return nil
+    }
+
+The counter app doesn't use a Merkle tree, it just counts how many times
+we've sent a transaction, asked for a hash, or committed the state. The
+result of `commit` is just the number of transactions sent.
+
+This application has two modes: `serial=off` and `serial=on`.
+
+When `serial=on`, transactions must be a big-endian encoded incrementing
+integer, starting at 0.
+
+If `serial=off`, there are no restrictions on transactions.
+
+We can toggle the value of `serial` using the `set_option` ABCI message.
+
+When `serial=on`, some transactions are invalid. In a live blockchain,
+transactions collect in memory before they are committed into blocks. To
+avoid wasting resources on invalid transactions, ABCI provides the
+`check_tx` message, which application developers can use to accept or
+reject transactions, before they are stored in memory or gossipped to
+other peers.
+
+In this instance of the counter app, `check_tx` only allows transactions
+whose integer is greater than the last committed one.
+
+Let's kill the console and the kvstore application, and start the
+counter app:
+
+    abci-cli counter
+
+In another window, start the `abci-cli console`:
+
+    > set_option serial on
+    -> code: OK
+    -> log: OK (SetOption doesn't return anything.)
+
+    > check_tx 0x00
+    -> code: OK
+
+    > check_tx 0xff
+    -> code: OK
+
+    > deliver_tx 0x00
+    -> code: OK
+
+    > check_tx 0x00
+    -> code: BadNonce
+    -> log: Invalid nonce. Expected >= 1, got 0
+
+    > deliver_tx 0x01
+    -> code: OK
+
+    > deliver_tx 0x04
+    -> code: BadNonce
+    -> log: Invalid nonce. Expected 2, got 4
+
+    > info
+    -> code: OK
+    -> data: {"hashes":0,"txs":2}
+    -> data.hex: 0x7B22686173686573223A302C22747873223A327D
+
+This is a very simple application, but between `counter` and `kvstore`,
+its easy to see how you can build out arbitrary application states on
+top of the ABCI. [Hyperledger's
+Burrow](https://github.com/hyperledger/burrow) also runs atop ABCI,
+bringing with it Ethereum-like accounts, the Ethereum virtual-machine,
+Monax's permissioning scheme, and native contracts extensions.
+
+But the ultimate flexibility comes from being able to write the
+application easily in any language.
+
+We have implemented the counter in a number of languages [see the
+example directory](https://github.com/tendermint/abci/tree/master/example).
+
+To run the Node JS version, `cd` to `example/js` and run
+
+    node app.js
+
+(you'll have to kill the other counter application process). In another
+window, run the console and those previous ABCI commands. You should get
+the same results as for the Go version.
+
+## Bounties
+
+Want to write the counter app in your favorite language?! We'd be happy
+to add you to our [ecosystem](https://tendermint.com/ecosystem)! We're
+also offering [bounties](https://hackerone.com/tendermint/) for
+implementations in new languages!
+
+The `abci-cli` is designed strictly for testing and debugging. In a real
+deployment, the role of sending messages is taken by Tendermint, which
+connects to the app using three separate connections, each with its own
+pattern of messages.
+
+For more information, see the [application developers
+guide](./app-development.html). For examples of running an ABCI app with
+Tendermint, see the [getting started guide](./getting-started.html).
+Next is the ABCI specification.

docs/abci-cli.rst

@@ -1,292 +0,0 @@
-Using ABCI-CLI
-==============
-
-To facilitate testing and debugging of ABCI servers and simple apps, we
-built a CLI, the ``abci-cli``, for sending ABCI messages from the
-command line.
-
-Install
--------
-
-Make sure you `have Go installed <https://golang.org/doc/install>`__.
-
-Next, install the ``abci-cli`` tool and example applications:
-
-::
-
-    go get -u github.com/tendermint/abci/cmd/abci-cli
-
-If this fails, you may need to use ``glide`` to get vendored
-dependencies:
-
-::
-
-    go get github.com/Masterminds/glide
-    cd $GOPATH/src/github.com/tendermint/abci
-    glide install
-    go install ./cmd/abci-cli
-
-Now run ``abci-cli`` to see the list of commands:
-
-::
-
-    Usage:
-      abci-cli [command]
-
-    Available Commands:
-      batch       Run a batch of abci commands against an application
-      check_tx    Validate a tx
-      commit      Commit the application state and return the Merkle root hash
-      console     Start an interactive abci console for multiple commands
-      counter     ABCI demo example
-      deliver_tx  Deliver a new tx to the application
-      dummy       ABCI demo example
-      echo        Have the application echo a message
-      help        Help about any command
-      info        Get some info about the application
-      query       Query the application state
-      set_option  Set an options on the application
-
-    Flags:
-          --abci string      socket or grpc (default "socket")
-          --address string   address of application socket (default "tcp://127.0.0.1:46658")
-      -h, --help             help for abci-cli
-      -v, --verbose          print the command and results as if it were a console session
-
-                                          Use "abci-cli [command] --help" for more information about a command.
-
-
-Dummy - First Example
----------------------
-
-The ``abci-cli`` tool lets us send ABCI messages to our application, to
-help build and debug them.
-
-The most important messages are ``deliver_tx``, ``check_tx``, and
-``commit``, but there are others for convenience, configuration, and
-information purposes.
-
-Let's start a dummy application, which was installed at the same time as
-``abci-cli`` above. The dummy just stores transactions in a merkle tree:
-
-::
-
-    abci-cli dummy
-
-In another terminal, run
-
-::
-
-    abci-cli echo hello
-    abci-cli info
-
-You'll see something like:
-
-::
-
-    -> data: hello
-    -> data.hex: 68656C6C6F
-
-and:
-
-::
-
-    -> data: {"size":0}
-    -> data.hex: 7B2273697A65223A307D
-
-An ABCI application must provide two things:
-
--  a socket server
--  a handler for ABCI messages
-
-When we run the ``abci-cli`` tool we open a new connection to the
-application's socket server, send the given ABCI message, and wait for a
-response.
-
-The server may be generic for a particular language, and we provide a
-`reference implementation in
-Golang <https://github.com/tendermint/abci/tree/master/server>`__. See
-the `list of other ABCI
-implementations <./ecosystem.html>`__ for servers in
-other languages.
-
-The handler is specific to the application, and may be arbitrary, so
-long as it is deterministic and conforms to the ABCI interface
-specification.
-
-So when we run ``abci-cli info``, we open a new connection to the ABCI
-server, which calls the ``Info()`` method on the application, which
-tells us the number of transactions in our Merkle tree.
-
-Now, since every command opens a new connection, we provide the
-``abci-cli console`` and ``abci-cli batch`` commands, to allow multiple
-ABCI messages to be sent over a single connection.
-
-Running ``abci-cli console`` should drop you in an interactive console
-for speaking ABCI messages to your application.
-
-Try running these commands:
-
-::
-
-    > echo hello
-    -> code: OK
-    -> data: hello
-    -> data.hex: 0x68656C6C6F
-    
-    > info
-    -> code: OK
-    -> data: {"size":0}
-    -> data.hex: 0x7B2273697A65223A307D
-    
-    > commit
-    -> code: OK
-    
-    > deliver_tx "abc"
-    -> code: OK
-    
-    > info
-    -> code: OK
-    -> data: {"size":1}
-    -> data.hex: 0x7B2273697A65223A317D
-    
-    > commit
-    -> code: OK
-    -> data.hex: 0x49DFD15CCDACDEAE9728CB01FBB5E8688CA58B91
-    
-    > query "abc"
-    -> code: OK
-    -> log: exists
-    -> height: 0
-    -> value: abc
-    -> value.hex: 616263
-    
-    > deliver_tx "def=xyz"
-    -> code: OK
-    
-    > commit
-    -> code: OK
-    -> data.hex: 0x70102DB32280373FBF3F9F89DA2A20CE2CD62B0B
-    
-    > query "def"
-    -> code: OK
-    -> log: exists
-    -> height: 0
-    -> value: xyz
-    -> value.hex: 78797A
-
-Note that if we do ``deliver_tx "abc"`` it will store ``(abc, abc)``,
-but if we do ``deliver_tx "abc=efg"`` it will store ``(abc, efg)``.
-
-Similarly, you could put the commands in a file and run
-``abci-cli --verbose batch < myfile``.
-
-Counter - Another Example
--------------------------
-
-Now that we've got the hang of it, let's try another application, the
-"counter" app.
-
-The counter app doesn't use a Merkle tree, it just counts how many times
-we've sent a transaction, asked for a hash, or committed the state. The
-result of ``commit`` is just the number of transactions sent.
-
-This application has two modes: ``serial=off`` and ``serial=on``.
-
-When ``serial=on``, transactions must be a big-endian encoded
-incrementing integer, starting at 0.
-
-If ``serial=off``, there are no restrictions on transactions.
-
-We can toggle the value of ``serial`` using the ``set_option`` ABCI
-message.
-
-When ``serial=on``, some transactions are invalid. In a live blockchain,
-transactions collect in memory before they are committed into blocks. To
-avoid wasting resources on invalid transactions, ABCI provides the
-``check_tx`` message, which application developers can use to accept or
-reject transactions, before they are stored in memory or gossipped to
-other peers.
-
-In this instance of the counter app, ``check_tx`` only allows
-transactions whose integer is greater than the last committed one.
-
-Let's kill the console and the dummy application, and start the counter
-app:
-
-::
-
-    abci-cli counter
-
-In another window, start the ``abci-cli console``:
-
-::
-
-    > set_option serial on
-    -> code: OK
-    
-    > check_tx 0x00
-    -> code: OK
-    
-    > check_tx 0xff
-    -> code: OK
-    
-    > deliver_tx 0x00
-    -> code: OK
-    
-    > check_tx 0x00
-    -> code: BadNonce
-    -> log: Invalid nonce. Expected >= 1, got 0
-    
-    > deliver_tx 0x01
-    -> code: OK
-    
-    > deliver_tx 0x04
-    -> code: BadNonce
-    -> log: Invalid nonce. Expected 2, got 4
-    
-    > info
-    -> code: OK
-    -> data: {"hashes":0,"txs":2}
-    -> data.hex: 0x7B22686173686573223A302C22747873223A327D
-
-This is a very simple application, but between ``counter`` and
-``dummy``, its easy to see how you can build out arbitrary application
-states on top of the ABCI. `Hyperledger's
-Burrow <https://github.com/hyperledger/burrow>`__ also runs atop ABCI,
-bringing with it Ethereum-like accounts, the Ethereum virtual-machine,
-Monax's permissioning scheme, and native contracts extensions.
-
-But the ultimate flexibility comes from being able to write the
-application easily in any language.
-
-We have implemented the counter in a number of languages (see the
-example directory).
-
-To run the Node JS version, ``cd`` to ``example/js`` and run
-
-::
-
-    node app.js
-
-(you'll have to kill the other counter application process). In another
-window, run the console and those previous ABCI commands. You should get
-the same results as for the Go version.
-
-Bounties
---------
-
-Want to write the counter app in your favorite language?! We'd be happy
-to add you to our `ecosystem <https://tendermint.com/ecosystem>`__!
-We're also offering `bounties <https://tendermint.com/bounties>`__ for
-implementations in new languages!
-
-The ``abci-cli`` is designed strictly for testing and debugging. In a
-real deployment, the role of sending messages is taken by Tendermint,
-which connects to the app using three separate connections, each with
-its own pattern of messages.
-
-For more information, see the `application developers
-guide <./app-development.html>`__. For examples of running an ABCI
-app with Tendermint, see the `getting started
-guide <./getting-started.html>`__.

docs/app-architecture.md

@@ -0,0 +1,50 @@
+# Application Architecture Guide
+
+Here we provide a brief guide on the recommended architecture of a
+Tendermint blockchain application.
+
+The following diagram provides a superb example:
+
+<https://drive.google.com/open?id=1yR2XpRi9YCY9H9uMfcw8-RMJpvDyvjz9>
+
+The end-user application here is the Cosmos Voyager, at the bottom left.
+Voyager communicates with a REST API exposed by a local Light-Client
+Daemon. The Light-Client Daemon is an application specific program that
+communicates with Tendermint nodes and verifies Tendermint light-client
+proofs through the Tendermint Core RPC. The Tendermint Core process
+communicates with a local ABCI application, where the user query or
+transaction is actually processed.
+
+The ABCI application must be a deterministic result of the Tendermint
+consensus - any external influence on the application state that didn't
+come through Tendermint could cause a consensus failure. Thus *nothing*
+should communicate with the application except Tendermint via ABCI.
+
+If the application is written in Go, it can be compiled into the
+Tendermint binary. Otherwise, it should use a unix socket to communicate
+with Tendermint. If it's necessary to use TCP, extra care must be taken
+to encrypt and authenticate the connection.
+
+All reads from the app happen through the Tendermint `/abci_query`
+endpoint. All writes to the app happen through the Tendermint
+`/broadcast_tx_*` endpoints.
+
+The Light-Client Daemon is what provides light clients (end users) with
+nearly all the security of a full node. It formats and broadcasts
+transactions, and verifies proofs of queries and transaction results.
+Note that it need not be a daemon - the Light-Client logic could instead
+be implemented in the same process as the end-user application.
+
+Note for those ABCI applications with weaker security requirements, the
+functionality of the Light-Client Daemon can be moved into the ABCI
+application process itself. That said, exposing the application process
+to anything besides Tendermint over ABCI requires extreme caution, as
+all transactions, and possibly all queries, should still pass through
+Tendermint.
+
+See the following for more extensive documentation:
+- [Interchain Standard for the Light-Client REST API](https://github.com/cosmos/cosmos-sdk/pull/1028)
+- [Tendermint RPC Docs](https://tendermint.github.io/slate/)
+- [Tendermint in Production](https://github.com/tendermint/tendermint/pull/1618)
+- [Tendermint Basics](https://tendermint.readthedocs.io/en/master/using-tendermint.html)
+- [ABCI spec](https://github.com/tendermint/abci/blob/develop/specification.md)

docs/app-architecture.rst

@@ -1,125 +0,0 @@
-Application Architecture Guide
-==============================
-
-Overview
---------
-
-A blockchain application is more than the consensus engine and the
-transaction logic (eg. smart contracts, business logic) as implemented
-in the ABCI app. There are also (mobile, web, desktop) clients that will
-need to connect and make use of the app. We will assume for now that you
-have a well designed transactions and database model, but maybe this
-will be the topic of another article. This article is more interested in
-various ways of setting up the "plumbing" and connecting these pieces,
-and demonstrating some evolving best practices.
-
-Security
---------
-
-A very important aspect when constructing a blockchain is security. The
-consensus model can be DoSed (no consensus possible) by corrupting 1/3
-of the validators and exploited (writing arbitrary blocks) by corrupting
-2/3 of the validators. So, while the security is not that of the
-"weakest link", you should take care that the "average link" is
-sufficiently hardened.
-
-One big attack surface on the validators is the communication between
-the ABCI app and the tendermint core. This should be highly protected.
-Ideally, the app and the core are running on the same machine, so no
-external agent can target the communication channel. You can use unix
-sockets (with permissions preventing access from other users), or even
-compile the two apps into one binary if the ABCI app is also writen in
-go. If you are unable to do that due to language support, then the ABCI
-app should bind a TCP connection to localhost (127.0.0.1), which is less
-efficient and secure, but still not reachable from outside. If you must
-run the ABCI app and tendermint core on separate machines, make sure you
-have a secure communication channel (ssh tunnel?)
-
-Now assuming, you have linked together your app and the core securely,
-you must also make sure no one can get on the machine it is hosted on.
-At this point it is basic network security. Run on a secure operating
-system (SELinux?). Limit who has access to the machine (user accounts,
-but also where the physical machine is hosted). Turn off all services
-except for ssh, which should only be accessible by some well-guarded
-public/private key pairs (no password). And maybe even firewall off
-access to the ports used by the validators, so only known validators can
-connect.
-
-There was also a suggestion on slack from @jhon about compiling
-everything together with a unikernel for more security, such as
-`Mirage <https://mirage.io>`__ or
-`UNIK <https://github.com/emc-advanced-dev/unik>`__.
-
-Connecting your client to the blockchain
-----------------------------------------
-
-Tendermint Core RPC
-~~~~~~~~~~~~~~~~~~~
-
-The concept is that the ABCI app is completely hidden from the outside
-world and only communicated through a tested and secured `interface
-exposed by the tendermint core <./specification/rpc.html>`__. This interface
-exposes a lot of data on the block header and consensus process, which
-is quite useful for externally verifying the system. It also includes
-3(!) methods to broadcast a transaction (propose it for the blockchain,
-and possibly await a response). And one method to query app-specific
-data from the ABCI application.
-
-Pros:
-* Server code already written
-* Access to block headers to validate merkle proofs (nice for light clients)
-* Basic read/write functionality is supported
-
-Cons:
-* Limited interface to app. All queries must be serialized into
-[]byte (less expressive than JSON over HTTP) and there is no way to push
-data from ABCI app to the client (eg. notify me if account X receives a
-transaction)
-
-Custom ABCI server
-~~~~~~~~~~~~~~~~~~
-
-This was proposed by @wolfposd on slack and demonstrated by
-`TMChat <https://github.com/wolfposd/TMChat>`__, a sample app. The
-concept is to write a custom server for your app (with typical REST
-API/websockets/etc for easy use by a mobile app). This custom server is
-in the same binary as the ABCI app and data store, so can easily react
-to complex events there that involve understanding the data format (send
-a message if my balance drops below 500). All "writes" sent to this
-server are proxied via websocket/JSON-RPC to tendermint core. When they
-come back as deliver\_tx over ABCI, they will be written to the data
-store. For "reads", we can do any queries we wish that are supported by
-our architecture, using any web technology that is useful. The general
-architecture is shown in the following diagram:
-
-Pros: \* Separates application logic from blockchain logic \* Allows
-much richer, more flexible client-facing API \* Allows pub-sub, watching
-certain fields, etc.
-
-Cons: \* Access to ABCI app can be dangerous (be VERY careful not to
-write unless it comes from the validator node) \* No direct access to
-the blockchain headers to verify tx \* You must write your own API (but
-maybe that's a pro...)
-
-Hybrid solutions
-~~~~~~~~~~~~~~~~
-
-Likely the least secure but most versatile. The client can access both
-the tendermint node for all blockchain info, as well as a custom app
-server, for complex queries and pub-sub on the abci app.
-
-Pros: All from both above solutions
-
-Cons: Even more complexity; even more attack vectors (less
-security)
-
-Scalability
------------
-
-Read replica using non-validating nodes? They could forward transactions
-to the validators (fewer connections, more security), and locally allow
-all queries in any of the above configurations. Thus, while
-transaction-processing speed is limited by the speed of the abci app and
-the number of validators, one should be able to scale our read
-performance to quite an extent (until the replication process drains too
-many resources from the validator nodes).

docs/app-development.md

@@ -0,0 +1,527 @@
+# Application Development Guide
+
+## ABCI Design
+
+The purpose of ABCI is to provide a clean interface between state
+transition machines on one computer and the mechanics of their
+replication across multiple computers. The former we call 'application
+logic' and the latter the 'consensus engine'. Application logic
+validates transactions and optionally executes transactions against some
+persistent state. A consensus engine ensures all transactions are
+replicated in the same order on every machine. We call each machine in a
+consensus engine a 'validator', and each validator runs the same
+transactions through the same application logic. In particular, we are
+interested in blockchain-style consensus engines, where transactions are
+committed in hash-linked blocks.
+
+The ABCI design has a few distinct components:
+
+-   message protocol
+    -   pairs of request and response messages
+    -   consensus makes requests, application responds
+    -   defined using protobuf
+-   server/client
+    -   consensus engine runs the client
+    -   application runs the server
+    -   two implementations:
+        -   async raw bytes
+        -   grpc
+-   blockchain protocol
+    -   abci is connection oriented
+    -   Tendermint Core maintains three connections:
+        -   [mempool connection](#mempool-connection): for checking if
+            transactions should be relayed before they are committed;
+            only uses `CheckTx`
+        -   [consensus connection](#consensus-connection): for executing
+            transactions that have been committed. Message sequence is
+            -for every block
+            -`BeginBlock, [DeliverTx, ...], EndBlock, Commit`
+        -   [query connection](#query-connection): for querying the
+            application state; only uses Query and Info
+
+The mempool and consensus logic act as clients, and each maintains an
+open ABCI connection with the application, which hosts an ABCI server.
+Shown are the request and response types sent on each connection.
+
+## Message Protocol
+
+The message protocol consists of pairs of requests and responses. Some
+messages have no fields, while others may include byte-arrays, strings,
+or integers. See the `message Request` and `message Response`
+definitions in [the protobuf definition
+file](https://github.com/tendermint/abci/blob/master/types/types.proto),
+and the [protobuf
+documentation](https://developers.google.com/protocol-buffers/docs/overview)
+for more details.
+
+For each request, a server should respond with the corresponding
+response, where order of requests is preserved in the order of
+responses.
+
+## Server
+
+To use ABCI in your programming language of choice, there must be a ABCI
+server in that language. Tendermint supports two kinds of implementation
+of the server:
+
+-   Asynchronous, raw socket server (Tendermint Socket Protocol, also
+    known as TSP or Teaspoon)
+-   GRPC
+
+Both can be tested using the `abci-cli` by setting the `--abci` flag
+appropriately (ie. to `socket` or `grpc`).
+
+See examples, in various stages of maintenance, in
+[Go](https://github.com/tendermint/abci/tree/master/server),
+[JavaScript](https://github.com/tendermint/js-abci),
+[Python](https://github.com/tendermint/abci/tree/master/example/python3/abci),
+[C++](https://github.com/mdyring/cpp-tmsp), and
+[Java](https://github.com/jTendermint/jabci).
+
+### GRPC
+
+If GRPC is available in your language, this is the easiest approach,
+though it will have significant performance overhead.
+
+To get started with GRPC, copy in the [protobuf
+file](https://github.com/tendermint/abci/blob/master/types/types.proto)
+and compile it using the GRPC plugin for your language. For instance,
+for golang, the command is `protoc --go_out=plugins=grpc:. types.proto`.
+See the [grpc documentation for more details](http://www.grpc.io/docs/).
+`protoc` will autogenerate all the necessary code for ABCI client and
+server in your language, including whatever interface your application
+must satisfy to be used by the ABCI server for handling requests.
+
+### TSP
+
+If GRPC is not available in your language, or you require higher
+performance, or otherwise enjoy programming, you may implement your own
+ABCI server using the Tendermint Socket Protocol, known affectionately
+as Teaspoon. The first step is still to auto-generate the relevant data
+types and codec in your language using `protoc`. Messages coming over
+the socket are Protobuf3 encoded, but additionally length-prefixed to
+facilitate use as a streaming protocol. Protobuf3 doesn't have an
+official length-prefix standard, so we use our own. The first byte in
+the prefix represents the length of the Big Endian encoded length. The
+remaining bytes in the prefix are the Big Endian encoded length.
+
+For example, if the Protobuf3 encoded ABCI message is 0xDEADBEEF (4
+bytes), the length-prefixed message is 0x0104DEADBEEF. If the Protobuf3
+encoded ABCI message is 65535 bytes long, the length-prefixed message
+would be like 0x02FFFF....
+
+Note this prefixing does not apply for grpc.
+
+An ABCI server must also be able to support multiple connections, as
+Tendermint uses three connections.
+
+## Client
+
+There are currently two use-cases for an ABCI client. One is a testing
+tool, as in the `abci-cli`, which allows ABCI requests to be sent via
+command line. The other is a consensus engine, such as Tendermint Core,
+which makes requests to the application every time a new transaction is
+received or a block is committed.
+
+It is unlikely that you will need to implement a client. For details of
+our client, see
+[here](https://github.com/tendermint/abci/tree/master/client).
+
+Most of the examples below are from [kvstore
+application](https://github.com/tendermint/abci/blob/master/example/kvstore/kvstore.go),
+which is a part of the abci repo. [persistent_kvstore
+application](https://github.com/tendermint/abci/blob/master/example/kvstore/persistent_kvstore.go)
+is used to show `BeginBlock`, `EndBlock` and `InitChain` example
+implementations.
+
+## Blockchain Protocol
+
+In ABCI, a transaction is simply an arbitrary length byte-array. It is
+the application's responsibility to define the transaction codec as they
+please, and to use it for both CheckTx and DeliverTx.
+
+Note that there are two distinct means for running transactions,
+corresponding to stages of 'awareness' of the transaction in the
+network. The first stage is when a transaction is received by a
+validator from a client into the so-called mempool or transaction pool
+-this is where we use CheckTx. The second is when the transaction is
+successfully committed on more than 2/3 of validators - where we use
+DeliverTx. In the former case, it may not be necessary to run all the
+state transitions associated with the transaction, as the transaction
+may not ultimately be committed until some much later time, when the
+result of its execution will be different. For instance, an Ethereum
+ABCI app would check signatures and amounts in CheckTx, but would not
+actually execute any contract code until the DeliverTx, so as to avoid
+executing state transitions that have not been finalized.
+
+To formalize the distinction further, two explicit ABCI connections are
+made between Tendermint Core and the application: the mempool connection
+and the consensus connection. We also make a third connection, the query
+connection, to query the local state of the app.
+
+### Mempool Connection
+
+The mempool connection is used *only* for CheckTx requests. Transactions
+are run using CheckTx in the same order they were received by the
+validator. If the CheckTx returns `OK`, the transaction is kept in
+memory and relayed to other peers in the same order it was received.
+Otherwise, it is discarded.
+
+CheckTx requests run concurrently with block processing; so they should
+run against a copy of the main application state which is reset after
+every block. This copy is necessary to track transitions made by a
+sequence of CheckTx requests before they are included in a block. When a
+block is committed, the application must ensure to reset the mempool
+state to the latest committed state. Tendermint Core will then filter
+through all transactions in the mempool, removing any that were included
+in the block, and re-run the rest using CheckTx against the post-Commit
+mempool state (this behaviour can be turned off with
+`[mempool] recheck = false`).
+
+In go:
+
+    func (app *KVStoreApplication) CheckTx(tx []byte) types.Result {
+      return types.OK
+    }
+
+In Java:
+
+    ResponseCheckTx requestCheckTx(RequestCheckTx req) {
+        byte[] transaction = req.getTx().toByteArray();
+    
+        // validate transaction
+    
+        if (notValid) {
+            return ResponseCheckTx.newBuilder().setCode(CodeType.BadNonce).setLog("invalid tx").build();
+        } else {
+            return ResponseCheckTx.newBuilder().setCode(CodeType.OK).build();
+        }
+    }
+
+### Replay Protection
+
+To prevent old transactions from being replayed, CheckTx must implement
+replay protection.
+
+Tendermint provides the first defence layer by keeping a lightweight
+in-memory cache of 100k (`[mempool] cache_size`) last transactions in
+the mempool. If Tendermint is just started or the clients sent more than
+100k transactions, old transactions may be sent to the application. So
+it is important CheckTx implements some logic to handle them.
+
+There are cases where a transaction will (or may) become valid in some
+future state, in which case you probably want to disable Tendermint's
+cache. You can do that by setting `[mempool] cache_size = 0` in the
+config.
+
+### Consensus Connection
+
+The consensus connection is used only when a new block is committed, and
+communicates all information from the block in a series of requests:
+`BeginBlock, [DeliverTx, ...], EndBlock, Commit`. That is, when a block
+is committed in the consensus, we send a list of DeliverTx requests (one
+for each transaction) sandwiched by BeginBlock and EndBlock requests,
+and followed by a Commit.
+
+### DeliverTx
+
+DeliverTx is the workhorse of the blockchain. Tendermint sends the
+DeliverTx requests asynchronously but in order, and relies on the
+underlying socket protocol (ie. TCP) to ensure they are received by the
+app in order. They have already been ordered in the global consensus by
+the Tendermint protocol.
+
+DeliverTx returns a abci.Result, which includes a Code, Data, and Log.
+The code may be non-zero (non-OK), meaning the corresponding transaction
+should have been rejected by the mempool, but may have been included in
+a block by a Byzantine proposer.
+
+The block header will be updated (TODO) to include some commitment to
+the results of DeliverTx, be it a bitarray of non-OK transactions, or a
+merkle root of the data returned by the DeliverTx requests, or both.
+
+In go:
+
+    // tx is either "key=value" or just arbitrary bytes
+    func (app *KVStoreApplication) DeliverTx(tx []byte) types.Result {
+      parts := strings.Split(string(tx), "=")
+      if len(parts) == 2 {
+        app.state.Set([]byte(parts[0]), []byte(parts[1]))
+      } else {
+        app.state.Set(tx, tx)
+      }
+      return types.OK
+    }
+
+In Java:
+
+    /**
+     * Using Protobuf types from the protoc compiler, we always start with a byte[]
+     */
+    ResponseDeliverTx deliverTx(RequestDeliverTx request) {
+        byte[] transaction  = request.getTx().toByteArray();
+    
+        // validate your transaction
+    
+        if (notValid) {
+            return ResponseDeliverTx.newBuilder().setCode(CodeType.BadNonce).setLog("transaction was invalid").build();
+        } else {
+            ResponseDeliverTx.newBuilder().setCode(CodeType.OK).build();
+        }
+    
+    }
+
+### Commit
+
+Once all processing of the block is complete, Tendermint sends the
+Commit request and blocks waiting for a response. While the mempool may
+run concurrently with block processing (the BeginBlock, DeliverTxs, and
+EndBlock), it is locked for the Commit request so that its state can be
+safely reset during Commit. This means the app *MUST NOT* do any
+blocking communication with the mempool (ie. broadcast\_tx) during
+Commit, or there will be deadlock. Note also that all remaining
+transactions in the mempool are replayed on the mempool connection
+(CheckTx) following a commit.
+
+The app should respond to the Commit request with a byte array, which is
+the deterministic state root of the application. It is included in the
+header of the next block. It can be used to provide easily verified
+Merkle-proofs of the state of the application.
+
+It is expected that the app will persist state to disk on Commit. The
+option to have all transactions replayed from some previous block is the
+job of the [Handshake](#handshake).
+
+In go:
+
+    func (app *KVStoreApplication) Commit() types.Result {
+      hash := app.state.Hash()
+      return types.NewResultOK(hash, "")
+    }
+
+In Java:
+
+    ResponseCommit requestCommit(RequestCommit requestCommit) {
+    
+        // update the internal app-state
+        byte[] newAppState = calculateAppState();
+    
+        // and return it to the node
+        return ResponseCommit.newBuilder().setCode(CodeType.OK).setData(ByteString.copyFrom(newAppState)).build();
+    }
+
+### BeginBlock
+
+The BeginBlock request can be used to run some code at the beginning of
+every block. It also allows Tendermint to send the current block hash
+and header to the application, before it sends any of the transactions.
+
+The app should remember the latest height and header (ie. from which it
+has run a successful Commit) so that it can tell Tendermint where to
+pick up from when it restarts. See information on the Handshake, below.
+
+In go:
+
+    // Track the block hash and header information
+    func (app *PersistentKVStoreApplication) BeginBlock(params types.RequestBeginBlock) {
+      // update latest block info
+      app.blockHeader = params.Header
+    
+      // reset valset changes
+      app.changes = make([]*types.Validator, 0)
+    }
+
+In Java:
+
+    /*
+     * all types come from protobuf definition
+     */
+    ResponseBeginBlock requestBeginBlock(RequestBeginBlock req) {
+    
+        Header header = req.getHeader();
+        byte[] prevAppHash = header.getAppHash().toByteArray();
+        long prevHeight = header.getHeight();
+        long numTxs = header.getNumTxs();
+    
+        // run your pre-block logic. Maybe prepare a state snapshot, message components, etc
+    
+        return ResponseBeginBlock.newBuilder().build();
+    }
+
+### EndBlock
+
+The EndBlock request can be used to run some code at the end of every
+block. Additionally, the response may contain a list of validators,
+which can be used to update the validator set. To add a new validator or
+update an existing one, simply include them in the list returned in the
+EndBlock response. To remove one, include it in the list with a `power`
+equal to `0`. Tendermint core will take care of updating the validator
+set. Note the change in voting power must be strictly less than 1/3 per
+block if you want a light client to be able to prove the transition
+externally. See the [light client
+docs](https://godoc.org/github.com/tendermint/tendermint/lite#hdr-How_We_Track_Validators)
+for details on how it tracks validators.
+
+In go:
+
+    // Update the validator set
+    func (app *PersistentKVStoreApplication) EndBlock(req types.RequestEndBlock) types.ResponseEndBlock {
+      return types.ResponseEndBlock{ValidatorUpdates: app.ValUpdates}
+    }
+
+In Java:
+
+    /*
+     * Assume that one validator changes. The new validator has a power of 10
+     */
+    ResponseEndBlock requestEndBlock(RequestEndBlock req) {
+        final long currentHeight = req.getHeight();
+        final byte[] validatorPubKey = getValPubKey();
+    
+        ResponseEndBlock.Builder builder = ResponseEndBlock.newBuilder();
+        builder.addDiffs(1, Types.Validator.newBuilder().setPower(10L).setPubKey(ByteString.copyFrom(validatorPubKey)).build());
+    
+        return builder.build();
+    }
+
+### Query Connection
+
+This connection is used to query the application without engaging
+consensus. It's exposed over the tendermint core rpc, so clients can
+query the app without exposing a server on the app itself, but they must
+serialize each query as a single byte array. Additionally, certain
+"standardized" queries may be used to inform local decisions, for
+instance about which peers to connect to.
+
+Tendermint Core currently uses the Query connection to filter peers upon
+connecting, according to IP address or public key. For instance,
+returning non-OK ABCI response to either of the following queries will
+cause Tendermint to not connect to the corresponding peer:
+
+-   `p2p/filter/addr/<addr>`, where `<addr>` is an IP address.
+-   `p2p/filter/pubkey/<pubkey>`, where `<pubkey>` is the hex-encoded
+    ED25519 key of the node (not it's validator key)
+
+Note: these query formats are subject to change!
+
+In go:
+
+    func (app *KVStoreApplication) Query(reqQuery types.RequestQuery) (resQuery types.ResponseQuery) {
+      if reqQuery.Prove {
+        value, proof, exists := app.state.Proof(reqQuery.Data)
+        resQuery.Index = -1 // TODO make Proof return index
+        resQuery.Key = reqQuery.Data
+        resQuery.Value = value
+        resQuery.Proof = proof
+        if exists {
+          resQuery.Log = "exists"
+        } else {
+          resQuery.Log = "does not exist"
+        }
+        return
+      } else {
+        index, value, exists := app.state.Get(reqQuery.Data)
+        resQuery.Index = int64(index)
+        resQuery.Value = value
+        if exists {
+          resQuery.Log = "exists"
+        } else {
+          resQuery.Log = "does not exist"
+        }
+        return
+      }
+    }
+
+In Java:
+
+    ResponseQuery requestQuery(RequestQuery req) {
+        final boolean isProveQuery = req.getProve();
+        final ResponseQuery.Builder responseBuilder = ResponseQuery.newBuilder();
+    
+        if (isProveQuery) {
+            com.app.example.ProofResult proofResult = generateProof(req.getData().toByteArray());
+            final byte[] proofAsByteArray = proofResult.getAsByteArray();
+    
+            responseBuilder.setProof(ByteString.copyFrom(proofAsByteArray));
+            responseBuilder.setKey(req.getData());
+            responseBuilder.setValue(ByteString.copyFrom(proofResult.getData()));
+            responseBuilder.setLog(result.getLogValue());
+        } else {
+            byte[] queryData = req.getData().toByteArray();
+    
+            final com.app.example.QueryResult result = generateQueryResult(queryData);
+    
+            responseBuilder.setIndex(result.getIndex());
+            responseBuilder.setValue(ByteString.copyFrom(result.getValue()));
+            responseBuilder.setLog(result.getLogValue());
+        }
+    
+        return responseBuilder.build();
+    }
+
+### Handshake
+
+When the app or tendermint restarts, they need to sync to a common
+height. When an ABCI connection is first established, Tendermint will
+call `Info` on the Query connection. The response should contain the
+LastBlockHeight and LastBlockAppHash - the former is the last block for
+which the app ran Commit successfully, the latter is the response from
+that Commit.
+
+Using this information, Tendermint will determine what needs to be
+replayed, if anything, against the app, to ensure both Tendermint and
+the app are synced to the latest block height.
+
+If the app returns a LastBlockHeight of 0, Tendermint will just replay
+all blocks.
+
+In go:
+
+    func (app *KVStoreApplication) Info(req types.RequestInfo) (resInfo types.ResponseInfo) {
+      return types.ResponseInfo{Data: cmn.Fmt("{\"size\":%v}", app.state.Size())}
+    }
+
+In Java:
+
+    ResponseInfo requestInfo(RequestInfo req) {
+        final byte[] lastAppHash = getLastAppHash();
+        final long lastHeight = getLastHeight();
+        return ResponseInfo.newBuilder().setLastBlockAppHash(ByteString.copyFrom(lastAppHash)).setLastBlockHeight(lastHeight).build();
+    }
+
+### Genesis
+
+`InitChain` will be called once upon the genesis. `params` includes the
+initial validator set. Later on, it may be extended to take parts of the
+consensus params.
+
+In go:
+
+    // Save the validators in the merkle tree
+    func (app *PersistentKVStoreApplication) InitChain(params types.RequestInitChain) {
+      for _, v := range params.Validators {
+        r := app.updateValidator(v)
+        if r.IsErr() {
+          app.logger.Error("Error updating validators", "r", r)
+        }
+      }
+    }
+
+In Java:
+
+    /*
+     * all types come from protobuf definition
+     */
+    ResponseInitChain requestInitChain(RequestInitChain req) {
+        final int validatorsCount = req.getValidatorsCount();
+        final List<Types.Validator> validatorsList = req.getValidatorsList();
+    
+        validatorsList.forEach((validator) -> {
+            long power = validator.getPower();
+            byte[] validatorPubKey = validator.getPubKey().toByteArray();
+    
+            // do somehing for validator setup in app
+        });
+    
+        return ResponseInitChain.newBuilder().build();
+    }

docs/app-development.rst

@@ -1,628 +0,0 @@
-Application Development Guide
-=============================
-
-ABCI Design
------------
-
-The purpose of ABCI is to provide a clean interface between state
-transition machines on one computer and the mechanics of their
-replication across multiple computers. The former we call 'application
-logic' and the latter the 'consensus engine'. Application logic
-validates transactions and optionally executes transactions against some
-persistent state. A consensus engine ensures all transactions are
-replicated in the same order on every machine. We call each machine in a
-consensus engine a 'validator', and each validator runs the same
-transactions through the same application logic. In particular, we are
-interested in blockchain-style consensus engines, where transactions are
-committed in hash-linked blocks.
-
-The ABCI design has a few distinct components:
-
--  message protocol
-
-   -  pairs of request and response messages
-   -  consensus makes requests, application responds
-   -  defined using protobuf
-
--  server/client
-
-   -  consensus engine runs the client
-   -  application runs the server
-   -  two implementations:
-
-      -  async raw bytes
-      -  grpc
-
--  blockchain protocol
-
-   -  abci is connection oriented
-   -  Tendermint Core maintains three connections:
-
-      -  `mempool connection <#mempool-connection>`__: for checking if
-         transactions should be relayed before they are committed; only
-         uses ``CheckTx``
-      -  `consensus connection <#consensus-connection>`__: for executing
-         transactions that have been committed. Message sequence is -
-         for every block -
-         ``BeginBlock, [DeliverTx, ...], EndBlock, Commit``
-      -  `query connection <#query-connection>`__: for querying the
-         application state; only uses Query and Info
-
-The mempool and consensus logic act as clients, and each maintains an
-open ABCI connection with the application, which hosts an ABCI server.
-Shown are the request and response types sent on each connection.
-
-Message Protocol
-----------------
-
-The message protocol consists of pairs of requests and responses. Some
-messages have no fields, while others may include byte-arrays, strings,
-or integers. See the ``message Request`` and ``message Response``
-definitions in `the protobuf definition
-file <https://github.com/tendermint/abci/blob/master/types/types.proto>`__,
-and the `protobuf
-documentation <https://developers.google.com/protocol-buffers/docs/overview>`__
-for more details.
-
-For each request, a server should respond with the corresponding
-response, where order of requests is preserved in the order of
-responses.
-
-Server
-------
-
-To use ABCI in your programming language of choice, there must be a ABCI
-server in that language. Tendermint supports two kinds of implementation
-of the server:
-
--  Asynchronous, raw socket server (Tendermint Socket Protocol, also
-   known as TSP or Teaspoon)
--  GRPC
-
-Both can be tested using the ``abci-cli`` by setting the ``--abci`` flag
-appropriately (ie. to ``socket`` or ``grpc``).
-
-See examples, in various stages of maintenance, in
-`Go <https://github.com/tendermint/abci/tree/master/server>`__,
-`JavaScript <https://github.com/tendermint/js-abci>`__,
-`Python <https://github.com/tendermint/abci/tree/master/example/python3/abci>`__,
-`C++ <https://github.com/mdyring/cpp-tmsp>`__, and
-`Java <https://github.com/jTendermint/jabci>`__.
-
-GRPC
-~~~~
-
-If GRPC is available in your language, this is the easiest approach,
-though it will have significant performance overhead.
-
-To get started with GRPC, copy in the `protobuf
-file <https://github.com/tendermint/abci/blob/master/types/types.proto>`__
-and compile it using the GRPC plugin for your language. For instance,
-for golang, the command is
-``protoc --go_out=plugins=grpc:. types.proto``. See the `grpc
-documentation for more details <http://www.grpc.io/docs/>`__. ``protoc``
-will autogenerate all the necessary code for ABCI client and server in
-your language, including whatever interface your application must
-satisfy to be used by the ABCI server for handling requests.
-
-TSP
-~~~
-
-If GRPC is not available in your language, or you require higher
-performance, or otherwise enjoy programming, you may implement your own
-ABCI server using the Tendermint Socket Protocol, known affectionately
-as Teaspoon. The first step is still to auto-generate the relevant data
-types and codec in your language using ``protoc``. Messages coming over
-the socket are Protobuf3 encoded, but additionally length-prefixed to
-facilitate use as a streaming protocol. Protobuf3 doesn't have an
-official length-prefix standard, so we use our own. The first byte in
-the prefix represents the length of the Big Endian encoded length. The
-remaining bytes in the prefix are the Big Endian encoded length.
-
-For example, if the Protobuf3 encoded ABCI message is 0xDEADBEEF (4
-bytes), the length-prefixed message is 0x0104DEADBEEF. If the Protobuf3
-encoded ABCI message is 65535 bytes long, the length-prefixed message
-would be like 0x02FFFF....
-
-Note this prefixing does not apply for grpc.
-
-An ABCI server must also be able to support multiple connections, as
-Tendermint uses three connections.
-
-Client
-------
-
-There are currently two use-cases for an ABCI client. One is a testing
-tool, as in the ``abci-cli``, which allows ABCI requests to be sent via
-command line. The other is a consensus engine, such as Tendermint Core,
-which makes requests to the application every time a new transaction is
-received or a block is committed.
-
-It is unlikely that you will need to implement a client. For details of
-our client, see
-`here <https://github.com/tendermint/abci/tree/master/client>`__.
-
-Most of the examples below are from `dummy application
-<https://github.com/tendermint/abci/blob/master/example/dummy/dummy.go>`__,
-which is a part of the abci repo. `persistent_dummy application
-<https://github.com/tendermint/abci/blob/master/example/dummy/persistent_dummy.go>`__
-is used to show ``BeginBlock``, ``EndBlock`` and ``InitChain``
-example implementations.
-
-Blockchain Protocol
--------------------
-
-In ABCI, a transaction is simply an arbitrary length byte-array. It is
-the application's responsibility to define the transaction codec as they
-please, and to use it for both CheckTx and DeliverTx.
-
-Note that there are two distinct means for running transactions,
-corresponding to stages of 'awareness' of the transaction in the
-network. The first stage is when a transaction is received by a
-validator from a client into the so-called mempool or transaction pool -
-this is where we use CheckTx. The second is when the transaction is
-successfully committed on more than 2/3 of validators - where we use
-DeliverTx. In the former case, it may not be necessary to run all the
-state transitions associated with the transaction, as the transaction
-may not ultimately be committed until some much later time, when the
-result of its execution will be different. For instance, an Ethereum
-ABCI app would check signatures and amounts in CheckTx, but would not
-actually execute any contract code until the DeliverTx, so as to avoid
-executing state transitions that have not been finalized.
-
-To formalize the distinction further, two explicit ABCI connections are
-made between Tendermint Core and the application: the mempool connection
-and the consensus connection. We also make a third connection, the query
-connection, to query the local state of the app.
-
-Mempool Connection
-~~~~~~~~~~~~~~~~~~
-
-The mempool connection is used *only* for CheckTx requests. Transactions
-are run using CheckTx in the same order they were received by the
-validator. If the CheckTx returns ``OK``, the transaction is kept in
-memory and relayed to other peers in the same order it was received.
-Otherwise, it is discarded.
-
-CheckTx requests run concurrently with block processing; so they should
-run against a copy of the main application state which is reset after
-every block. This copy is necessary to track transitions made by a
-sequence of CheckTx requests before they are included in a block. When a
-block is committed, the application must ensure to reset the mempool
-state to the latest committed state. Tendermint Core will then filter
-through all transactions in the mempool, removing any that were included
-in the block, and re-run the rest using CheckTx against the post-Commit
-mempool state.
-
-.. container:: toggle
-
-    .. container:: header
-
-        **Show/Hide Go Example**
-
-    .. code-block:: go
-
-        func (app *DummyApplication) CheckTx(tx []byte) types.Result {
-          return types.OK
-        }
-
-.. container:: toggle
-
-    .. container:: header
-
-        **Show/Hide Java Example**
-
-    .. code-block:: java
-
-        ResponseCheckTx requestCheckTx(RequestCheckTx req) {
-            byte[] transaction = req.getTx().toByteArray();
-
-            // validate transaction
-
-            if (notValid) {
-                return ResponseCheckTx.newBuilder().setCode(CodeType.BadNonce).setLog("invalid tx").build();
-            } else {
-                return ResponseCheckTx.newBuilder().setCode(CodeType.OK).build();
-            }
-        }
-
-Consensus Connection
-~~~~~~~~~~~~~~~~~~~~
-
-The consensus connection is used only when a new block is committed, and
-communicates all information from the block in a series of requests:
-``BeginBlock, [DeliverTx, ...], EndBlock, Commit``. That is, when a
-block is committed in the consensus, we send a list of DeliverTx
-requests (one for each transaction) sandwiched by BeginBlock and
-EndBlock requests, and followed by a Commit.
-
-DeliverTx
-^^^^^^^^^
-
-DeliverTx is the workhorse of the blockchain. Tendermint sends the
-DeliverTx requests asynchronously but in order, and relies on the
-underlying socket protocol (ie. TCP) to ensure they are received by the
-app in order. They have already been ordered in the global consensus by
-the Tendermint protocol.
-
-DeliverTx returns a abci.Result, which includes a Code, Data, and Log.
-The code may be non-zero (non-OK), meaning the corresponding transaction
-should have been rejected by the mempool, but may have been included in
-a block by a Byzantine proposer.
-
-The block header will be updated (TODO) to include some commitment to
-the results of DeliverTx, be it a bitarray of non-OK transactions, or a
-merkle root of the data returned by the DeliverTx requests, or both.
-
-.. container:: toggle
-
-    .. container:: header
-
-        **Show/Hide Go Example**
-
-    .. code-block:: go
-
-        // tx is either "key=value" or just arbitrary bytes
-        func (app *DummyApplication) DeliverTx(tx []byte) types.Result {
-          parts := strings.Split(string(tx), "=")
-          if len(parts) == 2 {
-            app.state.Set([]byte(parts[0]), []byte(parts[1]))
-          } else {
-            app.state.Set(tx, tx)
-          }
-          return types.OK
-        }
-
-.. container:: toggle
-
-    .. container:: header
-
-        **Show/Hide Java Example**
-
-    .. code-block:: java
-
-        /**
-         * Using Protobuf types from the protoc compiler, we always start with a byte[]
-         */
-        ResponseDeliverTx deliverTx(RequestDeliverTx request) {
-            byte[] transaction  = request.getTx().toByteArray();
-
-            // validate your transaction
-
-            if (notValid) {
-                return ResponseDeliverTx.newBuilder().setCode(CodeType.BadNonce).setLog("transaction was invalid").build();
-            } else {
-                ResponseDeliverTx.newBuilder().setCode(CodeType.OK).build();
-            }
-
-        }
-
-Commit
-^^^^^^
-
-Once all processing of the block is complete, Tendermint sends the
-Commit request and blocks waiting for a response. While the mempool may
-run concurrently with block processing (the BeginBlock, DeliverTxs, and
-EndBlock), it is locked for the Commit request so that its state can be
-safely reset during Commit. This means the app *MUST NOT* do any
-blocking communication with the mempool (ie. broadcast\_tx) during
-Commit, or there will be deadlock. Note also that all remaining
-transactions in the mempool are replayed on the mempool connection
-(CheckTx) following a commit.
-
-The app should respond to the Commit request with a byte array, which is the deterministic
-state root of the application. It is included in the header of the next
-block. It can be used to provide easily verified Merkle-proofs of the
-state of the application.
-
-It is expected that the app will persist state to disk on Commit. The
-option to have all transactions replayed from some previous block is the
-job of the `Handshake <#handshake>`__.
-
-.. container:: toggle
-
-    .. container:: header
-
-        **Show/Hide Go Example**
-
-    .. code-block:: go
-
-        func (app *DummyApplication) Commit() types.Result {
-          hash := app.state.Hash()
-          return types.NewResultOK(hash, "")
-        }
-
-.. container:: toggle
-
-    .. container:: header
-
-        **Show/Hide Java Example**
-
-    .. code-block:: java
-
-        ResponseCommit requestCommit(RequestCommit requestCommit) {
-
-            // update the internal app-state
-            byte[] newAppState = calculateAppState();
-
-            // and return it to the node
-            return ResponseCommit.newBuilder().setCode(CodeType.OK).setData(ByteString.copyFrom(newAppState)).build();
-        }
-
-BeginBlock
-^^^^^^^^^^
-
-The BeginBlock request can be used to run some code at the beginning of
-every block. It also allows Tendermint to send the current block hash
-and header to the application, before it sends any of the transactions.
-
-The app should remember the latest height and header (ie. from which it
-has run a successful Commit) so that it can tell Tendermint where to
-pick up from when it restarts. See information on the Handshake, below.
-
-.. container:: toggle
-
-    .. container:: header
-
-        **Show/Hide Go Example**
-
-    .. code-block:: go
-
-        // Track the block hash and header information
-        func (app *PersistentDummyApplication) BeginBlock(params types.RequestBeginBlock) {
-          // update latest block info
-          app.blockHeader = params.Header
-
-          // reset valset changes
-          app.changes = make([]*types.Validator, 0)
-        }
-
-.. container:: toggle
-
-    .. container:: header
-
-        **Show/Hide Java Example**
-
-    .. code-block:: java
-
-        /*
-         * all types come from protobuf definition
-         */
-        ResponseBeginBlock requestBeginBlock(RequestBeginBlock req) {
-
-            Header header = req.getHeader();
-            byte[] prevAppHash = header.getAppHash().toByteArray();
-            long prevHeight = header.getHeight();
-            long numTxs = header.getNumTxs();
-
-            // run your pre-block logic. Maybe prepare a state snapshot, message components, etc
-
-            return ResponseBeginBlock.newBuilder().build();
-        }
-
-EndBlock
-^^^^^^^^
-
-The EndBlock request can be used to run some code at the end of every
-block. Additionally, the response may contain a list of validators,
-which can be used to update the validator set. To add a new validator or
-update an existing one, simply include them in the list returned in the
-EndBlock response. To remove one, include it in the list with a
-``power`` equal to ``0``. Tendermint core will take care of updating the
-validator set. Note validator set changes are only available in v0.8.0
-and up.
-
-.. container:: toggle
-
-    .. container:: header
-
-        **Show/Hide Go Example**
-
-    .. code-block:: go
-
-        // Update the validator set
-        func (app *PersistentDummyApplication) EndBlock(height uint64) (resEndBlock types.ResponseEndBlock) {
-          return types.ResponseEndBlock{Diffs: app.changes}
-        }
-
-.. container:: toggle
-
-    .. container:: header
-
-        **Show/Hide Java Example**
-
-    .. code-block:: java
-
-        /*
-         * Assume that one validator changes. The new validator has a power of 10
-         */
-        ResponseEndBlock requestEndBlock(RequestEndBlock req) {
-            final long currentHeight = req.getHeight();
-            final byte[] validatorPubKey = getValPubKey();
-
-            ResponseEndBlock.Builder builder = ResponseEndBlock.newBuilder();
-            builder.addDiffs(1, Types.Validator.newBuilder().setPower(10L).setPubKey(ByteString.copyFrom(validatorPubKey)).build());
-
-            return builder.build();
-        }
-
-Query Connection
-~~~~~~~~~~~~~~~~
-
-This connection is used to query the application without engaging
-consensus. It's exposed over the tendermint core rpc, so clients can
-query the app without exposing a server on the app itself, but they must
-serialize each query as a single byte array. Additionally, certain
-"standardized" queries may be used to inform local decisions, for
-instance about which peers to connect to.
-
-Tendermint Core currently uses the Query connection to filter peers upon
-connecting, according to IP address or public key. For instance,
-returning non-OK ABCI response to either of the following queries will
-cause Tendermint to not connect to the corresponding peer:
-
--  ``p2p/filter/addr/<addr>``, where ``<addr>`` is an IP address.
--  ``p2p/filter/pubkey/<pubkey>``, where ``<pubkey>`` is the hex-encoded
-   ED25519 key of the node (not it's validator key)
-
-Note: these query formats are subject to change!
-
-.. container:: toggle
-
-    .. container:: header
-
-        **Show/Hide Go Example**
-
-    .. code-block:: go
-
-        func (app *DummyApplication) Query(reqQuery types.RequestQuery) (resQuery types.ResponseQuery) {
-          if reqQuery.Prove {
-            value, proof, exists := app.state.Proof(reqQuery.Data)
-            resQuery.Index = -1 // TODO make Proof return index
-            resQuery.Key = reqQuery.Data
-            resQuery.Value = value
-            resQuery.Proof = proof
-            if exists {
-              resQuery.Log = "exists"
-            } else {
-              resQuery.Log = "does not exist"
-            }
-            return
-          } else {
-            index, value, exists := app.state.Get(reqQuery.Data)
-            resQuery.Index = int64(index)
-            resQuery.Value = value
-            if exists {
-              resQuery.Log = "exists"
-            } else {
-              resQuery.Log = "does not exist"
-            }
-            return
-          }
-        }
-
-.. container:: toggle
-
-    .. container:: header
-
-        **Show/Hide Java Example**
-
-    .. code-block:: java
-
-        ResponseQuery requestQuery(RequestQuery req) {
-            final boolean isProveQuery = req.getProve();
-            final ResponseQuery.Builder responseBuilder = ResponseQuery.newBuilder();
-
-            if (isProveQuery) {
-                com.app.example.ProofResult proofResult = generateProof(req.getData().toByteArray());
-                final byte[] proofAsByteArray = proofResult.getAsByteArray();
-
-                responseBuilder.setProof(ByteString.copyFrom(proofAsByteArray));
-                responseBuilder.setKey(req.getData());
-                responseBuilder.setValue(ByteString.copyFrom(proofResult.getData()));
-                responseBuilder.setLog(result.getLogValue());
-            } else {
-                byte[] queryData = req.getData().toByteArray();
-
-                final com.app.example.QueryResult result = generateQueryResult(queryData);
-
-                responseBuilder.setIndex(result.getIndex());
-                responseBuilder.setValue(ByteString.copyFrom(result.getValue()));
-                responseBuilder.setLog(result.getLogValue());
-            }
-
-            return responseBuilder.build();
-        }
-
-Handshake
-~~~~~~~~~
-
-When the app or tendermint restarts, they need to sync to a common
-height. When an ABCI connection is first established, Tendermint will
-call ``Info`` on the Query connection. The response should contain the
-LastBlockHeight and LastBlockAppHash - the former is the last block for
-which the app ran Commit successfully, the latter is the response
-from that Commit.
-
-Using this information, Tendermint will determine what needs to be
-replayed, if anything, against the app, to ensure both Tendermint and
-the app are synced to the latest block height.
-
-If the app returns a LastBlockHeight of 0, Tendermint will just replay
-all blocks.
-
-.. container:: toggle
-
-    .. container:: header
-
-        **Show/Hide Go Example**
-
-    .. code-block:: go
-
-        func (app *DummyApplication) Info(req types.RequestInfo) (resInfo types.ResponseInfo) {
-          return types.ResponseInfo{Data: cmn.Fmt("{\"size\":%v}", app.state.Size())}
-        }
-
-.. container:: toggle
-
-    .. container:: header
-
-        **Show/Hide Java Example**
-
-    .. code-block:: java
-
-        ResponseInfo requestInfo(RequestInfo req) {
-            final byte[] lastAppHash = getLastAppHash();
-            final long lastHeight = getLastHeight();
-            return ResponseInfo.newBuilder().setLastBlockAppHash(ByteString.copyFrom(lastAppHash)).setLastBlockHeight(lastHeight).build();
-        }
-
-Genesis
-~~~~~~~
-
-``InitChain`` will be called once upon the genesis. ``params`` includes the
-initial validator set. Later on, it may be extended to take parts of the
-consensus params.
-
-.. container:: toggle
-
-    .. container:: header
-
-        **Show/Hide Go Example**
-
-    .. code-block:: go
-
-        // Save the validators in the merkle tree
-        func (app *PersistentDummyApplication) InitChain(params types.RequestInitChain) {
-          for _, v := range params.Validators {
-            r := app.updateValidator(v)
-            if r.IsErr() {
-              app.logger.Error("Error updating validators", "r", r)
-            }
-          }
-        }
-
-.. container:: toggle
-
-    .. container:: header
-
-        **Show/Hide Java Example**
-
-    .. code-block:: java
-
-        /*
-         * all types come from protobuf definition
-         */
-        ResponseInitChain requestInitChain(RequestInitChain req) {
-            final int validatorsCount = req.getValidatorsCount();
-            final List<Types.Validator> validatorsList = req.getValidatorsList();
-
-            validatorsList.forEach((validator) -> {
-                long power = validator.getPower();
-                byte[] validatorPubKey = validator.getPubKey().toByteArray();
-
-                // do somehing for validator setup in app
-            });
-
-            return ResponseInitChain.newBuilder().build();
-        }

docs/architecture/adr-005-consensus-params.md

@@ -22,30 +22,30 @@ The parameters are used to determine the validity of a block (and tx) via the un
 
 ```
 type ConsensusParams struct {
-    BlockSizeParams
-    TxSizeParams
-    BlockGossipParams
+    BlockSize
+    TxSize
+    BlockGossip
 }
 
-type BlockSizeParams struct {
+type BlockSize struct {
     MaxBytes int
     MaxTxs int
     MaxGas int
 }
 
-type TxSizeParams struct {
+type TxSize struct {
     MaxBytes int
     MaxGas int
 }
 
-type BlockGossipParams struct {
+type BlockGossip struct {
     BlockPartSizeBytes int
 }
 ```
 
 The `ConsensusParams` can evolve over time by adding new structs that cover different aspects of the consensus rules.
 
-The `BlockPartSizeBytes` and the `BlockSizeParams.MaxBytes` are enforced to be greater than 0. 
+The `BlockPartSizeBytes` and the `BlockSize.MaxBytes` are enforced to be greater than 0. 
 The former because we need a part size, the latter so that we always have at least some sanity check over the size of blocks.
 
 ### ABCI
@@ -58,7 +58,7 @@ like the BlockPartSize, that the app shouldn't really know about.
 
 #### EndBlock
 
-The EndBlock response includes a `ConsensusParams`, which includes BlockSizeParams and TxSizeParams, but not BlockGossipParams.
+The EndBlock response includes a `ConsensusParams`, which includes BlockSize and TxSize, but not BlockGossip.
 Other param struct can be added to `ConsensusParams` in the future.
 The `0` value is used to denote no change. 
 Any other value will update that parameter in the `State.ConsensusParams`, to be applied for the next block.
@@ -82,4 +82,5 @@ Proposed.
 
 ### Neutral
 
-- The TxSizeParams, which checks validity, may be in conflict with the config's `max_block_size_tx`, which determines proposal sizes
+- The TxSize, which checks validity, may be in conflict with the config's `max_block_size_tx`, which determines proposal sizes
+

docs/architecture/adr-007-trust-metric-usage.md

@@ -0,0 +1,103 @@
+# ADR 007: Trust Metric Usage Guide
+
+## Context
+
+Tendermint is required to monitor peer quality in order to inform its peer dialing and peer exchange strategies.
+
+When a node first connects to the network, it is important that it can quickly find good peers.
+Thus, while a node has fewer connections, it should prioritize connecting to higher quality peers.
+As the node becomes well connected to the rest of the network, it can dial lesser known or lesser
+quality peers and help assess their quality. Similarly, when queried for peers, a node should make
+sure they dont return low quality peers.
+
+Peer quality can be tracked using a trust metric that flags certain behaviours as good or bad. When enough
+bad behaviour accumulates, we can mark the peer as bad and disconnect.
+For example, when the PEXReactor makes a request for peers network addresses from an already known peer, and the returned network addresses are unreachable, this undesirable behavior should be tracked. Returning a few bad network addresses probably shouldn’t cause a peer to be dropped, while excessive amounts of this behavior does qualify the peer for removal. The originally proposed approach and design document for the trust metric can be found in the [ADR 006](adr-006-trust-metric.md) document.
+
+The trust metric implementation allows a developer to obtain a peer's trust metric from a trust metric store, and track good and bad events relevant to a peer's behavior, and at any time, the peer's metric can be queried for a current trust value. The current trust value is calculated with a formula that utilizes current behavior, previous behavior, and change between the two. Current behavior is calculated as the percentage of good behavior within a time interval. The time interval is short; probably set between 30 seconds and 5 minutes. On the other hand, the historic data can estimate a peer's behavior over days worth of tracking. At the end of a time interval, the current behavior becomes part of the historic data, and a new time interval begins with the good and bad counters reset to zero.
+
+These are some important things to keep in mind regarding how the trust metrics handle time intervals and scoring:
+- Each new time interval begins with a perfect score
+- Bad events quickly bring the score down and good events cause the score to slowly rise
+- When the time interval is over, the percentage of good events becomes historic data.
+
+Some useful information about the inner workings of the trust metric:
+- When a trust metric is first instantiated, a timer (ticker) periodically fires in order to handle transitions between trust metric time intervals
+- If a peer is disconnected from a node, the timer should be paused, since the node is no longer connected to that peer
+- The ability to pause the metric is supported with the store **PeerDisconnected** method and the metric **Pause** method
+- After a pause, if a good or bad event method is called on a metric, it automatically becomes unpaused and begins a new time interval.
+
+## Decision
+
+The trust metric capability is now available, yet, it still leaves the question of how should it be applied throughout Tendermint in order to properly track the quality of peers?
+
+### Proposed Process
+
+Peers are managed using an address book and a trust metric:
+
+- The address book keeps a record of peers and provides selection methods
+- The trust metric tracks the quality of the peers
+
+#### Presence in Address Book
+
+Outbound peers are added to the address book before they are dialed,
+and inbound peers are added once the peer connection is set up.
+Peers are also added to the address book when they are received in response to
+a pexRequestMessage.
+
+While a node has less than `needAddressThreshold`, it will periodically request more,
+via pexRequestMessage, from randomly selected peers and from newly dialed outbound peers.
+
+When a new address is added to an address book that has more than `0.5*needAddressThreshold` addresses,
+then with some low probability, a randomly chosen low quality peer is removed.
+
+#### Outbound Peers
+
+Peers attempt to maintain a minimum number of outbound connections by
+repeatedly querying the address book for peers to connect to.
+While a node has few to no outbound connections, the address book is biased to return
+higher quality peers. As the node increases the number of outbound connections,
+the address book is biased to return less-vetted or lower-quality peers.
+
+#### Inbound Peers
+
+Peers also maintain a maximum number of total connections, MaxNumPeers.
+If a peer has MaxNumPeers, new incoming connections will be accepted with low probability.
+When such a new connection is accepted, the peer disconnects from a probabilistically chosen low ranking peer
+so it does not exceed MaxNumPeers.
+
+#### Peer Exchange
+
+When a peer receives a pexRequestMessage, it returns a random sample of high quality peers from the address book. Peers with no score or low score should not be inclided in a response to pexRequestMessage.
+
+#### Peer Quality
+
+Peer quality is tracked in the connection and across the reactors by storing the TrustMetric in the peer's
+thread safe Data store.
+
+Peer behaviour is then defined as one of the following:
+- Fatal - something outright malicious that causes us to disconnect the peer and ban it from the address book for some amount of time
+- Bad - Any kind of timeout, messages that don't unmarshal, fail other validity checks, or messages we didn't ask for or aren't expecting (usually worth one bad event)
+- Neutral - Unknown channels/message types/version upgrades (no good or bad events recorded)
+- Correct - Normal correct behavior (worth one good event)
+- Good - some random majority of peers per reactor sending us useful messages (worth more than one good event).
+
+Note that Fatal behaviour causes us to remove the peer, and neutral behaviour does not affect the score.
+
+## Status
+
+Proposed.
+
+## Consequences
+
+### Positive
+
+- Bringing the address book and trust metric store together will cause the network to be built in a way that encourages greater security and reliability.
+
+### Negative
+
+- TBD
+
+### Neutral
+
+- Keep in mind that, good events need to be recorded just as bad events do using this implementation.

docs/architecture/adr-008-priv-validator.md

@@ -0,0 +1,29 @@
+# ADR 008: SocketPV
+
+Tendermint node's should support only two in-process PrivValidator
+implementations:
+
+- FilePV uses an unencrypted private key in a "priv_validator.json" file - no
+  configuration required (just `tendermint init`).
+- SocketPV uses a socket to send signing requests to another process - user is
+  responsible for starting that process themselves.
+
+The SocketPV address can be provided via flags at the command line - doing so
+will cause Tendermint to ignore any "priv_validator.json" file and to listen on
+the given address for incoming connections from an external priv_validator
+process.  It will halt any operation until at least one external process
+succesfully connected.
+
+The external priv_validator process will dial the address to connect to
+Tendermint, and then Tendermint will send requests on the ensuing connection to
+sign votes and proposals.  Thus the external process initiates the connection,
+but the Tendermint process makes all requests.  In a later stage we're going to
+support multiple validators for fault tolerance. To prevent double signing they
+need to be synced, which is deferred to an external solution (see #1185).
+
+In addition, Tendermint will provide implementations that can be run in that
+external process.  These include:
+
+- FilePV will encrypt the private key, and the user must enter password to
+  decrypt key when process is started.
+- LedgerPV uses a Ledger Nano S to handle all signing.

docs/conf.py

@@ -41,15 +41,22 @@ templates_path = ['_templates']
 # The suffix(es) of source filenames.
 # You can specify multiple suffix as a list of string:
 #
+
+from recommonmark.parser import CommonMarkParser
+
+source_parsers = {
+    '.md': CommonMarkParser,
+}
+
 source_suffix = ['.rst', '.md']
-# source_suffix = '.rst'
+#source_suffix = '.rst'
 
 # The master toctree document.
 master_doc = 'index'
 
 # General information about the project.
 project = u'Tendermint'
-copyright = u'2017, The Authors'
+copyright = u'2018, The Authors'
 author = u'Tendermint'
 
 # The version info for the project you're documenting, acts as replacement for
@@ -71,7 +78,7 @@ language = None
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
 # This patterns also effect to html_static_path and html_extra_path
-exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store', 'architecture']
+exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store', 'architecture', 'spec', 'examples']
 
 # The name of the Pygments (syntax highlighting) style to use.
 pygments_style = 'sphinx'
@@ -171,29 +178,29 @@ texinfo_documents = [
      'Database'),
 ]
 
-repo = "https://raw.githubusercontent.com/tendermint/tools/"
-branch = "master"
+# ---------------- customizations ----------------------
 
-tools = "./tools"
-assets = tools + "/assets"
+# for Docker README, below
+from shutil import copyfile
 
-if os.path.isdir(tools) != True:
-    os.mkdir(tools)
-if os.path.isdir(assets) != True:
-    os.mkdir(assets)
+# tm-bench and tm-monitor
+tools_repo = "https://raw.githubusercontent.com/tendermint/tools/"
+tools_branch = "master"
 
-urllib.urlretrieve(repo+branch+'/ansible/README.rst', filename=tools+'/ansible.rst')
-urllib.urlretrieve(repo+branch+'/ansible/assets/a_plus_t.png', filename=assets+'/a_plus_t.png')
+tools_dir = "./tools"
 
-urllib.urlretrieve(repo+branch+'/docker/README.rst', filename=tools+'/docker.rst')
 
-urllib.urlretrieve(repo+branch+'/mintnet-kubernetes/README.rst', filename=tools+'/mintnet-kubernetes.rst')
-urllib.urlretrieve(repo+branch+'/mintnet-kubernetes/assets/gce1.png', filename=assets+'/gce1.png')
-urllib.urlretrieve(repo+branch+'/mintnet-kubernetes/assets/gce2.png', filename=assets+'/gce2.png')
-urllib.urlretrieve(repo+branch+'/mintnet-kubernetes/assets/statefulset.png', filename=assets+'/statefulset.png')
-urllib.urlretrieve(repo+branch+'/mintnet-kubernetes/assets/t_plus_k.png', filename=assets+'/t_plus_k.png')
+if os.path.isdir(tools_dir) != True:
+    os.mkdir(tools_dir)
 
-urllib.urlretrieve(repo+branch+'/terraform-digitalocean/README.rst', filename=tools+'/terraform-digitalocean.rst')
-urllib.urlretrieve(repo+branch+'/tm-bench/README.rst', filename=tools+'/benchmarking-and-monitoring.rst')
-# the readme for below is included in tm-bench
-# urllib.urlretrieve('https://raw.githubusercontent.com/tendermint/tools/master/tm-monitor/README.rst', filename='tools/tm-monitor.rst')
+copyfile('../DOCKER/README.md', tools_dir+'/docker.md')
+
+urllib.urlretrieve(tools_repo+tools_branch+'/tm-bench/README.md', filename=tools_dir+'/benchmarking.md')
+urllib.urlretrieve(tools_repo+tools_branch+'/tm-monitor/README.md', filename=tools_dir+'/monitoring.md')
+
+#### abci spec #################################
+
+abci_repo = "https://raw.githubusercontent.com/tendermint/abci/"
+abci_branch = "develop"
+
+urllib.urlretrieve(abci_repo+abci_branch+'/specification.md', filename='abci-spec.md')

docs/deploy-testnets.md

@@ -0,0 +1,68 @@
+# Deploy a Testnet
+
+Now that we've seen how ABCI works, and even played with a few
+applications on a single validator node, it's time to deploy a test
+network to four validator nodes.
+
+## Manual Deployments
+
+It's relatively easy to setup a Tendermint cluster manually. The only
+requirements for a particular Tendermint node are a private key for the
+validator, stored as `priv_validator.json`, a node key, stored as
+`node_key.json` and a list of the public keys of all validators, stored
+as `genesis.json`. These files should be stored in
+`~/.tendermint/config`, or wherever the `$TMHOME` variable might be set
+to.
+
+Here are the steps to setting up a testnet manually:
+
+1)  Provision nodes on your cloud provider of choice
+2)  Install Tendermint and the application of interest on all nodes
+3)  Generate a private key and a node key for each validator using
+    `tendermint init`
+4)  Compile a list of public keys for each validator into a
+    `genesis.json` file and replace the existing file with it.
+5)  Run
+    `tendermint node --proxy_app=kvstore --p2p.persistent_peers=< peer addresses >`
+    on each node, where `< peer addresses >` is a comma separated list
+    of the IP:PORT combination for each node. The default port for
+    Tendermint is `26656`. Thus, if the IP addresses of your nodes were
+    `192.168.0.1, 192.168.0.2, 192.168.0.3, 192.168.0.4`, the command
+    would look like:
+
+
+    tendermint node --proxy_app=kvstore --p2p.persistent_peers=96663a3dd0d7b9d17d4c8211b191af259621c693@192.168.0.1:26656, 429fcf25974313b95673f58d77eacdd434402665@192.168.0.2:26656, 0491d373a8e0fcf1023aaf18c51d6a1d0d4f31bd@192.168.0.3:26656, f9baeaa15fedf5e1ef7448dd60f46c01f1a9e9c4@192.168.0.4:26656
+
+After a few seconds, all the nodes should connect to each other and
+start making blocks! For more information, see the Tendermint Networks
+section of [the guide to using Tendermint](using-tendermint.html).
+
+But wait! Steps 3 and 4 are quite manual. Instead, use [this
+script](https://github.com/tendermint/tendermint/blob/develop/docs/examples/init_testnet.sh),
+which does the heavy lifting for you. And it gets better.
+
+Instead of the previously linked script to initialize the files required
+for a testnet, we have the `tendermint testnet` command. By default,
+running `tendermint testnet` will create all the required files, just
+like the script. Of course, you'll still need to manually edit some
+fields in the `config.toml`. Alternatively, see the available flags to
+auto-populate the `config.toml` with the fields that would otherwise be
+passed in via flags when running `tendermint node`. As you might
+imagine, this command is useful for manual or automated deployments.
+
+## Automated Deployments
+
+The easiest and fastest way to get a testnet up in less than 5 minutes.
+
+### Local
+
+With `docker` and `docker-compose` installed, run the command:
+
+    make localnet-start
+
+from the root of the tendermint repository. This will spin up a 4-node
+local testnet. Review the target in the Makefile to debug any problems.
+
+### Cloud
+
+See the [next section](./terraform-and-ansible.html) for details.

docs/deploy-testnets.rst

@@ -1,90 +0,0 @@
-Deploy a Testnet
-================
-
-Now that we've seen how ABCI works, and even played with a few
-applications on a single validator node, it's time to deploy a test
-network to four validator nodes. For this deployment, we'll use the
-``basecoin`` application.
-
-Manual Deployments
-------------------
-
-It's relatively easy to setup a Tendermint cluster manually. The only
-requirements for a particular Tendermint node are a private key for the
-validator, stored as ``priv_validator.json``, and a list of the public
-keys of all validators, stored as ``genesis.json``. These files should
-be stored in ``~/.tendermint``, or wherever the ``$TMHOME`` variable
-might be set to.
-
-Here are the steps to setting up a testnet manually:
-
-1) Provision nodes on your cloud provider of choice
-2) Install Tendermint and the application of interest on all nodes
-3) Generate a private key for each validator using
-   ``tendermint gen_validator``
-4) Compile a list of public keys for each validator into a
-   ``genesis.json`` file.
-5) Run ``tendermint node --p2p.seeds=< seed addresses >`` on each node,
-   where ``< seed addresses >`` is a comma separated list of the IP:PORT
-   combination for each node. The default port for Tendermint is
-   ``46656``. Thus, if the IP addresses of your nodes were
-   ``192.168.0.1, 192.168.0.2, 192.168.0.3, 192.168.0.4``, the command
-   would look like:
-   ``tendermint node --p2p.seeds=192.168.0.1:46656,192.168.0.2:46656,192.168.0.3:46656,192.168.0.4:46656``.
-
-After a few seconds, all the nodes should connect to eachother and start
-making blocks! For more information, see the Tendermint Networks section
-of `the guide to using Tendermint <using-tendermint.html>`__.
-
-Automated Deployments
----------------------
-
-While the manual deployment is easy enough, an automated deployment is
-usually quicker. The below examples show different tools that can be used
-for automated deployments.
-
-Automated Deployment using Kubernetes
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-The `mintnet-kubernetes tool <https://github.com/tendermint/tools/tree/master/mintnet-kubernetes>`__
-allows automating the deployment of a Tendermint network on an already
-provisioned kubernetes cluster. For simple provisioning of a kubernetes
-cluster, check out the `Google Cloud Platform <https://cloud.google.com/>`__.
-
-Automated Deployment using Terraform and Ansible
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-The `terraform-digitalocean tool <https://github.com/tendermint/tools/tree/master/terraform-digitalocean>`__
-allows creating a set of servers on the DigitalOcean cloud.
-
-The `ansible playbooks <https://github.com/tendermint/tools/tree/master/ansible>`__
-allow creating and managing a ``basecoin`` or ``ethermint`` testnet on provisioned servers.
-
-Package Deployment on Linux for developers
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-The ``tendermint`` and ``basecoin`` applications can be installed from RPM or DEB packages on
-Linux machines for development purposes. The packages are configured to be validators on the
-one-node network that the machine represents. The services are not started after installation,
-this way giving an opportunity to reconfigure the applications before starting.
-
-The Ansible playbooks in the previous section use this repository to install ``basecoin``.
-After installation, additional steps are executed to make sure that the multi-node testnet has
-the right configuration before start.
-
-Install from the CentOS/RedHat repository:
-
-::
-
-    rpm --import https://tendermint-packages.interblock.io/centos/7/os/x86_64/RPM-GPG-KEY-Tendermint
-    wget -O /etc/yum.repos.d/tendermint.repo https://tendermint-packages.interblock.io/centos/7/os/x86_64/tendermint.repo
-    yum install basecoin
-
-Install from the Debian/Ubuntu repository:
-
-::
-
-    wget -O - https://tendermint-packages.interblock.io/centos/7/os/x86_64/RPM-GPG-KEY-Tendermint | apt-key add -
-    wget -O /etc/apt/sources.list.d/tendermint.list https://tendermint-packages.interblock.io/debian/tendermint.list
-    apt-get update && apt-get install basecoin
-

docs/determinism.md

@@ -0,0 +1,5 @@
+# On Determinism
+
+Arguably, the most difficult part of blockchain programming is determinism - that is, ensuring that sources of indeterminism do not creep into the design of such systems.
+
+See [this issue](https://github.com/tendermint/abci/issues/56) for more information on the potential sources of indeterminism.

docs/ecosystem.md

@@ -0,0 +1,21 @@
+# Ecosystem
+
+The growing list of applications built using various pieces of the
+Tendermint stack can be found at:
+
+-   https://tendermint.com/ecosystem
+
+We thank the community for their contributions thus far and welcome the
+addition of new projects. A pull request can be submitted to [this
+file](https://github.com/tendermint/aib-data/blob/master/json/ecosystem.json)
+to include your project.
+
+## Other Tools
+
+See [deploy testnets](./deploy-testnets.html) for information about all
+the tools built by Tendermint. We have Kubernetes, Ansible, and
+Terraform integrations.
+
+For upgrading from older to newer versions of tendermint and to migrate
+your chain data, see [tm-migrator](https://github.com/hxzqlh/tm-tools)
+written by @hxzqlh.