Example of client send task and monitor task

Refs #1422

.circleci/config.yml

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

.codecov.yml

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

.editorconfig

@@ -8,10 +8,7 @@ end_of_line = lf
 insert_final_newline = true
 trim_trailing_whitespace = true
 
-[Makefile]
-indent_style = tab
-
-[*.sh]
+[*.{sh,Makefile}]
 indent_style = tab
 
 [*.proto]

.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 and Anton. For now.
+*       @ebuchman @melekes

.github/ISSUE_TEMPLATE

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

.github/PULL_REQUEST_TEMPLATE.md

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

.gitignore

@@ -17,6 +17,11 @@ test/logs
 coverage.txt
 docs/_build
 docs/tools
+docs/abci-spec.rst
+*.log
 
 scripts/wal2json/wal2json
 scripts/cutWALUntil/cutWALUntil
+
+.idea/
+*.iml

CHANGELOG.md

@@ -3,13 +3,10 @@
 ## Roadmap
 
 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
 
 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)
@@ -27,6 +24,200 @@ BUG FIXES:
 - Graceful handling/recovery for apps that have non-determinism or fail to halt
 - Graceful handling/recovery for violations of safety, or liveness
 
+## 0.19.0 (April 13th, 2018)
+
+BREAKING:
+- [cmd] improved `testnet` command; now it can fill in `persistent_peers` for you in the config file and much more (see `tendermint testnet --help` for details)
+- [cmd] `show_node_id` now returns an error if there is no node key
+- [rpc]: changed the output format for the `/status` endpoint (see https://godoc.org/github.com/tendermint/tendermint/rpc/core#Status)
+
+Upgrade from go-wire to go-amino. This is a sweeping change that breaks everything that is
+serialized to disk or over the network.
+
+See github.com/tendermint/go-amino for details on the new format.
+
+See `scripts/wire2amino.go` for a tool to upgrade
+genesis/priv_validator/node_key JSON files.
+
+FEATURES:
+- [cmd] added `gen_node_key` command
+
+## 0.18.0 (April 6th, 2018)
+
+BREAKING:
+
+- [types] Merkle tree uses different encoding for varints (see tmlibs v0.8.0)
+- [types] ValidtorSet.GetByAddress returns -1 if no validator found
+- [p2p] require all addresses come with an ID no matter what
+- [rpc] Listening address must contain tcp:// or unix:// prefix
+
+FEATURES:
+
+- [rpc] StartHTTPAndTLSServer (not used yet)
+- [rpc] Include validator's voting power in `/status`
+- [rpc] `/tx` and `/tx_search` responses now include the transaction hash
+- [rpc] Include peer NodeIDs in `/net_info`
+
+IMPROVEMENTS:
+- [config] trim whitespace from elements of lists (like `persistent_peers`)
+- [rpc] `/tx_search` results are sorted by height
+- [p2p] do not try to connect to ourselves (ok, maybe only once)
+- [p2p] seeds respond with a bias towards good peers
+
+BUG FIXES:
+- [rpc] fix subscribing using an abci.ResponseDeliverTx tag
+- [rpc] fix tx_indexers matchRange
+- [rpc] fix unsubscribing (see tmlibs v0.8.0)
+
+## 0.17.1 (March 27th, 2018)
+
+BUG FIXES:
+- [types] Actually support `app_state` in genesis as `AppStateJSON`
+
+## 0.17.0 (March 27th, 2018)
+
+BREAKING:
+- [types] WriteSignBytes -> SignBytes
+
+IMPROVEMENTS:
+- [all] renamed `dummy` (`persistent_dummy`) to `kvstore` (`persistent_kvstore`) (name "dummy" is deprecated and will not work in the next breaking release)
+- [docs] note on determinism (docs/determinism.rst)
+- [genesis] `app_options` field is deprecated. please rename it to `app_state` in your genesis file(s). `app_options` will not work in the next breaking release
+- [p2p] dial seeds directly without potential peers
+- [p2p] exponential backoff for addrs in the address book
+- [p2p] mark peer as good if it contributed enough votes or block parts
+- [p2p] stop peer if it sends incorrect data, msg to unknown channel, msg we did not expect
+- [p2p] when `auth_enc` is true, all dialed peers must have a node ID in their address
+- [spec] various improvements
+- switched from glide to dep internally for package management
+- [wire] prep work for upgrading to new go-wire (which is now called go-amino)
+
+FEATURES:
+- [config] exposed `auth_enc` flag to enable/disable encryption
+- [config] added the `--p2p.private_peer_ids` flag and `PrivatePeerIDs` config variable (see config for description)
+- [rpc] added `/health` endpoint, which returns empty result for now
+- [types/priv_validator] new format and socket client, allowing for remote signing
+
+BUG FIXES:
+- [consensus] fix liveness bug by introducing ValidBlock mechanism
+
+## 0.16.0 (February 20th, 2018)
+
+BREAKING CHANGES:
+- [config] use $TMHOME/config for all config and json files
+- [p2p] old `--p2p.seeds` is now `--p2p.persistent_peers` (persistent peers to which TM will always connect to)
+- [p2p] now `--p2p.seeds` only used for getting addresses (if addrbook is empty; not persistent)
+- [p2p] NodeInfo: remove RemoteAddr and add Channels
+    - we must have at least one overlapping channel with peer
+    - we only send msgs for channels the peer advertised
+- [p2p/conn] pong timeout
+- [lite] comment out IAVL related code
+
+FEATURES:
+- [p2p] added new `/dial_peers&persistent=_` **unsafe** endpoint
+- [p2p] persistent node key in `$THMHOME/config/node_key.json`
+- [p2p] introduce peer ID and authenticate peers by ID using addresses like `ID@IP:PORT`
+- [p2p/pex] new seed mode crawls the network and serves as a seed.
+- [config] MempoolConfig.CacheSize
+- [config] P2P.SeedMode (`--p2p.seed_mode`)
+
+IMPROVEMENT:
+- [p2p/pex] stricter rules in the PEX reactor for better handling of abuse
+- [p2p] various improvements to code structure including subpackages for `pex` and `conn`
+- [docs] new spec!
+- [all] speed up the tests!
+
+BUG FIX:
+- [blockchain] StopPeerForError on timeout
+- [consensus] StopPeerForError on a bad Maj23 message
+- [state] flush mempool conn before calling commit
+- [types] fix priv val signing things that only differ by timestamp
+- [mempool] fix memory leak causing zombie peers
+- [p2p/conn] fix potential deadlock
+
+## 0.15.0 (December 29, 2017)
+
+BREAKING CHANGES:
+- [p2p] enable the Peer Exchange reactor by default
+- [types] add Timestamp field to Proposal/Vote
+- [types] add new fields to Header: TotalTxs, ConsensusParamsHash, LastResultsHash, EvidenceHash
+- [types] add Evidence to Block
+- [types] simplify ValidateBasic
+- [state] updates to support changes to the header
+- [state] Enforce <1/3 of validator set can change at a time
+
+FEATURES:
+- [state] Send indices of absent validators and addresses of byzantine validators in BeginBlock
+- [state] Historical ConsensusParams and ABCIResponses
+- [docs] Specification for the base Tendermint data structures.
+- [evidence] New evidence reactor for gossiping and managing evidence
+- [rpc] `/block_results?height=X` returns the DeliverTx results for a given height.
+
+IMPROVEMENTS:
+- [consensus] Better handling of corrupt WAL file
+
+BUG FIXES:
+- [lite] fix race
+- [state] validate block.Header.ValidatorsHash
+- [p2p] allow seed addresses to be prefixed with eg. `tcp://`
+- [p2p] use consistent key to refer to peers so we dont try to connect to existing peers
+- [cmd] fix `tendermint init` to ignore files that are there and generate files that aren't.
+
+## 0.14.0 (December 11, 2017)
+
+BREAKING CHANGES:
+- consensus/wal: removed separator
+- rpc/client: changed Subscribe/Unsubscribe/UnsubscribeAll funcs signatures to be identical to event bus.
+
+FEATURES:
+- new `tendermint lite` command (and `lite/proxy` pkg) for running a light-client RPC proxy.
+    NOTE it is currently insecure and its APIs are not yet covered by semver
+
+IMPROVEMENTS:
+- rpc/client: can act as event bus subscriber (See https://github.com/tendermint/tendermint/issues/945).
+- p2p: use exponential backoff from seconds to hours when attempting to reconnect to persistent peer
+- config: moniker defaults to the machine's hostname instead of "anonymous"
+
+BUG FIXES:
+- p2p: no longer exit if one of the seed addresses is incorrect
+
+## 0.13.0 (December 6, 2017)
+
+BREAKING CHANGES:
+- abci: update to v0.8 using gogo/protobuf; includes tx tags, vote info in RequestBeginBlock, data.Bytes everywhere, use int64, etc.
+- types: block heights are now `int64` everywhere
+- types & node: EventSwitch and EventCache have been replaced by EventBus and EventBuffer; event types have been overhauled
+- node: EventSwitch methods now refer to EventBus
+- rpc/lib/types: RPCResponse is no longer a pointer; WSRPCConnection interface has been modified
+- rpc/client: WaitForOneEvent takes an EventsClient instead of types.EventSwitch
+- rpc/client: Add/RemoveListenerForEvent are now Subscribe/Unsubscribe
+- rpc/core/types: ResultABCIQuery wraps an abci.ResponseQuery
+- rpc: `/subscribe` and `/unsubscribe` take `query` arg instead of `event`
+- rpc: `/status` returns the LatestBlockTime in human readable form instead of in nanoseconds
+- mempool: cached transactions return an error instead of an ABCI response with BadNonce
+
+FEATURES:
+- rpc: new `/unsubscribe_all` WebSocket RPC endpoint
+- rpc: new `/tx_search` endpoint for filtering transactions by more complex queries
+- p2p/trust: new trust metric for tracking peers. See ADR-006
+- config: TxIndexConfig allows to set what DeliverTx tags to index
+
+IMPROVEMENTS:
+- New asynchronous events system using `tmlibs/pubsub`
+- logging: Various small improvements
+- consensus: Graceful shutdown when app crashes
+- tests: Fix various non-deterministic errors
+- p2p: more defensive programming
+
+BUG FIXES:
+- consensus: fix panic where prs.ProposalBlockParts is not initialized
+- p2p: fix panic on bad channel
+
+## 0.12.1 (November 27, 2017)
+
+BUG FIXES:
+- upgrade tmlibs dependency to enable Windows builds for Tendermint
+
 ## 0.12.0 (October 27, 2017)
 
 BREAKING CHANGES:

CONTRIBUTING.md

@@ -34,16 +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, you can get started
+hacking Tendermint with the commands below.
+
+NOTE: In case you installed Vagrant in 2017, you might need to run
+`vagrant box update` to upgrade to the latest `ubuntu/xenial64`.
+
+```
+vagrant up
+vagrant ssh
+make test
+```
 
 ## Testing
 
-All repos should be hooked up to 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
 
@@ -75,3 +103,15 @@ especially `go-p2p` and `go-rpc`, as their versions are referenced in tendermint
 - push to release-vX.X.X to run the extended integration tests on the CI
 - merge to master
 - merge master back to develop
+
+### Hotfix Procedure:
+- start on `master`
+- checkout a new branch named hotfix-vX.X.X
+- make the required changes
+  - these changes should be small and an absolute necessity
+  - add a note to CHANGELOG.md
+- bumb versions
+- push to hotfix-vX.X.X to run the extended integration tests on the CI
+- merge hotfix-vX.X.X to master
+- merge hotfix-vX.X.X to develop
+- delete the hotfix-vX.X.X branch

DOCKER/Dockerfile

@@ -1,8 +1,8 @@
-FROM alpine:3.6
+FROM alpine:3.7
 
 # This is the release of tendermint to pull in.
-ENV TM_VERSION 0.11.0
-ENV TM_SHA256SUM 7e443bac4d42f12e7beaf9cee63b4a565dad8c58895291fdedde8057088b70c5
+ENV TM_VERSION 0.17.1
+ENV TM_SHA256SUM d57008c63d2d9176861137e38ed203da486febf20ae7d388fb810a75afff8f24
 
 # Tendermint will be looking for genesis file in /tendermint (unless you change
 # `genesis_file` in config.toml). You can put your config.toml and private
@@ -26,7 +26,7 @@ RUN mkdir -p $DATA_ROOT && \
 RUN apk add --no-cache bash curl jq
 
 RUN apk add --no-cache openssl && \
-    wget https://s3-us-west-2.amazonaws.com/tendermint/binaries/tendermint/v${TM_VERSION}/tendermint_${TM_VERSION}_linux_amd64.zip && \
+    wget https://github.com/tendermint/tendermint/releases/download/v${TM_VERSION}/tendermint_${TM_VERSION}_linux_amd64.zip && \
     echo "${TM_SHA256SUM}  tendermint_${TM_VERSION}_linux_amd64.zip" | sha256sum -c && \
     unzip -d /bin tendermint_${TM_VERSION}_linux_amd64.zip && \
     apk del openssl && \

DOCKER/Dockerfile.develop

@@ -1,4 +1,4 @@
-FROM alpine:3.6
+FROM alpine:3.7
 
 ENV DATA_ROOT /tendermint
 ENV TMHOME $DATA_ROOT
@@ -18,9 +18,9 @@ RUN mkdir -p /go/src/github.com/tendermint/tendermint && \
     cd /go/src/github.com/tendermint/tendermint && \
     git clone https://github.com/tendermint/tendermint . && \
     git checkout develop && \
+    make get_tools && \
     make get_vendor_deps && \
     make install && \
-    glide cc && \
     cd - && \
     rm -rf /go/src/github.com/tendermint/tendermint && \
     apk del go build-base git
@@ -32,4 +32,4 @@ EXPOSE 46657
 
 ENTRYPOINT ["tendermint"]
 
-CMD ["node", "--moniker=`hostname`", "--proxy_app=dummy"]
+CMD ["node", "--moniker=`hostname`", "--proxy_app=kvstore"]

DOCKER/README.md

@@ -1,6 +1,11 @@
 # Supported tags and respective `Dockerfile` links
 
-- `0.11.0`, `latest` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/9177cc1f64ca88a4a0243c5d1773d10fba67e201/DOCKER/Dockerfile)
+- `0.17.1`, `latest` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/208ac32fa266657bd6c304e84ec828aa252bb0b8/DOCKER/Dockerfile)
+- `0.15.0` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/170777300ea92dc21a8aec1abc16cb51812513a4/DOCKER/Dockerfile)
+- `0.13.0` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/a28b3fff49dce2fb31f90abb2fc693834e0029c2/DOCKER/Dockerfile)
+- `0.12.1` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/457c688346b565e90735431619ca3ca597ef9007/DOCKER/Dockerfile)
+- `0.12.0` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/70d8afa6e952e24c573ece345560a5971bf2cc0e/DOCKER/Dockerfile)
+- `0.11.0` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/9177cc1f64ca88a4a0243c5d1773d10fba67e201/DOCKER/Dockerfile)
 - `0.10.0` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/e5342f4054ab784b2cd6150e14f01053d7c8deb2/DOCKER/Dockerfile)
 - `0.9.1`, `0.9`, [(Dockerfile)](https://github.com/tendermint/tendermint/blob/809e0e8c5933604ba8b2d096803ada7c5ec4dfd3/DOCKER/Dockerfile)
 - `0.9.0` [(Dockerfile)](https://github.com/tendermint/tendermint/blob/d474baeeea6c22b289e7402449572f7c89ee21da/DOCKER/Dockerfile)
@@ -12,7 +17,7 @@
 # Quick reference
 
 * **Where to get help:**
-  [Chat on Rocket](https://cosmos.rocket.chat/)
+  https://tendermint.com/community
 
 * **Where to file issues:**
   https://github.com/tendermint/tendermint/issues
@@ -30,13 +35,13 @@ To get started developing applications, see the [application developers guide](h
 
 # How to use this image
 
-## Start one instance of the Tendermint core with the `dummy` app
+## Start one instance of the Tendermint core with the `kvstore` app
 
 A very simple example of a built-in app and Tendermint core in one container.
 
 ```
 docker run -it --rm -v "/tmp:/tendermint" tendermint/tendermint init
-docker run -it --rm -v "/tmp:/tendermint" tendermint/tendermint node --proxy_app=dummy
+docker run -it --rm -v "/tmp:/tendermint" tendermint/tendermint node --proxy_app=kvstore
 ```
 
 ## mintnet-kubernetes

Gopkg.lock

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

Gopkg.toml

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

INSTALL.md

@@ -1 +0,0 @@
-The installation guide has moved to the [docs directory](docs/guides/install-from-source.md) in order to easily be rendered by the website. Please update your links accordingly.

Makefile

@@ -1,29 +1,135 @@
 GOTOOLS = \
-					github.com/mitchellh/gox \
-					github.com/tcnksm/ghr \
-					github.com/Masterminds/glide \
-
+	github.com/golang/dep/cmd/dep \
+	gopkg.in/alecthomas/gometalinter.v2
 PACKAGES=$(shell go list ./... | grep -v '/vendor/')
 BUILD_TAGS?=tendermint
-TMHOME = $${TMHOME:-$$HOME/.tendermint}
+BUILD_FLAGS = -ldflags "-X github.com/tendermint/tendermint/version.GitCommit=`git rev-parse --short=8 HEAD`"
 
-all: install test
+all: check build test install
 
-install: get_vendor_deps
-	@go install --ldflags '-extldflags "-static"' \
-		--ldflags "-X github.com/tendermint/tendermint/version.GitCommit=`git rev-parse HEAD`" ./cmd/tendermint
+check: check_tools ensure_deps
+
+
+########################################
+### Build
 
 build:
-	go build \
-		--ldflags "-X github.com/tendermint/tendermint/version.GitCommit=`git rev-parse HEAD`"  -o build/tendermint ./cmd/tendermint/
+	CGO_ENABLED=0 go build $(BUILD_FLAGS) -tags '$(BUILD_TAGS)' -o build/tendermint ./cmd/tendermint/
 
 build_race:
-	go build -race -o build/tendermint ./cmd/tendermint
+	CGO_ENABLED=0 go build -race $(BUILD_FLAGS) -tags '$(BUILD_TAGS)' -o build/tendermint ./cmd/tendermint
+
+install:
+	CGO_ENABLED=0 go install $(BUILD_FLAGS) -tags '$(BUILD_TAGS)' ./cmd/tendermint
+
+########################################
+### Distribution
 
 # dist builds binaries for all platforms and packages them for distribution
 dist:
 	@BUILD_TAGS='$(BUILD_TAGS)' sh -c "'$(CURDIR)/scripts/dist.sh'"
 
+########################################
+### Tools & dependencies
+
+check_tools:
+	@# https://stackoverflow.com/a/25668869
+	@echo "Found tools: $(foreach tool,$(notdir $(GOTOOLS)),\
+        $(if $(shell which $(tool)),$(tool),$(error "No $(tool) in PATH")))"
+
+get_tools:
+	@echo "--> Installing tools"
+	go get -u -v $(GOTOOLS)
+	@gometalinter.v2 --install
+
+update_tools:
+	@echo "--> Updating tools"
+	@go get -u $(GOTOOLS)
+
+#Run this from CI
+get_vendor_deps:
+	@rm -rf vendor/
+	@echo "--> Running dep"
+	@dep ensure -vendor-only
+
+
+#Run this locally.
+ensure_deps:
+	@rm -rf vendor/
+	@echo "--> Running dep"
+	@dep ensure
+
+draw_deps:
+	@# requires brew install graphviz or apt-get install graphviz
+	go get github.com/RobotsAndPencils/goviz
+	@goviz -i github.com/tendermint/tendermint/cmd/tendermint -d 3 | dot -Tpng -o dependency-graph.png
+
+get_deps_bin_size:
+	@# Copy of build recipe with additional flags to perform binary size analysis
+	$(eval $(shell go build -work -a $(BUILD_FLAGS) -tags '$(BUILD_TAGS)' -o build/tendermint ./cmd/tendermint/ 2>&1))
+	@find $(WORK) -type f -name "*.a" | xargs -I{} du -hxs "{}" | sort -rh | sed -e s:${WORK}/::g > deps_bin_size.log
+	@echo "Results can be found here: $(CURDIR)/deps_bin_size.log"
+
+########################################
+### Testing
+
+## required to be run first by most tests
+build_docker_test_image:
+	docker build -t tester -f ./test/docker/Dockerfile .
+
+### coverage, app, persistence, and libs tests
+test_cover:
+	# run the go unit tests with coverage
+	bash test/test_cover.sh
+
+test_apps:
+	# run the app tests using bash
+	# requires `abci-cli` and `tendermint` binaries installed
+	bash test/app/test.sh
+
+test_persistence:
+	# run the persistence tests using bash
+	# requires `abci-cli` installed
+	docker run --name run_persistence -t tester bash test/persist/test_failure_indices.sh
+
+	# TODO undockerize
+	# bash test/persist/test_failure_indices.sh
+
+test_p2p:
+	docker rm -f rsyslog || true
+	rm -rf test/logs || true
+	mkdir test/logs
+	cd test/
+	docker run -d -v "logs:/var/log/" -p 127.0.0.1:5514:514/udp --name rsyslog voxxit/rsyslog
+	cd ..
+	# requires 'tester' the image from above
+	bash test/p2p/test.sh tester
+
+need_abci:
+	bash scripts/install_abci_apps.sh
+
+test_integrations:
+	make build_docker_test_image
+	make get_tools
+	make get_vendor_deps
+	make install
+	make need_abci
+	make test_cover
+	make test_apps
+	make test_persistence
+	make test_p2p
+
+test_release:
+	@go test -tags release $(PACKAGES)
+
+test100:
+	@for i in {1..100}; do make test; done
+
+vagrant_test:
+	vagrant up
+	vagrant ssh -c 'make test_integrations'
+
+### go tests
 test:
 	@echo "--> Running go test"
 	@go test $(PACKAGES)
@@ -32,55 +138,65 @@ test_race:
 	@echo "--> Running go test --race"
 	@go test -v -race $(PACKAGES)
 
-test_integrations:
-	@bash ./test/test.sh
-
-release:
-	@go test -tags release $(PACKAGES)
-
-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
-
-list_deps:
-	@go list -f '{{join .Deps "\n"}}' ./... | \
-		grep -v /vendor/ | sort | uniq | \
-		xargs go list -f '{{if not .Standard}}{{.ImportPath}}{{end}}'
-
-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
-
-get_vendor_deps: ensure_tools
-	@rm -rf vendor/
-	@echo "--> Running glide install"
-	@glide install
-
-update_deps: tools
-	@echo "--> Updating dependencies"
-	@go get -d -u ./...
-
-revision:
-	-echo `git rev-parse --verify HEAD` > $(TMHOME)/revision
-	-echo `git rev-parse --verify HEAD` >> $(TMHOME)/revision_history
-
-tools:
-	go get -u -v $(GOTOOLS)
-
-ensure_tools:
-	go get $(GOTOOLS)
 
+########################################
 ### Formatting, linting, and vetting
 
-megacheck:
-	@for pkg in ${PACKAGES}; do megacheck "$$pkg"; done
+fmt:
+	@go fmt ./...
 
+metalinter:
+	@echo "--> Running linter"
+	@gometalinter.v2 --vendor --deadline=600s --disable-all  \
+		--enable=deadcode \
+		--enable=gosimple \
+	 	--enable=misspell \
+		--enable=safesql \
+		./...
+		#--enable=gas \
+		#--enable=maligned \
+		#--enable=dupl \
+		#--enable=errcheck \
+		#--enable=goconst \
+		#--enable=gocyclo \
+		#--enable=goimports \
+		#--enable=golint \ <== comments on anything exported
+		#--enable=gotype \
+	 	#--enable=ineffassign \
+	   	#--enable=interfacer \
+	   	#--enable=megacheck \
+	   	#--enable=staticcheck \
+	   	#--enable=structcheck \
+	   	#--enable=unconvert \
+	   	#--enable=unparam \
+		#--enable=unused \
+	   	#--enable=varcheck \
+		#--enable=vet \
+		#--enable=vetshadow \
+
+metalinter_all:
+	@echo "--> Running linter (all)"
+	gometalinter.v2 --vendor --deadline=600s --enable-all --disable=lll ./...
+
+###########################################################
+### Local testnet using docker
+
+# Build linux binary on other platforms
+build-linux:
+	GOOS=linux GOARCH=amd64 $(MAKE) build
+
+# Run a 4-node testnet locally
+docker-start:
+	@echo "Wait until 'Attaching to node0, node1, node2, node3' message appears"
+	@if ! [ -f build/node0/config/genesis.json ]; then docker run --rm -v `pwd`/build:/tendermint:Z tendermint/localnode testnet --v 4 --o . --populate-persistent-peers --starting-ip-address 192.167.10.2 ; fi
+	docker-compose up
+
+# Stop testnet
+docker-stop:
+	docker-compose down
+
+# To avoid unintended conflicts with file names, always add to .PHONY
+# unless there is a reason not to.
+# https://www.gnu.org/software/make/manual/html_node/Phony-Targets.html
+.PHONY: check build build_race dist install check_tools get_tools update_tools get_vendor_deps draw_deps test_cover test_apps test_persistence test_p2p test test_race test_integrations test_release test100 vagrant_test fmt build-linux docker-start docker-stop
 
-.PHONY: install build build_race dist test test_race test_integrations test100 draw_deps list_deps get_deps get_vendor_deps update_deps revision tools

README.md

@@ -8,6 +8,7 @@ Or [Blockchain](https://en.wikipedia.org/wiki/Blockchain_(database)) for short.
 [![API Reference](
 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/)
 [![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)
@@ -23,7 +24,13 @@ _NOTE: This is alpha software. Please contact us if you intend to run it in prod
 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](http://tendermint.readthedocs.io/projects/tools/en/master).
+For more information, from introduction to install to application development, [Read The Docs](https://tendermint.readthedocs.io/en/master/).
+
+## Minimum requirements
+
+Requirement|Notes
+---|---
+Go version | Go1.9 or higher
 
 ## Install
 
@@ -33,13 +40,13 @@ To install from source, you should be able to:
 
 `go get -u github.com/tendermint/tendermint/cmd/tendermint`
 
-For more details (or if it fails), [read the docs](http://tendermint.readthedocs.io/projects/tools/en/master/install.html).
+For more details (or if it fails), [read the docs](https://tendermint.readthedocs.io/en/master/install.html).
 
 ## Resources
 
 ### Tendermint Core
 
-All resources involving the use of, building application on, or developing for, tendermint, can be found at [Read The Docs](http://tendermint.readthedocs.io/projects/tools/en/master). Additional information about some - and eventually all - of the sub-projects below, can be found at Read The Docs.
+All resources involving the use of, building application on, or developing for, tendermint, can be found at [Read The Docs](https://tendermint.readthedocs.io/en/master/). Additional information about some - and eventually all - of the sub-projects below, can be found at Read The Docs.
 
 ### Sub-projects
 

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
@@ -10,29 +10,43 @@ Vagrant.configure("2") do |config|
   end
 
   config.vm.provision "shell", inline: <<-SHELL
-    apt-get update
-    apt-get install -y --no-install-recommends wget curl jq shellcheck bsdmainutils psmisc
+    # add docker repo
+    curl -fsSL https://download.docker.com/linux/ubuntu/gpg | apt-key add -
+    add-apt-repository "deb [arch=amd64] https://download.docker.com/linux/ubuntu xenial stable"
 
-    wget -qO- https://get.docker.com/ | sh
-    usermod -a -G docker vagrant
+    # and golang 1.9 support
+    # official repo doesn't have race detection runtime...
+    # add-apt-repository ppa:gophers/archive
+    add-apt-repository ppa:longsleep/golang-backports
+
+    # install base requirements
+    apt-get update
+    apt-get install -y --no-install-recommends wget curl jq zip \
+        make shellcheck bsdmainutils psmisc
+    apt-get install -y docker-ce golang-1.9-go
+    apt-get install -y language-pack-en
+
+    # cleanup
     apt-get autoremove -y
 
-    curl -O https://storage.googleapis.com/golang/go1.9.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=$PATH:/usr/local/go/bin:/home/vagrant/go/bin' >> /home/vagrant/.bash_profile
+    # needed for docker
+    usermod -a -G docker vagrant
+
+    # set env variables
+    echo 'export PATH=$PATH:/usr/lib/go-1.9/bin:/home/vagrant/go/bin' >> /home/vagrant/.bash_profile
     echo 'export GOPATH=/home/vagrant/go' >> /home/vagrant/.bash_profile
-
     echo 'export LC_ALL=en_US.UTF-8' >> /home/vagrant/.bash_profile
+    echo 'cd go/src/github.com/tendermint/tendermint' >> /home/vagrant/.bash_profile
 
+    mkdir -p /home/vagrant/go/bin
     mkdir -p /home/vagrant/go/src/github.com/tendermint
     ln -s /vagrant /home/vagrant/go/src/github.com/tendermint/tendermint
 
     chown -R vagrant:vagrant /home/vagrant/go
+    chown vagrant:vagrant /home/vagrant/.bash_profile
 
-    su - vagrant -c 'cd /home/vagrant/go/src/github.com/tendermint/tendermint && make get_vendor_deps'
+    # get all deps and tools, ready to install/test
+    su - vagrant  -c 'source /home/vagrant/.bash_profile'
+    su - vagrant -c 'cd /home/vagrant/go/src/github.com/tendermint/tendermint && make get_tools && make get_vendor_deps'
   SHELL
 end

appveyor.yml

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

benchmarks/blockchain/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

@@ -2,37 +2,47 @@ package benchmarks
 
 import (
 	"testing"
+	"time"
 
+	amino "github.com/tendermint/go-amino"
 	"github.com/tendermint/go-crypto"
-	"github.com/tendermint/tendermint/p2p"
-	"github.com/tendermint/go-wire"
+
 	proto "github.com/tendermint/tendermint/benchmarks/proto"
+	"github.com/tendermint/tendermint/p2p"
 	ctypes "github.com/tendermint/tendermint/rpc/core/types"
 )
 
 func BenchmarkEncodeStatusWire(b *testing.B) {
 	b.StopTimer()
-	pubKey := crypto.GenPrivKeyEd25519().PubKey()
+	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:   1234,
+		SyncInfo: ctypes.SyncInfo{
+			LatestBlockHash:   []byte("SOMEBYTES"),
+			LatestBlockHeight: 123,
+			LatestBlockTime:   time.Unix(0, 1234),
+		},
+		ValidatorInfo: ctypes.ValidatorInfo{
+			PubKey: nodeKey.PubKey(),
+		},
 	}
 	b.StartTimer()
 
 	counter := 0
 	for i := 0; i < b.N; i++ {
-		jsonBytes := wire.JSONBytes(status)
+		jsonBytes, err := cdc.MarshalJSON(status)
+		if err != nil {
+			panic(err)
+		}
 		counter += len(jsonBytes)
 	}
 
@@ -40,12 +50,13 @@ func BenchmarkEncodeStatusWire(b *testing.B) {
 
 func BenchmarkEncodeNodeInfoWire(b *testing.B) {
 	b.StopTimer()
-	pubKey := crypto.GenPrivKeyEd25519().PubKey().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"},
@@ -54,19 +65,23 @@ func BenchmarkEncodeNodeInfoWire(b *testing.B) {
 
 	counter := 0
 	for i := 0; i < b.N; i++ {
-		jsonBytes := wire.JSONBytes(nodeInfo)
+		jsonBytes, err := cdc.MarshalJSON(nodeInfo)
+		if err != nil {
+			panic(err)
+		}
 		counter += len(jsonBytes)
 	}
 }
 
 func BenchmarkEncodeNodeInfoBinary(b *testing.B) {
 	b.StopTimer()
-	pubKey := crypto.GenPrivKeyEd25519().PubKey().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"},
@@ -75,7 +90,7 @@ func BenchmarkEncodeNodeInfoBinary(b *testing.B) {
 
 	counter := 0
 	for i := 0; i < b.N; i++ {
-		jsonBytes := wire.BinaryBytes(nodeInfo)
+		jsonBytes := cdc.MustMarshalBinaryBare(nodeInfo)
 		counter += len(jsonBytes)
 	}
 
@@ -83,16 +98,20 @@ func BenchmarkEncodeNodeInfoBinary(b *testing.B) {
 
 func BenchmarkEncodeNodeInfoProto(b *testing.B) {
 	b.StopTimer()
-	pubKey := crypto.GenPrivKeyEd25519().PubKey().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/experiments/Makefile

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

benchmarks/experiments/glide.yaml

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

benchmarks/experiments/main.go

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

benchmarks/os_test.go

@@ -18,12 +18,16 @@ func BenchmarkFileWrite(b *testing.B) {
 	b.StartTimer()
 
 	for i := 0; i < b.N; i++ {
-		file.Write([]byte(testString))
+		_, err := file.Write([]byte(testString))
+		if err != nil {
+			b.Error(err)
+		}
 	}
 
-	file.Close()
-	err = os.Remove("benchmark_file_write.out")
-	if err != nil {
+	if err := file.Close(); err != nil {
+		b.Error(err)
+	}
+	if err := os.Remove("benchmark_file_write.out"); err != nil {
 		b.Error(err)
 	}
 }

benchmarks/proto/test.proto

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

benchmarks/simu/counter.go

@@ -12,7 +12,7 @@ import (
 
 func main() {
 	wsc := rpcclient.NewWSClient("127.0.0.1:46657", "/websocket")
-	_, err := wsc.Start()
+	err := wsc.Start()
 	if err != nil {
 		cmn.Exit(err.Error())
 	}

blockchain/pool.go

@@ -1,18 +1,21 @@
 package blockchain
 
 import (
+	"errors"
+	"fmt"
 	"math"
 	"sync"
 	"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 +25,6 @@ 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 +32,20 @@ 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.
@@ -52,27 +64,27 @@ type BlockPool struct {
 
 	mtx sync.Mutex
 	// block requests
-	requesters map[int]*bpRequester
-	height     int   // the lowest key in requesters.
+	requesters map[int64]*bpRequester
+	height     int64 // the lowest key in requesters.
 	numPending int32 // number of requests pending assignment or block response
 	// peers
-	peers         map[string]*bpPeer
-	maxPeerHeight int
+	peers         map[p2p.ID]*bpPeer
+	maxPeerHeight int64
 
 	requestsCh chan<- BlockRequest
-	timeoutsCh chan<- string
+	errorsCh   chan<- peerError
 }
 
-func NewBlockPool(start int, requestsCh chan<- BlockRequest, timeoutsCh chan<- string) *BlockPool {
+func NewBlockPool(start int64, requestsCh chan<- BlockRequest, errorsCh chan<- peerError) *BlockPool {
 	bp := &BlockPool{
-		peers: make(map[string]*bpPeer),
+		peers: make(map[p2p.ID]*bpPeer),
 
-		requesters: make(map[int]*bpRequester),
+		requesters: make(map[int64]*bpRequester),
 		height:     start,
 		numPending: 0,
 
 		requestsCh: requestsCh,
-		timeoutsCh: timeoutsCh,
+		errorsCh:   errorsCh,
 	}
 	bp.BaseService = *cmn.NewBaseService(nil, "BlockPool", bp)
 	return bp
@@ -88,7 +100,6 @@ func (pool *BlockPool) OnStop() {}
 
 // Run spawns requesters as needed.
 func (pool *BlockPool) makeRequestersRoutine() {
-
 	for {
 		if !pool.IsRunning() {
 			break
@@ -119,10 +130,14 @@ func (pool *BlockPool) removeTimedoutPeers() {
 	for _, peer := range pool.peers {
 		if !peer.didTimeout && peer.numPending > 0 {
 			curRate := peer.recvMonitor.Status().CurRate
-			// XXX remove curRate != 0
+			// curRate can be 0 on start
 			if curRate != 0 && curRate < minRecvRate {
-				pool.sendTimeout(peer.id)
-				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
 			}
 		}
@@ -132,7 +147,7 @@ func (pool *BlockPool) removeTimedoutPeers() {
 	}
 }
 
-func (pool *BlockPool) GetStatus() (height int, numPending int32, lenRequesters int) {
+func (pool *BlockPool) GetStatus() (height int64, numPending int32, lenRequesters int) {
 	pool.mtx.Lock()
 	defer pool.mtx.Unlock()
 
@@ -189,35 +204,43 @@ 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 int) {
+// Returns the ID of the removed peer.
+func (pool *BlockPool) RedoRequest(height int64) p2p.ID {
 	pool.mtx.Lock()
 	defer pool.mtx.Unlock()
 
 	request := pool.requesters[height]
 
 	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
 	}
 
@@ -232,15 +255,15 @@ func (pool *BlockPool) AddBlock(peerID string, block *types.Block, blockSize int
 	}
 }
 
-// MaxPeerHeight returns the heighest height reported by a peer
-func (pool *BlockPool) MaxPeerHeight() int {
+// MaxPeerHeight returns the highest height reported by a peer.
+func (pool *BlockPool) MaxPeerHeight() int64 {
 	pool.mtx.Lock()
 	defer pool.mtx.Unlock()
 	return pool.maxPeerHeight
 }
 
 // Sets the peer's alleged blockchain height.
-func (pool *BlockPool) SetPeerHeight(peerID string, height int) {
+func (pool *BlockPool) SetPeerHeight(peerID p2p.ID, height int64) {
 	pool.mtx.Lock()
 	defer pool.mtx.Unlock()
 
@@ -258,14 +281,14 @@ func (pool *BlockPool) SetPeerHeight(peerID string, height int) {
 	}
 }
 
-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 {
@@ -279,7 +302,7 @@ func (pool *BlockPool) removePeer(peerID string) {
 
 // Pick an available peer with at least the given minHeight.
 // If no peers are available, returns nil.
-func (pool *BlockPool) pickIncrAvailablePeer(minHeight int) *bpPeer {
+func (pool *BlockPool) pickIncrAvailablePeer(minHeight int64) *bpPeer {
 	pool.mtx.Lock()
 	defer pool.mtx.Unlock()
 
@@ -304,28 +327,35 @@ func (pool *BlockPool) makeNextRequester() {
 	pool.mtx.Lock()
 	defer pool.mtx.Unlock()
 
-	nextHeight := pool.height + len(pool.requesters)
+	nextHeight := pool.height + pool.requestersLen()
 	request := newBPRequester(pool, nextHeight)
 	// request.SetLogger(pool.Logger.With("height", nextHeight))
 
 	pool.requesters[nextHeight] = request
 	pool.numPending++
 
-	request.Start()
+	err := request.Start()
+	if err != nil {
+		request.Logger.Error("Error starting request", "err", err)
+	}
 }
 
-func (pool *BlockPool) sendRequest(height int, peerID string) {
+func (pool *BlockPool) requestersLen() int64 {
+	return int64(len(pool.requesters))
+}
+
+func (pool *BlockPool) sendRequest(height int64, peerID p2p.ID) {
 	if !pool.IsRunning() {
 		return
 	}
 	pool.requestsCh <- BlockRequest{height, peerID}
 }
 
-func (pool *BlockPool) sendTimeout(peerID string) {
+func (pool *BlockPool) sendError(err error, peerID p2p.ID) {
 	if !pool.IsRunning() {
 		return
 	}
-	pool.timeoutsCh <- peerID
+	pool.errorsCh <- peerError{err, peerID}
 }
 
 // unused by tendermint; left for debugging purposes
@@ -334,7 +364,8 @@ func (pool *BlockPool) debug() string {
 	defer pool.mtx.Unlock()
 
 	str := ""
-	for h := pool.height; h < pool.height+len(pool.requesters); h++ {
+	nextHeight := pool.height + pool.requestersLen()
+	for h := pool.height; h < nextHeight; h++ {
 		if pool.requesters[h] == nil {
 			str += cmn.Fmt("H(%v):X ", h)
 		} else {
@@ -349,10 +380,10 @@ func (pool *BlockPool) debug() string {
 
 type bpPeer struct {
 	pool        *BlockPool
-	id          string
+	id          p2p.ID
 	recvMonitor *flow.Monitor
 
-	height     int
+	height     int64
 	numPending int32
 	timeout    *time.Timer
 	didTimeout bool
@@ -360,7 +391,7 @@ type bpPeer struct {
 	logger log.Logger
 }
 
-func newBPPeer(pool *BlockPool, peerID string, height int) *bpPeer {
+func newBPPeer(pool *BlockPool, peerID p2p.ID, height int64) *bpPeer {
 	peer := &bpPeer{
 		pool:       pool,
 		id:         peerID,
@@ -383,9 +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)
 	}
 }
 
@@ -411,8 +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
 }
 
@@ -421,16 +453,16 @@ func (peer *bpPeer) onTimeout() {
 type bpRequester struct {
 	cmn.BaseService
 	pool       *BlockPool
-	height     int
+	height     int64
 	gotBlockCh chan struct{}
 	redoCh     chan struct{}
 
 	mtx    sync.Mutex
-	peerID string
+	peerID p2p.ID
 	block  *types.Block
 }
 
-func newBPRequester(pool *BlockPool, height int) *bpRequester {
+func newBPRequester(pool *BlockPool, height int64) *bpRequester {
 	bpr := &bpRequester{
 		pool:       pool,
 		height:     height,
@@ -450,7 +482,7 @@ func (bpr *bpRequester) OnStart() error {
 }
 
 // Returns true if the peer matches
-func (bpr *bpRequester) setBlock(block *types.Block, peerID string) bool {
+func (bpr *bpRequester) setBlock(block *types.Block, peerID p2p.ID) bool {
 	bpr.mtx.Lock()
 	if bpr.block != nil || bpr.peerID != peerID {
 		bpr.mtx.Unlock()
@@ -469,7 +501,7 @@ func (bpr *bpRequester) getBlock() *types.Block {
 	return bpr.block
 }
 
-func (bpr *bpRequester) getPeerID() string {
+func (bpr *bpRequester) getPeerID() p2p.ID {
 	bpr.mtx.Lock()
 	defer bpr.mtx.Unlock()
 	return bpr.peerID
@@ -494,7 +526,7 @@ func (bpr *bpRequester) requestRoutine() {
 OUTER_LOOP:
 	for {
 		// Pick a peer to send request to.
-		var peer *bpPeer = nil
+		var peer *bpPeer
 	PICK_PEER_LOOP:
 		for {
 			if !bpr.IsRunning() || !bpr.pool.IsRunning() {
@@ -515,10 +547,10 @@ OUTER_LOOP:
 		// Send request and wait.
 		bpr.pool.sendRequest(bpr.height, peer.id)
 		select {
-		case <-bpr.pool.Quit:
+		case <-bpr.pool.Quit():
 			bpr.Stop()
 			return
-		case <-bpr.Quit:
+		case <-bpr.Quit():
 			return
 		case <-bpr.redoCh:
 			bpr.reset()
@@ -526,10 +558,10 @@ OUTER_LOOP:
 		case <-bpr.gotBlockCh:
 			// We got the block, now see if it's good.
 			select {
-			case <-bpr.pool.Quit:
+			case <-bpr.pool.Quit():
 				bpr.Stop()
 				return
-			case <-bpr.Quit:
+			case <-bpr.Quit():
 				return
 			case <-bpr.redoCh:
 				bpr.reset()
@@ -542,6 +574,6 @@ OUTER_LOOP:
 //-------------------------------------
 
 type BlockRequest struct {
-	Height int
-	PeerID string
+	Height int64
+	PeerID p2p.ID
 }

blockchain/pool_test.go

@@ -5,38 +5,45 @@ 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
-	height int
+	id     p2p.ID
+	height int64
 }
 
-func makePeers(numPeers int, minHeight, maxHeight int) map[string]testPeer {
-	peers := make(map[string]testPeer, numPeers)
+func makePeers(numPeers int, minHeight, maxHeight int64) map[p2p.ID]testPeer {
+	peers := make(map[p2p.ID]testPeer, numPeers)
 	for i := 0; i < numPeers; i++ {
-		peerID := cmn.RandStr(12)
-		height := minHeight + rand.Intn(maxHeight-minHeight)
+		peerID := p2p.ID(cmn.RandStr(12))
+		height := minHeight + rand.Int63n(maxHeight-minHeight)
 		peers[peerID] = testPeer{peerID, height}
 	}
 	return peers
 }
 
 func TestBasic(t *testing.T) {
-	start := 42
+	start := int64(42)
 	peers := makePeers(10, start+1, 1000)
-	timeoutsCh := make(chan string, 100)
-	requestsCh := make(chan BlockRequest, 100)
-	pool := NewBlockPool(start, requestsCh, timeoutsCh)
+	errorsCh := make(chan peerError, 1000)
+	requestsCh := make(chan BlockRequest, 1000)
+	pool := NewBlockPool(start, requestsCh, errorsCh)
 	pool.SetLogger(log.TestingLogger())
-	pool.Start()
+
+	err := pool.Start()
+	if err != nil {
+		t.Error(err)
+	}
+
 	defer pool.Stop()
 
 	// Introduce each peer.
@@ -64,8 +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 {
@@ -82,13 +89,16 @@ func TestBasic(t *testing.T) {
 }
 
 func TestTimeout(t *testing.T) {
-	start := 42
+	start := int64(42)
 	peers := makePeers(10, start+1, 1000)
-	timeoutsCh := make(chan string, 100)
-	requestsCh := make(chan BlockRequest, 100)
-	pool := NewBlockPool(start, requestsCh, timeoutsCh)
+	errorsCh := make(chan peerError, 1000)
+	requestsCh := make(chan BlockRequest, 1000)
+	pool := NewBlockPool(start, requestsCh, errorsCh)
 	pool.SetLogger(log.TestingLogger())
-	pool.Start()
+	err := pool.Start()
+	if err != nil {
+		t.Error(err)
+	}
 	defer pool.Stop()
 
 	for _, peer := range peers {
@@ -119,12 +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"
+	amino "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
@@ -29,52 +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
 
-	evsw types.EventSwitch
+	blockExec *sm.BlockExecutor
+	store     *BlockStore
+	pool      *BlockPool
+	fastSync  bool
+
+	requestsCh <-chan BlockRequest
+	errorsCh   <-chan peerError
 }
 
 // NewBlockchainReactor returns new reactor instance.
-func NewBlockchainReactor(state *sm.State, proxyAppConn proxy.AppConnConsensus, store *BlockStore, fastSync bool) *BlockchainReactor {
-	if state.LastBlockHeight == store.Height()-1 {
-		store.height-- // XXX HACK, make this better
-	}
+func NewBlockchainReactor(state sm.State, blockExec *sm.BlockExecutor, store *BlockStore,
+	fastSync bool) *BlockchainReactor {
+
 	if state.LastBlockHeight != store.Height() {
-		cmn.PanicSanity(cmn.Fmt("state (%v) and store (%v) height mismatch", state.LastBlockHeight, store.Height()))
+		panic(fmt.Sprintf("state (%v) and store (%v) height mismatch", state.LastBlockHeight,
+			store.Height()))
 	}
-	requestsCh := make(chan BlockRequest, defaultChannelCapacity)
-	timeoutsCh := make(chan string, defaultChannelCapacity)
+
+	const capacity = 1000 // must be bigger than peers count
+	requestsCh := make(chan BlockRequest, capacity)
+	errorsCh := make(chan peerError, capacity) // so we don't block in #Receive#pool.AddBlock
+
 	pool := NewBlockPool(
 		store.Height()+1,
 		requestsCh,
-		timeoutsCh,
+		errorsCh,
 	)
+
 	bcR := &BlockchainReactor{
-		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
@@ -88,9 +106,11 @@ func (bcR *BlockchainReactor) SetLogger(l log.Logger) {
 
 // OnStart implements cmn.Service.
 func (bcR *BlockchainReactor) OnStart() error {
-	bcR.BaseReactor.OnStart()
+	if err := bcR.BaseReactor.OnStart(); err != nil {
+		return err
+	}
 	if bcR.fastSync {
-		_, err := bcR.pool.Start()
+		err := bcR.pool.Start()
 		if err != nil {
 			return err
 		}
@@ -108,55 +128,61 @@ func (bcR *BlockchainReactor) OnStop() {
 // GetChannels implements Reactor
 func (bcR *BlockchainReactor) GetChannels() []*p2p.ChannelDescriptor {
 	return []*p2p.ChannelDescriptor{
-		&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
+	// bcStatusResponseMessage from the peer and call pool.SetPeerHeight
 }
 
 // RemovePeer implements Reactor by removing peer from the pool.
 func (bcR *BlockchainReactor) RemovePeer(peer p2p.Peer, reason interface{}) {
-	bcR.pool.RemovePeer(peer.Key())
+	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 {
@@ -164,27 +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.)
@@ -196,7 +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
@@ -204,27 +226,26 @@ 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
-			go bcR.BroadcastStatusRequest()
+			go bcR.BroadcastStatusRequest() // nolint: errcheck
 		case <-switchToConsensusTicker.C:
 			height, numPending, lenRequesters := bcR.pool.GetStatus()
 			outbound, inbound, _ := bcR.Switch.NumPeers()
@@ -235,7 +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
 			}
@@ -250,33 +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.evsw, bcR.proxyAppConn, first, firstPartsHeader, types.MockMempool{})
+					// TODO: same thing for app - but we would need a way to
+					// get the hash without persisting the state
+					var err error
+					state, err = bcR.blockExec.ApplyBlock(state, firstID, first)
 					if err != nil {
 						// TODO This is bad, are we zombie?
-						cmn.PanicQ(cmn.Fmt("Failed to process committed block (%d:%X): %v", first.Height, first.Hash(), err))
+						cmn.PanicQ(cmn.Fmt("Failed to process committed block (%d:%X): %v",
+							first.Height, first.Hash(), err))
 					}
-					blocksSynced += 1
+					blocksSynced++
 
 					if blocksSynced%100 == 0 {
 						lastRate = 0.9*lastRate + 0.1*(100/time.Since(lastHundred).Seconds())
@@ -287,7 +314,7 @@ FOR_LOOP:
 				}
 			}
 			continue FOR_LOOP
-		case <-bcR.Quit:
+		case <-bcR.Quit():
 			break FOR_LOOP
 		}
 	}
@@ -295,47 +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
 }
 
-// SetEventSwitch implements events.Eventable
-func (bcR *BlockchainReactor) SetEventSwitch(evsw types.EventSwitch) {
-	bcR.evsw = evsw
-}
-
 //-----------------------------------------------------------------------------
 // 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
 }
@@ -343,7 +359,7 @@ func DecodeMessage(bz []byte, maxSize int) (msgType byte, msg BlockchainMessage,
 //-------------------------------------
 
 type bcBlockRequestMessage struct {
-	Height int
+	Height int64
 }
 
 func (m *bcBlockRequestMessage) String() string {
@@ -351,7 +367,7 @@ func (m *bcBlockRequestMessage) String() string {
 }
 
 type bcNoBlockResponseMessage struct {
-	Height int
+	Height int64
 }
 
 func (brm *bcNoBlockResponseMessage) String() string {
@@ -360,7 +376,6 @@ func (brm *bcNoBlockResponseMessage) String() string {
 
 //-------------------------------------
 
-// NOTE: keep up-to-date with maxBlockchainResponseSize
 type bcBlockResponseMessage struct {
 	Block *types.Block
 }
@@ -372,7 +387,7 @@ func (m *bcBlockResponseMessage) String() string {
 //-------------------------------------
 
 type bcStatusRequestMessage struct {
-	Height int
+	Height int64
 }
 
 func (m *bcStatusRequestMessage) String() string {
@@ -382,7 +397,7 @@ func (m *bcStatusRequestMessage) String() string {
 //-------------------------------------
 
 type bcStatusResponseMessage struct {
-	Height int
+	Height int64
 }
 
 func (m *bcStatusResponseMessage) String() string {

blockchain/reactor_test.go

@@ -3,62 +3,72 @@ package blockchain
 import (
 	"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 int) *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,
+		types.MockMempool{}, types.MockEvidencePool{})
+
+	bcReactor := NewBlockchainReactor(state.Copy(), blockExec, blockStore, fastSync)
 	bcReactor.SetLogger(logger.With("module", "blockchain"))
 
 	// Next: we need to set a switch in order for peers to be added in
 	bcReactor.Switch = p2p.NewSwitch(cfg.DefaultP2PConfig())
 
 	// Lastly: let's add some blocks in
-	for blockHeight := 1; blockHeight <= maxBlockHeight; blockHeight++ {
+	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) {
-	maxBlockHeight := 20
+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)
 
 	tests := []struct {
-		height   int
+		height   int64
 		existent bool
 	}{
 		{maxBlockHeight + 2, false},
@@ -67,12 +77,13 @@ 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 {
@@ -90,62 +101,106 @@ 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
 
-func makeTxs(blockNumber int) (txs []types.Tx) {
+func makeTxs(height int64) (txs []types.Tx) {
 	for i := 0; i < 10; i++ {
-		txs = append(txs, types.Tx([]byte{byte(blockNumber), byte(i)}))
+		txs = append(txs, types.Tx([]byte{byte(height), byte(i)}))
 	}
 	return txs
 }
 
-func makeBlock(blockNumber int, state *sm.State) *types.Block {
-	prevHash := state.LastBlockID.Hash
-	prevParts := types.PartSetHeader{}
-	valHash := state.Validators.Hash()
-	prevBlockID := types.BlockID{prevHash, prevParts}
-	block, _ := types.MakeBlock(blockNumber, "test_chain", makeTxs(blockNumber),
-		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{})              {}

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"
-	. "github.com/tendermint/tmlibs/common"
+	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.
@@ -32,9 +29,11 @@ type BlockStore struct {
 	db dbm.DB
 
 	mtx    sync.RWMutex
-	height int
+	height int64
 }
 
+// NewBlockStore returns a new BlockStore with the given DB,
+// initialized to the last height that was committed to the DB.
 func NewBlockStore(db dbm.DB) *BlockStore {
 	bsjson := LoadBlockStoreStateJSON(db)
 	return &BlockStore{
@@ -43,134 +42,136 @@ func NewBlockStore(db dbm.DB) *BlockStore {
 	}
 }
 
-// Height() returns the last known contiguous block height.
-func (bs *BlockStore) Height() int {
+// Height returns the last known contiguous block height.
+func (bs *BlockStore) Height() int64 {
 	bs.mtx.RLock()
 	defer bs.mtx.RUnlock()
 	return bs.height
 }
 
-func (bs *BlockStore) GetReader(key []byte) io.Reader {
-	bytez := bs.db.Get(key)
-	if bytez == nil {
+// LoadBlock returns the block with the given height.
+// If no block is found for that height, it returns nil.
+func (bs *BlockStore) LoadBlock(height int64) *types.Block {
+	var blockMeta = bs.LoadBlockMeta(height)
+	if blockMeta == nil {
 		return nil
 	}
-	return bytes.NewReader(bytez)
-}
 
-func (bs *BlockStore) LoadBlock(height int) *types.Block {
-	var n int
-	var err error
-	r := bs.GetReader(calcBlockMetaKey(height))
-	if r == nil {
-		return nil
-	}
-	blockMeta := wire.ReadBinary(&types.BlockMeta{}, r, 0, &n, &err).(*types.BlockMeta)
-	if err != nil {
-		PanicCrisis(Fmt("Error reading block meta: %v", err))
-	}
-	bytez := []byte{}
+	var block = new(types.Block)
+	buf := []byte{}
 	for i := 0; i < blockMeta.BlockID.PartsHeader.Total; i++ {
 		part := bs.LoadBlockPart(height, i)
-		bytez = append(bytez, part.Bytes...)
+		buf = append(buf, part.Bytes...)
 	}
-	block := wire.ReadBinary(&types.Block{}, bytes.NewReader(bytez), 0, &n, &err).(*types.Block)
+	err := cdc.UnmarshalBinary(buf, block)
 	if err != nil {
-		PanicCrisis(Fmt("Error reading block: %v", err))
+		// NOTE: The existence of meta should imply the existence of the
+		// block. So, make sure meta is only saved after blocks are saved.
+		panic(cmn.ErrorWrap(err, "Error reading block"))
 	}
 	return block
 }
 
-func (bs *BlockStore) LoadBlockPart(height int, index int) *types.Part {
-	var n int
-	var err error
-	r := bs.GetReader(calcBlockPartKey(height, index))
-	if r == nil {
+// LoadBlockPart returns the Part at the given index
+// from the block at the given height.
+// If no part is found for the given height and index, it returns nil.
+func (bs *BlockStore) LoadBlockPart(height int64, index int) *types.Part {
+	var part = new(types.Part)
+	bz := bs.db.Get(calcBlockPartKey(height, index))
+	if len(bz) == 0 {
 		return nil
 	}
-	part := wire.ReadBinary(&types.Part{}, r, 0, &n, &err).(*types.Part)
+	err := cdc.UnmarshalBinaryBare(bz, part)
 	if err != nil {
-		PanicCrisis(Fmt("Error reading block part: %v", err))
+		panic(cmn.ErrorWrap(err, "Error reading block part"))
 	}
 	return part
 }
 
-func (bs *BlockStore) LoadBlockMeta(height int) *types.BlockMeta {
-	var n int
-	var err error
-	r := bs.GetReader(calcBlockMetaKey(height))
-	if r == nil {
+// LoadBlockMeta returns the BlockMeta for the given height.
+// If no block is found for the given height, it returns nil.
+func (bs *BlockStore) LoadBlockMeta(height int64) *types.BlockMeta {
+	var blockMeta = new(types.BlockMeta)
+	bz := bs.db.Get(calcBlockMetaKey(height))
+	if len(bz) == 0 {
 		return nil
 	}
-	blockMeta := wire.ReadBinary(&types.BlockMeta{}, r, 0, &n, &err).(*types.BlockMeta)
+	err := cdc.UnmarshalBinaryBare(bz, blockMeta)
 	if err != nil {
-		PanicCrisis(Fmt("Error reading block meta: %v", err))
+		panic(cmn.ErrorWrap(err, "Error reading block meta"))
 	}
 	return blockMeta
 }
 
-// The +2/3 and other Precommit-votes for block at `height`.
-// This Commit comes from block.LastCommit for `height+1`.
-func (bs *BlockStore) LoadBlockCommit(height int) *types.Commit {
-	var n int
-	var err error
-	r := bs.GetReader(calcBlockCommitKey(height))
-	if r == nil {
+// LoadBlockCommit returns the Commit for the given height.
+// This commit consists of the +2/3 and other Precommit-votes for block at `height`,
+// and it comes from the block.LastCommit for `height+1`.
+// If no commit is found for the given height, it returns nil.
+func (bs *BlockStore) LoadBlockCommit(height int64) *types.Commit {
+	var commit = new(types.Commit)
+	bz := bs.db.Get(calcBlockCommitKey(height))
+	if len(bz) == 0 {
 		return nil
 	}
-	commit := wire.ReadBinary(&types.Commit{}, r, 0, &n, &err).(*types.Commit)
+	err := cdc.UnmarshalBinaryBare(bz, commit)
 	if err != nil {
-		PanicCrisis(Fmt("Error reading commit: %v", err))
+		panic(cmn.ErrorWrap(err, "Error reading block commit"))
 	}
 	return commit
 }
 
-// NOTE: the Precommit-vote heights are for the block at `height`
-func (bs *BlockStore) LoadSeenCommit(height int) *types.Commit {
-	var n int
-	var err error
-	r := bs.GetReader(calcSeenCommitKey(height))
-	if r == nil {
+// LoadSeenCommit returns the locally seen Commit for the given height.
+// This is useful when we've seen a commit, but there has not yet been
+// a new block at `height + 1` that includes this commit in its block.LastCommit.
+func (bs *BlockStore) LoadSeenCommit(height int64) *types.Commit {
+	var commit = new(types.Commit)
+	bz := bs.db.Get(calcSeenCommitKey(height))
+	if len(bz) == 0 {
 		return nil
 	}
-	commit := wire.ReadBinary(&types.Commit{}, r, 0, &n, &err).(*types.Commit)
+	err := cdc.UnmarshalBinaryBare(bz, commit)
 	if err != nil {
-		PanicCrisis(Fmt("Error reading commit: %v", err))
+		panic(cmn.ErrorWrap(err, "Error reading block seen commit"))
 	}
 	return commit
 }
 
+// SaveBlock persists the given block, blockParts, and seenCommit to the underlying db.
 // blockParts: Must be parts of the block
 // seenCommit: The +2/3 precommits that were seen which committed at height.
 //             If all the nodes restart after committing a block,
 //             we need this to reload the precommits to catch-up nodes to the
 //             most recent height.  Otherwise they'd stall at H-1.
 func (bs *BlockStore) SaveBlock(block *types.Block, blockParts *types.PartSet, seenCommit *types.Commit) {
+	if block == nil {
+		cmn.PanicSanity("BlockStore can only save a non-nil block")
+	}
 	height := block.Height
-	if height != bs.Height()+1 {
-		PanicSanity(Fmt("BlockStore can only save contiguous blocks. Wanted %v, got %v", bs.Height()+1, height))
+	if g, w := height, bs.Height()+1; g != w {
+		cmn.PanicSanity(cmn.Fmt("BlockStore can only save contiguous blocks. Wanted %v, got %v", w, g))
 	}
 	if !blockParts.IsComplete() {
-		PanicSanity(Fmt("BlockStore can only save complete block part sets"))
+		cmn.PanicSanity(cmn.Fmt("BlockStore can only save complete block part sets"))
 	}
 
 	// Save block meta
 	blockMeta := types.NewBlockMeta(block, blockParts)
-	metaBytes := wire.BinaryBytes(blockMeta)
+	metaBytes := cdc.MustMarshalBinaryBare(blockMeta)
 	bs.db.Set(calcBlockMetaKey(height), metaBytes)
 
 	// Save block parts
 	for i := 0; i < blockParts.Total(); i++ {
-		bs.saveBlockPart(height, i, blockParts.GetPart(i))
+		part := blockParts.GetPart(i)
+		bs.saveBlockPart(height, i, part)
 	}
 
 	// Save block commit (duplicate and separate from the Block)
-	blockCommitBytes := wire.BinaryBytes(block.LastCommit)
+	blockCommitBytes := cdc.MustMarshalBinaryBare(block.LastCommit)
 	bs.db.Set(calcBlockCommitKey(height-1), blockCommitBytes)
 
 	// Save seen commit (seen +2/3 precommits for block)
 	// NOTE: we can delete this at a later height
-	seenCommitBytes := wire.BinaryBytes(seenCommit)
+	seenCommitBytes := cdc.MustMarshalBinaryBare(seenCommit)
 	bs.db.Set(calcSeenCommitKey(height), seenCommitBytes)
 
 	// Save new BlockStoreStateJSON descriptor
@@ -185,29 +186,29 @@ func (bs *BlockStore) SaveBlock(block *types.Block, blockParts *types.PartSet, s
 	bs.db.SetSync(nil, nil)
 }
 
-func (bs *BlockStore) saveBlockPart(height int, index int, part *types.Part) {
+func (bs *BlockStore) saveBlockPart(height int64, index int, part *types.Part) {
 	if height != bs.Height()+1 {
-		PanicSanity(Fmt("BlockStore can only save contiguous blocks. Wanted %v, got %v", bs.Height()+1, height))
+		cmn.PanicSanity(cmn.Fmt("BlockStore can only save contiguous blocks. Wanted %v, got %v", bs.Height()+1, height))
 	}
-	partBytes := wire.BinaryBytes(part)
+	partBytes := cdc.MustMarshalBinaryBare(part)
 	bs.db.Set(calcBlockPartKey(height, index), partBytes)
 }
 
 //-----------------------------------------------------------------------------
 
-func calcBlockMetaKey(height int) []byte {
+func calcBlockMetaKey(height int64) []byte {
 	return []byte(fmt.Sprintf("H:%v", height))
 }
 
-func calcBlockPartKey(height int, partIndex int) []byte {
+func calcBlockPartKey(height int64, partIndex int) []byte {
 	return []byte(fmt.Sprintf("P:%v:%v", height, partIndex))
 }
 
-func calcBlockCommitKey(height int) []byte {
+func calcBlockCommitKey(height int64) []byte {
 	return []byte(fmt.Sprintf("C:%v", height))
 }
 
-func calcSeenCommitKey(height int) []byte {
+func calcSeenCommitKey(height int64) []byte {
 	return []byte(fmt.Sprintf("SC:%v", height))
 }
 
@@ -216,28 +217,31 @@ func calcSeenCommitKey(height int) []byte {
 var blockStoreKey = []byte("blockStore")
 
 type BlockStoreStateJSON struct {
-	Height int
+	Height int64 `json:"height"`
 }
 
+// Save persists the blockStore state to the database as JSON.
 func (bsj BlockStoreStateJSON) Save(db dbm.DB) {
-	bytes, err := json.Marshal(bsj)
+	bytes, err := cdc.MarshalJSON(bsj)
 	if err != nil {
-		PanicSanity(Fmt("Could not marshal state bytes: %v", err))
+		cmn.PanicSanity(cmn.Fmt("Could not marshal state bytes: %v", err))
 	}
 	db.SetSync(blockStoreKey, bytes)
 }
 
+// LoadBlockStoreStateJSON returns the BlockStoreStateJSON as loaded from disk.
+// If no BlockStoreStateJSON was previously persisted, it returns the zero value.
 func LoadBlockStoreStateJSON(db dbm.DB) BlockStoreStateJSON {
 	bytes := db.Get(blockStoreKey)
-	if bytes == nil {
+	if len(bytes) == 0 {
 		return BlockStoreStateJSON{
 			Height: 0,
 		}
 	}
 	bsj := BlockStoreStateJSON{}
-	err := json.Unmarshal(bytes, &bsj)
+	err := cdc.UnmarshalJSON(bytes, &bsj)
 	if err != nil {
-		PanicCrisis(Fmt("Could not unmarshal bytes: %X", bytes))
+		panic(fmt.Sprintf("Could not unmarshal bytes: %X", bytes))
 	}
 	return bsj
 }

blockchain/store_test.go

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

blockchain/wire.go

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

certifiers/dynamic.go

@@ -1,89 +0,0 @@
-package certifiers
-
-import (
-	"github.com/tendermint/tendermint/types"
-
-	certerr "github.com/tendermint/tendermint/certifiers/errors"
-)
-
-var _ Certifier = &Dynamic{}
-
-// Dynamic uses a Static for Certify, but adds an
-// Update method to allow for a change of validators.
-//
-// You can pass in a FullCommit with another validator set,
-// and if this is a provably secure transition (< 1/3 change,
-// sufficient signatures), then it will update the
-// validator set for the next Certify call.
-// For security, it will only follow validator set changes
-// going forward.
-type Dynamic struct {
-	cert       *Static
-	lastHeight int
-}
-
-func NewDynamic(chainID string, vals *types.ValidatorSet, height int) *Dynamic {
-	return &Dynamic{
-		cert:       NewStatic(chainID, vals),
-		lastHeight: height,
-	}
-}
-
-func (c *Dynamic) ChainID() string {
-	return c.cert.ChainID()
-}
-
-func (c *Dynamic) Validators() *types.ValidatorSet {
-	return c.cert.vSet
-}
-
-func (c *Dynamic) Hash() []byte {
-	return c.cert.Hash()
-}
-
-func (c *Dynamic) LastHeight() int {
-	return c.lastHeight
-}
-
-// Certify handles this with
-func (c *Dynamic) Certify(check Commit) error {
-	err := c.cert.Certify(check)
-	if err == nil {
-		// update last seen height if input is valid
-		c.lastHeight = check.Height()
-	}
-	return err
-}
-
-// Update will verify if this is a valid change and update
-// the certifying validator set if safe to do so.
-//
-// Returns an error if update is impossible (invalid proof or IsTooMuchChangeErr)
-func (c *Dynamic) Update(fc FullCommit) error {
-	// ignore all checkpoints in the past -> only to the future
-	h := fc.Height()
-	if h <= c.lastHeight {
-		return certerr.ErrPastTime()
-	}
-
-	// first, verify if the input is self-consistent....
-	err := fc.ValidateBasic(c.ChainID())
-	if err != nil {
-		return err
-	}
-
-	// now, make sure not too much change... meaning this commit
-	// would be approved by the currently known validator set
-	// as well as the new set
-	commit := fc.Commit.Commit
-	err = c.Validators().VerifyCommitAny(fc.Validators, c.ChainID(),
-		commit.BlockID, h, commit)
-	if err != nil {
-		return certerr.ErrTooMuchChange()
-	}
-
-	// looks good, we can update
-	c.cert = NewStatic(c.ChainID(), fc.Validators)
-	c.lastHeight = h
-	return nil
-}

certifiers/files/commit.go

@@ -1,77 +0,0 @@
-package files
-
-import (
-	"encoding/json"
-	"os"
-
-	"github.com/pkg/errors"
-
-	wire "github.com/tendermint/go-wire"
-
-	"github.com/tendermint/tendermint/certifiers"
-	certerr "github.com/tendermint/tendermint/certifiers/errors"
-)
-
-const (
-	// MaxFullCommitSize is the maximum number of bytes we will
-	// read in for a full commit to avoid excessive allocations
-	// in the deserializer
-	MaxFullCommitSize = 1024 * 1024
-)
-
-// SaveFullCommit exports the seed in binary / go-wire style
-func SaveFullCommit(fc certifiers.FullCommit, path string) error {
-	f, err := os.Create(path)
-	if err != nil {
-		return errors.WithStack(err)
-	}
-	defer f.Close()
-
-	var n int
-	wire.WriteBinary(fc, f, &n, &err)
-	return errors.WithStack(err)
-}
-
-// SaveFullCommitJSON exports the seed in a json format
-func SaveFullCommitJSON(fc certifiers.FullCommit, path string) error {
-	f, err := os.Create(path)
-	if err != nil {
-		return errors.WithStack(err)
-	}
-	defer f.Close()
-	stream := json.NewEncoder(f)
-	err = stream.Encode(fc)
-	return errors.WithStack(err)
-}
-
-func LoadFullCommit(path string) (certifiers.FullCommit, error) {
-	var fc certifiers.FullCommit
-	f, err := os.Open(path)
-	if err != nil {
-		if os.IsNotExist(err) {
-			return fc, certerr.ErrCommitNotFound()
-		}
-		return fc, errors.WithStack(err)
-	}
-	defer f.Close()
-
-	var n int
-	wire.ReadBinaryPtr(&fc, f, MaxFullCommitSize, &n, &err)
-	return fc, errors.WithStack(err)
-}
-
-func LoadFullCommitJSON(path string) (certifiers.FullCommit, error) {
-	var fc certifiers.FullCommit
-	f, err := os.Open(path)
-	if err != nil {
-		if os.IsNotExist(err) {
-			return fc, certerr.ErrCommitNotFound()
-		}
-		return fc, errors.WithStack(err)
-	}
-	defer f.Close()
-
-	stream := json.NewDecoder(f)
-	err = stream.Decode(&fc)
-	return fc, errors.WithStack(err)
-}

certifiers/inquirer.go

@@ -1,142 +0,0 @@
-package certifiers
-
-import (
-	"github.com/tendermint/tendermint/types"
-
-	certerr "github.com/tendermint/tendermint/certifiers/errors"
-)
-
-type Inquiring struct {
-	cert *Dynamic
-	// These are only properly validated data, from local system
-	trusted Provider
-	// This is a source of new info, like a node rpc, or other import method
-	Source Provider
-}
-
-func NewInquiring(chainID string, fc FullCommit, trusted Provider, source Provider) *Inquiring {
-	// store the data in trusted
-	trusted.StoreCommit(fc)
-
-	return &Inquiring{
-		cert:    NewDynamic(chainID, fc.Validators, fc.Height()),
-		trusted: trusted,
-		Source:  source,
-	}
-}
-
-func (c *Inquiring) ChainID() string {
-	return c.cert.ChainID()
-}
-
-func (c *Inquiring) Validators() *types.ValidatorSet {
-	return c.cert.cert.vSet
-}
-
-func (c *Inquiring) LastHeight() int {
-	return c.cert.lastHeight
-}
-
-// Certify makes sure this is checkpoint is valid.
-//
-// If the validators have changed since the last know time, it looks
-// for a path to prove the new validators.
-//
-// On success, it will store the checkpoint in the store for later viewing
-func (c *Inquiring) Certify(commit Commit) error {
-	err := c.useClosestTrust(commit.Height())
-	if err != nil {
-		return err
-	}
-
-	err = c.cert.Certify(commit)
-	if !certerr.IsValidatorsChangedErr(err) {
-		return err
-	}
-	err = c.updateToHash(commit.Header.ValidatorsHash)
-	if err != nil {
-		return err
-	}
-
-	err = c.cert.Certify(commit)
-	if err != nil {
-		return err
-	}
-
-	// store the new checkpoint
-	c.trusted.StoreCommit(
-		NewFullCommit(commit, c.Validators()))
-	return nil
-}
-
-func (c *Inquiring) Update(fc FullCommit) error {
-	err := c.useClosestTrust(fc.Height())
-	if err != nil {
-		return err
-	}
-
-	err = c.cert.Update(fc)
-	if err == nil {
-		c.trusted.StoreCommit(fc)
-	}
-	return err
-}
-
-func (c *Inquiring) useClosestTrust(h int) error {
-	closest, err := c.trusted.GetByHeight(h)
-	if err != nil {
-		return err
-	}
-
-	// if the best seed is not the one we currently use,
-	// let's just reset the dynamic validator
-	if closest.Height() != c.LastHeight() {
-		c.cert = NewDynamic(c.ChainID(), closest.Validators, closest.Height())
-	}
-	return nil
-}
-
-// updateToHash gets the validator hash we want to update to
-// if IsTooMuchChangeErr, we try to find a path by binary search over height
-func (c *Inquiring) updateToHash(vhash []byte) error {
-	// try to get the match, and update
-	fc, err := c.Source.GetByHash(vhash)
-	if err != nil {
-		return err
-	}
-	err = c.cert.Update(fc)
-	// handle IsTooMuchChangeErr by using divide and conquer
-	if certerr.IsTooMuchChangeErr(err) {
-		err = c.updateToHeight(fc.Height())
-	}
-	return err
-}
-
-// updateToHeight will use divide-and-conquer to find a path to h
-func (c *Inquiring) updateToHeight(h int) error {
-	// try to update to this height (with checks)
-	fc, err := c.Source.GetByHeight(h)
-	if err != nil {
-		return err
-	}
-	start, end := c.LastHeight(), fc.Height()
-	if end <= start {
-		return certerr.ErrNoPathFound()
-	}
-	err = c.Update(fc)
-
-	// we can handle IsTooMuchChangeErr specially
-	if !certerr.IsTooMuchChangeErr(err) {
-		return err
-	}
-
-	// try to update to mid
-	mid := (start + end) / 2
-	err = c.updateToHeight(mid)
-	if err != nil {
-		return err
-	}
-
-	// if we made it to mid, we recurse
-	return c.updateToHeight(h)
-}

certifiers/memprovider.go

@@ -1,78 +0,0 @@
-package certifiers
-
-import (
-	"encoding/hex"
-	"sort"
-
-	certerr "github.com/tendermint/tendermint/certifiers/errors"
-)
-
-type memStoreProvider struct {
-	// byHeight is always sorted by Height... need to support range search (nil, h]
-	// btree would be more efficient for larger sets
-	byHeight fullCommits
-	byHash   map[string]FullCommit
-}
-
-// fullCommits just exists to allow easy sorting
-type fullCommits []FullCommit
-
-func (s fullCommits) Len() int      { return len(s) }
-func (s fullCommits) Swap(i, j int) { s[i], s[j] = s[j], s[i] }
-func (s fullCommits) Less(i, j int) bool {
-	return s[i].Height() < s[j].Height()
-}
-
-func NewMemStoreProvider() Provider {
-	return &memStoreProvider{
-		byHeight: fullCommits{},
-		byHash:   map[string]FullCommit{},
-	}
-}
-
-func (m *memStoreProvider) encodeHash(hash []byte) string {
-	return hex.EncodeToString(hash)
-}
-
-func (m *memStoreProvider) StoreCommit(fc FullCommit) error {
-	// make sure the fc is self-consistent before saving
-	err := fc.ValidateBasic(fc.Commit.Header.ChainID)
-	if err != nil {
-		return err
-	}
-
-	// store the valid fc
-	key := m.encodeHash(fc.ValidatorsHash())
-	m.byHash[key] = fc
-	m.byHeight = append(m.byHeight, fc)
-	sort.Sort(m.byHeight)
-	return nil
-}
-
-func (m *memStoreProvider) GetByHeight(h int) (FullCommit, error) {
-	// search from highest to lowest
-	for i := len(m.byHeight) - 1; i >= 0; i-- {
-		fc := m.byHeight[i]
-		if fc.Height() <= h {
-			return fc, nil
-		}
-	}
-	return FullCommit{}, certerr.ErrCommitNotFound()
-}
-
-func (m *memStoreProvider) GetByHash(hash []byte) (FullCommit, error) {
-	var err error
-	fc, ok := m.byHash[m.encodeHash(hash)]
-	if !ok {
-		err = certerr.ErrCommitNotFound()
-	}
-	return fc, err
-}
-
-func (m *memStoreProvider) LatestCommit() (FullCommit, error) {
-	l := len(m.byHeight)
-	if l == 0 {
-		return FullCommit{}, certerr.ErrCommitNotFound()
-	}
-	return m.byHeight[l-1], nil
-}

certifiers/performance_test.go

@@ -1,116 +0,0 @@
-package certifiers_test
-
-import (
-	"fmt"
-	"testing"
-
-	"github.com/tendermint/tendermint/certifiers"
-)
-
-func BenchmarkGenCommit20(b *testing.B) {
-	keys := certifiers.GenValKeys(20)
-	benchmarkGenCommit(b, keys)
-}
-
-func BenchmarkGenCommit100(b *testing.B) {
-	keys := certifiers.GenValKeys(100)
-	benchmarkGenCommit(b, keys)
-}
-
-func BenchmarkGenCommitSec20(b *testing.B) {
-	keys := certifiers.GenSecpValKeys(20)
-	benchmarkGenCommit(b, keys)
-}
-
-func BenchmarkGenCommitSec100(b *testing.B) {
-	keys := certifiers.GenSecpValKeys(100)
-	benchmarkGenCommit(b, keys)
-}
-
-func benchmarkGenCommit(b *testing.B, keys certifiers.ValKeys) {
-	chainID := fmt.Sprintf("bench-%d", len(keys))
-	vals := keys.ToValidators(20, 10)
-	for i := 0; i < b.N; i++ {
-		h := 1 + i
-		appHash := []byte(fmt.Sprintf("h=%d", h))
-		keys.GenCommit(chainID, h, nil, vals, appHash, 0, len(keys))
-	}
-}
-
-// this benchmarks generating one key
-func BenchmarkGenValKeys(b *testing.B) {
-	keys := certifiers.GenValKeys(20)
-	for i := 0; i < b.N; i++ {
-		keys = keys.Extend(1)
-	}
-}
-
-// this benchmarks generating one key
-func BenchmarkGenSecpValKeys(b *testing.B) {
-	keys := certifiers.GenSecpValKeys(20)
-	for i := 0; i < b.N; i++ {
-		keys = keys.Extend(1)
-	}
-}
-
-func BenchmarkToValidators20(b *testing.B) {
-	benchmarkToValidators(b, 20)
-}
-
-func BenchmarkToValidators100(b *testing.B) {
-	benchmarkToValidators(b, 100)
-}
-
-// this benchmarks constructing the validator set (.PubKey() * nodes)
-func benchmarkToValidators(b *testing.B, nodes int) {
-	keys := certifiers.GenValKeys(nodes)
-	for i := 1; i <= b.N; i++ {
-		keys.ToValidators(int64(2*i), int64(i))
-	}
-}
-
-func BenchmarkToValidatorsSec100(b *testing.B) {
-	benchmarkToValidatorsSec(b, 100)
-}
-
-// this benchmarks constructing the validator set (.PubKey() * nodes)
-func benchmarkToValidatorsSec(b *testing.B, nodes int) {
-	keys := certifiers.GenSecpValKeys(nodes)
-	for i := 1; i <= b.N; i++ {
-		keys.ToValidators(int64(2*i), int64(i))
-	}
-}
-
-func BenchmarkCertifyCommit20(b *testing.B) {
-	keys := certifiers.GenValKeys(20)
-	benchmarkCertifyCommit(b, keys)
-}
-
-func BenchmarkCertifyCommit100(b *testing.B) {
-	keys := certifiers.GenValKeys(100)
-	benchmarkCertifyCommit(b, keys)
-}
-
-func BenchmarkCertifyCommitSec20(b *testing.B) {
-	keys := certifiers.GenSecpValKeys(20)
-	benchmarkCertifyCommit(b, keys)
-}
-
-func BenchmarkCertifyCommitSec100(b *testing.B) {
-	keys := certifiers.GenSecpValKeys(100)
-	benchmarkCertifyCommit(b, keys)
-}
-
-func benchmarkCertifyCommit(b *testing.B, keys certifiers.ValKeys) {
-	chainID := "bench-certify"
-	vals := keys.ToValidators(20, 10)
-	cert := certifiers.NewStatic(chainID, vals)
-	check := keys.GenCommit(chainID, 123, nil, vals, []byte("foo"), 0, len(keys))
-	for i := 0; i < b.N; i++ {
-		err := cert.Certify(check)
-		if err != nil {
-			panic(err)
-		}
-	}
-
-}

certifiers/static.go

@@ -1,66 +0,0 @@
-package certifiers
-
-import (
-	"bytes"
-
-	"github.com/pkg/errors"
-
-	"github.com/tendermint/tendermint/types"
-
-	certerr "github.com/tendermint/tendermint/certifiers/errors"
-)
-
-var _ Certifier = &Static{}
-
-// Static assumes a static set of validators, set on
-// initilization and checks against them.
-// The signatures on every header is checked for > 2/3 votes
-// against the known validator set upon Certify
-//
-// Good for testing or really simple chains.  Building block
-// to support real-world functionality.
-type Static struct {
-	chainID string
-	vSet    *types.ValidatorSet
-	vhash   []byte
-}
-
-func NewStatic(chainID string, vals *types.ValidatorSet) *Static {
-	return &Static{
-		chainID: chainID,
-		vSet:    vals,
-	}
-}
-
-func (c *Static) ChainID() string {
-	return c.chainID
-}
-
-func (c *Static) Validators() *types.ValidatorSet {
-	return c.vSet
-}
-
-func (c *Static) Hash() []byte {
-	if len(c.vhash) == 0 {
-		c.vhash = c.vSet.Hash()
-	}
-	return c.vhash
-}
-
-func (c *Static) Certify(commit Commit) error {
-	// do basic sanity checks
-	err := commit.ValidateBasic(c.chainID)
-	if err != nil {
-		return err
-	}
-
-	// make sure it has the same validator set we have (static means static)
-	if !bytes.Equal(c.Hash(), commit.Header.ValidatorsHash) {
-		return certerr.ErrValidatorsChanged()
-	}
-
-	// then make sure we have the proper signatures for this
-	err = c.vSet.VerifyCommit(c.chainID, commit.Commit.BlockID,
-		commit.Header.Height, commit.Commit)
-	return errors.WithStack(err)
-}

circle.yml

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

cmd/priv_val_server/main.go

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

cmd/tendermint/commands/gen_node_key.go

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

cmd/tendermint/commands/gen_validator.go

@@ -1,12 +1,11 @@
 package commands
 
 import (
-	"encoding/json"
 	"fmt"
 
 	"github.com/spf13/cobra"
 
-	"github.com/tendermint/tendermint/types"
+	pvm "github.com/tendermint/tendermint/types/priv_validator"
 )
 
 // GenValidatorCmd allows the generation of a keypair for a
@@ -18,8 +17,11 @@ var GenValidatorCmd = &cobra.Command{
 }
 
 func genValidator(cmd *cobra.Command, args []string) {
-	privValidator := types.GenPrivValidatorFS("")
-	privValidatorJSONBytes, _ := json.MarshalIndent(privValidator, "", "\t")
+	pv := pvm.GenFilePV("")
+	jsbz, err := cdc.MarshalJSON(pv)
+	if err != nil {
+		panic(err)
+	}
 	fmt.Printf(`%v
-`, string(privValidatorJSONBytes))
+`, string(jsbz))
 }

cmd/tendermint/commands/init.go

@@ -1,11 +1,12 @@
 package commands
 
 import (
-	"os"
-
 	"github.com/spf13/cobra"
 
+	cfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tendermint/p2p"
 	"github.com/tendermint/tendermint/types"
+	pvm "github.com/tendermint/tendermint/types/priv_validator"
 	cmn "github.com/tendermint/tmlibs/common"
 )
 
@@ -13,31 +14,54 @@ 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{types.GenesisValidator{
-				PubKey: privValidator.GetPubKey(),
-				Power:  10,
-			}}
-
-			genDoc.SaveAs(genFile)
-		}
-
-		logger.Info("Initialized tendermint", "genesis", config.GenesisFile(), "priv_validator", config.PrivValidatorFile())
+	var pv *pvm.FilePV
+	if cmn.FileExists(privValFile) {
+		pv = pvm.LoadFilePV(privValFile)
+		logger.Info("Found private validator", "path", privValFile)
 	} else {
-		logger.Info("Already initialized", "priv_validator", config.PrivValidatorFile())
+		pv = pvm.GenFilePV(privValFile)
+		pv.Save()
+		logger.Info("Generated private validator", "path", privValFile)
 	}
+
+	nodeKeyFile := config.NodeKeyFile()
+	if cmn.FileExists(nodeKeyFile) {
+		logger.Info("Found node key", "path", nodeKeyFile)
+	} else {
+		if _, err := p2p.LoadOrGenNodeKey(nodeKeyFile); err != nil {
+			return err
+		}
+		logger.Info("Generated node key", "path", nodeKeyFile)
+	}
+
+	// genesis file
+	genFile := config.GenesisFile()
+	if cmn.FileExists(genFile) {
+		logger.Info("Found genesis file", "path", genFile)
+	} else {
+		genDoc := types.GenesisDoc{
+			ChainID: cmn.Fmt("test-chain-%v", cmn.RandStr(6)),
+		}
+		genDoc.Validators = []types.GenesisValidator{{
+			PubKey: pv.GetPubKey(),
+			Power:  10,
+		}}
+
+		if err := genDoc.SaveAs(genFile); err != nil {
+			return err
+		}
+		logger.Info("Generated genesis file", "path", genFile)
+	}
+
+	return nil
 }

cmd/tendermint/commands/lite.go

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

cmd/tendermint/commands/probe_upnp.go

@@ -1,7 +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"
+	pvm "github.com/tendermint/tendermint/types/priv_validator"
 	"github.com/tendermint/tmlibs/log"
 )
 
@@ -25,10 +25,13 @@ var ResetPrivValidatorCmd = &cobra.Command{
 }
 
 // ResetAll removes the privValidator files.
-// Exported so other CLI tools can use  it
+// Exported so other CLI tools can use it.
 func ResetAll(dbDir, privValFile string, logger log.Logger) {
-	resetPrivValidatorFS(privValFile, logger)
-	os.RemoveAll(dbDir)
+	resetFilePV(privValFile, logger)
+	if err := os.RemoveAll(dbDir); err != nil {
+		logger.Error("Error removing directory", "err", err)
+		return
+	}
 	logger.Info("Removed all data", "dir", dbDir)
 }
 
@@ -41,18 +44,18 @@ func resetAll(cmd *cobra.Command, args []string) {
 // 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) {
+func resetFilePV(privValFile string, logger log.Logger) {
 	// Get PrivValidator
 	if _, err := os.Stat(privValFile); err == nil {
-		privValidator := types.LoadPrivValidatorFS(privValFile)
-		privValidator.Reset()
+		pv := pvm.LoadFilePV(privValFile)
+		pv.Reset()
 		logger.Info("Reset PrivValidator", "file", privValFile)
 	} else {
-		privValidator := types.GenPrivValidatorFS(privValFile)
-		privValidator.Save()
+		pv := pvm.GenFilePV(privValFile)
+		pv.Save()
 		logger.Info("Generated PrivValidator", "file", privValFile)
 	}
 }

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 (
@@ -22,84 +26,151 @@ 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 {
-	os.Unsetenv("TMHOME")
-	os.Unsetenv("TM_HOME")
-	os.Unsetenv("TMROOT")
-	os.Unsetenv("TM_ROOT")
+// clearConfig clears env vars, the given root dir, and resets viper.
+func clearConfig(dir string) {
+	if err := os.Unsetenv("TMHOME"); err != nil {
+		panic(err)
+	}
+	if err := os.Unsetenv("TM_HOME"); err != nil {
+		panic(err)
+	}
 
+	if err := os.RemoveAll(dir); err != nil {
+		panic(err)
+	}
 	viper.Reset()
 	config = cfg.DefaultConfig()
-	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{"TMROOT": 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",
@@ -49,11 +55,10 @@ func NewRunNodeCmd(nodeProvider nm.NodeProvider) *cobra.Command {
 				return fmt.Errorf("Failed to create node: %v", err)
 			}
 
-			if _, err := n.Start(); err != nil {
+			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"
+	privval "github.com/tendermint/tendermint/types/priv_validator"
 )
 
 // 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 +2,103 @@ 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/types"
+	pvm "github.com/tendermint/tendermint/types/priv_validator"
 	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@node0:46656, ID1@node1:46656, ...)")
+	TestnetFilesCmd.Flags().StringVar(&startingIPAddress, "starting-ip-address", "",
+		"Starting IP address (192.168.0.1 results in persistent peers list ID0@192.168.0.1:46656, ID1@192.168.0.2:46656, ...)")
+	TestnetFilesCmd.Flags().IntVar(&p2pPort, "p2p-port", 46656,
+		"P2P Port")
 }
 
-// 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,
+	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 := pvm.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(),
@@ -61,32 +107,65 @@ func testnetFiles(cmd *cobra.Command, args []string) {
 	}
 
 	// Write genesis file.
-	for i := 0; i < nValidators; i++ {
-		mach := cmn.Fmt("mach%d", i)
-		genDoc.SaveAs(path.Join(dataDir, mach, "genesis.json"))
+	for i := 0; i < nValidators+nNonValidators; i++ {
+		nodeDir := filepath.Join(outputDir, cmn.Fmt("%s%d", nodeDirPrefix, i))
+		if err := genDoc.SaveAs(filepath.Join(nodeDir, config.BaseConfig.Genesis)); err != nil {
+			_ = os.RemoveAll(outputDir)
+			return err
+		}
 	}
 
-	fmt.Println(cmn.Fmt("Successfully initialized %v node directories", nValidators))
-}
-
-// Initialize per-machine core directory
-func initMachCoreDirectory(base, mach string) error {
-	dir := path.Join(base, mach)
-	err := cmn.EnsureDir(dir, 0777)
-	if err != nil {
-		return err
+	if populatePersistentPeers {
+		err := populatePersistentPeersInConfigAndWriteIt(config)
+		if err != nil {
+			_ = os.RemoveAll(outputDir)
+			return err
+		}
 	}
 
-	// Create priv_validator.json file if not present
-	ensurePrivValidator(path.Join(dir, "priv_validator.json"))
+	fmt.Printf("Successfully initialized %v node directories\n", nValidators+nNonValidators)
 	return nil
-
 }
 
-func ensurePrivValidator(file string) {
-	if cmn.FileExists(file) {
-		return
+func hostnameOrIP(i int) string {
+	if startingIPAddress != "" {
+		ip := net.ParseIP(startingIPAddress)
+		ip = ip.To4()
+		if ip == nil {
+			fmt.Printf("%v: non ipv4 address\n", startingIPAddress)
+			os.Exit(1)
+		}
+
+		for j := 0; j < i; j++ {
+			ip[3]++
+		}
+		return ip.String()
 	}
-	privValidator := types.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
+
+		// 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 (
+	amino "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:
@@ -36,6 +41,8 @@ func main() {
 	// Create & start node
 	rootCmd.AddCommand(cmd.NewRunNodeCmd(nodeFunc))
 
-	cmd := cli.PrepareBaseCmd(rootCmd, "TM", os.ExpandEnv("$HOME/.tendermint"))
-	cmd.Execute()
+	cmd := cli.PrepareBaseCmd(rootCmd, "TM", os.ExpandEnv(filepath.Join("$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 +2,36 @@ package config
 
 import (
 	"fmt"
+	"os"
 	"path/filepath"
 	"time"
 )
 
+// NOTE: Most of the structs & relevant comments + the
+// default configuration options were used to manually
+// generate the config.toml. Please reflect any changes
+// made here in the defaultConfigTemplate constant in
+// config/toml.go
+// NOTE: tmlibs/cli must know to look in the config dir!
+var (
+	DefaultTendermintDir = ".tendermint"
+	defaultConfigDir     = "config"
+	defaultDataDir       = "data"
+
+	defaultConfigFileName  = "config.toml"
+	defaultGenesisJSONName = "genesis.json"
+
+	defaultPrivValName  = "priv_validator.json"
+	defaultNodeKeyName  = "node_key.json"
+	defaultAddrBookName = "addrbook.json"
+
+	defaultConfigFilePath  = filepath.Join(defaultConfigDir, defaultConfigFileName)
+	defaultGenesisJSONPath = filepath.Join(defaultConfigDir, defaultGenesisJSONName)
+	defaultPrivValPath     = filepath.Join(defaultConfigDir, defaultPrivValName)
+	defaultNodeKeyPath     = filepath.Join(defaultConfigDir, defaultNodeKeyName)
+	defaultAddrBookPath    = filepath.Join(defaultConfigDir, defaultAddrBookName)
+)
+
 // Config defines the top level configuration for a Tendermint node
 type Config struct {
 	// Top level options use an anonymous struct
@@ -16,6 +42,7 @@ type Config struct {
 	P2P       *P2PConfig       `mapstructure:"p2p"`
 	Mempool   *MempoolConfig   `mapstructure:"mempool"`
 	Consensus *ConsensusConfig `mapstructure:"consensus"`
+	TxIndex   *TxIndexConfig   `mapstructure:"tx_index"`
 }
 
 // DefaultConfig returns a default configuration for a Tendermint node
@@ -26,6 +53,7 @@ func DefaultConfig() *Config {
 		P2P:        DefaultP2PConfig(),
 		Mempool:    DefaultMempoolConfig(),
 		Consensus:  DefaultConsensusConfig(),
+		TxIndex:    DefaultTxIndexConfig(),
 	}
 }
 
@@ -35,8 +63,9 @@ func TestConfig() *Config {
 		BaseConfig: TestBaseConfig(),
 		RPC:        TestRPCConfig(),
 		P2P:        TestP2PConfig(),
-		Mempool:    DefaultMempoolConfig(),
+		Mempool:    TestMempoolConfig(),
 		Consensus:  TestConsensusConfig(),
+		TxIndex:    TestTxIndexConfig(),
 	}
 }
 
@@ -55,22 +84,30 @@ 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"`
@@ -93,9 +130,6 @@ type BaseConfig struct {
 	// so the app can decide if we should keep the connection or not
 	FilterPeers bool `mapstructure:"filter_peers"` // false
 
-	// What indexer to use for transactions
-	TxIndex string `mapstructure:"tx_index"`
-
 	// Database backend: leveldb | memdb
 	DBBackend string `mapstructure:"db_backend"`
 
@@ -106,16 +140,16 @@ 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",
+		Genesis:           defaultGenesisJSONPath,
+		PrivValidator:     defaultPrivValPath,
+		NodeKey:           defaultNodeKeyPath,
+		Moniker:           defaultMoniker,
 		ProxyApp:          "tcp://127.0.0.1:46658",
 		ABCI:              "socket",
 		LogLevel:          DefaultPackageLogLevels(),
 		ProfListenAddress: "",
 		FastSync:          true,
 		FilterPeers:       false,
-		TxIndex:           "kv",
 		DBBackend:         "leveldb",
 		DBPath:            "data",
 	}
@@ -123,27 +157,36 @@ 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"
@@ -151,9 +194,10 @@ 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())
 }
 
 //-----------------------------------------------------------------------------
@@ -170,7 +214,7 @@ 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"`
 }
 
@@ -185,11 +229,11 @@ 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
 }
 
 //-----------------------------------------------------------------------------
@@ -203,8 +247,13 @@ 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"`
 
@@ -214,9 +263,6 @@ 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"`
 
@@ -224,40 +270,59 @@ 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"`
+
+	// Authenticated encryption
+	AuthEnc bool `mapstructure:"auth_enc"`
+
+	// Comma separated list of peer IDs to keep private (will not be gossiped to other peers)
+	PrivatePeerIDs string `mapstructure:"private_peer_ids"`
 }
 
 // DefaultP2PConfig returns a default configuration for the peer-to-peer layer
 func DefaultP2PConfig() *P2PConfig {
 	return &P2PConfig{
 		ListenAddress:           "tcp://0.0.0.0:46656",
-		AddrBook:                "addrbook.json",
+		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,
+		AuthEnc:                 true,
 	}
 }
 
 // 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
+	return cfg
 }
 
-// AddrBookFile returns the full path to the address bool
-func (p *P2PConfig) AddrBookFile() string {
-	return rootify(p.AddrBook, p.RootDir)
+// AddrBookFile returns the full path to the address book
+func (cfg *P2PConfig) AddrBookFile() string {
+	return rootify(cfg.AddrBook, cfg.RootDir)
 }
 
 //-----------------------------------------------------------------------------
@@ -270,6 +335,7 @@ type MempoolConfig struct {
 	RecheckEmpty bool   `mapstructure:"recheck_empty"`
 	Broadcast    bool   `mapstructure:"broadcast"`
 	WalPath      string `mapstructure:"wal_dir"`
+	CacheSize    int    `mapstructure:"cache_size"`
 }
 
 // DefaultMempoolConfig returns a default configuration for the Tendermint mempool
@@ -278,13 +344,21 @@ func DefaultMempoolConfig() *MempoolConfig {
 		Recheck:      true,
 		RecheckEmpty: true,
 		Broadcast:    true,
-		WalPath:      "data/mempool.wal",
+		WalPath:      filepath.Join(defaultDataDir, "mempool.wal"),
+		CacheSize:    100000,
 	}
 }
 
+// TestMempoolConfig returns a configuration for testing the Tendermint mempool
+func TestMempoolConfig() *MempoolConfig {
+	cfg := DefaultMempoolConfig()
+	cfg.CacheSize = 1000
+	return cfg
+}
+
 // WalDir returns the full path to the mempool's write-ahead log
-func (m *MempoolConfig) WalDir() string {
-	return rootify(m.WalPath, m.RootDir)
+func (cfg *MempoolConfig) WalDir() string {
+	return rootify(cfg.WalPath, cfg.RootDir)
 }
 
 //-----------------------------------------------------------------------------
@@ -298,7 +372,7 @@ type ConsensusConfig struct {
 	WalLight bool   `mapstructure:"wal_light"`
 	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"`
@@ -318,11 +392,49 @@ 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"),
+		WalLight:                    false,
+		TimeoutPropose:              3000,
+		TimeoutProposeDelta:         500,
+		TimeoutPrevote:              1000,
+		TimeoutPrevoteDelta:         500,
+		TimeoutPrecommit:            1000,
+		TimeoutPrecommitDelta:       500,
+		TimeoutCommit:               1000,
+		SkipTimeoutCommit:           false,
+		MaxBlockSizeTxs:             10000,
+		MaxBlockSizeBytes:           1, // TODO
+		CreateEmptyBlocks:           true,
+		CreateEmptyBlocksInterval:   0,
+		PeerGossipSleepDuration:     100,
+		PeerQueryMaj23SleepDuration: 2000,
+	}
+}
+
+// TestConsensusConfig returns a configuration for testing the consensus service
+func TestConsensusConfig() *ConsensusConfig {
+	cfg := DefaultConsensusConfig()
+	cfg.TimeoutPropose = 100
+	cfg.TimeoutProposeDelta = 1
+	cfg.TimeoutPrevote = 10
+	cfg.TimeoutPrevoteDelta = 1
+	cfg.TimeoutPrecommit = 10
+	cfg.TimeoutPrecommitDelta = 1
+	cfg.TimeoutCommit = 10
+	cfg.SkipTimeoutCommit = true
+	cfg.PeerGossipSleepDuration = 5
+	cfg.PeerQueryMaj23SleepDuration = 250
+	return cfg
+}
+
 // WaitForTxs returns true if the consensus should wait for transactions before entering the propose step
 func (cfg *ConsensusConfig) WaitForTxs() bool {
 	return !cfg.CreateEmptyBlocks || cfg.CreateEmptyBlocksInterval > 0
@@ -363,53 +475,57 @@ 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
+}
+
+//-----------------------------------------------------------------------------
+// TxIndexConfig
+
+// TxIndexConfig defines the confuguration for the transaction
+// indexer, including tags to index.
+type TxIndexConfig struct {
+	// What indexer to use for transactions
+	//
+	// Options:
+	//   1) "null" (default)
+	//   2) "kv" - the simplest possible indexer, backed by key-value storage (defaults to levelDB; see DBBackend).
+	Indexer string `mapstructure:"indexer"`
+
+	// Comma-separated list of tags to index (by default the only tag is tx hash)
+	//
+	// It's recommended to index only a subset of tags due to possible memory
+	// bloat. This is, of course, depends on the indexer's DB and the volume of
+	// transactions.
+	IndexTags string `mapstructure:"index_tags"`
+
+	// When set to true, tells indexer to index all tags. Note this may be not
+	// desirable (see the comment above). IndexTags has a precedence over
+	// IndexAllTags (i.e. when given both, IndexTags will be indexed).
+	IndexAllTags bool `mapstructure:"index_all_tags"`
+}
+
+// DefaultTxIndexConfig returns a default configuration for the transaction indexer.
+func DefaultTxIndexConfig() *TxIndexConfig {
+	return &TxIndexConfig{
+		Indexer:      "kv",
+		IndexTags:    "",
+		IndexAllTags: false,
+	}
+}
+
+// TestTxIndexConfig returns a default configuration for the transaction indexer.
+func TestTxIndexConfig() *TxIndexConfig {
+	return DefaultTxIndexConfig()
 }
 
 //-----------------------------------------------------------------------------
@@ -422,3 +538,18 @@ 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

@@ -1,50 +1,236 @@
 package config
 
 import (
+	"bytes"
 	"os"
-	"path"
 	"path/filepath"
-	"strings"
+	"text/template"
 
 	cmn "github.com/tendermint/tmlibs/common"
 )
 
-/****** these are for production settings ***********/
+var configTemplate *template.Template
 
-func EnsureRoot(rootDir string) {
-	cmn.EnsureDir(rootDir, 0700)
-	cmn.EnsureDir(rootDir+"/data", 0700)
-
-	configFilePath := path.Join(rootDir, "config.toml")
-
-	// 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)
+func init() {
+	var err error
+	if configTemplate, err = template.New("configFileTemplate").Parse(defaultConfigTemplate); err != nil {
+		panic(err)
 	}
 }
 
-var defaultConfigTmpl = `# This is a TOML config file.
+/****** these are for production settings ***********/
+
+// EnsureRoot creates the root, config, and data directories if they don't exist,
+// and panics if it fails.
+func EnsureRoot(rootDir string) {
+	if err := cmn.EnsureDir(rootDir, 0700); err != nil {
+		cmn.PanicSanity(err.Error())
+	}
+	if err := cmn.EnsureDir(filepath.Join(rootDir, defaultConfigDir), 0700); err != nil {
+		cmn.PanicSanity(err.Error())
+	}
+	if err := cmn.EnsureDir(filepath.Join(rootDir, defaultDataDir), 0700); err != nil {
+		cmn.PanicSanity(err.Error())
+	}
+
+	configFilePath := filepath.Join(rootDir, defaultConfigFilePath)
+
+	// Write default config file if missing.
+	if !cmn.FileExists(configFilePath) {
+		writeDefaultCondigFile(configFilePath)
+	}
+}
+
+// XXX: this func should probably be called by cmd/tendermint/commands/init.go
+// alongside the writing of the genesis.json and priv_validator.json
+func writeDefaultCondigFile(configFilePath string) {
+	WriteConfigFile(configFilePath, DefaultConfig())
+}
+
+// WriteConfigFile renders config using the template and writes it to configFilePath.
+func WriteConfigFile(configFilePath string, config *Config) {
+	var buffer bytes.Buffer
+
+	if err := configTemplate.Execute(&buffer, config); err != nil {
+		panic(err)
+	}
+
+	cmn.MustWriteFile(configFilePath, buffer.Bytes(), 0644)
+}
+
+// Note: any changes to the comments/variables/mapstructure
+// must be reflected in the appropriate struct in config/config.go
+const defaultConfigTemplate = `# This is a TOML config file.
 # For more information, see https://github.com/toml-lang/toml
 
-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 = "{{ .BaseConfig.DBPath }}"
+
+# Output level for logging, including package level options
+log_level = "{{ .BaseConfig.LogLevel }}"
+
+##### additional base config options #####
+
+# Path to the JSON file containing the initial validator set and other meta data
+genesis_file = "{{ .BaseConfig.Genesis }}"
+
+# Path to the JSON file containing the private key to use as a validator in the consensus protocol
+priv_validator_file = "{{ .BaseConfig.PrivValidator }}"
+
+# Path to the JSON file containing the private key to use for node authentication in the p2p protocol
+node_key_file = "{{ .BaseConfig.NodeKey}}"
+
+# Mechanism to connect to the ABCI application: socket | grpc
+abci = "{{ .BaseConfig.ABCI }}"
+
+# TCP or UNIX socket address for the profiling server to listen on
+prof_laddr = "{{ .BaseConfig.ProfListenAddress }}"
+
+# If true, query the ABCI app on connecting to a new peer
+# so the app can decide if we should keep the connection or not
+filter_peers = {{ .BaseConfig.FilterPeers }}
+
+##### advanced configuration options #####
+
+##### rpc server configuration options #####
 [rpc]
-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 = "{{ .P2P.AddrBook }}"
+
+# Set true for strict address routability rules
+addr_book_strict = {{ .P2P.AddrBookStrict }}
+
+# Time to wait before flushing messages out on the connection, in ms
+flush_throttle_timeout = {{ .P2P.FlushThrottleTimeout }}
+
+# Maximum number of peers to connect to
+max_num_peers = {{ .P2P.MaxNumPeers }}
+
+# Maximum size of a message packet payload, in bytes
+max_packet_msg_payload_size = {{ .P2P.MaxPacketMsgPayloadSize }}
+
+# Rate at which packets can be sent, in bytes/second
+send_rate = {{ .P2P.SendRate }}
+
+# Rate at which packets can be received, in bytes/second
+recv_rate = {{ .P2P.RecvRate }}
+
+# Set true to enable the peer-exchange reactor
+pex = {{ .P2P.PexReactor }}
+
+# Seed mode, in which node constantly crawls the network and looks for
+# peers. If another node asks it for addresses, it responds and disconnects.
+#
+# Does not work if the peer-exchange reactor is disabled.
+seed_mode = {{ .P2P.SeedMode }}
+
+# Authenticated encryption
+auth_enc = {{ .P2P.AuthEnc }}
+
+# Comma separated list of peer IDs to keep private (will not be gossiped to other peers)
+private_peer_ids = "{{ .P2P.PrivatePeerIDs }}"
+
+##### mempool configuration options #####
+[mempool]
+
+recheck = {{ .Mempool.Recheck }}
+recheck_empty = {{ .Mempool.RecheckEmpty }}
+broadcast = {{ .Mempool.Broadcast }}
+wal_dir = "{{ .Mempool.WalPath }}"
+
+##### consensus configuration options #####
+[consensus]
+
+wal_file = "{{ .Consensus.WalPath }}"
+wal_light = {{ .Consensus.WalLight }}
+
+# All timeouts are in milliseconds
+timeout_propose = {{ .Consensus.TimeoutPropose }}
+timeout_propose_delta = {{ .Consensus.TimeoutProposeDelta }}
+timeout_prevote = {{ .Consensus.TimeoutPrevote }}
+timeout_prevote_delta = {{ .Consensus.TimeoutPrevoteDelta }}
+timeout_precommit = {{ .Consensus.TimeoutPrecommit }}
+timeout_precommit_delta = {{ .Consensus.TimeoutPrecommitDelta }}
+timeout_commit = {{ .Consensus.TimeoutCommit }}
+
+# Make progress as soon as we have all the precommits (as if TimeoutCommit = 0)
+skip_timeout_commit = {{ .Consensus.SkipTimeoutCommit }}
+
+# BlockSize
+max_block_size_txs = {{ .Consensus.MaxBlockSizeTxs }}
+max_block_size_bytes = {{ .Consensus.MaxBlockSizeBytes }}
+
+# EmptyBlocks mode and possible interval between empty blocks in seconds
+create_empty_blocks = {{ .Consensus.CreateEmptyBlocks }}
+create_empty_blocks_interval = {{ .Consensus.CreateEmptyBlocksInterval }}
+
+# Reactor sleep duration parameters are in milliseconds
+peer_gossip_sleep_duration = {{ .Consensus.PeerGossipSleepDuration }}
+peer_query_maj23_sleep_duration = {{ .Consensus.PeerQueryMaj23SleepDuration }}
+
+##### transactions indexer configuration options #####
+[tx_index]
+
+# What indexer to use for transactions
+#
+# Options:
+#   1) "null" (default)
+#   2) "kv" - the simplest possible indexer, backed by key-value storage (defaults to levelDB; see DBBackend).
+indexer = "{{ .TxIndex.Indexer }}"
+
+# Comma-separated list of tags to index (by default the only tag is tx hash)
+#
+# It's recommended to index only a subset of tags due to possible memory
+# bloat. This is, of course, depends on the indexer's DB and the volume of
+# transactions.
+index_tags = "{{ .TxIndex.IndexTags }}"
+
+# When set to true, tells indexer to index all tags. Note this may be not
+# desirable (see the comment above). IndexTags has a precedence over
+# IndexAllTags (i.e. when given both, IndexTags will be indexed).
+index_all_tags = {{ .TxIndex.IndexAllTags }}
+`
 
 /****** these are for test settings ***********/
 
@@ -53,30 +239,35 @@ func ResetTestRoot(testName string) *Config {
 	rootDir = filepath.Join(rootDir, testName)
 	// Remove ~/.tendermint_test_bak
 	if cmn.FileExists(rootDir + "_bak") {
-		err := os.RemoveAll(rootDir + "_bak")
-		if err != nil {
+		if err := os.RemoveAll(rootDir + "_bak"); err != nil {
 			cmn.PanicSanity(err.Error())
 		}
 	}
 	// Move ~/.tendermint_test to ~/.tendermint_test_bak
 	if cmn.FileExists(rootDir) {
-		err := os.Rename(rootDir, rootDir+"_bak")
-		if err != nil {
+		if err := os.Rename(rootDir, rootDir+"_bak"); err != nil {
 			cmn.PanicSanity(err.Error())
 		}
 	}
 	// Create new dir
-	cmn.EnsureDir(rootDir, 0700)
-	cmn.EnsureDir(rootDir+"/data", 0700)
+	if err := cmn.EnsureDir(rootDir, 0700); err != nil {
+		cmn.PanicSanity(err.Error())
+	}
+	if err := cmn.EnsureDir(filepath.Join(rootDir, defaultConfigDir), 0700); err != nil {
+		cmn.PanicSanity(err.Error())
+	}
+	if err := cmn.EnsureDir(filepath.Join(rootDir, defaultDataDir), 0700); err != nil {
+		cmn.PanicSanity(err.Error())
+	}
 
-	configFilePath := 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)
+		writeDefaultCondigFile(configFilePath)
 	}
 	if !cmn.FileExists(genesisFilePath) {
 		cmn.MustWriteFile(genesisFilePath, []byte(testGenesis), 0644)
@@ -88,36 +279,14 @@ 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": ""
@@ -127,14 +296,14 @@ 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"
@@ -19,26 +20,29 @@ 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")
 	require.Nil(err)
-	defer os.RemoveAll(tmpDir)
+	defer os.RemoveAll(tmpDir) // nolint: errcheck
 
 	// create root dir
 	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/byzantine_test.go

@@ -1,16 +1,15 @@
 package consensus
 
 import (
+	"context"
 	"sync"
 	"testing"
 	"time"
 
-	crypto "github.com/tendermint/go-crypto"
-	data "github.com/tendermint/go-wire/data"
+	"github.com/stretchr/testify/require"
 	"github.com/tendermint/tendermint/p2p"
 	"github.com/tendermint/tendermint/types"
 	cmn "github.com/tendermint/tmlibs/common"
-	"github.com/tendermint/tmlibs/events"
 )
 
 func init() {
@@ -32,7 +31,9 @@ func TestByzantine(t *testing.T) {
 	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")
@@ -41,7 +42,47 @@ func TestByzantine(t *testing.T) {
 		switches[i].SetLogger(p2pLogger.With("validator", i))
 	}
 
+	eventChans := make([]chan interface{}, N)
 	reactors := make([]p2p.Reactor, N)
+	for i := 0; i < N; i++ {
+		// make first val byzantine
+		if i == 0 {
+			// NOTE: Now, test validators are MockPV, which by default doesn't
+			// do any safety checks.
+			css[i].privValidator.(*types.MockPV).DisableChecks()
+			css[i].decideProposal = func(j int) func(int64, int) {
+				return func(height int64, round int) {
+					byzantineDecideProposalFunc(t, height, round, css[j], switches[j])
+				}
+			}(i)
+			css[i].doPrevote = func(height int64, round int) {}
+		}
+
+		eventBus := types.NewEventBus()
+		eventBus.SetLogger(logger.With("module", "events", "validator", i))
+		err := eventBus.Start()
+		require.NoError(t, err)
+		defer eventBus.Stop()
+
+		eventChans[i] = make(chan interface{}, 1)
+		err = eventBus.Subscribe(context.Background(), testSubscriber, types.EventQueryNewBlock, eventChans[i])
+		require.NoError(t, err)
+
+		conR := NewConsensusReactor(css[i], true) // so we dont start the consensus states
+		conR.SetLogger(logger.With("validator", i))
+		conR.SetEventBus(eventBus)
+
+		var conRI p2p.Reactor // nolint: gotype, gosimple
+		conRI = conR
+
+		// make first val byzantine
+		if i == 0 {
+			conRI = NewByzantineReactor(conR)
+		}
+
+		reactors[i] = conRI
+	}
+
 	defer func() {
 		for _, r := range reactors {
 			if rr, ok := r.(*ByzantineReactor); ok {
@@ -51,40 +92,6 @@ func TestByzantine(t *testing.T) {
 			}
 		}
 	}()
-	eventChans := make([]chan interface{}, N)
-	eventLogger := logger.With("module", "events")
-	for i := 0; i < N; i++ {
-		if i == 0 {
-			css[i].privValidator = NewByzantinePrivValidator(css[i].privValidator)
-			// make byzantine
-			css[i].decideProposal = func(j int) func(int, int) {
-				return func(height, round int) {
-					byzantineDecideProposalFunc(t, height, round, css[j], switches[j])
-				}
-			}(i)
-			css[i].doPrevote = func(height, round int) {}
-		}
-
-		eventSwitch := events.NewEventSwitch()
-		eventSwitch.SetLogger(eventLogger.With("validator", i))
-		_, err := eventSwitch.Start()
-		if err != nil {
-			t.Fatalf("Failed to start switch: %v", err)
-		}
-		eventChans[i] = subscribeToEvent(eventSwitch, "tester", types.EventStringNewBlock(), 1)
-
-		conR := NewConsensusReactor(css[i], true) // so we dont start the consensus states
-		conR.SetLogger(logger.With("validator", i))
-		conR.SetEventSwitch(eventSwitch)
-
-		var conRI p2p.Reactor
-		conRI = conR
-
-		if i == 0 {
-			conRI = NewByzantineReactor(conR)
-		}
-		reactors[i] = conRI
-	}
 
 	p2p.MakeConnectedSwitches(config.P2P, N, func(i int, s *p2p.Switch) *p2p.Switch {
 		// ignore new switch s, we already made ours
@@ -111,19 +118,19 @@ func TestByzantine(t *testing.T) {
 	// 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)
 
@@ -159,7 +166,7 @@ func TestByzantine(t *testing.T) {
 //-------------------------------
 // byzantine consensus functions
 
-func byzantineDecideProposalFunc(t *testing.T, height, round int, cs *ConsensusState, sw *p2p.Switch) {
+func byzantineDecideProposalFunc(t *testing.T, height int64, round int, cs *ConsensusState, sw *p2p.Switch) {
 	// byzantine user should create two proposals and try to split the vote.
 	// Avoid sending on internalMsgQueue and running consensus state.
 
@@ -167,13 +174,17 @@ func byzantineDecideProposalFunc(t *testing.T, height, round int, cs *ConsensusS
 	block1, blockParts1 := cs.createProposalBlock()
 	polRound, polBlockID := cs.Votes.POLInfo()
 	proposal1 := types.NewProposal(height, round, blockParts1.Header(), polRound, polBlockID)
-	cs.privValidator.SignProposal(cs.state.ChainID, proposal1) // byzantine doesnt err
+	if err := cs.privValidator.SignProposal(cs.state.ChainID, proposal1); err != nil {
+		t.Error(err)
+	}
 
 	// Create a new proposal block from state/txs from the mempool.
 	block2, blockParts2 := cs.createProposalBlock()
 	polRound, polBlockID = cs.Votes.POLInfo()
 	proposal2 := types.NewProposal(height, round, blockParts2.Header(), polRound, polBlockID)
-	cs.privValidator.SignProposal(cs.state.ChainID, proposal2) // byzantine doesnt err
+	if err := cs.privValidator.SignProposal(cs.state.ChainID, proposal2); err != nil {
+		t.Error(err)
+	}
 
 	block1Hash := block1.Hash()
 	block2Hash := block2.Hash()
@@ -190,10 +201,10 @@ func byzantineDecideProposalFunc(t *testing.T, height, round int, cs *ConsensusS
 	}
 }
 
-func sendProposalAndParts(height, round int, cs *ConsensusState, peer p2p.Peer, proposal *types.Proposal, blockHash []byte, parts *types.PartSet) {
+func sendProposalAndParts(height int64, round int, cs *ConsensusState, peer p2p.Peer, proposal *types.Proposal, blockHash []byte, parts *types.PartSet) {
 	// proposal
 	msg := &ProposalMessage{Proposal: proposal}
-	peer.Send(DataChannel, struct{ ConsensusMessage }{msg})
+	peer.Send(DataChannel, cdc.MustMarshalBinaryBare(msg))
 
 	// parts
 	for i := 0; i < parts.Total(); i++ {
@@ -203,7 +214,7 @@ func sendProposalAndParts(height, round int, cs *ConsensusState, peer p2p.Peer,
 			Round:  round,  // This tells peer that this part applies to us.
 			Part:   part,
 		}
-		peer.Send(DataChannel, struct{ ConsensusMessage }{msg})
+		peer.Send(DataChannel, cdc.MustMarshalBinaryBare(msg))
 	}
 
 	// votes
@@ -212,8 +223,8 @@ func sendProposalAndParts(height, round int, cs *ConsensusState, peer p2p.Peer,
 	precommit, _ := cs.signVote(types.VoteTypePrecommit, blockHash, parts.Header())
 	cs.mtx.Unlock()
 
-	peer.Send(VoteChannel, struct{ ConsensusMessage }{&VoteMessage{prevote}})
-	peer.Send(VoteChannel, struct{ ConsensusMessage }{&VoteMessage{precommit}})
+	peer.Send(VoteChannel, cdc.MustMarshalBinaryBare(&VoteMessage{prevote}))
+	peer.Send(VoteChannel, cdc.MustMarshalBinaryBare(&VoteMessage{precommit}))
 }
 
 //----------------------------------------
@@ -254,47 +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, err = privVal.Sign(types.SignBytes(chainID, proposal))
-	return nil
-}
-
-func (privVal *ByzantinePrivValidator) SignHeartbeat(chainID string, heartbeat *types.Heartbeat) (err error) {
-	heartbeat.Signature, err = privVal.Sign(types.SignBytes(chainID, heartbeat))
-	return nil
-}
-
-func (privVal *ByzantinePrivValidator) String() string {
-	return cmn.Fmt("PrivValidator{%X}", privVal.GetAddress())
-}

consensus/common.go

@@ -1,35 +0,0 @@
-package consensus
-
-import (
-	"github.com/tendermint/tendermint/types"
-)
-
-// XXX: WARNING: these functions can halt the consensus as firing events is synchronous.
-// Make sure to read off the channels, and in the case of subscribeToEventRespond, to write back on it
-
-// NOTE: if chanCap=0, this blocks on the event being consumed
-func subscribeToEvent(evsw types.EventSwitch, receiver, eventID string, chanCap int) chan interface{} {
-	// listen for event
-	ch := make(chan interface{}, chanCap)
-	types.AddListenerForEvent(evsw, receiver, eventID, func(data types.TMEventData) {
-		ch <- data
-	})
-	return ch
-}
-
-// NOTE: this blocks on receiving a response after the event is consumed
-func subscribeToEventRespond(evsw types.EventSwitch, receiver, eventID string) chan interface{} {
-	// listen for event
-	ch := make(chan interface{})
-	types.AddListenerForEvent(evsw, receiver, eventID, func(data types.TMEventData) {
-		ch <- data
-		<-ch
-	})
-	return ch
-}
-
-func discardFromChan(ch chan interface{}, n int) {
-	for i := 0; i < n; i++ {
-		<-ch
-	}
-}

consensus/common_test.go

@@ -2,6 +2,7 @@ package consensus
 
 import (
 	"bytes"
+	"context"
 	"fmt"
 	"io/ioutil"
 	"os"
@@ -20,19 +21,24 @@ import (
 	"github.com/tendermint/tendermint/p2p"
 	sm "github.com/tendermint/tendermint/state"
 	"github.com/tendermint/tendermint/types"
+	pvm "github.com/tendermint/tendermint/types/priv_validator"
 	cmn "github.com/tendermint/tmlibs/common"
 	dbm "github.com/tendermint/tmlibs/db"
 	"github.com/tendermint/tmlibs/log"
 
 	"github.com/tendermint/abci/example/counter"
-	"github.com/tendermint/abci/example/dummy"
+	"github.com/tendermint/abci/example/kvstore"
 
 	"github.com/go-kit/kit/log/term"
 )
 
+const (
+	testSubscriber = "test-client"
+)
+
 // genesis, chain_id, priv_val
-var config *cfg.Config // NOTE: must be reset for each _test.go file
-var ensureTimeout = time.Second * 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 {
@@ -45,16 +51,16 @@ 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.
-	Height int
+	Height int64
 	Round  int
 	types.PrivValidator
 }
 
-var testMinPower = 10
+var testMinPower int64 = 10
 
 func NewValidatorStub(privValidator types.PrivValidator, valIndex int) *validatorStub {
 	return &validatorStub{
@@ -69,10 +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
 }
 
@@ -95,26 +102,26 @@ func signVotes(voteType byte, hash []byte, header types.PartSetHeader, vss ...*v
 
 func incrementHeight(vss ...*validatorStub) {
 	for _, vs := range vss {
-		vs.Height += 1
+		vs.Height++
 	}
 }
 
 func incrementRound(vss ...*validatorStub) {
 	for _, vs := range vss {
-		vs.Round += 1
+		vs.Round++
 	}
 }
 
 //-------------------------------------------------------------------------------
 // Functions for transitioning the consensus state
 
-func startTestRound(cs *ConsensusState, height, round int) {
+func startTestRound(cs *ConsensusState, height int64, round int) {
 	cs.enterNewRound(height, round)
 	cs.startRoutines(0)
 }
 
 // Create proposal block from cs1 but sign it with vs
-func decideProposal(cs1 *ConsensusState, vs *validatorStub, height, round int) (proposal *types.Proposal, block *types.Block) {
+func decideProposal(cs1 *ConsensusState, vs *validatorStub, height int64, round int) (proposal *types.Proposal, block *types.Block) {
 	block, blockParts := cs1.createProposalBlock()
 	if block == nil { // on error
 		panic("error creating proposal block")
@@ -123,7 +130,7 @@ func decideProposal(cs1 *ConsensusState, vs *validatorStub, height, round int) (
 	// Make proposal
 	polRound, polBlockID := cs1.Votes.POLInfo()
 	proposal = types.NewProposal(height, round, blockParts.Header(), polRound, polBlockID)
-	if err := vs.SignProposal(config.ChainID, proposal); err != nil {
+	if err := vs.SignProposal(cs1.state.ChainID, proposal); err != nil {
 		panic(err)
 	}
 	return
@@ -208,12 +215,15 @@ func validatePrevoteAndPrecommit(t *testing.T, cs *ConsensusState, thisRound, lo
 
 // genesis
 func subscribeToVoter(cs *ConsensusState, addr []byte) chan interface{} {
-	voteCh0 := subscribeToEvent(cs.evsw, "tester", types.EventStringVote(), 1)
+	voteCh0 := make(chan interface{})
+	err := cs.eventBus.Subscribe(context.Background(), testSubscriber, types.EventQueryVote, voteCh0)
+	if err != nil {
+		panic(fmt.Sprintf("failed to subscribe %s to %v", testSubscriber, types.EventQueryVote))
+	}
 	voteCh := make(chan interface{})
 	go func() {
-		for {
-			v := <-voteCh0
-			vote := v.(types.TMEventData).Unwrap().(types.EventDataVote)
+		for v := range voteCh0 {
+			vote := v.(types.EventDataVote)
 			// we only fire for our own votes
 			if bytes.Equal(addr, vote.Vote.ValidatorAddress) {
 				voteCh <- v
@@ -226,13 +236,17 @@ 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 {
-	// Get BlockStore
+func newConsensusStateWithConfig(thisConfig *cfg.Config, state sm.State, pv types.PrivValidator, app abci.Application) *ConsensusState {
 	blockDB := dbm.NewMemDB()
+	return newConsensusStateWithConfigAndBlockStore(thisConfig, state, pv, app, blockDB)
+}
+
+func newConsensusStateWithConfigAndBlockStore(thisConfig *cfg.Config, state sm.State, pv types.PrivValidator, app abci.Application, blockDB dbm.DB) *ConsensusState {
+	// Get BlockStore
 	blockStore := bc.NewBlockStore(blockDB)
 
 	// one for mempool, one for consensus
@@ -247,36 +261,31 @@ func newConsensusStateWithConfig(thisConfig *cfg.Config, state *sm.State, pv typ
 		mempool.EnableTxsAvailable()
 	}
 
+	// mock the evidence pool
+	evpool := types.MockEvidencePool{}
+
 	// Make ConsensusReactor
-	cs := NewConsensusState(thisConfig.Consensus, state, proxyAppConnCon, blockStore, mempool)
-	cs.SetLogger(log.TestingLogger())
+	stateDB := dbm.NewMemDB()
+	blockExec := sm.NewBlockExecutor(stateDB, log.TestingLogger(), proxyAppConnCon, mempool, evpool)
+	cs := NewConsensusState(thisConfig.Consensus, state, blockExec, blockStore, mempool, evpool)
+	cs.SetLogger(log.TestingLogger().With("module", "consensus"))
 	cs.SetPrivValidator(pv)
 
-	evsw := types.NewEventSwitch()
-	evsw.SetLogger(log.TestingLogger().With("module", "events"))
-	cs.SetEventSwitch(evsw)
-	evsw.Start()
+	eventBus := types.NewEventBus()
+	eventBus.SetLogger(log.TestingLogger().With("module", "events"))
+	eventBus.Start()
+	cs.SetEventBus(eventBus)
 	return cs
 }
 
-func loadPrivValidator(config *cfg.Config) *types.PrivValidatorFS {
+func loadPrivValidator(config *cfg.Config) *pvm.FilePV {
 	privValidatorFile := config.PrivValidatorFile()
 	ensureDir(path.Dir(privValidatorFile), 0700)
-	privValidator := types.LoadOrGenPrivValidatorFS(privValidatorFile)
+	privValidator := pvm.LoadOrGenFilePV(privValidatorFile)
 	privValidator.Reset()
 	return privValidator
 }
 
-func fixedConsensusStateDummy() *ConsensusState {
-	stateDB := dbm.NewMemDB()
-	state, _ := sm.MakeGenesisStateFromFile(stateDB, config.GenesisFile())
-	state.SetLogger(log.TestingLogger().With("module", "state"))
-	privValidator := loadPrivValidator(config)
-	cs := newConsensusState(state, privValidator, dummy.NewDummyApplication())
-	cs.SetLogger(log.TestingLogger())
-	return cs
-}
-
 func randConsensusState(nValidators int) (*ConsensusState, []*validatorStub) {
 	// Get State
 	state, privVals := randGenesisState(nValidators, false, 10)
@@ -284,7 +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)
@@ -297,7 +305,7 @@ func randConsensusState(nValidators int) (*ConsensusState, []*validatorStub) {
 
 //-------------------------------------------------------------------------------
 
-func ensureNoNewStep(stepCh chan interface{}) {
+func ensureNoNewStep(stepCh <-chan interface{}) {
 	timer := time.NewTimer(ensureTimeout)
 	select {
 	case <-timer.C:
@@ -307,7 +315,7 @@ func ensureNoNewStep(stepCh chan interface{}) {
 	}
 }
 
-func ensureNewStep(stepCh chan interface{}) {
+func ensureNewStep(stepCh <-chan interface{}) {
 	timer := time.NewTimer(ensureTimeout)
 	select {
 	case <-timer.C:
@@ -330,18 +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)
@@ -352,21 +358,20 @@ 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
 }
 
 // nPeers = nValidators + nNotValidator
 func randConsensusNetWithPeers(nValidators, nPeers int, testName string, tickerFunc func() TimeoutTicker, appFunc func() abci.Application) []*ConsensusState {
-	genDoc, privVals := randGenesisDoc(nValidators, false, int64(testMinPower))
+	genDoc, privVals := randGenesisDoc(nValidators, false, testMinPower)
 	css := make([]*ConsensusState, nPeers)
+	logger := consensusLogger()
 	for i := 0; i < nPeers; i++ {
-		db := dbm.NewMemDB() // each state needs its own db
-		state, _ := sm.MakeGenesisState(db, genDoc)
-		state.SetLogger(log.TestingLogger().With("module", "state"))
-		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
@@ -374,7 +379,7 @@ func randConsensusNetWithPeers(nValidators, nPeers int, testName string, tickerF
 			privVal = privVals[i]
 		} else {
 			_, tempFilePath := cmn.Tempfile("priv_validator_")
-			privVal = types.GenPrivValidatorFS(tempFilePath)
+			privVal = pvm.GenFilePV(tempFilePath)
 		}
 
 		app := appFunc()
@@ -382,15 +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(log.TestingLogger())
 		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
 		}
 	}
@@ -401,9 +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{
@@ -413,19 +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
 }
 
@@ -451,12 +456,12 @@ type mockTicker struct {
 	fired    bool
 }
 
-func (m *mockTicker) Start() (bool, error) {
-	return true, nil
+func (m *mockTicker) Start() error {
+	return nil
 }
 
-func (m *mockTicker) Stop() bool {
-	return true
+func (m *mockTicker) Stop() error {
+	return nil
 }
 
 func (m *mockTicker) ScheduleTimeout(ti timeoutInfo) {
@@ -484,7 +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

@@ -2,46 +2,49 @@ package consensus
 
 import (
 	"encoding/binary"
+	"fmt"
 	"testing"
 	"time"
 
-	abci "github.com/tendermint/abci/types"
-	"github.com/tendermint/tendermint/types"
+	"github.com/stretchr/testify/assert"
 
+	"github.com/tendermint/abci/example/code"
+	abci "github.com/tendermint/abci/types"
 	cmn "github.com/tendermint/tmlibs/common"
+
+	"github.com/tendermint/tendermint/types"
 )
 
 func init() {
 	config = 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)
 	cs := newConsensusStateWithConfig(config, state, privVals[0], NewCounterApplication())
 	cs.mempool.EnableTxsAvailable()
 	height, round := cs.Height, cs.Round
-	newBlockCh := subscribeToEvent(cs.evsw, "tester", types.EventStringNewBlock(), 1)
+	newBlockCh := subscribe(cs.eventBus, types.EventQueryNewBlock)
 	startTestRound(cs, height, round)
 
 	ensureNewStep(newBlockCh) // first block gets committed
 	ensureNoNewStep(newBlockCh)
-	deliverTxsRange(cs, 0, 2)
+	deliverTxsRange(cs, 0, 1)
 	ensureNewStep(newBlockCh) // commit txs
 	ensureNewStep(newBlockCh) // commit updated app hash
 	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)
 	cs := newConsensusStateWithConfig(config, state, privVals[0], NewCounterApplication())
 	cs.mempool.EnableTxsAvailable()
 	height, round := cs.Height, cs.Round
-	newBlockCh := subscribeToEvent(cs.evsw, "tester", types.EventStringNewBlock(), 1)
+	newBlockCh := subscribe(cs.eventBus, types.EventQueryNewBlock)
 	startTestRound(cs, height, round)
 
 	ensureNewStep(newBlockCh)   // first block gets committed
@@ -49,16 +52,16 @@ 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)
 	cs := newConsensusStateWithConfig(config, state, privVals[0], NewCounterApplication())
 	cs.mempool.EnableTxsAvailable()
 	height, round := cs.Height, cs.Round
-	newBlockCh := subscribeToEvent(cs.evsw, "tester", types.EventStringNewBlock(), 1)
-	newRoundCh := subscribeToEvent(cs.evsw, "tester", types.EventStringNewRound(), 1)
-	timeoutCh := subscribeToEvent(cs.evsw, "tester", types.EventStringTimeoutPropose(), 1)
+	newBlockCh := subscribe(cs.eventBus, types.EventQueryNewBlock)
+	newRoundCh := subscribe(cs.eventBus, types.EventQueryNewRound)
+	timeoutCh := subscribe(cs.eventBus, types.EventQueryTimeoutPropose)
 	cs.setProposal = func(proposal *types.Proposal) error {
 		if cs.Height == 2 && cs.Round == 0 {
 			// dont set the proposal in round 0 so we timeout and
@@ -73,7 +76,7 @@ func TestProgressInHigherRound(t *testing.T) {
 	ensureNewStep(newRoundCh) // first round at first height
 	ensureNewStep(newBlockCh) // first block gets committed
 	ensureNewStep(newRoundCh) // first round at next height
-	deliverTxsRange(cs, 0, 2) // we deliver txs, but dont set a proposal so we get the next round
+	deliverTxsRange(cs, 0, 1) // we deliver txs, but dont set a proposal so we get the next round
 	<-timeoutCh
 	ensureNewStep(newRoundCh) // wait for the next round
 	ensureNewStep(newBlockCh) // now we can commit the block
@@ -91,29 +94,29 @@ 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
-	newBlockCh := subscribeToEvent(cs.evsw, "tester", types.EventStringNewBlock(), 1)
+	newBlockCh := subscribe(cs.eventBus, types.EventQueryNewBlock)
 
 	NTxs := 10000
 	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)
@@ -121,41 +124,44 @@ func TestRmBadTx(t *testing.T) {
 	// increment the counter by 1
 	txBytes := make([]byte, 8)
 	binary.BigEndian.PutUint64(txBytes, uint64(0))
-	app.DeliverTx(txBytes)
-	app.Commit()
 
-	ch := make(chan struct{})
-	cbCh := make(chan struct{})
+	resDeliver := app.DeliverTx(txBytes)
+	assert.False(t, resDeliver.IsErr(), cmn.Fmt("expected no error. got %v", resDeliver))
+
+	resCommit := app.Commit()
+	assert.True(t, len(resCommit.Data) > 0)
+
+	emptyMempoolCh := make(chan struct{})
+	checkTxRespCh := make(chan struct{})
 	go func() {
 		// Try to send the tx through the mempool.
 		// CheckTx should not err, but the app should return a bad abci code
 		// and the tx should get removed from the pool
 		err := cs.mempool.CheckTx(txBytes, func(r *abci.Response) {
-			if r.GetCheckTx().Code != abci.CodeType_BadNonce {
+			if r.GetCheckTx().Code != code.CodeTypeBadNonce {
 				t.Fatalf("expected checktx to return bad nonce, got %v", r)
 			}
-			cbCh <- struct{}{}
+			checkTxRespCh <- struct{}{}
 		})
 		if err != nil {
-			t.Fatal("Error after CheckTx: %v", err)
+			t.Fatalf("Error after CheckTx: %v", err)
 		}
 
 		// check for the tx
 		for {
-			time.Sleep(time.Second)
 			txs := cs.mempool.Reap(1)
 			if len(txs) == 0 {
-				ch <- struct{}{}
+				emptyMempoolCh <- struct{}{}
 				return
 			}
-
+			time.Sleep(10 * time.Millisecond)
 		}
 	}()
 
 	// Wait until the tx returns
 	ticker := time.After(time.Second * 5)
 	select {
-	case <-cbCh:
+	case <-checkTxRespCh:
 		// success
 	case <-ticker:
 		t.Fatalf("Timed out waiting for tx to return")
@@ -164,7 +170,7 @@ func TestRmBadTx(t *testing.T) {
 	// Wait until the tx is removed
 	ticker = time.After(time.Second * 5)
 	select {
-	case <-ch:
+	case <-emptyMempoolCh:
 		// success
 	case <-ticker:
 		t.Fatalf("Timed out waiting for tx to be removed")
@@ -187,33 +193,40 @@ func (app *CounterApplication) Info(req abci.RequestInfo) abci.ResponseInfo {
 	return abci.ResponseInfo{Data: cmn.Fmt("txs:%v", app.txCount)}
 }
 
-func (app *CounterApplication) DeliverTx(tx []byte) abci.Result {
-	return runTx(tx, &app.txCount)
+func (app *CounterApplication) DeliverTx(tx []byte) abci.ResponseDeliverTx {
+	txValue := txAsUint64(tx)
+	if txValue != uint64(app.txCount) {
+		return abci.ResponseDeliverTx{
+			Code: code.CodeTypeBadNonce,
+			Log:  fmt.Sprintf("Invalid nonce. Expected %v, got %v", app.txCount, txValue)}
+	}
+	app.txCount++
+	return abci.ResponseDeliverTx{Code: code.CodeTypeOK}
 }
 
-func (app *CounterApplication) CheckTx(tx []byte) abci.Result {
-	return runTx(tx, &app.mempoolTxCount)
+func (app *CounterApplication) CheckTx(tx []byte) abci.ResponseCheckTx {
+	txValue := txAsUint64(tx)
+	if txValue != uint64(app.mempoolTxCount) {
+		return abci.ResponseCheckTx{
+			Code: code.CodeTypeBadNonce,
+			Log:  fmt.Sprintf("Invalid nonce. Expected %v, got %v", app.mempoolTxCount, txValue)}
+	}
+	app.mempoolTxCount++
+	return abci.ResponseCheckTx{Code: code.CodeTypeOK}
 }
 
-func runTx(tx []byte, countPtr *int) abci.Result {
-	count := *countPtr
+func txAsUint64(tx []byte) uint64 {
 	tx8 := make([]byte, 8)
 	copy(tx8[len(tx8)-len(tx):], tx)
-	txValue := binary.BigEndian.Uint64(tx8)
-	if txValue != uint64(count) {
-		return abci.ErrBadNonce.AppendLog(cmn.Fmt("Invalid nonce. Expected %v, got %v", count, txValue))
-	}
-	*countPtr += 1
-	return abci.OK
+	return binary.BigEndian.Uint64(tx8)
 }
 
-func (app *CounterApplication) Commit() abci.Result {
+func (app *CounterApplication) Commit() abci.ResponseCommit {
 	app.mempoolTxCount = app.txCount
 	if app.txCount == 0 {
-		return abci.OK
-	} else {
-		hash := make([]byte, 8)
-		binary.BigEndian.PutUint64(hash, uint64(app.txCount))
-		return abci.NewResultOK(hash, "")
+		return abci.ResponseCommit{}
 	}
+	hash := make([]byte, 8)
+	binary.BigEndian.PutUint64(hash, uint64(app.txCount))
+	return abci.ResponseCommit{Data: hash}
 }

consensus/reactor.go

@@ -1,14 +1,15 @@
 package consensus
 
 import (
-	"bytes"
-	"errors"
+	"context"
 	"fmt"
 	"reflect"
 	"sync"
 	"time"
 
-	wire "github.com/tendermint/go-wire"
+	"github.com/pkg/errors"
+
+	amino "github.com/tendermint/go-amino"
 	cmn "github.com/tendermint/tmlibs/common"
 	"github.com/tendermint/tmlibs/log"
 
@@ -24,7 +25,9 @@ const (
 	VoteChannel        = byte(0x22)
 	VoteSetBitsChannel = byte(0x23)
 
-	maxConsensusMessageSize = 1048576 // 1MB; NOTE/TODO: keep in sync with types.PartSet sizes.
+	maxMsgSize = 1048576 // 1MB; NOTE/TODO: keep in sync with types.PartSet sizes.
+
+	blocksToContributeToBecomeGoodPeer = 10000
 )
 
 //-----------------------------------------------------------------------------
@@ -34,10 +37,10 @@ type ConsensusReactor struct {
 	p2p.BaseReactor // BaseService + p2p.Switch
 
 	conS *ConsensusState
-	evsw types.EventSwitch
 
 	mtx      sync.RWMutex
 	fastSync bool
+	eventBus *types.EventBus
 }
 
 // NewConsensusReactor returns a new ConsensusReactor with the given consensusState.
@@ -53,18 +56,22 @@ func NewConsensusReactor(consensusState *ConsensusState, fastSync bool) *Consens
 // OnStart implements BaseService.
 func (conR *ConsensusReactor) OnStart() error {
 	conR.Logger.Info("ConsensusReactor ", "fastSync", conR.FastSync())
-	conR.BaseReactor.OnStart()
+	if err := conR.BaseReactor.OnStart(); err != nil {
+		return err
+	}
 
-	// callbacks for broadcasting new steps and votes to peers
-	// upon their respective events (ie. uses evsw)
-	conR.registerEventCallbacks()
+	err := conR.startBroadcastRoutine()
+	if err != nil {
+		return err
+	}
 
 	if !conR.FastSync() {
-		_, err := conR.conS.Start()
+		err := conR.conS.Start()
 		if err != nil {
 			return err
 		}
 	}
+
 	return nil
 }
 
@@ -76,7 +83,7 @@ func (conR *ConsensusReactor) OnStop() {
 
 // SwitchToConsensus switches from fast_sync mode to consensus mode.
 // It resets the state, turns off fast_sync, and starts the consensus state-machine
-func (conR *ConsensusReactor) SwitchToConsensus(state *sm.State, blocksSynced int) {
+func (conR *ConsensusReactor) SwitchToConsensus(state sm.State, blocksSynced int) {
 	conR.Logger.Info("SwitchToConsensus")
 	conR.conS.reconstructLastCommit(state)
 	// NOTE: The line below causes broadcastNewRoundStepRoutine() to
@@ -91,35 +98,42 @@ func (conR *ConsensusReactor) SwitchToConsensus(state *sm.State, blocksSynced in
 		// dont bother with the WAL if we fast synced
 		conR.conS.doWALCatchup = false
 	}
-	conR.conS.Start()
+	err := conR.conS.Start()
+	if err != nil {
+		conR.Logger.Error("Error starting conS", "err", err)
+	}
 }
 
 // GetChannels implements Reactor
 func (conR *ConsensusReactor) GetChannels() []*p2p.ChannelDescriptor {
 	// TODO optimize
 	return []*p2p.ChannelDescriptor{
-		&p2p.ChannelDescriptor{
-			ID:                StateChannel,
-			Priority:          5,
-			SendQueueCapacity: 100,
+		{
+			ID:                  StateChannel,
+			Priority:            5,
+			SendQueueCapacity:   100,
+			RecvMessageCapacity: maxMsgSize,
 		},
-		&p2p.ChannelDescriptor{
-			ID:                 DataChannel, // maybe split between gossiping current block and catchup stuff
-			Priority:           10,          // once we gossip the whole block there's nothing left to send until next height or round
-			SendQueueCapacity:  100,
-			RecvBufferCapacity: 50 * 4096,
+		{
+			ID:                  DataChannel, // maybe split between gossiping current block and catchup stuff
+			Priority:            10,          // once we gossip the whole block there's nothing left to send until next height or round
+			SendQueueCapacity:   100,
+			RecvBufferCapacity:  50 * 4096,
+			RecvMessageCapacity: maxMsgSize,
 		},
-		&p2p.ChannelDescriptor{
-			ID:                 VoteChannel,
-			Priority:           5,
-			SendQueueCapacity:  100,
-			RecvBufferCapacity: 100 * 100,
+		{
+			ID:                  VoteChannel,
+			Priority:            5,
+			SendQueueCapacity:   100,
+			RecvBufferCapacity:  100 * 100,
+			RecvMessageCapacity: maxMsgSize,
 		},
-		&p2p.ChannelDescriptor{
-			ID:                 VoteSetBitsChannel,
-			Priority:           1,
-			SendQueueCapacity:  2,
-			RecvBufferCapacity: 1024,
+		{
+			ID:                  VoteSetBitsChannel,
+			Priority:            1,
+			SendQueueCapacity:   2,
+			RecvBufferCapacity:  1024,
+			RecvMessageCapacity: maxMsgSize,
 		},
 	}
 }
@@ -167,10 +181,10 @@ func (conR *ConsensusReactor) Receive(chID byte, src p2p.Peer, msgBytes []byte)
 		return
 	}
 
-	_, msg, err := DecodeMessage(msgBytes)
+	msg, err := DecodeMessage(msgBytes)
 	if err != nil {
 		conR.Logger.Error("Error decoding message", "src", src, "chId", chID, "msg", msg, "err", err, "bytes", msgBytes)
-		// TODO punish peer?
+		conR.Switch.StopPeerForError(src, err)
 		return
 	}
 	conR.Logger.Debug("Receive", "src", src, "chId", chID, "msg", msg)
@@ -196,7 +210,11 @@ func (conR *ConsensusReactor) Receive(chID byte, src p2p.Peer, msgBytes []byte)
 				return
 			}
 			// Peer claims to have a maj23 for some BlockID at H,R,S,
-			votes.SetPeerMaj23(msg.Round, msg.Type, ps.Peer.Key(), msg.BlockID)
+			err := votes.SetPeerMaj23(msg.Round, msg.Type, ps.Peer.ID(), msg.BlockID)
+			if err != nil {
+				conR.Switch.StopPeerForError(src, err)
+				return
+			}
 			// Respond with a VoteSetBitsMessage showing which votes we have.
 			// (and consequently shows which we don't have)
 			var ourVotes *cmn.BitArray
@@ -209,13 +227,13 @@ func (conR *ConsensusReactor) Receive(chID byte, src p2p.Peer, msgBytes []byte)
 				conR.Logger.Error("Bad VoteSetBitsMessage field Type")
 				return
 			}
-			src.TrySend(VoteSetBitsChannel, struct{ ConsensusMessage }{&VoteSetBitsMessage{
+			src.TrySend(VoteSetBitsChannel, cdc.MustMarshalBinaryBare(&VoteSetBitsMessage{
 				Height:  msg.Height,
 				Round:   msg.Round,
 				Type:    msg.Type,
 				BlockID: msg.BlockID,
 				Votes:   ourVotes,
-			}})
+			}))
 		case *ProposalHeartbeatMessage:
 			hb := msg.Heartbeat
 			conR.Logger.Debug("Received proposal heartbeat message",
@@ -233,12 +251,15 @@ func (conR *ConsensusReactor) Receive(chID byte, src p2p.Peer, msgBytes []byte)
 		switch msg := msg.(type) {
 		case *ProposalMessage:
 			ps.SetHasProposal(msg.Proposal)
-			conR.conS.peerMsgQueue <- msgInfo{msg, src.Key()}
+			conR.conS.peerMsgQueue <- msgInfo{msg, src.ID()}
 		case *ProposalPOLMessage:
 			ps.ApplyProposalPOLMessage(msg)
 		case *BlockPartMessage:
 			ps.SetHasProposalBlockPart(msg.Height, msg.Round, msg.Part.Index)
-			conR.conS.peerMsgQueue <- msgInfo{msg, src.Key()}
+			if numBlocks := ps.RecordBlockPart(msg); numBlocks%blocksToContributeToBecomeGoodPeer == 0 {
+				conR.Switch.MarkPeerAsGood(src)
+			}
+			conR.conS.peerMsgQueue <- msgInfo{msg, src.ID()}
 		default:
 			conR.Logger.Error(cmn.Fmt("Unknown message type %v", reflect.TypeOf(msg)))
 		}
@@ -257,8 +278,11 @@ func (conR *ConsensusReactor) Receive(chID byte, src p2p.Peer, msgBytes []byte)
 			ps.EnsureVoteBitArrays(height, valSize)
 			ps.EnsureVoteBitArrays(height-1, lastCommitSize)
 			ps.SetHasVote(msg.Vote)
+			if blocks := ps.RecordVote(msg.Vote); blocks%blocksToContributeToBecomeGoodPeer == 0 {
+				conR.Switch.MarkPeerAsGood(src)
+			}
 
-			cs.peerMsgQueue <- msgInfo{msg, src.Key()}
+			cs.peerMsgQueue <- msgInfo{msg, src.ID()}
 
 		default:
 			// don't punish (leave room for soft upgrades)
@@ -306,10 +330,10 @@ func (conR *ConsensusReactor) Receive(chID byte, src p2p.Peer, msgBytes []byte)
 	}
 }
 
-// SetEventSwitch implements events.Eventable
-func (conR *ConsensusReactor) SetEventSwitch(evsw types.EventSwitch) {
-	conR.evsw = evsw
-	conR.conS.SetEventSwitch(evsw)
+// SetEventBus sets event bus.
+func (conR *ConsensusReactor) SetEventBus(b *types.EventBus) {
+	conR.eventBus = b
+	conR.conS.SetEventBus(b)
 }
 
 // FastSync returns whether the consensus reactor is in fast-sync mode.
@@ -321,24 +345,66 @@ func (conR *ConsensusReactor) FastSync() bool {
 
 //--------------------------------------
 
-// Listens for new steps and votes,
-// broadcasting the result to peers
-func (conR *ConsensusReactor) registerEventCallbacks() {
+// startBroadcastRoutine subscribes for new round steps, votes and proposal
+// heartbeats using the event bus and starts a go routine to broadcasts events
+// to peers upon receiving them.
+func (conR *ConsensusReactor) startBroadcastRoutine() error {
+	const subscriber = "consensus-reactor"
+	ctx := context.Background()
 
-	types.AddListenerForEvent(conR.evsw, "conR", types.EventStringNewRoundStep(), func(data types.TMEventData) {
-		rs := data.Unwrap().(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
-		conR.broadcastNewRoundStep(rs)
-	})
+	// new round steps
+	stepsCh := make(chan interface{})
+	err := conR.eventBus.Subscribe(ctx, subscriber, types.EventQueryNewRoundStep, stepsCh)
+	if err != nil {
+		return errors.Wrapf(err, "failed to subscribe %s to %s", subscriber, types.EventQueryNewRoundStep)
+	}
 
-	types.AddListenerForEvent(conR.evsw, "conR", types.EventStringVote(), func(data types.TMEventData) {
-		edv := data.Unwrap().(types.EventDataVote)
-		conR.broadcastHasVoteMessage(edv.Vote)
-	})
+	// votes
+	votesCh := make(chan interface{})
+	err = conR.eventBus.Subscribe(ctx, subscriber, types.EventQueryVote, votesCh)
+	if err != nil {
+		return errors.Wrapf(err, "failed to subscribe %s to %s", subscriber, types.EventQueryVote)
+	}
 
-	types.AddListenerForEvent(conR.evsw, "conR", types.EventStringProposalHeartbeat(), func(data types.TMEventData) {
-		heartbeat := data.Unwrap().(types.EventDataProposalHeartbeat)
-		conR.broadcastProposalHeartbeatMessage(heartbeat)
-	})
+	// proposal heartbeats
+	heartbeatsCh := make(chan interface{})
+	err = conR.eventBus.Subscribe(ctx, subscriber, types.EventQueryProposalHeartbeat, heartbeatsCh)
+	if err != nil {
+		return errors.Wrapf(err, "failed to subscribe %s to %s", subscriber, types.EventQueryProposalHeartbeat)
+	}
+
+	go func() {
+		var data interface{}
+		var ok bool
+		for {
+			select {
+			case data, ok = <-stepsCh:
+				if ok { // a receive from a closed channel returns the zero value immediately
+					edrs := data.(types.EventDataRoundState)
+					conR.broadcastNewRoundStep(edrs.RoundState.(*cstypes.RoundState))
+				}
+			case data, ok = <-votesCh:
+				if ok {
+					edv := data.(types.EventDataVote)
+					conR.broadcastHasVoteMessage(edv.Vote)
+				}
+			case data, ok = <-heartbeatsCh:
+				if ok {
+					edph := data.(types.EventDataProposalHeartbeat)
+					conR.broadcastProposalHeartbeatMessage(edph)
+				}
+			case <-conR.Quit():
+				conR.eventBus.UnsubscribeAll(ctx, subscriber)
+				return
+			}
+			if !ok {
+				conR.eventBus.UnsubscribeAll(ctx, subscriber)
+				return
+			}
+		}
+	}()
+
+	return nil
 }
 
 func (conR *ConsensusReactor) broadcastProposalHeartbeatMessage(heartbeat types.EventDataProposalHeartbeat) {
@@ -346,17 +412,16 @@ func (conR *ConsensusReactor) broadcastProposalHeartbeatMessage(heartbeat types.
 	conR.Logger.Debug("Broadcasting proposal heartbeat message",
 		"height", hb.Height, "round", hb.Round, "sequence", hb.Sequence)
 	msg := &ProposalHeartbeatMessage{hb}
-	conR.Switch.Broadcast(StateChannel, struct{ ConsensusMessage }{msg})
+	conR.Switch.Broadcast(StateChannel, cdc.MustMarshalBinaryBare(msg))
 }
 
 func (conR *ConsensusReactor) broadcastNewRoundStep(rs *cstypes.RoundState) {
-
 	nrsMsg, csMsg := makeRoundStepMessages(rs)
 	if nrsMsg != nil {
-		conR.Switch.Broadcast(StateChannel, struct{ ConsensusMessage }{nrsMsg})
+		conR.Switch.Broadcast(StateChannel, cdc.MustMarshalBinaryBare(nrsMsg))
 	}
 	if csMsg != nil {
-		conR.Switch.Broadcast(StateChannel, struct{ ConsensusMessage }{csMsg})
+		conR.Switch.Broadcast(StateChannel, cdc.MustMarshalBinaryBare(csMsg))
 	}
 }
 
@@ -368,7 +433,7 @@ func (conR *ConsensusReactor) broadcastHasVoteMessage(vote *types.Vote) {
 		Type:   vote.Type,
 		Index:  vote.ValidatorIndex,
 	}
-	conR.Switch.Broadcast(StateChannel, struct{ ConsensusMessage }{msg})
+	conR.Switch.Broadcast(StateChannel, cdc.MustMarshalBinaryBare(msg))
 	/*
 		// TODO: Make this broadcast more selective.
 		for _, peer := range conR.Switch.Peers().List() {
@@ -408,10 +473,10 @@ func (conR *ConsensusReactor) sendNewRoundStepMessages(peer p2p.Peer) {
 	rs := conR.conS.GetRoundState()
 	nrsMsg, csMsg := makeRoundStepMessages(rs)
 	if nrsMsg != nil {
-		peer.Send(StateChannel, struct{ ConsensusMessage }{nrsMsg})
+		peer.Send(StateChannel, cdc.MustMarshalBinaryBare(nrsMsg))
 	}
 	if csMsg != nil {
-		peer.Send(StateChannel, struct{ ConsensusMessage }{csMsg})
+		peer.Send(StateChannel, cdc.MustMarshalBinaryBare(csMsg))
 	}
 }
 
@@ -438,7 +503,7 @@ OUTER_LOOP:
 					Part:   part,
 				}
 				logger.Debug("Sending block part", "height", prs.Height, "round", prs.Round)
-				if peer.Send(DataChannel, struct{ ConsensusMessage }{msg}) {
+				if peer.Send(DataChannel, cdc.MustMarshalBinaryBare(msg)) {
 					ps.SetHasProposalBlockPart(prs.Height, prs.Round, index)
 				}
 				continue OUTER_LOOP
@@ -448,6 +513,18 @@ OUTER_LOOP:
 		// If the peer is on a previous height, help catch up.
 		if (0 < prs.Height) && (prs.Height < rs.Height) {
 			heightLogger := logger.With("height", prs.Height)
+
+			// if we never received the commit message from the peer, the block parts wont be initialized
+			if prs.ProposalBlockParts == nil {
+				blockMeta := conR.conS.blockStore.LoadBlockMeta(prs.Height)
+				if blockMeta == nil {
+					cmn.PanicCrisis(cmn.Fmt("Failed to load block %d when blockStore is at %d",
+						prs.Height, conR.conS.blockStore.Height()))
+				}
+				ps.InitProposalBlockParts(blockMeta.BlockID.PartsHeader)
+				// continue the loop since prs is a copy and not effected by this initialization
+				continue OUTER_LOOP
+			}
 			conR.gossipDataForCatchup(heightLogger, rs, prs, ps, peer)
 			continue OUTER_LOOP
 		}
@@ -470,7 +547,7 @@ OUTER_LOOP:
 			{
 				msg := &ProposalMessage{Proposal: rs.Proposal}
 				logger.Debug("Sending proposal", "height", prs.Height, "round", prs.Round)
-				if peer.Send(DataChannel, struct{ ConsensusMessage }{msg}) {
+				if peer.Send(DataChannel, cdc.MustMarshalBinaryBare(msg)) {
 					ps.SetHasProposal(rs.Proposal)
 				}
 			}
@@ -485,7 +562,7 @@ OUTER_LOOP:
 					ProposalPOL:      rs.Votes.Prevotes(rs.Proposal.POLRound).BitArray(),
 				}
 				logger.Debug("Sending POL", "height", prs.Height, "round", prs.Round)
-				peer.Send(DataChannel, struct{ ConsensusMessage }{msg})
+				peer.Send(DataChannel, cdc.MustMarshalBinaryBare(msg))
 			}
 			continue OUTER_LOOP
 		}
@@ -527,16 +604,16 @@ func (conR *ConsensusReactor) gossipDataForCatchup(logger log.Logger, rs *cstype
 			Round:  prs.Round,  // Not our height, so it doesn't matter.
 			Part:   part,
 		}
-		logger.Debug("Sending block part for catchup", "round", prs.Round)
-		if peer.Send(DataChannel, struct{ ConsensusMessage }{msg}) {
+		logger.Debug("Sending block part for catchup", "round", prs.Round, "index", index)
+		if peer.Send(DataChannel, cdc.MustMarshalBinaryBare(msg)) {
 			ps.SetHasProposalBlockPart(prs.Height, prs.Round, index)
+		} else {
+			logger.Debug("Sending block part for catchup failed")
 		}
 		return
-	} else {
-		//logger.Info("No parts to send in catch-up, sleeping")
-		time.Sleep(conR.conS.config.PeerGossipSleep())
-		return
 	}
+	//logger.Info("No parts to send in catch-up, sleeping")
+	time.Sleep(conR.conS.config.PeerGossipSleep())
 }
 
 func (conR *ConsensusReactor) gossipVotesRoutine(peer p2p.Peer, ps *PeerState) {
@@ -588,7 +665,6 @@ OUTER_LOOP:
 			// Load the block commit for prs.Height,
 			// which contains precommit signatures for prs.Height.
 			commit := conR.conS.blockStore.LoadBlockCommit(prs.Height)
-			logger.Info("Loaded BlockCommit for catch-up", "height", prs.Height, "commit", commit)
 			if ps.PickSendVote(commit) {
 				logger.Debug("Picked Catchup commit to send", "height", prs.Height)
 				continue OUTER_LOOP
@@ -666,12 +742,12 @@ OUTER_LOOP:
 			prs := ps.GetRoundState()
 			if rs.Height == prs.Height {
 				if maj23, ok := rs.Votes.Prevotes(prs.Round).TwoThirdsMajority(); ok {
-					peer.TrySend(StateChannel, struct{ ConsensusMessage }{&VoteSetMaj23Message{
+					peer.TrySend(StateChannel, cdc.MustMarshalBinaryBare(&VoteSetMaj23Message{
 						Height:  prs.Height,
 						Round:   prs.Round,
 						Type:    types.VoteTypePrevote,
 						BlockID: maj23,
-					}})
+					}))
 					time.Sleep(conR.conS.config.PeerQueryMaj23Sleep())
 				}
 			}
@@ -683,12 +759,12 @@ OUTER_LOOP:
 			prs := ps.GetRoundState()
 			if rs.Height == prs.Height {
 				if maj23, ok := rs.Votes.Precommits(prs.Round).TwoThirdsMajority(); ok {
-					peer.TrySend(StateChannel, struct{ ConsensusMessage }{&VoteSetMaj23Message{
+					peer.TrySend(StateChannel, cdc.MustMarshalBinaryBare(&VoteSetMaj23Message{
 						Height:  prs.Height,
 						Round:   prs.Round,
 						Type:    types.VoteTypePrecommit,
 						BlockID: maj23,
-					}})
+					}))
 					time.Sleep(conR.conS.config.PeerQueryMaj23Sleep())
 				}
 			}
@@ -700,12 +776,12 @@ OUTER_LOOP:
 			prs := ps.GetRoundState()
 			if rs.Height == prs.Height && prs.ProposalPOLRound >= 0 {
 				if maj23, ok := rs.Votes.Prevotes(prs.ProposalPOLRound).TwoThirdsMajority(); ok {
-					peer.TrySend(StateChannel, struct{ ConsensusMessage }{&VoteSetMaj23Message{
+					peer.TrySend(StateChannel, cdc.MustMarshalBinaryBare(&VoteSetMaj23Message{
 						Height:  prs.Height,
 						Round:   prs.ProposalPOLRound,
 						Type:    types.VoteTypePrevote,
 						BlockID: maj23,
-					}})
+					}))
 					time.Sleep(conR.conS.config.PeerQueryMaj23Sleep())
 				}
 			}
@@ -719,12 +795,12 @@ OUTER_LOOP:
 			prs := ps.GetRoundState()
 			if prs.CatchupCommitRound != -1 && 0 < prs.Height && prs.Height <= conR.conS.blockStore.Height() {
 				commit := conR.conS.LoadCommit(prs.Height)
-				peer.TrySend(StateChannel, struct{ ConsensusMessage }{&VoteSetMaj23Message{
+				peer.TrySend(StateChannel, cdc.MustMarshalBinaryBare(&VoteSetMaj23Message{
 					Height:  prs.Height,
 					Round:   commit.Round(),
 					Type:    types.VoteTypePrecommit,
 					BlockID: commit.BlockID,
-				}})
+				}))
 				time.Sleep(conR.conS.config.PeerQueryMaj23Sleep())
 			}
 		}
@@ -762,14 +838,29 @@ var (
 	ErrPeerStateInvalidStartTime = errors.New("Error peer state invalid startTime")
 )
 
-// PeerState contains the known state of a peer, including its connection
-// and threadsafe access to its PeerRoundState.
+// PeerState contains the known state of a peer, including its connection and
+// threadsafe access to its PeerRoundState.
 type PeerState struct {
 	Peer   p2p.Peer
 	logger log.Logger
 
 	mtx sync.Mutex
 	cstypes.PeerRoundState
+
+	stats *peerStateStats
+}
+
+// peerStateStats holds internal statistics for a peer.
+type peerStateStats struct {
+	lastVoteHeight int64
+	votes          int
+
+	lastBlockPartHeight int64
+	blockParts          int
+}
+
+func (pss peerStateStats) String() string {
+	return fmt.Sprintf("peerStateStats{votes: %d, blockParts: %d}", pss.votes, pss.blockParts)
 }
 
 // NewPeerState returns a new PeerState for the given Peer
@@ -783,15 +874,18 @@ func NewPeerState(peer p2p.Peer) *PeerState {
 			LastCommitRound:    -1,
 			CatchupCommitRound: -1,
 		},
+		stats: &peerStateStats{},
 	}
 }
 
+// SetLogger allows to set a logger on the peer state. Returns the peer state
+// itself.
 func (ps *PeerState) SetLogger(logger log.Logger) *PeerState {
 	ps.logger = logger
 	return ps
 }
 
-// GetRoundState returns an atomic snapshot of the PeerRoundState.
+// GetRoundState returns an shallow copy of the PeerRoundState.
 // There's no point in mutating it since it won't change PeerState.
 func (ps *PeerState) GetRoundState() *cstypes.PeerRoundState {
 	ps.mtx.Lock()
@@ -801,9 +895,17 @@ func (ps *PeerState) GetRoundState() *cstypes.PeerRoundState {
 	return &prs
 }
 
+// GetRoundStateJSON returns a json of PeerRoundState, marshalled using go-amino.
+func (ps *PeerState) GetRoundStateJSON() ([]byte, error) {
+	ps.mtx.Lock()
+	defer ps.mtx.Unlock()
+
+	return cdc.MarshalJSON(ps.PeerRoundState)
+}
+
 // GetHeight returns an atomic snapshot of the PeerRoundState's height
 // used by the mempool to ensure peers are caught up before broadcasting new txs
-func (ps *PeerState) GetHeight() int {
+func (ps *PeerState) GetHeight() int64 {
 	ps.mtx.Lock()
 	defer ps.mtx.Unlock()
 	return ps.PeerRoundState.Height
@@ -828,8 +930,21 @@ func (ps *PeerState) SetHasProposal(proposal *types.Proposal) {
 	ps.ProposalPOL = nil // Nil until ProposalPOLMessage received.
 }
 
+// InitProposalBlockParts initializes the peer's proposal block parts header and bit array.
+func (ps *PeerState) InitProposalBlockParts(partsHeader types.PartSetHeader) {
+	ps.mtx.Lock()
+	defer ps.mtx.Unlock()
+
+	if ps.ProposalBlockParts != nil {
+		return
+	}
+
+	ps.ProposalBlockPartsHeader = partsHeader
+	ps.ProposalBlockParts = cmn.NewBitArray(partsHeader.Total)
+}
+
 // SetHasProposalBlockPart sets the given block part index as known for the peer.
-func (ps *PeerState) SetHasProposalBlockPart(height int, round int, index int) {
+func (ps *PeerState) SetHasProposalBlockPart(height int64, round int, index int) {
 	ps.mtx.Lock()
 	defer ps.mtx.Unlock()
 
@@ -845,7 +960,8 @@ func (ps *PeerState) SetHasProposalBlockPart(height int, round int, index int) {
 func (ps *PeerState) PickSendVote(votes types.VoteSetReader) bool {
 	if vote, ok := ps.PickVoteToSend(votes); ok {
 		msg := &VoteMessage{vote}
-		return ps.Peer.Send(VoteChannel, struct{ ConsensusMessage }{msg})
+		ps.logger.Debug("Sending vote message", "ps", ps, "vote", vote)
+		return ps.Peer.Send(VoteChannel, cdc.MustMarshalBinaryBare(msg))
 	}
 	return false
 }
@@ -880,7 +996,7 @@ func (ps *PeerState) PickVoteToSend(votes types.VoteSetReader) (vote *types.Vote
 	return nil, false
 }
 
-func (ps *PeerState) getVoteBitArray(height, round int, type_ byte) *cmn.BitArray {
+func (ps *PeerState) getVoteBitArray(height int64, round int, type_ byte) *cmn.BitArray {
 	if !types.IsVoteTypeValid(type_) {
 		return nil
 	}
@@ -927,7 +1043,7 @@ func (ps *PeerState) getVoteBitArray(height, round int, type_ byte) *cmn.BitArra
 }
 
 // 'round': A round for which we have a +2/3 commit.
-func (ps *PeerState) ensureCatchupCommitRound(height, round int, numValidators int) {
+func (ps *PeerState) ensureCatchupCommitRound(height int64, round int, numValidators int) {
 	if ps.Height != height {
 		return
 	}
@@ -949,17 +1065,17 @@ func (ps *PeerState) ensureCatchupCommitRound(height, round int, numValidators i
 	}
 }
 
-// EnsureVoteVitArrays ensures the bit-arrays have been allocated for tracking
+// EnsureVoteBitArrays ensures the bit-arrays have been allocated for tracking
 // what votes this peer has received.
 // NOTE: It's important to make sure that numValidators actually matches
 // what the node sees as the number of validators for height.
-func (ps *PeerState) EnsureVoteBitArrays(height int, numValidators int) {
+func (ps *PeerState) EnsureVoteBitArrays(height int64, numValidators int) {
 	ps.mtx.Lock()
 	defer ps.mtx.Unlock()
 	ps.ensureVoteBitArrays(height, numValidators)
 }
 
-func (ps *PeerState) ensureVoteBitArrays(height int, numValidators int) {
+func (ps *PeerState) ensureVoteBitArrays(height int64, numValidators int) {
 	if ps.Height == height {
 		if ps.Prevotes == nil {
 			ps.Prevotes = cmn.NewBitArray(numValidators)
@@ -980,6 +1096,56 @@ func (ps *PeerState) ensureVoteBitArrays(height int, numValidators int) {
 	}
 }
 
+// RecordVote updates internal statistics for this peer by recording the vote.
+// It returns the total number of votes (1 per block). This essentially means
+// the number of blocks for which peer has been sending us votes.
+func (ps *PeerState) RecordVote(vote *types.Vote) int {
+	ps.mtx.Lock()
+	defer ps.mtx.Unlock()
+
+	if ps.stats.lastVoteHeight >= vote.Height {
+		return ps.stats.votes
+	}
+	ps.stats.lastVoteHeight = vote.Height
+	ps.stats.votes++
+	return ps.stats.votes
+}
+
+// VotesSent returns the number of blocks for which peer has been sending us
+// votes.
+func (ps *PeerState) VotesSent() int {
+	ps.mtx.Lock()
+	defer ps.mtx.Unlock()
+
+	return ps.stats.votes
+}
+
+// RecordBlockPart updates internal statistics for this peer by recording the
+// block part. It returns the total number of block parts (1 per block). This
+// essentially means the number of blocks for which peer has been sending us
+// block parts.
+func (ps *PeerState) RecordBlockPart(bp *BlockPartMessage) int {
+	ps.mtx.Lock()
+	defer ps.mtx.Unlock()
+
+	if ps.stats.lastBlockPartHeight >= bp.Height {
+		return ps.stats.blockParts
+	}
+
+	ps.stats.lastBlockPartHeight = bp.Height
+	ps.stats.blockParts++
+	return ps.stats.blockParts
+}
+
+// BlockPartsSent returns the number of blocks for which peer has been sending
+// us block parts.
+func (ps *PeerState) BlockPartsSent() int {
+	ps.mtx.Lock()
+	defer ps.mtx.Unlock()
+
+	return ps.stats.blockParts
+}
+
 // SetHasVote sets the given vote as known by the peer
 func (ps *PeerState) SetHasVote(vote *types.Vote) {
 	ps.mtx.Lock()
@@ -988,9 +1154,9 @@ func (ps *PeerState) SetHasVote(vote *types.Vote) {
 	ps.setHasVote(vote.Height, vote.Round, vote.Type, vote.ValidatorIndex)
 }
 
-func (ps *PeerState) setHasVote(height int, round int, type_ byte, index int) {
-	logger := ps.logger.With("peerRound", ps.Round, "height", height, "round", round)
-	logger.Debug("setHasVote(LastCommit)", "lastCommit", ps.LastCommit, "index", index)
+func (ps *PeerState) setHasVote(height int64, round int, type_ byte, index int) {
+	logger := ps.logger.With("peerH/R", cmn.Fmt("%d/%d", ps.Height, ps.Round), "H/R", cmn.Fmt("%d/%d", height, round))
+	logger.Debug("setHasVote", "type", type_, "index", index)
 
 	// NOTE: some may be nil BitArrays -> no side effects.
 	psVotes := ps.getVoteBitArray(height, round, type_)
@@ -1123,57 +1289,46 @@ func (ps *PeerState) String() string {
 
 // StringIndented returns a string representation of the PeerState
 func (ps *PeerState) StringIndented(indent string) string {
+	ps.mtx.Lock()
+	defer ps.mtx.Unlock()
 	return fmt.Sprintf(`PeerState{
-%s  Key %v
-%s  PRS %v
+%s  Key   %v
+%s  PRS   %v
+%s  Stats %v
 %s}`,
-		indent, ps.Peer.Key(),
+		indent, ps.Peer.ID(),
 		indent, ps.PeerRoundState.StringIndented(indent+"  "),
+		indent, ps.stats,
 		indent)
 }
 
 //-----------------------------------------------------------------------------
 // Messages
 
-const (
-	msgTypeNewRoundStep = byte(0x01)
-	msgTypeCommitStep   = byte(0x02)
-	msgTypeProposal     = byte(0x11)
-	msgTypeProposalPOL  = byte(0x12)
-	msgTypeBlockPart    = byte(0x13) // both block & POL
-	msgTypeVote         = byte(0x14)
-	msgTypeHasVote      = byte(0x15)
-	msgTypeVoteSetMaj23 = byte(0x16)
-	msgTypeVoteSetBits  = byte(0x17)
-
-	msgTypeProposalHeartbeat = byte(0x20)
-)
-
 // ConsensusMessage is a message that can be sent and received on the ConsensusReactor
 type ConsensusMessage interface{}
 
-var _ = wire.RegisterInterface(
-	struct{ ConsensusMessage }{},
-	wire.ConcreteType{&NewRoundStepMessage{}, msgTypeNewRoundStep},
-	wire.ConcreteType{&CommitStepMessage{}, msgTypeCommitStep},
-	wire.ConcreteType{&ProposalMessage{}, msgTypeProposal},
-	wire.ConcreteType{&ProposalPOLMessage{}, msgTypeProposalPOL},
-	wire.ConcreteType{&BlockPartMessage{}, msgTypeBlockPart},
-	wire.ConcreteType{&VoteMessage{}, msgTypeVote},
-	wire.ConcreteType{&HasVoteMessage{}, msgTypeHasVote},
-	wire.ConcreteType{&VoteSetMaj23Message{}, msgTypeVoteSetMaj23},
-	wire.ConcreteType{&VoteSetBitsMessage{}, msgTypeVoteSetBits},
-	wire.ConcreteType{&ProposalHeartbeatMessage{}, msgTypeProposalHeartbeat},
-)
+func RegisterConsensusMessages(cdc *amino.Codec) {
+	cdc.RegisterInterface((*ConsensusMessage)(nil), nil)
+	cdc.RegisterConcrete(&NewRoundStepMessage{}, "tendermint/NewRoundStepMessage", nil)
+	cdc.RegisterConcrete(&CommitStepMessage{}, "tendermint/CommitStep", nil)
+	cdc.RegisterConcrete(&ProposalMessage{}, "tendermint/Proposal", nil)
+	cdc.RegisterConcrete(&ProposalPOLMessage{}, "tendermint/ProposalPOL", nil)
+	cdc.RegisterConcrete(&BlockPartMessage{}, "tendermint/BlockPart", nil)
+	cdc.RegisterConcrete(&VoteMessage{}, "tendermint/Vote", nil)
+	cdc.RegisterConcrete(&HasVoteMessage{}, "tendermint/HasVote", nil)
+	cdc.RegisterConcrete(&VoteSetMaj23Message{}, "tendermint/VoteSetMaj23", nil)
+	cdc.RegisterConcrete(&VoteSetBitsMessage{}, "tendermint/VoteSetBits", nil)
+	cdc.RegisterConcrete(&ProposalHeartbeatMessage{}, "tendermint/ProposalHeartbeat", nil)
+}
 
 // DecodeMessage decodes the given bytes into a ConsensusMessage.
-// TODO: check for unnecessary extra bytes at the end.
-func DecodeMessage(bz []byte) (msgType byte, msg ConsensusMessage, err error) {
-	msgType = bz[0]
-	n := new(int)
-	r := bytes.NewReader(bz)
-	msgI := wire.ReadBinary(struct{ ConsensusMessage }{}, r, maxConsensusMessageSize, n, &err)
-	msg = msgI.(struct{ ConsensusMessage }).ConsensusMessage
+func DecodeMessage(bz []byte) (msg ConsensusMessage, err error) {
+	if len(bz) > maxMsgSize {
+		return msg, fmt.Errorf("Msg exceeds max size (%d > %d)",
+			len(bz), maxMsgSize)
+	}
+	err = cdc.UnmarshalBinaryBare(bz, &msg)
 	return
 }
 
@@ -1182,7 +1337,7 @@ func DecodeMessage(bz []byte) (msgType byte, msg ConsensusMessage, err error) {
 // NewRoundStepMessage is sent for every step taken in the ConsensusState.
 // For every height/round/step transition
 type NewRoundStepMessage struct {
-	Height                int
+	Height                int64
 	Round                 int
 	Step                  cstypes.RoundStepType
 	SecondsSinceStartTime int
@@ -1199,7 +1354,7 @@ func (m *NewRoundStepMessage) String() string {
 
 // CommitStepMessage is sent when a block is committed.
 type CommitStepMessage struct {
-	Height           int
+	Height           int64
 	BlockPartsHeader types.PartSetHeader
 	BlockParts       *cmn.BitArray
 }
@@ -1225,7 +1380,7 @@ func (m *ProposalMessage) String() string {
 
 // ProposalPOLMessage is sent when a previous proposal is re-proposed.
 type ProposalPOLMessage struct {
-	Height           int
+	Height           int64
 	ProposalPOLRound int
 	ProposalPOL      *cmn.BitArray
 }
@@ -1239,7 +1394,7 @@ func (m *ProposalPOLMessage) String() string {
 
 // BlockPartMessage is sent when gossipping a piece of the proposed block.
 type BlockPartMessage struct {
-	Height int
+	Height int64
 	Round  int
 	Part   *types.Part
 }
@@ -1265,7 +1420,7 @@ func (m *VoteMessage) String() string {
 
 // HasVoteMessage is sent to indicate that a particular vote has been received.
 type HasVoteMessage struct {
-	Height int
+	Height int64
 	Round  int
 	Type   byte
 	Index  int
@@ -1273,14 +1428,14 @@ type HasVoteMessage struct {
 
 // String returns a string representation.
 func (m *HasVoteMessage) String() string {
-	return fmt.Sprintf("[HasVote VI:%v V:{%v/%02d/%v} VI:%v]", m.Index, m.Height, m.Round, m.Type, m.Index)
+	return fmt.Sprintf("[HasVote VI:%v V:{%v/%02d/%v}]", m.Index, m.Height, m.Round, m.Type)
 }
 
 //-------------------------------------
 
 // VoteSetMaj23Message is sent to indicate that a given BlockID has seen +2/3 votes.
 type VoteSetMaj23Message struct {
-	Height  int
+	Height  int64
 	Round   int
 	Type    byte
 	BlockID types.BlockID
@@ -1295,7 +1450,7 @@ func (m *VoteSetMaj23Message) String() string {
 
 // VoteSetBitsMessage is sent to communicate the bit-array of votes seen for the BlockID.
 type VoteSetBitsMessage struct {
-	Height  int
+	Height  int64
 	Round   int
 	Type    byte
 	BlockID types.BlockID

consensus/reactor_test.go

@@ -1,17 +1,26 @@
 package consensus
 
 import (
+	"context"
 	"fmt"
+	"os"
+	"runtime"
+	"runtime/pprof"
 	"sync"
 	"testing"
 	"time"
 
-	"github.com/tendermint/abci/example/dummy"
-	"github.com/tendermint/tmlibs/events"
+	"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"
 )
 
 func init() {
@@ -21,60 +30,64 @@ func init() {
 //----------------------------------------------
 // in-process testnets
 
-func startConsensusNet(t *testing.T, css []*ConsensusState, N int, subscribeEventRespond bool) ([]*ConsensusReactor, []chan interface{}) {
+func startConsensusNet(t *testing.T, css []*ConsensusState, N int) ([]*ConsensusReactor, []chan interface{}, []*types.EventBus) {
 	reactors := make([]*ConsensusReactor, N)
 	eventChans := make([]chan interface{}, N)
-	logger := consensusLogger()
+	eventBuses := make([]*types.EventBus, N)
 	for i := 0; i < N; i++ {
+		/*logger, err := tmflags.ParseLogLevel("consensus:info,*:error", logger, "info")
+		if err != nil {	t.Fatal(err)}*/
 		reactors[i] = NewConsensusReactor(css[i], true) // so we dont start the consensus states
-		reactors[i].SetLogger(logger.With("validator", i))
+		reactors[i].SetLogger(css[i].Logger)
 
-		eventSwitch := events.NewEventSwitch()
-		eventSwitch.SetLogger(logger.With("module", "events", "validator", i))
-		_, err := eventSwitch.Start()
-		if err != nil {
-			t.Fatalf("Failed to start switch: %v", err)
-		}
+		// eventBus is already started with the cs
+		eventBuses[i] = css[i].eventBus
+		reactors[i].SetEventBus(eventBuses[i])
 
-		reactors[i].SetEventSwitch(eventSwitch)
-		if subscribeEventRespond {
-			eventChans[i] = subscribeToEventRespond(eventSwitch, "tester", types.EventStringNewBlock())
-		} else {
-			eventChans[i] = subscribeToEvent(eventSwitch, "tester", types.EventStringNewBlock(), 1)
-		}
+		eventChans[i] = make(chan interface{}, 1)
+		err := eventBuses[i].Subscribe(context.Background(), testSubscriber, types.EventQueryNewBlock, eventChans[i])
+		require.NoError(t, err)
 	}
 	// make connected switches and start all reactors
 	p2p.MakeConnectedSwitches(config.P2P, N, func(i int, s *p2p.Switch) *p2p.Switch {
 		s.AddReactor("CONSENSUS", reactors[i])
+		s.SetLogger(reactors[i].conS.Logger.With("module", "p2p"))
 		return s
 	}, p2p.Connect2Switches)
 
 	// now that everyone is connected,  start the state machines
 	// If we started the state machines before everyone was connected,
 	// we'd block when the cs fires NewBlockEvent and the peers are trying to start their reactors
+	// TODO: is this still true with new pubsub?
 	for i := 0; i < N; i++ {
 		s := reactors[i].conS.GetState()
 		reactors[i].SwitchToConsensus(s, 0)
 	}
-	return reactors, eventChans
+	return reactors, eventChans, eventBuses
 }
 
-func stopConsensusNet(reactors []*ConsensusReactor) {
-	for _, r := range reactors {
+func stopConsensusNet(logger log.Logger, reactors []*ConsensusReactor, eventBuses []*types.EventBus) {
+	logger.Info("stopConsensusNet", "n", len(reactors))
+	for i, r := range reactors {
+		logger.Info("stopConsensusNet: Stopping ConsensusReactor", "i", i)
 		r.Switch.Stop()
 	}
+	for i, b := range eventBuses {
+		logger.Info("stopConsensusNet: Stopping eventBus", "i", i)
+		b.Stop()
+	}
+	logger.Info("stopConsensusNet: DONE", "n", len(reactors))
 }
 
 // Ensure a testnet makes blocks
-func TestReactor(t *testing.T) {
+func TestReactorBasic(t *testing.T) {
 	N := 4
 	css := randConsensusNet(N, "consensus_reactor_test", newMockTickerFunc(true), newCounter)
-	reactors, eventChans := startConsensusNet(t, css, N, false)
-	defer stopConsensusNet(reactors)
+	reactors, eventChans, eventBuses := startConsensusNet(t, css, N)
+	defer stopConsensusNet(log.TestingLogger(), reactors, eventBuses)
 	// wait till everyone makes the first new block
-	timeoutWaitGroup(t, N, func(wg *sync.WaitGroup, j int) {
+	timeoutWaitGroup(t, N, func(j int) {
 		<-eventChans[j]
-		wg.Done()
 	}, css)
 }
 
@@ -85,36 +98,146 @@ func TestReactorProposalHeartbeats(t *testing.T) {
 		func(c *cfg.Config) {
 			c.Consensus.CreateEmptyBlocks = false
 		})
-	reactors, eventChans := startConsensusNet(t, css, N, false)
-	defer stopConsensusNet(reactors)
+	reactors, eventChans, eventBuses := startConsensusNet(t, css, N)
+	defer stopConsensusNet(log.TestingLogger(), reactors, eventBuses)
 	heartbeatChans := make([]chan interface{}, N)
+	var err error
 	for i := 0; i < N; i++ {
-		heartbeatChans[i] = subscribeToEvent(css[i].evsw, "tester", types.EventStringProposalHeartbeat(), 1)
+		heartbeatChans[i] = make(chan interface{}, 1)
+		err = eventBuses[i].Subscribe(context.Background(), testSubscriber, types.EventQueryProposalHeartbeat, heartbeatChans[i])
+		require.NoError(t, err)
 	}
 	// wait till everyone sends a proposal heartbeat
-	timeoutWaitGroup(t, N, func(wg *sync.WaitGroup, j int) {
+	timeoutWaitGroup(t, N, func(j int) {
 		<-heartbeatChans[j]
-		wg.Done()
 	}, css)
 
 	// send a tx
-	css[3].mempool.CheckTx([]byte{1, 2, 3}, nil)
+	if err := css[3].mempool.CheckTx([]byte{1, 2, 3}, nil); err != nil {
+		//t.Fatal(err)
+	}
 
 	// wait till everyone makes the first new block
-	timeoutWaitGroup(t, N, func(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)
-	reactors, eventChans := startConsensusNet(t, css, nVals, true)
-	defer stopConsensusNet(reactors)
+	logger := log.TestingLogger()
+	css := randConsensusNet(nVals, "consensus_voting_power_changes_test", newMockTickerFunc(true), newPersistentKVStore)
+	reactors, eventChans, eventBuses := startConsensusNet(t, css, nVals)
+	defer stopConsensusNet(logger, reactors, eventBuses)
 
 	// map of active validators
 	activeVals := make(map[string]struct{})
@@ -123,21 +246,19 @@ func TestVotingPowerChange(t *testing.T) {
 	}
 
 	// wait till everyone makes block 1
-	timeoutWaitGroup(t, nVals, func(wg *sync.WaitGroup, j int) {
+	timeoutWaitGroup(t, nVals, func(j int) {
 		<-eventChans[j]
-		eventChans[j] <- struct{}{}
-		wg.Done()
 	}, css)
 
 	//---------------------------------------------------------------------------
-	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)
+	updateValidatorTx := kvstore.MakeValSetChangeTx(val1PubKey.Bytes(), 25)
 	previousTotalVotingPower := css[0].GetRoundState().LastValidators.TotalVotingPower()
 
 	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css, updateValidatorTx)
-	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
+	waitForAndValidateBlockWithTx(t, nVals, activeVals, eventChans, css, updateValidatorTx)
 	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
 	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
 
@@ -145,11 +266,11 @@ func TestVotingPowerChange(t *testing.T) {
 		t.Fatalf("expected voting power to change (before: %d, after: %d)", previousTotalVotingPower, css[0].GetRoundState().LastValidators.TotalVotingPower())
 	}
 
-	updateValidatorTx = dummy.MakeValSetChangeTx(val1PubKey.Bytes(), 2)
+	updateValidatorTx = kvstore.MakeValSetChangeTx(val1PubKey.Bytes(), 2)
 	previousTotalVotingPower = css[0].GetRoundState().LastValidators.TotalVotingPower()
 
 	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css, updateValidatorTx)
-	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
+	waitForAndValidateBlockWithTx(t, nVals, activeVals, eventChans, css, updateValidatorTx)
 	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
 	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
 
@@ -157,11 +278,11 @@ func TestVotingPowerChange(t *testing.T) {
 		t.Fatalf("expected voting power to change (before: %d, after: %d)", previousTotalVotingPower, css[0].GetRoundState().LastValidators.TotalVotingPower())
 	}
 
-	updateValidatorTx = dummy.MakeValSetChangeTx(val1PubKey.Bytes(), 100)
+	updateValidatorTx = kvstore.MakeValSetChangeTx(val1PubKey.Bytes(), 26)
 	previousTotalVotingPower = css[0].GetRoundState().LastValidators.TotalVotingPower()
 
 	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css, updateValidatorTx)
-	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
+	waitForAndValidateBlockWithTx(t, nVals, activeVals, eventChans, css, updateValidatorTx)
 	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
 	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
 
@@ -170,12 +291,15 @@ func TestVotingPowerChange(t *testing.T) {
 	}
 }
 
-func TestValidatorSetChanges(t *testing.T) {
+func TestReactorValidatorSetChanges(t *testing.T) {
 	nPeers := 7
 	nVals := 4
-	css := randConsensusNetWithPeers(nVals, nPeers, "consensus_val_set_changes_test", newMockTickerFunc(true), newPersistentDummy)
-	reactors, eventChans := startConsensusNet(t, css, nPeers, true)
-	defer stopConsensusNet(reactors)
+	css := randConsensusNetWithPeers(nVals, nPeers, "consensus_val_set_changes_test", newMockTickerFunc(true), newPersistentKVStore)
+
+	logger := log.TestingLogger()
+
+	reactors, eventChans, eventBuses := startConsensusNet(t, css, nPeers)
+	defer stopConsensusNet(logger, reactors, eventBuses)
 
 	// map of active validators
 	activeVals := make(map[string]struct{})
@@ -184,17 +308,15 @@ func TestValidatorSetChanges(t *testing.T) {
 	}
 
 	// wait till everyone makes block 1
-	timeoutWaitGroup(t, nPeers, func(wg *sync.WaitGroup, j int) {
+	timeoutWaitGroup(t, nPeers, func(j int) {
 		<-eventChans[j]
-		eventChans[j] <- struct{}{}
-		wg.Done()
 	}, css)
 
 	//---------------------------------------------------------------------------
-	t.Log("---------------------------- Testing adding one validator")
+	logger.Info("---------------------------- Testing adding one validator")
 
 	newValidatorPubKey1 := css[nVals].privValidator.GetPubKey()
-	newValidatorTx1 := dummy.MakeValSetChangeTx(newValidatorPubKey1.Bytes(), uint64(testMinPower))
+	newValidatorTx1 := kvstore.MakeValSetChangeTx(newValidatorPubKey1.Bytes(), testMinPower)
 
 	// wait till everyone makes block 2
 	// ensure the commit includes all validators
@@ -203,7 +325,7 @@ func TestValidatorSetChanges(t *testing.T) {
 
 	// wait till everyone makes block 3.
 	// it includes the commit for block 2, which is by the original validator set
-	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
+	waitForAndValidateBlockWithTx(t, nPeers, activeVals, eventChans, css, newValidatorTx1)
 
 	// wait till everyone makes block 4.
 	// it includes the commit for block 3, which is by the original validator set
@@ -214,52 +336,52 @@ func TestValidatorSetChanges(t *testing.T) {
 
 	// wait till everyone makes block 5
 	// it includes the commit for block 4, which should have the updated validator set
-	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
+	waitForBlockWithUpdatedValsAndValidateIt(t, nPeers, activeVals, eventChans, css)
 
 	//---------------------------------------------------------------------------
-	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)
+	updateValidatorTx1 := kvstore.MakeValSetChangeTx(updateValidatorPubKey1.Bytes(), 25)
 	previousTotalVotingPower := css[nVals].GetRoundState().LastValidators.TotalVotingPower()
 
 	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css, updateValidatorTx1)
+	waitForAndValidateBlockWithTx(t, nPeers, activeVals, eventChans, css, updateValidatorTx1)
 	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
-	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
-	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
+	waitForBlockWithUpdatedValsAndValidateIt(t, nPeers, activeVals, eventChans, css)
 
 	if css[nVals].GetRoundState().LastValidators.TotalVotingPower() == previousTotalVotingPower {
 		t.Errorf("expected voting power to change (before: %d, after: %d)", previousTotalVotingPower, css[nVals].GetRoundState().LastValidators.TotalVotingPower())
 	}
 
 	//---------------------------------------------------------------------------
-	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(), uint64(testMinPower))
+	newValidatorTx2 := kvstore.MakeValSetChangeTx(newValidatorPubKey2.Bytes(), testMinPower)
 
 	newValidatorPubKey3 := css[nVals+2].privValidator.GetPubKey()
-	newValidatorTx3 := dummy.MakeValSetChangeTx(newValidatorPubKey3.Bytes(), uint64(testMinPower))
+	newValidatorTx3 := kvstore.MakeValSetChangeTx(newValidatorPubKey3.Bytes(), testMinPower)
 
 	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css, newValidatorTx2, newValidatorTx3)
-	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
+	waitForAndValidateBlockWithTx(t, nPeers, activeVals, eventChans, css, newValidatorTx2, newValidatorTx3)
 	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
 	activeVals[string(newValidatorPubKey2.Address())] = struct{}{}
 	activeVals[string(newValidatorPubKey3.Address())] = struct{}{}
-	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
+	waitForBlockWithUpdatedValsAndValidateIt(t, nPeers, activeVals, eventChans, css)
 
 	//---------------------------------------------------------------------------
-	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(newValidatorPubKey2.Bytes(), 0)
+	removeValidatorTx3 := kvstore.MakeValSetChangeTx(newValidatorPubKey3.Bytes(), 0)
 
 	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css, removeValidatorTx2, removeValidatorTx3)
-	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
+	waitForAndValidateBlockWithTx(t, nPeers, activeVals, eventChans, css, removeValidatorTx2, removeValidatorTx3)
 	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
 	delete(activeVals, string(newValidatorPubKey2.Address()))
 	delete(activeVals, string(newValidatorPubKey3.Address()))
-	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
+	waitForBlockWithUpdatedValsAndValidateIt(t, nPeers, activeVals, eventChans, css)
 }
 
 // Check we can make blocks with skip_timeout_commit=false
@@ -271,31 +393,86 @@ func TestReactorWithTimeoutCommit(t *testing.T) {
 		css[i].config.SkipTimeoutCommit = false
 	}
 
-	reactors, eventChans := startConsensusNet(t, css, N-1, false)
-	defer stopConsensusNet(reactors)
+	reactors, eventChans, eventBuses := startConsensusNet(t, css, N-1)
+	defer stopConsensusNet(log.TestingLogger(), reactors, eventBuses)
 
 	// wait till everyone makes the first new block
-	timeoutWaitGroup(t, N-1, func(wg *sync.WaitGroup, j int) {
+	timeoutWaitGroup(t, N-1, func(j int) {
 		<-eventChans[j]
-		wg.Done()
 	}, css)
 }
 
 func waitForAndValidateBlock(t *testing.T, n int, activeVals map[string]struct{}, eventChans []chan interface{}, css []*ConsensusState, txs ...[]byte) {
-	timeoutWaitGroup(t, n, func(wg *sync.WaitGroup, j int) {
-		newBlockI := <-eventChans[j]
-		newBlock := newBlockI.(types.TMEventData).Unwrap().(types.EventDataNewBlock).Block
-		t.Logf("[WARN] Got block height=%v validator=%v", newBlock.Height, j)
-		err := validateBlock(newBlock, activeVals)
-		if err != nil {
-			t.Fatal(err)
+	timeoutWaitGroup(t, n, func(j int) {
+		css[j].Logger.Debug("waitForAndValidateBlock")
+		newBlockI, ok := <-eventChans[j]
+		if !ok {
+			return
 		}
+		newBlock := newBlockI.(types.EventDataNewBlock).Block
+		css[j].Logger.Debug("waitForAndValidateBlock: Got block", "height", newBlock.Height)
+		err := validateBlock(newBlock, activeVals)
+		assert.Nil(t, err)
 		for _, tx := range txs {
 			css[j].mempool.CheckTx(tx, nil)
+			assert.Nil(t, err)
+		}
+	}, css)
+}
+
+func waitForAndValidateBlockWithTx(t *testing.T, n int, activeVals map[string]struct{}, eventChans []chan interface{}, css []*ConsensusState, txs ...[]byte) {
+	timeoutWaitGroup(t, n, func(j int) {
+		ntxs := 0
+	BLOCK_TX_LOOP:
+		for {
+			css[j].Logger.Debug("waitForAndValidateBlockWithTx", "ntxs", ntxs)
+			newBlockI, ok := <-eventChans[j]
+			if !ok {
+				return
+			}
+			newBlock := newBlockI.(types.EventDataNewBlock).Block
+			css[j].Logger.Debug("waitForAndValidateBlockWithTx: Got block", "height", newBlock.Height)
+			err := validateBlock(newBlock, activeVals)
+			assert.Nil(t, err)
+
+			// check that txs match the txs we're waiting for.
+			// note they could be spread over multiple blocks,
+			// but they should be in order.
+			for _, tx := range newBlock.Data.Txs {
+				assert.EqualValues(t, txs[ntxs], tx)
+				ntxs++
+			}
+
+			if ntxs == len(txs) {
+				break BLOCK_TX_LOOP
+			}
 		}
 
-		eventChans[j] <- struct{}{}
-		wg.Done()
+	}, css)
+}
+
+func waitForBlockWithUpdatedValsAndValidateIt(t *testing.T, n int, updatedVals map[string]struct{}, eventChans []chan interface{}, css []*ConsensusState) {
+	timeoutWaitGroup(t, n, func(j int) {
+
+		var newBlock *types.Block
+	LOOP:
+		for {
+			css[j].Logger.Debug("waitForBlockWithUpdatedValsAndValidateIt")
+			newBlockI, ok := <-eventChans[j]
+			if !ok {
+				return
+			}
+			newBlock = newBlockI.(types.EventDataNewBlock).Block
+			if newBlock.LastCommit.Size() == len(updatedVals) {
+				css[j].Logger.Debug("waitForBlockWithUpdatedValsAndValidateIt: Got block", "height", newBlock.Height)
+				break LOOP
+			} else {
+				css[j].Logger.Debug("waitForBlockWithUpdatedValsAndValidateIt: Got block with no new validators. Skipping", "height", newBlock.Height)
+			}
+		}
+
+		err := validateBlock(newBlock, updatedVals)
+		assert.Nil(t, err)
 	}, css)
 }
 
@@ -313,11 +490,14 @@ func validateBlock(block *types.Block, activeVals map[string]struct{}) error {
 	return nil
 }
 
-func timeoutWaitGroup(t *testing.T, n int, f func(*sync.WaitGroup, int), css []*ConsensusState) {
+func timeoutWaitGroup(t *testing.T, n int, f func(int), css []*ConsensusState) {
 	wg := new(sync.WaitGroup)
 	wg.Add(n)
 	for i := 0; i < n; i++ {
-		go f(wg, i)
+		go func(j int) {
+			f(j)
+			wg.Done()
+		}(i)
 	}
 
 	done := make(chan struct{})
@@ -326,15 +506,28 @@ func timeoutWaitGroup(t *testing.T, n int, f func(*sync.WaitGroup, int), css []*
 		close(done)
 	}()
 
+	// we're running many nodes in-process, possibly in in a virtual machine,
+	// and spewing debug messages - making a block could take a while,
+	timeout := time.Second * 300
+
 	select {
 	case <-done:
-	case <-time.After(time.Second * 10):
+	case <-time.After(timeout):
 		for i, cs := range css {
-			fmt.Println("#################")
-			fmt.Println("Validator", i)
-			fmt.Println(cs.GetRoundState())
-			fmt.Println("")
+			t.Log("#################")
+			t.Log("Validator", i)
+			t.Log(cs.GetRoundState())
+			t.Log("")
 		}
+		os.Stdout.Write([]byte("pprof.Lookup('goroutine'):\n"))
+		pprof.Lookup("goroutine").WriteTo(os.Stdout, 1)
+		capture()
 		panic("Timed out waiting for all validators to commit a block")
 	}
 }
+
+func capture() {
+	trace := make([]byte, 10240000)
+	count := runtime.Stack(trace, true)
+	fmt.Printf("Stack of %d bytes: %s\n", count, trace)
+}

consensus/replay.go

@@ -2,18 +2,19 @@ package consensus
 
 import (
 	"bytes"
-	"errors"
+	"encoding/json"
 	"fmt"
 	"hash/crc32"
 	"io"
 	"reflect"
-	"strconv"
-	"strings"
+	//"strconv"
+	//"strings"
 	"time"
 
 	abci "github.com/tendermint/abci/types"
-	auto "github.com/tendermint/tmlibs/autofile"
+	//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"
@@ -61,21 +62,21 @@ 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)
@@ -90,34 +91,43 @@ func (cs *ConsensusState) readReplayMessage(msg *TimedWALMessage, newStepCh chan
 
 // replay only those messages since the last block.
 // timeoutRoutine should run concurrently to read off tickChan
-func (cs *ConsensusState) catchupReplay(csHeight int) error {
-
+func (cs *ConsensusState) catchupReplay(csHeight int64) error {
 	// set replayMode
 	cs.replayMode = true
 	defer func() { cs.replayMode = false }()
 
-	// Ensure that ENDHEIGHT for this height doesn't exist
-	// NOTE: This is just a sanity check. As far as we know things work fine without it,
-	// and Handshake could reuse ConsensusState if it weren't for this check (since we can crash after writing ENDHEIGHT).
-	gr, found, err := cs.wal.SearchForEndHeight(uint64(csHeight))
+	// Ensure that ENDHEIGHT for this height doesn't exist.
+	// NOTE: This is just a sanity check. As far as we know things work fine
+	// without it, and Handshake could reuse ConsensusState if it weren't for
+	// this check (since we can crash after writing ENDHEIGHT).
+	//
+	// Ignore data corruption errors since this is a sanity check.
+	gr, found, err := cs.wal.SearchForEndHeight(csHeight, &WALSearchOptions{IgnoreDataCorruptionErrors: true})
+	if err != nil {
+		return err
+	}
 	if gr != nil {
-		gr.Close()
+		if err := gr.Close(); err != nil {
+			return err
+		}
 	}
 	if found {
-		return errors.New(cmn.Fmt("WAL should not contain #ENDHEIGHT %d.", csHeight))
+		return fmt.Errorf("WAL should not contain #ENDHEIGHT %d", csHeight)
 	}
 
 	// Search for last height marker
-	gr, found, err = cs.wal.SearchForEndHeight(uint64(csHeight - 1))
+	//
+	// Ignore data corruption errors in previous heights because we only care about last height
+	gr, found, err = cs.wal.SearchForEndHeight(csHeight-1, &WALSearchOptions{IgnoreDataCorruptionErrors: true})
 	if err == io.EOF {
 		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()
+	defer gr.Close() // nolint: errcheck
 
 	cs.Logger.Info("Catchup by replaying consensus messages", "height", csHeight)
 
@@ -128,9 +138,13 @@ func (cs *ConsensusState) catchupReplay(csHeight int) 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
@@ -146,7 +160,8 @@ func (cs *ConsensusState) catchupReplay(csHeight int) error {
 
 // Parses marker lines of the form:
 // #ENDHEIGHT: 12345
-func makeHeightSearchFunc(height int) auto.SearchFunc {
+/*
+func makeHeightSearchFunc(height int64) auto.SearchFunc {
 	return func(line string) (int, error) {
 		line = strings.TrimRight(line, "\n")
 		parts := strings.Split(line, " ")
@@ -165,7 +180,7 @@ func makeHeightSearchFunc(height int) auto.SearchFunc {
 			return -1, nil
 		}
 	}
-}
+}*/
 
 //----------------------------------------------
 // Recover from failure during block processing
@@ -173,15 +188,26 @@ func makeHeightSearchFunc(height int) auto.SearchFunc {
 // 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        types.BlockStore
+	appState     json.RawMessage
+	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 types.BlockStore, appState json.RawMessage) *Handshaker {
+
+	return &Handshaker{
+		stateDB:      stateDB,
+		initialState: state,
+		store:        store,
+		appState:     appState,
+		logger:       log.NewNopLogger(),
+		nBlocks:      0,
+	}
 }
 
 func (h *Handshaker) SetLogger(l log.Logger) {
@@ -197,10 +223,13 @@ func (h *Handshaker) Handshake(proxyApp proxy.AppConns) error {
 	// handshake is done via info request 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 := int(res.LastBlockHeight) // XXX: beware overflow
+	blockHeight := int64(res.LastBlockHeight)
+	if blockHeight < 0 {
+		return fmt.Errorf("Got a negative last block height (%d) from the app", blockHeight)
+	}
 	appHash := res.LastBlockAppHash
 
 	h.logger.Info("ABCI Handshake", "appHeight", blockHeight, "appHash", fmt.Sprintf("%X", appHash))
@@ -208,9 +237,9 @@ func (h *Handshaker) Handshake(proxyApp proxy.AppConns) error {
 	// TODO: check version
 
 	// replay blocks up to the latest in the blockstore
-	_, err = h.ReplayBlocks(appHash, blockHeight, proxyApp)
+	_, 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))
@@ -222,21 +251,28 @@ func (h *Handshaker) Handshake(proxyApp proxy.AppConns) error {
 
 // Replay all blocks since appBlockHeight and ensure the result matches the current state.
 // Returns the final AppHash or an error
-func (h *Handshaker) ReplayBlocks(appHash []byte, appBlockHeight int, proxyApp proxy.AppConns) ([]byte, error) {
+func (h *Handshaker) ReplayBlocks(state sm.State, appHash []byte, appBlockHeight int64, proxyApp proxy.AppConns) ([]byte, error) {
 
 	storeBlockHeight := h.store.Height()
-	stateBlockHeight := h.state.LastBlockHeight
+	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)
-		proxyApp.Consensus().InitChainSync(abci.RequestInitChain{validators})
+		validators := types.TM2PB.Validators(state.Validators)
+		req := abci.RequestInitChain{
+			Validators:    validators,
+			AppStateBytes: h.appState,
+		}
+		_, err := proxyApp.Consensus().InitChainSync(req)
+		if err != nil {
+			return nil, err
+		}
 	}
 
 	// First handle edge cases and constraints on the storeBlockHeight
 	if storeBlockHeight == 0 {
-		return appHash, h.checkAppHash(appHash)
+		return appHash, checkAppHash(state, appHash)
 
 	} else if storeBlockHeight < appBlockHeight {
 		// the app should never be ahead of the store (but this is under app's control)
@@ -251,6 +287,7 @@ func (h *Handshaker) ReplayBlocks(appHash []byte, appBlockHeight int, proxyApp p
 		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 {
@@ -258,11 +295,11 @@ func (h *Handshaker) ReplayBlocks(appHash []byte, appBlockHeight int, proxyApp p
 		// Either the app is asking for replay, or we're all synced up.
 		if appBlockHeight < storeBlockHeight {
 			// the app is behind, so replay blocks, but no need to go through WAL (state is already synced to store)
-			return h.replayBlocks(proxyApp, appBlockHeight, storeBlockHeight, false)
+			return h.replayBlocks(state, proxyApp, appBlockHeight, storeBlockHeight, false)
 
 		} else if appBlockHeight == storeBlockHeight {
 			// We're good!
-			return appHash, h.checkAppHash(appHash)
+			return appHash, checkAppHash(state, appHash)
 		}
 
 	} else if storeBlockHeight == stateBlockHeight+1 {
@@ -271,7 +308,7 @@ func (h *Handshaker) ReplayBlocks(appHash []byte, appBlockHeight int, proxyApp p
 		if appBlockHeight < stateBlockHeight {
 			// the app is further behind than it should be, so replay blocks
 			// but leave the last block to go through the WAL
-			return h.replayBlocks(proxyApp, appBlockHeight, storeBlockHeight, true)
+			return h.replayBlocks(state, proxyApp, appBlockHeight, storeBlockHeight, true)
 
 		} else if appBlockHeight == stateBlockHeight {
 			// We haven't run Commit (both the state and app are one block behind),
@@ -279,14 +316,19 @@ func (h *Handshaker) ReplayBlocks(appHash []byte, appBlockHeight int, proxyApp p
 			// 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
 			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
 		}
 
 	}
@@ -295,13 +337,14 @@ func (h *Handshaker) ReplayBlocks(appHash []byte, appBlockHeight int, proxyApp p
 	return nil, nil
 }
 
-func (h *Handshaker) replayBlocks(proxyApp proxy.AppConns, appBlockHeight, storeBlockHeight int, mutateState bool) ([]byte, error) {
+func (h *Handshaker) replayBlocks(state sm.State, proxyApp proxy.AppConns, appBlockHeight, storeBlockHeight int64, mutateState bool) ([]byte, error) {
 	// App is further behind than it should be, so we need to replay blocks.
 	// We replay all blocks from appBlockHeight+1.
 	//
 	// Note that we don't have an old version of the state,
 	// so we by-pass state validation/mutation using sm.ExecCommitBlock.
 	// This also means we won't be saving validator sets if they change during this period.
+	// TODO: Load the historical information to fix this and just use state.ApplyBlock
 	//
 	// If mutateState == true, the final block is replayed with h.replayBlock()
 
@@ -309,7 +352,7 @@ 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)
@@ -319,38 +362,42 @@ func (h *Handshaker) replayBlocks(proxyApp proxy.AppConns, appBlockHeight, store
 			return nil, err
 		}
 
-		h.nBlocks += 1
+		h.nBlocks++
 	}
 
 	if mutateState {
 		// sync the final block
-		return h.replayBlock(storeBlockHeight, proxyApp.Consensus())
+		state, err = h.replayBlock(state, storeBlockHeight, proxyApp.Consensus())
+		if err != nil {
+			return nil, err
+		}
+		appHash = state.AppHash
 	}
 
-	return appHash, h.checkAppHash(appHash)
+	return appHash, checkAppHash(state, appHash)
 }
 
 // ApplyBlock on the proxyApp with the last block.
-func (h *Handshaker) replayBlock(height int, proxyApp proxy.AppConnConsensus) ([]byte, error) {
-	mempool := types.MockMempool{}
-
-	var eventCache types.Fireable // nil
+func (h *Handshaker) replayBlock(state sm.State, height int64, proxyApp proxy.AppConnConsensus) (sm.State, error) {
 	block := h.store.LoadBlock(height)
 	meta := h.store.LoadBlockMeta(height)
 
-	if err := h.state.ApplyBlock(eventCache, proxyApp, block, meta.BlockID.PartsHeader, mempool); err != nil {
-		return nil, err
+	blockExec := sm.NewBlockExecutor(h.stateDB, h.logger, proxyApp, types.MockMempool{}, types.MockEvidencePool{})
+
+	var err error
+	state, err = blockExec.ApplyBlock(state, meta.BlockID, block)
+	if err != nil {
+		return sm.State{}, err
 	}
 
-	h.nBlocks += 1
+	h.nBlocks++
 
-	return h.state.AppHash, nil
+	return state, nil
 }
 
-func (h *Handshaker) checkAppHash(appHash []byte) error {
-	if !bytes.Equal(h.state.AppHash, appHash) {
-		panic(errors.New(cmn.Fmt("Tendermint state.AppHash does not match AppHash after replay. Got %X, expected %X", appHash, h.state.AppHash)).Error())
-		return nil
+func checkAppHash(state sm.State, appHash []byte) error {
+	if !bytes.Equal(state.AppHash, appHash) {
+		panic(fmt.Errorf("Tendermint state.AppHash does not match AppHash after replay. Got %X, expected %X", appHash, state.AppHash).Error())
 	}
 	return nil
 }
@@ -365,7 +412,10 @@ func newMockProxyApp(appHash []byte, abciResponses *sm.ABCIResponses) proxy.AppC
 		abciResponses: abciResponses,
 	})
 	cli, _ := clientCreator.NewABCIClient()
-	cli.Start()
+	err := cli.Start()
+	if err != nil {
+		panic(err)
+	}
 	return proxy.NewAppConnConsensus(cli)
 }
 
@@ -377,21 +427,17 @@ type mockProxyApp struct {
 	abciResponses *sm.ABCIResponses
 }
 
-func (mock *mockProxyApp) DeliverTx(tx []byte) abci.Result {
+func (mock *mockProxyApp) DeliverTx(tx []byte) abci.ResponseDeliverTx {
 	r := mock.abciResponses.DeliverTx[mock.txCount]
-	mock.txCount += 1
-	return abci.Result{
-		r.Code,
-		r.Data,
-		r.Log,
-	}
+	mock.txCount++
+	return *r
 }
 
-func (mock *mockProxyApp) EndBlock(height uint64) abci.ResponseEndBlock {
+func (mock *mockProxyApp) EndBlock(req abci.RequestEndBlock) abci.ResponseEndBlock {
 	mock.txCount = 0
-	return mock.abciResponses.EndBlock
+	return *mock.abciResponses.EndBlock
 }
 
-func (mock *mockProxyApp) Commit() abci.Result {
-	return abci.NewResultOK(mock.appHash, "")
+func (mock *mockProxyApp) Commit() abci.ResponseCommit {
+	return abci.ResponseCommit{Data: mock.appHash}
 }

consensus/replay_file.go

@@ -2,13 +2,15 @@ package consensus
 
 import (
 	"bufio"
-	"errors"
+	"context"
 	"fmt"
 	"io"
 	"os"
 	"strconv"
 	"strings"
 
+	"github.com/pkg/errors"
+
 	bc "github.com/tendermint/tendermint/blockchain"
 	cfg "github.com/tendermint/tendermint/config"
 	"github.com/tendermint/tendermint/proxy"
@@ -16,6 +18,12 @@ import (
 	"github.com/tendermint/tendermint/types"
 	cmn "github.com/tendermint/tmlibs/common"
 	dbm "github.com/tendermint/tmlibs/db"
+	"github.com/tendermint/tmlibs/log"
+)
+
+const (
+	// event bus subscriber
+	subscriber = "replay-file"
 )
 
 //--------------------------------------------------------
@@ -42,16 +50,23 @@ func (cs *ConsensusState) ReplayFile(file string, console bool) error {
 	cs.startForReplay()
 
 	// ensure all new step events are regenerated as expected
-	newStepCh := subscribeToEvent(cs.evsw, "replay-test", types.EventStringNewRoundStep(), 1)
+	newStepCh := make(chan interface{}, 1)
+
+	ctx := context.Background()
+	err := cs.eventBus.Subscribe(ctx, subscriber, types.EventQueryNewRoundStep, newStepCh)
+	if err != nil {
+		return errors.Errorf("failed to subscribe %s to %v", subscriber, types.EventQueryNewRoundStep)
+	}
+	defer cs.eventBus.Unsubscribe(ctx, subscriber, types.EventQueryNewRoundStep)
 
 	// just open the file for reading, no need to use wal
-	fp, err := os.OpenFile(file, os.O_RDONLY, 0666)
+	fp, err := os.OpenFile(file, os.O_RDONLY, 0600)
 	if err != nil {
 		return err
 	}
 
 	pb := newPlayback(file, fp, cs, cs.state.Copy())
-	defer pb.fp.Close()
+	defer pb.fp.Close() // nolint: errcheck
 
 	var nextN int // apply N msgs in a row
 	var msg *TimedWALMessage
@@ -72,9 +87,9 @@ func (cs *ConsensusState) ReplayFile(file string, console bool) error {
 		}
 
 		if nextN > 0 {
-			nextN -= 1
+			nextN--
 		}
-		pb.count += 1
+		pb.count++
 	}
 	return nil
 }
@@ -90,11 +105,11 @@ 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,
@@ -106,16 +121,18 @@ func newPlayback(fileName string, fp *os.File, cs *ConsensusState, genState *sm.
 
 // go back count steps by resetting the state and running (pb.count - count) steps
 func (pb *playback) replayReset(count int, newStepCh chan interface{}) error {
-
 	pb.cs.Stop()
 	pb.cs.Wait()
 
-	newCS := NewConsensusState(pb.cs.config, pb.genesisState.Copy(), pb.cs.proxyAppConn, pb.cs.blockStore, pb.cs.mempool)
-	newCS.SetEventSwitch(pb.cs.evsw)
+	newCS := NewConsensusState(pb.cs.config, pb.genesisState.Copy(), pb.cs.blockExec,
+		pb.cs.blockStore, pb.cs.mempool, pb.cs.evpool)
+	newCS.SetEventBus(pb.cs.eventBus)
 	newCS.startForReplay()
 
-	pb.fp.Close()
-	fp, err := os.OpenFile(pb.fileName, os.O_RDONLY, 0666)
+	if err := pb.fp.Close(); err != nil {
+		return err
+	}
+	fp, err := os.OpenFile(pb.fileName, os.O_RDONLY, 0600)
 	if err != nil {
 		return err
 	}
@@ -136,7 +153,7 @@ 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
 }
@@ -180,13 +197,12 @@ func (pb *playback) replayConsoleLoop() int {
 
 			if len(tokens) == 1 {
 				return 0
+			}
+			i, err := strconv.Atoi(tokens[1])
+			if err != nil {
+				fmt.Println("next takes an integer argument")
 			} else {
-				i, err := strconv.Atoi(tokens[1])
-				if err != nil {
-					fmt.Println("next takes an integer argument")
-				} else {
-					return i
-				}
+				return i
 			}
 
 		case "back":
@@ -196,10 +212,20 @@ func (pb *playback) replayConsoleLoop() int {
 			// NOTE: "back" is not supported in the state machine design,
 			// so we restart and replay up to
 
+			ctx := context.Background()
 			// ensure all new step events are regenerated as expected
-			newStepCh := subscribeToEvent(pb.cs.evsw, "replay-test", types.EventStringNewRoundStep(), 1)
+			newStepCh := make(chan interface{}, 1)
+
+			err := pb.cs.eventBus.Subscribe(ctx, subscriber, types.EventQueryNewRoundStep, newStepCh)
+			if err != nil {
+				cmn.Exit(fmt.Sprintf("failed to subscribe %s to %v", subscriber, types.EventQueryNewRoundStep))
+			}
+			defer pb.cs.eventBus.Unsubscribe(ctx, subscriber, types.EventQueryNewRoundStep)
+
 			if len(tokens) == 1 {
-				pb.replayReset(1, newStepCh)
+				if err := pb.replayReset(1, newStepCh); err != nil {
+					pb.cs.Logger.Error("Replay reset error", "err", err)
+				}
 			} else {
 				i, err := strconv.Atoi(tokens[1])
 				if err != nil {
@@ -207,7 +233,9 @@ func (pb *playback) replayConsoleLoop() int {
 				} else if i > pb.count {
 					fmt.Printf("argument to back must not be larger than the current count (%d)\n", pb.count)
 				} else {
-					pb.replayReset(i, newStepCh)
+					if err := pb.replayReset(i, newStepCh); err != nil {
+						pb.cs.Logger.Error("Replay reset error", "err", err)
+					}
 				}
 			}
 
@@ -251,33 +279,42 @@ 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))
-	_, err = proxyApp.Start()
+	proxyApp := proxy.NewAppConns(clientCreator,
+		NewHandshaker(stateDB, state, blockStore, gdoc.AppState()))
+	err = proxyApp.Start()
 	if err != nil {
 		cmn.Exit(cmn.Fmt("Error starting proxy app conns: %v", err))
 	}
 
-	// Make event switch
-	eventSwitch := types.NewEventSwitch()
-	if _, err := eventSwitch.Start(); err != nil {
-		cmn.Exit(cmn.Fmt("Failed to start event switch: %v", err))
+	eventBus := types.NewEventBus()
+	if err := eventBus.Start(); err != nil {
+		cmn.Exit(cmn.Fmt("Failed to start event bus: %v", err))
 	}
 
-	consensusState := NewConsensusState(csConfig, state.Copy(), proxyApp.Consensus(), blockStore, types.MockMempool{})
+	mempool, evpool := types.MockMempool{}, types.MockEvidencePool{}
+	blockExec := sm.NewBlockExecutor(stateDB, log.TestingLogger(), proxyApp.Consensus(), mempool, evpool)
 
-	consensusState.SetEventSwitch(eventSwitch)
+	consensusState := NewConsensusState(csConfig, state.Copy(), blockExec,
+		blockStore, mempool, evpool)
+
+	consensusState.SetEventBus(eventBus)
 	return consensusState
 }

consensus/replay_test.go

@@ -2,19 +2,23 @@ package consensus
 
 import (
 	"bytes"
+	"context"
 	"errors"
 	"fmt"
 	"io"
 	"io/ioutil"
 	"os"
 	"path"
+	"runtime"
 	"testing"
 	"time"
 
-	"github.com/tendermint/abci/example/dummy"
+	"github.com/stretchr/testify/require"
+
+	"github.com/tendermint/abci/example/kvstore"
 	abci "github.com/tendermint/abci/types"
-	crypto "github.com/tendermint/go-crypto"
-	wire "github.com/tendermint/go-wire"
+	"github.com/tendermint/go-crypto"
+	auto "github.com/tendermint/tmlibs/autofile"
 	cmn "github.com/tendermint/tmlibs/common"
 	dbm "github.com/tendermint/tmlibs/db"
 
@@ -22,11 +26,14 @@ import (
 	"github.com/tendermint/tendermint/proxy"
 	sm "github.com/tendermint/tendermint/state"
 	"github.com/tendermint/tendermint/types"
+	pvm "github.com/tendermint/tendermint/types/priv_validator"
 	"github.com/tendermint/tmlibs/log"
 )
 
+var consensusReplayConfig *cfg.Config
+
 func init() {
-	config = ResetConfig("consensus_replay_test")
+	consensusReplayConfig = ResetConfig("consensus_replay_test")
 }
 
 // These tests ensure we can always recover from failure at any part of the consensus process.
@@ -37,14 +44,6 @@ func init() {
 // the `Handshake Tests` are for failures in applying the block.
 // With the help of the WAL, we can recover from it all!
 
-// 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, and the stepChanges may need to be adjusted
-// after running it (eg. sometimes small_block2 will have 5 block parts, sometimes 6).
-// 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
 
@@ -52,236 +51,216 @@ var data_dir = path.Join(cmn.GoPath(), "src/github.com/tendermint/tendermint/con
 // and which ones we need the wal for - then we'd also be able to only flush the
 // wal writer when we need to, instead of with every message.
 
-// the priv validator changes step at these lines for a block with 1 val and 1 part
-var baseStepChanges = []int{3, 6, 8}
+func startNewConsensusStateAndWaitForBlock(t *testing.T, lastBlockHeight int64, blockDB dbm.DB, stateDB dbm.DB) {
+	logger := log.TestingLogger()
+	state, _ := sm.LoadStateFromDBOrGenesisFile(stateDB, consensusReplayConfig.GenesisFile())
+	privValidator := loadPrivValidator(consensusReplayConfig)
+	cs := newConsensusStateWithConfigAndBlockStore(consensusReplayConfig, state, privValidator, kvstore.NewKVStoreApplication(), blockDB)
+	cs.SetLogger(logger)
 
-// test recovery from each line in each testCase
-var testCases = []*testCase{
-	newTestCase("empty_block", baseStepChanges),   // empty block (has 1 block part)
-	newTestCase("small_block1", baseStepChanges),  // small block with txs in 1 block part
-	newTestCase("small_block2", []int{3, 12, 14}), // small block with txs across 6 smaller block parts
-}
+	bytes, _ := ioutil.ReadFile(cs.config.WalFile())
+	// fmt.Printf("====== WAL: \n\r%s\n", bytes)
+	t.Logf("====== WAL: \n\r%X\n", bytes)
 
-type testCase struct {
-	name    string
-	log     []byte       //full cs wal
-	stepMap map[int]int8 // map lines of log to privval step
+	err := cs.Start()
+	require.NoError(t, err)
+	defer cs.Stop()
 
-	proposeLine   int
-	prevoteLine   int
-	precommitLine int
-}
-
-func newTestCase(name string, stepChanges []int) *testCase {
-	if len(stepChanges) != 3 {
-		panic(cmn.Fmt("a full wal has 3 step changes! Got array %v", stepChanges))
-	}
-	return &testCase{
-		name:    name,
-		log:     readWAL(path.Join(data_dir, name+".cswal")),
-		stepMap: newMapFromChanges(stepChanges),
-
-		proposeLine:   stepChanges[0],
-		prevoteLine:   stepChanges[1],
-		precommitLine: stepChanges[2],
-	}
-}
-
-func newMapFromChanges(changes []int) map[int]int8 {
-	changes = append(changes, changes[2]+1) // so we add the last step change to the map
-	m := make(map[int]int8)
-	var count int
-	for changeNum, nextChange := range changes {
-		for ; count < nextChange; count++ {
-			m[count] = int8(changeNum)
-		}
-	}
-	return m
-}
-
-func readWAL(p string) []byte {
-	b, err := ioutil.ReadFile(p)
-	if err != nil {
-		panic(err)
-	}
-	return b
-}
-
-func writeWAL(walMsgs []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)
-	if err != nil {
-		panic(fmt.Errorf("failed to write to temp WAL file: %v", err))
-	}
-	if err := walFile.Close(); err != nil {
-		panic(fmt.Errorf("failed to close temp WAL file: %v", err))
-	}
-	return walFile.Name()
-}
-
-func waitForBlock(newBlockCh chan interface{}, thisCase *testCase, i int) {
-	after := time.After(time.Second * 10)
+	// This is just a signal that we haven't halted; its not something contained
+	// in the WAL itself. Assuming the consensus state is running, replay of any
+	// WAL, including the empty one, should eventually be followed by a new
+	// block, or else something is wrong.
+	newBlockCh := make(chan interface{}, 1)
+	err = cs.eventBus.Subscribe(context.Background(), testSubscriber, types.EventQueryNewBlock, newBlockCh)
+	require.NoError(t, err)
 	select {
 	case <-newBlockCh:
-	case <-after:
-		panic(cmn.Fmt("Timed out waiting for new block for case '%s' line %d", thisCase.name, i))
+	case <-time.After(60 * time.Second):
+		t.Fatalf("Timed out waiting for new block (see trace above)")
 	}
 }
 
-func runReplayTest(t *testing.T, cs *ConsensusState, walFile string, newBlockCh chan interface{},
-	thisCase *testCase, i int) {
-
-	cs.config.SetWalFile(walFile)
-	started, err := cs.Start()
-	if err != nil {
-		t.Fatalf("Cannot start consensus: %v", err)
-	}
-	if !started {
-		t.Error("Consensus did not start")
-	}
-	// Wait to make a new block.
-	// This is just a signal that we haven't halted; its not something contained in the WAL itself.
-	// Assuming the consensus state is running, replay of any WAL, including the empty one,
-	// should eventually be followed by a new block, or else something is wrong
-	waitForBlock(newBlockCh, thisCase, i)
-	cs.evsw.Stop()
-	cs.Stop()
-LOOP:
-	for {
+func sendTxs(cs *ConsensusState, ctx context.Context) {
+	for i := 0; i < 256; i++ {
 		select {
-		case <-newBlockCh:
+		case <-ctx.Done():
+			return
 		default:
-			break LOOP
-		}
-	}
-	cs.Wait()
-}
-
-func toPV(pv types.PrivValidator) *types.PrivValidatorFS {
-	return pv.(*types.PrivValidatorFS)
-}
-
-func setupReplayTest(t *testing.T, thisCase *testCase, nLines int, crashAfter bool) (*ConsensusState, chan interface{}, []byte, string) {
-	t.Log("-------------------------------------")
-	t.Logf("Starting replay test %v (of %d lines of WAL). Crash after = %v", thisCase.name, nLines, crashAfter)
-
-	lineStep := nLines
-	if crashAfter {
-		lineStep -= 1
-	}
-
-	split := bytes.Split(thisCase.log, walSeparator)
-	lastMsg := split[nLines]
-
-	// we write those lines up to (not including) one with the signature
-	b := bytes.Join(split[:nLines], walSeparator)
-	b = append(b, walSeparator...)
-	walFile := writeWAL(b)
-
-	cs := fixedConsensusStateDummy()
-
-	// set the last step according to when we crashed vs the wal
-	toPV(cs.privValidator).LastHeight = 1 // first block
-	toPV(cs.privValidator).LastStep = thisCase.stepMap[lineStep]
-
-	t.Logf("[WARN] setupReplayTest LastStep=%v", toPV(cs.privValidator).LastStep)
-
-	newBlockCh := subscribeToEvent(cs.evsw, "tester", types.EventStringNewBlock(), 1)
-
-	return cs, newBlockCh, lastMsg, walFile
-}
-
-func readTimedWALMessage(t *testing.T, rawMsg []byte) TimedWALMessage {
-	b := bytes.NewBuffer(rawMsg)
-	// because rawMsg does not contain a separator and WALDecoder#Decode expects it
-	_, err := b.Write(walSeparator)
-	if err != nil {
-		t.Fatal(err)
-	}
-	dec := NewWALDecoder(b)
-	msg, err := dec.Decode()
-	if err != nil {
-		t.Fatalf("Error reading json data: %v", err)
-	}
-	return *msg
-}
-
-//-----------------------------------------------
-// Test the log at every iteration, and set the privVal last step
-// as if the log was written after signing, before the crash
-
-func TestWALCrashAfterWrite(t *testing.T) {
-	for _, thisCase := range testCases {
-		splitSize := bytes.Count(thisCase.log, walSeparator)
-		for i := 0; i < splitSize-1; i++ {
-			t.Run(fmt.Sprintf("%s:%d", thisCase.name, i), func(t *testing.T) {
-				cs, newBlockCh, _, walFile := setupReplayTest(t, thisCase, i+1, true)
-				cs.config.TimeoutPropose = 100
-				runReplayTest(t, cs, walFile, newBlockCh, thisCase, i+1)
-				// cleanup
-				os.Remove(walFile)
-			})
+			tx := []byte{byte(i)}
+			cs.mempool.CheckTx(tx, nil)
+			i++
 		}
 	}
 }
 
-//-----------------------------------------------
-// Test the log as if we crashed after signing but before writing.
-// This relies on privValidator.LastSignature being set
+// TestWALCrash uses crashing WAL to test we can recover from any WAL failure.
+func TestWALCrash(t *testing.T) {
+	testCases := []struct {
+		name         string
+		initFn       func(dbm.DB, *ConsensusState, context.Context)
+		heightToStop int64
+	}{
+		{"empty block",
+			func(stateDB dbm.DB, cs *ConsensusState, ctx context.Context) {},
+			1},
+		{"block with a smaller part size",
+			func(stateDB dbm.DB, cs *ConsensusState, ctx context.Context) {
+				// XXX: is there a better way to change BlockPartSizeBytes?
+				cs.state.ConsensusParams.BlockPartSizeBytes = 512
+				sm.SaveState(stateDB, cs.state)
+				go sendTxs(cs, ctx)
+			},
+			1},
+		{"many non-empty blocks",
+			func(stateDB dbm.DB, cs *ConsensusState, ctx context.Context) {
+				go sendTxs(cs, ctx)
+			},
+			3},
+	}
 
-func TestWALCrashBeforeWritePropose(t *testing.T) {
-	for _, thisCase := range testCases {
-		lineNum := thisCase.proposeLine
-		t.Run(fmt.Sprintf("%s:%d", thisCase.name, lineNum), func(t *testing.T) {
-			// setup replay test where last message is a proposal
-			cs, newBlockCh, proposalMsg, walFile := setupReplayTest(t, thisCase, lineNum, false)
-			cs.config.TimeoutPropose = 100
-			msg := readTimedWALMessage(t, proposalMsg)
-			proposal := msg.Msg.(msgInfo).Msg.(*ProposalMessage)
-			// Set LastSig
-			toPV(cs.privValidator).LastSignBytes = types.SignBytes(cs.state.ChainID, proposal.Proposal)
-			toPV(cs.privValidator).LastSignature = proposal.Proposal.Signature
-			runReplayTest(t, cs, walFile, newBlockCh, thisCase, lineNum)
-			// cleanup
-			os.Remove(walFile)
+	for _, tc := range testCases {
+		t.Run(tc.name, func(t *testing.T) {
+			crashWALandCheckLiveness(t, tc.initFn, tc.heightToStop)
 		})
 	}
 }
 
-func TestWALCrashBeforeWritePrevote(t *testing.T) {
-	for _, thisCase := range testCases {
-		testReplayCrashBeforeWriteVote(t, thisCase, thisCase.prevoteLine, types.EventStringCompleteProposal())
+func crashWALandCheckLiveness(t *testing.T, initFn func(dbm.DB, *ConsensusState, context.Context), heightToStop int64) {
+	walPaniced := make(chan error)
+	crashingWal := &crashingWAL{panicCh: walPaniced, heightToStop: heightToStop}
+
+	i := 1
+LOOP:
+	for {
+		// fmt.Printf("====== LOOP %d\n", i)
+		t.Logf("====== LOOP %d\n", i)
+
+		// create consensus state from a clean slate
+		logger := log.NewNopLogger()
+		stateDB := dbm.NewMemDB()
+		state, _ := sm.MakeGenesisStateFromFile(consensusReplayConfig.GenesisFile())
+		privValidator := loadPrivValidator(consensusReplayConfig)
+		blockDB := dbm.NewMemDB()
+		cs := newConsensusStateWithConfigAndBlockStore(consensusReplayConfig, state, privValidator, kvstore.NewKVStoreApplication(), blockDB)
+		cs.SetLogger(logger)
+
+		// start sending transactions
+		ctx, cancel := context.WithCancel(context.Background())
+		initFn(stateDB, cs, ctx)
+
+		// clean up WAL file from the previous iteration
+		walFile := cs.config.WalFile()
+		os.Remove(walFile)
+
+		// set crashing WAL
+		csWal, err := cs.OpenWAL(walFile)
+		require.NoError(t, err)
+		crashingWal.next = csWal
+		// reset the message counter
+		crashingWal.msgIndex = 1
+		cs.wal = crashingWal
+
+		// start consensus state
+		err = cs.Start()
+		require.NoError(t, err)
+
+		i++
+
+		select {
+		case err := <-walPaniced:
+			t.Logf("WAL paniced: %v", err)
+
+			// make sure we can make blocks after a crash
+			startNewConsensusStateAndWaitForBlock(t, cs.Height, blockDB, stateDB)
+
+			// stop consensus state and transactions sender (initFn)
+			cs.Stop()
+			cancel()
+
+			// if we reached the required height, exit
+			if _, ok := err.(ReachedHeightToStopError); ok {
+				break LOOP
+			}
+		case <-time.After(10 * time.Second):
+			t.Fatal("WAL did not panic for 10 seconds (check the log)")
+		}
 	}
 }
 
-func TestWALCrashBeforeWritePrecommit(t *testing.T) {
-	for _, thisCase := range testCases {
-		testReplayCrashBeforeWriteVote(t, thisCase, thisCase.precommitLine, types.EventStringPolka())
+// crashingWAL is a WAL which crashes or rather simulates a crash during Save
+// (before and after). It remembers a message for which we last panicked
+// (lastPanicedForMsgIndex), so we don't panic for it in subsequent iterations.
+type crashingWAL struct {
+	next         WAL
+	panicCh      chan error
+	heightToStop int64
+
+	msgIndex               int // current message index
+	lastPanicedForMsgIndex int // last message for which we panicked
+}
+
+// WALWriteError indicates a WAL crash.
+type WALWriteError struct {
+	msg string
+}
+
+func (e WALWriteError) Error() string {
+	return e.msg
+}
+
+// ReachedHeightToStopError indicates we've reached the required consensus
+// height and may exit.
+type ReachedHeightToStopError struct {
+	height int64
+}
+
+func (e ReachedHeightToStopError) Error() string {
+	return fmt.Sprintf("reached height to stop %d", e.height)
+}
+
+// Save simulate WAL's crashing by sending an error to the panicCh and then
+// exiting the cs.receiveRoutine.
+func (w *crashingWAL) Save(m WALMessage) {
+	if endMsg, ok := m.(EndHeightMessage); ok {
+		if endMsg.Height == w.heightToStop {
+			w.panicCh <- ReachedHeightToStopError{endMsg.Height}
+			runtime.Goexit()
+		} else {
+			w.next.Save(m)
+		}
+		return
+	}
+
+	if w.msgIndex > w.lastPanicedForMsgIndex {
+		w.lastPanicedForMsgIndex = w.msgIndex
+		_, file, line, _ := runtime.Caller(1)
+		w.panicCh <- WALWriteError{fmt.Sprintf("failed to write %T to WAL (fileline: %s:%d)", m, file, line)}
+		runtime.Goexit()
+	} else {
+		w.msgIndex++
+		w.next.Save(m)
 	}
 }
 
-func testReplayCrashBeforeWriteVote(t *testing.T, thisCase *testCase, lineNum int, eventString string) {
-	// setup replay test where last message is a vote
-	cs, newBlockCh, voteMsg, walFile := setupReplayTest(t, thisCase, lineNum, false)
-	types.AddListenerForEvent(cs.evsw, "tester", eventString, func(data types.TMEventData) {
-		msg := readTimedWALMessage(t, voteMsg)
-		vote := msg.Msg.(msgInfo).Msg.(*VoteMessage)
-		// Set LastSig
-		toPV(cs.privValidator).LastSignBytes = types.SignBytes(cs.state.ChainID, vote.Vote)
-		toPV(cs.privValidator).LastSignature = vote.Vote.Signature
-	})
-	runReplayTest(t, cs, walFile, newBlockCh, thisCase, lineNum)
+func (w *crashingWAL) Group() *auto.Group { return w.next.Group() }
+func (w *crashingWAL) SearchForEndHeight(height int64, options *WALSearchOptions) (gr *auto.GroupReader, found bool, err error) {
+	return w.next.SearchForEndHeight(height, options)
 }
 
+func (w *crashingWAL) Start() error { return w.next.Start() }
+func (w *crashingWAL) Stop() error  { return w.next.Stop() }
+func (w *crashingWAL) Wait()        { w.next.Wait() }
+
 //------------------------------------------------------------------------------------------
 // Handshake Tests
 
+const (
+	NUM_BLOCKS = 6
+)
+
 var (
-	NUM_BLOCKS = 6 // number of blocks in the test_data/many_blocks.cswal
-	mempool    = types.MockMempool{}
+	mempool = types.MockMempool{}
+	evpool  = types.MockEvidencePool{}
 )
 
 //---------------------------------------
@@ -320,57 +299,75 @@ func TestHandshakeReplayNone(t *testing.T) {
 	}
 }
 
+func tempWALWithData(data []byte) string {
+	walFile, err := ioutil.TempFile("", "wal")
+	if err != nil {
+		panic(fmt.Errorf("failed to create temp WAL file: %v", err))
+	}
+	_, err = walFile.Write(data)
+	if err != nil {
+		panic(fmt.Errorf("failed to write to temp WAL file: %v", err))
+	}
+	if err := walFile.Close(); err != nil {
+		panic(fmt.Errorf("failed to close temp WAL file: %v", err))
+	}
+	return walFile.Name()
+}
+
 // Make some blocks. Start a fresh app and apply nBlocks blocks. Then restart the app and sync it up with the remaining blocks
 func testHandshakeReplay(t *testing.T, nBlocks int, mode uint) {
 	config := 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 := pvm.LoadFilePV(config.PrivValidatorFile())
 
 	wal, err := NewWAL(walFile, false)
 	if err != nil {
 		t.Fatal(err)
 	}
 	wal.SetLogger(log.TestingLogger())
-	if _, err := wal.Start(); err != nil {
+	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)
+	handshaker := NewHandshaker(stateDB, state, store, nil)
 	proxyApp := proxy.NewAppConns(clientCreator2, handshaker)
-	if _, err := proxyApp.Start(); err != nil {
+	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 +382,9 @@ func testHandshakeReplay(t *testing.T, nBlocks int, mode uint) {
 
 	expectedBlocksToSync := NUM_BLOCKS - nBlocks
 	if nBlocks == NUM_BLOCKS && mode > 0 {
-		expectedBlocksToSync += 1
+		expectedBlocksToSync++
 	} else if nBlocks > 0 && mode == 1 {
-		expectedBlocksToSync += 1
+		expectedBlocksToSync++
 	}
 
 	if handshaker.NBlocks() != expectedBlocksToSync {
@@ -395,105 +392,115 @@ 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(nil, proxyApp.Consensus(), blk, blk.MakePartSet(testPartSize).Header(), mempool)
+func applyBlock(stateDB dbm.DB, st sm.State, blk *types.Block, proxyApp proxy.AppConns) sm.State {
+	testPartSize := st.ConsensusParams.BlockPartSizeBytes
+	blockExec := sm.NewBlockExecutor(stateDB, log.TestingLogger(), proxyApp.Consensus(), mempool, evpool)
+
+	blkID := types.BlockID{blk.Hash(), blk.MakePartSet(testPartSize).Header()}
+	newState, err := blockExec.ApplyBlock(st, blkID, blk)
 	if err != nil {
 		panic(err)
 	}
+	return newState
 }
 
-func buildAppStateFromChain(proxyApp proxy.AppConns,
-	state *sm.State, chain []*types.Block, nBlocks int, mode uint) {
+func buildAppStateFromChain(proxyApp proxy.AppConns, stateDB dbm.DB,
+	state sm.State, chain []*types.Block, nBlocks int, mode uint) {
 	// start a new app without handshake, play nBlocks blocks
-	if _, err := proxyApp.Start(); err != nil {
+	if err := proxyApp.Start(); err != nil {
+		panic(err)
+	}
+	defer proxyApp.Stop()
+
+	// TODO: get the genesis bytes (https://github.com/tendermint/tendermint/issues/1224)
+	var genesisBytes []byte
+	validators := types.TM2PB.Validators(state.Validators)
+	if _, err := proxyApp.Consensus().InitChainSync(abci.RequestInitChain{validators, genesisBytes}); err != nil {
 		panic(err)
 	}
 
-	validators := types.TM2PB.Validators(state.Validators)
-	proxyApp.Consensus().InitChainSync(abci.RequestInitChain{validators})
-
-	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 {
+	if err := proxyApp.Start(); err != nil {
 		panic(err)
 	}
 	defer proxyApp.Stop()
 
+	// TODO: get the genesis bytes (https://github.com/tendermint/tendermint/issues/1224)
+	var genesisBytes []byte
 	validators := types.TM2PB.Validators(state.Validators)
-	proxyApp.Consensus().InitChainSync(abci.RequestInitChain{validators})
-
-	var latestAppHash []byte
+	if _, err := proxyApp.Consensus().InitChainSync(abci.RequestInitChain{validators, genesisBytes}); err != nil {
+		panic(err)
+	}
 
 	switch mode {
 	case 0:
 		// sync right up
 		for _, block := range chain {
-			applyBlock(state, block, proxyApp)
+			state = applyBlock(stateDB, state, block, proxyApp)
 		}
 
-		latestAppHash = state.AppHash
 	case 1, 2:
 		// sync up to the penultimate as if we stored the block.
 		// whether we commit or not depends on the appHash
 		for _, block := range chain[:len(chain)-1] {
-			applyBlock(state, block, proxyApp)
+			state = applyBlock(stateDB, state, block, proxyApp)
 		}
 
 		// apply the final block to a state copy so we can
 		// get the right next appHash but keep the state back
-		stateCopy := state.Copy()
-		applyBlock(stateCopy, chain[len(chain)-1], proxyApp)
-		latestAppHash = stateCopy.AppHash
+		applyBlock(stateDB, state, chain[len(chain)-1], proxyApp)
 	}
 
-	return latestAppHash
+	return state
 }
 
 //--------------------------
 // utils for making blocks
 
-func makeBlockchainFromWAL(wal *WAL) ([]*types.Block, []*types.Commit, error) {
+func makeBlockchainFromWAL(wal WAL) ([]*types.Block, []*types.Commit, error) {
 	// Search for height marker
-	gr, found, err := wal.SearchForEndHeight(0)
+	gr, found, err := wal.SearchForEndHeight(0, &WALSearchOptions{})
 	if err != nil {
 		return nil, nil, err
 	}
 	if !found {
 		return nil, nil, errors.New(cmn.Fmt("WAL does not contain height %d.", 1))
 	}
-	defer gr.Close()
+	defer gr.Close() // nolint: errcheck
 
 	// log.Notice("Build a blockchain by reading from the WAL")
 
-	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()
@@ -509,42 +516,60 @@ 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, false)
 			if err != nil {
 				return nil, nil, err
 			}
 		case *types.Vote:
 			if p.Type == types.VoteTypePrecommit {
-				commit := &types.Commit{
+				thisBlockCommit = &types.Commit{
 					BlockID:    p.BlockID,
 					Precommits: []*types.Vote{p},
 				}
-				commits = append(commits, commit)
 			}
 		}
 	}
 	// grab the last block too
-	var n int
-	block := wire.ReadBinary(&types.Block{}, blockParts.GetReader(), 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:
@@ -556,19 +581,19 @@ 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
 }
 
 //----------------------------------
@@ -586,21 +611,21 @@ func NewMockBlockStore(config *cfg.Config, params types.ConsensusParams) *mockBl
 	return &mockBlockStore{config, params, nil, nil}
 }
 
-func (bs *mockBlockStore) Height() int                       { return len(bs.chain) }
-func (bs *mockBlockStore) LoadBlock(height int) *types.Block { return bs.chain[height-1] }
-func (bs *mockBlockStore) LoadBlockMeta(height int) *types.BlockMeta {
+func (bs *mockBlockStore) Height() int64                       { return int64(len(bs.chain)) }
+func (bs *mockBlockStore) LoadBlock(height int64) *types.Block { return bs.chain[height-1] }
+func (bs *mockBlockStore) LoadBlockMeta(height int64) *types.BlockMeta {
 	block := bs.chain[height-1]
 	return &types.BlockMeta{
 		BlockID: types.BlockID{block.Hash(), block.MakePartSet(bs.params.BlockPartSizeBytes).Header()},
 		Header:  block.Header,
 	}
 }
-func (bs *mockBlockStore) LoadBlockPart(height int, index int) *types.Part { return nil }
+func (bs *mockBlockStore) LoadBlockPart(height int64, index int) *types.Part { return nil }
 func (bs *mockBlockStore) SaveBlock(block *types.Block, blockParts *types.PartSet, seenCommit *types.Commit) {
 }
-func (bs *mockBlockStore) LoadBlockCommit(height int) *types.Commit {
+func (bs *mockBlockStore) LoadBlockCommit(height int64) *types.Commit {
 	return bs.commits[height-1]
 }
-func (bs *mockBlockStore) LoadSeenCommit(height int) *types.Commit {
+func (bs *mockBlockStore) LoadSeenCommit(height int64) *types.Commit {
 	return bs.commits[height-1]
 }

consensus/state_test.go

@@ -2,6 +2,7 @@ package consensus
 
 import (
 	"bytes"
+	"context"
 	"fmt"
 	"testing"
 	"time"
@@ -9,6 +10,8 @@ import (
 	cstypes "github.com/tendermint/tendermint/consensus/types"
 	"github.com/tendermint/tendermint/types"
 	cmn "github.com/tendermint/tmlibs/common"
+	"github.com/tendermint/tmlibs/log"
+	tmpubsub "github.com/tendermint/tmlibs/pubsub"
 )
 
 func init() {
@@ -52,12 +55,12 @@ x * TestHalt1 - if we see +2/3 precommits after timing out into new round, we sh
 //----------------------------------------------------------------------------------------------------
 // ProposeSuite
 
-func TestProposerSelection0(t *testing.T) {
+func TestStateProposerSelection0(t *testing.T) {
 	cs1, vss := randConsensusState(4)
 	height, round := cs1.Height, cs1.Round
 
-	newRoundCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringNewRound(), 1)
-	proposalCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringCompleteProposal(), 1)
+	newRoundCh := subscribe(cs1.eventBus, types.EventQueryNewRound)
+	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
 
 	startTestRound(cs1, height, round)
 
@@ -86,10 +89,10 @@ 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 := subscribeToEvent(cs1.evsw, "tester", types.EventStringNewRound(), 1)
+	newRoundCh := subscribe(cs1.eventBus, types.EventQueryNewRound)
 
 	// this time we jump in at round 2
 	incrementRound(vss[1:]...)
@@ -115,13 +118,13 @@ func TestProposerSelection2(t *testing.T) {
 }
 
 // a non-validator should timeout into the prevote round
-func TestEnterProposeNoPrivValidator(t *testing.T) {
+func TestStateEnterProposeNoPrivValidator(t *testing.T) {
 	cs, _ := randConsensusState(1)
 	cs.SetPrivValidator(nil)
 	height, round := cs.Height, cs.Round
 
 	// Listen for propose timeout event
-	timeoutCh := subscribeToEvent(cs.evsw, "tester", types.EventStringTimeoutPropose(), 1)
+	timeoutCh := subscribe(cs.eventBus, types.EventQueryTimeoutPropose)
 
 	startTestRound(cs, height, round)
 
@@ -140,14 +143,14 @@ func TestEnterProposeNoPrivValidator(t *testing.T) {
 }
 
 // a validator should not timeout of the prevote round (TODO: unless the block is really big!)
-func TestEnterProposeYesPrivValidator(t *testing.T) {
+func TestStateEnterProposeYesPrivValidator(t *testing.T) {
 	cs, _ := randConsensusState(1)
 	height, round := cs.Height, cs.Round
 
 	// Listen for propose timeout event
 
-	timeoutCh := subscribeToEvent(cs.evsw, "tester", types.EventStringTimeoutPropose(), 1)
-	proposalCh := subscribeToEvent(cs.evsw, "tester", types.EventStringCompleteProposal(), 1)
+	timeoutCh := subscribe(cs.eventBus, types.EventQueryTimeoutPropose)
+	proposalCh := subscribe(cs.eventBus, types.EventQueryCompleteProposal)
 
 	cs.enterNewRound(height, round)
 	cs.startRoutines(3)
@@ -176,15 +179,15 @@ func TestEnterProposeYesPrivValidator(t *testing.T) {
 	}
 }
 
-func TestBadProposal(t *testing.T) {
+func TestStateBadProposal(t *testing.T) {
 	cs1, vss := randConsensusState(2)
 	height, round := cs1.Height, cs1.Round
 	vs2 := vss[1]
 
-	partSize := cs1.state.Params.BlockPartSizeBytes
+	partSize := cs1.state.ConsensusParams.BlockPartSizeBytes
 
-	proposalCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringCompleteProposal(), 1)
-	voteCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringVote(), 1)
+	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
+	voteCh := subscribe(cs1.eventBus, types.EventQueryVote)
 
 	propBlock, _ := cs1.createProposalBlock() //changeProposer(t, cs1, vs2)
 
@@ -201,12 +204,14 @@ func TestBadProposal(t *testing.T) {
 	propBlock.AppHash = stateHash
 	propBlockParts := propBlock.MakePartSet(partSize)
 	proposal := types.NewProposal(vs2.Height, round, propBlockParts.Header(), -1, types.BlockID{})
-	if err := vs2.SignProposal(config.ChainID, proposal); err != nil {
+	if err := vs2.SignProposal(config.ChainID(), proposal); err != nil {
 		t.Fatal("failed to sign bad proposal", err)
 	}
 
 	// set the proposal block
-	cs1.SetProposalAndBlock(proposal, propBlock, propBlockParts, "some peer")
+	if err := cs1.SetProposalAndBlock(proposal, propBlock, propBlockParts, "some peer"); err != nil {
+		t.Fatal(err)
+	}
 
 	// start the machine
 	startTestRound(cs1, height, round)
@@ -234,13 +239,21 @@ func TestBadProposal(t *testing.T) {
 // FullRoundSuite
 
 // propose, prevote, and precommit a block
-func TestFullRound1(t *testing.T) {
+func TestStateFullRound1(t *testing.T) {
 	cs, vss := randConsensusState(1)
 	height, round := cs.Height, cs.Round
 
-	voteCh := subscribeToEvent(cs.evsw, "tester", types.EventStringVote(), 0)
-	propCh := subscribeToEvent(cs.evsw, "tester", types.EventStringCompleteProposal(), 1)
-	newRoundCh := subscribeToEvent(cs.evsw, "tester", types.EventStringNewRound(), 1)
+	// NOTE: buffer capacity of 0 ensures we can validate prevote and last commit
+	// before consensus can move to the next height (and cause a race condition)
+	cs.eventBus.Stop()
+	eventBus := types.NewEventBusWithBufferCapacity(0)
+	eventBus.SetLogger(log.TestingLogger().With("module", "events"))
+	cs.SetEventBus(eventBus)
+	eventBus.Start()
+
+	voteCh := subscribe(cs.eventBus, types.EventQueryVote)
+	propCh := subscribe(cs.eventBus, types.EventQueryCompleteProposal)
+	newRoundCh := subscribe(cs.eventBus, types.EventQueryNewRound)
 
 	startTestRound(cs, height, round)
 
@@ -248,11 +261,9 @@ func TestFullRound1(t *testing.T) {
 
 	// grab proposal
 	re := <-propCh
-	propBlockHash := re.(types.TMEventData).Unwrap().(types.EventDataRoundState).RoundState.(*cstypes.RoundState).ProposalBlock.Hash()
+	propBlockHash := re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState).ProposalBlock.Hash()
 
 	<-voteCh // wait for prevote
-	// NOTE: voteChan cap of 0 ensures we can complete this
-	// before consensus can move to the next height (and cause a race condition)
 	validatePrevote(t, cs, round, vss[0], propBlockHash)
 
 	<-voteCh // wait for precommit
@@ -264,11 +275,11 @@ func TestFullRound1(t *testing.T) {
 }
 
 // nil is proposed, so prevote and precommit nil
-func TestFullRoundNil(t *testing.T) {
+func TestStateFullRoundNil(t *testing.T) {
 	cs, vss := randConsensusState(1)
 	height, round := cs.Height, cs.Round
 
-	voteCh := subscribeToEvent(cs.evsw, "tester", types.EventStringVote(), 1)
+	voteCh := subscribe(cs.eventBus, types.EventQueryVote)
 
 	cs.enterPrevote(height, round)
 	cs.startRoutines(4)
@@ -282,13 +293,13 @@ func TestFullRoundNil(t *testing.T) {
 
 // run through propose, prevote, precommit commit with two validators
 // where the first validator has to wait for votes from the second
-func TestFullRound2(t *testing.T) {
+func TestStateFullRound2(t *testing.T) {
 	cs1, vss := randConsensusState(2)
 	vs2 := vss[1]
 	height, round := cs1.Height, cs1.Round
 
-	voteCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringVote(), 1)
-	newBlockCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringNewBlock(), 1)
+	voteCh := subscribe(cs1.eventBus, types.EventQueryVote)
+	newBlockCh := subscribe(cs1.eventBus, types.EventQueryNewBlock)
 
 	// start round and wait for propose and prevote
 	startTestRound(cs1, height, round)
@@ -323,18 +334,18 @@ func TestFullRound2(t *testing.T) {
 
 // two validators, 4 rounds.
 // two vals take turns proposing. val1 locks on first one, precommits nil on everything else
-func TestLockNoPOL(t *testing.T) {
+func TestStateLockNoPOL(t *testing.T) {
 	cs1, vss := randConsensusState(2)
 	vs2 := vss[1]
 	height := cs1.Height
 
-	partSize := cs1.state.Params.BlockPartSizeBytes
+	partSize := cs1.state.ConsensusParams.BlockPartSizeBytes
 
-	timeoutProposeCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringTimeoutPropose(), 1)
-	timeoutWaitCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringTimeoutWait(), 1)
-	voteCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringVote(), 1)
-	proposalCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringCompleteProposal(), 1)
-	newRoundCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringNewRound(), 1)
+	timeoutProposeCh := subscribe(cs1.eventBus, types.EventQueryTimeoutPropose)
+	timeoutWaitCh := subscribe(cs1.eventBus, types.EventQueryTimeoutWait)
+	voteCh := subscribe(cs1.eventBus, types.EventQueryVote)
+	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
+	newRoundCh := subscribe(cs1.eventBus, types.EventQueryNewRound)
 
 	/*
 		Round1 (cs1, B) // B B // B B2
@@ -345,7 +356,7 @@ func TestLockNoPOL(t *testing.T) {
 	cs1.startRoutines(0)
 
 	re := <-proposalCh
-	rs := re.(types.TMEventData).Unwrap().(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
+	rs := re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 	theBlockHash := rs.ProposalBlock.Hash()
 
 	<-voteCh // prevote
@@ -385,7 +396,7 @@ func TestLockNoPOL(t *testing.T) {
 
 	// now we're on a new round and not the proposer, so wait for timeout
 	re = <-timeoutProposeCh
-	rs = re.(types.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")
@@ -398,7 +409,7 @@ func TestLockNoPOL(t *testing.T) {
 	validatePrevote(t, cs1, 1, vss[0], rs.LockedBlock.Hash())
 
 	// add a conflicting prevote from the other validator
-	signAddVotes(cs1, types.VoteTypePrevote, hash, rs.ProposalBlock.MakePartSet(partSize).Header(), vs2)
+	signAddVotes(cs1, types.VoteTypePrevote, hash, rs.LockedBlock.MakePartSet(partSize).Header(), vs2)
 	<-voteCh
 
 	// now we're going to enter prevote again, but with invalid args
@@ -413,7 +424,7 @@ func TestLockNoPOL(t *testing.T) {
 
 	// add conflicting precommit from vs2
 	// NOTE: in practice we should never get to a point where there are precommits for different blocks at the same round
-	signAddVotes(cs1, types.VoteTypePrecommit, hash, rs.ProposalBlock.MakePartSet(partSize).Header(), vs2)
+	signAddVotes(cs1, types.VoteTypePrecommit, hash, rs.LockedBlock.MakePartSet(partSize).Header(), vs2)
 	<-voteCh
 
 	// (note we're entering precommit for a second time this round, but with invalid args
@@ -429,7 +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()) {
@@ -469,7 +480,9 @@ func TestLockNoPOL(t *testing.T) {
 
 	// now we're on a new round and not the proposer
 	// so set the proposal block
-	cs1.SetProposalAndBlock(prop, propBlock, propBlock.MakePartSet(partSize), "")
+	if err := cs1.SetProposalAndBlock(prop, propBlock, propBlock.MakePartSet(partSize), ""); err != nil {
+		t.Fatal(err)
+	}
 
 	<-proposalCh
 	<-voteCh // prevote
@@ -490,18 +503,18 @@ func TestLockNoPOL(t *testing.T) {
 }
 
 // 4 vals, one precommits, other 3 polka at next round, so we unlock and precomit the polka
-func TestLockPOLRelock(t *testing.T) {
+func TestStateLockPOLRelock(t *testing.T) {
 	cs1, vss := randConsensusState(4)
 	vs2, vs3, vs4 := vss[1], vss[2], vss[3]
 
-	partSize := cs1.state.Params.BlockPartSizeBytes
+	partSize := cs1.state.ConsensusParams.BlockPartSizeBytes
 
-	timeoutProposeCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringTimeoutPropose(), 1)
-	timeoutWaitCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringTimeoutWait(), 1)
-	proposalCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringCompleteProposal(), 1)
-	voteCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringVote(), 1)
-	newRoundCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringNewRound(), 1)
-	newBlockCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringNewBlockHeader(), 1)
+	timeoutProposeCh := subscribe(cs1.eventBus, types.EventQueryTimeoutPropose)
+	timeoutWaitCh := subscribe(cs1.eventBus, types.EventQueryTimeoutWait)
+	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
+	voteCh := subscribe(cs1.eventBus, types.EventQueryVote)
+	newRoundCh := subscribe(cs1.eventBus, types.EventQueryNewRound)
+	newBlockCh := subscribe(cs1.eventBus, types.EventQueryNewBlockHeader)
 
 	// everything done from perspective of cs1
 
@@ -516,7 +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
@@ -546,7 +559,9 @@ func TestLockPOLRelock(t *testing.T) {
 	<-timeoutWaitCh
 
 	//XXX: this isnt guaranteed to get there before the timeoutPropose ...
-	cs1.SetProposalAndBlock(prop, propBlock, propBlockParts, "some peer")
+	if err := cs1.SetProposalAndBlock(prop, propBlock, propBlockParts, "some peer"); err != nil {
+		t.Fatal(err)
+	}
 
 	<-newRoundCh
 	t.Log("### ONTO ROUND 1")
@@ -590,9 +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")
 	}
@@ -603,17 +618,17 @@ func TestLockPOLRelock(t *testing.T) {
 }
 
 // 4 vals, one precommits, other 3 polka at next round, so we unlock and precomit the polka
-func TestLockPOLUnlock(t *testing.T) {
+func TestStateLockPOLUnlock(t *testing.T) {
 	cs1, vss := randConsensusState(4)
 	vs2, vs3, vs4 := vss[1], vss[2], vss[3]
 
-	partSize := cs1.state.Params.BlockPartSizeBytes
+	partSize := cs1.state.ConsensusParams.BlockPartSizeBytes
 
-	proposalCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringCompleteProposal(), 1)
-	timeoutProposeCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringTimeoutPropose(), 1)
-	timeoutWaitCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringTimeoutWait(), 1)
-	newRoundCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringNewRound(), 1)
-	unlockCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringUnlock(), 1)
+	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
+	timeoutProposeCh := subscribe(cs1.eventBus, types.EventQueryTimeoutPropose)
+	timeoutWaitCh := subscribe(cs1.eventBus, types.EventQueryTimeoutWait)
+	newRoundCh := subscribe(cs1.eventBus, types.EventQueryNewRound)
+	unlockCh := subscribe(cs1.eventBus, types.EventQueryUnlock)
 	voteCh := subscribeToVoter(cs1, cs1.privValidator.GetAddress())
 
 	// everything done from perspective of cs1
@@ -628,7 +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
@@ -654,11 +669,13 @@ 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 ...
-	cs1.SetProposalAndBlock(prop, propBlock, propBlockParts, "some peer")
+	if err := cs1.SetProposalAndBlock(prop, propBlock, propBlockParts, "some peer"); err != nil {
+		t.Fatal(err)
+	}
 
 	<-newRoundCh
 	t.Log("#### ONTO ROUND 1")
@@ -698,23 +715,23 @@ func TestLockPOLUnlock(t *testing.T) {
 // a polka at round 1 but we miss it
 // then a polka at round 2 that we lock on
 // then we see the polka from round 1 but shouldn't unlock
-func TestLockPOLSafety1(t *testing.T) {
+func TestStateLockPOLSafety1(t *testing.T) {
 	cs1, vss := randConsensusState(4)
 	vs2, vs3, vs4 := vss[1], vss[2], vss[3]
 
-	partSize := cs1.state.Params.BlockPartSizeBytes
+	partSize := cs1.state.ConsensusParams.BlockPartSizeBytes
 
-	proposalCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringCompleteProposal(), 1)
-	timeoutProposeCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringTimeoutPropose(), 1)
-	timeoutWaitCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringTimeoutWait(), 1)
-	newRoundCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringNewRound(), 1)
+	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
+	timeoutProposeCh := subscribe(cs1.eventBus, types.EventQueryTimeoutPropose)
+	timeoutWaitCh := subscribe(cs1.eventBus, types.EventQueryTimeoutWait)
+	newRoundCh := subscribe(cs1.eventBus, types.EventQueryNewRound)
 	voteCh := subscribeToVoter(cs1, cs1.privValidator.GetAddress())
 
 	// start round and wait for propose and prevote
 	startTestRound(cs1, cs1.Height, 0)
 	<-newRoundCh
 	re := <-proposalCh
-	rs := re.(types.TMEventData).Unwrap().(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
+	rs := re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 	propBlock := rs.ProposalBlock
 
 	<-voteCh // prevote
@@ -745,7 +762,9 @@ func TestLockPOLSafety1(t *testing.T) {
 	incrementRound(vs2, vs3, vs4)
 
 	//XXX: this isnt guaranteed to get there before the timeoutPropose ...
-	cs1.SetProposalAndBlock(prop, propBlock, propBlockParts, "some peer")
+	if err := cs1.SetProposalAndBlock(prop, propBlock, propBlockParts, "some peer"); err != nil {
+		t.Fatal(err)
+	}
 
 	<-newRoundCh
 	t.Log("### ONTO ROUND 1")
@@ -762,7 +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!")
@@ -802,7 +821,7 @@ func TestLockPOLSafety1(t *testing.T) {
 	// we should prevote what we're locked on
 	validatePrevote(t, cs1, 2, vss[0], propBlockHash)
 
-	newStepCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringNewRoundStep(), 1)
+	newStepCh := subscribe(cs1.eventBus, types.EventQueryNewRoundStep)
 
 	// add prevotes from the earlier round
 	addVotes(cs1, prevotes...)
@@ -819,17 +838,17 @@ func TestLockPOLSafety1(t *testing.T) {
 
 // What we want:
 // dont see P0, lock on P1 at R1, dont unlock using P0 at R2
-func TestLockPOLSafety2(t *testing.T) {
+func TestStateLockPOLSafety2(t *testing.T) {
 	cs1, vss := randConsensusState(4)
 	vs2, vs3, vs4 := vss[1], vss[2], vss[3]
 
-	partSize := cs1.state.Params.BlockPartSizeBytes
+	partSize := cs1.state.ConsensusParams.BlockPartSizeBytes
 
-	proposalCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringCompleteProposal(), 1)
-	timeoutProposeCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringTimeoutPropose(), 1)
-	timeoutWaitCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringTimeoutWait(), 1)
-	newRoundCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringNewRound(), 1)
-	unlockCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringUnlock(), 1)
+	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
+	timeoutProposeCh := subscribe(cs1.eventBus, types.EventQueryTimeoutPropose)
+	timeoutWaitCh := subscribe(cs1.eventBus, types.EventQueryTimeoutWait)
+	newRoundCh := subscribe(cs1.eventBus, types.EventQueryNewRound)
+	unlockCh := subscribe(cs1.eventBus, types.EventQueryUnlock)
 	voteCh := subscribeToVoter(cs1, cs1.privValidator.GetAddress())
 
 	// the block for R0: gets polkad but we miss it
@@ -857,7 +876,9 @@ func TestLockPOLSafety2(t *testing.T) {
 	startTestRound(cs1, height, 1)
 	<-newRoundCh
 
-	cs1.SetProposalAndBlock(prop1, propBlock1, propBlockParts1, "some peer")
+	if err := cs1.SetProposalAndBlock(prop1, propBlock1, propBlockParts1, "some peer"); err != nil {
+		t.Fatal(err)
+	}
 	<-proposalCh
 
 	<-voteCh // prevote
@@ -879,10 +900,12 @@ 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 {
 		t.Fatal(err)
 	}
-	cs1.SetProposalAndBlock(newProp, propBlock0, propBlockParts0, "some peer")
 
 	// Add the pol votes
 	addVotes(cs1, prevotes...)
@@ -914,14 +937,14 @@ func TestLockPOLSafety2(t *testing.T) {
 // TODO: Slashing
 
 /*
-func TestSlashingPrevotes(t *testing.T) {
+func TestStateSlashingPrevotes(t *testing.T) {
 	cs1, vss := randConsensusState(2)
 	vs2 := vss[1]
 
 
-	proposalCh := subscribeToEvent(cs1.evsw,"tester",types.EventStringCompleteProposal() , 1)
-	timeoutWaitCh := subscribeToEvent(cs1.evsw,"tester",types.EventStringTimeoutWait() , 1)
-	newRoundCh := subscribeToEvent(cs1.evsw,"tester",types.EventStringNewRound() , 1)
+	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
+	timeoutWaitCh := subscribe(cs1.eventBus, types.EventQueryTimeoutWait)
+	newRoundCh := subscribe(cs1.eventBus, types.EventQueryNewRound)
 	voteCh := subscribeToVoter(cs1, cs1.privValidator.GetAddress())
 
 	// start round and wait for propose and prevote
@@ -949,14 +972,14 @@ func TestSlashingPrevotes(t *testing.T) {
 	// XXX: Check for existence of Dupeout info
 }
 
-func TestSlashingPrecommits(t *testing.T) {
+func TestStateSlashingPrecommits(t *testing.T) {
 	cs1, vss := randConsensusState(2)
 	vs2 := vss[1]
 
 
-	proposalCh := subscribeToEvent(cs1.evsw,"tester",types.EventStringCompleteProposal() , 1)
-	timeoutWaitCh := subscribeToEvent(cs1.evsw,"tester",types.EventStringTimeoutWait() , 1)
-	newRoundCh := subscribeToEvent(cs1.evsw,"tester",types.EventStringNewRound() , 1)
+	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
+	timeoutWaitCh := subscribe(cs1.eventBus, types.EventQueryTimeoutWait)
+	newRoundCh := subscribe(cs1.eventBus, types.EventQueryNewRound)
 	voteCh := subscribeToVoter(cs1, cs1.privValidator.GetAddress())
 
 	// start round and wait for propose and prevote
@@ -994,23 +1017,23 @@ func TestSlashingPrecommits(t *testing.T) {
 
 // 4 vals.
 // we receive a final precommit after going into next round, but others might have gone to commit already!
-func TestHalt1(t *testing.T) {
+func TestStateHalt1(t *testing.T) {
 	cs1, vss := randConsensusState(4)
 	vs2, vs3, vs4 := vss[1], vss[2], vss[3]
 
-	partSize := cs1.state.Params.BlockPartSizeBytes
+	partSize := cs1.state.ConsensusParams.BlockPartSizeBytes
 
-	proposalCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringCompleteProposal(), 1)
-	timeoutWaitCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringTimeoutWait(), 1)
-	newRoundCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringNewRound(), 1)
-	newBlockCh := subscribeToEvent(cs1.evsw, "tester", types.EventStringNewBlock(), 1)
+	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
+	timeoutWaitCh := subscribe(cs1.eventBus, types.EventQueryTimeoutWait)
+	newRoundCh := subscribe(cs1.eventBus, types.EventQueryNewRound)
+	newBlockCh := subscribe(cs1.eventBus, types.EventQueryNewBlock)
 	voteCh := subscribeToVoter(cs1, cs1.privValidator.GetAddress())
 
 	// start round and wait for propose and prevote
 	startTestRound(cs1, cs1.Height, 0)
 	<-newRoundCh
 	re := <-proposalCh
-	rs := re.(types.TMEventData).Unwrap().(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
+	rs := re.(types.EventDataRoundState).RoundState.(*cstypes.RoundState)
 	propBlock := rs.ProposalBlock
 	propBlockParts := propBlock.MakePartSet(partSize)
 
@@ -1033,7 +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
@@ -1051,9 +1074,26 @@ 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")
 	}
 }
+
+// subscribe subscribes test client to the given query and returns a channel with cap = 1.
+func subscribe(eventBus *types.EventBus, q tmpubsub.Query) <-chan interface{} {
+	out := make(chan interface{}, 1)
+	err := eventBus.Subscribe(context.Background(), testSubscriber, q, out)
+	if err != nil {
+		panic(fmt.Sprintf("failed to subscribe %s to %v", testSubscriber, q))
+	}
+	return out
+}
+
+// discardFromChan reads n values from the channel.
+func discardFromChan(ch <-chan interface{}, n int) {
+	for i := 0; i < n; i++ {
+		<-ch
+	}
+}

consensus/test_data/README.md

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

consensus/test_data/build.sh

@@ -1,148 +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

@@ -15,8 +15,8 @@ var (
 // conditional on the height/round/step in the timeoutInfo.
 // The timeoutInfo.Duration may be non-positive.
 type TimeoutTicker interface {
-	Start() (bool, error)
-	Stop() bool
+	Start() error
+	Stop() error
 	Chan() <-chan timeoutInfo       // on which to receive a timeout
 	ScheduleTimeout(ti timeoutInfo) // reset the timer
 
@@ -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'.
 
@@ -29,16 +36,16 @@ One for their LastCommit round, and another for the official commit round.
 */
 type HeightVoteSet struct {
 	chainID string
-	height  int
+	height  int64
 	valSet  *types.ValidatorSet
 
 	mtx               sync.Mutex
 	round             int                  // max tracked round
 	roundVoteSets     map[int]RoundVoteSet // keys: [0...round]
-	peerCatchupRounds map[string][]int     // keys: peer.Key; values: at most 2 rounds
+	peerCatchupRounds map[p2p.ID][]int     // keys: peer.ID; values: at most 2 rounds
 }
 
-func NewHeightVoteSet(chainID string, height int, valSet *types.ValidatorSet) *HeightVoteSet {
+func NewHeightVoteSet(chainID string, height int64, valSet *types.ValidatorSet) *HeightVoteSet {
 	hvs := &HeightVoteSet{
 		chainID: chainID,
 	}
@@ -46,20 +53,20 @@ func NewHeightVoteSet(chainID string, height int, valSet *types.ValidatorSet) *H
 	return hvs
 }
 
-func (hvs *HeightVoteSet) Reset(height int, valSet *types.ValidatorSet) {
+func (hvs *HeightVoteSet) Reset(height int64, valSet *types.ValidatorSet) {
 	hvs.mtx.Lock()
 	defer hvs.mtx.Unlock()
 
 	hvs.height = height
 	hvs.valSet = valSet
 	hvs.roundVoteSets = make(map[int]RoundVoteSet)
-	hvs.peerCatchupRounds = make(map[string][]int)
+	hvs.peerCatchupRounds = make(map[p2p.ID][]int)
 
 	hvs.addRound(0)
 	hvs.round = 0
 }
 
-func (hvs *HeightVoteSet) Height() int {
+func (hvs *HeightVoteSet) Height() int64 {
 	hvs.mtx.Lock()
 	defer hvs.mtx.Unlock()
 	return hvs.height
@@ -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
 		}
 	}
@@ -206,15 +211,15 @@ func (hvs *HeightVoteSet) StringIndented(indent string) string {
 // NOTE: if there are too many peers, or too much peer churn,
 // this can cause memory issues.
 // TODO: implement ability to remove peers too
-func (hvs *HeightVoteSet) SetPeerMaj23(round int, type_ byte, peerID string, blockID types.BlockID) {
+func (hvs *HeightVoteSet) SetPeerMaj23(round int, type_ byte, peerID p2p.ID, blockID types.BlockID) error {
 	hvs.mtx.Lock()
 	defer hvs.mtx.Unlock()
 	if !types.IsVoteTypeValid(type_) {
-		return
+		return fmt.Errorf("SetPeerMaj23: Invalid vote type %v", type_)
 	}
 	voteSet := hvs.getVoteSet(round, type_)
 	if voteSet == nil {
-		return
+		return nil // something we don't know about yet
 	}
-	voteSet.SetPeerMaj23(peerID, blockID)
+	return voteSet.SetPeerMaj23(types.P2PID(peerID), blockID)
 }

consensus/types/height_vote_set_test.go

@@ -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, 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/reactor.go

@@ -13,7 +13,7 @@ import (
 // PeerRoundState contains the known state of a peer.
 // NOTE: Read-only when returned by PeerState.GetRoundState().
 type PeerRoundState struct {
-	Height                   int                 // Height peer is at
+	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

consensus/types/state.go

@@ -52,11 +52,10 @@ 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             int // Height we are working on
+	Height             int64 // Height we are working on
 	Round              int
 	Step               RoundStepType
 	StartTime          time.Time
@@ -68,6 +67,9 @@ type RoundState struct {
 	LockedRound        int
 	LockedBlock        *types.Block
 	LockedBlockParts   *types.PartSet
+	ValidRound         int
+	ValidBlock         *types.Block
+	ValidBlockParts    *types.PartSet
 	Votes              *HeightVoteSet
 	CommitRound        int            //
 	LastCommit         *types.VoteSet // Last precommits at Height-1
@@ -76,11 +78,14 @@ type RoundState struct {
 
 // RoundStateEvent returns the H/R/S of the RoundState as an event.
 func (rs *RoundState) RoundStateEvent() types.EventDataRoundState {
+	// XXX: copy the RoundState
+	// if we want to avoid this, we may need synchronous events after all
+	rs_ := *rs
 	edrs := types.EventDataRoundState{
 		Height:     rs.Height,
 		Round:      rs.Round,
 		Step:       rs.Step.String(),
-		RoundState: rs,
+		RoundState: &rs_,
 	}
 	return edrs
 }
@@ -101,9 +106,11 @@ 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,
@@ -113,6 +120,8 @@ func (rs *RoundState) StringIndented(indent string) string {
 		indent, rs.ProposalBlockParts.StringShort(), rs.ProposalBlock.StringShort(),
 		indent, rs.LockedRound,
 		indent, rs.LockedBlockParts.StringShort(), rs.LockedBlock.StringShort(),
+		indent, rs.ValidRound,
+		indent, rs.ValidBlockParts.StringShort(), rs.ValidBlock.StringShort(),
 		indent, rs.Votes.StringIndented(indent+"    "),
 		indent, rs.LastCommit.StringShort(),
 		indent, rs.LastValidators.StringIndented(indent+"    "),

consensus/wal.go

@@ -1,55 +1,69 @@
 package consensus
 
 import (
-	"bytes"
 	"encoding/binary"
 	"fmt"
 	"hash/crc32"
 	"io"
+	"path/filepath"
 	"time"
 
-	wire "github.com/tendermint/go-wire"
+	"github.com/pkg/errors"
+
+	amino "github.com/tendermint/go-amino"
 	"github.com/tendermint/tendermint/types"
 	auto "github.com/tendermint/tmlibs/autofile"
 	cmn "github.com/tendermint/tmlibs/common"
 )
 
+const (
+	// must be greater than params.BlockGossip.BlockPartSizeBytes + a few bytes
+	maxMsgSizeBytes = 1024 * 1024 // 1MB
+)
+
 //--------------------------------------------------------
 // types and functions for savings consensus messages
 
-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 uint64 `json:"height"`
+	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)
+	Group() *auto.Group
+	SearchForEndHeight(height int64, options *WALSearchOptions) (gr *auto.GroupReader, found bool, err error)
+
+	Start() error
+	Stop() error
+	Wait()
+}
+
 // Write ahead logger writes msgs to disk before they are processed.
 // Can be used for crash-recovery and deterministic replay
 // TODO: currently the wal is overwritten during replay catchup
 //   give it a mode so it's either reading or appending - must read to end to start appending again
-type WAL struct {
+type baseWAL struct {
 	cmn.BaseService
 
 	group *auto.Group
@@ -58,38 +72,47 @@ type WAL struct {
 	enc *WALEncoder
 }
 
-func NewWAL(walFile string, light bool) (*WAL, error) {
+func NewWAL(walFile string, light bool) (*baseWAL, error) {
+	err := cmn.EnsureDir(filepath.Dir(walFile), 0700)
+	if err != nil {
+		return nil, errors.Wrap(err, "failed to ensure WAL directory is in place")
+	}
+
 	group, err := auto.OpenGroup(walFile)
 	if err != nil {
 		return nil, err
 	}
-	wal := &WAL{
+	wal := &baseWAL{
 		group: group,
 		light: light,
 		enc:   NewWALEncoder(group),
 	}
-	wal.BaseService = *cmn.NewBaseService(nil, "WAL", wal)
+	wal.BaseService = *cmn.NewBaseService(nil, "baseWAL", wal)
 	return wal, nil
 }
 
-func (wal *WAL) OnStart() error {
+func (wal *baseWAL) Group() *auto.Group {
+	return wal.group
+}
+
+func (wal *baseWAL) OnStart() error {
 	size, err := wal.group.Head.Size()
 	if err != nil {
 		return err
 	} else if size == 0 {
 		wal.Save(EndHeightMessage{0})
 	}
-	_, err = wal.group.Start()
+	err = wal.group.Start()
 	return err
 }
 
-func (wal *WAL) OnStop() {
+func (wal *baseWAL) OnStop() {
 	wal.BaseService.OnStop()
 	wal.group.Stop()
 }
 
 // called in newStep and for each pass in receiveRoutine
-func (wal *WAL) Save(msg WALMessage) {
+func (wal *baseWAL) Save(msg WALMessage) {
 	if wal == nil {
 		return
 	}
@@ -97,7 +120,7 @@ func (wal *WAL) Save(msg WALMessage) {
 	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 != "" {
+			if mi.PeerID != "" {
 				return
 			}
 		}
@@ -114,12 +137,18 @@ func (wal *WAL) Save(msg WALMessage) {
 	}
 }
 
+// WALSearchOptions are optional arguments to SearchForEndHeight.
+type WALSearchOptions struct {
+	// IgnoreDataCorruptionErrors set to true will result in skipping data corruption errors.
+	IgnoreDataCorruptionErrors bool
+}
+
 // SearchForEndHeight searches for the EndHeightMessage with the height and
 // returns an auto.GroupReader, whenever it was found or not and an error.
 // Group reader will be nil if found equals false.
 //
 // CONTRACT: caller must close group reader.
-func (wal *WAL) SearchForEndHeight(height uint64) (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
 
 	// NOTE: starting from the last file in the group because we're usually
@@ -139,7 +168,9 @@ func (wal *WAL) SearchForEndHeight(height uint64) (gr *auto.GroupReader, found b
 				// check next file
 				break
 			}
-			if err != nil {
+			if options.IgnoreDataCorruptionErrors && IsDataCorruptionError(err) {
+				// do nothing
+			} else if err != nil {
 				gr.Close()
 				return nil, false, err
 			}
@@ -151,7 +182,6 @@ func (wal *WAL) SearchForEndHeight(height uint64) (gr *auto.GroupReader, found b
 				}
 			}
 		}
-
 		gr.Close()
 	}
 
@@ -162,7 +192,7 @@ func (wal *WAL) SearchForEndHeight(height uint64) (gr *auto.GroupReader, found b
 
 // 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
 }
@@ -173,8 +203,8 @@ 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))
@@ -187,16 +217,30 @@ 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.
 //
@@ -215,7 +259,7 @@ 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
 	}
@@ -225,7 +269,7 @@ func (dec *WALDecoder) Decode() (*TimedWALMessage, error) {
 	crc := binary.BigEndian.Uint32(b)
 
 	b = make([]byte, 4)
-	n, err = dec.rd.Read(b)
+	_, err = dec.rd.Read(b)
 	if err == io.EOF {
 		return nil, err
 	}
@@ -234,46 +278,41 @@ func (dec *WALDecoder) Decode() (*TimedWALMessage, error) {
 	}
 	length := binary.BigEndian.Uint32(b)
 
+	if length > maxMsgSizeBytes {
+		return nil, DataCorruptionError{fmt.Errorf("length %d exceeded maximum possible value of %d bytes", length, maxMsgSizeBytes)}
+	}
+
 	data := make([]byte, length)
-	n, err = dec.rd.Read(data)
+	_, err = dec.rd.Read(data)
 	if err == io.EOF {
 		return nil, err
 	}
 	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
-	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, options *WALSearchOptions) (gr *auto.GroupReader, found bool, err error) {
+	return nil, false, nil
 }
+func (nilWAL) Start() error { return nil }
+func (nilWAL) Stop() error  { return nil }
+func (nilWAL) Wait()        {}

consensus/wal_fuzz.go

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

consensus/wal_generator.go

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

consensus/wal_test.go

@@ -2,7 +2,8 @@ package consensus
 
 import (
 	"bytes"
-	"path"
+	"crypto/rand"
+	// "sync"
 	"testing"
 	"time"
 
@@ -34,19 +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, false)
 	if err != nil {
 		t.Fatal(err)
 	}
 
-	h := 3
-	gr, found, err := wal.SearchForEndHeight(uint64(h))
+	h := int64(3)
+	gr, found, err := wal.SearchForEndHeight(h, &WALSearchOptions{})
 	assert.NoError(t, err, cmn.Fmt("expected not to err on height %d", h))
 	assert.True(t, found, cmn.Fmt("expected to find end height for %d", h))
 	assert.NotNil(t, gr, "expected group not to be nil")
@@ -58,5 +65,69 @@ func TestSearchForEndHeight(t *testing.T) {
 	rs, ok := msg.Msg.(tmtypes.EventDataRoundState)
 	assert.True(t, ok, "expected message of type EventDataRoundState")
 	assert.Equal(t, rs.Height, h+1, cmn.Fmt("wrong height"))
-
+}
+
+/*
+var initOnce sync.Once
+
+func registerInterfacesOnce() {
+	initOnce.Do(func() {
+		var _ = wire.RegisterInterface(
+			struct{ WALMessage }{},
+			wire.ConcreteType{[]byte{}, 0x10},
+		)
+	})
+}
+*/
+
+func nBytes(n int) []byte {
+	buf := make([]byte, n)
+	n, _ = rand.Read(buf)
+	return buf[:n]
+}
+
+func benchmarkWalDecode(b *testing.B, n int) {
+	// registerInterfacesOnce()
+
+	buf := new(bytes.Buffer)
+	enc := NewWALEncoder(buf)
+
+	data := nBytes(n)
+	enc.Encode(&TimedWALMessage{Msg: data, Time: time.Now().Round(time.Second)})
+
+	encoded := buf.Bytes()
+
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		buf.Reset()
+		buf.Write(encoded)
+		dec := NewWALDecoder(buf)
+		if _, err := dec.Decode(); err != nil {
+			b.Fatal(err)
+		}
+	}
+	b.ReportAllocs()
+}
+
+func BenchmarkWalDecode512B(b *testing.B) {
+	benchmarkWalDecode(b, 512)
+}
+
+func BenchmarkWalDecode10KB(b *testing.B) {
+	benchmarkWalDecode(b, 10*1024)
+}
+func BenchmarkWalDecode100KB(b *testing.B) {
+	benchmarkWalDecode(b, 100*1024)
+}
+func BenchmarkWalDecode1MB(b *testing.B) {
+	benchmarkWalDecode(b, 1024*1024)
+}
+func BenchmarkWalDecode10MB(b *testing.B) {
+	benchmarkWalDecode(b, 10*1024*1024)
+}
+func BenchmarkWalDecode100MB(b *testing.B) {
+	benchmarkWalDecode(b, 100*1024*1024)
+}
+func BenchmarkWalDecode1GB(b *testing.B) {
+	benchmarkWalDecode(b, 1024*1024*1024)
 }

consensus/wire.go

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

docker-compose.yml

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

docker-compose/Makefile

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

docker-compose/README.rst

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

docker-compose/localnode/Dockerfile

@@ -0,0 +1,16 @@
+FROM alpine:3.7
+MAINTAINER Greg Szabo <greg@tendermint.com>
+
+RUN apk update && \
+    apk upgrade && \
+    apk --no-cache add curl jq file
+
+VOLUME [ /tendermint ]
+WORKDIR /tendermint
+EXPOSE 46656 46657
+ENTRYPOINT ["/usr/bin/wrapper.sh"]
+CMD ["node", "--proxy_app dummy"]
+STOPSIGNAL SIGTERM
+
+COPY wrapper.sh /usr/bin/wrapper.sh
+

docker-compose/localnode/wrapper.sh

@@ -0,0 +1,33 @@
+#!/usr/bin/env sh
+
+##
+## Input parameters
+##
+BINARY=/tendermint/${BINARY:-tendermint}
+ID=${ID:-0}
+LOG=${LOG:-tendermint.log}
+
+##
+## Assert linux binary
+##
+if ! [ -f "${BINARY}" ]; then
+	echo "The binary `basename ${BINARY}` cannot be found. Please add the binary to the shared folder. Please use the BINARY environment variable if the name of the binary is not 'tendermint' E.g.: -e BINARY=tendermint_my_test_version"
+	exit 1
+fi
+BINARY_CHECK="`file $BINARY | grep 'ELF 64-bit LSB executable, x86-64'`"
+if [ -z "${BINARY_CHECK}" ]; then
+	echo "Binary needs to be OS linux, ARCH amd64"
+	exit 1
+fi
+
+##
+## Run binary with all parameters
+##
+export TMHOME="/tendermint/node${ID}"
+
+if [ -d "${TMHOME}/${LOG}" ]; then
+  "$BINARY" $@ | tee "${TMHOME}/${LOG}"
+else
+  "$BINARY" $@
+fi
+

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/_static/custom_collapsible_code.css

@@ -0,0 +1,17 @@
+.toggle {
+    padding-bottom: 1em ;
+}
+
+.toggle .header {
+    display: block;
+    clear: both;
+    cursor: pointer;
+}
+
+.toggle .header:after {
+    content: " ▼";
+}
+
+.toggle .header.open:after {
+    content: " ▲";
+}

docs/_static/custom_collapsible_code.js

@@ -0,0 +1,10 @@
+let makeCodeBlocksCollapsible = function() {
+    $(".toggle > *").hide();
+    $(".toggle .header").show();
+    $(".toggle .header").click(function() {
+        $(this).parent().children().not(".header").toggle({"duration": 400});
+        $(this).parent().children(".header").toggleClass("open");
+    });
+};
+// we could use the }(); way if we would have access to jQuery in HEAD, i.e. we would need to force the theme
+// to load jQuery before our custom scripts

docs/_templates/layout.html

@@ -0,0 +1,20 @@
+{% extends "!layout.html" %}
+
+{% set css_files = css_files + ["_static/custom_collapsible_code.css"] %}
+
+# sadly, I didn't find a css style way to add custom JS to a list that is automagically added to head like CSS (above) #}
+{% block extrahead %}
+<script type="text/javascript" src="_static/custom_collapsible_code.js"></script>
+{% endblock %}
+
+{% block footer %}
+<script type="text/javascript">
+    $(document).ready(function() {
+        // using this approach as we don't have access to the jQuery selectors
+        // when executing the function on load in HEAD
+        makeCodeBlocksCollapsible();
+    });
+</script>
+{% endblock %}
+
+

docs/abci-cli.rst

@@ -14,40 +14,50 @@ Next, install the ``abci-cli`` tool and example applications:
 
 ::
 
-    go get -u github.com/tendermint/abci/cmd/...
+    go get -u github.com/tendermint/abci/cmd/abci-cli
 
-If this fails, you may need to use ``glide`` to get vendored
+If this fails, you may need to use `dep <https://github.com/golang/dep>`__ to get vendored
 dependencies:
 
 ::
 
-    go get github.com/Masterminds/glide
     cd $GOPATH/src/github.com/tendermint/abci
-    glide install
-    go install ./cmd/...
+    make get_tools
+    make get_vendor_deps
+    make install
 
-Now run ``abci-cli --help`` to see the list of commands:
+Now run ``abci-cli`` to see the list of commands:
 
 ::
 
-    COMMANDS:
-       batch        Run a batch of ABCI commands against an application
-       console      Start an interactive console for multiple commands
-       echo         Have the application echo a message
-       info         Get some info about the application
-       set_option   Set an option on the application
-       deliver_tx    Append a new tx to application
-       check_tx     Validate a tx
-       commit       Get application Merkle root hash
-       help, h      Shows a list of commands or help for one command
+    Usage:
+      abci-cli [command]
 
-    GLOBAL OPTIONS:
-       --address "tcp://127.0.0.1:46658"    address of application socket
-       --help, -h                           show help
-       --version, -v                        print the version
+    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
 
-Dummy - First Example
----------------------
+    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.
+
+
+KVStore - First Example
+-----------------------
 
 The ``abci-cli`` tool lets us send ABCI messages to our application, to
 help build and debug them.
@@ -56,22 +66,75 @@ 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:
+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:
+
+.. container:: toggle
+
+    .. container:: header
+
+        **Show/Hide KVStore Example**
+
+    .. code-block:: go
+
+        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:
 
 ::
 
-    dummy
+    abci-cli kvstore
 
-In another terminal, run
+And in another terminal, run
 
 ::
 
     abci-cli echo hello
     abci-cli info
 
-The application should echo ``hello`` and give you some information
-about itself.
+You'll see something like:
+
+::
+
+    -> data: hello
+    -> data.hex: 68656C6C6F
+
+and:
+
+::
+
+    -> data: {"size":0}
+    -> data.hex: 7B2273697A65223A307D
 
 An ABCI application must provide two things:
 
@@ -86,7 +149,7 @@ 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 <https://tendermint.com/ecosystem>`__ for servers in
+implementations <./ecosystem.html>`__ for servers in
 other languages.
 
 The handler is specific to the application, and may be arbitrary, so
@@ -109,36 +172,50 @@ Try running these commands:
 ::
 
     > echo hello
+    -> code: OK
     -> data: hello
+    -> data.hex: 0x68656C6C6F
     
     > info
+    -> code: OK
     -> data: {"size":0}
+    -> data.hex: 0x7B2273697A65223A307D
     
     > commit
-    -> data: 0x
+    -> code: OK
     
     > deliver_tx "abc"
     -> code: OK
     
     > info
+    -> code: OK
     -> data: {"size":1}
+    -> data.hex: 0x7B2273697A65223A317D
     
     > commit
-    -> data: 0x750502FC7E84BBD788ED589624F06CFA871845D1
+    -> code: OK
+    -> data.hex: 0x49DFD15CCDACDEAE9728CB01FBB5E8688CA58B91
     
     > query "abc"
     -> code: OK
-    -> data: {"index":0,"value":"abc","exists":true}
+    -> log: exists
+    -> height: 0
+    -> value: abc
+    -> value.hex: 616263
     
     > deliver_tx "def=xyz"
     -> code: OK
     
     > commit
-    -> data: 0x76393B8A182E450286B0694C629ECB51B286EFD5
+    -> code: OK
+    -> data.hex: 0x70102DB32280373FBF3F9F89DA2A20CE2CD62B0B
     
     > query "def"
     -> code: OK
-    -> data: {"index":1,"value":"xyz","exists":true}
+    -> 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)``.
@@ -152,6 +229,41 @@ 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:
+
+.. container:: toggle
+
+    .. container:: header
+
+        **Show/Hide Counter Example**
+
+    .. code-block:: go
+
+        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.
@@ -176,19 +288,19 @@ 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
+Let's kill the console and the kvstore application, and start the counter
 app:
 
 ::
 
-    counter
+    abci-cli counter
 
 In another window, start the ``abci-cli console``:
 
 ::
 
     > set_option serial on
-    -> data: serial=on
+    -> code: OK
     
     > check_tx 0x00
     -> code: OK
@@ -211,10 +323,12 @@ In another window, start the ``abci-cli console``:
     -> 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
+``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,
@@ -224,7 +338,7 @@ 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).
+`example directory <https://github.com/tendermint/abci/tree/master/example`__).
 
 To run the Node JS version, ``cd`` to ``example/js`` and run
 
@@ -252,4 +366,4 @@ 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>`__.
+guide <./getting-started.html>`__. Next is the ABCI specification.

docs/app-development.rst

@@ -142,10 +142,10 @@ 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>`__
+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.
 
@@ -194,11 +194,37 @@ 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
 
-    func (app *DummyApplication) CheckTx(tx []byte) types.Result {
-      return types.OK
-    }
+    .. container:: header
+
+        **Show/Hide Go Example**
+
+    .. code-block:: go
+
+        func (app *KVStoreApplication) 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
 ~~~~~~~~~~~~~~~~~~~~
@@ -228,18 +254,48 @@ 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
 
-    // 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:: header
+
+        **Show/Hide Go Example**
+
+    .. code-block:: 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
+        }
+
+.. 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
 ^^^^^^
@@ -263,12 +319,35 @@ 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
 
-    func (app *DummyApplication) Commit() types.Result {
-      hash := app.state.Hash()
-      return types.NewResultOK(hash, "")
-    }
+    .. container:: header
+
+        **Show/Hide Go Example**
+
+    .. code-block:: go
+
+        func (app *KVStoreApplication) 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
 ^^^^^^^^^^
@@ -281,35 +360,93 @@ 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
 
-    // Track the block hash and header information
-    func (app *PersistentDummyApplication) BeginBlock(params types.RequestBeginBlock) {
-      // update latest block info
-      app.blockHeader = params.Header
+    .. container:: header
 
-      // reset valset changes
-      app.changes = make([]*types.Validator, 0)
-    }
+        **Show/Hide Go Example**
+
+    .. code-block:: 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)
+        }
+
+.. 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.
+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.
 
-::
+.. container:: toggle
 
-    // Update the validator set
-    func (app *PersistentDummyApplication) EndBlock(height uint64) (resEndBlock types.ResponseEndBlock) {
-      return types.ResponseEndBlock{Diffs: app.changes}
-    }
+    .. container:: header
+
+        **Show/Hide Go Example**
+
+    .. code-block:: go
+
+        // Update the validator set
+        func (app *PersistentKVStoreApplication) EndBlock(req types.RequestEndBlock) types.ResponseEndBlock {
+          return types.ResponseEndBlock{ValidatorUpdates: app.ValUpdates}
+        }
+
+.. 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
 ~~~~~~~~~~~~~~~~
@@ -332,33 +469,72 @@ cause Tendermint to not connect to the corresponding peer:
 
 Note: these query formats are subject to change!
 
-::
+.. container:: toggle
 
-    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"
+    .. container:: header
+
+        **Show/Hide Go Example**
+
+    .. code-block:: 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
+          }
         }
-        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"
+
+.. 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();
         }
-        return
-      }
-    }
 
 Handshake
 ~~~~~~~~~
@@ -377,11 +553,31 @@ 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
 
-    func (app *DummyApplication) Info(req types.RequestInfo) (resInfo types.ResponseInfo) {
-      return types.ResponseInfo{Data: cmn.Fmt("{\"size\":%v}", app.state.Size())}
-    }
+    .. container:: header
+
+        **Show/Hide Go Example**
+
+    .. code-block:: go
+
+        func (app *KVStoreApplication) 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
 ~~~~~~~
@@ -390,14 +586,45 @@ Genesis
 initial validator set. Later on, it may be extended to take parts of the
 consensus params.
 
-::
+.. container:: toggle
 
-    // 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:: header
+
+        **Show/Hide Go Example**
+
+    .. code-block:: 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)
+            }
+          }
+        }
+
+.. 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();
         }
-      }
-    }