privval: improve Remote Signer implementation (#3351)

This issue is related to #3107
This is a first renaming/refactoring step before reworking and removing heartbeats.
As discussed with @Liamsi , we preferred to go for a couple of independent and separate PRs to simplify review work.

The changes:

    Help to clarify the relation between the validator and remote signer endpoints
    Differentiate between timeouts and deadlines
    Prepare to encapsulate networking related code behind RemoteSigner in the next PR

My intention is to separate and encapsulate the "network related" code from the actual signer.

SignerRemote ---(uses/contains)--> SignerValidatorEndpoint <--(connects to)--> SignerServiceEndpoint ---> SignerService (future.. not here yet but would like to decouple too)

All reconnection/heartbeat/whatever code goes in the endpoints. Signer[Remote/Service] do not need to know about that.

I agree Endpoint may not be the perfect name. I tried to find something "Go-ish" enough. It is a common name in go-kit, kubernetes, etc.

Right now:
SignerValidatorEndpoint:

    handles the listener
    contains SignerRemote
    Implements the PrivValidator interface
    connects and sets a connection object in a contained SignerRemote
    delegates PrivValidator some calls to SignerRemote which in turn uses the conn object that was set externally

SignerRemote:

    Implements the PrivValidator interface
    read/writes from a connection object directly
    handles heartbeats

SignerServiceEndpoint:

    Does most things in a single place
    delegates to a PrivValidator IIRC.

* cleanup

* Refactoring step 1

* Refactoring step 2

* move messages to another file

* mark for future work / next steps

* mark deprecated classes in docs

* Fix linter problems

* additional linter fixes

.circleci/config.yml

@@ -48,10 +48,10 @@ jobs:
           key: v3-pkg-cache
           paths:
             - /go/pkg
-      # - save_cache:
-      #     key: v3-tree-{{ .Environment.CIRCLE_SHA1 }}
-      #     paths:
-      #       - /go/src/github.com/tendermint/tendermint
+      - save_cache:
+          key: v3-tree-{{ .Environment.CIRCLE_SHA1 }}
+          paths:
+            - /go/src/github.com/tendermint/tendermint
 
   build_slate:
     <<: *defaults
@@ -60,23 +60,8 @@ jobs:
           at: /tmp/workspace
       - restore_cache:
           key: v3-pkg-cache
-      # https://discuss.circleci.com/t/saving-cache-stopped-working-warning-skipping-this-step-disabled-in-configuration/24423/2
-      # - restore_cache:
-      #     key: v3-tree-{{ .Environment.CIRCLE_SHA1 }}
-      - checkout
-      - run:
-          name: tools
-          command: |
-            export PATH="$GOBIN:$PATH"
-            make get_tools
-      - run:
-          name: dependencies
-          command: |
-            export PATH="$GOBIN:$PATH"
-            make get_vendor_deps
-      - run: mkdir -p $GOPATH/src/github.com/tendermint
-      - run: ln -sf /home/circleci/project $GOPATH/src/github.com/tendermint/tendermint
-
+      - restore_cache:
+          key: v3-tree-{{ .Environment.CIRCLE_SHA1 }}
       - run:
           name: slate docs
           command: |
@@ -91,29 +76,14 @@ jobs:
           at: /tmp/workspace
       - restore_cache:
           key: v3-pkg-cache
-      # - restore_cache:
-      #     key: v3-tree-{{ .Environment.CIRCLE_SHA1 }}
-      - checkout
-      - run:
-          name: tools
-          command: |
-            export PATH="$GOBIN:$PATH"
-            make get_tools
-            make get_dev_tools
-      - run:
-          name: dependencies
-          command: |
-            export PATH="$GOBIN:$PATH"
-            make get_vendor_deps
-      - run: mkdir -p $GOPATH/src/github.com/tendermint
-      - run: ln -sf /home/circleci/project $GOPATH/src/github.com/tendermint/tendermint
-
+      - restore_cache:
+          key: v3-tree-{{ .Environment.CIRCLE_SHA1 }}
       - run:
           name: metalinter
           command: |
             set -ex
             export PATH="$GOBIN:$PATH"
-            make metalinter
+            make lint
       - run:
           name: check_dep
           command: |
@@ -128,22 +98,8 @@ jobs:
           at: /tmp/workspace
       - restore_cache:
           key: v3-pkg-cache
-      # - restore_cache:
-      #     key: v3-tree-{{ .Environment.CIRCLE_SHA1 }}
-      - checkout
-      - run:
-          name: tools
-          command: |
-            export PATH="$GOBIN:$PATH"
-            make get_tools
-      - run:
-          name: dependencies
-          command: |
-            export PATH="$GOBIN:$PATH"
-            make get_vendor_deps
-      - run: mkdir -p $GOPATH/src/github.com/tendermint
-      - run: ln -sf /home/circleci/project $GOPATH/src/github.com/tendermint/tendermint
-
+      - restore_cache:
+          key: v3-tree-{{ .Environment.CIRCLE_SHA1 }}
       - run:
           name: Run abci apps tests
           command: |
@@ -159,22 +115,8 @@ jobs:
           at: /tmp/workspace
       - restore_cache:
           key: v3-pkg-cache
-      # - restore_cache:
-      #     key: v3-tree-{{ .Environment.CIRCLE_SHA1 }}
-      - checkout
-      - run:
-          name: tools
-          command: |
-            export PATH="$GOBIN:$PATH"
-            make get_tools
-      - run:
-          name: dependencies
-          command: |
-            export PATH="$GOBIN:$PATH"
-            make get_vendor_deps
-      - run: mkdir -p $GOPATH/src/github.com/tendermint
-      - run: ln -sf /home/circleci/project $GOPATH/src/github.com/tendermint/tendermint
-
+      - restore_cache:
+          key: v3-tree-{{ .Environment.CIRCLE_SHA1 }}
       - run:
           name: Run abci-cli tests
           command: |
@@ -188,22 +130,8 @@ jobs:
           at: /tmp/workspace
       - restore_cache:
           key: v3-pkg-cache
-      # - restore_cache:
-      #     key: v3-tree-{{ .Environment.CIRCLE_SHA1 }}
-      - checkout
-      - run:
-          name: tools
-          command: |
-            export PATH="$GOBIN:$PATH"
-            make get_tools
-      - run:
-          name: dependencies
-          command: |
-            export PATH="$GOBIN:$PATH"
-            make get_vendor_deps
-      - run: mkdir -p $GOPATH/src/github.com/tendermint
-      - run: ln -sf /home/circleci/project $GOPATH/src/github.com/tendermint/tendermint
-
+      - restore_cache:
+          key: v3-tree-{{ .Environment.CIRCLE_SHA1 }}
       - run: sudo apt-get update && sudo apt-get install -y --no-install-recommends bsdmainutils
       - run:
           name: Run tests
@@ -217,22 +145,8 @@ jobs:
           at: /tmp/workspace
       - restore_cache:
           key: v3-pkg-cache
-      # - restore_cache:
-      #     key: v3-tree-{{ .Environment.CIRCLE_SHA1 }}
-      - checkout
-      - run:
-          name: tools
-          command: |
-            export PATH="$GOBIN:$PATH"
-            make get_tools
-      - run:
-          name: dependencies
-          command: |
-            export PATH="$GOBIN:$PATH"
-            make get_vendor_deps
-      - run: mkdir -p $GOPATH/src/github.com/tendermint
-      - run: ln -sf /home/circleci/project $GOPATH/src/github.com/tendermint/tendermint
-
+      - restore_cache:
+          key: v3-tree-{{ .Environment.CIRCLE_SHA1 }}
       - run: mkdir -p /tmp/logs
       - run:
           name: Run tests
@@ -256,22 +170,8 @@ jobs:
           at: /tmp/workspace
       - restore_cache:
           key: v3-pkg-cache
-      # - restore_cache:
-      #     key: v3-tree-{{ .Environment.CIRCLE_SHA1 }}
-      - checkout
-      - run:
-          name: tools
-          command: |
-            export PATH="$GOBIN:$PATH"
-            make get_tools
-      - run:
-          name: dependencies
-          command: |
-            export PATH="$GOBIN:$PATH"
-            make get_vendor_deps
-      - run: mkdir -p $GOPATH/src/github.com/tendermint
-      - run: ln -sf /home/circleci/project $GOPATH/src/github.com/tendermint/tendermint
-
+      - restore_cache:
+          key: v3-tree-{{ .Environment.CIRCLE_SHA1 }}
       - run:
           name: Run tests
           command: bash test/persist/test_failure_indices.sh
@@ -292,9 +192,7 @@ jobs:
             name: run localnet and exit on failure
             command: |
               set -x
-              make get_tools
-              make get_vendor_deps
-              make build-linux
+              docker run --rm -v "$PWD":/go/src/github.com/tendermint/tendermint -w /go/src/github.com/tendermint/tendermint golang:1.11.4 make build-linux
               make localnet-start &
               ./scripts/localnet-blocks-test.sh 40 5 10 localhost
 
@@ -317,22 +215,10 @@ jobs:
     steps:
       - attach_workspace:
           at: /tmp/workspace
-      # - restore_cache:
-      #     key: v3-tree-{{ .Environment.CIRCLE_SHA1 }}
-      - checkout
-      - run:
-          name: tools
-          command: |
-            export PATH="$GOBIN:$PATH"
-            make get_tools
-      - run:
-          name: dependencies
-          command: |
-            export PATH="$GOBIN:$PATH"
-            make get_vendor_deps
-      - run: mkdir -p $GOPATH/src/github.com/tendermint
-      - run: ln -sf /home/circleci/project $GOPATH/src/github.com/tendermint/tendermint
-
+      - restore_cache:
+          key: v3-pkg-cache
+      - restore_cache:
+          key: v3-tree-{{ .Environment.CIRCLE_SHA1 }}
       - run:
           name: gather
           command: |

.github/CODEOWNERS

@@ -4,4 +4,6 @@
 *       @ebuchman @melekes @xla
 
 # Precious documentation
-/docs/  @zramsay
+/docs/README.md  @zramsay
+/docs/DOCS_README.md  @zramsay
+/docs/.vuepress/  @zramsay

.golangci.yml

@@ -0,0 +1,59 @@
+run:
+  deadline: 1m
+
+linters:
+  enable-all: true
+  disable:
+    - gocyclo
+    - golint
+    - maligned
+    - errcheck
+    - staticcheck
+    - dupl
+    - ineffassign
+    - interfacer
+    - unconvert
+    - goconst
+    - unparam
+    - nakedret
+    - lll
+    - gochecknoglobals
+    - gocritic
+    - gochecknoinits
+    - scopelint
+    - stylecheck
+
+# linters-settings:
+#   govet:
+#     check-shadowing: true
+#   golint:
+#     min-confidence: 0
+#   gocyclo:
+#     min-complexity: 10
+#   maligned:
+#     suggest-new: true
+#   dupl:
+#     threshold: 100
+#   goconst:
+#     min-len: 2
+#     min-occurrences: 2
+#   depguard:
+#     list-type: blacklist
+#     packages:
+#       # logging is allowed only by logutils.Log, logrus
+#       # is allowed to use only in logutils package
+#       - github.com/sirupsen/logrus
+#   misspell:
+#     locale: US
+#   lll:
+#     line-length: 140
+#   goimports:
+#     local-prefixes: github.com/golangci/golangci-lint
+#   gocritic:
+#     enabled-tags:
+#       - performance
+#       - style
+#       - experimental
+#     disabled-checks:
+#       - wrapperFunc
+#       - commentFormatting # https://github.com/go-critic/go-critic/issues/755

CHANGELOG.md

@@ -1,5 +1,124 @@
 # Changelog
 
+## v0.30.1
+
+*February 20th, 2019*
+
+This release fixes a consensus halt and a DataCorruptionError after restart
+discovered in `game_of_stakes_6`. It also fixes a security issue in the p2p
+handshake by authenticating the NetAddress.ID of the peer we're dialing.
+
+### IMPROVEMENTS:
+
+* [config] [\#3291](https://github.com/tendermint/tendermint/issues/3291) Make
+  config.ResetTestRootWithChainID() create concurrency-safe test directories.
+
+### BUG FIXES:
+
+* [consensus] [\#3295](https://github.com/tendermint/tendermint/issues/3295)
+  Flush WAL on stop to prevent data corruption during graceful shutdown.
+* [consensus] [\#3302](https://github.com/tendermint/tendermint/issues/3302)
+  Fix possible halt by resetting TriggeredTimeoutPrecommit before starting next height.
+* [rpc] [\#3251](https://github.com/tendermint/tendermint/issues/3251) Fix
+  `/net_info#peers#remote_ip` format. New format spec:
+  * dotted decimal ("192.0.2.1"), if ip is an IPv4 or IP4-mapped IPv6 address
+  * IPv6 ("2001:db8::1"), if ip is a valid IPv6 address
+* [cmd] [\#3314](https://github.com/tendermint/tendermint/issues/3314) Return
+  an error on `show_validator` when the private validator file does not exist.
+* [p2p] [\#3010](https://github.com/tendermint/tendermint/issues/3010#issuecomment-464287627)
+  Authenticate a peer against its NetAddress.ID when dialing.
+
+## v0.30.0
+
+*February 8th, 2019*
+
+This release fixes yet another issue with the proposer selection algorithm.
+We hope it's the last one, but we won't be surprised if it's not.
+We plan to one day expose the selection algorithm more directly to
+the application ([\#3285](https://github.com/tendermint/tendermint/issues/3285)), and even to support randomness ([\#763](https://github.com/tendermint/tendermint/issues/763)).
+For more, see issues marked
+[proposer-selection](https://github.com/tendermint/tendermint/labels/proposer-selection).
+
+This release also includes a fix to prevent Tendermint from including the same
+piece of evidence in more than one block. This issue was reported by @chengwenxi in our
+[bug bounty program](https://hackerone.com/tendermint).
+
+### BREAKING CHANGES:
+
+* Apps
+  - [state] [\#3222](https://github.com/tendermint/tendermint/issues/3222)
+    Duplicate updates for the same validator are forbidden. Apps must ensure
+    that a given `ResponseEndBlock.ValidatorUpdates` contains only one entry per pubkey.
+
+* Go API
+  - [types] [\#3222](https://github.com/tendermint/tendermint/issues/3222)
+    Remove `Add` and `Update` methods from `ValidatorSet` in favor of new
+    `UpdateWithChangeSet`. This allows updates to be applied as a set, instead of
+    one at a time.
+
+* Block Protocol
+  - [state] [\#3286](https://github.com/tendermint/tendermint/issues/3286) Blocks that include already committed evidence are invalid.
+
+* P2P Protocol
+  - [consensus] [\#3222](https://github.com/tendermint/tendermint/issues/3222)
+    Validator updates are applied as a set, instead of one at a time, thus
+    impacting the proposer priority calculation. This ensures that the proposer
+    selection algorithm does not depend on the order of updates in
+    `ResponseEndBlock.ValidatorUpdates`.
+
+### IMPROVEMENTS:
+- [crypto] [\#3279](https://github.com/tendermint/tendermint/issues/3279) Use `btcec.S256().N` directly instead of hard coding a copy.
+
+### BUG FIXES:
+- [state] [\#3222](https://github.com/tendermint/tendermint/issues/3222) Fix validator set updates so they are applied as a set, rather
+  than one at a time. This makes the proposer selection algorithm independent of
+  the order of updates in `ResponseEndBlock.ValidatorUpdates`.
+- [evidence] [\#3286](https://github.com/tendermint/tendermint/issues/3286) Don't add committed evidence to evidence pool.
+
+## v0.29.2
+
+*February 7th, 2019*
+
+Special thanks to external contributors on this release:
+@ackratos, @rickyyangz
+
+**Note**: This release contains security sensitive patches in the `p2p` and
+`crypto` packages:
+- p2p:
+  - Partial fix for MITM attacks on the p2p connection. MITM conditions may
+    still exist. See [\#3010](https://github.com/tendermint/tendermint/issues/3010).
+- crypto:
+  - Eliminate our fork of `btcd` and use the `btcd/btcec` library directly for
+    native secp256k1 signing. Note we still modify the signature encoding to
+    prevent malleability.
+  - Support the libsecp256k1 library via CGo through the `go-ethereum/crypto/secp256k1` package.
+  - Eliminate MixEntropy functions
+
+### BREAKING CHANGES:
+
+* Go API
+  - [crypto] [\#3278](https://github.com/tendermint/tendermint/issues/3278) Remove
+    MixEntropy functions
+  - [types] [\#3245](https://github.com/tendermint/tendermint/issues/3245) Commit uses `type CommitSig Vote` instead of `Vote` directly.
+    In preparation for removing redundant fields from the commit [\#1648](https://github.com/tendermint/tendermint/issues/1648)
+
+### IMPROVEMENTS:
+- [consensus] [\#3246](https://github.com/tendermint/tendermint/issues/3246) Better logging and notes on recovery for corrupted WAL file
+- [crypto] [\#3163](https://github.com/tendermint/tendermint/issues/3163) Use ethereum's libsecp256k1 go-wrapper for signatures when cgo is available
+- [crypto] [\#3162](https://github.com/tendermint/tendermint/issues/3162) Wrap btcd instead of forking it to keep up with fixes (used if cgo is not available)
+- [makefile] [\#3233](https://github.com/tendermint/tendermint/issues/3233) Use golangci-lint instead of go-metalinter
+- [tools] [\#3218](https://github.com/tendermint/tendermint/issues/3218) Add go-deadlock tool to help detect deadlocks
+- [tools] [\#3106](https://github.com/tendermint/tendermint/issues/3106) Add tm-signer-harness test harness for remote signers
+- [tests] [\#3258](https://github.com/tendermint/tendermint/issues/3258) Fixed a bunch of non-deterministic test failures
+
+### BUG FIXES:
+- [node] [\#3186](https://github.com/tendermint/tendermint/issues/3186) EventBus and indexerService should be started before first block (for replay last block on handshake) execution (@ackratos)
+- [p2p] [\#3232](https://github.com/tendermint/tendermint/issues/3232) Fix infinite loop leading to addrbook deadlock for seed nodes
+- [p2p] [\#3247](https://github.com/tendermint/tendermint/issues/3247) Fix panic in SeedMode when calling FlushStop and OnStop
+  concurrently
+- [p2p] [\#3040](https://github.com/tendermint/tendermint/issues/3040) Fix MITM on secret connection by checking low-order points
+- [privval] [\#3258](https://github.com/tendermint/tendermint/issues/3258) Fix race between sign requests and ping requests in socket that was causing messages to be corrupted
+
 ## v0.29.1
 
 *January 24, 2019*

CHANGELOG_PENDING.md

@@ -1,23 +1,34 @@
-## v0.30.0
+## v0.31.0
 
-*TBD*
+**
 
 Special thanks to external contributors on this release:
 
 ### BREAKING CHANGES:
 
 * CLI/RPC/Config
+- [httpclient] Update Subscribe interface to reflect new pubsub/eventBus API [ADR-33](https://github.com/tendermint/tendermint/blob/develop/docs/architecture/adr-033-pubsub.md)
 
 * Apps
 
 * Go API
+- [libs/common] TrapSignal accepts logger as a first parameter and does not block anymore
+  * previously it was dumping "captured ..." msg to os.Stdout
+  * TrapSignal should not be responsible for blocking thread of execution
 
 * Blockchain Protocol
 
 * P2P Protocol
 
 ### FEATURES:
+- [mempool] \#3079 bound mempool memory usage (`mempool.max_txs_bytes` is set to 1GB by default; see config.toml)
+  mempool's current `txs_total_bytes` is exposed via `total_bytes` field in
+  `/num_unconfirmed_txs` and `/unconfirmed_txs` RPC endpoints.
 
 ### IMPROVEMENTS:
+- [libs/common] \#3238 exit with zero (0) code upon receiving SIGTERM/SIGINT
 
 ### BUG FIXES:
+
+- [p2p/conn] \#3347 Reject all-zero shared secrets in the Diffie-Hellman step of secret-connection
+- [libs/pubsub] \#951, \#1880 use non-blocking send when dispatching messages [ADR-33](https://github.com/tendermint/tendermint/blob/develop/docs/architecture/adr-033-pubsub.md)

Gopkg.lock

@@ -10,12 +10,11 @@
   revision = "3a771d992973f24aa725d07868b467d1ddfceafb"
 
 [[projects]]
-  branch = "master"
-  digest = "1:c0decf632843204d2b8781de7b26e7038584e2dcccc7e2f401e88ae85b1df2b7"
+  digest = "1:093bf93a65962e8191e3e8cd8fc6c363f83d43caca9739c906531ba7210a9904"
   name = "github.com/btcsuite/btcd"
   packages = ["btcec"]
   pruneopts = "UT"
-  revision = "67e573d211ace594f1366b4ce9d39726c4b19bd0"
+  revision = "ed77733ec07dfc8a513741138419b8d9d3de9d2d"
 
 [[projects]]
   digest = "1:1d8e1cb71c33a9470bbbae09bfec09db43c6bf358dfcae13cd8807c4e2a9a2bf"
@@ -35,6 +34,14 @@
   revision = "8991bc29aa16c548c550c7ff78260e27b9ab7c73"
   version = "v1.1.1"
 
+[[projects]]
+  digest = "1:b42be5a3601f833e0b9f2d6625d887ec1309764bfcac3d518f3db425dcd4ec5c"
+  name = "github.com/ethereum/go-ethereum"
+  packages = ["crypto/secp256k1"]
+  pruneopts = "T"
+  revision = "9dc5d1a915ac0e0bd8429d6ac41df50eec91de5f"
+  version = "v1.8.21"
+
 [[projects]]
   digest = "1:544229a3ca0fb2dd5ebc2896d3d2ff7ce096d9751635301e44e37e761349ee70"
   name = "github.com/fortytw2/leaktest"
@@ -360,14 +367,6 @@
   pruneopts = "UT"
   revision = "6b91fda63f2e36186f1c9d0e48578defb69c5d43"
 
-[[projects]]
-  digest = "1:83f5e189eea2baad419a6a410984514266ff690075759c87e9ede596809bd0b8"
-  name = "github.com/tendermint/btcd"
-  packages = ["btcec"]
-  pruneopts = "UT"
-  revision = "80daadac05d1cd29571fccf27002d79667a88b58"
-  version = "v0.1.1"
-
 [[projects]]
   digest = "1:ad9c4c1a4e7875330b1f62906f2830f043a23edb5db997e3a5ac5d3e6eadf80a"
   name = "github.com/tendermint/go-amino"
@@ -504,8 +503,10 @@
   analyzer-name = "dep"
   analyzer-version = 1
   input-imports = [
+    "github.com/btcsuite/btcd/btcec",
     "github.com/btcsuite/btcutil/base58",
     "github.com/btcsuite/btcutil/bech32",
+    "github.com/ethereum/go-ethereum/crypto/secp256k1",
     "github.com/fortytw2/leaktest",
     "github.com/go-kit/kit/log",
     "github.com/go-kit/kit/log/level",
@@ -535,7 +536,6 @@
     "github.com/syndtr/goleveldb/leveldb/errors",
     "github.com/syndtr/goleveldb/leveldb/iterator",
     "github.com/syndtr/goleveldb/leveldb/opt",
-    "github.com/tendermint/btcd/btcec",
     "github.com/tendermint/go-amino",
     "golang.org/x/crypto/bcrypt",
     "golang.org/x/crypto/chacha20poly1305",

Gopkg.toml

@@ -75,14 +75,26 @@
   name = "github.com/prometheus/client_golang"
   version = "^0.9.1"
 
+# we use the secp256k1 implementation:
 [[constraint]]
-  name = "github.com/tendermint/btcd"
-  version = "v0.1.1"
+  name = "github.com/ethereum/go-ethereum"
+  version = "^v1.8.21"
+
+   # Prevent dep from pruning build scripts and codegen templates
+   # note: this leaves the whole go-ethereum package in vendor
+   # can be removed when https://github.com/golang/dep/issues/1847 is resolved
+   [[prune.project]]
+     name = "github.com/ethereum/go-ethereum"
+     unused-packages = false
 
 ###################################
 ## Some repos dont have releases.
 ## Pin to revision
 
+[[constraint]]
+  name = "github.com/btcsuite/btcd"
+  revision = "ed77733ec07dfc8a513741138419b8d9d3de9d2d"
+
 [[constraint]]
   name = "golang.org/x/crypto"
   revision = "505ab145d0a99da450461ae2c1a9f6cd10d1f447"

Makefile

@@ -1,7 +1,7 @@
 GOTOOLS = \
 	github.com/mitchellh/gox \
 	github.com/golang/dep/cmd/dep \
-	github.com/alecthomas/gometalinter \
+	github.com/golangci/golangci-lint/cmd/golangci-lint \
 	github.com/gogo/protobuf/protoc-gen-gogo \
 	github.com/square/certstrap
 GOBIN?=${GOPATH}/bin
@@ -11,8 +11,6 @@ INCLUDE = -I=. -I=${GOPATH}/src -I=${GOPATH}/src/github.com/gogo/protobuf/protob
 BUILD_TAGS?='tendermint'
 BUILD_FLAGS = -ldflags "-X github.com/tendermint/tendermint/version.GitCommit=`git rev-parse --short=8 HEAD`"
 
-LINT_FLAGS = --exclude '.*\.pb\.go' --exclude 'vendor/*' --vendor --deadline=600s
-
 all: check build test install
 
 check: check_tools get_vendor_deps
@@ -82,10 +80,6 @@ get_tools:
 	@echo "--> Installing tools"
 	./scripts/get_tools.sh
 
-get_dev_tools:
-	@echo "--> Downloading linters (this may take awhile)"
-	$(GOPATH)/src/github.com/alecthomas/gometalinter/scripts/install.sh -b $(GOBIN)
-
 update_tools:
 	@echo "--> Updating tools"
 	./scripts/get_tools.sh
@@ -226,6 +220,22 @@ test_race:
 	@echo "--> Running go test --race"
 	@GOCACHE=off go test -p 1 -v -race $(PACKAGES)
 
+# uses https://github.com/sasha-s/go-deadlock/ to detect potential deadlocks
+test_with_deadlock:
+	make set_with_deadlock
+	make test
+	make cleanup_after_test_with_deadlock
+
+set_with_deadlock:
+	find . -name "*.go" | grep -v "vendor/" | xargs -n 1 sed -i.bak 's/sync.RWMutex/deadlock.RWMutex/'
+	find . -name "*.go" | grep -v "vendor/" | xargs -n 1 sed -i.bak 's/sync.Mutex/deadlock.Mutex/'
+	find . -name "*.go" | grep -v "vendor/" | xargs -n 1 goimports -w
+
+# cleanes up after you ran test_with_deadlock
+cleanup_after_test_with_deadlock:
+	find . -name "*.go" | grep -v "vendor/" | xargs -n 1 sed -i.bak 's/deadlock.RWMutex/sync.RWMutex/'
+	find . -name "*.go" | grep -v "vendor/" | xargs -n 1 sed -i.bak 's/deadlock.Mutex/sync.Mutex/'
+	find . -name "*.go" | grep -v "vendor/" | xargs -n 1 goimports -w
 
 ########################################
 ### Formatting, linting, and vetting
@@ -233,38 +243,9 @@ test_race:
 fmt:
 	@go fmt ./...
 
-metalinter:
+lint:
 	@echo "--> Running linter"
-	@gometalinter $(LINT_FLAGS) --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 $(LINT_FLAGS) --enable-all --disable=lll ./...
+	@golangci-lint run
 
 DESTINATION = ./index.html.md
 
@@ -288,7 +269,7 @@ build-docker:
 ### Local testnet using docker
 
 # Build linux binary on other platforms
-build-linux:
+build-linux: get_tools get_vendor_deps
 	GOOS=linux GOARCH=amd64 $(MAKE) build
 
 build-docker-localnode:
@@ -330,4 +311,4 @@ build-slate:
 # 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 build_abci dist install install_abci check_dep check_tools get_tools get_dev_tools update_tools get_vendor_deps draw_deps get_protoc protoc_abci protoc_libs gen_certs clean_certs grpc_dbserver test_cover test_apps test_persistence test_p2p test test_race test_integrations test_release test100 vagrant_test fmt rpc-docs build-linux localnet-start localnet-stop build-docker build-docker-localnode sentry-start sentry-config sentry-stop build-slate protoc_grpc protoc_all build_c install_c
+.PHONY: check build build_race build_abci dist install install_abci check_dep check_tools get_tools update_tools get_vendor_deps draw_deps get_protoc protoc_abci protoc_libs gen_certs clean_certs grpc_dbserver test_cover test_apps test_persistence test_p2p test test_race test_integrations test_release test100 vagrant_test fmt rpc-docs build-linux localnet-start localnet-stop build-docker build-docker-localnode sentry-start sentry-config sentry-stop build-slate protoc_grpc protoc_all build_c install_c test_with_deadlock cleanup_after_test_with_deadlock lint

PHILOSOPHY.md

@@ -0,0 +1,158 @@
+## Design goals
+
+The design goals for Tendermint (and the SDK and related libraries) are:
+
+ * Simplicity and Legibility
+ * Parallel performance, namely ability to utilize multicore architecture
+ * Ability to evolve the codebase bug-free
+ * Debuggability
+ * Complete correctness that considers all edge cases, esp in concurrency
+ * Future-proof modular architecture, message protocol, APIs, and encapsulation
+
+
+### Justification
+
+Legibility is key to maintaining bug-free software as it evolves toward more
+optimizations, more ease of debugging, and additional features.
+
+It is too easy to introduce bugs over time by replacing lines of code with
+those that may panic, which means ideally locks are unlocked by defer
+statements.
+
+For example,
+
+```go
+func (obj *MyObj) something() {
+	mtx.Lock()
+	obj.something = other
+	mtx.Unlock()
+}
+```
+
+It is too easy to refactor the codebase in the future to replace `other` with
+`other.String()` for example, and this may introduce a bug that causes a
+deadlock.  So as much as reasonably possible, we need to be using defer
+statements, even though it introduces additional overhead.
+
+If it is necessary to optimize the unlocking of mutex locks, the solution is
+more modularity via smaller functions, so that defer'd unlocks are scoped
+within a smaller function.
+
+Similarly, idiomatic for-loops should always be preferred over those that use
+custom counters, because it is too easy to evolve the body of a for-loop to
+become more complicated over time, and it becomes more and more difficult to
+assess the correctness of such a for-loop by visual inspection.
+
+
+### On performance
+
+It doesn't matter whether there are alternative implementations that are 2x or
+3x more performant, when the software doesn't work, deadlocks, or if bugs
+cannot be debugged.  By taking advantage of multicore concurrency, the
+Tendermint implementation will at least be an order of magnitude within the
+range of what is theoretically possible.  The design philosophy of Tendermint,
+and the choice of Go as implementation language, is designed to make Tendermint
+implementation the standard specification for concurrent BFT software.
+
+By focusing on the message protocols (e.g. ABCI, p2p messages), and
+encapsulation e.g. IAVL module, (relatively) independent reactors, we are both
+implementing a standard implementation to be used as the specification for
+future implementations in more optimizable languages like Rust, Java, and C++;
+as well as creating sufficiently performant software. Tendermint Core will
+never be as fast as future implementations of the Tendermint Spec, because Go
+isn't designed to be as fast as possible.  The advantage of using Go is that we
+can develop the whole stack of modular components **faster** than in other
+languages.
+
+Furthermore, the real bottleneck is in the application layer, and it isn't
+necessary to support more than a sufficiently decentralized set of validators
+(e.g. 100 ~ 300 validators is sufficient, with delegated bonded PoS).
+
+Instead of optimizing Tendermint performance down to the metal, lets focus on
+optimizing on other matters, namely ability to push feature complete software
+that works well enough, can be debugged and maintained, and can serve as a spec
+for future implementations.
+
+
+### On encapsulation
+
+In order to create maintainable, forward-optimizable software, it is critical
+to develop well-encapsulated objects that have well understood properties, and
+to re-use these easy-to-use-correctly components as building blocks for further
+encapsulated meta-objects.
+
+For example, mutexes are cheap enough for Tendermint's design goals when there
+isn't goroutine contention, so it is encouraged to create concurrency safe
+structures with struct-level mutexes.  If they are used in the context of
+non-concurrent logic, then the performance is good enough.  If they are used in
+the context of concurrent logic, then it will still perform correctly.
+
+Examples of this design principle can be seen in the types.ValidatorSet struct,
+and the cmn.Rand struct.  It's one single struct declaration that can be used
+in both concurrent and non-concurrent logic, and due to its well encapsulation,
+it's easy to get the usage of the mutex right.
+
+#### example: cmn.Rand:
+
+`The default Source is safe for concurrent use by multiple goroutines, but
+Sources created by NewSource are not`.  The reason why the default
+package-level source is safe for concurrent use is because it is protected (see
+`lockedSource` in https://golang.org/src/math/rand/rand.go).
+
+But we shouldn't rely on the global source, we should be creating our own
+Rand/Source instances and using them, especially for determinism in testing.
+So it is reasonable to have cmn.Rand be protected by a mutex.  Whether we want
+our own implementation of Rand is another question, but the answer there is
+also in the affirmative.  Sometimes you want to know where Rand is being used
+in your code, so it becomes a simple matter of dropping in a log statement to
+inject inspectability into Rand usage.  Also, it is nice to be able to extend
+the functionality of Rand with custom methods.  For these reasons, and for the
+reasons which is outlined in this design philosophy document, we should
+continue to use the cmn.Rand object, with mutex protection.
+
+Another key aspect of good encapsulation is the choice of exposed vs unexposed
+methods.  It should be clear to the reader of the code, which methods are
+intended to be used in what context, and what safe usage is.  Part of this is
+solved by hiding methods via unexported methods.  Another part of this is
+naming conventions on the methods (e.g. underscores) with good documentation,
+and code organization.  If there are too many exposed methods and it isn't
+clear what methods have what side effects, then there is something wrong about
+the design of abstractions that should be revisited.
+
+
+### On concurrency
+
+In order for Tendermint to remain relevant in the years to come, it is vital
+for Tendermint to take advantage of multicore architectures.  Due to the nature
+of the problem, namely consensus across a concurrent p2p gossip network, and to
+handle RPC requests for a large number of consuming subscribers, it is
+unavoidable for Tendermint development to require expertise in concurrency
+design, especially when it comes to the reactor design, and also for RPC
+request handling.
+
+
+## Guidelines
+
+Here are some guidelines for designing for (sufficient) performance and concurrency:
+
+ * Mutex locks are cheap enough when there isn't contention.
+ * Do not optimize code without analytical or observed proof that it is in a hot path.
+ * Don't over-use channels when mutex locks w/ encapsulation are sufficient.
+ * The need to drain channels are often a hint of unconsidered edge cases.
+ * The creation of O(N) one-off goroutines is generally technical debt that
+   needs to get addressed sooner than later.  Avoid creating too many
+goroutines as a patch around incomplete concurrency design, or at least be
+aware of the debt and do not invest in the debt.  On the other hand, Tendermint
+is designed to have a limited number of peers (e.g. 10 or 20), so the creation
+of O(C) goroutines per O(P) peers is still O(C\*P=constant).
+  * Use defer statements to unlock as much as possible.  If you want to unlock sooner,
+    try to create more modular functions that do make use of defer statements.
+
+## Matras
+
+* Premature optimization kills
+* Readability is paramount
+* Beautiful is better than fast.
+* In the face of ambiguity, refuse the temptation to guess.
+* In the face of bugs, refuse the temptation to cover the bug.
+* There should be one-- and preferably only one --obvious way to do it.

README.md

@@ -96,6 +96,7 @@ include the in-process Go APIs.
 That said, breaking changes in the following packages will be documented in the
 CHANGELOG even if they don't lead to MINOR version bumps:
 
+- crypto
 - types
 - rpc/client
 - config

UPGRADING.md

@@ -3,6 +3,29 @@
 This guide provides steps to be followed when you upgrade your applications to
 a newer version of Tendermint Core.
 
+## v0.30.0
+
+This release contains a breaking change to both the block and p2p protocols,
+however it may be compatible with blockchains created with v0.29.0 depending on
+the chain history. If your blockchain has not included any pieces of evidence,
+or no piece of evidence has been included in more than one block,
+and if your application has never returned multiple updates
+for the same validator in a single block, then v0.30.0 will work fine with
+blockchains created with v0.29.0.
+
+The p2p protocol change is to fix the proposer selection algorithm again.
+Note that proposer selection is purely a p2p concern right
+now since the algorithm is only relevant during real time consensus.
+This change is thus compatible with v0.29.0, but
+all nodes must be upgraded to avoid disagreements on the proposer.
+
+### Applications
+
+Applications must ensure they do not return duplicates in
+`ResponseEndBlock.ValidatorUpdates`. A pubkey must only appear once per set of
+updates. Duplicates will cause irrecoverable failure. If you have a very good
+reason why we shouldn't do this, please open an issue.
+
 ## v0.29.0
 
 This release contains some breaking changes to the block and p2p protocols,

Vagrantfile

@@ -34,6 +34,10 @@ Vagrant.configure("2") do |config|
     mv go /usr/local
     rm -f go1.11.linux-amd64.tar.gz
 
+    # install nodejs (for docs)
+    curl -sL https://deb.nodesource.com/setup_11.x | bash -
+    apt-get install -y nodejs
+
     # cleanup
     apt-get autoremove -y
 
@@ -53,6 +57,6 @@ Vagrant.configure("2") do |config|
 
     # 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_dev_tools && make get_vendor_deps'
+    su - vagrant -c 'cd /home/vagrant/go/src/github.com/tendermint/tendermint && make get_tools && make get_vendor_deps'
   SHELL
 end

abci/client/grpc_client.go

@@ -129,7 +129,7 @@ func (cli *grpcClient) EchoAsync(msg string) *ReqRes {
 	if err != nil {
 		cli.StopForError(err)
 	}
-	return cli.finishAsyncCall(req, &types.Response{Value: &types.Response_Echo{res}})
+	return cli.finishAsyncCall(req, &types.Response{Value: &types.Response_Echo{Echo: res}})
 }
 
 func (cli *grpcClient) FlushAsync() *ReqRes {
@@ -138,7 +138,7 @@ func (cli *grpcClient) FlushAsync() *ReqRes {
 	if err != nil {
 		cli.StopForError(err)
 	}
-	return cli.finishAsyncCall(req, &types.Response{Value: &types.Response_Flush{res}})
+	return cli.finishAsyncCall(req, &types.Response{Value: &types.Response_Flush{Flush: res}})
 }
 
 func (cli *grpcClient) InfoAsync(params types.RequestInfo) *ReqRes {
@@ -147,7 +147,7 @@ func (cli *grpcClient) InfoAsync(params types.RequestInfo) *ReqRes {
 	if err != nil {
 		cli.StopForError(err)
 	}
-	return cli.finishAsyncCall(req, &types.Response{Value: &types.Response_Info{res}})
+	return cli.finishAsyncCall(req, &types.Response{Value: &types.Response_Info{Info: res}})
 }
 
 func (cli *grpcClient) SetOptionAsync(params types.RequestSetOption) *ReqRes {
@@ -156,7 +156,7 @@ func (cli *grpcClient) SetOptionAsync(params types.RequestSetOption) *ReqRes {
 	if err != nil {
 		cli.StopForError(err)
 	}
-	return cli.finishAsyncCall(req, &types.Response{Value: &types.Response_SetOption{res}})
+	return cli.finishAsyncCall(req, &types.Response{Value: &types.Response_SetOption{SetOption: res}})
 }
 
 func (cli *grpcClient) DeliverTxAsync(tx []byte) *ReqRes {
@@ -165,7 +165,7 @@ func (cli *grpcClient) DeliverTxAsync(tx []byte) *ReqRes {
 	if err != nil {
 		cli.StopForError(err)
 	}
-	return cli.finishAsyncCall(req, &types.Response{Value: &types.Response_DeliverTx{res}})
+	return cli.finishAsyncCall(req, &types.Response{Value: &types.Response_DeliverTx{DeliverTx: res}})
 }
 
 func (cli *grpcClient) CheckTxAsync(tx []byte) *ReqRes {
@@ -174,7 +174,7 @@ func (cli *grpcClient) CheckTxAsync(tx []byte) *ReqRes {
 	if err != nil {
 		cli.StopForError(err)
 	}
-	return cli.finishAsyncCall(req, &types.Response{Value: &types.Response_CheckTx{res}})
+	return cli.finishAsyncCall(req, &types.Response{Value: &types.Response_CheckTx{CheckTx: res}})
 }
 
 func (cli *grpcClient) QueryAsync(params types.RequestQuery) *ReqRes {
@@ -183,7 +183,7 @@ func (cli *grpcClient) QueryAsync(params types.RequestQuery) *ReqRes {
 	if err != nil {
 		cli.StopForError(err)
 	}
-	return cli.finishAsyncCall(req, &types.Response{Value: &types.Response_Query{res}})
+	return cli.finishAsyncCall(req, &types.Response{Value: &types.Response_Query{Query: res}})
 }
 
 func (cli *grpcClient) CommitAsync() *ReqRes {
@@ -192,7 +192,7 @@ func (cli *grpcClient) CommitAsync() *ReqRes {
 	if err != nil {
 		cli.StopForError(err)
 	}
-	return cli.finishAsyncCall(req, &types.Response{Value: &types.Response_Commit{res}})
+	return cli.finishAsyncCall(req, &types.Response{Value: &types.Response_Commit{Commit: res}})
 }
 
 func (cli *grpcClient) InitChainAsync(params types.RequestInitChain) *ReqRes {
@@ -201,7 +201,7 @@ func (cli *grpcClient) InitChainAsync(params types.RequestInitChain) *ReqRes {
 	if err != nil {
 		cli.StopForError(err)
 	}
-	return cli.finishAsyncCall(req, &types.Response{Value: &types.Response_InitChain{res}})
+	return cli.finishAsyncCall(req, &types.Response{Value: &types.Response_InitChain{InitChain: res}})
 }
 
 func (cli *grpcClient) BeginBlockAsync(params types.RequestBeginBlock) *ReqRes {
@@ -210,7 +210,7 @@ func (cli *grpcClient) BeginBlockAsync(params types.RequestBeginBlock) *ReqRes {
 	if err != nil {
 		cli.StopForError(err)
 	}
-	return cli.finishAsyncCall(req, &types.Response{Value: &types.Response_BeginBlock{res}})
+	return cli.finishAsyncCall(req, &types.Response{Value: &types.Response_BeginBlock{BeginBlock: res}})
 }
 
 func (cli *grpcClient) EndBlockAsync(params types.RequestEndBlock) *ReqRes {
@@ -219,7 +219,7 @@ func (cli *grpcClient) EndBlockAsync(params types.RequestEndBlock) *ReqRes {
 	if err != nil {
 		cli.StopForError(err)
 	}
-	return cli.finishAsyncCall(req, &types.Response{Value: &types.Response_EndBlock{res}})
+	return cli.finishAsyncCall(req, &types.Response{Value: &types.Response_EndBlock{EndBlock: res}})
 }
 
 func (cli *grpcClient) finishAsyncCall(req *types.Request, res *types.Response) *ReqRes {

abci/cmd/abci-cli/abci-cli.go

@@ -394,7 +394,6 @@ func cmdConsole(cmd *cobra.Command, args []string) error {
 			return err
 		}
 	}
-	return nil
 }
 
 func muxOnCommands(cmd *cobra.Command, pArgs []string) error {
@@ -637,9 +636,7 @@ func cmdQuery(cmd *cobra.Command, args []string) error {
 }
 
 func cmdCounter(cmd *cobra.Command, args []string) error {
-
 	app := counter.NewCounterApplication(flagSerial)
-
 	logger := log.NewTMLogger(log.NewSyncWriter(os.Stdout))
 
 	// Start the listener
@@ -652,12 +649,14 @@ func cmdCounter(cmd *cobra.Command, args []string) error {
 		return err
 	}
 
-	// Wait forever
-	cmn.TrapSignal(func() {
+	// Stop upon receiving SIGTERM or CTRL-C.
+	cmn.TrapSignal(logger, func() {
 		// Cleanup
 		srv.Stop()
 	})
-	return nil
+
+	// Run forever.
+	select {}
 }
 
 func cmdKVStore(cmd *cobra.Command, args []string) error {
@@ -682,12 +681,14 @@ func cmdKVStore(cmd *cobra.Command, args []string) error {
 		return err
 	}
 
-	// Wait forever
-	cmn.TrapSignal(func() {
+	// Stop upon receiving SIGTERM or CTRL-C.
+	cmn.TrapSignal(logger, func() {
 		// Cleanup
 		srv.Stop()
 	})
-	return nil
+
+	// Run forever.
+	select {}
 }
 
 //--------------------------------------------------------------------------------

abci/types/messages_test.go

@@ -83,7 +83,7 @@ func TestWriteReadMessage2(t *testing.T) {
 			Log:       phrase,
 			GasWanted: 10,
 			Tags: []cmn.KVPair{
-				cmn.KVPair{Key: []byte("abc"), Value: []byte("def")},
+				{Key: []byte("abc"), Value: []byte("def")},
 			},
 		},
 		// TODO: add the rest

benchmarks/codec_test.go

@@ -4,7 +4,7 @@ import (
 	"testing"
 	"time"
 
-	"github.com/tendermint/go-amino"
+	amino "github.com/tendermint/go-amino"
 
 	proto "github.com/tendermint/tendermint/benchmarks/proto"
 	"github.com/tendermint/tendermint/crypto/ed25519"

blockchain/pool.go

@@ -363,7 +363,8 @@ func (pool *BlockPool) sendError(err error, peerID p2p.ID) {
 	pool.errorsCh <- peerError{err, peerID}
 }
 
-// unused by tendermint; left for debugging purposes
+// for debugging purposes
+//nolint:unused
 func (pool *BlockPool) debug() string {
 	pool.mtx.Lock()
 	defer pool.mtx.Unlock()

blockchain/reactor.go

@@ -8,7 +8,6 @@ import (
 
 	amino "github.com/tendermint/go-amino"
 
-	cmn "github.com/tendermint/tendermint/libs/common"
 	"github.com/tendermint/tendermint/libs/log"
 	"github.com/tendermint/tendermint/p2p"
 	sm "github.com/tendermint/tendermint/state"
@@ -302,7 +301,7 @@ FOR_LOOP:
 
 			firstParts := first.MakePartSet(types.BlockPartSizeBytes)
 			firstPartsHeader := firstParts.Header()
-			firstID := types.BlockID{first.Hash(), firstPartsHeader}
+			firstID := types.BlockID{Hash: first.Hash(), PartsHeader: 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
@@ -338,8 +337,7 @@ FOR_LOOP:
 				state, err = bcR.blockExec.ApplyBlock(state, firstID, first)
 				if err != nil {
 					// TODO This is bad, are we zombie?
-					cmn.PanicQ(fmt.Sprintf("Failed to process committed block (%d:%X): %v",
-						first.Height, first.Hash(), err))
+					panic(fmt.Sprintf("Failed to process committed block (%d:%X): %v", first.Height, first.Hash(), err))
 				}
 				blocksSynced++
 

blockchain/reactor_test.go

@@ -1,6 +1,7 @@
 package blockchain
 
 import (
+	"os"
 	"sort"
 	"testing"
 	"time"
@@ -95,13 +96,13 @@ func newBlockchainReactor(logger log.Logger, genDoc *types.GenesisDoc, privVals
 
 	// let's add some blocks in
 	for blockHeight := int64(1); blockHeight <= maxBlockHeight; blockHeight++ {
-		lastCommit := &types.Commit{}
+		lastCommit := types.NewCommit(types.BlockID{}, nil)
 		if blockHeight > 1 {
 			lastBlockMeta := blockStore.LoadBlockMeta(blockHeight - 1)
 			lastBlock := blockStore.LoadBlock(blockHeight - 1)
 
-			vote := makeVote(&lastBlock.Header, lastBlockMeta.BlockID, state.Validators, privVals[0])
-			lastCommit = &types.Commit{Precommits: []*types.Vote{vote}, BlockID: lastBlockMeta.BlockID}
+			vote := makeVote(&lastBlock.Header, lastBlockMeta.BlockID, state.Validators, privVals[0]).CommitSig()
+			lastCommit = types.NewCommit(lastBlockMeta.BlockID, []*types.CommitSig{vote})
 		}
 
 		thisBlock := makeBlock(blockHeight, state, lastCommit)
@@ -125,6 +126,7 @@ func newBlockchainReactor(logger log.Logger, genDoc *types.GenesisDoc, privVals
 
 func TestNoBlockResponse(t *testing.T) {
 	config = cfg.ResetTestRoot("blockchain_reactor_test")
+	defer os.RemoveAll(config.RootDir)
 	genDoc, privVals := randGenesisDoc(1, false, 30)
 
 	maxBlockHeight := int64(65)
@@ -184,6 +186,7 @@ func TestNoBlockResponse(t *testing.T) {
 // that seems extreme.
 func TestBadBlockStopsPeer(t *testing.T) {
 	config = cfg.ResetTestRoot("blockchain_reactor_test")
+	defer os.RemoveAll(config.RootDir)
 	genDoc, privVals := randGenesisDoc(1, false, 30)
 
 	maxBlockHeight := int64(148)

blockchain/store_test.go

@@ -3,9 +3,11 @@ package blockchain
 import (
 	"bytes"
 	"fmt"
+	"os"
 	"runtime/debug"
 	"strings"
 	"testing"
+	"time"
 
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
@@ -20,7 +22,17 @@ import (
 	tmtime "github.com/tendermint/tendermint/types/time"
 )
 
-func makeStateAndBlockStore(logger log.Logger) (sm.State, *BlockStore) {
+// A cleanupFunc cleans up any config / test files created for a particular
+// test.
+type cleanupFunc func()
+
+// make a Commit with a single vote containing just the height and a timestamp
+func makeTestCommit(height int64, timestamp time.Time) *types.Commit {
+	commitSigs := []*types.CommitSig{{Height: height, Timestamp: timestamp}}
+	return types.NewCommit(types.BlockID{}, commitSigs)
+}
+
+func makeStateAndBlockStore(logger log.Logger) (sm.State, *BlockStore, cleanupFunc) {
 	config := cfg.ResetTestRoot("blockchain_reactor_test")
 	// blockDB := dbm.NewDebugDB("blockDB", dbm.NewMemDB())
 	// stateDB := dbm.NewDebugDB("stateDB", dbm.NewMemDB())
@@ -30,7 +42,7 @@ func makeStateAndBlockStore(logger log.Logger) (sm.State, *BlockStore) {
 	if err != nil {
 		panic(cmn.ErrorWrap(err, "error constructing state from genesis file"))
 	}
-	return state, NewBlockStore(blockDB)
+	return state, NewBlockStore(blockDB), func() { os.RemoveAll(config.RootDir) }
 }
 
 func TestLoadBlockStoreStateJSON(t *testing.T) {
@@ -80,20 +92,32 @@ func freshBlockStore() (*BlockStore, db.DB) {
 }
 
 var (
-	state, _ = makeStateAndBlockStore(log.NewTMLogger(new(bytes.Buffer)))
-
-	block       = makeBlock(1, state, new(types.Commit))
-	partSet     = block.MakePartSet(2)
-	part1       = partSet.GetPart(0)
-	part2       = partSet.GetPart(1)
-	seenCommit1 = &types.Commit{Precommits: []*types.Vote{{Height: 10,
-		Timestamp: tmtime.Now()}}}
+	state       sm.State
+	block       *types.Block
+	partSet     *types.PartSet
+	part1       *types.Part
+	part2       *types.Part
+	seenCommit1 *types.Commit
 )
 
+func TestMain(m *testing.M) {
+	var cleanup cleanupFunc
+	state, _, cleanup = makeStateAndBlockStore(log.NewTMLogger(new(bytes.Buffer)))
+	block = makeBlock(1, state, new(types.Commit))
+	partSet = block.MakePartSet(2)
+	part1 = partSet.GetPart(0)
+	part2 = partSet.GetPart(1)
+	seenCommit1 = makeTestCommit(10, tmtime.Now())
+	code := m.Run()
+	cleanup()
+	os.Exit(code)
+}
+
 // TODO: This test should be simplified ...
 
 func TestBlockStoreSaveLoadBlock(t *testing.T) {
-	state, bs := makeStateAndBlockStore(log.NewTMLogger(new(bytes.Buffer)))
+	state, bs, cleanup := makeStateAndBlockStore(log.NewTMLogger(new(bytes.Buffer)))
+	defer cleanup()
 	require.Equal(t, bs.Height(), int64(0), "initially the height should be zero")
 
 	// check there are no blocks at various heights
@@ -107,8 +131,7 @@ func TestBlockStoreSaveLoadBlock(t *testing.T) {
 	// save a block
 	block := makeBlock(bs.Height()+1, state, new(types.Commit))
 	validPartSet := block.MakePartSet(2)
-	seenCommit := &types.Commit{Precommits: []*types.Vote{{Height: 10,
-		Timestamp: tmtime.Now()}}}
+	seenCommit := makeTestCommit(10, tmtime.Now())
 	bs.SaveBlock(block, partSet, seenCommit)
 	require.Equal(t, bs.Height(), block.Header.Height, "expecting the new height to be changed")
 
@@ -127,8 +150,7 @@ func TestBlockStoreSaveLoadBlock(t *testing.T) {
 
 	// End of setup, test data
 
-	commitAtH10 := &types.Commit{Precommits: []*types.Vote{{Height: 10,
-		Timestamp: tmtime.Now()}}}
+	commitAtH10 := makeTestCommit(10, tmtime.Now())
 	tuples := []struct {
 		block      *types.Block
 		parts      *types.PartSet
@@ -346,14 +368,13 @@ func TestLoadBlockMeta(t *testing.T) {
 }
 
 func TestBlockFetchAtHeight(t *testing.T) {
-	state, bs := makeStateAndBlockStore(log.NewTMLogger(new(bytes.Buffer)))
+	state, bs, cleanup := makeStateAndBlockStore(log.NewTMLogger(new(bytes.Buffer)))
+	defer cleanup()
 	require.Equal(t, bs.Height(), int64(0), "initially the height should be zero")
 	block := makeBlock(bs.Height()+1, state, new(types.Commit))
 
 	partSet := block.MakePartSet(2)
-	seenCommit := &types.Commit{Precommits: []*types.Vote{{Height: 10,
-		Timestamp: tmtime.Now()}}}
-
+	seenCommit := makeTestCommit(10, tmtime.Now())
 	bs.SaveBlock(block, partSet, seenCommit)
 	require.Equal(t, bs.Height(), block.Header.Height, "expecting the new height to be changed")
 

blockchain/wire.go

@@ -1,7 +1,7 @@
 package blockchain
 
 import (
-	"github.com/tendermint/go-amino"
+	amino "github.com/tendermint/go-amino"
 	"github.com/tendermint/tendermint/types"
 )
 

cmd/priv_val_server/main.go

@@ -35,7 +35,7 @@ func main() {
 
 	pv := privval.LoadFilePV(*privValKeyPath, *privValStatePath)
 
-	var dialer privval.Dialer
+	var dialer privval.SocketDialer
 	protocol, address := cmn.ProtocolAndAddress(*addr)
 	switch protocol {
 	case "unix":
@@ -48,16 +48,20 @@ func main() {
 		os.Exit(1)
 	}
 
-	rs := privval.NewRemoteSigner(logger, *chainID, pv, dialer)
+	rs := privval.NewSignerServiceEndpoint(logger, *chainID, pv, dialer)
 	err := rs.Start()
 	if err != nil {
 		panic(err)
 	}
 
-	cmn.TrapSignal(func() {
+	// Stop upon receiving SIGTERM or CTRL-C.
+	cmn.TrapSignal(logger, func() {
 		err := rs.Stop()
 		if err != nil {
 			panic(err)
 		}
 	})
+
+	// Run forever.
+	select {}
 }

cmd/tendermint/commands/lite.go

@@ -59,6 +59,11 @@ func ensureAddrHasSchemeOrDefaultToTCP(addr string) (string, error) {
 }
 
 func runProxy(cmd *cobra.Command, args []string) error {
+	// Stop upon receiving SIGTERM or CTRL-C.
+	cmn.TrapSignal(logger, func() {
+		// TODO: close up shop
+	})
+
 	nodeAddr, err := ensureAddrHasSchemeOrDefaultToTCP(nodeAddr)
 	if err != nil {
 		return err
@@ -86,9 +91,6 @@ func runProxy(cmd *cobra.Command, args []string) error {
 		return cmn.ErrorWrap(err, "starting proxy")
 	}
 
-	cmn.TrapSignal(func() {
-		// TODO: close up shop
-	})
-
-	return nil
+	// Run forever
+	select {}
 }

cmd/tendermint/commands/reset_priv_validator.go

@@ -61,7 +61,7 @@ func resetFilePV(privValKeyFile, privValStateFile string, logger log.Logger) {
 	} else {
 		pv := privval.GenFilePV(privValKeyFile, privValStateFile)
 		pv.Save()
-		logger.Info("Generated private validator file", "file", "keyFile", privValKeyFile,
+		logger.Info("Generated private validator file", "keyFile", privValKeyFile,
 			"stateFile", privValStateFile)
 	}
 }

cmd/tendermint/commands/root_test.go

@@ -22,10 +22,6 @@ var (
 	defaultRoot = os.ExpandEnv("$HOME/.some/test/dir")
 )
 
-const (
-	rootName = "root"
-)
-
 // clearConfig clears env vars, the given root dir, and resets viper.
 func clearConfig(dir string) {
 	if err := os.Unsetenv("TMHOME"); err != nil {

cmd/tendermint/commands/run_node.go

@@ -2,12 +2,10 @@ package commands
 
 import (
 	"fmt"
-	"os"
-	"os/signal"
-	"syscall"
 
 	"github.com/spf13/cobra"
 
+	cmn "github.com/tendermint/tendermint/libs/common"
 	nm "github.com/tendermint/tendermint/node"
 )
 
@@ -57,28 +55,20 @@ func NewRunNodeCmd(nodeProvider nm.NodeProvider) *cobra.Command {
 				return fmt.Errorf("Failed to create node: %v", err)
 			}
 
-			// Stop upon receiving SIGTERM or CTRL-C
-			c := make(chan os.Signal, 1)
-			signal.Notify(c, os.Interrupt, syscall.SIGTERM)
-			go func() {
-				for sig := range c {
-					logger.Error(fmt.Sprintf("captured %v, exiting...", sig))
-					if n.IsRunning() {
-						n.Stop()
-					}
-					os.Exit(1)
+			// Stop upon receiving SIGTERM or CTRL-C.
+			cmn.TrapSignal(logger, func() {
+				if n.IsRunning() {
+					n.Stop()
 				}
-			}()
+			})
 
 			if err := n.Start(); err != nil {
 				return fmt.Errorf("Failed to start node: %v", err)
 			}
 			logger.Info("Started node", "nodeInfo", n.Switch().NodeInfo())
 
-			// Run forever
+			// Run forever.
 			select {}
-
-			return nil
 		},
 	}
 

cmd/tendermint/commands/show_node_id.go

@@ -16,12 +16,11 @@ var ShowNodeIDCmd = &cobra.Command{
 }
 
 func showNodeID(cmd *cobra.Command, args []string) error {
-
 	nodeKey, err := p2p.LoadNodeKey(config.NodeKeyFile())
 	if err != nil {
 		return err
 	}
-	fmt.Println(nodeKey.ID())
 
+	fmt.Println(nodeKey.ID())
 	return nil
 }

cmd/tendermint/commands/show_validator.go

@@ -3,8 +3,10 @@ package commands
 import (
 	"fmt"
 
+	"github.com/pkg/errors"
 	"github.com/spf13/cobra"
 
+	cmn "github.com/tendermint/tendermint/libs/common"
 	"github.com/tendermint/tendermint/privval"
 )
 
@@ -12,11 +14,21 @@ import (
 var ShowValidatorCmd = &cobra.Command{
 	Use:   "show_validator",
 	Short: "Show this node's validator info",
-	Run:   showValidator,
+	RunE:  showValidator,
 }
 
-func showValidator(cmd *cobra.Command, args []string) {
-	privValidator := privval.LoadOrGenFilePV(config.PrivValidatorKeyFile(), config.PrivValidatorStateFile())
-	pubKeyJSONBytes, _ := cdc.MarshalJSON(privValidator.GetPubKey())
-	fmt.Println(string(pubKeyJSONBytes))
+func showValidator(cmd *cobra.Command, args []string) error {
+	keyFilePath := config.PrivValidatorKeyFile()
+	if !cmn.FileExists(keyFilePath) {
+		return fmt.Errorf("private validator file %s does not exist", keyFilePath)
+	}
+
+	pv := privval.LoadFilePV(keyFilePath, config.PrivValidatorStateFile())
+	bz, err := cdc.MarshalJSON(pv.GetPubKey())
+	if err != nil {
+		return errors.Wrap(err, "failed to marshal private validator pubkey")
+	}
+
+	fmt.Println(string(bz))
+	return nil
 }

cmd/tendermint/commands/wire.go

@@ -1,7 +1,7 @@
 package commands
 
 import (
-	"github.com/tendermint/go-amino"
+	amino "github.com/tendermint/go-amino"
 	cryptoAmino "github.com/tendermint/tendermint/crypto/encoding/amino"
 )
 

config/config.go

@@ -530,12 +530,13 @@ func DefaultFuzzConnConfig() *FuzzConnConfig {
 
 // MempoolConfig defines the configuration options for the Tendermint mempool
 type MempoolConfig struct {
-	RootDir   string `mapstructure:"home"`
-	Recheck   bool   `mapstructure:"recheck"`
-	Broadcast bool   `mapstructure:"broadcast"`
-	WalPath   string `mapstructure:"wal_dir"`
-	Size      int    `mapstructure:"size"`
-	CacheSize int    `mapstructure:"cache_size"`
+	RootDir     string `mapstructure:"home"`
+	Recheck     bool   `mapstructure:"recheck"`
+	Broadcast   bool   `mapstructure:"broadcast"`
+	WalPath     string `mapstructure:"wal_dir"`
+	Size        int    `mapstructure:"size"`
+	MaxTxsBytes int64  `mapstructure:"max_txs_bytes"`
+	CacheSize   int    `mapstructure:"cache_size"`
 }
 
 // DefaultMempoolConfig returns a default configuration for the Tendermint mempool
@@ -544,10 +545,11 @@ func DefaultMempoolConfig() *MempoolConfig {
 		Recheck:   true,
 		Broadcast: true,
 		WalPath:   "",
-		// Each signature verification takes .5ms, size reduced until we implement
+		// Each signature verification takes .5ms, Size reduced until we implement
 		// ABCI Recheck
-		Size:      5000,
-		CacheSize: 10000,
+		Size:        5000,
+		MaxTxsBytes: 1024 * 1024 * 1024, // 1GB
+		CacheSize:   10000,
 	}
 }
 
@@ -574,6 +576,9 @@ func (cfg *MempoolConfig) ValidateBasic() error {
 	if cfg.Size < 0 {
 		return errors.New("size can't be negative")
 	}
+	if cfg.MaxTxsBytes < 0 {
+		return errors.New("max_txs_bytes can't be negative")
+	}
 	if cfg.CacheSize < 0 {
 		return errors.New("cache_size can't be negative")
 	}

config/toml.go

@@ -2,13 +2,17 @@ package config
 
 import (
 	"bytes"
-	"os"
+	"fmt"
+	"io/ioutil"
 	"path/filepath"
 	"text/template"
 
 	cmn "github.com/tendermint/tendermint/libs/common"
 )
 
+// DefaultDirPerm is the default permissions used when creating directories.
+const DefaultDirPerm = 0700
+
 var configTemplate *template.Template
 
 func init() {
@@ -23,13 +27,13 @@ func init() {
 // 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 {
+	if err := cmn.EnsureDir(rootDir, DefaultDirPerm); err != nil {
 		cmn.PanicSanity(err.Error())
 	}
-	if err := cmn.EnsureDir(filepath.Join(rootDir, defaultConfigDir), 0700); err != nil {
+	if err := cmn.EnsureDir(filepath.Join(rootDir, defaultConfigDir), DefaultDirPerm); err != nil {
 		cmn.PanicSanity(err.Error())
 	}
-	if err := cmn.EnsureDir(filepath.Join(rootDir, defaultDataDir), 0700); err != nil {
+	if err := cmn.EnsureDir(filepath.Join(rootDir, defaultDataDir), DefaultDirPerm); err != nil {
 		cmn.PanicSanity(err.Error())
 	}
 
@@ -233,10 +237,15 @@ recheck = {{ .Mempool.Recheck }}
 broadcast = {{ .Mempool.Broadcast }}
 wal_dir = "{{ js .Mempool.WalPath }}"
 
-# size of the mempool
+# Maximum number of transactions in the mempool
 size = {{ .Mempool.Size }}
 
-# size of the cache (used to filter transactions we saw earlier)
+# Limit the total size of all txs in the mempool.
+# This only accounts for raw transactions (e.g. given 1MB transactions and
+# max_txs_bytes=5MB, mempool will only accept 5 transactions).
+max_txs_bytes = {{ .Mempool.MaxTxsBytes }}
+
+# Size of the cache (used to filter transactions we saw earlier) in transactions
 cache_size = {{ .Mempool.CacheSize }}
 
 ##### consensus configuration options #####
@@ -317,29 +326,21 @@ namespace = "{{ .Instrumentation.Namespace }}"
 /****** these are for test settings ***********/
 
 func ResetTestRoot(testName string) *Config {
-	rootDir := os.ExpandEnv("$HOME/.tendermint_test")
-	rootDir = filepath.Join(rootDir, testName)
-	// Remove ~/.tendermint_test_bak
-	if cmn.FileExists(rootDir + "_bak") {
-		if err := os.RemoveAll(rootDir + "_bak"); err != nil {
-			cmn.PanicSanity(err.Error())
-		}
+	return ResetTestRootWithChainID(testName, "")
+}
+
+func ResetTestRootWithChainID(testName string, chainID string) *Config {
+	// create a unique, concurrency-safe test directory under os.TempDir()
+	rootDir, err := ioutil.TempDir("", fmt.Sprintf("%s-%s_", chainID, testName))
+	if err != nil {
+		panic(err)
 	}
-	// Move ~/.tendermint_test to ~/.tendermint_test_bak
-	if cmn.FileExists(rootDir) {
-		if err := os.Rename(rootDir, rootDir+"_bak"); err != nil {
-			cmn.PanicSanity(err.Error())
-		}
+	// ensure config and data subdirs are created
+	if err := cmn.EnsureDir(filepath.Join(rootDir, defaultConfigDir), DefaultDirPerm); err != nil {
+		panic(err)
 	}
-	// Create new dir
-	if err := cmn.EnsureDir(rootDir, 0700); err != nil {
-		cmn.PanicSanity(err.Error())
-	}
-	if err := cmn.EnsureDir(filepath.Join(rootDir, defaultConfigDir), 0700); err != nil {
-		cmn.PanicSanity(err.Error())
-	}
-	if err := cmn.EnsureDir(filepath.Join(rootDir, defaultDataDir), 0700); err != nil {
-		cmn.PanicSanity(err.Error())
+	if err := cmn.EnsureDir(filepath.Join(rootDir, defaultDataDir), DefaultDirPerm); err != nil {
+		panic(err)
 	}
 
 	baseConfig := DefaultBaseConfig()
@@ -353,6 +354,10 @@ func ResetTestRoot(testName string) *Config {
 		writeDefaultConfigFile(configFilePath)
 	}
 	if !cmn.FileExists(genesisFilePath) {
+		if chainID == "" {
+			chainID = "tendermint_test"
+		}
+		testGenesis := fmt.Sprintf(testGenesisFmt, chainID)
 		cmn.MustWriteFile(genesisFilePath, []byte(testGenesis), 0644)
 	}
 	// we always overwrite the priv val
@@ -363,9 +368,9 @@ func ResetTestRoot(testName string) *Config {
 	return config
 }
 
-var testGenesis = `{
+var testGenesisFmt = `{
   "genesis_time": "2018-10-10T08:20:13.695936996Z",
-  "chain_id": "tendermint_test",
+  "chain_id": "%s",
   "validators": [
     {
       "pub_key": {

config/toml_test.go

@@ -48,6 +48,7 @@ func TestEnsureTestRoot(t *testing.T) {
 
 	// create root dir
 	cfg := ResetTestRoot(testName)
+	defer os.RemoveAll(cfg.RootDir)
 	rootDir := cfg.RootDir
 
 	// make sure config is set properly

consensus/byzantine_test.go

@@ -13,10 +13,6 @@ import (
 	"github.com/tendermint/tendermint/types"
 )
 
-func init() {
-	config = ResetConfig("consensus_byzantine_test")
-}
-
 //----------------------------------------------
 // byzantine failures
 
@@ -29,7 +25,8 @@ func init() {
 func TestByzantine(t *testing.T) {
 	N := 4
 	logger := consensusLogger().With("test", "byzantine")
-	css := randConsensusNet(N, "consensus_byzantine_test", newMockTickerFunc(false), newCounter)
+	css, cleanup := randConsensusNet(N, "consensus_byzantine_test", newMockTickerFunc(false), newCounter)
+	defer cleanup()
 
 	// give the byzantine validator a normal ticker
 	ticker := NewTimeoutTicker()
@@ -49,7 +46,7 @@ func TestByzantine(t *testing.T) {
 		switches[i].SetLogger(p2pLogger.With("validator", i))
 	}
 
-	eventChans := make([]chan interface{}, N)
+	blocksSubs := make([]types.Subscription, N)
 	reactors := make([]p2p.Reactor, N)
 	for i := 0; i < N; i++ {
 		// make first val byzantine
@@ -68,16 +65,15 @@ func TestByzantine(t *testing.T) {
 		eventBus := css[i].eventBus
 		eventBus.SetLogger(logger.With("module", "events", "validator", i))
 
-		eventChans[i] = make(chan interface{}, 1)
-		err := eventBus.Subscribe(context.Background(), testSubscriber, types.EventQueryNewBlock, eventChans[i])
+		var err error
+		blocksSubs[i], err = eventBus.Subscribe(context.Background(), testSubscriber, types.EventQueryNewBlock)
 		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
+		var conRI p2p.Reactor = conR
 
 		// make first val byzantine
 		if i == 0 {
@@ -135,7 +131,7 @@ func TestByzantine(t *testing.T) {
 	p2p.Connect2Switches(switches, ind1, ind2)
 
 	// wait for someone in the big partition (B) to make a block
-	<-eventChans[ind2]
+	<-blocksSubs[ind2].Out()
 
 	t.Log("A block has been committed. Healing partition")
 	p2p.Connect2Switches(switches, ind0, ind1)
@@ -147,7 +143,7 @@ func TestByzantine(t *testing.T) {
 	wg.Add(2)
 	for i := 1; i < N-1; i++ {
 		go func(j int) {
-			<-eventChans[j]
+			<-blocksSubs[j].Out()
 			wg.Done()
 		}(i)
 	}

consensus/common_test.go

@@ -7,7 +7,6 @@ import (
 	"io/ioutil"
 	"os"
 	"path/filepath"
-	"reflect"
 	"sort"
 	"sync"
 	"testing"
@@ -25,6 +24,7 @@ import (
 	cmn "github.com/tendermint/tendermint/libs/common"
 	dbm "github.com/tendermint/tendermint/libs/db"
 	"github.com/tendermint/tendermint/libs/log"
+	tmpubsub "github.com/tendermint/tendermint/libs/pubsub"
 	mempl "github.com/tendermint/tendermint/mempool"
 	"github.com/tendermint/tendermint/p2p"
 	"github.com/tendermint/tendermint/privval"
@@ -37,8 +37,13 @@ const (
 	testSubscriber = "test-client"
 )
 
+// A cleanupFunc cleans up any config / test files created for a particular
+// test.
+type cleanupFunc func()
+
 // genesis, chain_id, priv_val
 var config *cfg.Config // NOTE: must be reset for each _test.go file
+var consensusReplayConfig *cfg.Config
 var ensureTimeout = time.Millisecond * 100
 
 func ensureDir(dir string, mode os.FileMode) {
@@ -122,17 +127,21 @@ func startTestRound(cs *ConsensusState, height int64, round int) {
 	cs.startRoutines(0)
 }
 
-// Create proposal block from cs1 but sign it with vs
+// Create proposal block from cs1 but sign it with vs.
 func decideProposal(cs1 *ConsensusState, vs *validatorStub, height int64, round int) (proposal *types.Proposal, block *types.Block) {
+	cs1.mtx.Lock()
 	block, blockParts := cs1.createProposalBlock()
-	if block == nil { // on error
-		panic("error creating proposal block")
+	validRound := cs1.ValidRound
+	chainID := cs1.state.ChainID
+	cs1.mtx.Unlock()
+	if block == nil {
+		panic("Failed to createProposalBlock. Did you forget to add commit for previous block?")
 	}
 
 	// Make proposal
-	polRound, propBlockID := cs1.ValidRound, types.BlockID{block.Hash(), blockParts.Header()}
+	polRound, propBlockID := validRound, types.BlockID{block.Hash(), blockParts.Header()}
 	proposal = types.NewProposal(height, round, polRound, propBlockID)
-	if err := vs.SignProposal(cs1.state.ChainID, proposal); err != nil {
+	if err := vs.SignProposal(chainID, proposal); err != nil {
 		panic(err)
 	}
 	return
@@ -218,30 +227,29 @@ func validatePrevoteAndPrecommit(t *testing.T, cs *ConsensusState, thisRound, lo
 	cs.mtx.Unlock()
 }
 
-// genesis
-func subscribeToVoter(cs *ConsensusState, addr []byte) chan interface{} {
-	voteCh0 := make(chan interface{})
-	err := cs.eventBus.Subscribe(context.Background(), testSubscriber, types.EventQueryVote, voteCh0)
+func subscribeToVoter(cs *ConsensusState, addr []byte) <-chan tmpubsub.Message {
+	votesSub, err := cs.eventBus.Subscribe(context.Background(), testSubscriber, types.EventQueryVote)
 	if err != nil {
 		panic(fmt.Sprintf("failed to subscribe %s to %v", testSubscriber, types.EventQueryVote))
 	}
-	voteCh := make(chan interface{})
+	ch := make(chan tmpubsub.Message)
 	go func() {
-		for v := range voteCh0 {
-			vote := v.(types.EventDataVote)
+		for msg := range votesSub.Out() {
+			vote := msg.Data().(types.EventDataVote)
 			// we only fire for our own votes
 			if bytes.Equal(addr, vote.Vote.ValidatorAddress) {
-				voteCh <- v
+				ch <- msg
 			}
 		}
 	}()
-	return voteCh
+	return ch
 }
 
 //-------------------------------------------------------------------------------
 // consensus states
 
 func newConsensusState(state sm.State, pv types.PrivValidator, app abci.Application) *ConsensusState {
+	config := cfg.ResetTestRoot("consensus_state_test")
 	return newConsensusStateWithConfig(config, state, pv, app)
 }
 
@@ -311,7 +319,7 @@ func randConsensusState(nValidators int) (*ConsensusState, []*validatorStub) {
 
 //-------------------------------------------------------------------------------
 
-func ensureNoNewEvent(ch <-chan interface{}, timeout time.Duration,
+func ensureNoNewEvent(ch <-chan tmpubsub.Message, timeout time.Duration,
 	errorMessage string) {
 	select {
 	case <-time.After(timeout):
@@ -321,28 +329,28 @@ func ensureNoNewEvent(ch <-chan interface{}, timeout time.Duration,
 	}
 }
 
-func ensureNoNewEventOnChannel(ch <-chan interface{}) {
+func ensureNoNewEventOnChannel(ch <-chan tmpubsub.Message) {
 	ensureNoNewEvent(
 		ch,
 		ensureTimeout,
 		"We should be stuck waiting, not receiving new event on the channel")
 }
 
-func ensureNoNewRoundStep(stepCh <-chan interface{}) {
+func ensureNoNewRoundStep(stepCh <-chan tmpubsub.Message) {
 	ensureNoNewEvent(
 		stepCh,
 		ensureTimeout,
 		"We should be stuck waiting, not receiving NewRoundStep event")
 }
 
-func ensureNoNewUnlock(unlockCh <-chan interface{}) {
+func ensureNoNewUnlock(unlockCh <-chan tmpubsub.Message) {
 	ensureNoNewEvent(
 		unlockCh,
 		ensureTimeout,
 		"We should be stuck waiting, not receiving Unlock event")
 }
 
-func ensureNoNewTimeout(stepCh <-chan interface{}, timeout int64) {
+func ensureNoNewTimeout(stepCh <-chan tmpubsub.Message, timeout int64) {
 	timeoutDuration := time.Duration(timeout*5) * time.Nanosecond
 	ensureNoNewEvent(
 		stepCh,
@@ -350,172 +358,157 @@ func ensureNoNewTimeout(stepCh <-chan interface{}, timeout int64) {
 		"We should be stuck waiting, not receiving NewTimeout event")
 }
 
-func ensureNewEvent(
-	ch <-chan interface{},
-	height int64,
-	round int,
-	timeout time.Duration,
-	errorMessage string) {
-
+func ensureNewEvent(ch <-chan tmpubsub.Message, height int64, round int, timeout time.Duration, errorMessage string) {
 	select {
 	case <-time.After(timeout):
 		panic(errorMessage)
-	case ev := <-ch:
-		rs, ok := ev.(types.EventDataRoundState)
+	case msg := <-ch:
+		roundStateEvent, ok := msg.Data().(types.EventDataRoundState)
 		if !ok {
-			panic(
-				fmt.Sprintf(
-					"expected a EventDataRoundState, got %v.Wrong subscription channel?",
-					reflect.TypeOf(rs)))
+			panic(fmt.Sprintf("expected a EventDataRoundState, got %T. Wrong subscription channel?",
+				msg.Data()))
 		}
-		if rs.Height != height {
-			panic(fmt.Sprintf("expected height %v, got %v", height, rs.Height))
+		if roundStateEvent.Height != height {
+			panic(fmt.Sprintf("expected height %v, got %v", height, roundStateEvent.Height))
 		}
-		if rs.Round != round {
-			panic(fmt.Sprintf("expected round %v, got %v", round, rs.Round))
+		if roundStateEvent.Round != round {
+			panic(fmt.Sprintf("expected round %v, got %v", round, roundStateEvent.Round))
 		}
 		// TODO: We could check also for a step at this point!
 	}
 }
 
-func ensureNewRoundStep(stepCh <-chan interface{}, height int64, round int) {
-	ensureNewEvent(
-		stepCh,
-		height,
-		round,
-		ensureTimeout,
-		"Timeout expired while waiting for NewStep event")
-}
-
-func ensureNewVote(voteCh <-chan interface{}, height int64, round int) {
-	select {
-	case <-time.After(ensureTimeout):
-		break
-	case v := <-voteCh:
-		edv, ok := v.(types.EventDataVote)
-		if !ok {
-			panic(fmt.Sprintf("expected a *types.Vote, "+
-				"got %v. wrong subscription channel?",
-				reflect.TypeOf(v)))
-		}
-		vote := edv.Vote
-		if vote.Height != height {
-			panic(fmt.Sprintf("expected height %v, got %v", height, vote.Height))
-		}
-		if vote.Round != round {
-			panic(fmt.Sprintf("expected round %v, got %v", round, vote.Round))
-		}
-	}
-}
-
-func ensureNewRound(roundCh <-chan interface{}, height int64, round int) {
+func ensureNewRound(roundCh <-chan tmpubsub.Message, height int64, round int) {
 	select {
 	case <-time.After(ensureTimeout):
 		panic("Timeout expired while waiting for NewRound event")
-	case ev := <-roundCh:
-		rs, ok := ev.(types.EventDataNewRound)
+	case msg := <-roundCh:
+		newRoundEvent, ok := msg.Data().(types.EventDataNewRound)
 		if !ok {
-			panic(
-				fmt.Sprintf(
-					"expected a EventDataNewRound, got %v.Wrong subscription channel?",
-					reflect.TypeOf(rs)))
+			panic(fmt.Sprintf("expected a EventDataNewRound, got %T. Wrong subscription channel?",
+				msg.Data()))
 		}
-		if rs.Height != height {
-			panic(fmt.Sprintf("expected height %v, got %v", height, rs.Height))
+		if newRoundEvent.Height != height {
+			panic(fmt.Sprintf("expected height %v, got %v", height, newRoundEvent.Height))
 		}
-		if rs.Round != round {
-			panic(fmt.Sprintf("expected round %v, got %v", round, rs.Round))
+		if newRoundEvent.Round != round {
+			panic(fmt.Sprintf("expected round %v, got %v", round, newRoundEvent.Round))
 		}
 	}
 }
 
-func ensureNewTimeout(timeoutCh <-chan interface{}, height int64, round int, timeout int64) {
-	timeoutDuration := time.Duration(timeout*3) * time.Nanosecond
+func ensureNewTimeout(timeoutCh <-chan tmpubsub.Message, height int64, round int, timeout int64) {
+	timeoutDuration := time.Duration(timeout*5) * time.Nanosecond
 	ensureNewEvent(timeoutCh, height, round, timeoutDuration,
 		"Timeout expired while waiting for NewTimeout event")
 }
 
-func ensureNewProposal(proposalCh <-chan interface{}, height int64, round int) {
+func ensureNewProposal(proposalCh <-chan tmpubsub.Message, height int64, round int) {
 	select {
 	case <-time.After(ensureTimeout):
 		panic("Timeout expired while waiting for NewProposal event")
-	case ev := <-proposalCh:
-		rs, ok := ev.(types.EventDataCompleteProposal)
+	case msg := <-proposalCh:
+		proposalEvent, ok := msg.Data().(types.EventDataCompleteProposal)
 		if !ok {
-			panic(
-				fmt.Sprintf(
-					"expected a EventDataCompleteProposal, got %v.Wrong subscription channel?",
-					reflect.TypeOf(rs)))
+			panic(fmt.Sprintf("expected a EventDataCompleteProposal, got %T. Wrong subscription channel?",
+				msg.Data()))
 		}
-		if rs.Height != height {
-			panic(fmt.Sprintf("expected height %v, got %v", height, rs.Height))
+		if proposalEvent.Height != height {
+			panic(fmt.Sprintf("expected height %v, got %v", height, proposalEvent.Height))
 		}
-		if rs.Round != round {
-			panic(fmt.Sprintf("expected round %v, got %v", round, rs.Round))
+		if proposalEvent.Round != round {
+			panic(fmt.Sprintf("expected round %v, got %v", round, proposalEvent.Round))
 		}
 	}
 }
 
-func ensureNewValidBlock(validBlockCh <-chan interface{}, height int64, round int) {
+func ensureNewValidBlock(validBlockCh <-chan tmpubsub.Message, height int64, round int) {
 	ensureNewEvent(validBlockCh, height, round, ensureTimeout,
 		"Timeout expired while waiting for NewValidBlock event")
 }
 
-func ensureNewBlock(blockCh <-chan interface{}, height int64) {
+func ensureNewBlock(blockCh <-chan tmpubsub.Message, height int64) {
 	select {
 	case <-time.After(ensureTimeout):
 		panic("Timeout expired while waiting for NewBlock event")
-	case ev := <-blockCh:
-		block, ok := ev.(types.EventDataNewBlock)
+	case msg := <-blockCh:
+		blockEvent, ok := msg.Data().(types.EventDataNewBlock)
 		if !ok {
-			panic(fmt.Sprintf("expected a *types.EventDataNewBlock, "+
-				"got %v. wrong subscription channel?",
-				reflect.TypeOf(block)))
+			panic(fmt.Sprintf("expected a EventDataNewBlock, got %T. Wrong subscription channel?",
+				msg.Data()))
 		}
-		if block.Block.Height != height {
-			panic(fmt.Sprintf("expected height %v, got %v", height, block.Block.Height))
+		if blockEvent.Block.Height != height {
+			panic(fmt.Sprintf("expected height %v, got %v", height, blockEvent.Block.Height))
 		}
 	}
 }
 
-func ensureNewBlockHeader(blockCh <-chan interface{}, height int64, blockHash cmn.HexBytes) {
+func ensureNewBlockHeader(blockCh <-chan tmpubsub.Message, height int64, blockHash cmn.HexBytes) {
 	select {
 	case <-time.After(ensureTimeout):
 		panic("Timeout expired while waiting for NewBlockHeader event")
-	case ev := <-blockCh:
-		blockHeader, ok := ev.(types.EventDataNewBlockHeader)
+	case msg := <-blockCh:
+		blockHeaderEvent, ok := msg.Data().(types.EventDataNewBlockHeader)
 		if !ok {
-			panic(fmt.Sprintf("expected a *types.EventDataNewBlockHeader, "+
-				"got %v. wrong subscription channel?",
-				reflect.TypeOf(blockHeader)))
+			panic(fmt.Sprintf("expected a EventDataNewBlockHeader, got %T. Wrong subscription channel?",
+				msg.Data()))
 		}
-		if blockHeader.Header.Height != height {
-			panic(fmt.Sprintf("expected height %v, got %v", height, blockHeader.Header.Height))
+		if blockHeaderEvent.Header.Height != height {
+			panic(fmt.Sprintf("expected height %v, got %v", height, blockHeaderEvent.Header.Height))
 		}
-		if !bytes.Equal(blockHeader.Header.Hash(), blockHash) {
-			panic(fmt.Sprintf("expected header %X, got %X", blockHash, blockHeader.Header.Hash()))
+		if !bytes.Equal(blockHeaderEvent.Header.Hash(), blockHash) {
+			panic(fmt.Sprintf("expected header %X, got %X", blockHash, blockHeaderEvent.Header.Hash()))
 		}
 	}
 }
 
-func ensureNewUnlock(unlockCh <-chan interface{}, height int64, round int) {
+func ensureNewUnlock(unlockCh <-chan tmpubsub.Message, height int64, round int) {
 	ensureNewEvent(unlockCh, height, round, ensureTimeout,
 		"Timeout expired while waiting for NewUnlock event")
 }
 
-func ensureVote(voteCh <-chan interface{}, height int64, round int,
+func ensureProposal(proposalCh <-chan tmpubsub.Message, height int64, round int, propID types.BlockID) {
+	select {
+	case <-time.After(ensureTimeout):
+		panic("Timeout expired while waiting for NewProposal event")
+	case msg := <-proposalCh:
+		proposalEvent, ok := msg.Data().(types.EventDataCompleteProposal)
+		if !ok {
+			panic(fmt.Sprintf("expected a EventDataCompleteProposal, got %T. Wrong subscription channel?",
+				msg.Data()))
+		}
+		if proposalEvent.Height != height {
+			panic(fmt.Sprintf("expected height %v, got %v", height, proposalEvent.Height))
+		}
+		if proposalEvent.Round != round {
+			panic(fmt.Sprintf("expected round %v, got %v", round, proposalEvent.Round))
+		}
+		if !proposalEvent.BlockID.Equals(propID) {
+			panic("Proposed block does not match expected block")
+		}
+	}
+}
+
+func ensurePrecommit(voteCh <-chan tmpubsub.Message, height int64, round int) {
+	ensureVote(voteCh, height, round, types.PrecommitType)
+}
+
+func ensurePrevote(voteCh <-chan tmpubsub.Message, height int64, round int) {
+	ensureVote(voteCh, height, round, types.PrevoteType)
+}
+
+func ensureVote(voteCh <-chan tmpubsub.Message, height int64, round int,
 	voteType types.SignedMsgType) {
 	select {
 	case <-time.After(ensureTimeout):
 		panic("Timeout expired while waiting for NewVote event")
-	case v := <-voteCh:
-		edv, ok := v.(types.EventDataVote)
+	case msg := <-voteCh:
+		voteEvent, ok := msg.Data().(types.EventDataVote)
 		if !ok {
-			panic(fmt.Sprintf("expected a *types.Vote, "+
-				"got %v. wrong subscription channel?",
-				reflect.TypeOf(v)))
+			panic(fmt.Sprintf("expected a EventDataVote, got %T. Wrong subscription channel?",
+				msg.Data()))
 		}
-		vote := edv.Vote
+		vote := voteEvent.Vote
 		if vote.Height != height {
 			panic(fmt.Sprintf("expected height %v, got %v", height, vote.Height))
 		}
@@ -528,39 +521,7 @@ func ensureVote(voteCh <-chan interface{}, height int64, round int,
 	}
 }
 
-func ensureProposal(proposalCh <-chan interface{}, height int64, round int, propId types.BlockID) {
-	select {
-	case <-time.After(ensureTimeout):
-		panic("Timeout expired while waiting for NewProposal event")
-	case ev := <-proposalCh:
-		rs, ok := ev.(types.EventDataCompleteProposal)
-		if !ok {
-			panic(
-				fmt.Sprintf(
-					"expected a EventDataCompleteProposal, got %v.Wrong subscription channel?",
-					reflect.TypeOf(rs)))
-		}
-		if rs.Height != height {
-			panic(fmt.Sprintf("expected height %v, got %v", height, rs.Height))
-		}
-		if rs.Round != round {
-			panic(fmt.Sprintf("expected round %v, got %v", round, rs.Round))
-		}
-		if !rs.BlockID.Equals(propId) {
-			panic("Proposed block does not match expected block")
-		}
-	}
-}
-
-func ensurePrecommit(voteCh <-chan interface{}, height int64, round int) {
-	ensureVote(voteCh, height, round, types.PrecommitType)
-}
-
-func ensurePrevote(voteCh <-chan interface{}, height int64, round int) {
-	ensureVote(voteCh, height, round, types.PrevoteType)
-}
-
-func ensureNewEventOnChannel(ch <-chan interface{}) {
+func ensureNewEventOnChannel(ch <-chan tmpubsub.Message) {
 	select {
 	case <-time.After(ensureTimeout):
 		panic("Timeout expired while waiting for new activity on the channel")
@@ -584,14 +545,17 @@ func consensusLogger() log.Logger {
 	}).With("module", "consensus")
 }
 
-func randConsensusNet(nValidators int, testName string, tickerFunc func() TimeoutTicker, appFunc func() abci.Application, configOpts ...func(*cfg.Config)) []*ConsensusState {
+func randConsensusNet(nValidators int, testName string, tickerFunc func() TimeoutTicker,
+	appFunc func() abci.Application, configOpts ...func(*cfg.Config)) ([]*ConsensusState, cleanupFunc) {
 	genDoc, privVals := randGenesisDoc(nValidators, false, 30)
 	css := make([]*ConsensusState, nValidators)
 	logger := consensusLogger()
+	configRootDirs := make([]string, 0, nValidators)
 	for i := 0; i < nValidators; i++ {
 		stateDB := dbm.NewMemDB() // each state needs its own db
 		state, _ := sm.LoadStateFromDBOrGenesisDoc(stateDB, genDoc)
 		thisConfig := ResetConfig(fmt.Sprintf("%s_%d", testName, i))
+		configRootDirs = append(configRootDirs, thisConfig.RootDir)
 		for _, opt := range configOpts {
 			opt(thisConfig)
 		}
@@ -604,18 +568,26 @@ func randConsensusNet(nValidators int, testName string, tickerFunc func() Timeou
 		css[i].SetTimeoutTicker(tickerFunc())
 		css[i].SetLogger(logger.With("validator", i, "module", "consensus"))
 	}
-	return css
+	return css, func() {
+		for _, dir := range configRootDirs {
+			os.RemoveAll(dir)
+		}
+	}
 }
 
 // nPeers = nValidators + nNotValidator
-func randConsensusNetWithPeers(nValidators, nPeers int, testName string, tickerFunc func() TimeoutTicker, appFunc func() abci.Application) []*ConsensusState {
+func randConsensusNetWithPeers(nValidators, nPeers int, testName string, tickerFunc func() TimeoutTicker,
+	appFunc func() abci.Application) ([]*ConsensusState, cleanupFunc) {
+
 	genDoc, privVals := randGenesisDoc(nValidators, false, testMinPower)
 	css := make([]*ConsensusState, nPeers)
 	logger := consensusLogger()
+	configRootDirs := make([]string, 0, nPeers)
 	for i := 0; i < nPeers; i++ {
 		stateDB := dbm.NewMemDB() // each state needs its own db
 		state, _ := sm.LoadStateFromDBOrGenesisDoc(stateDB, genDoc)
 		thisConfig := ResetConfig(fmt.Sprintf("%s_%d", testName, i))
+		configRootDirs = append(configRootDirs, thisConfig.RootDir)
 		ensureDir(filepath.Dir(thisConfig.Consensus.WalFile()), 0700) // dir for wal
 		var privVal types.PrivValidator
 		if i < nValidators {
@@ -641,7 +613,11 @@ func randConsensusNetWithPeers(nValidators, nPeers int, testName string, tickerF
 		css[i].SetTimeoutTicker(tickerFunc())
 		css[i].SetLogger(logger.With("validator", i, "module", "consensus"))
 	}
-	return css
+	return css, func() {
+		for _, dir := range configRootDirs {
+			os.RemoveAll(dir)
+		}
+	}
 }
 
 func getSwitchIndex(switches []*p2p.Switch, peer p2p.Peer) int {
@@ -651,7 +627,6 @@ func getSwitchIndex(switches []*p2p.Switch, peer p2p.Peer) int {
 		}
 	}
 	panic("didnt find peer in switches")
-	return -1
 }
 
 //-------------------------------------------------------------------------------
@@ -729,8 +704,7 @@ func (m *mockTicker) Chan() <-chan timeoutInfo {
 	return m.c
 }
 
-func (mockTicker) SetLogger(log.Logger) {
-}
+func (*mockTicker) SetLogger(log.Logger) {}
 
 //------------------------------------
 
@@ -739,6 +713,9 @@ func newCounter() abci.Application {
 }
 
 func newPersistentKVStore() abci.Application {
-	dir, _ := ioutil.TempDir("/tmp", "persistent-kvstore")
+	dir, err := ioutil.TempDir("", "persistent-kvstore")
+	if err != nil {
+		panic(err)
+	}
 	return kvstore.NewPersistentKVStoreApplication(dir)
 }

consensus/mempool_test.go

@@ -3,6 +3,7 @@ package consensus
 import (
 	"encoding/binary"
 	"fmt"
+	"os"
 	"testing"
 	"time"
 
@@ -14,10 +15,6 @@ import (
 	"github.com/tendermint/tendermint/types"
 )
 
-func init() {
-	config = ResetConfig("consensus_mempool_test")
-}
-
 // for testing
 func assertMempool(txn txNotifier) sm.Mempool {
 	return txn.(sm.Mempool)
@@ -25,6 +22,7 @@ func assertMempool(txn txNotifier) sm.Mempool {
 
 func TestMempoolNoProgressUntilTxsAvailable(t *testing.T) {
 	config := ResetConfig("consensus_mempool_txs_available_test")
+	defer os.RemoveAll(config.RootDir)
 	config.Consensus.CreateEmptyBlocks = false
 	state, privVals := randGenesisState(1, false, 10)
 	cs := newConsensusStateWithConfig(config, state, privVals[0], NewCounterApplication())
@@ -43,6 +41,7 @@ func TestMempoolNoProgressUntilTxsAvailable(t *testing.T) {
 
 func TestMempoolProgressAfterCreateEmptyBlocksInterval(t *testing.T) {
 	config := ResetConfig("consensus_mempool_txs_available_test")
+	defer os.RemoveAll(config.RootDir)
 	config.Consensus.CreateEmptyBlocksInterval = ensureTimeout
 	state, privVals := randGenesisState(1, false, 10)
 	cs := newConsensusStateWithConfig(config, state, privVals[0], NewCounterApplication())
@@ -58,6 +57,7 @@ func TestMempoolProgressAfterCreateEmptyBlocksInterval(t *testing.T) {
 
 func TestMempoolProgressInHigherRound(t *testing.T) {
 	config := ResetConfig("consensus_mempool_txs_available_test")
+	defer os.RemoveAll(config.RootDir)
 	config.Consensus.CreateEmptyBlocks = false
 	state, privVals := randGenesisState(1, false, 10)
 	cs := newConsensusStateWithConfig(config, state, privVals[0], NewCounterApplication())
@@ -117,9 +117,9 @@ func TestMempoolTxConcurrentWithCommit(t *testing.T) {
 	for nTxs := 0; nTxs < NTxs; {
 		ticker := time.NewTicker(time.Second * 30)
 		select {
-		case b := <-newBlockCh:
-			evt := b.(types.EventDataNewBlock)
-			nTxs += int(evt.Block.Header.NumTxs)
+		case msg := <-newBlockCh:
+			blockEvent := msg.Data().(types.EventDataNewBlock)
+			nTxs += int(blockEvent.Block.Header.NumTxs)
 		case <-ticker.C:
 			panic("Timed out waiting to commit blocks with transactions")
 		}

consensus/reactor.go

@@ -8,7 +8,7 @@ import (
 
 	"github.com/pkg/errors"
 
-	"github.com/tendermint/go-amino"
+	amino "github.com/tendermint/go-amino"
 	cstypes "github.com/tendermint/tendermint/consensus/types"
 	cmn "github.com/tendermint/tendermint/libs/common"
 	tmevents "github.com/tendermint/tendermint/libs/events"
@@ -438,9 +438,9 @@ func (conR *ConsensusReactor) broadcastHasVoteMessage(vote *types.Vote) {
 
 func makeRoundStepMessage(rs *cstypes.RoundState) (nrsMsg *NewRoundStepMessage) {
 	nrsMsg = &NewRoundStepMessage{
-		Height: rs.Height,
-		Round:  rs.Round,
-		Step:   rs.Step,
+		Height:                rs.Height,
+		Round:                 rs.Round,
+		Step:                  rs.Step,
 		SecondsSinceStartTime: int(time.Since(rs.StartTime).Seconds()),
 		LastCommitRound:       rs.LastCommit.Round(),
 	}
@@ -896,7 +896,7 @@ type PeerState struct {
 	peer   p2p.Peer
 	logger log.Logger
 
-	mtx   sync.Mutex             `json:"-"`           // NOTE: Modify below using setters, never directly.
+	mtx   sync.Mutex             // NOTE: Modify below using setters, never directly.
 	PRS   cstypes.PeerRoundState `json:"round_state"` // Exposed.
 	Stats *peerStateStats        `json:"stats"`       // Exposed.
 }

consensus/reactor_test.go

@@ -14,7 +14,7 @@ import (
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 
-	"github.com/tendermint/tendermint/abci/client"
+	abcicli "github.com/tendermint/tendermint/abci/client"
 	"github.com/tendermint/tendermint/abci/example/kvstore"
 	abci "github.com/tendermint/tendermint/abci/types"
 	bc "github.com/tendermint/tendermint/blockchain"
@@ -27,16 +27,16 @@ import (
 	"github.com/tendermint/tendermint/types"
 )
 
-func init() {
-	config = ResetConfig("consensus_reactor_test")
-}
-
 //----------------------------------------------
 // in-process testnets
 
-func startConsensusNet(t *testing.T, css []*ConsensusState, N int) ([]*ConsensusReactor, []chan interface{}, []*types.EventBus) {
+func startConsensusNet(t *testing.T, css []*ConsensusState, N int) (
+	[]*ConsensusReactor,
+	[]types.Subscription,
+	[]*types.EventBus,
+) {
 	reactors := make([]*ConsensusReactor, N)
-	eventChans := make([]chan interface{}, N)
+	blocksSubs := make([]types.Subscription, 0)
 	eventBuses := make([]*types.EventBus, N)
 	for i := 0; i < N; i++ {
 		/*logger, err := tmflags.ParseLogLevel("consensus:info,*:error", logger, "info")
@@ -48,9 +48,9 @@ func startConsensusNet(t *testing.T, css []*ConsensusState, N int) ([]*Consensus
 		eventBuses[i] = css[i].eventBus
 		reactors[i].SetEventBus(eventBuses[i])
 
-		eventChans[i] = make(chan interface{}, 1)
-		err := eventBuses[i].Subscribe(context.Background(), testSubscriber, types.EventQueryNewBlock, eventChans[i])
+		blocksSub, err := eventBuses[i].Subscribe(context.Background(), testSubscriber, types.EventQueryNewBlock)
 		require.NoError(t, err)
+		blocksSubs = append(blocksSubs, blocksSub)
 	}
 	// make connected switches and start all reactors
 	p2p.MakeConnectedSwitches(config.P2P, N, func(i int, s *p2p.Switch) *p2p.Switch {
@@ -67,7 +67,7 @@ func startConsensusNet(t *testing.T, css []*ConsensusState, N int) ([]*Consensus
 		s := reactors[i].conS.GetState()
 		reactors[i].SwitchToConsensus(s, 0)
 	}
-	return reactors, eventChans, eventBuses
+	return reactors, blocksSubs, eventBuses
 }
 
 func stopConsensusNet(logger log.Logger, reactors []*ConsensusReactor, eventBuses []*types.EventBus) {
@@ -86,12 +86,13 @@ func stopConsensusNet(logger log.Logger, reactors []*ConsensusReactor, eventBuse
 // Ensure a testnet makes blocks
 func TestReactorBasic(t *testing.T) {
 	N := 4
-	css := randConsensusNet(N, "consensus_reactor_test", newMockTickerFunc(true), newCounter)
-	reactors, eventChans, eventBuses := startConsensusNet(t, css, N)
+	css, cleanup := randConsensusNet(N, "consensus_reactor_test", newMockTickerFunc(true), newCounter)
+	defer cleanup()
+	reactors, blocksSubs, eventBuses := startConsensusNet(t, css, N)
 	defer stopConsensusNet(log.TestingLogger(), reactors, eventBuses)
 	// wait till everyone makes the first new block
 	timeoutWaitGroup(t, N, func(j int) {
-		<-eventChans[j]
+		<-blocksSubs[j].Out()
 	}, css)
 }
 
@@ -116,6 +117,7 @@ func TestReactorWithEvidence(t *testing.T) {
 		stateDB := dbm.NewMemDB() // each state needs its own db
 		state, _ := sm.LoadStateFromDBOrGenesisDoc(stateDB, genDoc)
 		thisConfig := ResetConfig(fmt.Sprintf("%s_%d", testName, i))
+		defer os.RemoveAll(thisConfig.RootDir)
 		ensureDir(path.Dir(thisConfig.Consensus.WalFile()), 0700) // dir for wal
 		app := appFunc()
 		vals := types.TM2PB.ValidatorUpdates(state.Validators)
@@ -163,20 +165,20 @@ func TestReactorWithEvidence(t *testing.T) {
 		css[i] = cs
 	}
 
-	reactors, eventChans, eventBuses := startConsensusNet(t, css, nValidators)
+	reactors, blocksSubs, eventBuses := startConsensusNet(t, css, nValidators)
 	defer stopConsensusNet(log.TestingLogger(), reactors, eventBuses)
 
 	// wait till everyone makes the first new block with no evidence
 	timeoutWaitGroup(t, nValidators, func(j int) {
-		blockI := <-eventChans[j]
-		block := blockI.(types.EventDataNewBlock).Block
+		msg := <-blocksSubs[j].Out()
+		block := msg.Data().(types.EventDataNewBlock).Block
 		assert.True(t, len(block.Evidence.Evidence) == 0)
 	}, css)
 
 	// second block should have evidence
 	timeoutWaitGroup(t, nValidators, func(j int) {
-		blockI := <-eventChans[j]
-		block := blockI.(types.EventDataNewBlock).Block
+		msg := <-blocksSubs[j].Out()
+		block := msg.Data().(types.EventDataNewBlock).Block
 		assert.True(t, len(block.Evidence.Evidence) > 0)
 	}, css)
 }
@@ -211,17 +213,19 @@ func (m *mockEvidencePool) Update(block *types.Block, state sm.State) {
 	}
 	m.height++
 }
+func (m *mockEvidencePool) IsCommitted(types.Evidence) bool { return false }
 
 //------------------------------------
 
 // Ensure a testnet makes blocks when there are txs
 func TestReactorCreatesBlockWhenEmptyBlocksFalse(t *testing.T) {
 	N := 4
-	css := randConsensusNet(N, "consensus_reactor_test", newMockTickerFunc(true), newCounter,
+	css, cleanup := randConsensusNet(N, "consensus_reactor_test", newMockTickerFunc(true), newCounter,
 		func(c *cfg.Config) {
 			c.Consensus.CreateEmptyBlocks = false
 		})
-	reactors, eventChans, eventBuses := startConsensusNet(t, css, N)
+	defer cleanup()
+	reactors, blocksSubs, eventBuses := startConsensusNet(t, css, N)
 	defer stopConsensusNet(log.TestingLogger(), reactors, eventBuses)
 
 	// send a tx
@@ -231,20 +235,21 @@ func TestReactorCreatesBlockWhenEmptyBlocksFalse(t *testing.T) {
 
 	// wait till everyone makes the first new block
 	timeoutWaitGroup(t, N, func(j int) {
-		<-eventChans[j]
+		<-blocksSubs[j].Out()
 	}, css)
 }
 
 // Test we record stats about votes and block parts from other peers.
 func TestReactorRecordsVotesAndBlockParts(t *testing.T) {
 	N := 4
-	css := randConsensusNet(N, "consensus_reactor_test", newMockTickerFunc(true), newCounter)
-	reactors, eventChans, eventBuses := startConsensusNet(t, css, N)
+	css, cleanup := randConsensusNet(N, "consensus_reactor_test", newMockTickerFunc(true), newCounter)
+	defer cleanup()
+	reactors, blocksSubs, eventBuses := startConsensusNet(t, css, N)
 	defer stopConsensusNet(log.TestingLogger(), reactors, eventBuses)
 
 	// wait till everyone makes the first new block
 	timeoutWaitGroup(t, N, func(j int) {
-		<-eventChans[j]
+		<-blocksSubs[j].Out()
 	}, css)
 
 	// Get peer
@@ -262,8 +267,9 @@ func TestReactorRecordsVotesAndBlockParts(t *testing.T) {
 func TestReactorVotingPowerChange(t *testing.T) {
 	nVals := 4
 	logger := log.TestingLogger()
-	css := randConsensusNet(nVals, "consensus_voting_power_changes_test", newMockTickerFunc(true), newPersistentKVStore)
-	reactors, eventChans, eventBuses := startConsensusNet(t, css, nVals)
+	css, cleanup := randConsensusNet(nVals, "consensus_voting_power_changes_test", newMockTickerFunc(true), newPersistentKVStore)
+	defer cleanup()
+	reactors, blocksSubs, eventBuses := startConsensusNet(t, css, nVals)
 	defer stopConsensusNet(logger, reactors, eventBuses)
 
 	// map of active validators
@@ -275,7 +281,7 @@ func TestReactorVotingPowerChange(t *testing.T) {
 
 	// wait till everyone makes block 1
 	timeoutWaitGroup(t, nVals, func(j int) {
-		<-eventChans[j]
+		<-blocksSubs[j].Out()
 	}, css)
 
 	//---------------------------------------------------------------------------
@@ -286,10 +292,10 @@ func TestReactorVotingPowerChange(t *testing.T) {
 	updateValidatorTx := kvstore.MakeValSetChangeTx(val1PubKeyABCI, 25)
 	previousTotalVotingPower := css[0].GetRoundState().LastValidators.TotalVotingPower()
 
-	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css, updateValidatorTx)
-	waitForAndValidateBlockWithTx(t, nVals, activeVals, eventChans, css, updateValidatorTx)
-	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
-	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
+	waitForAndValidateBlock(t, nVals, activeVals, blocksSubs, css, updateValidatorTx)
+	waitForAndValidateBlockWithTx(t, nVals, activeVals, blocksSubs, css, updateValidatorTx)
+	waitForAndValidateBlock(t, nVals, activeVals, blocksSubs, css)
+	waitForAndValidateBlock(t, nVals, activeVals, blocksSubs, css)
 
 	if css[0].GetRoundState().LastValidators.TotalVotingPower() == previousTotalVotingPower {
 		t.Fatalf("expected voting power to change (before: %d, after: %d)", previousTotalVotingPower, css[0].GetRoundState().LastValidators.TotalVotingPower())
@@ -298,10 +304,10 @@ func TestReactorVotingPowerChange(t *testing.T) {
 	updateValidatorTx = kvstore.MakeValSetChangeTx(val1PubKeyABCI, 2)
 	previousTotalVotingPower = css[0].GetRoundState().LastValidators.TotalVotingPower()
 
-	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css, updateValidatorTx)
-	waitForAndValidateBlockWithTx(t, nVals, activeVals, eventChans, css, updateValidatorTx)
-	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
-	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
+	waitForAndValidateBlock(t, nVals, activeVals, blocksSubs, css, updateValidatorTx)
+	waitForAndValidateBlockWithTx(t, nVals, activeVals, blocksSubs, css, updateValidatorTx)
+	waitForAndValidateBlock(t, nVals, activeVals, blocksSubs, css)
+	waitForAndValidateBlock(t, nVals, activeVals, blocksSubs, css)
 
 	if css[0].GetRoundState().LastValidators.TotalVotingPower() == previousTotalVotingPower {
 		t.Fatalf("expected voting power to change (before: %d, after: %d)", previousTotalVotingPower, css[0].GetRoundState().LastValidators.TotalVotingPower())
@@ -310,10 +316,10 @@ func TestReactorVotingPowerChange(t *testing.T) {
 	updateValidatorTx = kvstore.MakeValSetChangeTx(val1PubKeyABCI, 26)
 	previousTotalVotingPower = css[0].GetRoundState().LastValidators.TotalVotingPower()
 
-	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css, updateValidatorTx)
-	waitForAndValidateBlockWithTx(t, nVals, activeVals, eventChans, css, updateValidatorTx)
-	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
-	waitForAndValidateBlock(t, nVals, activeVals, eventChans, css)
+	waitForAndValidateBlock(t, nVals, activeVals, blocksSubs, css, updateValidatorTx)
+	waitForAndValidateBlockWithTx(t, nVals, activeVals, blocksSubs, css, updateValidatorTx)
+	waitForAndValidateBlock(t, nVals, activeVals, blocksSubs, css)
+	waitForAndValidateBlock(t, nVals, activeVals, blocksSubs, css)
 
 	if css[0].GetRoundState().LastValidators.TotalVotingPower() == previousTotalVotingPower {
 		t.Fatalf("expected voting power to change (before: %d, after: %d)", previousTotalVotingPower, css[0].GetRoundState().LastValidators.TotalVotingPower())
@@ -323,11 +329,11 @@ func TestReactorVotingPowerChange(t *testing.T) {
 func TestReactorValidatorSetChanges(t *testing.T) {
 	nPeers := 7
 	nVals := 4
-	css := randConsensusNetWithPeers(nVals, nPeers, "consensus_val_set_changes_test", newMockTickerFunc(true), newPersistentKVStore)
-
+	css, cleanup := randConsensusNetWithPeers(nVals, nPeers, "consensus_val_set_changes_test", newMockTickerFunc(true), newPersistentKVStore)
+	defer cleanup()
 	logger := log.TestingLogger()
 
-	reactors, eventChans, eventBuses := startConsensusNet(t, css, nPeers)
+	reactors, blocksSubs, eventBuses := startConsensusNet(t, css, nPeers)
 	defer stopConsensusNet(logger, reactors, eventBuses)
 
 	// map of active validators
@@ -339,7 +345,7 @@ func TestReactorValidatorSetChanges(t *testing.T) {
 
 	// wait till everyone makes block 1
 	timeoutWaitGroup(t, nPeers, func(j int) {
-		<-eventChans[j]
+		<-blocksSubs[j].Out()
 	}, css)
 
 	//---------------------------------------------------------------------------
@@ -352,22 +358,22 @@ func TestReactorValidatorSetChanges(t *testing.T) {
 	// wait till everyone makes block 2
 	// ensure the commit includes all validators
 	// send newValTx to change vals in block 3
-	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css, newValidatorTx1)
+	waitForAndValidateBlock(t, nPeers, activeVals, blocksSubs, css, newValidatorTx1)
 
 	// wait till everyone makes block 3.
 	// it includes the commit for block 2, which is by the original validator set
-	waitForAndValidateBlockWithTx(t, nPeers, activeVals, eventChans, css, newValidatorTx1)
+	waitForAndValidateBlockWithTx(t, nPeers, activeVals, blocksSubs, css, newValidatorTx1)
 
 	// wait till everyone makes block 4.
 	// it includes the commit for block 3, which is by the original validator set
-	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
+	waitForAndValidateBlock(t, nPeers, activeVals, blocksSubs, css)
 
 	// the commits for block 4 should be with the updated validator set
 	activeVals[string(newValidatorPubKey1.Address())] = struct{}{}
 
 	// wait till everyone makes block 5
 	// it includes the commit for block 4, which should have the updated validator set
-	waitForBlockWithUpdatedValsAndValidateIt(t, nPeers, activeVals, eventChans, css)
+	waitForBlockWithUpdatedValsAndValidateIt(t, nPeers, activeVals, blocksSubs, css)
 
 	//---------------------------------------------------------------------------
 	logger.Info("---------------------------- Testing changing the voting power of one validator")
@@ -377,10 +383,10 @@ func TestReactorValidatorSetChanges(t *testing.T) {
 	updateValidatorTx1 := kvstore.MakeValSetChangeTx(updatePubKey1ABCI, 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)
-	waitForBlockWithUpdatedValsAndValidateIt(t, nPeers, activeVals, eventChans, css)
+	waitForAndValidateBlock(t, nPeers, activeVals, blocksSubs, css, updateValidatorTx1)
+	waitForAndValidateBlockWithTx(t, nPeers, activeVals, blocksSubs, css, updateValidatorTx1)
+	waitForAndValidateBlock(t, nPeers, activeVals, blocksSubs, css)
+	waitForBlockWithUpdatedValsAndValidateIt(t, nPeers, activeVals, blocksSubs, 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())
@@ -397,12 +403,12 @@ func TestReactorValidatorSetChanges(t *testing.T) {
 	newVal3ABCI := types.TM2PB.PubKey(newValidatorPubKey3)
 	newValidatorTx3 := kvstore.MakeValSetChangeTx(newVal3ABCI, testMinPower)
 
-	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css, newValidatorTx2, newValidatorTx3)
-	waitForAndValidateBlockWithTx(t, nPeers, activeVals, eventChans, css, newValidatorTx2, newValidatorTx3)
-	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
+	waitForAndValidateBlock(t, nPeers, activeVals, blocksSubs, css, newValidatorTx2, newValidatorTx3)
+	waitForAndValidateBlockWithTx(t, nPeers, activeVals, blocksSubs, css, newValidatorTx2, newValidatorTx3)
+	waitForAndValidateBlock(t, nPeers, activeVals, blocksSubs, css)
 	activeVals[string(newValidatorPubKey2.Address())] = struct{}{}
 	activeVals[string(newValidatorPubKey3.Address())] = struct{}{}
-	waitForBlockWithUpdatedValsAndValidateIt(t, nPeers, activeVals, eventChans, css)
+	waitForBlockWithUpdatedValsAndValidateIt(t, nPeers, activeVals, blocksSubs, css)
 
 	//---------------------------------------------------------------------------
 	logger.Info("---------------------------- Testing removing two validators at once")
@@ -410,40 +416,45 @@ func TestReactorValidatorSetChanges(t *testing.T) {
 	removeValidatorTx2 := kvstore.MakeValSetChangeTx(newVal2ABCI, 0)
 	removeValidatorTx3 := kvstore.MakeValSetChangeTx(newVal3ABCI, 0)
 
-	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css, removeValidatorTx2, removeValidatorTx3)
-	waitForAndValidateBlockWithTx(t, nPeers, activeVals, eventChans, css, removeValidatorTx2, removeValidatorTx3)
-	waitForAndValidateBlock(t, nPeers, activeVals, eventChans, css)
+	waitForAndValidateBlock(t, nPeers, activeVals, blocksSubs, css, removeValidatorTx2, removeValidatorTx3)
+	waitForAndValidateBlockWithTx(t, nPeers, activeVals, blocksSubs, css, removeValidatorTx2, removeValidatorTx3)
+	waitForAndValidateBlock(t, nPeers, activeVals, blocksSubs, css)
 	delete(activeVals, string(newValidatorPubKey2.Address()))
 	delete(activeVals, string(newValidatorPubKey3.Address()))
-	waitForBlockWithUpdatedValsAndValidateIt(t, nPeers, activeVals, eventChans, css)
+	waitForBlockWithUpdatedValsAndValidateIt(t, nPeers, activeVals, blocksSubs, css)
 }
 
 // Check we can make blocks with skip_timeout_commit=false
 func TestReactorWithTimeoutCommit(t *testing.T) {
 	N := 4
-	css := randConsensusNet(N, "consensus_reactor_with_timeout_commit_test", newMockTickerFunc(false), newCounter)
+	css, cleanup := randConsensusNet(N, "consensus_reactor_with_timeout_commit_test", newMockTickerFunc(false), newCounter)
+	defer cleanup()
 	// override default SkipTimeoutCommit == true for tests
 	for i := 0; i < N; i++ {
 		css[i].config.SkipTimeoutCommit = false
 	}
 
-	reactors, eventChans, eventBuses := startConsensusNet(t, css, N-1)
+	reactors, blocksSubs, 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(j int) {
-		<-eventChans[j]
+		<-blocksSubs[j].Out()
 	}, css)
 }
 
-func waitForAndValidateBlock(t *testing.T, n int, activeVals map[string]struct{}, eventChans []chan interface{}, css []*ConsensusState, txs ...[]byte) {
+func waitForAndValidateBlock(
+	t *testing.T,
+	n int,
+	activeVals map[string]struct{},
+	blocksSubs []types.Subscription,
+	css []*ConsensusState,
+	txs ...[]byte,
+) {
 	timeoutWaitGroup(t, n, func(j int) {
 		css[j].Logger.Debug("waitForAndValidateBlock")
-		newBlockI, ok := <-eventChans[j]
-		if !ok {
-			return
-		}
-		newBlock := newBlockI.(types.EventDataNewBlock).Block
+		msg := <-blocksSubs[j].Out()
+		newBlock := msg.Data().(types.EventDataNewBlock).Block
 		css[j].Logger.Debug("waitForAndValidateBlock: Got block", "height", newBlock.Height)
 		err := validateBlock(newBlock, activeVals)
 		assert.Nil(t, err)
@@ -454,17 +465,21 @@ func waitForAndValidateBlock(t *testing.T, n int, activeVals map[string]struct{}
 	}, css)
 }
 
-func waitForAndValidateBlockWithTx(t *testing.T, n int, activeVals map[string]struct{}, eventChans []chan interface{}, css []*ConsensusState, txs ...[]byte) {
+func waitForAndValidateBlockWithTx(
+	t *testing.T,
+	n int,
+	activeVals map[string]struct{},
+	blocksSubs []types.Subscription,
+	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
+			msg := <-blocksSubs[j].Out()
+			newBlock := msg.Data().(types.EventDataNewBlock).Block
 			css[j].Logger.Debug("waitForAndValidateBlockWithTx: Got block", "height", newBlock.Height)
 			err := validateBlock(newBlock, activeVals)
 			assert.Nil(t, err)
@@ -485,18 +500,21 @@ func waitForAndValidateBlockWithTx(t *testing.T, n int, activeVals map[string]st
 	}, css)
 }
 
-func waitForBlockWithUpdatedValsAndValidateIt(t *testing.T, n int, updatedVals map[string]struct{}, eventChans []chan interface{}, css []*ConsensusState) {
+func waitForBlockWithUpdatedValsAndValidateIt(
+	t *testing.T,
+	n int,
+	updatedVals map[string]struct{},
+	blocksSubs []types.Subscription,
+	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
+			msg := <-blocksSubs[j].Out()
+			newBlock = msg.Data().(types.EventDataNewBlock).Block
 			if newBlock.LastCommit.Size() == len(updatedVals) {
 				css[j].Logger.Debug("waitForBlockWithUpdatedValsAndValidateIt: Got block", "height", newBlock.Height)
 				break LOOP

consensus/replay.go

@@ -6,6 +6,7 @@ import (
 	"hash/crc32"
 	"io"
 	"reflect"
+
 	//"strconv"
 	//"strings"
 	"time"
@@ -41,7 +42,7 @@ var crc32c = crc32.MakeTable(crc32.Castagnoli)
 // Unmarshal and apply a single message to the consensus state as if it were
 // received in receiveRoutine.  Lines that start with "#" are ignored.
 // NOTE: receiveRoutine should not be running.
-func (cs *ConsensusState) readReplayMessage(msg *TimedWALMessage, newStepCh chan interface{}) error {
+func (cs *ConsensusState) readReplayMessage(msg *TimedWALMessage, newStepSub types.Subscription) error {
 	// Skip meta messages which exist for demarcating boundaries.
 	if _, ok := msg.Msg.(EndHeightMessage); ok {
 		return nil
@@ -53,15 +54,17 @@ func (cs *ConsensusState) readReplayMessage(msg *TimedWALMessage, newStepCh chan
 		cs.Logger.Info("Replay: New Step", "height", m.Height, "round", m.Round, "step", m.Step)
 		// these are playback checks
 		ticker := time.After(time.Second * 2)
-		if newStepCh != nil {
+		if newStepSub != nil {
 			select {
-			case mi := <-newStepCh:
-				m2 := mi.(types.EventDataRoundState)
+			case stepMsg := <-newStepSub.Out():
+				m2 := stepMsg.Data().(types.EventDataRoundState)
 				if m.Height != m2.Height || m.Round != m2.Round || m.Step != m2.Step {
 					return fmt.Errorf("RoundState mismatch. Got %v; Expected %v", m2, m)
 				}
+			case <-newStepSub.Cancelled():
+				return fmt.Errorf("Failed to read off newStepSub.Out(). newStepSub was cancelled")
 			case <-ticker:
-				return fmt.Errorf("Failed to read off newStepCh")
+				return fmt.Errorf("Failed to read off newStepSub.Out()")
 			}
 		}
 	case msgInfo:
@@ -143,8 +146,8 @@ func (cs *ConsensusState) catchupReplay(csHeight int64) error {
 		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))
+			cs.Logger.Error("data has been corrupted in last height of consensus WAL", "err", err, "height", csHeight)
+			return err
 		} else if err != nil {
 			return err
 		}
@@ -196,6 +199,7 @@ type Handshaker struct {
 	stateDB      dbm.DB
 	initialState sm.State
 	store        sm.BlockStore
+	eventBus     types.BlockEventPublisher
 	genDoc       *types.GenesisDoc
 	logger       log.Logger
 
@@ -209,6 +213,7 @@ func NewHandshaker(stateDB dbm.DB, state sm.State,
 		stateDB:      stateDB,
 		initialState: state,
 		store:        store,
+		eventBus:     types.NopEventBus{},
 		genDoc:       genDoc,
 		logger:       log.NewNopLogger(),
 		nBlocks:      0,
@@ -219,6 +224,12 @@ func (h *Handshaker) SetLogger(l log.Logger) {
 	h.logger = l
 }
 
+// SetEventBus - sets the event bus for publishing block related events.
+// If not called, it defaults to types.NopEventBus.
+func (h *Handshaker) SetEventBus(eventBus types.BlockEventPublisher) {
+	h.eventBus = eventBus
+}
+
 func (h *Handshaker) NBlocks() int {
 	return h.nBlocks
 }
@@ -325,7 +336,7 @@ func (h *Handshaker) ReplayBlocks(
 
 	} else if storeBlockHeight < appBlockHeight {
 		// the app should never be ahead of the store (but this is under app's control)
-		return appHash, sm.ErrAppBlockHeightTooHigh{storeBlockHeight, appBlockHeight}
+		return appHash, sm.ErrAppBlockHeightTooHigh{CoreHeight: storeBlockHeight, AppHeight: appBlockHeight}
 
 	} else if storeBlockHeight < stateBlockHeight {
 		// the state should never be ahead of the store (this is under tendermint's control)
@@ -432,6 +443,7 @@ func (h *Handshaker) replayBlock(state sm.State, height int64, proxyApp proxy.Ap
 	meta := h.store.LoadBlockMeta(height)
 
 	blockExec := sm.NewBlockExecutor(h.stateDB, h.logger, proxyApp, sm.MockMempool{}, sm.MockEvidencePool{})
+	blockExec.SetEventBus(h.eventBus)
 
 	var err error
 	state, err = blockExec.ApplyBlock(state, meta.BlockID, block)

consensus/replay_file.go

@@ -51,25 +51,13 @@ func (cs *ConsensusState) ReplayFile(file string, console bool) error {
 	cs.startForReplay()
 
 	// ensure all new step events are regenerated as expected
-	newStepCh := make(chan interface{}, 1)
 
 	ctx := context.Background()
-	err := cs.eventBus.Subscribe(ctx, subscriber, types.EventQueryNewRoundStep, newStepCh)
+	newStepSub, err := cs.eventBus.Subscribe(ctx, subscriber, types.EventQueryNewRoundStep)
 	if err != nil {
 		return errors.Errorf("failed to subscribe %s to %v", subscriber, types.EventQueryNewRoundStep)
 	}
-	defer func() {
-		// drain newStepCh to make sure we don't block
-	LOOP:
-		for {
-			select {
-			case <-newStepCh:
-			default:
-				break LOOP
-			}
-		}
-		cs.eventBus.Unsubscribe(ctx, 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, 0600)
@@ -94,7 +82,7 @@ func (cs *ConsensusState) ReplayFile(file string, console bool) error {
 			return err
 		}
 
-		if err := pb.cs.readReplayMessage(msg, newStepCh); err != nil {
+		if err := pb.cs.readReplayMessage(msg, newStepSub); err != nil {
 			return err
 		}
 
@@ -103,7 +91,6 @@ func (cs *ConsensusState) ReplayFile(file string, console bool) error {
 		}
 		pb.count++
 	}
-	return nil
 }
 
 //------------------------------------------------
@@ -132,7 +119,7 @@ func newPlayback(fileName string, fp *os.File, cs *ConsensusState, genState sm.S
 }
 
 // go back count steps by resetting the state and running (pb.count - count) steps
-func (pb *playback) replayReset(count int, newStepCh chan interface{}) error {
+func (pb *playback) replayReset(count int, newStepSub types.Subscription) error {
 	pb.cs.Stop()
 	pb.cs.Wait()
 
@@ -162,7 +149,7 @@ func (pb *playback) replayReset(count int, newStepCh chan interface{}) error {
 		} else if err != nil {
 			return err
 		}
-		if err := pb.cs.readReplayMessage(msg, newStepCh); err != nil {
+		if err := pb.cs.readReplayMessage(msg, newStepSub); err != nil {
 			return err
 		}
 		pb.count++
@@ -226,27 +213,15 @@ func (pb *playback) replayConsoleLoop() int {
 
 			ctx := context.Background()
 			// ensure all new step events are regenerated as expected
-			newStepCh := make(chan interface{}, 1)
 
-			err := pb.cs.eventBus.Subscribe(ctx, subscriber, types.EventQueryNewRoundStep, newStepCh)
+			newStepSub, err := pb.cs.eventBus.Subscribe(ctx, subscriber, types.EventQueryNewRoundStep)
 			if err != nil {
 				cmn.Exit(fmt.Sprintf("failed to subscribe %s to %v", subscriber, types.EventQueryNewRoundStep))
 			}
-			defer func() {
-				// drain newStepCh to make sure we don't block
-			LOOP:
-				for {
-					select {
-					case <-newStepCh:
-					default:
-						break LOOP
-					}
-				}
-				pb.cs.eventBus.Unsubscribe(ctx, subscriber, types.EventQueryNewRoundStep)
-			}()
+			defer pb.cs.eventBus.Unsubscribe(ctx, subscriber, types.EventQueryNewRoundStep)
 
 			if len(tokens) == 1 {
-				if err := pb.replayReset(1, newStepCh); err != nil {
+				if err := pb.replayReset(1, newStepSub); err != nil {
 					pb.cs.Logger.Error("Replay reset error", "err", err)
 				}
 			} else {
@@ -256,7 +231,7 @@ 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 {
-					if err := pb.replayReset(i, newStepCh); err != nil {
+					if err := pb.replayReset(i, newStepSub); err != nil {
 						pb.cs.Logger.Error("Replay reset error", "err", err)
 					}
 				}
@@ -295,7 +270,6 @@ func (pb *playback) replayConsoleLoop() int {
 			fmt.Println(pb.count)
 		}
 	}
-	return 0
 }
 
 //--------------------------------------------------------------------------------
@@ -326,17 +300,18 @@ func newConsensusStateForReplay(config cfg.BaseConfig, csConfig *cfg.ConsensusCo
 		cmn.Exit(fmt.Sprintf("Error starting proxy app conns: %v", err))
 	}
 
-	handshaker := NewHandshaker(stateDB, state, blockStore, gdoc)
-	err = handshaker.Handshake(proxyApp)
-	if err != nil {
-		cmn.Exit(fmt.Sprintf("Error on handshake: %v", err))
-	}
-
 	eventBus := types.NewEventBus()
 	if err := eventBus.Start(); err != nil {
 		cmn.Exit(fmt.Sprintf("Failed to start event bus: %v", err))
 	}
 
+	handshaker := NewHandshaker(stateDB, state, blockStore, gdoc)
+	handshaker.SetEventBus(eventBus)
+	err = handshaker.Handshake(proxyApp)
+	if err != nil {
+		cmn.Exit(fmt.Sprintf("Error on handshake: %v", err))
+	}
+
 	mempool, evpool := sm.MockMempool{}, sm.MockEvidencePool{}
 	blockExec := sm.NewBlockExecutor(stateDB, log.TestingLogger(), proxyApp.Consensus(), mempool, evpool)
 

consensus/replay_test.go

@@ -17,23 +17,30 @@ import (
 
 	"github.com/tendermint/tendermint/abci/example/kvstore"
 	abci "github.com/tendermint/tendermint/abci/types"
-	"github.com/tendermint/tendermint/crypto"
-	auto "github.com/tendermint/tendermint/libs/autofile"
-	dbm "github.com/tendermint/tendermint/libs/db"
-	"github.com/tendermint/tendermint/version"
-
 	cfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tendermint/crypto"
+	dbm "github.com/tendermint/tendermint/libs/db"
 	"github.com/tendermint/tendermint/libs/log"
 	"github.com/tendermint/tendermint/privval"
 	"github.com/tendermint/tendermint/proxy"
 	sm "github.com/tendermint/tendermint/state"
 	"github.com/tendermint/tendermint/types"
+	"github.com/tendermint/tendermint/version"
 )
 
-var consensusReplayConfig *cfg.Config
-
-func init() {
+func TestMain(m *testing.M) {
+	config = ResetConfig("consensus_reactor_test")
 	consensusReplayConfig = ResetConfig("consensus_replay_test")
+	configStateTest := ResetConfig("consensus_state_test")
+	configMempoolTest := ResetConfig("consensus_mempool_test")
+	configByzantineTest := ResetConfig("consensus_byzantine_test")
+	code := m.Run()
+	os.RemoveAll(config.RootDir)
+	os.RemoveAll(consensusReplayConfig.RootDir)
+	os.RemoveAll(configStateTest.RootDir)
+	os.RemoveAll(configMempoolTest.RootDir)
+	os.RemoveAll(configByzantineTest.RootDir)
+	os.Exit(code)
 }
 
 // These tests ensure we can always recover from failure at any part of the consensus process.
@@ -51,7 +58,8 @@ func init() {
 // 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.
 
-func startNewConsensusStateAndWaitForBlock(t *testing.T, lastBlockHeight int64, blockDB dbm.DB, stateDB dbm.DB) {
+func startNewConsensusStateAndWaitForBlock(t *testing.T, consensusReplayConfig *cfg.Config,
+	lastBlockHeight int64, blockDB dbm.DB, stateDB dbm.DB) {
 	logger := log.TestingLogger()
 	state, _ := sm.LoadStateFromDBOrGenesisFile(stateDB, consensusReplayConfig.GenesisFile())
 	privValidator := loadPrivValidator(consensusReplayConfig)
@@ -59,7 +67,6 @@ func startNewConsensusStateAndWaitForBlock(t *testing.T, lastBlockHeight int64,
 	cs.SetLogger(logger)
 
 	bytes, _ := ioutil.ReadFile(cs.config.WalFile())
-	// fmt.Printf("====== WAL: \n\r%s\n", bytes)
 	t.Logf("====== WAL: \n\r%X\n", bytes)
 
 	err := cs.Start()
@@ -70,13 +77,14 @@ func startNewConsensusStateAndWaitForBlock(t *testing.T, lastBlockHeight int64,
 	// 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)
+	newBlockSub, err := cs.eventBus.Subscribe(context.Background(), testSubscriber, types.EventQueryNewBlock)
 	require.NoError(t, err)
 	select {
-	case <-newBlockCh:
-	case <-time.After(60 * time.Second):
-		t.Fatalf("Timed out waiting for new block (see trace above)")
+	case <-newBlockSub.Out():
+	case <-newBlockSub.Cancelled():
+		t.Fatal("newBlockSub was cancelled")
+	case <-time.After(120 * time.Second):
+		t.Fatal("Timed out waiting for new block (see trace above)")
 	}
 }
 
@@ -110,21 +118,22 @@ func TestWALCrash(t *testing.T) {
 			3},
 	}
 
-	for _, tc := range testCases {
+	for i, tc := range testCases {
+		consensusReplayConfig := ResetConfig(fmt.Sprintf("%s_%d", t.Name(), i))
 		t.Run(tc.name, func(t *testing.T) {
-			crashWALandCheckLiveness(t, tc.initFn, tc.heightToStop)
+			crashWALandCheckLiveness(t, consensusReplayConfig, tc.initFn, tc.heightToStop)
 		})
 	}
 }
 
-func crashWALandCheckLiveness(t *testing.T, initFn func(dbm.DB, *ConsensusState, context.Context), heightToStop int64) {
-	walPaniced := make(chan error)
-	crashingWal := &crashingWAL{panicCh: walPaniced, heightToStop: heightToStop}
+func crashWALandCheckLiveness(t *testing.T, consensusReplayConfig *cfg.Config,
+	initFn func(dbm.DB, *ConsensusState, context.Context), heightToStop int64) {
+	walPanicked := make(chan error)
+	crashingWal := &crashingWAL{panicCh: walPanicked, 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
@@ -159,11 +168,11 @@ LOOP:
 		i++
 
 		select {
-		case err := <-walPaniced:
-			t.Logf("WAL paniced: %v", err)
+		case err := <-walPanicked:
+			t.Logf("WAL panicked: %v", err)
 
 			// make sure we can make blocks after a crash
-			startNewConsensusStateAndWaitForBlock(t, cs.Height, blockDB, stateDB)
+			startNewConsensusStateAndWaitForBlock(t, consensusReplayConfig, cs.Height, blockDB, stateDB)
 
 			// stop consensus state and transactions sender (initFn)
 			cs.Stop()
@@ -181,16 +190,18 @@ LOOP:
 
 // 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.
+// (lastPanickedForMsgIndex), 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
+	msgIndex                int // current message index
+	lastPanickedForMsgIndex int // last message for which we panicked
 }
 
+var _ WAL = &crashingWAL{}
+
 // WALWriteError indicates a WAL crash.
 type WALWriteError struct {
 	msg string
@@ -223,8 +234,8 @@ func (w *crashingWAL) Write(m WALMessage) {
 		return
 	}
 
-	if w.msgIndex > w.lastPanicedForMsgIndex {
-		w.lastPanicedForMsgIndex = w.msgIndex
+	if w.msgIndex > w.lastPanickedForMsgIndex {
+		w.lastPanickedForMsgIndex = 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()
@@ -238,8 +249,9 @@ func (w *crashingWAL) WriteSync(m WALMessage) {
 	w.Write(m)
 }
 
-func (w *crashingWAL) Group() *auto.Group { return w.next.Group() }
-func (w *crashingWAL) SearchForEndHeight(height int64, options *WALSearchOptions) (gr *auto.GroupReader, found bool, err error) {
+func (w *crashingWAL) FlushAndSync() error { return w.next.FlushAndSync() }
+
+func (w *crashingWAL) SearchForEndHeight(height int64, options *WALSearchOptions) (rd io.ReadCloser, found bool, err error) {
 	return w.next.SearchForEndHeight(height, options)
 }
 
@@ -269,29 +281,37 @@ var modes = []uint{0, 1, 2}
 
 // Sync from scratch
 func TestHandshakeReplayAll(t *testing.T) {
-	for _, m := range modes {
-		testHandshakeReplay(t, 0, m)
+	for i, m := range modes {
+		config := ResetConfig(fmt.Sprintf("%s_%v", t.Name(), i))
+		defer os.RemoveAll(config.RootDir)
+		testHandshakeReplay(t, config, 0, m)
 	}
 }
 
 // Sync many, not from scratch
 func TestHandshakeReplaySome(t *testing.T) {
-	for _, m := range modes {
-		testHandshakeReplay(t, 1, m)
+	for i, m := range modes {
+		config := ResetConfig(fmt.Sprintf("%s_%v", t.Name(), i))
+		defer os.RemoveAll(config.RootDir)
+		testHandshakeReplay(t, config, 1, m)
 	}
 }
 
 // Sync from lagging by one
 func TestHandshakeReplayOne(t *testing.T) {
-	for _, m := range modes {
-		testHandshakeReplay(t, NUM_BLOCKS-1, m)
+	for i, m := range modes {
+		config := ResetConfig(fmt.Sprintf("%s_%v", t.Name(), i))
+		defer os.RemoveAll(config.RootDir)
+		testHandshakeReplay(t, config, NUM_BLOCKS-1, m)
 	}
 }
 
 // Sync from caught up
 func TestHandshakeReplayNone(t *testing.T) {
-	for _, m := range modes {
-		testHandshakeReplay(t, NUM_BLOCKS, m)
+	for i, m := range modes {
+		config := ResetConfig(fmt.Sprintf("%s_%v", t.Name(), i))
+		defer os.RemoveAll(config.RootDir)
+		testHandshakeReplay(t, config, NUM_BLOCKS, m)
 	}
 }
 
@@ -311,10 +331,8 @@ func tempWALWithData(data []byte) string {
 }
 
 // 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_")
-
-	walBody, err := WALWithNBlocks(NUM_BLOCKS)
+func testHandshakeReplay(t *testing.T, config *cfg.Config, nBlocks int, mode uint) {
+	walBody, err := WALWithNBlocks(t, NUM_BLOCKS)
 	require.NoError(t, err)
 	walFile := tempWALWithData(walBody)
 	config.Consensus.SetWalFile(walFile)
@@ -537,10 +555,8 @@ func makeBlockchainFromWAL(wal WAL) ([]*types.Block, []*types.Commit, error) {
 			}
 		case *types.Vote:
 			if p.Type == types.PrecommitType {
-				thisBlockCommit = &types.Commit{
-					BlockID:    p.BlockID,
-					Precommits: []*types.Vote{p},
-				}
+				commitSigs := []*types.CommitSig{p.CommitSig()}
+				thisBlockCommit = types.NewCommit(p.BlockID, commitSigs)
 			}
 		}
 	}
@@ -633,6 +649,7 @@ func TestInitChainUpdateValidators(t *testing.T) {
 	clientCreator := proxy.NewLocalClientCreator(app)
 
 	config := ResetConfig("proxy_test_")
+	defer os.RemoveAll(config.RootDir)
 	privVal := privval.LoadFilePV(config.PrivValidatorKeyFile(), config.PrivValidatorStateFile())
 	stateDB, state, store := stateAndStore(config, privVal.GetPubKey(), 0x0)
 

consensus/state.go

@@ -94,7 +94,7 @@ type ConsensusState struct {
 	// internal state
 	mtx sync.RWMutex
 	cstypes.RoundState
-	state                     sm.State // State until height-1.
+	state sm.State // State until height-1.
 
 	// state changes may be triggered by: msgs from peers,
 	// msgs from ourself, or by timeouts
@@ -307,6 +307,23 @@ func (cs *ConsensusState) OnStart() error {
 	// reload from consensus log to catchup
 	if cs.doWALCatchup {
 		if err := cs.catchupReplay(cs.Height); err != nil {
+			// don't try to recover from data corruption error
+			if IsDataCorruptionError(err) {
+				cs.Logger.Error("Encountered corrupt WAL file", "err", err.Error())
+				cs.Logger.Error("Please repair the WAL file before restarting")
+				fmt.Println(`You can attempt to repair the WAL as follows:
+
+----
+WALFILE=~/.tendermint/data/cs.wal/wal
+cp $WALFILE ${WALFILE}.bak # backup the file
+go run scripts/wal2json/main.go $WALFILE > wal.json # this will panic, but can be ignored
+rm $WALFILE # remove the corrupt file
+go run scripts/json2wal/main.go wal.json $WALFILE # rebuild the file without corruption
+----`)
+
+				return err
+			}
+
 			cs.Logger.Error("Error on catchup replay. Proceeding to start ConsensusState anyway", "err", err.Error())
 			// NOTE: if we ever do return an error here,
 			// make sure to stop the timeoutTicker
@@ -437,7 +454,7 @@ func (cs *ConsensusState) updateRoundStep(round int, step cstypes.RoundStepType)
 // enterNewRound(height, 0) at cs.StartTime.
 func (cs *ConsensusState) scheduleRound0(rs *cstypes.RoundState) {
 	//cs.Logger.Info("scheduleRound0", "now", tmtime.Now(), "startTime", cs.StartTime)
-	sleepDuration := rs.StartTime.Sub(tmtime.Now()) // nolint: gotype, gosimple
+	sleepDuration := rs.StartTime.Sub(tmtime.Now())
 	cs.scheduleTimeout(sleepDuration, rs.Height, 0, cstypes.RoundStepNewHeight)
 }
 
@@ -472,7 +489,7 @@ func (cs *ConsensusState) reconstructLastCommit(state sm.State) {
 		if precommit == nil {
 			continue
 		}
-		added, err := lastPrecommits.AddVote(precommit)
+		added, err := lastPrecommits.AddVote(seenCommit.ToVote(precommit))
 		if !added || err != nil {
 			cmn.PanicCrisis(fmt.Sprintf("Failed to reconstruct LastCommit: %v", err))
 		}
@@ -549,6 +566,7 @@ func (cs *ConsensusState) updateToState(state sm.State) {
 	cs.CommitRound = -1
 	cs.LastCommit = lastPrecommits
 	cs.LastValidators = state.LastValidators
+	cs.TriggeredTimeoutPrecommit = false
 
 	cs.state = state
 
@@ -624,6 +642,15 @@ func (cs *ConsensusState) receiveRoutine(maxSteps int) {
 			cs.handleMsg(mi)
 		case mi = <-cs.internalMsgQueue:
 			cs.wal.WriteSync(mi) // NOTE: fsync
+
+			if _, ok := mi.Msg.(*VoteMessage); ok {
+				// we actually want to simulate failing during
+				// the previous WriteSync, but this isn't easy to do.
+				// Equivalent would be to fail here and manually remove
+				// some bytes from the end of the wal.
+				fail.Fail() // XXX
+			}
+
 			// handles proposals, block parts, votes
 			cs.handleMsg(mi)
 		case ti := <-cs.timeoutTicker.Chan(): // tockChan:
@@ -882,8 +909,11 @@ func (cs *ConsensusState) defaultDecideProposal(height int64, round int) {
 		}
 	}
 
+	// Flush the WAL. Otherwise, we may not recompute the same proposal to sign, and the privValidator will refuse to sign anything.
+	cs.wal.FlushAndSync()
+
 	// Make proposal
-	propBlockId := types.BlockID{block.Hash(), blockParts.Header()}
+	propBlockId := types.BlockID{Hash: block.Hash(), PartsHeader: blockParts.Header()}
 	proposal := types.NewProposal(height, round, cs.ValidRound, propBlockId)
 	if err := cs.privValidator.SignProposal(cs.state.ChainID, proposal); err == nil {
 
@@ -928,7 +958,7 @@ func (cs *ConsensusState) createProposalBlock() (block *types.Block, blockParts
 	if cs.Height == 1 {
 		// We're creating a proposal for the first block.
 		// The commit is empty, but not nil.
-		commit = &types.Commit{}
+		commit = types.NewCommit(types.BlockID{}, nil)
 	} else if cs.LastCommit.HasTwoThirdsMajority() {
 		// Make the commit from LastCommit
 		commit = cs.LastCommit.MakeCommit()
@@ -1294,7 +1324,7 @@ func (cs *ConsensusState) finalizeCommit(height int64) {
 	// Execute and commit the block, update and save the state, and update the mempool.
 	// NOTE The block.AppHash wont reflect these txs until the next block.
 	var err error
-	stateCopy, err = cs.blockExec.ApplyBlock(stateCopy, types.BlockID{block.Hash(), blockParts.Header()}, block)
+	stateCopy, err = cs.blockExec.ApplyBlock(stateCopy, types.BlockID{Hash: block.Hash(), PartsHeader: blockParts.Header()}, block)
 	if err != nil {
 		cs.Logger.Error("Error on ApplyBlock. Did the application crash? Please restart tendermint", "err", err)
 		err := cmn.Kill()
@@ -1330,7 +1360,7 @@ func (cs *ConsensusState) recordMetrics(height int64, block *types.Block) {
 	missingValidators := 0
 	missingValidatorsPower := int64(0)
 	for i, val := range cs.Validators.Validators {
-		var vote *types.Vote
+		var vote *types.CommitSig
 		if i < len(block.LastCommit.Precommits) {
 			vote = block.LastCommit.Precommits[i]
 		}
@@ -1517,7 +1547,7 @@ func (cs *ConsensusState) addVote(vote *types.Vote, peerID p2p.ID) (added bool,
 		}
 
 		cs.Logger.Info(fmt.Sprintf("Added to lastPrecommits: %v", cs.LastCommit.StringShort()))
-		cs.eventBus.PublishEventVote(types.EventDataVote{vote})
+		cs.eventBus.PublishEventVote(types.EventDataVote{Vote: vote})
 		cs.evsw.FireEvent(types.EventVote, vote)
 
 		// if we can skip timeoutCommit and have all the votes now,
@@ -1545,7 +1575,7 @@ func (cs *ConsensusState) addVote(vote *types.Vote, peerID p2p.ID) (added bool,
 		return
 	}
 
-	cs.eventBus.PublishEventVote(types.EventDataVote{vote})
+	cs.eventBus.PublishEventVote(types.EventDataVote{Vote: vote})
 	cs.evsw.FireEvent(types.EventVote, vote)
 
 	switch vote.Type {
@@ -1647,6 +1677,9 @@ func (cs *ConsensusState) addVote(vote *types.Vote, peerID p2p.ID) (added bool,
 }
 
 func (cs *ConsensusState) signVote(type_ types.SignedMsgType, hash []byte, header types.PartSetHeader) (*types.Vote, error) {
+	// Flush the WAL. Otherwise, we may not recompute the same vote to sign, and the privValidator will refuse to sign anything.
+	cs.wal.FlushAndSync()
+
 	addr := cs.privValidator.GetPubKey().Address()
 	valIndex, _ := cs.Validators.GetByAddress(addr)
 
@@ -1657,7 +1690,7 @@ func (cs *ConsensusState) signVote(type_ types.SignedMsgType, hash []byte, heade
 		Round:            cs.Round,
 		Timestamp:        cs.voteTime(),
 		Type:             type_,
-		BlockID:          types.BlockID{hash, header},
+		BlockID:          types.BlockID{Hash: hash, PartsHeader: header},
 	}
 	err := cs.privValidator.SignVote(cs.state.ChainID, vote)
 	return vote, err

consensus/state_test.go

@@ -18,14 +18,6 @@ import (
 	"github.com/tendermint/tendermint/types"
 )
 
-func init() {
-	config = ResetConfig("consensus_state_test")
-}
-
-func ensureProposeTimeout(timeoutPropose time.Duration) time.Duration {
-	return time.Duration(timeoutPropose.Nanoseconds()*2) * time.Nanosecond
-}
-
 /*
 
 ProposeSuite
@@ -1292,8 +1284,8 @@ func (n *fakeTxNotifier) Notify() {
 }
 
 func TestStartNextHeightCorrectly(t *testing.T) {
+	config.Consensus.SkipTimeoutCommit = false
 	cs1, vss := randConsensusState(4)
-	cs1.config.SkipTimeoutCommit = false
 	cs1.txNotifier = &fakeTxNotifier{ch: make(chan struct{})}
 
 	vs2, vs3, vs4 := vss[1], vss[2], vss[3]
@@ -1330,13 +1322,14 @@ func TestStartNextHeightCorrectly(t *testing.T) {
 	// add precommits
 	signAddVotes(cs1, types.PrecommitType, nil, types.PartSetHeader{}, vs2)
 	signAddVotes(cs1, types.PrecommitType, theBlockHash, theBlockParts, vs3)
+	time.Sleep(5 * time.Millisecond)
 	signAddVotes(cs1, types.PrecommitType, theBlockHash, theBlockParts, vs4)
 
-	ensureNewBlockHeader(newBlockHeader, height, theBlockHash)
-
 	rs = cs1.GetRoundState()
 	assert.True(t, rs.TriggeredTimeoutPrecommit)
 
+	ensureNewBlockHeader(newBlockHeader, height, theBlockHash)
+
 	cs1.txNotifier.(*fakeTxNotifier).Notify()
 
 	ensureNewTimeout(timeoutProposeCh, height+1, round, cs1.config.TimeoutPropose.Nanoseconds())
@@ -1344,6 +1337,64 @@ func TestStartNextHeightCorrectly(t *testing.T) {
 	assert.False(t, rs.TriggeredTimeoutPrecommit, "triggeredTimeoutPrecommit should be false at the beginning of each round")
 }
 
+func TestResetTimeoutPrecommitUponNewHeight(t *testing.T) {
+	config.Consensus.SkipTimeoutCommit = false
+	cs1, vss := randConsensusState(4)
+
+	vs2, vs3, vs4 := vss[1], vss[2], vss[3]
+	height, round := cs1.Height, cs1.Round
+
+	partSize := types.BlockPartSizeBytes
+
+	proposalCh := subscribe(cs1.eventBus, types.EventQueryCompleteProposal)
+
+	newRoundCh := subscribe(cs1.eventBus, types.EventQueryNewRound)
+	newBlockHeader := subscribe(cs1.eventBus, types.EventQueryNewBlockHeader)
+	addr := cs1.privValidator.GetPubKey().Address()
+	voteCh := subscribeToVoter(cs1, addr)
+
+	// start round and wait for propose and prevote
+	startTestRound(cs1, height, round)
+	ensureNewRound(newRoundCh, height, round)
+
+	ensureNewProposal(proposalCh, height, round)
+	rs := cs1.GetRoundState()
+	theBlockHash := rs.ProposalBlock.Hash()
+	theBlockParts := rs.ProposalBlockParts.Header()
+
+	ensurePrevote(voteCh, height, round)
+	validatePrevote(t, cs1, round, vss[0], theBlockHash)
+
+	signAddVotes(cs1, types.PrevoteType, theBlockHash, theBlockParts, vs2, vs3, vs4)
+
+	ensurePrecommit(voteCh, height, round)
+	validatePrecommit(t, cs1, round, round, vss[0], theBlockHash, theBlockHash)
+
+	rs = cs1.GetRoundState()
+
+	// add precommits
+	signAddVotes(cs1, types.PrecommitType, nil, types.PartSetHeader{}, vs2)
+	signAddVotes(cs1, types.PrecommitType, theBlockHash, theBlockParts, vs3)
+	time.Sleep(5 * time.Millisecond)
+	signAddVotes(cs1, types.PrecommitType, theBlockHash, theBlockParts, vs4)
+
+	rs = cs1.GetRoundState()
+	assert.True(t, rs.TriggeredTimeoutPrecommit)
+
+	ensureNewBlockHeader(newBlockHeader, height, theBlockHash)
+
+	prop, propBlock := decideProposal(cs1, vs2, height+1, 0)
+	propBlockParts := propBlock.MakePartSet(partSize)
+
+	if err := cs1.SetProposalAndBlock(prop, propBlock, propBlockParts, "some peer"); err != nil {
+		t.Fatal(err)
+	}
+	ensureNewProposal(proposalCh, height+1, 0)
+
+	rs = cs1.GetRoundState()
+	assert.False(t, rs.TriggeredTimeoutPrecommit, "triggeredTimeoutPrecommit should be false at the beginning of each height")
+}
+
 //------------------------------------------------------------------------------------------
 // SlashingSuite
 // TODO: Slashing
@@ -1569,11 +1620,10 @@ func TestStateOutputVoteStats(t *testing.T) {
 }
 
 // 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)
+func subscribe(eventBus *types.EventBus, q tmpubsub.Query) <-chan tmpubsub.Message {
+	sub, err := eventBus.Subscribe(context.Background(), testSubscriber, q)
 	if err != nil {
 		panic(fmt.Sprintf("failed to subscribe %s to %v", testSubscriber, q))
 	}
-	return out
+	return sub.Out()
 }

consensus/types/height_vote_set_test.go

@@ -2,6 +2,7 @@ package types
 
 import (
 	"fmt"
+	"os"
 	"testing"
 
 	cfg "github.com/tendermint/tendermint/config"
@@ -11,8 +12,11 @@ import (
 
 var config *cfg.Config // NOTE: must be reset for each _test.go file
 
-func init() {
+func TestMain(m *testing.M) {
 	config = cfg.ResetTestRoot("consensus_height_vote_set_test")
+	code := m.Run()
+	os.RemoveAll(config.RootDir)
+	os.Exit(code)
 }
 
 func TestPeerCatchupRounds(t *testing.T) {
@@ -64,7 +68,6 @@ func makeVoteHR(t *testing.T, height int64, round int, privVals []types.PrivVali
 	err := privVal.SignVote(chainID, vote)
 	if err != nil {
 		panic(fmt.Sprintf("Error signing vote: %v", err))
-		return nil
 	}
 	return vote
 }

consensus/types/round_state_test.go

@@ -3,7 +3,7 @@ package types
 import (
 	"testing"
 
-	"github.com/tendermint/go-amino"
+	amino "github.com/tendermint/go-amino"
 	"github.com/tendermint/tendermint/crypto/ed25519"
 	cmn "github.com/tendermint/tendermint/libs/common"
 	"github.com/tendermint/tendermint/types"
@@ -16,7 +16,7 @@ func BenchmarkRoundStateDeepCopy(b *testing.B) {
 	// Random validators
 	nval, ntxs := 100, 100
 	vset, _ := types.RandValidatorSet(nval, 1)
-	precommits := make([]*types.Vote, nval)
+	precommits := make([]*types.CommitSig, nval)
 	blockID := types.BlockID{
 		Hash: cmn.RandBytes(20),
 		PartsHeader: types.PartSetHeader{
@@ -25,12 +25,12 @@ func BenchmarkRoundStateDeepCopy(b *testing.B) {
 	}
 	sig := make([]byte, ed25519.SignatureSize)
 	for i := 0; i < nval; i++ {
-		precommits[i] = &types.Vote{
+		precommits[i] = (&types.Vote{
 			ValidatorAddress: types.Address(cmn.RandBytes(20)),
 			Timestamp:        tmtime.Now(),
 			BlockID:          blockID,
 			Signature:        sig,
-		}
+		}).CommitSig()
 	}
 	txs := make([]types.Tx, ntxs)
 	for i := 0; i < ntxs; i++ {
@@ -53,11 +53,8 @@ func BenchmarkRoundStateDeepCopy(b *testing.B) {
 		Data: types.Data{
 			Txs: txs,
 		},
-		Evidence: types.EvidenceData{},
-		LastCommit: &types.Commit{
-			BlockID:    blockID,
-			Precommits: precommits,
-		},
+		Evidence:   types.EvidenceData{},
+		LastCommit: types.NewCommit(blockID, precommits),
 	}
 	parts := block.MakePartSet(4096)
 	// Random Proposal

consensus/wal.go

@@ -21,6 +21,9 @@ import (
 const (
 	// must be greater than types.BlockPartSizeBytes + a few bytes
 	maxMsgSizeBytes = 1024 * 1024 // 1MB
+
+	// how often the WAL should be sync'd during period sync'ing
+	walDefaultFlushInterval = 2 * time.Second
 )
 
 //--------------------------------------------------------
@@ -54,26 +57,36 @@ func RegisterWALMessages(cdc *amino.Codec) {
 type WAL interface {
 	Write(WALMessage)
 	WriteSync(WALMessage)
-	Group() *auto.Group
-	SearchForEndHeight(height int64, options *WALSearchOptions) (gr *auto.GroupReader, found bool, err error)
+	FlushAndSync() error
 
+	SearchForEndHeight(height int64, options *WALSearchOptions) (rd io.ReadCloser, found bool, err error)
+
+	// service methods
 	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
+// 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 baseWAL struct {
 	cmn.BaseService
 
 	group *auto.Group
 
 	enc *WALEncoder
+
+	flushTicker   *time.Ticker
+	flushInterval time.Duration
 }
 
+var _ WAL = &baseWAL{}
+
+// NewWAL returns a new write-ahead logger based on `baseWAL`, which implements
+// WAL. It's flushed and synced to disk every 2s and once when stopped.
 func NewWAL(walFile string, groupOptions ...func(*auto.Group)) (*baseWAL, error) {
 	err := cmn.EnsureDir(filepath.Dir(walFile), 0700)
 	if err != nil {
@@ -85,13 +98,19 @@ func NewWAL(walFile string, groupOptions ...func(*auto.Group)) (*baseWAL, error)
 		return nil, err
 	}
 	wal := &baseWAL{
-		group: group,
-		enc:   NewWALEncoder(group),
+		group:         group,
+		enc:           NewWALEncoder(group),
+		flushInterval: walDefaultFlushInterval,
 	}
 	wal.BaseService = *cmn.NewBaseService(nil, "baseWAL", wal)
 	return wal, nil
 }
 
+// SetFlushInterval allows us to override the periodic flush interval for the WAL.
+func (wal *baseWAL) SetFlushInterval(i time.Duration) {
+	wal.flushInterval = i
+}
+
 func (wal *baseWAL) Group() *auto.Group {
 	return wal.group
 }
@@ -109,14 +128,49 @@ func (wal *baseWAL) OnStart() error {
 		wal.WriteSync(EndHeightMessage{0})
 	}
 	err = wal.group.Start()
-	return err
+	if err != nil {
+		return err
+	}
+	wal.flushTicker = time.NewTicker(wal.flushInterval)
+	go wal.processFlushTicks()
+	return nil
 }
 
+func (wal *baseWAL) processFlushTicks() {
+	for {
+		select {
+		case <-wal.flushTicker.C:
+			if err := wal.FlushAndSync(); err != nil {
+				wal.Logger.Error("Periodic WAL flush failed", "err", err)
+			}
+		case <-wal.Quit():
+			return
+		}
+	}
+}
+
+// FlushAndSync flushes and fsync's the underlying group's data to disk.
+// See auto#FlushAndSync
+func (wal *baseWAL) FlushAndSync() error {
+	return wal.group.FlushAndSync()
+}
+
+// Stop the underlying autofile group.
+// Use Wait() to ensure it's finished shutting down
+// before cleaning up files.
 func (wal *baseWAL) OnStop() {
+	wal.flushTicker.Stop()
+	wal.FlushAndSync()
 	wal.group.Stop()
 	wal.group.Close()
 }
 
+// Wait for the underlying autofile group to finish shutting down
+// so it's safe to cleanup files.
+func (wal *baseWAL) Wait() {
+	wal.group.Wait()
+}
+
 // Write is called in newStep and for each receive on the
 // peerMsgQueue and the timeoutTicker.
 // NOTE: does not call fsync()
@@ -140,7 +194,7 @@ func (wal *baseWAL) WriteSync(msg WALMessage) {
 	}
 
 	wal.Write(msg)
-	if err := wal.group.Flush(); err != nil {
+	if err := wal.FlushAndSync(); err != nil {
 		panic(fmt.Sprintf("Error flushing consensus wal buf to file. Error: %v \n", err))
 	}
 }
@@ -156,14 +210,17 @@ type WALSearchOptions struct {
 // Group reader will be nil if found equals false.
 //
 // CONTRACT: caller must close group reader.
-func (wal *baseWAL) SearchForEndHeight(height int64, options *WALSearchOptions) (gr *auto.GroupReader, found bool, err error) {
-	var msg *TimedWALMessage
+func (wal *baseWAL) SearchForEndHeight(height int64, options *WALSearchOptions) (rd io.ReadCloser, found bool, err error) {
+	var (
+		msg *TimedWALMessage
+		gr  *auto.GroupReader
+	)
 	lastHeightFound := int64(-1)
 
 	// NOTE: starting from the last file in the group because we're usually
 	// searching for the last height. See replay.go
 	min, max := wal.group.MinIndex(), wal.group.MaxIndex()
-	wal.Logger.Debug("Searching for height", "height", height, "min", min, "max", max)
+	wal.Logger.Info("Searching for height", "height", height, "min", min, "max", max)
 	for index := max; index >= min; index-- {
 		gr, err = wal.group.NewReader(index)
 		if err != nil {
@@ -183,7 +240,7 @@ func (wal *baseWAL) SearchForEndHeight(height int64, options *WALSearchOptions)
 				break
 			}
 			if options.IgnoreDataCorruptionErrors && IsDataCorruptionError(err) {
-				wal.Logger.Debug("Corrupted entry. Skipping...", "err", err)
+				wal.Logger.Error("Corrupted entry. Skipping...", "err", err)
 				// do nothing
 				continue
 			} else if err != nil {
@@ -194,7 +251,7 @@ func (wal *baseWAL) SearchForEndHeight(height int64, options *WALSearchOptions)
 			if m, ok := msg.Msg.(EndHeightMessage); ok {
 				lastHeightFound = m.Height
 				if m.Height == height { // found
-					wal.Logger.Debug("Found", "height", height, "index", index)
+					wal.Logger.Info("Found", "height", height, "index", index)
 					return gr, true, nil
 				}
 			}
@@ -219,12 +276,17 @@ func NewWALEncoder(wr io.Writer) *WALEncoder {
 	return &WALEncoder{wr}
 }
 
-// Encode writes the custom encoding of v to the stream.
+// Encode writes the custom encoding of v to the stream. It returns an error if
+// the amino-encoded size of v is greater than 1MB. Any error encountered
+// during the write is also returned.
 func (enc *WALEncoder) Encode(v *TimedWALMessage) error {
 	data := cdc.MustMarshalBinaryBare(v)
 
 	crc := crc32.Checksum(data, crc32c)
 	length := uint32(len(data))
+	if length > maxMsgSizeBytes {
+		return fmt.Errorf("Msg is too big: %d bytes, max: %d bytes", length, maxMsgSizeBytes)
+	}
 	totalLength := 8 + int(length)
 
 	msg := make([]byte, totalLength)
@@ -281,31 +343,31 @@ func (dec *WALDecoder) Decode() (*TimedWALMessage, error) {
 		return nil, err
 	}
 	if err != nil {
-		return nil, fmt.Errorf("failed to read checksum: %v", err)
+		return nil, DataCorruptionError{fmt.Errorf("failed to read checksum: %v", err)}
 	}
 	crc := binary.BigEndian.Uint32(b)
 
 	b = make([]byte, 4)
 	_, err = dec.rd.Read(b)
 	if err != nil {
-		return nil, fmt.Errorf("failed to read length: %v", err)
+		return nil, DataCorruptionError{fmt.Errorf("failed to read length: %v", err)}
 	}
 	length := binary.BigEndian.Uint32(b)
 
 	if length > maxMsgSizeBytes {
-		return nil, fmt.Errorf("length %d exceeded maximum possible value of %d bytes", length, maxMsgSizeBytes)
+		return nil, DataCorruptionError{fmt.Errorf("length %d exceeded maximum possible value of %d bytes", length, maxMsgSizeBytes)}
 	}
 
 	data := make([]byte, length)
-	_, err = dec.rd.Read(data)
+	n, err := dec.rd.Read(data)
 	if err != nil {
-		return nil, fmt.Errorf("failed to read data: %v", err)
+		return nil, DataCorruptionError{fmt.Errorf("failed to read data: %v (read: %d, wanted: %d)", err, n, length)}
 	}
 
 	// check checksum before decoding data
 	actualCRC := crc32.Checksum(data, crc32c)
 	if actualCRC != crc {
-		return nil, DataCorruptionError{fmt.Errorf("checksums do not match: (read: %v, actual: %v)", crc, actualCRC)}
+		return nil, DataCorruptionError{fmt.Errorf("checksums do not match: read: %v, actual: %v", crc, actualCRC)}
 	}
 
 	var res = new(TimedWALMessage) // nolint: gosimple
@@ -319,10 +381,12 @@ func (dec *WALDecoder) Decode() (*TimedWALMessage, error) {
 
 type nilWAL struct{}
 
+var _ WAL = nilWAL{}
+
 func (nilWAL) Write(m WALMessage)     {}
 func (nilWAL) WriteSync(m WALMessage) {}
-func (nilWAL) Group() *auto.Group     { return nil }
-func (nilWAL) SearchForEndHeight(height int64, options *WALSearchOptions) (gr *auto.GroupReader, found bool, err error) {
+func (nilWAL) FlushAndSync() error    { return nil }
+func (nilWAL) SearchForEndHeight(height int64, options *WALSearchOptions) (rd io.ReadCloser, found bool, err error) {
 	return nil, false, nil
 }
 func (nilWAL) Start() error { return nil }

consensus/wal_generator.go

@@ -5,16 +5,14 @@ import (
 	"bytes"
 	"fmt"
 	"io"
-	"os"
 	"path/filepath"
-	"strings"
+	"testing"
 	"time"
 
 	"github.com/pkg/errors"
 	"github.com/tendermint/tendermint/abci/example/kvstore"
 	bc "github.com/tendermint/tendermint/blockchain"
 	cfg "github.com/tendermint/tendermint/config"
-	auto "github.com/tendermint/tendermint/libs/autofile"
 	cmn "github.com/tendermint/tendermint/libs/common"
 	"github.com/tendermint/tendermint/libs/db"
 	"github.com/tendermint/tendermint/libs/log"
@@ -24,12 +22,12 @@ import (
 	"github.com/tendermint/tendermint/types"
 )
 
-// WALGenerateNBlocks generates a consensus WAL. It does this by spining up a
+// WALGenerateNBlocks generates a consensus WAL. It does this by spinning 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. If the node fails to produce given numBlocks, it returns an error.
-func WALGenerateNBlocks(wr io.Writer, numBlocks int) (err error) {
-	config := getConfig()
+func WALGenerateNBlocks(t *testing.T, wr io.Writer, numBlocks int) (err error) {
+	config := getConfig(t)
 
 	app := kvstore.NewPersistentKVStoreApplication(filepath.Join(config.DBDir(), "wal_generator"))
 
@@ -102,11 +100,11 @@ func WALGenerateNBlocks(wr io.Writer, numBlocks int) (err error) {
 }
 
 //WALWithNBlocks returns a WAL content with numBlocks.
-func WALWithNBlocks(numBlocks int) (data []byte, err error) {
+func WALWithNBlocks(t *testing.T, numBlocks int) (data []byte, err error) {
 	var b bytes.Buffer
 	wr := bufio.NewWriter(&b)
 
-	if err := WALGenerateNBlocks(wr, numBlocks); err != nil {
+	if err := WALGenerateNBlocks(t, wr, numBlocks); err != nil {
 		return []byte{}, err
 	}
 
@@ -114,18 +112,6 @@ func WALWithNBlocks(numBlocks int) (data []byte, err error) {
 	return b.Bytes(), nil
 }
 
-// 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
@@ -140,9 +126,8 @@ func makeAddrs() (string, string, string) {
 }
 
 // getConfig returns a config for test cases
-func getConfig() *cfg.Config {
-	pathname := makePathname()
-	c := cfg.ResetTestRoot(fmt.Sprintf("%s_%d", pathname, cmn.RandInt()))
+func getConfig(t *testing.T) *cfg.Config {
+	c := cfg.ResetTestRoot(t.Name())
 
 	// and we use random ports to run in parallel
 	tm, rpc, grpc := makeAddrs()
@@ -206,10 +191,9 @@ func (w *byteBufferWAL) WriteSync(m WALMessage) {
 	w.Write(m)
 }
 
-func (w *byteBufferWAL) Group() *auto.Group {
-	panic("not implemented")
-}
-func (w *byteBufferWAL) SearchForEndHeight(height int64, options *WALSearchOptions) (gr *auto.GroupReader, found bool, err error) {
+func (w *byteBufferWAL) FlushAndSync() error { return nil }
+
+func (w *byteBufferWAL) SearchForEndHeight(height int64, options *WALSearchOptions) (rd io.ReadCloser, found bool, err error) {
 	return nil, false, nil
 }
 

consensus/wal_test.go

@@ -3,10 +3,10 @@ package consensus
 import (
 	"bytes"
 	"crypto/rand"
-	"fmt"
 	"io/ioutil"
 	"os"
 	"path/filepath"
+
 	// "sync"
 	"testing"
 	"time"
@@ -21,6 +21,10 @@ import (
 	"github.com/stretchr/testify/require"
 )
 
+const (
+	walTestFlushInterval = time.Duration(100) * time.Millisecond
+)
+
 func TestWALTruncate(t *testing.T) {
 	walDir, err := ioutil.TempDir("", "wal")
 	require.NoError(t, err)
@@ -28,8 +32,10 @@ func TestWALTruncate(t *testing.T) {
 
 	walFile := filepath.Join(walDir, "wal")
 
-	//this magic number 4K can truncate the content when RotateFile. defaultHeadSizeLimit(10M) is hard to simulate.
-	//this magic number 1 * time.Millisecond make RotateFile check frequently. defaultGroupCheckDuration(5s) is hard to simulate.
+	// this magic number 4K can truncate the content when RotateFile.
+	// defaultHeadSizeLimit(10M) is hard to simulate.
+	// this magic number 1 * time.Millisecond make RotateFile check frequently.
+	// defaultGroupCheckDuration(5s) is hard to simulate.
 	wal, err := NewWAL(walFile,
 		autofile.GroupHeadSizeLimit(4096),
 		autofile.GroupCheckDuration(1*time.Millisecond),
@@ -38,22 +44,28 @@ func TestWALTruncate(t *testing.T) {
 	wal.SetLogger(log.TestingLogger())
 	err = wal.Start()
 	require.NoError(t, err)
-	defer wal.Stop()
+	defer func() {
+		wal.Stop()
+		// wait for the wal to finish shutting down so we
+		// can safely remove the directory
+		wal.Wait()
+	}()
 
-	//60 block's size nearly 70K, greater than group's headBuf size(4096 * 10), when headBuf is full, truncate content will Flush to the file.
-	//at this time, RotateFile is called, truncate content exist in each file.
-	err = WALGenerateNBlocks(wal.Group(), 60)
+	// 60 block's size nearly 70K, greater than group's headBuf size(4096 * 10),
+	// when headBuf is full, truncate content will Flush to the file. at this
+	// time, RotateFile is called, truncate content exist in each file.
+	err = WALGenerateNBlocks(t, wal.Group(), 60)
 	require.NoError(t, err)
 
 	time.Sleep(1 * time.Millisecond) //wait groupCheckDuration, make sure RotateFile run
 
-	wal.Group().Flush()
+	wal.FlushAndSync()
 
 	h := int64(50)
 	gr, found, err := wal.SearchForEndHeight(h, &WALSearchOptions{})
-	assert.NoError(t, err, fmt.Sprintf("expected not to err on height %d", h))
-	assert.True(t, found, fmt.Sprintf("expected to find end height for %d", h))
-	assert.NotNil(t, gr, "expected group not to be nil")
+	assert.NoError(t, err, "expected not to err on height %d", h)
+	assert.True(t, found, "expected to find end height for %d", h)
+	assert.NotNil(t, gr)
 	defer gr.Close()
 
 	dec := NewWALDecoder(gr)
@@ -61,14 +73,14 @@ func TestWALTruncate(t *testing.T) {
 	assert.NoError(t, err, "expected to decode a message")
 	rs, ok := msg.Msg.(tmtypes.EventDataRoundState)
 	assert.True(t, ok, "expected message of type EventDataRoundState")
-	assert.Equal(t, rs.Height, h+1, fmt.Sprintf("wrong height"))
+	assert.Equal(t, rs.Height, h+1, "wrong height")
 }
 
 func TestWALEncoderDecoder(t *testing.T) {
 	now := tmtime.Now()
 	msgs := []TimedWALMessage{
-		TimedWALMessage{Time: now, Msg: EndHeightMessage{0}},
-		TimedWALMessage{Time: now, Msg: timeoutInfo{Duration: time.Second, Height: 1, Round: 1, Step: types.RoundStepPropose}},
+		{Time: now, Msg: EndHeightMessage{0}},
+		{Time: now, Msg: timeoutInfo{Duration: time.Second, Height: 1, Round: 1, Step: types.RoundStepPropose}},
 	}
 
 	b := new(bytes.Buffer)
@@ -89,8 +101,28 @@ func TestWALEncoderDecoder(t *testing.T) {
 	}
 }
 
+func TestWALWritePanicsIfMsgIsTooBig(t *testing.T) {
+	walDir, err := ioutil.TempDir("", "wal")
+	require.NoError(t, err)
+	defer os.RemoveAll(walDir)
+	walFile := filepath.Join(walDir, "wal")
+
+	wal, err := NewWAL(walFile)
+	require.NoError(t, err)
+	err = wal.Start()
+	require.NoError(t, err)
+	defer func() {
+		wal.Stop()
+		// wait for the wal to finish shutting down so we
+		// can safely remove the directory
+		wal.Wait()
+	}()
+
+	assert.Panics(t, func() { wal.Write(make([]byte, maxMsgSizeBytes+1)) })
+}
+
 func TestWALSearchForEndHeight(t *testing.T) {
-	walBody, err := WALWithNBlocks(6)
+	walBody, err := WALWithNBlocks(t, 6)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -102,9 +134,9 @@ func TestWALSearchForEndHeight(t *testing.T) {
 
 	h := int64(3)
 	gr, found, err := wal.SearchForEndHeight(h, &WALSearchOptions{})
-	assert.NoError(t, err, fmt.Sprintf("expected not to err on height %d", h))
-	assert.True(t, found, fmt.Sprintf("expected to find end height for %d", h))
-	assert.NotNil(t, gr, "expected group not to be nil")
+	assert.NoError(t, err, "expected not to err on height %d", h)
+	assert.True(t, found, "expected to find end height for %d", h)
+	assert.NotNil(t, gr)
 	defer gr.Close()
 
 	dec := NewWALDecoder(gr)
@@ -112,7 +144,47 @@ func TestWALSearchForEndHeight(t *testing.T) {
 	assert.NoError(t, err, "expected to decode a message")
 	rs, ok := msg.Msg.(tmtypes.EventDataRoundState)
 	assert.True(t, ok, "expected message of type EventDataRoundState")
-	assert.Equal(t, rs.Height, h+1, fmt.Sprintf("wrong height"))
+	assert.Equal(t, rs.Height, h+1, "wrong height")
+}
+
+func TestWALPeriodicSync(t *testing.T) {
+	walDir, err := ioutil.TempDir("", "wal")
+	require.NoError(t, err)
+	defer os.RemoveAll(walDir)
+
+	walFile := filepath.Join(walDir, "wal")
+	wal, err := NewWAL(walFile, autofile.GroupCheckDuration(1*time.Millisecond))
+	require.NoError(t, err)
+
+	wal.SetFlushInterval(walTestFlushInterval)
+	wal.SetLogger(log.TestingLogger())
+
+	// Generate some data
+	err = WALGenerateNBlocks(t, wal.Group(), 5)
+	require.NoError(t, err)
+
+	// We should have data in the buffer now
+	assert.NotZero(t, wal.Group().Buffered())
+
+	require.NoError(t, wal.Start())
+	defer func() {
+		wal.Stop()
+		wal.Wait()
+	}()
+
+	time.Sleep(walTestFlushInterval + (10 * time.Millisecond))
+
+	// The data should have been flushed by the periodic sync
+	assert.Zero(t, wal.Group().Buffered())
+
+	h := int64(4)
+	gr, found, err := wal.SearchForEndHeight(h, &WALSearchOptions{})
+	assert.NoError(t, err, "expected not to err on height %d", h)
+	assert.True(t, found, "expected to find end height for %d", h)
+	assert.NotNil(t, gr)
+	if gr != nil {
+		gr.Close()
+	}
 }
 
 /*

consensus/wire.go

@@ -1,7 +1,7 @@
 package consensus
 
 import (
-	"github.com/tendermint/go-amino"
+	amino "github.com/tendermint/go-amino"
 	"github.com/tendermint/tendermint/types"
 )
 

crypto/encoding/amino/encode_test.go

@@ -25,9 +25,8 @@ func checkAminoBinary(t *testing.T, src, dst interface{}, size int) {
 		assert.Equal(t, byterSrc.Bytes(), bz, "Amino binary vs Bytes() mismatch")
 	}
 	// Make sure we have the expected length.
-	if size != -1 {
-		assert.Equal(t, size, len(bz), "Amino binary size mismatch")
-	}
+	assert.Equal(t, size, len(bz), "Amino binary size mismatch")
+
 	// Unmarshal.
 	err = cdc.UnmarshalBinaryBare(bz, dst)
 	require.Nil(t, err, "%+v", err)
@@ -48,6 +47,8 @@ func checkAminoJSON(t *testing.T, src interface{}, dst interface{}, isNil bool)
 	require.Nil(t, err, "%+v", err)
 }
 
+// ExamplePrintRegisteredTypes refers to unknown identifier: PrintRegisteredTypes
+//nolint:govet
 func ExamplePrintRegisteredTypes() {
 	cdc.PrintTypes(os.Stdout)
 	// Output: | Type | Name | Prefix | Length | Notes |

crypto/merkle/proof.go

@@ -98,7 +98,7 @@ func (prt *ProofRuntime) Decode(pop ProofOp) (ProofOperator, error) {
 }
 
 func (prt *ProofRuntime) DecodeProof(proof *Proof) (ProofOperators, error) {
-	var poz ProofOperators
+	poz := make(ProofOperators, 0, len(proof.Ops))
 	for _, pop := range proof.Ops {
 		operator, err := prt.Decode(pop)
 		if err != nil {

crypto/merkle/proof_key_path_test.go

@@ -1,6 +1,8 @@
 package merkle
 
 import (
+	// it is ok to use math/rand here: we do not need a cryptographically secure random
+	// number generator here and we can run the tests a bit faster
 	"math/rand"
 	"testing"
 
@@ -24,7 +26,7 @@ func TestKeyPath(t *testing.T) {
 					keys[i][j] = alphanum[rand.Intn(len(alphanum))]
 				}
 			case KeyEncodingHex:
-				rand.Read(keys[i])
+				rand.Read(keys[i]) //nolint: gosec
 			default:
 				panic("Unexpected encoding")
 			}

crypto/merkle/proof_test.go

@@ -4,7 +4,7 @@ import (
 	"testing"
 
 	"github.com/stretchr/testify/assert"
-	"github.com/tendermint/go-amino"
+	amino "github.com/tendermint/go-amino"
 	cmn "github.com/tendermint/tendermint/libs/common"
 )
 
@@ -26,6 +26,7 @@ func NewDominoOp(key, input, output string) DominoOp {
 	}
 }
 
+//nolint:unused
 func DominoOpDecoder(pop ProofOp) (ProofOperator, error) {
 	if pop.Type != ProofOpDomino {
 		panic("unexpected proof op type")

crypto/merkle/rfc6962_test.go

@@ -26,7 +26,7 @@ import (
 func TestRFC6962Hasher(t *testing.T) {
 	_, leafHashTrail := trailsFromByteSlices([][]byte{[]byte("L123456")})
 	leafHash := leafHashTrail.Hash
-	_, leafHashTrail = trailsFromByteSlices([][]byte{[]byte{}})
+	_, leafHashTrail = trailsFromByteSlices([][]byte{{}})
 	emptyLeafHash := leafHashTrail.Hash
 	for _, tc := range []struct {
 		desc string

crypto/merkle/wire.go

@@ -1,7 +1,7 @@
 package merkle
 
 import (
-	"github.com/tendermint/go-amino"
+	amino "github.com/tendermint/go-amino"
 )
 
 var cdc *amino.Codec

crypto/random.go

@@ -1,42 +1,11 @@
 package crypto
 
 import (
-	"crypto/cipher"
 	crand "crypto/rand"
-	"crypto/sha256"
 	"encoding/hex"
 	"io"
-	"sync"
-
-	"golang.org/x/crypto/chacha20poly1305"
 )
 
-// NOTE: This is ignored for now until we have time
-// to properly review the MixEntropy function - https://github.com/tendermint/tendermint/issues/2099.
-//
-// The randomness here is derived from xoring a chacha20 keystream with
-// output from crypto/rand's OS Entropy Reader. (Due to fears of the OS'
-// entropy being backdoored)
-//
-// For forward secrecy of produced randomness, the internal chacha key is hashed
-// and thereby rotated after each call.
-var gRandInfo *randInfo
-
-func init() {
-	gRandInfo = &randInfo{}
-
-	// TODO: uncomment after reviewing MixEntropy -
-	// https://github.com/tendermint/tendermint/issues/2099
-	// gRandInfo.MixEntropy(randBytes(32)) // Init
-}
-
-// WARNING: This function needs review - https://github.com/tendermint/tendermint/issues/2099.
-// Mix additional bytes of randomness, e.g. from hardware, user-input, etc.
-// It is OK to call it multiple times.  It does not diminish security.
-func MixEntropy(seedBytes []byte) {
-	gRandInfo.MixEntropy(seedBytes)
-}
-
 // This only uses the OS's randomness
 func randBytes(numBytes int) []byte {
 	b := make([]byte, numBytes)
@@ -52,19 +21,6 @@ func CRandBytes(numBytes int) []byte {
 	return randBytes(numBytes)
 }
 
-/* TODO: uncomment after reviewing MixEntropy - https://github.com/tendermint/tendermint/issues/2099
-// This uses the OS and the Seed(s).
-func CRandBytes(numBytes int) []byte {
-	return randBytes(numBytes)
-		b := make([]byte, numBytes)
-		_, err := gRandInfo.Read(b)
-		if err != nil {
-			panic(err)
-		}
-		return b
-}
-*/
-
 // CRandHex returns a hex encoded string that's floor(numDigits/2) * 2 long.
 //
 // Note: CRandHex(24) gives 96 bits of randomness that
@@ -77,63 +33,3 @@ func CRandHex(numDigits int) string {
 func CReader() io.Reader {
 	return crand.Reader
 }
-
-/* TODO: uncomment after reviewing MixEntropy - https://github.com/tendermint/tendermint/issues/2099
-// Returns a crand.Reader mixed with user-supplied entropy
-func CReader() io.Reader {
-	return gRandInfo
-}
-*/
-
-//--------------------------------------------------------------------------------
-
-type randInfo struct {
-	mtx       sync.Mutex
-	seedBytes [chacha20poly1305.KeySize]byte
-	chacha    cipher.AEAD
-	reader    io.Reader
-}
-
-// You can call this as many times as you'd like.
-// XXX/TODO: review - https://github.com/tendermint/tendermint/issues/2099
-func (ri *randInfo) MixEntropy(seedBytes []byte) {
-	ri.mtx.Lock()
-	defer ri.mtx.Unlock()
-	// Make new ri.seedBytes using passed seedBytes and current ri.seedBytes:
-	// ri.seedBytes = sha256( seedBytes || ri.seedBytes )
-	h := sha256.New()
-	h.Write(seedBytes)
-	h.Write(ri.seedBytes[:])
-	hashBytes := h.Sum(nil)
-	copy(ri.seedBytes[:], hashBytes)
-	chacha, err := chacha20poly1305.New(ri.seedBytes[:])
-	if err != nil {
-		panic("Initializing chacha20 failed")
-	}
-	ri.chacha = chacha
-	// Create new reader
-	ri.reader = &cipher.StreamReader{S: ri, R: crand.Reader}
-}
-
-func (ri *randInfo) XORKeyStream(dst, src []byte) {
-	// nonce being 0 is safe due to never re-using a key.
-	emptyNonce := make([]byte, 12)
-	tmpDst := ri.chacha.Seal([]byte{}, emptyNonce, src, []byte{0})
-	// this removes the poly1305 tag as well, since chacha is a stream cipher
-	// and we truncate at input length.
-	copy(dst, tmpDst[:len(src)])
-	// hash seedBytes for forward secrecy, and initialize new chacha instance
-	newSeed := sha256.Sum256(ri.seedBytes[:])
-	chacha, err := chacha20poly1305.New(newSeed[:])
-	if err != nil {
-		panic("Initializing chacha20 failed")
-	}
-	ri.chacha = chacha
-}
-
-func (ri *randInfo) Read(b []byte) (n int, err error) {
-	ri.mtx.Lock()
-	n, err = ri.reader.Read(b)
-	ri.mtx.Unlock()
-	return
-}

crypto/secp256k1/secp256k1.go

@@ -7,10 +7,12 @@ import (
 	"fmt"
 	"io"
 
-	secp256k1 "github.com/tendermint/btcd/btcec"
-	amino "github.com/tendermint/go-amino"
 	"golang.org/x/crypto/ripemd160"
 
+	secp256k1 "github.com/btcsuite/btcd/btcec"
+
+	amino "github.com/tendermint/go-amino"
+
 	"github.com/tendermint/tendermint/crypto"
 )
 
@@ -44,16 +46,6 @@ func (privKey PrivKeySecp256k1) Bytes() []byte {
 	return cdc.MustMarshalBinaryBare(privKey)
 }
 
-// Sign creates an ECDSA signature on curve Secp256k1, using SHA256 on the msg.
-func (privKey PrivKeySecp256k1) Sign(msg []byte) ([]byte, error) {
-	priv, _ := secp256k1.PrivKeyFromBytes(secp256k1.S256(), privKey[:])
-	sig, err := priv.Sign(crypto.Sha256(msg))
-	if err != nil {
-		return nil, err
-	}
-	return sig.Serialize(), nil
-}
-
 // PubKey performs the point-scalar multiplication from the privKey on the
 // generator point to get the pubkey.
 func (privKey PrivKeySecp256k1) PubKey() crypto.PubKey {
@@ -137,20 +129,6 @@ func (pubKey PubKeySecp256k1) Bytes() []byte {
 	return bz
 }
 
-func (pubKey PubKeySecp256k1) VerifyBytes(msg []byte, sig []byte) bool {
-	pub, err := secp256k1.ParsePubKey(pubKey[:], secp256k1.S256())
-	if err != nil {
-		return false
-	}
-	parsedSig, err := secp256k1.ParseSignature(sig[:], secp256k1.S256())
-	if err != nil {
-		return false
-	}
-	// Underlying library ensures that this signature is in canonical form, to
-	// prevent Secp256k1 malleability from altering the sign of the s term.
-	return parsedSig.Verify(crypto.Sha256(msg), pub)
-}
-
 func (pubKey PubKeySecp256k1) String() string {
 	return fmt.Sprintf("PubKeySecp256k1{%X}", pubKey[:])
 }

crypto/secp256k1/secp256k1_cgo.go

@@ -0,0 +1,24 @@
+// +build libsecp256k1
+
+package secp256k1
+
+import (
+	"github.com/ethereum/go-ethereum/crypto/secp256k1"
+
+	"github.com/tendermint/tendermint/crypto"
+)
+
+// Sign creates an ECDSA signature on curve Secp256k1, using SHA256 on the msg.
+func (privKey PrivKeySecp256k1) Sign(msg []byte) ([]byte, error) {
+	rsv, err := secp256k1.Sign(crypto.Sha256(msg), privKey[:])
+	if err != nil {
+		return nil, err
+	}
+	// we do not need v  in r||s||v:
+	rs := rsv[:len(rsv)-1]
+	return rs, nil
+}
+
+func (pubKey PubKeySecp256k1) VerifyBytes(msg []byte, sig []byte) bool {
+	return secp256k1.VerifySignature(pubKey[:], crypto.Sha256(msg), sig)
+}

crypto/secp256k1/secp256k1_nocgo.go

@@ -0,0 +1,70 @@
+// +build !libsecp256k1
+
+package secp256k1
+
+import (
+	"math/big"
+
+	secp256k1 "github.com/btcsuite/btcd/btcec"
+
+	"github.com/tendermint/tendermint/crypto"
+)
+
+// used to reject malleable signatures
+// see:
+//  - https://github.com/ethereum/go-ethereum/blob/f9401ae011ddf7f8d2d95020b7446c17f8d98dc1/crypto/signature_nocgo.go#L90-L93
+//  - https://github.com/ethereum/go-ethereum/blob/f9401ae011ddf7f8d2d95020b7446c17f8d98dc1/crypto/crypto.go#L39
+var secp256k1halfN = new(big.Int).Rsh(secp256k1.S256().N, 1)
+
+// Sign creates an ECDSA signature on curve Secp256k1, using SHA256 on the msg.
+// The returned signature will be of the form R || S (in lower-S form).
+func (privKey PrivKeySecp256k1) Sign(msg []byte) ([]byte, error) {
+	priv, _ := secp256k1.PrivKeyFromBytes(secp256k1.S256(), privKey[:])
+	sig, err := priv.Sign(crypto.Sha256(msg))
+	if err != nil {
+		return nil, err
+	}
+	sigBytes := serializeSig(sig)
+	return sigBytes, nil
+}
+
+// VerifyBytes verifies a signature of the form R || S.
+// It rejects signatures which are not in lower-S form.
+func (pubKey PubKeySecp256k1) VerifyBytes(msg []byte, sigStr []byte) bool {
+	if len(sigStr) != 64 {
+		return false
+	}
+	pub, err := secp256k1.ParsePubKey(pubKey[:], secp256k1.S256())
+	if err != nil {
+		return false
+	}
+	// parse the signature:
+	signature := signatureFromBytes(sigStr)
+	// Reject malleable signatures. libsecp256k1 does this check but btcec doesn't.
+	// see: https://github.com/ethereum/go-ethereum/blob/f9401ae011ddf7f8d2d95020b7446c17f8d98dc1/crypto/signature_nocgo.go#L90-L93
+	if signature.S.Cmp(secp256k1halfN) > 0 {
+		return false
+	}
+	return signature.Verify(crypto.Sha256(msg), pub)
+}
+
+// Read Signature struct from R || S. Caller needs to ensure
+// that len(sigStr) == 64.
+func signatureFromBytes(sigStr []byte) *secp256k1.Signature {
+	return &secp256k1.Signature{
+		R: new(big.Int).SetBytes(sigStr[:32]),
+		S: new(big.Int).SetBytes(sigStr[32:64]),
+	}
+}
+
+// Serialize signature to R || S.
+// R, S are padded to 32 bytes respectively.
+func serializeSig(sig *secp256k1.Signature) []byte {
+	rBytes := sig.R.Bytes()
+	sBytes := sig.S.Bytes()
+	sigBytes := make([]byte, 64)
+	// 0 pad the byte arrays from the left if they aren't big enough.
+	copy(sigBytes[32-len(rBytes):32], rBytes)
+	copy(sigBytes[64-len(sBytes):64], sBytes)
+	return sigBytes
+}

crypto/secp256k1/secp256k1_nocgo_test.go

@@ -0,0 +1,39 @@
+// +build !libsecp256k1
+
+package secp256k1
+
+import (
+	"testing"
+
+	secp256k1 "github.com/btcsuite/btcd/btcec"
+
+	"github.com/stretchr/testify/require"
+)
+
+// Ensure that signature verification works, and that
+// non-canonical signatures fail.
+// Note: run with CGO_ENABLED=0 or go test -tags !cgo.
+func TestSignatureVerificationAndRejectUpperS(t *testing.T) {
+	msg := []byte("We have lingered long enough on the shores of the cosmic ocean.")
+	for i := 0; i < 500; i++ {
+		priv := GenPrivKey()
+		sigStr, err := priv.Sign(msg)
+		require.NoError(t, err)
+		sig := signatureFromBytes(sigStr)
+		require.False(t, sig.S.Cmp(secp256k1halfN) > 0)
+
+		pub := priv.PubKey()
+		require.True(t, pub.VerifyBytes(msg, sigStr))
+
+		// malleate:
+		sig.S.Sub(secp256k1.S256().CurveParams.N, sig.S)
+		require.True(t, sig.S.Cmp(secp256k1halfN) > 0)
+		malSigStr := serializeSig(sig)
+
+		require.False(t, pub.VerifyBytes(msg, malSigStr),
+			"VerifyBytes incorrect with malleated & invalid S. sig=%v, key=%v",
+			sig,
+			priv,
+		)
+	}
+}

crypto/secp256k1/secpk256k1_test.go

@@ -11,7 +11,7 @@ import (
 	"github.com/tendermint/tendermint/crypto"
 	"github.com/tendermint/tendermint/crypto/secp256k1"
 
-	underlyingSecp256k1 "github.com/tendermint/btcd/btcec"
+	underlyingSecp256k1 "github.com/btcsuite/btcd/btcec"
 )
 
 type keyData struct {

crypto/xsalsa20symmetric/symmetric.go

@@ -17,7 +17,6 @@ const secretLen = 32
 
 // secret must be 32 bytes long. Use something like Sha256(Bcrypt(passphrase))
 // The ciphertext is (secretbox.Overhead + 24) bytes longer than the plaintext.
-// NOTE: call crypto.MixEntropy() first.
 func EncryptSymmetric(plaintext []byte, secret []byte) (ciphertext []byte) {
 	if len(secret) != secretLen {
 		cmn.PanicSanity(fmt.Sprintf("Secret must be 32 bytes long, got len %v", len(secret)))

crypto/xsalsa20symmetric/symmetric_test.go

@@ -13,8 +13,6 @@ import (
 
 func TestSimple(t *testing.T) {
 
-	crypto.MixEntropy([]byte("someentropy"))
-
 	plaintext := []byte("sometext")
 	secret := []byte("somesecretoflengththirtytwo===32")
 	ciphertext := EncryptSymmetric(plaintext, secret)
@@ -26,8 +24,6 @@ func TestSimple(t *testing.T) {
 
 func TestSimpleWithKDF(t *testing.T) {
 
-	crypto.MixEntropy([]byte("someentropy"))
-
 	plaintext := []byte("sometext")
 	secretPass := []byte("somesecret")
 	secret, err := bcrypt.GenerateFromPassword(secretPass, 12)

docs/.vuepress/config.js

@@ -21,7 +21,7 @@ module.exports = {
     },
     nav: [
       { text: "Back to Tendermint", link: "https://tendermint.com" },
-      { text: "RPC", link: "../rpc/" }
+      { text: "RPC", link: "https://tendermint.com/rpc/" }
     ],
     sidebar: [
       {
@@ -63,7 +63,8 @@ module.exports = {
           "/tendermint-core/light-client-protocol",
           "/tendermint-core/metrics",
           "/tendermint-core/secure-p2p",
-          "/tendermint-core/validators"
+          "/tendermint-core/validators",
+          "/tendermint-core/mempool"
         ]
       },
       {
@@ -79,10 +80,11 @@ module.exports = {
         title: "Tools",
         collapsable: false,
         children:  [
-	  "/tools/",
-	  "/tools/benchmarking",
-	  "/tools/monitoring"
-	]
+          "/tools/",
+          "/tools/benchmarking",
+          "/tools/monitoring",
+          "/tools/remote-signer-validation"
+        ]
       },
       {
         title: "Tendermint Spec",

docs/DOCS_README.md

@@ -66,11 +66,12 @@ To build and serve the documentation locally, run:
 
 ```
 # from this directory
-npm install
 npm install -g vuepress
 ```
 
-then change the following line in the `config.js`:
+NOTE: the command may require `sudo`.
+
+then change the following line in the `.vuepress/config.js`:
 
 ```
 base: "/docs/",

docs/app-dev/abci-cli.md

@@ -89,12 +89,14 @@ func cmdKVStore(cmd *cobra.Command, args []string) error {
         return err
     }
 
-    // Wait forever
-    cmn.TrapSignal(func() {
+    // Stop upon receiving SIGTERM or CTRL-C.
+    cmn.TrapSignal(logger, func() {
         // Cleanup
         srv.Stop()
     })
-    return nil
+
+    // Run forever.
+    select {}
 }
 ```
 
@@ -238,12 +240,14 @@ func cmdCounter(cmd *cobra.Command, args []string) error {
         return err
     }
 
-    // Wait forever
-    cmn.TrapSignal(func() {
+    // Stop upon receiving SIGTERM or CTRL-C.
+    cmn.TrapSignal(logger, func() {
         // Cleanup
         srv.Stop()
     })
-    return nil
+
+    // Run forever.
+    select {}
 }
 ```
 

docs/architecture/adr-033-pubsub.md

@@ -5,13 +5,17 @@ Author: Anton Kaliaev (@melekes)
 ## Changelog
 
 02-10-2018: Initial draft
+
 16-01-2019: Second version based on our conversation with Jae
+
 17-01-2019: Third version explaining how new design solves current issues
 
+25-01-2019: Fourth version to treat buffered and unbuffered channels differently
+
 ## Context
 
 Since the initial version of the pubsub, there's been a number of issues
-raised: #951, #1879, #1880. Some of them are high-level issues questioning the
+raised: [#951], [#1879], [#1880]. Some of them are high-level issues questioning the
 core design choices made. Others are minor and mostly about the interface of
 `Subscribe()` / `Publish()` functions.
 
@@ -51,7 +55,10 @@ channels to distribute msg to these goroutines).
 
 ### Non-blocking send
 
-There is also a question whenever we should have a non-blocking send:
+There is also a question whenever we should have a non-blocking send.
+Currently, sends are blocking, so publishing to one client can block on
+publishing to another. This means a slow or unresponsive client can halt the
+system. Instead, we can use a non-blocking send:
 
 ```go
 for each subscriber {
@@ -87,11 +94,26 @@ Go channels are de-facto standard for carrying data between goroutines.
 ### Why `Subscribe()` accepts an `out` channel?
 
 Because in our tests, we create buffered channels (cap: 1). Alternatively, we
-can make capacity an argument.
+can make capacity an argument and return a channel.
 
 ## Decision
 
-Change Subscribe() function to return a `Subscription` struct:
+### MsgAndTags
+
+Use a `MsgAndTags` struct on the subscription channel to indicate what tags the
+msg matched.
+
+```go
+type MsgAndTags struct {
+    Msg interface{}
+    Tags TagMap
+}
+```
+
+### Subscription Struct
+
+
+Change `Subscribe()` function to return a `Subscription` struct:
 
 ```go
 type Subscription struct {
@@ -103,18 +125,18 @@ func (s *Subscription) Cancelled() <-chan struct{}
 func (s *Subscription) Err() error
 ```
 
-Out returns a channel onto which messages and tags are published.
-Unsubscribe/UnsubscribeAll does not close the channel to avoid clients from
+`Out()` returns a channel onto which messages and tags are published.
+`Unsubscribe`/`UnsubscribeAll` does not close the channel to avoid clients from
 receiving a nil message.
 
-Cancelled returns a channel that's closed when the subscription is terminated
+`Cancelled()` returns a channel that's closed when the subscription is terminated
 and supposed to be used in a select statement.
 
-If Cancelled is not closed yet, Err() returns nil.
-If Cancelled is closed, Err returns a non-nil error explaining why:
-Unsubscribed if the subscriber choose to unsubscribe,
-OutOfCapacity if the subscriber is not pulling messages fast enough and the Out channel become full.
-After Err returns a non-nil error, successive calls to Err() return the same error.
+If the channel returned by `Cancelled()` is not closed yet, `Err()` returns nil.
+If the channel is closed, `Err()` returns a non-nil error explaining why:
+`ErrUnsubscribed` if the subscriber choose to unsubscribe,
+`ErrOutOfCapacity` if the subscriber is not pulling messages fast enough and the channel returned by `Out()` became full.
+After `Err()` returns a non-nil error, successive calls to `Err() return the same error.
 
 ```go
 subscription, err := pubsub.Subscribe(...)
@@ -130,42 +152,68 @@ select {
 }
 ```
 
-Make Out() channel buffered (cap: 1) by default. In most cases, we want to
+### Capacity and Subscriptions
+
+Make the `Out()` channel buffered (with capacity 1) by default. In most cases, we want to
 terminate the slow subscriber. Only in rare cases, we want to block the pubsub
 (e.g. when debugging consensus). This should lower the chances of the pubsub
 being frozen.
 
 ```go
-// outCap can be used to set capacity of Out channel (1 by default). Set to 0
-for unbuffered channel (WARNING: it may block the pubsub).
+// outCap can be used to set capacity of Out channel
+// (1 by default, must be greater than 0).
 Subscribe(ctx context.Context, clientID string, query Query, outCap... int) (Subscription, error) {
 ```
 
-Also, Out() channel should return tags along with a message:
+Use a different function for an unbuffered channel:
 
 ```go
-type MsgAndTags struct {
-    Msg interface{}
-    Tags TagMap
-}
+// Subscription uses an unbuffered channel. Publishing will block.
+SubscribeUnbuffered(ctx context.Context, clientID string, query Query) (Subscription, error) {
 ```
 
-to inform clients of which Tags were used with Msg.
+SubscribeUnbuffered should not be exposed to users.
+
+### Blocking/Nonblocking
+
+The publisher should treat these kinds of channels separately.
+It should block on unbuffered channels (for use with internal consensus events
+in the consensus tests) and not block on the buffered ones. If a client is too
+slow to keep up with it's messages, it's subscription is terminated:
+
+for each subscription {
+    out := subscription.outChan
+    if cap(out) == 0 {
+        // block on unbuffered channel
+        out <- msg
+    } else {
+        // don't block on buffered channels
+        select {
+            case out <- msg:
+            default:
+                // set the error, notify on the cancel chan
+                subscription.err = fmt.Errorf("client is too slow for msg)
+                close(subscription.cancelChan)
+
+                // ... unsubscribe and close out
+        }
+    }
+}
 
 ### How this new design solves the current issues?
 
-https://github.com/tendermint/tendermint/issues/951 (https://github.com/tendermint/tendermint/issues/1880)
+[#951] ([#1880]):
 
 Because of non-blocking send, situation where we'll deadlock is not possible
 anymore. If the client stops reading messages, it will be removed.
 
-https://github.com/tendermint/tendermint/issues/1879
+[#1879]:
 
 MsgAndTags is used now instead of a plain message.
 
 ### Future problems and their possible solutions
 
-https://github.com/tendermint/tendermint/issues/2826
+[#2826]
 
 One question I am still pondering about: how to prevent pubsub from slowing
 down consensus. We can increase the pubsub queue size (which is 0 now). Also,
@@ -191,3 +239,9 @@ In review
 - (since v1) no concurrency when it comes to publishing messages
 
 ### Neutral
+
+
+[#951]: https://github.com/tendermint/tendermint/issues/951
+[#1879]: https://github.com/tendermint/tendermint/issues/1879
+[#1880]: https://github.com/tendermint/tendermint/issues/1880
+[#2826]: https://github.com/tendermint/tendermint/issues/2826

docs/spec/abci/apps.md

@@ -171,6 +171,10 @@ Note that the maximum total power of the validator set is bounded by
 they do not make changes to the validator set that cause it to exceed this
 limit.
 
+Additionally, applications must ensure that a single set of updates does not contain any duplicates -
+a given public key can only appear in an update once. If an update includes
+duplicates, the block execution will fail irrecoverably.
+
 ### InitChain
 
 ResponseInitChain can return a list of validators.

docs/spec/reactors/mempool/functionality.md

@@ -40,4 +40,4 @@ However, we only store valid txs in the cache, not invalid ones.
 This is because invalid txs could become good later.
 Txs that are included in a block aren't removed from the cache,
 as they still may be getting received over the p2p network.
-These txs are stored in the cache by their hash, to mitigate memory concerns.
+These txs are stored in the cache by their hash, to mitigate memory concerns.

docs/tendermint-core/configuration.md

@@ -183,10 +183,15 @@ recheck = true
 broadcast = true
 wal_dir = ""
 
-# size of the mempool
+# Maximum number of transactions in the mempool
 size = 5000
 
-# size of the cache (used to filter transactions we saw earlier)
+# Limit the total size of all txs in the mempool.
+# This only accounts for raw transactions (e.g. given 1MB transactions and
+# max_txs_bytes=5MB, mempool will only accept 5 transactions).
+max_txs_bytes = 1073741824
+
+# Size of the cache (used to filter transactions we saw earlier) in transactions
 cache_size = 10000
 
 ##### consensus configuration options #####
@@ -263,3 +268,74 @@ max_open_connections = 3
 # Instrumentation namespace
 namespace = "tendermint"
 ```
+
+## Empty blocks VS no empty blocks
+
+**create_empty_blocks = true**
+
+If `create_empty_blocks` is set to `true` in your config, blocks will be
+created ~ every second (with default consensus parameters). You can regulate
+the delay between blocks by changing the `timeout_commit`. E.g. `timeout_commit
+= "10s"` should result in ~ 10 second blocks.
+
+**create_empty_blocks = false**
+
+In this setting, blocks are created when transactions received.
+
+Note after the block H, Tendermint creates something we call a "proof block"
+(only if the application hash changed) H+1. The reason for this is to support
+proofs. If you have a transaction in block H that changes the state to X, the
+new application hash will only be included in block H+1. If after your
+transaction is committed, you want to get a lite-client proof for the new state
+(X), you need the new block to be committed in order to do that because the new
+block has the new application hash for the state X. That's why we make a new
+(empty) block if the application hash changes. Otherwise, you won't be able to
+make a proof for the new state.
+
+Plus, if you set `create_empty_blocks_interval` to something other than the
+default (`0`), Tendermint will be creating empty blocks even in the absence of
+transactions every `create_empty_blocks_interval`. For instance, with
+`create_empty_blocks = false` and `create_empty_blocks_interval = "30s"`,
+Tendermint will only create blocks if there are transactions, or after waiting
+30 seconds without receiving any transactions.
+
+## Consensus timeouts explained
+
+There's a variety of information about timeouts in [Running in
+production](./running-in-production.html)
+
+You can also find more detailed technical explanation in the spec: [The latest
+gossip on BFT consensus](https://arxiv.org/abs/1807.04938).
+
+```
+[consensus]
+...
+
+timeout_propose = "3s"
+timeout_propose_delta = "500ms"
+timeout_prevote = "1s"
+timeout_prevote_delta = "500ms"
+timeout_precommit = "1s"
+timeout_precommit_delta = "500ms"
+timeout_commit = "1s"
+```
+
+Note that in a successful round, the only timeout that we absolutely wait no
+matter what is `timeout_commit`.
+
+Here's a brief summary of the timeouts:
+
+- `timeout_propose` = how long we wait for a proposal block before prevoting
+  nil
+- `timeout_propose_delta` = how much timeout_propose increases with each round
+- `timeout_prevote` = how long we wait after receiving +2/3 prevotes for
+  anything (ie. not a single block or nil)
+- `timeout_prevote_delta` = how much the timeout_prevote increases with each
+  round
+- `timeout_precommit` = how long we wait after receiving +2/3 precommits for
+  anything (ie. not a single block or nil)
+- `timeout_precommit_delta` = how much the timeout_precommit increases with
+  each round
+- `timeout_commit` = how long we wait after committing a block, before starting
+  on the new height (this gives us a chance to receive some more precommits,
+  even though we already have +2/3)

docs/tendermint-core/mempool.md

@@ -0,0 +1,41 @@
+# Mempool
+
+## Transaction ordering
+
+Currently, there's no ordering of transactions other than the order they've
+arrived (via RPC or from other nodes).
+
+So the only way to specify the order is to send them to a single node.
+
+valA:
+  - tx1
+  - tx2
+  - tx3
+
+If the transactions are split up across different nodes, there's no way to
+ensure they are processed in the expected order.
+
+valA:
+  - tx1
+  - tx2
+
+valB:
+  - tx3
+
+If valB is the proposer, the order might be:
+
+  - tx3
+  - tx1
+  - tx2
+
+If valA is the proposer, the order might be:
+
+  - tx1
+  - tx2
+  - tx3
+
+That said, if the transactions contain some internal value, like an
+order/nonce/sequence number, the application can reject transactions that are
+out of order. So if a node receives tx3, then tx1, it can reject tx3 and then
+accept tx1. The sender can then retry sending tx3, which should probably be
+rejected until the node has seen tx2.

docs/tendermint-core/rpc.md

@@ -2,6 +2,6 @@
 
 The RPC documentation is hosted here:
 
-- https://tendermint.com/rpc/
+- [https://tendermint.com/rpc/](https://tendermint.com/rpc/)
 
 To update the documentation, edit the relevant `godoc` comments in the [rpc/core directory](https://github.com/tendermint/tendermint/tree/develop/rpc/core).

docs/tools/README.md

@@ -1,4 +1,7 @@
 # Overview
 
-Tendermint comes with some tools for [benchmarking](./benchmarking.md)
-and [monitoring](./monitoring.md).
+Tendermint comes with some tools for:
+
+* [Benchmarking](./benchmarking.md)
+* [Monitoring](./monitoring.md)
+* [Validation of remote signers](./remote-signer-validation.md)

docs/tools/benchmarking.md

@@ -2,7 +2,7 @@
 
 Tendermint blockchain benchmarking tool:
 
-- https://github.com/tendermint/tools/tree/master/tm-bench
+- [https://github.com/tendermint/tendermint/tree/master/tools/tm-bench](https://github.com/tendermint/tendermint/tree/master/tools/tm-bench)
 
 For example, the following:
 

docs/tools/monitoring.md

@@ -3,7 +3,7 @@
 Tendermint blockchain monitoring tool; watches over one or more nodes,
 collecting and providing various statistics to the user:
 
-- https://github.com/tendermint/tendermint/tree/master/tools/tm-monitor
+- [https://github.com/tendermint/tendermint/tree/master/tools/tm-monitor](https://github.com/tendermint/tendermint/tree/master/tools/tm-monitor)
 
 ## Quick Start
 

docs/tools/remote-signer-validation.md

@@ -0,0 +1,146 @@
+# tm-signer-harness
+
+Located under the `tools/tm-signer-harness` folder in the [Tendermint
+repository](https://github.com/tendermint/tendermint).
+
+The Tendermint remote signer test harness facilitates integration testing
+between Tendermint and remote signers such as
+[KMS](https://github.com/tendermint/kms). Such remote signers allow for signing
+of important Tendermint messages using
+[HSMs](https://en.wikipedia.org/wiki/Hardware_security_module), providing
+additional security.
+
+When executed, `tm-signer-harness`:
+
+1. Runs a listener (either TCP or Unix sockets).
+2. Waits for a connection from the remote signer.
+3. Upon connection from the remote signer, executes a number of automated tests
+   to ensure compatibility.
+4. Upon successful validation, the harness process exits with a 0 exit code.
+   Upon validation failure, it exits with a particular exit code related to the
+   error.
+
+## Prerequisites
+Requires the same prerequisites as for building
+[Tendermint](https://github.com/tendermint/tendermint).
+
+## Building
+From the `tools/tm-signer-harness` directory in your Tendermint source
+repository, simply run:
+
+```bash
+make
+
+# To have global access to this executable
+make install
+```
+
+## Docker Image
+To build a Docker image containing the `tm-signer-harness`, also from the
+`tools/tm-signer-harness` directory of your Tendermint source repo, simply run:
+
+```bash
+make docker-image
+```
+
+## Running against KMS
+As an example of how to use `tm-signer-harness`, the following instructions show
+you how to execute its tests against [KMS](https://github.com/tendermint/kms).
+For this example, we will make use of the **software signing module in KMS**, as
+the hardware signing module requires a physical
+[YubiHSM](https://www.yubico.com/products/yubihsm/) device.
+
+### Step 1: Install KMS on your local machine
+See the [KMS repo](https://github.com/tendermint/kms) for details on how to set
+KMS up on your local machine.
+
+If you have [Rust](https://www.rust-lang.org/) installed on your local machine,
+you can simply install KMS by:
+
+```bash
+cargo install tmkms
+```
+
+### Step 2: Make keys for KMS
+The KMS software signing module needs a key with which to sign messages. In our
+example, we will simply export a signing key from our local Tendermint instance.
+
+```bash
+# Will generate all necessary Tendermint configuration files, including:
+# - ~/.tendermint/config/priv_validator_key.json
+# - ~/.tendermint/data/priv_validator_state.json
+tendermint init
+
+# Extract the signing key from our local Tendermint instance
+tm-signer-harness extract_key \      # Use the "extract_key" command
+    -tmhome ~/.tendermint \          # Where to find the Tendermint home directory
+    -output ./signing.key            # Where to write the key
+```
+
+Also, because we want KMS to connect to `tm-signer-harness`, we will need to
+provide a secret connection key from KMS' side:
+
+```bash
+tmkms keygen secret_connection.key
+```
+
+### Step 3: Configure and run KMS
+KMS needs some configuration to tell it to use the softer signing module as well
+as the `signing.key` file we just generated. Save the following to a file called
+`tmkms.toml`:
+
+```toml
+[[validator]]
+addr = "tcp://127.0.0.1:61219"         # This is where we will find tm-signer-harness.
+chain_id = "test-chain-0XwP5E"         # The Tendermint chain ID for which KMS will be signing (found in ~/.tendermint/config/genesis.json).
+reconnect = true                       # true is the default
+secret_key = "./secret_connection.key" # Where to find our secret connection key.
+
+[[providers.softsign]]
+id = "test-chain-0XwP5E"               # The Tendermint chain ID for which KMS will be signing (same as validator.chain_id above).
+path = "./signing.key"                 # The signing key we extracted earlier.
+```
+
+Then run KMS with this configuration:
+
+```bash
+tmkms start -c tmkms.toml
+```
+
+This will start KMS, which will repeatedly try to connect to
+`tcp://127.0.0.1:61219` until it is successful.
+
+### Step 4: Run tm-signer-harness
+Now we get to run the signer test harness:
+
+```bash
+tm-signer-harness run \             # The "run" command executes the tests
+    -addr tcp://127.0.0.1:61219 \   # The address we promised KMS earlier
+    -tmhome ~/.tendermint           # Where to find our Tendermint configuration/data files.
+```
+
+If the current version of Tendermint and KMS are compatible, `tm-signer-harness`
+should now exit with a 0 exit code. If they are somehow not compatible, it
+should exit with a meaningful non-zero exit code (see the exit codes below).
+
+### Step 5: Shut down KMS
+Simply hit Ctrl+Break on your KMS instance (or use the `kill` command in Linux)
+to terminate it gracefully.
+
+## Exit Code Meanings
+The following list shows the various exit codes from `tm-signer-harness` and
+their meanings:
+
+| Exit Code | Description |
+| --- | --- |
+| 0 | Success! |
+| 1 | Invalid command line parameters supplied to `tm-signer-harness` |
+| 2 | Maximum number of accept retries reached (the `-accept-retries` parameter) |
+| 3 | Failed to load `${TMHOME}/config/genesis.json` |
+| 4 | Failed to create listener specified by `-addr` parameter |
+| 5 | Failed to start listener |
+| 6 | Interrupted by `SIGINT` (e.g. when hitting Ctrl+Break or Ctrl+C) |
+| 7 | Other unknown error |
+| 8 | Test 1 failed: public key mismatch |
+| 9 | Test 2 failed: signing of proposals failed |
+| 10 | Test 3 failed: signing of votes failed |

evidence/pool.go

@@ -28,7 +28,8 @@ type EvidencePool struct {
 	state sm.State
 }
 
-func NewEvidencePool(stateDB dbm.DB, evidenceStore *EvidenceStore) *EvidencePool {
+func NewEvidencePool(stateDB, evidenceDB dbm.DB) *EvidencePool {
+	evidenceStore := NewEvidenceStore(evidenceDB)
 	evpool := &EvidencePool{
 		stateDB:       stateDB,
 		state:         sm.LoadState(stateDB),
@@ -132,6 +133,12 @@ func (evpool *EvidencePool) MarkEvidenceAsCommitted(height int64, evidence []typ
 
 }
 
+// IsCommitted returns true if we have already seen this exact evidence and it is already marked as committed.
+func (evpool *EvidencePool) IsCommitted(evidence types.Evidence) bool {
+	ei := evpool.evidenceStore.getEvidenceInfo(evidence)
+	return ei.Evidence != nil && ei.Committed
+}
+
 func (evpool *EvidencePool) removeEvidence(height, maxAge int64, blockEvidenceMap map[string]struct{}) {
 	for e := evpool.evidenceList.Front(); e != nil; e = e.Next() {
 		ev := e.Value.(types.Evidence)

evidence/pool_test.go

@@ -13,8 +13,6 @@ import (
 	tmtime "github.com/tendermint/tendermint/types/time"
 )
 
-var mockState = sm.State{}
-
 func TestMain(m *testing.M) {
 	types.RegisterMockEvidences(cdc)
 
@@ -58,8 +56,8 @@ func TestEvidencePool(t *testing.T) {
 	valAddr := []byte("val1")
 	height := int64(5)
 	stateDB := initializeValidatorState(valAddr, height)
-	store := NewEvidenceStore(dbm.NewMemDB())
-	pool := NewEvidencePool(stateDB, store)
+	evidenceDB := dbm.NewMemDB()
+	pool := NewEvidencePool(stateDB, evidenceDB)
 
 	goodEvidence := types.NewMockGoodEvidence(height, 0, valAddr)
 	badEvidence := types.MockBadEvidence{goodEvidence}
@@ -86,3 +84,24 @@ func TestEvidencePool(t *testing.T) {
 	assert.Nil(t, err)
 	assert.Equal(t, 1, pool.evidenceList.Len())
 }
+
+func TestEvidencePoolIsCommitted(t *testing.T) {
+	// Initialization:
+	valAddr := []byte("validator_address")
+	height := int64(42)
+	stateDB := initializeValidatorState(valAddr, height)
+	evidenceDB := dbm.NewMemDB()
+	pool := NewEvidencePool(stateDB, evidenceDB)
+
+	// evidence not seen yet:
+	evidence := types.NewMockGoodEvidence(height, 0, valAddr)
+	assert.False(t, pool.IsCommitted(evidence))
+
+	// evidence seen but not yet committed:
+	assert.NoError(t, pool.AddEvidence(evidence))
+	assert.False(t, pool.IsCommitted(evidence))
+
+	// evidence seen and committed:
+	pool.MarkEvidenceAsCommitted(height, []types.Evidence{evidence})
+	assert.True(t, pool.IsCommitted(evidence))
+}

evidence/reactor.go

@@ -48,7 +48,7 @@ func (evR *EvidenceReactor) SetLogger(l log.Logger) {
 // It returns the list of channels for this reactor.
 func (evR *EvidenceReactor) GetChannels() []*p2p.ChannelDescriptor {
 	return []*p2p.ChannelDescriptor{
-		&p2p.ChannelDescriptor{
+		{
 			ID:       EvidenceChannel,
 			Priority: 5,
 		},

evidence/reactor_test.go

@@ -37,8 +37,8 @@ func makeAndConnectEvidenceReactors(config *cfg.Config, stateDBs []dbm.DB) []*Ev
 	logger := evidenceLogger()
 	for i := 0; i < N; i++ {
 
-		store := NewEvidenceStore(dbm.NewMemDB())
-		pool := NewEvidencePool(stateDBs[i], store)
+		evidenceDB := dbm.NewMemDB()
+		pool := NewEvidencePool(stateDBs[i], evidenceDB)
 		reactors[i] = NewEvidenceReactor(pool)
 		reactors[i].SetLogger(logger.With("validator", i))
 	}

evidence/store.go

@@ -117,32 +117,33 @@ func (store *EvidenceStore) listEvidence(prefixKey string, maxNum int64) (eviden
 	return evidence
 }
 
-// GetEvidence fetches the evidence with the given height and hash.
-func (store *EvidenceStore) GetEvidence(height int64, hash []byte) *EvidenceInfo {
+// GetEvidenceInfo fetches the EvidenceInfo with the given height and hash.
+// If not found, ei.Evidence is nil.
+func (store *EvidenceStore) GetEvidenceInfo(height int64, hash []byte) EvidenceInfo {
 	key := keyLookupFromHeightAndHash(height, hash)
 	val := store.db.Get(key)
 
 	if len(val) == 0 {
-		return nil
+		return EvidenceInfo{}
 	}
 	var ei EvidenceInfo
 	err := cdc.UnmarshalBinaryBare(val, &ei)
 	if err != nil {
 		panic(err)
 	}
-	return &ei
+	return ei
 }
 
 // AddNewEvidence adds the given evidence to the database.
 // It returns false if the evidence is already stored.
 func (store *EvidenceStore) AddNewEvidence(evidence types.Evidence, priority int64) bool {
 	// check if we already have seen it
-	ei_ := store.GetEvidence(evidence.Height(), evidence.Hash())
-	if ei_ != nil && ei_.Evidence != nil {
+	ei := store.getEvidenceInfo(evidence)
+	if ei.Evidence != nil {
 		return false
 	}
 
-	ei := EvidenceInfo{
+	ei = EvidenceInfo{
 		Committed: false,
 		Priority:  priority,
 		Evidence:  evidence,
@@ -165,6 +166,11 @@ func (store *EvidenceStore) AddNewEvidence(evidence types.Evidence, priority int
 // MarkEvidenceAsBroadcasted removes evidence from Outqueue.
 func (store *EvidenceStore) MarkEvidenceAsBroadcasted(evidence types.Evidence) {
 	ei := store.getEvidenceInfo(evidence)
+	if ei.Evidence == nil {
+		// nothing to do; we did not store the evidence yet (AddNewEvidence):
+		return
+	}
+	// remove from the outqueue
 	key := keyOutqueue(evidence, ei.Priority)
 	store.db.Delete(key)
 }
@@ -177,8 +183,12 @@ func (store *EvidenceStore) MarkEvidenceAsCommitted(evidence types.Evidence) {
 	pendingKey := keyPending(evidence)
 	store.db.Delete(pendingKey)
 
-	ei := store.getEvidenceInfo(evidence)
-	ei.Committed = true
+	// committed EvidenceInfo doens't need priority
+	ei := EvidenceInfo{
+		Committed: true,
+		Evidence:  evidence,
+		Priority:  0,
+	}
 
 	lookupKey := keyLookup(evidence)
 	store.db.SetSync(lookupKey, cdc.MustMarshalBinaryBare(ei))
@@ -187,13 +197,7 @@ func (store *EvidenceStore) MarkEvidenceAsCommitted(evidence types.Evidence) {
 //---------------------------------------------------
 // utils
 
+// getEvidenceInfo is convenience for calling GetEvidenceInfo if we have the full evidence.
 func (store *EvidenceStore) getEvidenceInfo(evidence types.Evidence) EvidenceInfo {
-	key := keyLookup(evidence)
-	var ei EvidenceInfo
-	b := store.db.Get(key)
-	err := cdc.UnmarshalBinaryBare(b, &ei)
-	if err != nil {
-		panic(err)
-	}
-	return ei
+	return store.GetEvidenceInfo(evidence.Height(), evidence.Hash())
 }

evidence/store_test.go

@@ -27,6 +27,21 @@ func TestStoreAddDuplicate(t *testing.T) {
 	assert.False(added)
 }
 
+func TestStoreCommitDuplicate(t *testing.T) {
+	assert := assert.New(t)
+
+	db := dbm.NewMemDB()
+	store := NewEvidenceStore(db)
+
+	priority := int64(10)
+	ev := types.NewMockGoodEvidence(2, 1, []byte("val1"))
+
+	store.MarkEvidenceAsCommitted(ev)
+
+	added := store.AddNewEvidence(ev, priority)
+	assert.False(added)
+}
+
 func TestStoreMark(t *testing.T) {
 	assert := assert.New(t)
 
@@ -46,7 +61,7 @@ func TestStoreMark(t *testing.T) {
 	assert.True(added)
 
 	// get the evidence. verify. should be uncommitted
-	ei := store.GetEvidence(ev.Height(), ev.Hash())
+	ei := store.GetEvidenceInfo(ev.Height(), ev.Hash())
 	assert.Equal(ev, ei.Evidence)
 	assert.Equal(priority, ei.Priority)
 	assert.False(ei.Committed)
@@ -72,9 +87,10 @@ func TestStoreMark(t *testing.T) {
 	assert.Equal(0, len(pendingEv))
 
 	// evidence should show committed
-	ei = store.GetEvidence(ev.Height(), ev.Hash())
+	newPriority := int64(0)
+	ei = store.GetEvidenceInfo(ev.Height(), ev.Hash())
 	assert.Equal(ev, ei.Evidence)
-	assert.Equal(priority, ei.Priority)
+	assert.Equal(newPriority, ei.Priority)
 	assert.True(ei.Committed)
 }
 

evidence/wire.go

@@ -1,7 +1,7 @@
 package evidence
 
 import (
-	"github.com/tendermint/go-amino"
+	amino "github.com/tendermint/go-amino"
 	cryptoAmino "github.com/tendermint/tendermint/crypto/encoding/amino"
 	"github.com/tendermint/tendermint/types"
 )

libs/autofile/cmd/logjack.go

@@ -29,7 +29,21 @@ func parseFlags() (headPath string, chopSize int64, limitSize int64, version boo
 	return
 }
 
+type fmtLogger struct{}
+
+func (fmtLogger) Info(msg string, keyvals ...interface{}) {
+	strs := make([]string, len(keyvals))
+	for i, kv := range keyvals {
+		strs[i] = fmt.Sprintf("%v", kv)
+	}
+	fmt.Printf("%s %s\n", msg, strings.Join(strs, ","))
+}
+
 func main() {
+	// Stop upon receiving SIGTERM or CTRL-C.
+	cmn.TrapSignal(fmtLogger{}, func() {
+		fmt.Println("logjack shutting down")
+	})
 
 	// Read options
 	headPath, chopSize, limitSize, version := parseFlags()
@@ -51,29 +65,22 @@ func main() {
 		os.Exit(1)
 	}
 
-	go func() {
-		// Forever, read from stdin and write to AutoFile.
-		buf := make([]byte, readBufferSize)
-		for {
-			n, err := os.Stdin.Read(buf)
-			group.Write(buf[:n])
-			group.Flush()
-			if err != nil {
-				group.Stop()
-				if err == io.EOF {
-					os.Exit(0)
-				} else {
-					fmt.Println("logjack errored")
-					os.Exit(1)
-				}
+	// Forever read from stdin and write to AutoFile.
+	buf := make([]byte, readBufferSize)
+	for {
+		n, err := os.Stdin.Read(buf)
+		group.Write(buf[:n])
+		group.FlushAndSync()
+		if err != nil {
+			group.Stop()
+			if err == io.EOF {
+				os.Exit(0)
+			} else {
+				fmt.Println("logjack errored")
+				os.Exit(1)
 			}
 		}
-	}()
-
-	// Trap signal
-	cmn.TrapSignal(func() {
-		fmt.Println("logjack shutting down")
-	})
+	}
 }
 
 func parseBytesize(chopSize string) int64 {

libs/autofile/group.go

@@ -67,6 +67,11 @@ type Group struct {
 	minIndex           int // Includes head
 	maxIndex           int // Includes head, where Head will move to
 
+	// close this when the processTicks routine is done.
+	// this ensures we can cleanup the dir after calling Stop
+	// and the routine won't be trying to access it anymore
+	doneProcessTicks chan struct{}
+
 	// TODO: When we start deleting files, we need to start tracking GroupReaders
 	// and their dependencies.
 }
@@ -90,6 +95,7 @@ func OpenGroup(headPath string, groupOptions ...func(*Group)) (g *Group, err err
 		groupCheckDuration: defaultGroupCheckDuration,
 		minIndex:           0,
 		maxIndex:           0,
+		doneProcessTicks:   make(chan struct{}),
 	}
 
 	for _, option := range groupOptions {
@@ -125,24 +131,31 @@ func GroupTotalSizeLimit(limit int64) func(*Group) {
 	}
 }
 
-// OnStart implements Service by starting the goroutine that checks file and
-// group limits.
+// OnStart implements cmn.Service by starting the goroutine that checks file
+// and group limits.
 func (g *Group) OnStart() error {
 	g.ticker = time.NewTicker(g.groupCheckDuration)
 	go g.processTicks()
 	return nil
 }
 
-// OnStop implements Service by stopping the goroutine described above.
+// OnStop implements cmn.Service by stopping the goroutine described above.
 // NOTE: g.Head must be closed separately using Close.
 func (g *Group) OnStop() {
 	g.ticker.Stop()
-	g.Flush() // flush any uncommitted data
+	g.FlushAndSync()
+}
+
+// Wait blocks until all internal goroutines are finished. Supposed to be
+// called after Stop.
+func (g *Group) Wait() {
+	// wait for processTicks routine to finish
+	<-g.doneProcessTicks
 }
 
 // Close closes the head file. The group must be stopped by this moment.
 func (g *Group) Close() {
-	g.Flush() // flush any uncommitted data
+	g.FlushAndSync()
 
 	g.mtx.Lock()
 	_ = g.Head.closeFile()
@@ -198,9 +211,16 @@ func (g *Group) WriteLine(line string) error {
 	return err
 }
 
-// Flush writes any buffered data to the underlying file and commits the
-// current content of the file to stable storage.
-func (g *Group) Flush() error {
+// Buffered returns the size of the currently buffered data.
+func (g *Group) Buffered() int {
+	g.mtx.Lock()
+	defer g.mtx.Unlock()
+	return g.headBuf.Buffered()
+}
+
+// FlushAndSync writes any buffered data to the underlying file and commits the
+// current content of the file to stable storage (fsync).
+func (g *Group) FlushAndSync() error {
 	g.mtx.Lock()
 	defer g.mtx.Unlock()
 	err := g.headBuf.Flush()
@@ -211,6 +231,7 @@ func (g *Group) Flush() error {
 }
 
 func (g *Group) processTicks() {
+	defer close(g.doneProcessTicks)
 	for {
 		select {
 		case <-g.ticker.C:

libs/autofile/group_test.go

@@ -55,7 +55,7 @@ func TestCheckHeadSizeLimit(t *testing.T) {
 		err := g.WriteLine(cmn.RandStr(999))
 		require.NoError(t, err, "Error appending to head")
 	}
-	g.Flush()
+	g.FlushAndSync()
 	assertGroupInfo(t, g.ReadGroupInfo(), 0, 0, 999000, 999000)
 
 	// Even calling checkHeadSizeLimit manually won't rotate it.
@@ -65,7 +65,7 @@ func TestCheckHeadSizeLimit(t *testing.T) {
 	// Write 1000 more bytes.
 	err := g.WriteLine(cmn.RandStr(999))
 	require.NoError(t, err, "Error appending to head")
-	g.Flush()
+	g.FlushAndSync()
 
 	// Calling checkHeadSizeLimit this time rolls it.
 	g.checkHeadSizeLimit()
@@ -74,7 +74,7 @@ func TestCheckHeadSizeLimit(t *testing.T) {
 	// Write 1000 more bytes.
 	err = g.WriteLine(cmn.RandStr(999))
 	require.NoError(t, err, "Error appending to head")
-	g.Flush()
+	g.FlushAndSync()
 
 	// Calling checkHeadSizeLimit does nothing.
 	g.checkHeadSizeLimit()
@@ -85,7 +85,7 @@ func TestCheckHeadSizeLimit(t *testing.T) {
 		err = g.WriteLine(cmn.RandStr(999))
 		require.NoError(t, err, "Error appending to head")
 	}
-	g.Flush()
+	g.FlushAndSync()
 	assertGroupInfo(t, g.ReadGroupInfo(), 0, 1, 2000000, 1000000)
 
 	// Calling checkHeadSizeLimit rolls it again.
@@ -95,7 +95,7 @@ func TestCheckHeadSizeLimit(t *testing.T) {
 	// Write 1000 more bytes.
 	_, err = g.Head.Write([]byte(cmn.RandStr(999) + "\n"))
 	require.NoError(t, err, "Error appending to head")
-	g.Flush()
+	g.FlushAndSync()
 	assertGroupInfo(t, g.ReadGroupInfo(), 0, 2, 2001000, 1000)
 
 	// Calling checkHeadSizeLimit does nothing.
@@ -212,12 +212,12 @@ func TestRotateFile(t *testing.T) {
 	g.WriteLine("Line 1")
 	g.WriteLine("Line 2")
 	g.WriteLine("Line 3")
-	g.Flush()
+	g.FlushAndSync()
 	g.RotateFile()
 	g.WriteLine("Line 4")
 	g.WriteLine("Line 5")
 	g.WriteLine("Line 6")
-	g.Flush()
+	g.FlushAndSync()
 
 	// Read g.Head.Path+"000"
 	body1, err := ioutil.ReadFile(g.Head.Path + ".000")
@@ -244,13 +244,13 @@ func TestFindLast1(t *testing.T) {
 	g.WriteLine("Line 2")
 	g.WriteLine("# a")
 	g.WriteLine("Line 3")
-	g.Flush()
+	g.FlushAndSync()
 	g.RotateFile()
 	g.WriteLine("Line 4")
 	g.WriteLine("Line 5")
 	g.WriteLine("Line 6")
 	g.WriteLine("# b")
-	g.Flush()
+	g.FlushAndSync()
 
 	match, found, err := g.FindLast("#")
 	assert.NoError(t, err)
@@ -267,14 +267,14 @@ func TestFindLast2(t *testing.T) {
 	g.WriteLine("Line 1")
 	g.WriteLine("Line 2")
 	g.WriteLine("Line 3")
-	g.Flush()
+	g.FlushAndSync()
 	g.RotateFile()
 	g.WriteLine("# a")
 	g.WriteLine("Line 4")
 	g.WriteLine("Line 5")
 	g.WriteLine("# b")
 	g.WriteLine("Line 6")
-	g.Flush()
+	g.FlushAndSync()
 
 	match, found, err := g.FindLast("#")
 	assert.NoError(t, err)
@@ -293,12 +293,12 @@ func TestFindLast3(t *testing.T) {
 	g.WriteLine("Line 2")
 	g.WriteLine("# b")
 	g.WriteLine("Line 3")
-	g.Flush()
+	g.FlushAndSync()
 	g.RotateFile()
 	g.WriteLine("Line 4")
 	g.WriteLine("Line 5")
 	g.WriteLine("Line 6")
-	g.Flush()
+	g.FlushAndSync()
 
 	match, found, err := g.FindLast("#")
 	assert.NoError(t, err)
@@ -315,12 +315,12 @@ func TestFindLast4(t *testing.T) {
 	g.WriteLine("Line 1")
 	g.WriteLine("Line 2")
 	g.WriteLine("Line 3")
-	g.Flush()
+	g.FlushAndSync()
 	g.RotateFile()
 	g.WriteLine("Line 4")
 	g.WriteLine("Line 5")
 	g.WriteLine("Line 6")
-	g.Flush()
+	g.FlushAndSync()
 
 	match, found, err := g.FindLast("#")
 	assert.NoError(t, err)
@@ -336,7 +336,7 @@ func TestWrite(t *testing.T) {
 
 	written := []byte("Medusa")
 	g.Write(written)
-	g.Flush()
+	g.FlushAndSync()
 
 	read := make([]byte, len(written))
 	gr, err := g.NewReader(0)
@@ -357,11 +357,11 @@ func TestGroupReaderRead(t *testing.T) {
 
 	professor := []byte("Professor Monster")
 	g.Write(professor)
-	g.Flush()
+	g.FlushAndSync()
 	g.RotateFile()
 	frankenstein := []byte("Frankenstein's Monster")
 	g.Write(frankenstein)
-	g.Flush()
+	g.FlushAndSync()
 
 	totalWrittenLength := len(professor) + len(frankenstein)
 	read := make([]byte, totalWrittenLength)
@@ -386,12 +386,12 @@ func TestGroupReaderRead2(t *testing.T) {
 
 	professor := []byte("Professor Monster")
 	g.Write(professor)
-	g.Flush()
+	g.FlushAndSync()
 	g.RotateFile()
 	frankenstein := []byte("Frankenstein's Monster")
 	frankensteinPart := []byte("Frankenstein")
 	g.Write(frankensteinPart) // note writing only a part
-	g.Flush()
+	g.FlushAndSync()
 
 	totalLength := len(professor) + len(frankenstein)
 	read := make([]byte, totalLength)
@@ -427,7 +427,7 @@ func TestMaxIndex(t *testing.T) {
 	assert.Zero(t, g.MaxIndex(), "MaxIndex should be zero at the beginning")
 
 	g.WriteLine("Line 1")
-	g.Flush()
+	g.FlushAndSync()
 	g.RotateFile()
 
 	assert.Equal(t, 1, g.MaxIndex(), "MaxIndex should point to the last file")

libs/clist/clist_test.go

@@ -65,12 +65,13 @@ func TestSmall(t *testing.T) {
 
 }
 
-/*
-This test is quite hacky because it relies on SetFinalizer
-which isn't guaranteed to run at all.
-*/
-// nolint: megacheck
+// This test is quite hacky because it relies on SetFinalizer
+// which isn't guaranteed to run at all.
+//nolint:unused,deadcode
 func _TestGCFifo(t *testing.T) {
+	if runtime.GOARCH != "amd64" {
+		t.Skipf("Skipping on non-amd64 machine")
+	}
 
 	const numElements = 1000000
 	l := New()
@@ -113,12 +114,13 @@ func _TestGCFifo(t *testing.T) {
 	}
 }
 
-/*
-This test is quite hacky because it relies on SetFinalizer
-which isn't guaranteed to run at all.
-*/
-// nolint: megacheck
+// This test is quite hacky because it relies on SetFinalizer
+// which isn't guaranteed to run at all.
+//nolint:unused,deadcode
 func _TestGCRandom(t *testing.T) {
+	if runtime.GOARCH != "amd64" {
+		t.Skipf("Skipping on non-amd64 machine")
+	}
 
 	const numElements = 1000000
 	l := New()

libs/common/bit_array.go

@@ -412,6 +412,6 @@ func (bA *BitArray) UnmarshalJSON(bz []byte) error {
 			bA2.SetIndex(i, true)
 		}
 	}
-	*bA = *bA2
+	*bA = *bA2 //nolint:govet
 	return nil
 }

libs/common/colors.go

@@ -43,7 +43,7 @@ func treat(s string, color string) string {
 }
 
 func treatAll(color string, args ...interface{}) string {
-	var parts []string
+	parts := make([]string, 0, len(args))
 	for _, arg := range args {
 		parts = append(parts, treat(fmt.Sprintf("%v", arg), color))
 	}

libs/common/net.go

@@ -24,3 +24,20 @@ func ProtocolAndAddress(listenAddr string) (string, string) {
 	}
 	return protocol, address
 }
+
+// GetFreePort gets a free port from the operating system.
+// Ripped from https://github.com/phayes/freeport.
+// BSD-licensed.
+func GetFreePort() (int, error) {
+	addr, err := net.ResolveTCPAddr("tcp", "localhost:0")
+	if err != nil {
+		return 0, err
+	}
+
+	l, err := net.ListenTCP("tcp", addr)
+	if err != nil {
+		return 0, err
+	}
+	defer l.Close()
+	return l.Addr().(*net.TCPAddr).Port, nil
+}

libs/common/os.go

@@ -34,21 +34,24 @@ func GoPath() string {
 	return path
 }
 
-// TrapSignal catches the SIGTERM and executes cb function. After that it exits
-// with code 1.
-func TrapSignal(cb func()) {
+type logger interface {
+	Info(msg string, keyvals ...interface{})
+}
+
+// TrapSignal catches the SIGTERM/SIGINT and executes cb function. After that it exits
+// with code 0.
+func TrapSignal(logger logger, cb func()) {
 	c := make(chan os.Signal, 1)
 	signal.Notify(c, os.Interrupt, syscall.SIGTERM)
 	go func() {
 		for sig := range c {
-			fmt.Printf("captured %v, exiting...\n", sig)
+			logger.Info(fmt.Sprintf("captured %v, exiting...", sig))
 			if cb != nil {
 				cb()
 			}
-			os.Exit(1)
+			os.Exit(0)
 		}
 	}()
-	select {}
 }
 
 // Kill the running process by sending itself SIGTERM.

libs/common/os_test.go

@@ -5,7 +5,7 @@ import (
 	"testing"
 )
 
-func TestGoPath(t *testing.T) {
+func TestOSGoPath(t *testing.T) {
 	// restore original gopath upon exit
 	path := os.Getenv("GOPATH")
 	defer func() {
@@ -28,7 +28,7 @@ func TestGoPath(t *testing.T) {
 	}
 }
 
-func TestGoPathWithoutEnvVar(t *testing.T) {
+func TestOSGoPathWithoutEnvVar(t *testing.T) {
 	// restore original gopath upon exit
 	path := os.Getenv("GOPATH")
 	defer func() {

libs/db/remotedb/doc.go

@@ -11,7 +11,7 @@ remotedb's RemoteDB implements db.DB so can be used normally
 like other databases. One just has to explicitly connect to the
 remote database with a client setup such as:
 
-	client, err := remotedb.NewInsecure(addr)
+	client, err := remotedb.NewRemoteDB(addr, cert)
 	// Make sure to invoke InitRemote!
 	if err := client.InitRemote(&remotedb.Init{Name: "test-remote-db", Type: "leveldb"}); err != nil {
 	    log.Fatalf("Failed to initialize the remote db")

libs/db/remotedb/grpcdb/client.go

@@ -7,14 +7,6 @@ import (
 	protodb "github.com/tendermint/tendermint/libs/db/remotedb/proto"
 )
 
-// Security defines how the client will talk to the gRPC server.
-type Security uint
-
-const (
-	Insecure Security = iota
-	Secure
-)
-
 // NewClient creates a gRPC client connected to the bound gRPC server at serverAddr.
 // Use kind to set the level of security to either Secure or Insecure.
 func NewClient(serverAddr, serverCert string) (protodb.DBClient, error) {

libs/db/remotedb/remotedb_test.go

@@ -14,7 +14,7 @@ import (
 func TestRemoteDB(t *testing.T) {
 	cert := "test.crt"
 	key := "test.key"
-	ln, err := net.Listen("tcp", "0.0.0.0:0")
+	ln, err := net.Listen("tcp", "localhost:0")
 	require.Nil(t, err, "expecting a port to have been assigned on which we can listen")
 	srv, err := grpcdb.NewServer(cert, key)
 	require.Nil(t, err)

libs/db/remotedb/test.crt

@@ -1,25 +1,19 @@
 -----BEGIN CERTIFICATE-----
-MIIEQTCCAimgAwIBAgIRANqF1HD19i/uvQ3n62TAKTwwDQYJKoZIhvcNAQELBQAw
-GTEXMBUGA1UEAxMOdGVuZGVybWludC5jb20wHhcNMTgwNzAyMDMwNzMyWhcNMjAw
-MTAyMDMwNzMwWjANMQswCQYDVQQDEwI6OjCCASIwDQYJKoZIhvcNAQEBBQADggEP
-ADCCAQoCggEBAOuWUMCSzYJmvKU1vsouDTe7OxnPWO3oV0FjSH8vKYoi2zpZQX35
-dQDPtLDF2/v/ANZJ5pzMJR8yMMtEQ4tWxKuGzJw1ZgTgHtASPbj/M5fDnDO7Hqg4
-D09eLTkZAUfiBf6BzDyQIHn22CUexhaS70TbIT9AOAoOsGXMZz9d+iImKIm+gbzf
-pR52LNbBGesHWGjwIuGF4InstIMsKSwGv2DctzhWI+i/m5Goi3rd1V8z/lzUbsf1
-0uXqQcSfTyv3ee6YiCWj2W8vcdc5H+B6KzSlGjAR4sRcHTHOQJYO9BgA9evQ3qsJ
-Pp00iez13RdheJWPtbfUqQy4gdpu8HFeZx8CAwEAAaOBjzCBjDAOBgNVHQ8BAf8E
-BAMCA7gwHQYDVR0lBBYwFAYIKwYBBQUHAwEGCCsGAQUFBwMCMB0GA1UdDgQWBBRc
-XBo+bJILrLcJiGkTWeMPpXb1TDAfBgNVHSMEGDAWgBQqk1Xu65Ww7EBCROw4KLGw
-KuToaDAbBgNVHREEFDAShxAAAAAAAAAAAAAAAAAAAAAAMA0GCSqGSIb3DQEBCwUA
-A4ICAQAbGsIMhL8clczNmhGl9xZhmyNz6FbLq6g163x9LTgfvwHPt+7urthtd++O
-uy4Ut8zFurh/yk7eooPlzf8jO7QUJBAFVy4vj8IcsvpWbFa7cuEOIulbjIzyAm/v
-lgy7vUQ6xrWn8x8O9K1ww9z7wugwCyl22BD0wSHZKclJz++AwpL6vUVOD76IIuJO
-+S6bE6z26/0ndpundh2AkA++2eIleD6ygnTeTl0PWu6aGoCggBmos50f8KgYHZF/
-OZVef203kDls9xCaOiMzaU91VsgLqq/gNcT+2cBd5r3IZTY3C8Rve6EEHS+/4zxf
-PKlmiLN7lU9GFZogKecYzY+zPT7OArY7OVFnGTo4qdhdmxnXzHsI+anMCjxLOgEJ
-381hyplQGPQOouEupCBxFcwa7oMYoGu20+1nLWYEqFcIXCeyH+s77MyteJSsseqL
-xivG5PT+jKJn9hrnFb39bBmht9Vsa+Th6vk953zi5wCSe1j2wXsxFaENDq6BQZOK
-f86Kp86M2elYnv3lJ3j2DE2ZTMpw+PA5ThYUnB+HVqYeeB2Y3ErRS8P1FOp1LBE8
-+eTz7yXQO5OM2wdYhNNL1zDri/41fHXi9b6337PZVqc39GM+N74x/O4Q7xEBiWgQ
-T0dT8SNwf55kv63MeZh63ImxFV0FNRkCteYLcJMle3ohIY4zyQ==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 -----END CERTIFICATE-----

libs/db/remotedb/test.key

@@ -1,27 +1,27 @@
 -----BEGIN RSA PRIVATE KEY-----
-MIIEpgIBAAKCAQEA65ZQwJLNgma8pTW+yi4NN7s7Gc9Y7ehXQWNIfy8piiLbOllB
-ffl1AM+0sMXb+/8A1knmnMwlHzIwy0RDi1bEq4bMnDVmBOAe0BI9uP8zl8OcM7se
-qDgPT14tORkBR+IF/oHMPJAgefbYJR7GFpLvRNshP0A4Cg6wZcxnP136IiYoib6B
-vN+lHnYs1sEZ6wdYaPAi4YXgiey0gywpLAa/YNy3OFYj6L+bkaiLet3VXzP+XNRu
-x/XS5epBxJ9PK/d57piIJaPZby9x1zkf4HorNKUaMBHixFwdMc5Alg70GAD169De
-qwk+nTSJ7PXdF2F4lY+1t9SpDLiB2m7wcV5nHwIDAQABAoIBAQCB2/ilPgaUE8d2
-ldqWHa5hgw4/2uCdO04ll/GVUczm/PG1BxAnvYL2MIfcTSRGkrjGZjP9SDZKLONi
-mD1XKDv+hK5yiKi0lUnGzddCC0JILKYEieeLOGOQD0yERblEA13kfW20EIomUJ+y
-TnVIajQD03pPIDoDqTco1fQvpMDFYw5Q//UhH7VBC261GO1akvhT2Gqdb4aKLaYQ
-iDW9IEButL5cRKIJuRxToB/JbmPVEF7xIZtm0sf9dtYVOlBQLeID0uHXgaci0enc
-de6GMajmj7NFqc36ypb+Ct18fqEwQBYD+TSQdKs7/lMsAXwRjd5HW4RbYiMZyYnf
-Dxgh7QVBAoGBAP9aLLIUcIG7+gk1x7xd+8wRhfo+dhsungeCluSigI9AsfDr6dpR
-G9/0lEJH56noZZKQueACTmj7shmRB40xFFLc8w0IDRZCnofsl+Z15k9K84uFPA3W
-hdZH9nMieU/mRKdcUYK7pHGqbicHTaJQ5ydZ+xb2E+zYQHOzYpQacHv/AoGBAOwv
-TjDZSiassnAPYmmfcHtkUF4gf7PTpiZfH0hXHGAb0mJX4cXAoktAeDeHSi2tz3LW
-dAc0ReP8Pdf3uSNv7wkJ1KpNRxAhU5bhnDFmjRc7gMZknVOU+az2M+4yGOn/SOiJ
-I6uMHgQDS/VsI+N583n6gbGxVHbQfr9TOc4bLpThAoGBAKin0JmWMnEdzRnEMbZS
-hPrWIB2Wn794XNws/qjoQ+1aF60+xGhz5etXyYy1nWd1nZDekkZIf62LgKiuR8ST
-xA6u7MGQrcQkID06oWGQQZvhr1ZZm76wEBnl0ftdq66AMpwvt46XjReeL78LbdVl
-hidRoSwbQDHQ61EADH4xsFXVAoGBAISXqhXSZsZ/fU1b1avmTod3MYcmR4r07vnr
-vOwnu05ZUCrVm3IhSvtkHhlOYl5yjVuy+UByICp1mWJ9N/qlBFTWqAVTjOmJTBwQ
-XFd/cwXv6cN3CLu7js+DCHRYu5PiNVQWaWgNKWynTSViqGM0O3PnJphTLU/mjMFs
-P69toyEBAoGBALh9YsqxHdYdS5WK9chzDfGlaTQ79jwN+gEzQuP1ooLF0JkMgh5W
-//2C6kCrgBsGTm1gfHAjEfC04ZDZLFbKLm56YVKUGL6JJNapm6e5kfiZGjbRKWAg
-ViCeRS2qQnVbH74GfHyimeTPDI9cJMiJfDDTPbfosqWSsPEcg2jfsySJ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 -----END RSA PRIVATE KEY-----

libs/events/events.go

@@ -188,7 +188,7 @@ func (cell *eventCell) RemoveListener(listenerID string) int {
 
 func (cell *eventCell) FireEvent(data EventData) {
 	cell.mtx.RLock()
-	var eventCallbacks []EventCallback
+	eventCallbacks := make([]EventCallback, 0, len(cell.listeners))
 	for _, cb := range cell.listeners {
 		eventCallbacks = append(eventCallbacks, cb)
 	}

libs/fail/fail.go

@@ -72,7 +72,8 @@ func FailRand(n int) {
 
 func Exit() {
 	fmt.Printf("*** fail-test %d ***\n", callIndex)
-	proc, _ := os.FindProcess(os.Getpid())
-	proc.Signal(os.Interrupt)
+	os.Exit(1)
+	//	proc, _ := os.FindProcess(os.Getpid())
+	//	proc.Signal(os.Interrupt)
 	//	panic(fmt.Sprintf("*** fail-test %d ***", callIndex))
 }

libs/flowrate/io_test.go

@@ -81,12 +81,12 @@ func TestReader(t *testing.T) {
 
 	// Active, Start, Duration, Idle, Bytes, Samples, InstRate, CurRate, AvgRate, PeakRate, BytesRem, TimeRem, Progress
 	want := []Status{
-		Status{true, start, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
-		Status{true, start, _100ms, 0, 10, 1, 100, 100, 100, 100, 0, 0, 0},
-		Status{true, start, _200ms, _100ms, 20, 2, 100, 100, 100, 100, 0, 0, 0},
-		Status{true, start, _300ms, _200ms, 20, 3, 0, 90, 67, 100, 0, 0, 0},
-		Status{false, start, _300ms, 0, 20, 3, 0, 0, 67, 100, 0, 0, 0},
-		Status{false, start, _300ms, 0, 20, 3, 0, 0, 67, 100, 0, 0, 0},
+		{true, start, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0},
+		{true, start, _100ms, 0, 10, 1, 100, 100, 100, 100, 0, 0, 0},
+		{true, start, _200ms, _100ms, 20, 2, 100, 100, 100, 100, 0, 0, 0},
+		{true, start, _300ms, _200ms, 20, 3, 0, 90, 67, 100, 0, 0, 0},
+		{false, start, _300ms, 0, 20, 3, 0, 0, 67, 100, 0, 0, 0},
+		{false, start, _300ms, 0, 20, 3, 0, 0, 67, 100, 0, 0, 0},
 	}
 	for i, s := range status {
 		if !statusesAreEqual(&s, &want[i]) {
@@ -139,8 +139,8 @@ func TestWriter(t *testing.T) {
 
 	// Active, Start, Duration, Idle, Bytes, Samples, InstRate, CurRate, AvgRate, PeakRate, BytesRem, TimeRem, Progress
 	want := []Status{
-		Status{true, start, _400ms, 0, 80, 4, 200, 200, 200, 200, 20, _100ms, 80000},
-		Status{true, start, _500ms, _100ms, 100, 5, 200, 200, 200, 200, 0, 0, 100000},
+		{true, start, _400ms, 0, 80, 4, 200, 200, 200, 200, 20, _100ms, 80000},
+		{true, start, _500ms, _100ms, 100, 5, 200, 200, 200, 200, 0, 0, 100000},
 	}
 	for i, s := range status {
 		if !statusesAreEqual(&s, &want[i]) {

libs/pubsub/example_test.go

@@ -19,10 +19,9 @@ func TestExample(t *testing.T) {
 	defer s.Stop()
 
 	ctx := context.Background()
-	ch := make(chan interface{}, 1)
-	err := s.Subscribe(ctx, "example-client", query.MustParse("abci.account.name='John'"), ch)
+	subscription, err := s.Subscribe(ctx, "example-client", query.MustParse("abci.account.name='John'"))
 	require.NoError(t, err)
-	err = s.PublishWithTags(ctx, "Tombstone", pubsub.NewTagMap(map[string]string{"abci.account.name": "John"}))
+	err = s.PublishWithTags(ctx, "Tombstone", map[string]string{"abci.account.name": "John"})
 	require.NoError(t, err)
-	assertReceive(t, "Tombstone", ch)
+	assertReceive(t, "Tombstone", subscription.Out())
 }