create valset-change tool

.github/dependabot.yml

@@ -53,10 +53,10 @@ updates:
   - package-ecosystem: gomod
     directory: "/"
     schedule:
-      interval: daily
+      interval: weekly
     target-branch: "v0.37.x"
-    # Only allow automated security-related dependency updates on release
-    # branches.
+    # Only allow automated security-related dependency updates until we cut the
+    # final v0.37.0 release.
     open-pull-requests-limit: 0
     labels:
       - T:dependencies
@@ -65,11 +65,9 @@ updates:
   - package-ecosystem: gomod
     directory: "/"
     schedule:
-      interval: daily
+      interval: weekly
     target-branch: "v0.34.x"
-    # Only allow automated security-related dependency updates on release
-    # branches.
-    open-pull-requests-limit: 0
+    open-pull-requests-limit: 10
     labels:
       - T:dependencies
       - S:automerge

.github/workflows/docker.yml

@@ -41,17 +41,17 @@ jobs:
           platforms: all
 
       - name: Set up Docker Build
-        uses: docker/setup-buildx-action@v2.2.1
+        uses: docker/setup-buildx-action@v2.0.0
 
       - name: Login to DockerHub
         if: ${{ github.event_name != 'pull_request' }}
-        uses: docker/login-action@v2.1.0
+        uses: docker/login-action@v2.0.0
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Publish to Docker Hub
-        uses: docker/build-push-action@v3.2.0
+        uses: docker/build-push-action@v3.1.1
         with:
           context: .
           file: ./DOCKER/Dockerfile

.github/workflows/e2e-nightly-34x.yml

@@ -57,7 +57,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Notify Slack on failure
-        uses: slackapi/slack-github-action@v1.23.0
+        uses: slackapi/slack-github-action@v1.22.0
         env:
           SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
           SLACK_WEBHOOK_TYPE: INCOMING_WEBHOOK
@@ -72,7 +72,7 @@ jobs:
                   "type": "section",
                   "text": {
                     "type": "mrkdwn",
-                    "text": ":skull: Nightly E2E tests for `${{ env.BRANCH }}` failed. See the <${{ env.RUN_URL }}|run details> and the <${{ env.COMMIT_URL }}|commit> related to the failure."
+                    "text": ":skull: Nightly E2E tests for `${{ env.BRANCH }}` failed. See the <${{ env.RUN_URL }}|run details> and the <${{ env.COMMIT_URL }}|commit> that caused the failure."
                   }
                 }
               ]

.github/workflows/e2e-nightly-37x.yml

@@ -57,7 +57,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Notify Slack on failure
-        uses: slackapi/slack-github-action@v1.23.0
+        uses: slackapi/slack-github-action@v1.22.0
         env:
           SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
           SLACK_WEBHOOK_TYPE: INCOMING_WEBHOOK
@@ -72,7 +72,7 @@ jobs:
                   "type": "section",
                   "text": {
                     "type": "mrkdwn",
-                    "text": ":skull: Nightly E2E tests for `${{ env.BRANCH }}` failed. See the <${{ env.RUN_URL }}|run details> and the <${{ env.COMMIT_URL }}|commit> related to the failure."
+                    "text": ":skull: Nightly E2E tests for `${{ env.BRANCH }}` failed. See the <${{ env.RUN_URL }}|run details> and the <${{ env.COMMIT_URL }}|commit> that caused the failure."
                   }
                 }
               ]

.github/workflows/e2e-nightly-main.yml

@@ -46,7 +46,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Notify Slack on failure
-        uses: slackapi/slack-github-action@v1.23.0
+        uses: slackapi/slack-github-action@v1.22.0
         env:
           SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
           SLACK_WEBHOOK_TYPE: INCOMING_WEBHOOK
@@ -61,7 +61,7 @@ jobs:
                   "type": "section",
                   "text": {
                     "type": "mrkdwn",
-                    "text": ":skull: Nightly E2E tests for `${{ env.BRANCH }}` failed. See the <${{ env.RUN_URL }}|run details> and the <${{ env.COMMIT_URL }}|commit> related to the failure."
+                    "text": ":skull: Nightly E2E tests for `${{ env.BRANCH }}` failed. See the <${{ env.RUN_URL }}|run details> and the <${{ env.COMMIT_URL }}|commit> that caused the failure."
                   }
                 }
               ]

.github/workflows/fuzz-nightly.yml

@@ -76,7 +76,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Notify Slack on failure
-        uses: slackapi/slack-github-action@v1.23.0
+        uses: slackapi/slack-github-action@v1.22.0
         env:
           SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
           SLACK_WEBHOOK_TYPE: INCOMING_WEBHOOK

.github/workflows/gosec.yml

@@ -0,0 +1,41 @@
+name: Run Gosec
+on:
+  pull_request:
+    paths:
+      - '**/*.go'
+      - 'go.mod'
+      - 'go.sum'
+  push:
+    branches:
+      - main
+      - 'feature/*'
+      - 'v0.37.x'
+      - 'v0.34.x'
+    paths:
+      - '**/*.go'
+      - 'go.mod'
+      - 'go.sum'
+
+jobs:
+  Gosec:
+    permissions:
+      security-events: write
+
+    runs-on: ubuntu-latest
+    env:
+      GO111MODULE: on
+    steps:
+      - name: Checkout Source
+        uses: actions/checkout@v3
+
+      - name: Run Gosec Security Scanner
+        uses: cosmos/gosec@master
+        with:
+          # Let the report trigger a failure with the Github Security scanner features.
+          args: "-no-fail -fmt sarif -out results.sarif ./..."
+
+      - name: Upload SARIF file
+        uses: github/codeql-action/upload-sarif@v2
+        with:
+          # Path to SARIF file relative to the root of the repository
+          sarif_file: results.sarif

.github/workflows/janitor.yml

@@ -10,7 +10,7 @@ jobs:
     runs-on: ubuntu-latest
     timeout-minutes: 3
     steps:
-      - uses: styfle/cancel-workflow-action@0.11.0
+      - uses: styfle/cancel-workflow-action@0.10.1
         with:
           workflow_id: 1041851,1401230,2837803
           access_token: ${{ github.token }}

.github/workflows/lint.yml

@@ -31,7 +31,10 @@ jobs:
             go.sum
       - uses: golangci/golangci-lint-action@v3
         with:
-          version: v1.50.1
+          # Required: the version of golangci-lint is required and
+          # must be specified without patch version: we always use the
+          # latest patch version.
+          version: v1.47.3
           args: --timeout 10m
           github-token: ${{ secrets.github_token }}
         if: env.GIT_DIFF

.github/workflows/markdown-links.yml

@@ -1,20 +1,23 @@
 name: Check Markdown links
 
 on:
-  schedule:
-    # 2am UTC daily
-    - cron: '0 2 * * *'
+  push:
+    branches:
+      - main
+  pull_request:
+    branches: [main]
 
 jobs:
   markdown-link-check:
-    strategy:
-      matrix:
-        branch: ['main', 'v0.37.x', 'v0.34.x']
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
+      - uses: technote-space/get-diff-action@v6
         with:
-          ref: ${{ matrix.branch }}
-      - uses: informalsystems/github-action-markdown-link-check@main
+          PATTERNS: |
+            **/**.md
+      - uses: creachadair/github-action-markdown-link-check@master
         with:
+          check-modified-files-only: 'yes'
           config-file: '.md-link-check.json'
+        if: env.GIT_DIFF

.github/workflows/pre-release.yml

@@ -8,7 +8,7 @@ on:
       - "v[0-9]+.[0-9]+.[0-9]+-rc[0-9]+"      # e.g. v0.37.0-rc1, v0.38.0-rc10
 
 jobs:
-  prerelease:
+  goreleaser:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
@@ -38,28 +38,3 @@ jobs:
           args: release --rm-dist --release-notes=../release_notes.md
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-
-  prerelease-success:
-    needs: prerelease
-    if: ${{ success() }}
-    runs-on: ubuntu-latest
-    steps:
-      - name: Notify Slack upon pre-release
-        uses: slackapi/slack-github-action@v1.22.0
-        env:
-          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
-          SLACK_WEBHOOK_TYPE: INCOMING_WEBHOOK
-          RELEASE_URL: "${{ github.server_url }}/${{ github.repository }}/releases/tag/${{ github.ref_name }}"
-        with:
-          payload: |
-            {
-              "blocks": [
-                {
-                  "type": "section",
-                  "text": {
-                    "type": "mrkdwn",
-                    "text": ":sparkles: New Tendermint pre-release: <${{ env.RELEASE_URL }}|${{ github.ref_name }}>"
-                  }
-                }
-              ]
-            }

.github/workflows/proto-lint.yml

@@ -15,7 +15,7 @@ jobs:
     timeout-minutes: 5
     steps:
       - uses: actions/checkout@v3
-      - uses: bufbuild/buf-setup-action@v1.9.0
+      - uses: bufbuild/buf-setup-action@v1.8.0
       - uses: bufbuild/buf-lint-action@v1
         with:
           input: 'proto'

.github/workflows/release.yml

@@ -6,7 +6,7 @@ on:
       - "v[0-9]+.[0-9]+.[0-9]+"  # Push events to matching v*, i.e. v1.0, v20.15.10
 
 jobs:
-  release:
+  goreleaser:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
@@ -35,28 +35,3 @@ jobs:
           args: release --rm-dist --release-notes=../release_notes.md
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-
-  release-success:
-    needs: release
-    if: ${{ success() }}
-    runs-on: ubuntu-latest
-    steps:
-      - name: Notify Slack upon release
-        uses: slackapi/slack-github-action@v1.22.0
-        env:
-          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
-          SLACK_WEBHOOK_TYPE: INCOMING_WEBHOOK
-          RELEASE_URL: "${{ github.server_url }}/${{ github.repository }}/releases/tag/${{ github.ref_name }}"
-        with:
-          payload: |
-            {
-              "blocks": [
-                {
-                  "type": "section",
-                  "text": {
-                    "type": "mrkdwn",
-                    "text": ":rocket: New Tendermint release: <${{ env.RELEASE_URL }}|${{ github.ref_name }}>"
-                  }
-                }
-              ]
-            }

.gitignore

@@ -55,5 +55,3 @@ proto/spec/**/*.pb.go
 *.pdf
 *.gz
 *.dvi
-# Python virtual environments
-.venv

.golangci.yml

@@ -2,6 +2,7 @@ linters:
   enable:
     - asciicheck
     - bodyclose
+    - deadcode
     - depguard
     - dogsled
     - dupl
@@ -25,6 +26,7 @@ linters:
     - typecheck
     - unconvert
     - unused
+    - varcheck
 
 issues:
   exclude-rules:

.md-link-check.json

@@ -2,16 +2,5 @@
     "retryOn429": true,
     "retryCount": 5,
     "fallbackRetryDelay": "30s",
-    "aliveStatusCodes": [200, 206, 503],
-    "httpHeaders": [
-        {
-            "urls": [
-                "https://docs.github.com/",
-                "https://help.github.com/"
-            ],
-            "headers": {
-                "Accept-Encoding": "zstd, br, gzip, deflate"
-            }
-        }
-    ]
+    "aliveStatusCodes": [200, 206, 503]
 }

CHANGELOG.md

@@ -2,36 +2,6 @@
 
 Friendly reminder, we have a [bug bounty program](https://hackerone.com/cosmos).
 
-## v0.34.22
-
-This release includes several bug fixes, [one of
-which](https://github.com/tendermint/tendermint/pull/9518) we discovered while
-building up a baseline for v0.34 against which to compare our upcoming v0.37
-release during our [QA process](./docs/qa/).
-
-Special thanks to external contributors on this release: @RiccardoM
-
-### FEATURES
-
-- [rpc] [\#9423](https://github.com/tendermint/tendermint/pull/9423) Support
-  HTTPS URLs from the WebSocket client (@RiccardoM, @cmwaters)
-
-### BUG FIXES
-
-- [config] [\#9483](https://github.com/tendermint/tendermint/issues/9483)
-  Calling `tendermint init` would incorrectly leave out the new `[storage]`
-  section delimiter in the generated configuration file - this has now been
-  fixed
-- [p2p] [\#9500](https://github.com/tendermint/tendermint/issues/9500) Prevent
-  peers who have errored being added to the peer set (@jmalicevic)
-- [indexer] [\#9473](https://github.com/tendermint/tendermint/issues/9473) Fix
-  bug that caused the psql indexer to index empty blocks whenever one of the
-  transactions returned a non zero code. The relevant deduplication logic has
-  been moved within the kv indexer only (@cmwaters)
-- [blocksync] [\#9518](https://github.com/tendermint/tendermint/issues/9518) A
-  block sync stall was observed during our QA process whereby the node was
-  unable to make progress. Retrying block requests after a timeout fixes this.
-
 ## v0.34.21
 
 Release highlights include:

CHANGELOG_PENDING.md

@@ -11,7 +11,6 @@
 - P2P Protocol
 
 - Go API
-  - [p2p] \#9625 Remove unused p2p/trust package (@cmwaters)
 
 - Blockchain Protocol
 
@@ -91,10 +90,8 @@ Friendly reminder, we have a [bug bounty program](https://hackerone.com/tendermi
 - [crypto] \#6120 Implement batch verification interface for ed25519 and sr25519. (@marbar3778 & @Yawning)
 - [types] \#6120 use batch verification for verifying commits signatures. (@marbar3778 & @cmwaters & @Yawning)
     - If the key type supports the batch verification API it will try to batch verify. If the verification fails we will single verify each signature.
-- [state] \#9505 Added logic so when pruning, the evidence period is taken into consideration and only deletes unecessary data (@samricotta)
 
 ### BUG FIXES
 
 - [consensus] \#9229 fix round number of `enterPropose` when handling `RoundStepNewRound` timeout. (@fatcat22)
 - [docker] \#9073 enable cross platform build using docker buildx
-- [blocksync] \#9518 handle the case when the sending queue is full: retry block request after a timeout

CODE_OF_CONDUCT.md

@@ -12,7 +12,7 @@ and hence to Tendermint.
 * We are committed to providing a friendly, safe and welcoming environment for
   all, regardless of level of experience, gender, gender identity and
   expression, sexual orientation, disability, personal appearance, body size,
-  race, ethnicity, age, religion, nationality, or other similar characteristics.
+  race, ethnicity, age, religion, nationality, or other similar characteristic.
 
 * On Slack, please avoid using overtly sexual nicknames or other nicknames that
   might detract from a friendly, safe and welcoming environment for all.

CONTRIBUTING.md

@@ -12,7 +12,7 @@ landing changes in `main`.
 All work on the code base should be motivated by a [Github
 Issue](https://github.com/tendermint/tendermint/issues).
 [Search](https://github.com/tendermint/tendermint/issues?q=is%3Aopen+is%3Aissue+label%3A%22help+wanted%22)
-is a good place to start when looking for places to contribute. If you
+is a good place start when looking for places to contribute. If you
 would like to work on an issue which already exists, please indicate so
 by leaving a comment.
 
@@ -213,7 +213,7 @@ Changes with multiple classifications should be doubly included (eg. a bug fix
 that is also a breaking change should be recorded under both).
 
 Breaking changes are further subdivided according to the APIs/users they impact.
-Any change that affects multiple APIs/users should be recorded multiply - for
+Any change that effects multiple APIs/users should be recorded multiply - for
 instance, a change to the `Blockchain Protocol` that removes a field from the
 header should also be recorded under `CLI/RPC/Config` since the field will be
 removed from the header in RPC responses as well.
@@ -247,7 +247,7 @@ To begin contributing, create a development branch either on `github.com/tenderm
 Make changes, and before submitting a pull request, update the `CHANGELOG_PENDING.md` to record your change. Also, run either `git rebase` or `git merge` on top of the latest `main`. (Since pull requests are squash-merged, either is fine!)
 
 Update the `UPGRADING.md` if the change you've made is breaking and the
-instructions should be in place for a user on how he/she can upgrade its
+instructions should be in place for a user on how he/she can upgrade it's
 software (ABCI application, Tendermint-based blockchain, light client, wallet).
 
 Once you have submitted a pull request label the pull request with either `R:minor`, if the change should be included in the next minor release, or `R:major`, if the change is meant for a major release.

Makefile

@@ -4,8 +4,14 @@ OUTPUT?=$(BUILDDIR)/tendermint
 
 BUILD_TAGS?=tendermint
 
-COMMIT_HASH := $(shell git rev-parse --short HEAD)
-LD_FLAGS = -X github.com/tendermint/tendermint/version.TMGitCommitHash=$(COMMIT_HASH)
+# If building a release, please checkout the version tag to get the correct version setting
+ifneq ($(shell git symbolic-ref -q --short HEAD),)
+VERSION := unreleased-$(shell git symbolic-ref -q --short HEAD)-$(shell git rev-parse HEAD)
+else
+VERSION := $(shell git describe)
+endif
+
+LD_FLAGS = -X github.com/tendermint/tendermint/version.TMCoreSemVer=$(VERSION)
 BUILD_FLAGS = -mod=readonly -ldflags "$(LD_FLAGS)"
 HTTPS_GIT := https://github.com/tendermint/tendermint.git
 CGO_ENABLED ?= 0
@@ -271,7 +277,7 @@ format:
 
 lint:
 	@echo "--> Running linter"
-	@go run github.com/golangci/golangci-lint/cmd/golangci-lint run
+	@golangci-lint run
 .PHONY: lint
 
 DESTINATION = ./index.html.md

abci/example/kvstore/kvstore.go

@@ -79,7 +79,7 @@ func NewApplication() *Application {
 func (app *Application) Info(req types.RequestInfo) (resInfo types.ResponseInfo) {
 	return types.ResponseInfo{
 		Data:             fmt.Sprintf("{\"size\":%v}", app.state.Size),
-		Version:          version.ABCISemVer,
+		Version:          version.ABCIVersion,
 		AppVersion:       ProtocolVersion,
 		LastBlockHeight:  app.state.Height,
 		LastBlockAppHash: app.state.AppHash,

abci/version/version.go

@@ -6,4 +6,4 @@ import (
 
 // TODO: eliminate this after some version refactor
 
-const Version = version.ABCISemVer
+const Version = version.ABCIVersion

blocksync/metrics.gen.go

@@ -1,30 +0,0 @@
-// Code generated by metricsgen. DO NOT EDIT.
-
-package blocksync
-
-import (
-	"github.com/go-kit/kit/metrics/discard"
-	prometheus "github.com/go-kit/kit/metrics/prometheus"
-	stdprometheus "github.com/prometheus/client_golang/prometheus"
-)
-
-func PrometheusMetrics(namespace string, labelsAndValues ...string) *Metrics {
-	labels := []string{}
-	for i := 0; i < len(labelsAndValues); i += 2 {
-		labels = append(labels, labelsAndValues[i])
-	}
-	return &Metrics{
-		Syncing: prometheus.NewGaugeFrom(stdprometheus.GaugeOpts{
-			Namespace: namespace,
-			Subsystem: MetricsSubsystem,
-			Name:      "syncing",
-			Help:      "Whether or not a node is block syncing. 1 if yes, 0 if no.",
-		}, labels).With(labelsAndValues...),
-	}
-}
-
-func NopMetrics() *Metrics {
-	return &Metrics{
-		Syncing: discard.NewGauge(),
-	}
-}

blocksync/metrics.go

@@ -1,19 +0,0 @@
-package blocksync
-
-import (
-	"github.com/go-kit/kit/metrics"
-)
-
-const (
-	// MetricsSubsystem is a subsystem shared by all metrics exposed by this
-	// package.
-	MetricsSubsystem = "blocksync"
-)
-
-//go:generate go run ../scripts/metricsgen -struct=Metrics
-
-// Metrics contains metrics exposed by this package.
-type Metrics struct {
-	// Whether or not a node is block syncing. 1 if yes, 0 if no.
-	Syncing metrics.Gauge
-}

blocksync/msgs.go

@@ -19,6 +19,58 @@ const (
 		BlockResponseMessageFieldKeySize
 )
 
+// EncodeMsg encodes a Protobuf message
+func EncodeMsg(pb proto.Message) ([]byte, error) {
+	msg := bcproto.Message{}
+
+	switch pb := pb.(type) {
+	case *bcproto.BlockRequest:
+		msg.Sum = &bcproto.Message_BlockRequest{BlockRequest: pb}
+	case *bcproto.BlockResponse:
+		msg.Sum = &bcproto.Message_BlockResponse{BlockResponse: pb}
+	case *bcproto.NoBlockResponse:
+		msg.Sum = &bcproto.Message_NoBlockResponse{NoBlockResponse: pb}
+	case *bcproto.StatusRequest:
+		msg.Sum = &bcproto.Message_StatusRequest{StatusRequest: pb}
+	case *bcproto.StatusResponse:
+		msg.Sum = &bcproto.Message_StatusResponse{StatusResponse: pb}
+	default:
+		return nil, fmt.Errorf("unknown message type %T", pb)
+	}
+
+	bz, err := proto.Marshal(&msg)
+	if err != nil {
+		return nil, fmt.Errorf("unable to marshal %T: %w", pb, err)
+	}
+
+	return bz, nil
+}
+
+// DecodeMsg decodes a Protobuf message.
+func DecodeMsg(bz []byte) (proto.Message, error) {
+	pb := &bcproto.Message{}
+
+	err := proto.Unmarshal(bz, pb)
+	if err != nil {
+		return nil, err
+	}
+
+	switch msg := pb.Sum.(type) {
+	case *bcproto.Message_BlockRequest:
+		return msg.BlockRequest, nil
+	case *bcproto.Message_BlockResponse:
+		return msg.BlockResponse, nil
+	case *bcproto.Message_NoBlockResponse:
+		return msg.NoBlockResponse, nil
+	case *bcproto.Message_StatusRequest:
+		return msg.StatusRequest, nil
+	case *bcproto.Message_StatusResponse:
+		return msg.StatusResponse, nil
+	default:
+		return nil, fmt.Errorf("unknown message type %T", msg)
+	}
+}
+
 // ValidateMsg validates a message.
 func ValidateMsg(pb proto.Message) error {
 	if pb == nil {

blocksync/msgs_test.go

@@ -80,7 +80,7 @@ func TestBcStatusResponseMessageValidateBasic(t *testing.T) {
 }
 
 //nolint:lll // ignore line length in tests
-func TestBlocksyncMessageVectors(t *testing.T) {
+func TestBlockchainMessageVectors(t *testing.T) {
 	block := types.MakeBlock(int64(3), []types.Tx{types.Tx("Hello World")}, nil, nil)
 	block.Version.Block = 11 // overwrite updated protocol version
 

blocksync/pool.go

@@ -32,7 +32,6 @@ const (
 	maxTotalRequesters        = 600
 	maxPendingRequests        = maxTotalRequesters
 	maxPendingRequestsPerPeer = 20
-	requestRetrySeconds       = 30
 
 	// Minimum recv rate to ensure we're receiving blocks from a peer fast
 	// enough. If a peer is not sending us data at at least that rate, we
@@ -99,9 +98,6 @@ func NewBlockPool(start int64, requestsCh chan<- BlockRequest, errorsCh chan<- p
 // OnStart implements service.Service by spawning requesters routine and recording
 // pool's start time.
 func (pool *BlockPool) OnStart() error {
-	if pool.height == 0 {
-		return errors.New("height not set")
-	}
 	go pool.makeRequestersRoutine()
 	pool.startTime = time.Now()
 	return nil
@@ -114,19 +110,22 @@ func (pool *BlockPool) makeRequestersRoutine() {
 			break
 		}
 
-		height, maxPeerHeight, numPending, lenRequesters := pool.GetStatus()
-		if height >= maxPeerHeight ||
-			numPending >= maxPendingRequests ||
-			lenRequesters >= maxTotalRequesters {
+		_, numPending, lenRequesters := pool.GetStatus()
+		switch {
+		case numPending >= maxPendingRequests:
 			// sleep for a bit.
 			time.Sleep(requestIntervalMS * time.Millisecond)
 			// check for timed out peers
 			pool.removeTimedoutPeers()
-			continue
+		case lenRequesters >= maxTotalRequesters:
+			// sleep for a bit.
+			time.Sleep(requestIntervalMS * time.Millisecond)
+			// check for timed out peers
+			pool.removeTimedoutPeers()
+		default:
+			// request for more blocks.
+			pool.makeNextRequester()
 		}
-
-		// request for more blocks.
-		pool.makeNextRequester()
 	}
 }
 
@@ -156,11 +155,11 @@ func (pool *BlockPool) removeTimedoutPeers() {
 
 // GetStatus returns pool's height, numPending requests and the number of
 // requesters.
-func (pool *BlockPool) GetStatus() (height, maxPeerHeight int64, numPending int32, lenRequesters int) {
+func (pool *BlockPool) GetStatus() (height int64, numPending int32, lenRequesters int) {
 	pool.mtx.Lock()
 	defer pool.mtx.Unlock()
 
-	return pool.height, pool.maxPeerHeight, atomic.LoadInt32(&pool.numPending), len(pool.requesters)
+	return pool.height, atomic.LoadInt32(&pool.numPending), len(pool.requesters)
 }
 
 // IsCaughtUp returns true if this node is caught up, false - otherwise.
@@ -302,7 +301,6 @@ func (pool *BlockPool) SetPeerRange(peerID p2p.ID, base int64, height int64) {
 	}
 
 	if height > pool.maxPeerHeight {
-		pool.Logger.Info("new max peer height", "height", height)
 		pool.maxPeerHeight = height
 	}
 }
@@ -389,7 +387,7 @@ func (pool *BlockPool) makeNextRequester() {
 
 	err := request.Start()
 	if err != nil {
-		pool.Logger.Error("Error starting request", "err", err)
+		request.Logger.Error("Error starting request", "err", err)
 	}
 }
 
@@ -604,7 +602,7 @@ OUTER_LOOP:
 			}
 			peer = bpr.pool.pickIncrAvailablePeer(bpr.height)
 			if peer == nil {
-				bpr.Logger.Debug("No peers currently available; will retry shortly", "height", bpr.height)
+				// log.Info("No peers available", "height", height)
 				time.Sleep(requestIntervalMS * time.Millisecond)
 				continue PICK_PEER_LOOP
 			}
@@ -614,7 +612,6 @@ OUTER_LOOP:
 		bpr.peerID = peer.id
 		bpr.mtx.Unlock()
 
-		to := time.NewTimer(requestRetrySeconds * time.Second)
 		// Send request and wait.
 		bpr.pool.sendRequest(bpr.height, peer.id)
 	WAIT_LOOP:
@@ -627,11 +624,6 @@ OUTER_LOOP:
 				return
 			case <-bpr.Quit():
 				return
-			case <-to.C:
-				bpr.Logger.Debug("Retrying block request after timeout", "height", bpr.height, "peer", bpr.peerID)
-				// Simulate a redo
-				bpr.reset()
-				continue OUTER_LOOP
 			case peerID := <-bpr.redoCh:
 				if peerID == bpr.peerID {
 					bpr.reset()

blocksync/reactor.go

@@ -30,9 +30,9 @@ const (
 )
 
 type consensusReactor interface {
-	// for when we switch from blocksync reactor and block sync to
+	// for when we switch from blockchain reactor and block sync to
 	// the consensus machine
-	SwitchToConsensus(state sm.State, skipWAL bool) error
+	SwitchToConsensus(state sm.State, skipWAL bool)
 }
 
 type peerError struct {
@@ -54,15 +54,16 @@ type Reactor struct {
 	blockExec *sm.BlockExecutor
 	store     *store.BlockStore
 	pool      *BlockPool
+	blockSync bool
 
 	requestsCh <-chan BlockRequest
 	errorsCh   <-chan peerError
-
-	metrics *Metrics
 }
 
 // NewReactor returns new reactor instance.
-func NewReactor(state sm.State, blockExec *sm.BlockExecutor, store *store.BlockStore, metrics *Metrics) *Reactor {
+func NewReactor(state sm.State, blockExec *sm.BlockExecutor, store *store.BlockStore,
+	blockSync bool) *Reactor {
+
 	if state.LastBlockHeight != store.Height() {
 		panic(fmt.Sprintf("state (%v) and store (%v) height mismatch", state.LastBlockHeight,
 			store.Height()))
@@ -84,9 +85,9 @@ func NewReactor(state sm.State, blockExec *sm.BlockExecutor, store *store.BlockS
 		blockExec:    blockExec,
 		store:        store,
 		pool:         pool,
+		blockSync:    blockSync,
 		requestsCh:   requestsCh,
 		errorsCh:     errorsCh,
-		metrics:      metrics,
 	}
 	bcR.BaseReactor = *p2p.NewBaseReactor("Reactor", bcR)
 	return bcR
@@ -100,22 +101,22 @@ func (bcR *Reactor) SetLogger(l log.Logger) {
 
 // OnStart implements service.Service.
 func (bcR *Reactor) OnStart() error {
+	if bcR.blockSync {
+		err := bcR.pool.Start()
+		if err != nil {
+			return err
+		}
+		go bcR.poolRoutine(false)
+	}
 	return nil
 }
 
-// IsSyncing returns whether the node is using blocksync to advance heights
-func (bcR *Reactor) IsSyncing() bool {
-	return bcR.pool.IsRunning()
-}
-
 // SwitchToBlockSync is called by the state sync reactor when switching to block sync.
 func (bcR *Reactor) SwitchToBlockSync(state sm.State) error {
+	bcR.blockSync = true
 	bcR.initialState = state
-	if state.LastBlockHeight == 0 {
-		bcR.pool.height = state.InitialHeight
-	} else {
-		bcR.pool.height = state.LastBlockHeight + 1
-	}
+
+	bcR.pool.height = state.LastBlockHeight + 1
 	err := bcR.pool.Start()
 	if err != nil {
 		return err
@@ -126,7 +127,7 @@ func (bcR *Reactor) SwitchToBlockSync(state sm.State) error {
 
 // OnStop implements service.Service.
 func (bcR *Reactor) OnStop() {
-	if bcR.pool.IsRunning() {
+	if bcR.blockSync {
 		if err := bcR.pool.Stop(); err != nil {
 			bcR.Logger.Error("Error stopping pool", "err", err)
 		}
@@ -142,20 +143,21 @@ func (bcR *Reactor) GetChannels() []*p2p.ChannelDescriptor {
 			SendQueueCapacity:   1000,
 			RecvBufferCapacity:  50 * 4096,
 			RecvMessageCapacity: MaxMsgSize,
-			MessageType:         &bcproto.Message{},
 		},
 	}
 }
 
 // AddPeer implements Reactor by sending our state to peer.
 func (bcR *Reactor) AddPeer(peer p2p.Peer) {
-	peer.Send(p2p.Envelope{
-		ChannelID: BlocksyncChannel,
-		Message: &bcproto.StatusResponse{
-			Base:   bcR.store.Base(),
-			Height: bcR.store.Height(),
-		},
-	})
+	msgBytes, err := EncodeMsg(&bcproto.StatusResponse{
+		Base:   bcR.store.Base(),
+		Height: bcR.store.Height()})
+	if err != nil {
+		bcR.Logger.Error("could not convert msg to protobuf", "err", err)
+		return
+	}
+
+	peer.Send(BlocksyncChannel, msgBytes)
 	// it's OK if send fails. will try later in poolRoutine
 
 	// peer is added to the pool once we receive the first
@@ -180,53 +182,69 @@ func (bcR *Reactor) respondToPeer(msg *bcproto.BlockRequest,
 			return false
 		}
 
-		return src.TrySend(p2p.Envelope{
-			ChannelID: BlocksyncChannel,
-			Message:   &bcproto.BlockResponse{Block: bl},
-		})
+		msgBytes, err := EncodeMsg(&bcproto.BlockResponse{Block: bl})
+		if err != nil {
+			bcR.Logger.Error("could not marshal msg", "err", err)
+			return false
+		}
+
+		return src.TrySend(BlocksyncChannel, msgBytes)
 	}
 
 	bcR.Logger.Info("Peer asking for a block we don't have", "src", src, "height", msg.Height)
-	return src.TrySend(p2p.Envelope{
-		ChannelID: BlocksyncChannel,
-		Message:   &bcproto.NoBlockResponse{Height: msg.Height},
-	})
+
+	msgBytes, err := EncodeMsg(&bcproto.NoBlockResponse{Height: msg.Height})
+	if err != nil {
+		bcR.Logger.Error("could not convert msg to protobuf", "err", err)
+		return false
+	}
+
+	return src.TrySend(BlocksyncChannel, msgBytes)
 }
 
 // Receive implements Reactor by handling 4 types of messages (look below).
-func (bcR *Reactor) Receive(e p2p.Envelope) {
-	if err := ValidateMsg(e.Message); err != nil {
-		bcR.Logger.Error("Peer sent us invalid msg", "peer", e.Src, "msg", e.Message, "err", err)
-		bcR.Switch.StopPeerForError(e.Src, err)
+func (bcR *Reactor) Receive(chID byte, src p2p.Peer, msgBytes []byte) {
+	msg, err := DecodeMsg(msgBytes)
+	if err != nil {
+		bcR.Logger.Error("Error decoding message", "src", src, "chId", chID, "err", err)
+		bcR.Switch.StopPeerForError(src, err)
 		return
 	}
 
-	bcR.Logger.Debug("Receive", "e.Src", e.Src, "chID", e.ChannelID, "msg", e.Message)
+	if err = ValidateMsg(msg); err != nil {
+		bcR.Logger.Error("Peer sent us invalid msg", "peer", src, "msg", msg, "err", err)
+		bcR.Switch.StopPeerForError(src, err)
+		return
+	}
 
-	switch msg := e.Message.(type) {
+	bcR.Logger.Debug("Receive", "src", src, "chID", chID, "msg", msg)
+
+	switch msg := msg.(type) {
 	case *bcproto.BlockRequest:
-		bcR.respondToPeer(msg, e.Src)
+		bcR.respondToPeer(msg, src)
 	case *bcproto.BlockResponse:
 		bi, err := types.BlockFromProto(msg.Block)
 		if err != nil {
 			bcR.Logger.Error("Block content is invalid", "err", err)
 			return
 		}
-		bcR.pool.AddBlock(e.Src.ID(), bi, msg.Block.Size())
+		bcR.pool.AddBlock(src.ID(), bi, len(msgBytes))
 	case *bcproto.StatusRequest:
 		// Send peer our state.
-		e.Src.TrySend(p2p.Envelope{
-			ChannelID: BlocksyncChannel,
-			Message: &bcproto.StatusResponse{
-				Height: bcR.store.Height(),
-				Base:   bcR.store.Base(),
-			},
+		msgBytes, err := EncodeMsg(&bcproto.StatusResponse{
+			Height: bcR.store.Height(),
+			Base:   bcR.store.Base(),
 		})
+		if err != nil {
+			bcR.Logger.Error("could not convert msg to protobut", "err", err)
+			return
+		}
+		src.TrySend(BlocksyncChannel, msgBytes)
 	case *bcproto.StatusResponse:
 		// Got a peer status. Unverified.
-		bcR.pool.SetPeerRange(e.Src.ID(), msg.Base, msg.Height)
+		bcR.pool.SetPeerRange(src.ID(), msg.Base, msg.Height)
 	case *bcproto.NoBlockResponse:
-		bcR.Logger.Debug("Peer does not have requested block", "peer", e.Src, "height", msg.Height)
+		bcR.Logger.Debug("Peer does not have requested block", "peer", src, "height", msg.Height)
 	default:
 		bcR.Logger.Error(fmt.Sprintf("Unknown message type %v", reflect.TypeOf(msg)))
 	}
@@ -235,8 +253,6 @@ func (bcR *Reactor) Receive(e p2p.Envelope) {
 // Handle messages from the poolReactor telling the reactor what to do.
 // NOTE: Don't sleep in the FOR_LOOP or otherwise slow it down!
 func (bcR *Reactor) poolRoutine(stateSynced bool) {
-	bcR.metrics.Syncing.Set(1)
-	defer bcR.metrics.Syncing.Set(0)
 
 	trySyncTicker := time.NewTicker(trySyncIntervalMS * time.Millisecond)
 	defer trySyncTicker.Stop()
@@ -269,10 +285,13 @@ func (bcR *Reactor) poolRoutine(stateSynced bool) {
 				if peer == nil {
 					continue
 				}
-				queued := peer.TrySend(p2p.Envelope{
-					ChannelID: BlocksyncChannel,
-					Message:   &bcproto.BlockRequest{Height: request.Height},
-				})
+				msgBytes, err := EncodeMsg(&bcproto.BlockRequest{Height: request.Height})
+				if err != nil {
+					bcR.Logger.Error("could not convert msg to proto", "err", err)
+					continue
+				}
+
+				queued := peer.TrySend(BlocksyncChannel, msgBytes)
 				if !queued {
 					bcR.Logger.Debug("Send queue is full, drop block request", "peer", peer.ID(), "height", request.Height)
 				}
@@ -284,7 +303,7 @@ func (bcR *Reactor) poolRoutine(stateSynced bool) {
 
 			case <-statusUpdateTicker.C:
 				// ask for status updates
-				go bcR.BroadcastStatusRequest()
+				go bcR.BroadcastStatusRequest() //nolint: errcheck
 
 			}
 		}
@@ -294,28 +313,24 @@ FOR_LOOP:
 	for {
 		select {
 		case <-switchToConsensusTicker.C:
-			height, peerHeight, numPending, lenRequesters := bcR.pool.GetStatus()
+			height, numPending, lenRequesters := bcR.pool.GetStatus()
 			outbound, inbound, _ := bcR.Switch.NumPeers()
 			bcR.Logger.Debug("Consensus ticker", "numPending", numPending, "total", lenRequesters,
-				"outbound", outbound, "inbound", inbound, "peerHeight", peerHeight)
+				"outbound", outbound, "inbound", inbound)
 			if bcR.pool.IsCaughtUp() {
 				bcR.Logger.Info("Time to switch to consensus reactor!", "height", height)
 				if err := bcR.pool.Stop(); err != nil {
 					bcR.Logger.Error("Error stopping pool", "err", err)
 				}
-
-				// TODO: node struct should be responsible for switching from block sync to
-				// consensus. It's messy to have to grab the consensus reactor from the switch
 				conR, ok := bcR.Switch.Reactor("CONSENSUS").(consensusReactor)
 				if ok {
-					err := conR.SwitchToConsensus(state, blocksSynced > 0 || stateSynced)
-					bcR.Logger.Error("failed to switch to consensus", "err", err)
+					conR.SwitchToConsensus(state, blocksSynced > 0 || stateSynced)
 				}
 				// else {
 				// should only happen during testing
 				// }
 
-				return
+				break FOR_LOOP
 			}
 
 		case <-trySyncTicker.C: // chan time
@@ -414,9 +429,14 @@ FOR_LOOP:
 }
 
 // BroadcastStatusRequest broadcasts `BlockStore` base and height.
-func (bcR *Reactor) BroadcastStatusRequest() {
-	bcR.Switch.Broadcast(p2p.Envelope{
-		ChannelID: BlocksyncChannel,
-		Message:   &bcproto.StatusRequest{},
-	})
+func (bcR *Reactor) BroadcastStatusRequest() error {
+	bm, err := EncodeMsg(&bcproto.StatusRequest{})
+	if err != nil {
+		bcR.Logger.Error("could not convert msg to proto", "err", err)
+		return fmt.Errorf("could not convert msg to proto: %w", err)
+	}
+
+	bcR.Switch.Broadcast(BlocksyncChannel, bm)
+
+	return nil
 }

blocksync/reactor_test.go

@@ -95,6 +95,14 @@ func newReactor(
 		mock.Anything,
 		mock.Anything).Return(nil)
 
+	// Make the Reactor itself.
+	// NOTE we have to create and commit the blocks first because
+	// pool.height is determined from the store.
+	fastSync := true
+	db := dbm.NewMemDB()
+	stateStore = sm.NewStore(db, sm.StoreOptions{
+		DiscardABCIResponses: false,
+	})
 	blockExec := sm.NewBlockExecutor(stateStore, log.TestingLogger(), proxyApp.Consensus(),
 		mp, sm.EmptyEvidencePool{}, blockStore)
 	if err = stateStore.Save(state); err != nil {
@@ -137,20 +145,17 @@ func newReactor(
 		blockStore.SaveBlock(thisBlock, thisParts, lastCommit)
 	}
 
-	bcReactor := NewReactor(state.Copy(), blockExec, blockStore, NopMetrics())
-	bcReactor.SetLogger(logger.With("module", "blocksync"))
+	bcReactor := NewReactor(state.Copy(), blockExec, blockStore, fastSync)
+	bcReactor.SetLogger(logger.With("module", "blockchain"))
 
 	return ReactorPair{bcReactor, proxyApp}
 }
 
 func TestNoBlockResponse(t *testing.T) {
-	config = test.ResetTestRoot("blocksync_reactor_test")
+	config = test.ResetTestRoot("blockchain_reactor_test")
 	defer os.RemoveAll(config.RootDir)
 	genDoc, privVals := randGenesisDoc(1, false, 30)
 
-	state, err := sm.MakeGenesisState(genDoc)
-	require.NoError(t, err)
-
 	maxBlockHeight := int64(65)
 
 	reactorPairs := make([]ReactorPair, 2)
@@ -159,17 +164,11 @@ func TestNoBlockResponse(t *testing.T) {
 	reactorPairs[1] = newReactor(t, log.TestingLogger(), genDoc, privVals, 0)
 
 	p2p.MakeConnectedSwitches(config.P2P, 2, func(i int, s *p2p.Switch) *p2p.Switch {
-		s.AddReactor("BLOCKSYNC", reactorPairs[i].reactor)
+		s.AddReactor("BLOCKCHAIN", reactorPairs[i].reactor)
 		return s
 
 	}, p2p.Connect2Switches)
 
-	for _, reactor := range reactorPairs {
-		// turn on the syncing algorithm
-		err := reactor.reactor.SwitchToBlockSync(state)
-		require.NoError(t, err)
-	}
-
 	defer func() {
 		for _, r := range reactorPairs {
 			err := r.reactor.Stop()
@@ -215,13 +214,10 @@ func TestNoBlockResponse(t *testing.T) {
 // Alternatively we could actually dial a TCP conn but
 // that seems extreme.
 func TestBadBlockStopsPeer(t *testing.T) {
-	config = test.ResetTestRoot("blocksync_reactor_test")
+	config = test.ResetTestRoot("blockchain_reactor_test")
 	defer os.RemoveAll(config.RootDir)
 	genDoc, privVals := randGenesisDoc(1, false, 30)
 
-	state, err := sm.MakeGenesisState(genDoc)
-	require.NoError(t, err)
-
 	maxBlockHeight := int64(148)
 
 	// Other chain needs a different validator set
@@ -243,17 +239,11 @@ func TestBadBlockStopsPeer(t *testing.T) {
 	reactorPairs[3] = newReactor(t, log.TestingLogger(), genDoc, privVals, 0)
 
 	switches := p2p.MakeConnectedSwitches(config.P2P, 4, func(i int, s *p2p.Switch) *p2p.Switch {
-		s.AddReactor("BLOCKSYNC", reactorPairs[i].reactor)
+		s.AddReactor("BLOCKCHAIN", reactorPairs[i].reactor)
 		return s
 
 	}, p2p.Connect2Switches)
 
-	for _, reactor := range reactorPairs {
-		// turn on the syncing algorithm
-		err := reactor.reactor.SwitchToBlockSync(state)
-		require.NoError(t, err)
-	}
-
 	defer func() {
 		for _, r := range reactorPairs {
 			err := r.reactor.Stop()
@@ -288,7 +278,7 @@ func TestBadBlockStopsPeer(t *testing.T) {
 	reactorPairs = append(reactorPairs, lastReactorPair)
 
 	switches = append(switches, p2p.MakeConnectedSwitches(config.P2P, 1, func(i int, s *p2p.Switch) *p2p.Switch {
-		s.AddReactor("BLOCKSYNC", reactorPairs[len(reactorPairs)-1].reactor)
+		s.AddReactor("BLOCKCHAIN", reactorPairs[len(reactorPairs)-1].reactor)
 		return s
 
 	}, p2p.Connect2Switches)...)
@@ -297,11 +287,6 @@ func TestBadBlockStopsPeer(t *testing.T) {
 		p2p.Connect2Switches(switches, i, len(reactorPairs)-1)
 	}
 
-	otherState, err := sm.MakeGenesisState(otherGenDoc)
-	require.NoError(t, err)
-	err = lastReactorPair.reactor.SwitchToBlockSync(otherState)
-	require.NoError(t, err)
-
 	for {
 		if lastReactorPair.reactor.pool.IsCaughtUp() || lastReactorPair.reactor.Switch.Peers().Size() == 0 {
 			break

cmd/tendermint/commands/debug/util.go

@@ -67,8 +67,7 @@ func copyConfig(home, dir string) error {
 func dumpProfile(dir, addr, profile string, debug int) error {
 	endpoint := fmt.Sprintf("%s/debug/pprof/%s?debug=%d", addr, profile, debug)
 
-	//nolint:all
-	resp, err := http.Get(endpoint)
+	resp, err := http.Get(endpoint) //nolint: gosec
 	if err != nil {
 		return fmt.Errorf("failed to query for %s profile: %w", profile, err)
 	}

cmd/tendermint/commands/rollback.go

@@ -14,7 +14,7 @@ import (
 	"github.com/tendermint/tendermint/store"
 )
 
-var removeBlock = false
+var removeBlock bool = false
 
 func init() {
 	RollbackStateCmd.Flags().BoolVar(&removeBlock, "hard", false, "remove last block as well as state")

cmd/tendermint/commands/version.go

@@ -14,11 +14,6 @@ var VersionCmd = &cobra.Command{
 	Use:   "version",
 	Short: "Show version info",
 	Run: func(cmd *cobra.Command, args []string) {
-		tmVersion := version.TMCoreSemVer
-		if version.TMGitCommitHash != "" {
-			tmVersion += "+" + version.TMGitCommitHash
-		}
-
 		if verbose {
 			values, _ := json.MarshalIndent(struct {
 				Tendermint    string `json:"tendermint"`
@@ -26,14 +21,14 @@ var VersionCmd = &cobra.Command{
 				BlockProtocol uint64 `json:"block_protocol"`
 				P2PProtocol   uint64 `json:"p2p_protocol"`
 			}{
-				Tendermint:    tmVersion,
-				ABCI:          version.ABCISemVer,
+				Tendermint:    version.TMCoreSemVer,
+				ABCI:          version.ABCIVersion,
 				BlockProtocol: version.BlockProtocol,
 				P2PProtocol:   version.P2PProtocol,
 			}, "", "  ")
 			fmt.Println(string(values))
 		} else {
-			fmt.Println(tmVersion)
+			fmt.Println(version.TMCoreSemVer)
 		}
 	},
 }

config/config.go

@@ -423,7 +423,6 @@ type RPCConfig struct {
 	TLSKeyFile string `mapstructure:"tls_key_file"`
 
 	// pprof listen address (https://golang.org/pkg/net/http/pprof)
-	// FIXME: This should be moved under the instrumentation section
 	PprofListenAddress string `mapstructure:"pprof_laddr"`
 }
 
@@ -507,10 +506,6 @@ func (cfg *RPCConfig) IsCorsEnabled() bool {
 	return len(cfg.CORSAllowedOrigins) != 0
 }
 
-func (cfg *RPCConfig) IsPprofEnabled() bool {
-	return len(cfg.PprofListenAddress) != 0
-}
-
 func (cfg RPCConfig) KeyFile() string {
 	path := cfg.TLSKeyFile
 	if filepath.IsAbs(path) {
@@ -708,6 +703,9 @@ type MempoolConfig struct {
 	// Mempool version to use:
 	//  1) "v0" - (default) FIFO mempool.
 	//  2) "v1" - prioritized mempool.
+	// WARNING: There's a known memory leak with the prioritized mempool
+	// that the team are working on. Read more here:
+	// https://github.com/tendermint/tendermint/issues/8775
 	Version   string `mapstructure:"version"`
 	RootDir   string `mapstructure:"home"`
 	Recheck   bool   `mapstructure:"recheck"`
@@ -1206,10 +1204,6 @@ func (cfg *InstrumentationConfig) ValidateBasic() error {
 	return nil
 }
 
-func (cfg *InstrumentationConfig) IsPrometheusEnabled() bool {
-	return cfg.Prometheus && cfg.PrometheusListenAddr != ""
-}
-
 //-----------------------------------------------------------------------------
 // Utils
 

consensus/byzantine_test.go

@@ -26,7 +26,6 @@ import (
 	mempoolv0 "github.com/tendermint/tendermint/mempool/v0"
 	mempoolv1 "github.com/tendermint/tendermint/mempool/v1"
 	"github.com/tendermint/tendermint/p2p"
-	tmcons "github.com/tendermint/tendermint/proto/tendermint/consensus"
 	tmproto "github.com/tendermint/tendermint/proto/tendermint/types"
 	sm "github.com/tendermint/tendermint/state"
 	"github.com/tendermint/tendermint/store"
@@ -46,8 +45,6 @@ func TestByzantinePrevoteEquivocation(t *testing.T) {
 	appFunc := newKVStore
 
 	genDoc, privVals := randGenesisDoc(nValidators, false, 30)
-	state, err := sm.MakeGenesisState(genDoc)
-	require.NoError(t, err)
 	css := make([]*State, nValidators)
 
 	for i := 0; i < nValidators; i++ {
@@ -56,6 +53,7 @@ func TestByzantinePrevoteEquivocation(t *testing.T) {
 		stateStore := sm.NewStore(stateDB, sm.StoreOptions{
 			DiscardABCIResponses: false,
 		})
+		state, _ := stateStore.LoadFromDBOrGenesisDoc(genDoc)
 		thisConfig := ResetConfig(fmt.Sprintf("%s_%d", testName, i))
 		defer os.RemoveAll(thisConfig.RootDir)
 		ensureDir(path.Dir(thisConfig.Consensus.WalFile()), 0700) // dir for wal
@@ -103,7 +101,7 @@ func TestByzantinePrevoteEquivocation(t *testing.T) {
 
 		// Make State
 		blockExec := sm.NewBlockExecutor(stateStore, log.TestingLogger(), proxyAppConnCon, mempool, evpool, blockStore)
-		cs := NewState(thisConfig.Consensus, blockExec, blockStore, mempool, evpool, WithState(state.Copy()))
+		cs := NewState(thisConfig.Consensus, state, blockExec, blockStore, mempool, evpool)
 		cs.SetLogger(cs.Logger)
 		// set private validator
 		pv := privVals[i]
@@ -126,8 +124,7 @@ func TestByzantinePrevoteEquivocation(t *testing.T) {
 	blocksSubs := make([]types.Subscription, 0)
 	eventBuses := make([]*types.EventBus, nValidators)
 	for i := 0; i < nValidators; i++ {
-		// Note, we dont start the consensus states
-		reactors[i] = NewReactor(css[i])
+		reactors[i] = NewReactor(css[i], true) // so we dont start the consensus states
 		reactors[i].SetLogger(css[i].Logger)
 
 		// eventBus is already started with the cs
@@ -168,16 +165,10 @@ func TestByzantinePrevoteEquivocation(t *testing.T) {
 			for i, peer := range peerList {
 				if i < len(peerList)/2 {
 					bcs.Logger.Info("Signed and pushed vote", "vote", prevote1, "peer", peer)
-					peer.Send(p2p.Envelope{
-						Message:   &tmcons.Vote{Vote: prevote1.ToProto()},
-						ChannelID: VoteChannel,
-					})
+					peer.Send(VoteChannel, MustEncode(&VoteMessage{prevote1}))
 				} else {
 					bcs.Logger.Info("Signed and pushed vote", "vote", prevote2, "peer", peer)
-					peer.Send(p2p.Envelope{
-						Message:   &tmcons.Vote{Vote: prevote2.ToProto()},
-						ChannelID: VoteChannel,
-					})
+					peer.Send(VoteChannel, MustEncode(&VoteMessage{prevote2}))
 				}
 			}
 		} else {
@@ -256,7 +247,8 @@ func TestByzantinePrevoteEquivocation(t *testing.T) {
 
 	// start the consensus reactors
 	for i := 0; i < nValidators; i++ {
-		require.NoError(t, reactors[i].SwitchToConsensus(state.Copy(), false))
+		s := reactors[i].conS.GetState()
+		reactors[i].SwitchToConsensus(s, false)
 	}
 	defer stopConsensusNet(log.TestingLogger(), reactors, eventBuses)
 
@@ -315,7 +307,7 @@ func TestByzantineConflictingProposalsWithPartition(t *testing.T) {
 	N := 4
 	logger := consensusLogger().With("test", "byzantine")
 	app := newKVStore
-	css, cleanup := randConsensusNet(t, N, "consensus_byzantine_test", newMockTickerFunc(false), app)
+	css, cleanup := randConsensusNet(N, "consensus_byzantine_test", newMockTickerFunc(false), app)
 	defer cleanup()
 
 	// give the byzantine validator a normal ticker
@@ -364,8 +356,7 @@ func TestByzantineConflictingProposalsWithPartition(t *testing.T) {
 		blocksSubs[i], err = eventBus.Subscribe(context.Background(), testSubscriber, types.EventQueryNewBlock)
 		require.NoError(t, err)
 
-		// Note, we don't start the consensus states
-		conR := NewReactor(css[i])
+		conR := NewReactor(css[i], true) // so we don't start the consensus states
 		conR.SetLogger(logger.With("validator", i))
 		conR.SetEventBus(eventBus)
 
@@ -409,13 +400,13 @@ func TestByzantineConflictingProposalsWithPartition(t *testing.T) {
 	// note these must be started before the byz
 	for i := 1; i < N; i++ {
 		cr := reactors[i].(*Reactor)
-		require.NoError(t, cr.SwitchToConsensus(cr.conS.GetState(), false))
+		cr.SwitchToConsensus(cr.conS.GetState(), false)
 	}
 
 	// start the byzantine state machine
 	byzR := reactors[0].(*ByzantineReactor)
 	s := byzR.reactor.conS.GetState()
-	require.NoError(t, byzR.reactor.SwitchToConsensus(s, false))
+	byzR.reactor.SwitchToConsensus(s, false)
 
 	// byz proposer sends one block to peers[0]
 	// and the other block to peers[1] and peers[2].
@@ -529,26 +520,18 @@ func sendProposalAndParts(
 	parts *types.PartSet,
 ) {
 	// proposal
-	peer.Send(p2p.Envelope{
-		ChannelID: DataChannel,
-		Message:   &tmcons.Proposal{Proposal: *proposal.ToProto()},
-	})
+	msg := &ProposalMessage{Proposal: proposal}
+	peer.Send(DataChannel, MustEncode(msg))
 
 	// parts
 	for i := 0; i < int(parts.Total()); i++ {
 		part := parts.GetPart(i)
-		pp, err := part.ToProto()
-		if err != nil {
-			panic(err) // TODO: wbanfield better error handling
+		msg := &BlockPartMessage{
+			Height: height, // This tells peer that this part applies to us.
+			Round:  round,  // This tells peer that this part applies to us.
+			Part:   part,
 		}
-		peer.Send(p2p.Envelope{
-			ChannelID: DataChannel,
-			Message: &tmcons.BlockPart{
-				Height: height, // This tells peer that this part applies to us.
-				Round:  round,  // This tells peer that this part applies to us.
-				Part:   *pp,
-			},
-		})
+		peer.Send(DataChannel, MustEncode(msg))
 	}
 
 	// votes
@@ -556,14 +539,9 @@ func sendProposalAndParts(
 	prevote, _ := cs.signVote(tmproto.PrevoteType, blockHash, parts.Header())
 	precommit, _ := cs.signVote(tmproto.PrecommitType, blockHash, parts.Header())
 	cs.mtx.Unlock()
-	peer.Send(p2p.Envelope{
-		ChannelID: VoteChannel,
-		Message:   &tmcons.Vote{Vote: prevote.ToProto()},
-	})
-	peer.Send(p2p.Envelope{
-		ChannelID: VoteChannel,
-		Message:   &tmcons.Vote{Vote: precommit.ToProto()},
-	})
+
+	peer.Send(VoteChannel, MustEncode(&VoteMessage{prevote}))
+	peer.Send(VoteChannel, MustEncode(&VoteMessage{precommit}))
 }
 
 //----------------------------------------
@@ -594,14 +572,14 @@ func (br *ByzantineReactor) AddPeer(peer p2p.Peer) {
 
 	// Send our state to peer.
 	// If we're syncing, broadcast a RoundStepMessage later upon SwitchToConsensus().
-	if br.reactor.conS.IsRunning() {
+	if !br.reactor.waitSync {
 		br.reactor.sendNewRoundStepMessage(peer)
 	}
 }
 func (br *ByzantineReactor) RemovePeer(peer p2p.Peer, reason interface{}) {
 	br.reactor.RemovePeer(peer, reason)
 }
-func (br *ByzantineReactor) Receive(e p2p.Envelope) {
-	br.reactor.Receive(e)
+func (br *ByzantineReactor) Receive(chID byte, peer p2p.Peer, msgBytes []byte) {
+	br.reactor.Receive(chID, peer, msgBytes)
 }
 func (br *ByzantineReactor) InitPeer(peer p2p.Peer) p2p.Peer { return peer }

consensus/common_test.go

@@ -440,7 +440,7 @@ func newStateWithConfigAndBlockStore(
 	}
 
 	blockExec := sm.NewBlockExecutor(stateStore, log.TestingLogger(), proxyAppConnCon, mempool, evpool, blockStore)
-	cs := NewState(thisConfig.Consensus, blockExec, blockStore, mempool, evpool, WithState(state.Copy()))
+	cs := NewState(thisConfig.Consensus, state, blockExec, blockStore, mempool, evpool)
 	cs.SetLogger(log.TestingLogger().With("module", "consensus"))
 	cs.SetPrivValidator(pv)
 
@@ -747,17 +747,18 @@ func consensusLogger() log.Logger {
 	}).With("module", "consensus")
 }
 
-func randConsensusNet(t *testing.T, nValidators int, testName string, tickerFunc func() TimeoutTicker,
+func randConsensusNet(nValidators int, testName string, tickerFunc func() TimeoutTicker,
 	appFunc func() abci.Application, configOpts ...func(*cfg.Config)) ([]*State, cleanupFunc) {
-	t.Helper()
 	genDoc, privVals := randGenesisDoc(nValidators, false, 30)
-	state, err := sm.MakeGenesisState(genDoc)
-	require.NoError(t, err)
 	css := make([]*State, nValidators)
 	logger := consensusLogger()
 	configRootDirs := make([]string, 0, nValidators)
 	for i := 0; i < nValidators; i++ {
 		stateDB := dbm.NewMemDB() // each state needs its own db
+		stateStore := sm.NewStore(stateDB, sm.StoreOptions{
+			DiscardABCIResponses: false,
+		})
+		state, _ := stateStore.LoadFromDBOrGenesisDoc(genDoc)
 		thisConfig := ResetConfig(fmt.Sprintf("%s_%d", testName, i))
 		configRootDirs = append(configRootDirs, thisConfig.RootDir)
 		for _, opt := range configOpts {
@@ -771,7 +772,6 @@ func randConsensusNet(t *testing.T, nValidators int, testName string, tickerFunc
 		css[i] = newStateWithConfigAndBlockStore(thisConfig, state, privVals[i], app, stateDB)
 		css[i].SetTimeoutTicker(tickerFunc())
 		css[i].SetLogger(logger.With("validator", i, "module", "consensus"))
-		css[i].updateToState(state.Copy())
 	}
 	return css, func() {
 		for _, dir := range configRootDirs {

consensus/invalid_test.go

@@ -7,7 +7,6 @@ import (
 	"github.com/tendermint/tendermint/libs/log"
 	tmrand "github.com/tendermint/tendermint/libs/rand"
 	"github.com/tendermint/tendermint/p2p"
-	tmcons "github.com/tendermint/tendermint/proto/tendermint/consensus"
 	tmproto "github.com/tendermint/tendermint/proto/tendermint/types"
 	"github.com/tendermint/tendermint/types"
 )
@@ -19,7 +18,7 @@ import (
 // Ensure a testnet makes blocks
 func TestReactorInvalidPrecommit(t *testing.T) {
 	N := 4
-	css, cleanup := randConsensusNet(t, N, "consensus_reactor_test", newMockTickerFunc(true), newKVStore)
+	css, cleanup := randConsensusNet(N, "consensus_reactor_test", newMockTickerFunc(true), newKVStore)
 	defer cleanup()
 
 	for i := 0; i < 4; i++ {
@@ -95,10 +94,7 @@ func invalidDoPrevoteFunc(t *testing.T, height int64, round int32, cs *State, sw
 		peers := sw.Peers().List()
 		for _, peer := range peers {
 			cs.Logger.Info("Sending bad vote", "block", blockHash, "peer", peer)
-			peer.Send(p2p.Envelope{
-				Message:   &tmcons.Vote{Vote: precommit.ToProto()},
-				ChannelID: VoteChannel,
-			})
+			peer.Send(VoteChannel, MustEncode(&VoteMessage{precommit}))
 		}
 	}()
 }

consensus/metrics.gen.go

@@ -118,6 +118,18 @@ func PrometheusMetrics(namespace string, labelsAndValues ...string) *Metrics {
 			Name:      "latest_block_height",
 			Help:      "The latest block height.",
 		}, labels).With(labelsAndValues...),
+		BlockSyncing: prometheus.NewGaugeFrom(stdprometheus.GaugeOpts{
+			Namespace: namespace,
+			Subsystem: MetricsSubsystem,
+			Name:      "block_syncing",
+			Help:      "Whether or not a node is block syncing. 1 if yes, 0 if no.",
+		}, labels).With(labelsAndValues...),
+		StateSyncing: prometheus.NewGaugeFrom(stdprometheus.GaugeOpts{
+			Namespace: namespace,
+			Subsystem: MetricsSubsystem,
+			Name:      "state_syncing",
+			Help:      "Whether or not a node is state syncing. 1 if yes, 0 if no.",
+		}, labels).With(labelsAndValues...),
 		BlockParts: prometheus.NewCounterFrom(stdprometheus.CounterOpts{
 			Namespace: namespace,
 			Subsystem: MetricsSubsystem,
@@ -196,6 +208,8 @@ func NopMetrics() *Metrics {
 		BlockSizeBytes:            discard.NewGauge(),
 		TotalTxs:                  discard.NewGauge(),
 		CommittedHeight:           discard.NewGauge(),
+		BlockSyncing:              discard.NewGauge(),
+		StateSyncing:              discard.NewGauge(),
 		BlockParts:                discard.NewCounter(),
 		StepDurationSeconds:       discard.NewHistogram(),
 		BlockGossipPartsReceived:  discard.NewCounter(),

consensus/metrics.go

@@ -61,6 +61,10 @@ type Metrics struct {
 	TotalTxs metrics.Gauge
 	// The latest block height.
 	CommittedHeight metrics.Gauge `metrics_name:"latest_block_height"`
+	// Whether or not a node is block syncing. 1 if yes, 0 if no.
+	BlockSyncing metrics.Gauge
+	// Whether or not a node is state syncing. 1 if yes, 0 if no.
+	StateSyncing metrics.Gauge
 
 	// Number of block parts transmitted by each peer.
 	BlockParts metrics.Counter `metrics_labels:"peer_id"`

consensus/msgs.go

@@ -5,6 +5,7 @@ import (
 	"fmt"
 
 	"github.com/cosmos/gogoproto/proto"
+
 	cstypes "github.com/tendermint/tendermint/consensus/types"
 	"github.com/tendermint/tendermint/libs/bits"
 	tmmath "github.com/tendermint/tendermint/libs/math"
@@ -14,147 +15,173 @@ import (
 	"github.com/tendermint/tendermint/types"
 )
 
-// MsgToProto takes a consensus message type and returns the proto defined consensus message.
-//
-// TODO: This needs to be removed, but WALToProto depends on this.
-func MsgToProto(msg Message) (proto.Message, error) {
+// MsgToProto takes a consensus message type and returns the proto defined consensus message
+func MsgToProto(msg Message) (*tmcons.Message, error) {
 	if msg == nil {
 		return nil, errors.New("consensus: message is nil")
 	}
-	var pb proto.Message
+	var pb tmcons.Message
 
 	switch msg := msg.(type) {
 	case *NewRoundStepMessage:
-		pb = &tmcons.NewRoundStep{
-			Height:                msg.Height,
-			Round:                 msg.Round,
-			Step:                  uint32(msg.Step),
-			SecondsSinceStartTime: msg.SecondsSinceStartTime,
-			LastCommitRound:       msg.LastCommitRound,
+		pb = tmcons.Message{
+			Sum: &tmcons.Message_NewRoundStep{
+				NewRoundStep: &tmcons.NewRoundStep{
+					Height:                msg.Height,
+					Round:                 msg.Round,
+					Step:                  uint32(msg.Step),
+					SecondsSinceStartTime: msg.SecondsSinceStartTime,
+					LastCommitRound:       msg.LastCommitRound,
+				},
+			},
 		}
-
 	case *NewValidBlockMessage:
 		pbPartSetHeader := msg.BlockPartSetHeader.ToProto()
 		pbBits := msg.BlockParts.ToProto()
-		pb = &tmcons.NewValidBlock{
-			Height:             msg.Height,
-			Round:              msg.Round,
-			BlockPartSetHeader: pbPartSetHeader,
-			BlockParts:         pbBits,
-			IsCommit:           msg.IsCommit,
+		pb = tmcons.Message{
+			Sum: &tmcons.Message_NewValidBlock{
+				NewValidBlock: &tmcons.NewValidBlock{
+					Height:             msg.Height,
+					Round:              msg.Round,
+					BlockPartSetHeader: pbPartSetHeader,
+					BlockParts:         pbBits,
+					IsCommit:           msg.IsCommit,
+				},
+			},
 		}
-
 	case *ProposalMessage:
 		pbP := msg.Proposal.ToProto()
-		pb = &tmcons.Proposal{
-			Proposal: *pbP,
+		pb = tmcons.Message{
+			Sum: &tmcons.Message_Proposal{
+				Proposal: &tmcons.Proposal{
+					Proposal: *pbP,
+				},
+			},
 		}
-
 	case *ProposalPOLMessage:
 		pbBits := msg.ProposalPOL.ToProto()
-		pb = &tmcons.ProposalPOL{
-			Height:           msg.Height,
-			ProposalPolRound: msg.ProposalPOLRound,
-			ProposalPol:      *pbBits,
+		pb = tmcons.Message{
+			Sum: &tmcons.Message_ProposalPol{
+				ProposalPol: &tmcons.ProposalPOL{
+					Height:           msg.Height,
+					ProposalPolRound: msg.ProposalPOLRound,
+					ProposalPol:      *pbBits,
+				},
+			},
 		}
-
 	case *BlockPartMessage:
 		parts, err := msg.Part.ToProto()
 		if err != nil {
 			return nil, fmt.Errorf("msg to proto error: %w", err)
 		}
-		pb = &tmcons.BlockPart{
-			Height: msg.Height,
-			Round:  msg.Round,
-			Part:   *parts,
+		pb = tmcons.Message{
+			Sum: &tmcons.Message_BlockPart{
+				BlockPart: &tmcons.BlockPart{
+					Height: msg.Height,
+					Round:  msg.Round,
+					Part:   *parts,
+				},
+			},
 		}
-
 	case *VoteMessage:
 		vote := msg.Vote.ToProto()
-		pb = &tmcons.Vote{
-			Vote: vote,
+		pb = tmcons.Message{
+			Sum: &tmcons.Message_Vote{
+				Vote: &tmcons.Vote{
+					Vote: vote,
+				},
+			},
 		}
-
 	case *HasVoteMessage:
-		pb = &tmcons.HasVote{
-			Height: msg.Height,
-			Round:  msg.Round,
-			Type:   msg.Type,
-			Index:  msg.Index,
+		pb = tmcons.Message{
+			Sum: &tmcons.Message_HasVote{
+				HasVote: &tmcons.HasVote{
+					Height: msg.Height,
+					Round:  msg.Round,
+					Type:   msg.Type,
+					Index:  msg.Index,
+				},
+			},
 		}
-
 	case *VoteSetMaj23Message:
 		bi := msg.BlockID.ToProto()
-		pb = &tmcons.VoteSetMaj23{
-			Height:  msg.Height,
-			Round:   msg.Round,
-			Type:    msg.Type,
-			BlockID: bi,
+		pb = tmcons.Message{
+			Sum: &tmcons.Message_VoteSetMaj23{
+				VoteSetMaj23: &tmcons.VoteSetMaj23{
+					Height:  msg.Height,
+					Round:   msg.Round,
+					Type:    msg.Type,
+					BlockID: bi,
+				},
+			},
 		}
-
 	case *VoteSetBitsMessage:
 		bi := msg.BlockID.ToProto()
 		bits := msg.Votes.ToProto()
 
-		vsb := &tmcons.VoteSetBits{
-			Height:  msg.Height,
-			Round:   msg.Round,
-			Type:    msg.Type,
-			BlockID: bi,
+		vsb := &tmcons.Message_VoteSetBits{
+			VoteSetBits: &tmcons.VoteSetBits{
+				Height:  msg.Height,
+				Round:   msg.Round,
+				Type:    msg.Type,
+				BlockID: bi,
+			},
 		}
 
 		if bits != nil {
-			vsb.Votes = *bits
+			vsb.VoteSetBits.Votes = *bits
 		}
 
-		pb = vsb
+		pb = tmcons.Message{
+			Sum: vsb,
+		}
 
 	default:
 		return nil, fmt.Errorf("consensus: message not recognized: %T", msg)
 	}
 
-	return pb, nil
+	return &pb, nil
 }
 
 // MsgFromProto takes a consensus proto message and returns the native go type
-func MsgFromProto(p proto.Message) (Message, error) {
-	if p == nil {
+func MsgFromProto(msg *tmcons.Message) (Message, error) {
+	if msg == nil {
 		return nil, errors.New("consensus: nil message")
 	}
 	var pb Message
 
-	switch msg := p.(type) {
-	case *tmcons.NewRoundStep:
-		rs, err := tmmath.SafeConvertUint8(int64(msg.Step))
+	switch msg := msg.Sum.(type) {
+	case *tmcons.Message_NewRoundStep:
+		rs, err := tmmath.SafeConvertUint8(int64(msg.NewRoundStep.Step))
 		// deny message based on possible overflow
 		if err != nil {
 			return nil, fmt.Errorf("denying message due to possible overflow: %w", err)
 		}
 		pb = &NewRoundStepMessage{
-			Height:                msg.Height,
-			Round:                 msg.Round,
+			Height:                msg.NewRoundStep.Height,
+			Round:                 msg.NewRoundStep.Round,
 			Step:                  cstypes.RoundStepType(rs),
-			SecondsSinceStartTime: msg.SecondsSinceStartTime,
-			LastCommitRound:       msg.LastCommitRound,
+			SecondsSinceStartTime: msg.NewRoundStep.SecondsSinceStartTime,
+			LastCommitRound:       msg.NewRoundStep.LastCommitRound,
 		}
-	case *tmcons.NewValidBlock:
-		pbPartSetHeader, err := types.PartSetHeaderFromProto(&msg.BlockPartSetHeader)
+	case *tmcons.Message_NewValidBlock:
+		pbPartSetHeader, err := types.PartSetHeaderFromProto(&msg.NewValidBlock.BlockPartSetHeader)
 		if err != nil {
 			return nil, fmt.Errorf("parts to proto error: %w", err)
 		}
 
 		pbBits := new(bits.BitArray)
-		pbBits.FromProto(msg.BlockParts)
+		pbBits.FromProto(msg.NewValidBlock.BlockParts)
 
 		pb = &NewValidBlockMessage{
-			Height:             msg.Height,
-			Round:              msg.Round,
+			Height:             msg.NewValidBlock.Height,
+			Round:              msg.NewValidBlock.Round,
 			BlockPartSetHeader: *pbPartSetHeader,
 			BlockParts:         pbBits,
-			IsCommit:           msg.IsCommit,
+			IsCommit:           msg.NewValidBlock.IsCommit,
 		}
-	case *tmcons.Proposal:
-		pbP, err := types.ProposalFromProto(&msg.Proposal)
+	case *tmcons.Message_Proposal:
+		pbP, err := types.ProposalFromProto(&msg.Proposal.Proposal)
 		if err != nil {
 			return nil, fmt.Errorf("proposal msg to proto error: %w", err)
 		}
@@ -162,26 +189,26 @@ func MsgFromProto(p proto.Message) (Message, error) {
 		pb = &ProposalMessage{
 			Proposal: pbP,
 		}
-	case *tmcons.ProposalPOL:
+	case *tmcons.Message_ProposalPol:
 		pbBits := new(bits.BitArray)
-		pbBits.FromProto(&msg.ProposalPol)
+		pbBits.FromProto(&msg.ProposalPol.ProposalPol)
 		pb = &ProposalPOLMessage{
-			Height:           msg.Height,
-			ProposalPOLRound: msg.ProposalPolRound,
+			Height:           msg.ProposalPol.Height,
+			ProposalPOLRound: msg.ProposalPol.ProposalPolRound,
 			ProposalPOL:      pbBits,
 		}
-	case *tmcons.BlockPart:
-		parts, err := types.PartFromProto(&msg.Part)
+	case *tmcons.Message_BlockPart:
+		parts, err := types.PartFromProto(&msg.BlockPart.Part)
 		if err != nil {
 			return nil, fmt.Errorf("blockpart msg to proto error: %w", err)
 		}
 		pb = &BlockPartMessage{
-			Height: msg.Height,
-			Round:  msg.Round,
+			Height: msg.BlockPart.Height,
+			Round:  msg.BlockPart.Round,
 			Part:   parts,
 		}
-	case *tmcons.Vote:
-		vote, err := types.VoteFromProto(msg.Vote)
+	case *tmcons.Message_Vote:
+		vote, err := types.VoteFromProto(msg.Vote.Vote)
 		if err != nil {
 			return nil, fmt.Errorf("vote msg to proto error: %w", err)
 		}
@@ -189,36 +216,36 @@ func MsgFromProto(p proto.Message) (Message, error) {
 		pb = &VoteMessage{
 			Vote: vote,
 		}
-	case *tmcons.HasVote:
+	case *tmcons.Message_HasVote:
 		pb = &HasVoteMessage{
-			Height: msg.Height,
-			Round:  msg.Round,
-			Type:   msg.Type,
-			Index:  msg.Index,
+			Height: msg.HasVote.Height,
+			Round:  msg.HasVote.Round,
+			Type:   msg.HasVote.Type,
+			Index:  msg.HasVote.Index,
 		}
-	case *tmcons.VoteSetMaj23:
-		bi, err := types.BlockIDFromProto(&msg.BlockID)
+	case *tmcons.Message_VoteSetMaj23:
+		bi, err := types.BlockIDFromProto(&msg.VoteSetMaj23.BlockID)
 		if err != nil {
 			return nil, fmt.Errorf("voteSetMaj23 msg to proto error: %w", err)
 		}
 		pb = &VoteSetMaj23Message{
-			Height:  msg.Height,
-			Round:   msg.Round,
-			Type:    msg.Type,
+			Height:  msg.VoteSetMaj23.Height,
+			Round:   msg.VoteSetMaj23.Round,
+			Type:    msg.VoteSetMaj23.Type,
 			BlockID: *bi,
 		}
-	case *tmcons.VoteSetBits:
-		bi, err := types.BlockIDFromProto(&msg.BlockID)
+	case *tmcons.Message_VoteSetBits:
+		bi, err := types.BlockIDFromProto(&msg.VoteSetBits.BlockID)
 		if err != nil {
 			return nil, fmt.Errorf("voteSetBits msg to proto error: %w", err)
 		}
 		bits := new(bits.BitArray)
-		bits.FromProto(&msg.Votes)
+		bits.FromProto(&msg.VoteSetBits.Votes)
 
 		pb = &VoteSetBitsMessage{
-			Height:  msg.Height,
-			Round:   msg.Round,
-			Type:    msg.Type,
+			Height:  msg.VoteSetBits.Height,
+			Round:   msg.VoteSetBits.Round,
+			Type:    msg.VoteSetBits.Type,
 			BlockID: *bi,
 			Votes:   bits,
 		}
@@ -233,6 +260,20 @@ func MsgFromProto(p proto.Message) (Message, error) {
 	return pb, nil
 }
 
+// MustEncode takes the reactors msg, makes it proto and marshals it
+// this mimics `MustMarshalBinaryBare` in that is panics on error
+func MustEncode(msg Message) []byte {
+	pb, err := MsgToProto(msg)
+	if err != nil {
+		panic(err)
+	}
+	enc, err := proto.Marshal(pb)
+	if err != nil {
+		panic(err)
+	}
+	return enc
+}
+
 // WALToProto takes a WAL message and return a proto walMessage and error
 func WALToProto(msg WALMessage) (*tmcons.WALMessage, error) {
 	var pb tmcons.WALMessage
@@ -253,14 +294,10 @@ func WALToProto(msg WALMessage) (*tmcons.WALMessage, error) {
 		if err != nil {
 			return nil, err
 		}
-		if w, ok := consMsg.(p2p.Wrapper); ok {
-			consMsg = w.Wrap()
-		}
-		cm := consMsg.(*tmcons.Message)
 		pb = tmcons.WALMessage{
 			Sum: &tmcons.WALMessage_MsgInfo{
 				MsgInfo: &tmcons.MsgInfo{
-					Msg:    *cm,
+					Msg:    *consMsg,
 					PeerID: string(msg.PeerID),
 				},
 			},
@@ -306,11 +343,7 @@ func WALFromProto(msg *tmcons.WALMessage) (WALMessage, error) {
 			Step:   msg.EventDataRoundState.Step,
 		}
 	case *tmcons.WALMessage_MsgInfo:
-		um, err := msg.MsgInfo.Msg.Unwrap()
-		if err != nil {
-			return nil, fmt.Errorf("unwrap message: %w", err)
-		}
-		walMsg, err := MsgFromProto(um)
+		walMsg, err := MsgFromProto(&msg.MsgInfo.Msg)
 		if err != nil {
 			return nil, fmt.Errorf("msgInfo from proto error: %w", err)
 		}

consensus/msgs_test.go

@@ -71,7 +71,7 @@ func TestMsgToProto(t *testing.T) {
 	testsCases := []struct {
 		testName string
 		msg      Message
-		want     proto.Message
+		want     *tmcons.Message
 		wantErr  bool
 	}{
 		{"successful NewRoundStepMessage", &NewRoundStepMessage{
@@ -80,15 +80,17 @@ func TestMsgToProto(t *testing.T) {
 			Step:                  1,
 			SecondsSinceStartTime: 1,
 			LastCommitRound:       2,
-		}, &tmcons.NewRoundStep{
-			Height:                2,
-			Round:                 1,
-			Step:                  1,
-			SecondsSinceStartTime: 1,
-			LastCommitRound:       2,
-		},
-
-			false},
+		}, &tmcons.Message{
+			Sum: &tmcons.Message_NewRoundStep{
+				NewRoundStep: &tmcons.NewRoundStep{
+					Height:                2,
+					Round:                 1,
+					Step:                  1,
+					SecondsSinceStartTime: 1,
+					LastCommitRound:       2,
+				},
+			},
+		}, false},
 
 		{"successful NewValidBlockMessage", &NewValidBlockMessage{
 			Height:             1,
@@ -96,78 +98,92 @@ func TestMsgToProto(t *testing.T) {
 			BlockPartSetHeader: psh,
 			BlockParts:         bits,
 			IsCommit:           false,
-		}, &tmcons.NewValidBlock{
-			Height:             1,
-			Round:              1,
-			BlockPartSetHeader: pbPsh,
-			BlockParts:         pbBits,
-			IsCommit:           false,
-		},
-
-			false},
+		}, &tmcons.Message{
+			Sum: &tmcons.Message_NewValidBlock{
+				NewValidBlock: &tmcons.NewValidBlock{
+					Height:             1,
+					Round:              1,
+					BlockPartSetHeader: pbPsh,
+					BlockParts:         pbBits,
+					IsCommit:           false,
+				},
+			},
+		}, false},
 		{"successful BlockPartMessage", &BlockPartMessage{
 			Height: 100,
 			Round:  1,
 			Part:   &parts,
-		}, &tmcons.BlockPart{
-			Height: 100,
-			Round:  1,
-			Part:   *pbParts,
-		},
-
-			false},
+		}, &tmcons.Message{
+			Sum: &tmcons.Message_BlockPart{
+				BlockPart: &tmcons.BlockPart{
+					Height: 100,
+					Round:  1,
+					Part:   *pbParts,
+				},
+			},
+		}, false},
 		{"successful ProposalPOLMessage", &ProposalPOLMessage{
 			Height:           1,
 			ProposalPOLRound: 1,
 			ProposalPOL:      bits,
-		}, &tmcons.ProposalPOL{
-			Height:           1,
-			ProposalPolRound: 1,
-			ProposalPol:      *pbBits,
-		},
-			false},
+		}, &tmcons.Message{
+			Sum: &tmcons.Message_ProposalPol{
+				ProposalPol: &tmcons.ProposalPOL{
+					Height:           1,
+					ProposalPolRound: 1,
+					ProposalPol:      *pbBits,
+				},
+			}}, false},
 		{"successful ProposalMessage", &ProposalMessage{
 			Proposal: &proposal,
-		}, &tmcons.Proposal{
-			Proposal: *pbProposal,
-		},
-
-			false},
+		}, &tmcons.Message{
+			Sum: &tmcons.Message_Proposal{
+				Proposal: &tmcons.Proposal{
+					Proposal: *pbProposal,
+				},
+			},
+		}, false},
 		{"successful VoteMessage", &VoteMessage{
 			Vote: vote,
-		}, &tmcons.Vote{
-			Vote: pbVote,
-		},
-
-			false},
+		}, &tmcons.Message{
+			Sum: &tmcons.Message_Vote{
+				Vote: &tmcons.Vote{
+					Vote: pbVote,
+				},
+			},
+		}, false},
 		{"successful VoteSetMaj23", &VoteSetMaj23Message{
 			Height:  1,
 			Round:   1,
 			Type:    1,
 			BlockID: bi,
-		}, &tmcons.VoteSetMaj23{
-			Height:  1,
-			Round:   1,
-			Type:    1,
-			BlockID: pbBi,
-		},
-
-			false},
+		}, &tmcons.Message{
+			Sum: &tmcons.Message_VoteSetMaj23{
+				VoteSetMaj23: &tmcons.VoteSetMaj23{
+					Height:  1,
+					Round:   1,
+					Type:    1,
+					BlockID: pbBi,
+				},
+			},
+		}, false},
 		{"successful VoteSetBits", &VoteSetBitsMessage{
 			Height:  1,
 			Round:   1,
 			Type:    1,
 			BlockID: bi,
 			Votes:   bits,
-		}, &tmcons.VoteSetBits{
-			Height:  1,
-			Round:   1,
-			Type:    1,
-			BlockID: pbBi,
-			Votes:   *pbBits,
-		},
-
-			false},
+		}, &tmcons.Message{
+			Sum: &tmcons.Message_VoteSetBits{
+				VoteSetBits: &tmcons.VoteSetBits{
+					Height:  1,
+					Round:   1,
+					Type:    1,
+					BlockID: pbBi,
+					Votes:   *pbBits,
+				},
+			},
+		}, false},
 		{"failure", nil, &tmcons.Message{}, true},
 	}
 	for _, tt := range testsCases {

consensus/reactor.go

@@ -7,6 +7,8 @@ import (
 	"sync"
 	"time"
 
+	"github.com/cosmos/gogoproto/proto"
+
 	cstypes "github.com/tendermint/tendermint/consensus/types"
 	"github.com/tendermint/tendermint/libs/bits"
 	tmevents "github.com/tendermint/tendermint/libs/events"
@@ -42,6 +44,7 @@ type Reactor struct {
 	conS *State
 
 	mtx      tmsync.RWMutex
+	waitSync bool
 	eventBus *types.EventBus
 	rs       *cstypes.RoundState
 
@@ -52,11 +55,12 @@ type ReactorOption func(*Reactor)
 
 // NewReactor returns a new Reactor with the given
 // consensusState.
-func NewReactor(consensusState *State, options ...ReactorOption) *Reactor {
+func NewReactor(consensusState *State, waitSync bool, options ...ReactorOption) *Reactor {
 	conR := &Reactor{
-		conS:    consensusState,
-		rs:      consensusState.GetRoundState(),
-		Metrics: NopMetrics(),
+		conS:     consensusState,
+		waitSync: waitSync,
+		rs:       consensusState.GetRoundState(),
+		Metrics:  NopMetrics(),
 	}
 	conR.BaseReactor = *p2p.NewBaseReactor("Consensus", conR)
 
@@ -70,12 +74,21 @@ func NewReactor(consensusState *State, options ...ReactorOption) *Reactor {
 // OnStart implements BaseService by subscribing to events, which later will be
 // broadcasted to other peers and starting state if we're not in block sync.
 func (conR *Reactor) OnStart() error {
+	conR.Logger.Info("Reactor ", "waitSync", conR.WaitSync())
+
 	// start routine that computes peer statistics for evaluating peer quality
 	go conR.peerStatsRoutine()
 
 	conR.subscribeToBroadcastEvents()
 	go conR.updateRoundStateRoutine()
 
+	if !conR.WaitSync() {
+		err := conR.conS.Start()
+		if err != nil {
+			return err
+		}
+	}
+
 	return nil
 }
 
@@ -83,34 +96,47 @@ func (conR *Reactor) OnStart() error {
 // state.
 func (conR *Reactor) OnStop() {
 	conR.unsubscribeFromBroadcastEvents()
-	if conR.conS.IsRunning() {
-		if err := conR.conS.Stop(); err != nil {
-			conR.Logger.Error("Error stopping consensus state", "err", err)
-		}
+	if err := conR.conS.Stop(); err != nil {
+		conR.Logger.Error("Error stopping consensus state", "err", err)
+	}
+	if !conR.WaitSync() {
 		conR.conS.Wait()
 	}
 }
 
-func (conR *Reactor) IsConsensusRunning() bool {
-	return conR.conS.IsRunning()
-}
-
 // SwitchToConsensus switches from block_sync mode to consensus mode.
 // It resets the state, turns off block_sync, and starts the consensus state-machine
-func (conR *Reactor) SwitchToConsensus(state sm.State, skipWAL bool) error {
+func (conR *Reactor) SwitchToConsensus(state sm.State, skipWAL bool) {
 	conR.Logger.Info("SwitchToConsensus")
 
 	// We have no votes, so reconstruct LastCommit from SeenCommit.
-	if state.LastBlockHeight > state.InitialHeight {
+	if state.LastBlockHeight > 0 {
 		conR.conS.reconstructLastCommit(state)
 	}
 
+	// NOTE: The line below causes broadcastNewRoundStepRoutine() to broadcast a
+	// NewRoundStepMessage.
 	conR.conS.updateToState(state)
 
+	conR.mtx.Lock()
+	conR.waitSync = false
+	conR.mtx.Unlock()
+	conR.Metrics.BlockSyncing.Set(0)
+	conR.Metrics.StateSyncing.Set(0)
+
 	if skipWAL {
 		conR.conS.doWALCatchup = false
 	}
-	return conR.conS.Start()
+	err := conR.conS.Start()
+	if err != nil {
+		panic(fmt.Sprintf(`Failed to start consensus state: %v
+
+conS:
+%+v
+
+conR:
+%+v`, err, conR.conS, conR))
+	}
 }
 
 // GetChannels implements Reactor
@@ -122,7 +148,6 @@ func (conR *Reactor) GetChannels() []*p2p.ChannelDescriptor {
 			Priority:            6,
 			SendQueueCapacity:   100,
 			RecvMessageCapacity: maxMsgSize,
-			MessageType:         &tmcons.Message{},
 		},
 		{
 			ID: DataChannel, // maybe split between gossiping current block and catchup stuff
@@ -131,7 +156,6 @@ func (conR *Reactor) GetChannels() []*p2p.ChannelDescriptor {
 			SendQueueCapacity:   100,
 			RecvBufferCapacity:  50 * 4096,
 			RecvMessageCapacity: maxMsgSize,
-			MessageType:         &tmcons.Message{},
 		},
 		{
 			ID:                  VoteChannel,
@@ -139,7 +163,6 @@ func (conR *Reactor) GetChannels() []*p2p.ChannelDescriptor {
 			SendQueueCapacity:   100,
 			RecvBufferCapacity:  100 * 100,
 			RecvMessageCapacity: maxMsgSize,
-			MessageType:         &tmcons.Message{},
 		},
 		{
 			ID:                  VoteSetBitsChannel,
@@ -147,7 +170,6 @@ func (conR *Reactor) GetChannels() []*p2p.ChannelDescriptor {
 			SendQueueCapacity:   2,
 			RecvBufferCapacity:  1024,
 			RecvMessageCapacity: maxMsgSize,
-			MessageType:         &tmcons.Message{},
 		},
 	}
 }
@@ -177,7 +199,7 @@ func (conR *Reactor) AddPeer(peer p2p.Peer) {
 
 	// Send our state to peer.
 	// If we're block_syncing, broadcast a RoundStepMessage later upon SwitchToConsensus().
-	if conR.conS.IsRunning() {
+	if !conR.WaitSync() {
 		conR.sendNewRoundStepMessage(peer)
 	}
 }
@@ -201,33 +223,34 @@ func (conR *Reactor) RemovePeer(peer p2p.Peer, reason interface{}) {
 // Peer state updates can happen in parallel, but processing of
 // proposals, block parts, and votes are ordered by the receiveRoutine
 // NOTE: blocks on consensus state for proposals, block parts, and votes
-func (conR *Reactor) Receive(e p2p.Envelope) {
+func (conR *Reactor) Receive(chID byte, src p2p.Peer, msgBytes []byte) {
 	if !conR.IsRunning() {
-		conR.Logger.Debug("Receive", "src", e.Src, "chId", e.ChannelID)
+		conR.Logger.Debug("Receive", "src", src, "chId", chID, "bytes", msgBytes)
 		return
 	}
-	msg, err := MsgFromProto(e.Message)
+
+	msg, err := decodeMsg(msgBytes)
 	if err != nil {
-		conR.Logger.Error("Error decoding message", "src", e.Src, "chId", e.ChannelID, "err", err)
-		conR.Switch.StopPeerForError(e.Src, err)
+		conR.Logger.Error("Error decoding message", "src", src, "chId", chID, "err", err)
+		conR.Switch.StopPeerForError(src, err)
 		return
 	}
 
 	if err = msg.ValidateBasic(); err != nil {
-		conR.Logger.Error("Peer sent us invalid msg", "peer", e.Src, "msg", e.Message, "err", err)
-		conR.Switch.StopPeerForError(e.Src, err)
+		conR.Logger.Error("Peer sent us invalid msg", "peer", src, "msg", msg, "err", err)
+		conR.Switch.StopPeerForError(src, err)
 		return
 	}
 
-	conR.Logger.Debug("Receive", "src", e.Src, "chId", e.ChannelID, "msg", msg)
+	conR.Logger.Debug("Receive", "src", src, "chId", chID, "msg", msg)
 
 	// Get peer states
-	ps, ok := e.Src.Get(types.PeerStateKey).(*PeerState)
+	ps, ok := src.Get(types.PeerStateKey).(*PeerState)
 	if !ok {
-		panic(fmt.Sprintf("Peer %v has no state", e.Src))
+		panic(fmt.Sprintf("Peer %v has no state", src))
 	}
 
-	switch e.ChannelID {
+	switch chID {
 	case StateChannel:
 		switch msg := msg.(type) {
 		case *NewRoundStepMessage:
@@ -235,8 +258,8 @@ func (conR *Reactor) Receive(e p2p.Envelope) {
 			initialHeight := conR.conS.state.InitialHeight
 			conR.conS.mtx.Unlock()
 			if err = msg.ValidateHeight(initialHeight); err != nil {
-				conR.Logger.Error("Peer sent us invalid msg", "peer", e.Src, "msg", msg, "err", err)
-				conR.Switch.StopPeerForError(e.Src, err)
+				conR.Logger.Error("Peer sent us invalid msg", "peer", src, "msg", msg, "err", err)
+				conR.Switch.StopPeerForError(src, err)
 				return
 			}
 			ps.ApplyNewRoundStepMessage(msg)
@@ -255,7 +278,7 @@ func (conR *Reactor) Receive(e p2p.Envelope) {
 			// Peer claims to have a maj23 for some BlockID at H,R,S,
 			err := votes.SetPeerMaj23(msg.Round, msg.Type, ps.peer.ID(), msg.BlockID)
 			if err != nil {
-				conR.Switch.StopPeerForError(e.Src, err)
+				conR.Switch.StopPeerForError(src, err)
 				return
 			}
 			// Respond with a VoteSetBitsMessage showing which votes we have.
@@ -269,44 +292,38 @@ func (conR *Reactor) Receive(e p2p.Envelope) {
 			default:
 				panic("Bad VoteSetBitsMessage field Type. Forgot to add a check in ValidateBasic?")
 			}
-			eMsg := &tmcons.VoteSetBits{
+			src.TrySend(VoteSetBitsChannel, MustEncode(&VoteSetBitsMessage{
 				Height:  msg.Height,
 				Round:   msg.Round,
 				Type:    msg.Type,
-				BlockID: msg.BlockID.ToProto(),
-			}
-			if votes := ourVotes.ToProto(); votes != nil {
-				eMsg.Votes = *votes
-			}
-			e.Src.TrySend(p2p.Envelope{
-				ChannelID: VoteSetBitsChannel,
-				Message:   eMsg,
-			})
+				BlockID: msg.BlockID,
+				Votes:   ourVotes,
+			}))
 		default:
 			conR.Logger.Error(fmt.Sprintf("Unknown message type %v", reflect.TypeOf(msg)))
 		}
 
 	case DataChannel:
-		if !conR.conS.IsRunning() {
+		if conR.WaitSync() {
 			conR.Logger.Info("Ignoring message received during sync", "msg", msg)
 			return
 		}
 		switch msg := msg.(type) {
 		case *ProposalMessage:
 			ps.SetHasProposal(msg.Proposal)
-			conR.conS.peerMsgQueue <- msgInfo{msg, e.Src.ID()}
+			conR.conS.peerMsgQueue <- msgInfo{msg, src.ID()}
 		case *ProposalPOLMessage:
 			ps.ApplyProposalPOLMessage(msg)
 		case *BlockPartMessage:
 			ps.SetHasProposalBlockPart(msg.Height, msg.Round, int(msg.Part.Index))
-			conR.Metrics.BlockParts.With("peer_id", string(e.Src.ID())).Add(1)
-			conR.conS.peerMsgQueue <- msgInfo{msg, e.Src.ID()}
+			conR.Metrics.BlockParts.With("peer_id", string(src.ID())).Add(1)
+			conR.conS.peerMsgQueue <- msgInfo{msg, src.ID()}
 		default:
 			conR.Logger.Error(fmt.Sprintf("Unknown message type %v", reflect.TypeOf(msg)))
 		}
 
 	case VoteChannel:
-		if !conR.conS.IsRunning() {
+		if conR.WaitSync() {
 			conR.Logger.Info("Ignoring message received during sync", "msg", msg)
 			return
 		}
@@ -320,7 +337,7 @@ func (conR *Reactor) Receive(e p2p.Envelope) {
 			ps.EnsureVoteBitArrays(height-1, lastCommitSize)
 			ps.SetHasVote(msg.Vote)
 
-			cs.peerMsgQueue <- msgInfo{msg, e.Src.ID()}
+			cs.peerMsgQueue <- msgInfo{msg, src.ID()}
 
 		default:
 			// don't punish (leave room for soft upgrades)
@@ -328,7 +345,7 @@ func (conR *Reactor) Receive(e p2p.Envelope) {
 		}
 
 	case VoteSetBitsChannel:
-		if !conR.conS.IsRunning() {
+		if conR.WaitSync() {
 			conR.Logger.Info("Ignoring message received during sync", "msg", msg)
 			return
 		}
@@ -359,7 +376,7 @@ func (conR *Reactor) Receive(e p2p.Envelope) {
 		}
 
 	default:
-		conR.Logger.Error(fmt.Sprintf("Unknown chId %X", e.ChannelID))
+		conR.Logger.Error(fmt.Sprintf("Unknown chId %X", chID))
 	}
 }
 
@@ -369,6 +386,13 @@ func (conR *Reactor) SetEventBus(b *types.EventBus) {
 	conR.conS.SetEventBus(b)
 }
 
+// WaitSync returns whether the consensus reactor is waiting for state/block sync.
+func (conR *Reactor) WaitSync() bool {
+	conR.mtx.RLock()
+	defer conR.mtx.RUnlock()
+	return conR.waitSync
+}
+
 //--------------------------------------
 
 // subscribeToBroadcastEvents subscribes for new round steps and votes
@@ -406,39 +430,29 @@ func (conR *Reactor) unsubscribeFromBroadcastEvents() {
 
 func (conR *Reactor) broadcastNewRoundStepMessage(rs *cstypes.RoundState) {
 	nrsMsg := makeRoundStepMessage(rs)
-	conR.Switch.Broadcast(p2p.Envelope{
-		ChannelID: StateChannel,
-		Message:   nrsMsg,
-	})
+	conR.Switch.Broadcast(StateChannel, MustEncode(nrsMsg))
 }
 
 func (conR *Reactor) broadcastNewValidBlockMessage(rs *cstypes.RoundState) {
-	psh := rs.ProposalBlockParts.Header()
-	csMsg := &tmcons.NewValidBlock{
+	csMsg := &NewValidBlockMessage{
 		Height:             rs.Height,
 		Round:              rs.Round,
-		BlockPartSetHeader: psh.ToProto(),
-		BlockParts:         rs.ProposalBlockParts.BitArray().ToProto(),
+		BlockPartSetHeader: rs.ProposalBlockParts.Header(),
+		BlockParts:         rs.ProposalBlockParts.BitArray(),
 		IsCommit:           rs.Step == cstypes.RoundStepCommit,
 	}
-	conR.Switch.Broadcast(p2p.Envelope{
-		ChannelID: StateChannel,
-		Message:   csMsg,
-	})
+	conR.Switch.Broadcast(StateChannel, MustEncode(csMsg))
 }
 
 // Broadcasts HasVoteMessage to peers that care.
 func (conR *Reactor) broadcastHasVoteMessage(vote *types.Vote) {
-	msg := &tmcons.HasVote{
+	msg := &HasVoteMessage{
 		Height: vote.Height,
 		Round:  vote.Round,
 		Type:   vote.Type,
 		Index:  vote.ValidatorIndex,
 	}
-	conR.Switch.Broadcast(p2p.Envelope{
-		ChannelID: StateChannel,
-		Message:   msg,
-	})
+	conR.Switch.Broadcast(StateChannel, MustEncode(msg))
 	/*
 		// TODO: Make this broadcast more selective.
 		for _, peer := range conR.Switch.Peers().List() {
@@ -449,11 +463,7 @@ func (conR *Reactor) broadcastHasVoteMessage(vote *types.Vote) {
 			prs := ps.GetRoundState()
 			if prs.Height == vote.Height {
 				// TODO: Also filter on round?
-				e := p2p.Envelope{
-					ChannelID: StateChannel, struct{ ConsensusMessage }{msg},
-					Message: p,
-				}
-				peer.TrySend(e)
+				peer.TrySend(StateChannel, struct{ ConsensusMessage }{msg})
 			} else {
 				// Height doesn't match
 				// TODO: check a field, maybe CatchupCommitRound?
@@ -463,11 +473,11 @@ func (conR *Reactor) broadcastHasVoteMessage(vote *types.Vote) {
 	*/
 }
 
-func makeRoundStepMessage(rs *cstypes.RoundState) (nrsMsg *tmcons.NewRoundStep) {
-	nrsMsg = &tmcons.NewRoundStep{
+func makeRoundStepMessage(rs *cstypes.RoundState) (nrsMsg *NewRoundStepMessage) {
+	nrsMsg = &NewRoundStepMessage{
 		Height:                rs.Height,
 		Round:                 rs.Round,
-		Step:                  uint32(rs.Step),
+		Step:                  rs.Step,
 		SecondsSinceStartTime: int64(time.Since(rs.StartTime).Seconds()),
 		LastCommitRound:       rs.LastCommit.GetRound(),
 	}
@@ -477,10 +487,7 @@ func makeRoundStepMessage(rs *cstypes.RoundState) (nrsMsg *tmcons.NewRoundStep)
 func (conR *Reactor) sendNewRoundStepMessage(peer p2p.Peer) {
 	rs := conR.getRoundState()
 	nrsMsg := makeRoundStepMessage(rs)
-	peer.Send(p2p.Envelope{
-		ChannelID: StateChannel,
-		Message:   nrsMsg,
-	})
+	peer.Send(StateChannel, MustEncode(nrsMsg))
 }
 
 func (conR *Reactor) updateRoundStateRoutine() {
@@ -512,11 +519,6 @@ OUTER_LOOP:
 		if !peer.IsRunning() || !conR.IsRunning() {
 			return
 		}
-		if !conR.IsConsensusRunning() {
-			time.Sleep(conR.conS.config.PeerGossipSleepDuration)
-			continue OUTER_LOOP
-		}
-
 		rs := conR.getRoundState()
 		prs := ps.GetRoundState()
 
@@ -524,19 +526,13 @@ OUTER_LOOP:
 		if rs.ProposalBlockParts.HasHeader(prs.ProposalBlockPartSetHeader) {
 			if index, ok := rs.ProposalBlockParts.BitArray().Sub(prs.ProposalBlockParts.Copy()).PickRandom(); ok {
 				part := rs.ProposalBlockParts.GetPart(index)
-				parts, err := part.ToProto()
-				if err != nil {
-					panic(err)
+				msg := &BlockPartMessage{
+					Height: rs.Height, // This tells peer that this part applies to us.
+					Round:  rs.Round,  // This tells peer that this part applies to us.
+					Part:   part,
 				}
 				logger.Debug("Sending block part", "height", prs.Height, "round", prs.Round)
-				if peer.Send(p2p.Envelope{
-					ChannelID: DataChannel,
-					Message: &tmcons.BlockPart{
-						Height: rs.Height, // This tells peer that this part applies to us.
-						Round:  rs.Round,  // This tells peer that this part applies to us.
-						Part:   *parts,
-					},
-				}) {
+				if peer.Send(DataChannel, MustEncode(msg)) {
 					ps.SetHasProposalBlockPart(prs.Height, prs.Round, index)
 				}
 				continue OUTER_LOOP
@@ -582,11 +578,9 @@ OUTER_LOOP:
 		if rs.Proposal != nil && !prs.Proposal {
 			// Proposal: share the proposal metadata with peer.
 			{
+				msg := &ProposalMessage{Proposal: rs.Proposal}
 				logger.Debug("Sending proposal", "height", prs.Height, "round", prs.Round)
-				if peer.Send(p2p.Envelope{
-					ChannelID: DataChannel,
-					Message:   &tmcons.Proposal{Proposal: *rs.Proposal.ToProto()},
-				}) {
+				if peer.Send(DataChannel, MustEncode(msg)) {
 					// NOTE[ZM]: A peer might have received different proposal msg so this Proposal msg will be rejected!
 					ps.SetHasProposal(rs.Proposal)
 				}
@@ -596,15 +590,13 @@ OUTER_LOOP:
 			// rs.Proposal was validated, so rs.Proposal.POLRound <= rs.Round,
 			// so we definitely have rs.Votes.Prevotes(rs.Proposal.POLRound).
 			if 0 <= rs.Proposal.POLRound {
+				msg := &ProposalPOLMessage{
+					Height:           rs.Height,
+					ProposalPOLRound: rs.Proposal.POLRound,
+					ProposalPOL:      rs.Votes.Prevotes(rs.Proposal.POLRound).BitArray(),
+				}
 				logger.Debug("Sending POL", "height", prs.Height, "round", prs.Round)
-				peer.Send(p2p.Envelope{
-					ChannelID: DataChannel,
-					Message: &tmcons.ProposalPOL{
-						Height:           rs.Height,
-						ProposalPolRound: rs.Proposal.POLRound,
-						ProposalPol:      *rs.Votes.Prevotes(rs.Proposal.POLRound).BitArray().ToProto(),
-					},
-				})
+				peer.Send(DataChannel, MustEncode(msg))
 			}
 			continue OUTER_LOOP
 		}
@@ -641,27 +633,20 @@ func (conR *Reactor) gossipDataForCatchup(logger log.Logger, rs *cstypes.RoundSt
 			return
 		}
 		// Send the part
-		logger.Debug("Sending block part for catchup", "round", prs.Round, "index", index)
-		pp, err := part.ToProto()
-		if err != nil {
-			logger.Error("Could not convert part to proto", "index", index, "error", err)
-			return
+		msg := &BlockPartMessage{
+			Height: prs.Height, // Not our height, so it doesn't matter.
+			Round:  prs.Round,  // Not our height, so it doesn't matter.
+			Part:   part,
 		}
-		if peer.Send(p2p.Envelope{
-			ChannelID: DataChannel,
-			Message: &tmcons.BlockPart{
-				Height: prs.Height, // Not our height, so it doesn't matter.
-				Round:  prs.Round,  // Not our height, so it doesn't matter.
-				Part:   *pp,
-			},
-		}) {
+		logger.Debug("Sending block part for catchup", "round", prs.Round, "index", index)
+		if peer.Send(DataChannel, MustEncode(msg)) {
 			ps.SetHasProposalBlockPart(prs.Height, prs.Round, index)
 		} else {
 			logger.Debug("Sending block part for catchup failed")
 		}
 		return
 	}
-
+	//  logger.Info("No parts to send in catch-up, sleeping")
 	time.Sleep(conR.conS.config.PeerGossipSleepDuration)
 }
 
@@ -671,16 +656,12 @@ func (conR *Reactor) gossipVotesRoutine(peer p2p.Peer, ps *PeerState) {
 	// Simple hack to throttle logs upon sleep.
 	var sleeping = 0
 
+OUTER_LOOP:
 	for {
 		// Manage disconnects from self or peer.
 		if !peer.IsRunning() || !conR.IsRunning() {
 			return
 		}
-		if !conR.IsConsensusRunning() {
-			time.Sleep(conR.conS.config.PeerGossipSleepDuration)
-			continue
-		}
-
 		rs := conR.getRoundState()
 		prs := ps.GetRoundState()
 
@@ -691,11 +672,14 @@ func (conR *Reactor) gossipVotesRoutine(peer p2p.Peer, ps *PeerState) {
 			sleeping = 0
 		}
 
+		// logger.Debug("gossipVotesRoutine", "rsHeight", rs.Height, "rsRound", rs.Round,
+		// "prsHeight", prs.Height, "prsRound", prs.Round, "prsStep", prs.Step)
+
 		// If height matches, then send LastCommit, Prevotes, Precommits.
 		if rs.Height == prs.Height {
 			heightLogger := logger.With("height", prs.Height)
 			if conR.gossipVotesForHeight(heightLogger, rs, prs, ps) {
-				continue
+				continue OUTER_LOOP
 			}
 		}
 
@@ -704,7 +688,7 @@ func (conR *Reactor) gossipVotesRoutine(peer p2p.Peer, ps *PeerState) {
 		if prs.Height != 0 && rs.Height == prs.Height+1 {
 			if ps.PickSendVote(rs.LastCommit) {
 				logger.Debug("Picked rs.LastCommit to send", "height", prs.Height)
-				continue
+				continue OUTER_LOOP
 			}
 		}
 
@@ -717,7 +701,7 @@ func (conR *Reactor) gossipVotesRoutine(peer p2p.Peer, ps *PeerState) {
 			if commit := conR.conS.blockStore.LoadBlockCommit(prs.Height); commit != nil {
 				if ps.PickSendVote(commit) {
 					logger.Debug("Picked Catchup commit to send", "height", prs.Height)
-					continue
+					continue OUTER_LOOP
 				}
 			}
 		}
@@ -734,7 +718,7 @@ func (conR *Reactor) gossipVotesRoutine(peer p2p.Peer, ps *PeerState) {
 		}
 
 		time.Sleep(conR.conS.config.PeerGossipSleepDuration)
-		continue
+		continue OUTER_LOOP
 	}
 }
 
@@ -808,27 +792,18 @@ OUTER_LOOP:
 			return
 		}
 
-		if !conR.IsConsensusRunning() {
-			time.Sleep(conR.conS.config.PeerQueryMaj23SleepDuration)
-			continue OUTER_LOOP
-		}
-
 		// Maybe send Height/Round/Prevotes
 		{
 			rs := conR.getRoundState()
 			prs := ps.GetRoundState()
 			if rs.Height == prs.Height {
 				if maj23, ok := rs.Votes.Prevotes(prs.Round).TwoThirdsMajority(); ok {
-
-					peer.TrySend(p2p.Envelope{
-						ChannelID: StateChannel,
-						Message: &tmcons.VoteSetMaj23{
-							Height:  prs.Height,
-							Round:   prs.Round,
-							Type:    tmproto.PrevoteType,
-							BlockID: maj23.ToProto(),
-						},
-					})
+					peer.TrySend(StateChannel, MustEncode(&VoteSetMaj23Message{
+						Height:  prs.Height,
+						Round:   prs.Round,
+						Type:    tmproto.PrevoteType,
+						BlockID: maj23,
+					}))
 					time.Sleep(conR.conS.config.PeerQueryMaj23SleepDuration)
 				}
 			}
@@ -840,15 +815,12 @@ OUTER_LOOP:
 			prs := ps.GetRoundState()
 			if rs.Height == prs.Height {
 				if maj23, ok := rs.Votes.Precommits(prs.Round).TwoThirdsMajority(); ok {
-					peer.TrySend(p2p.Envelope{
-						ChannelID: StateChannel,
-						Message: &tmcons.VoteSetMaj23{
-							Height:  prs.Height,
-							Round:   prs.Round,
-							Type:    tmproto.PrecommitType,
-							BlockID: maj23.ToProto(),
-						},
-					})
+					peer.TrySend(StateChannel, MustEncode(&VoteSetMaj23Message{
+						Height:  prs.Height,
+						Round:   prs.Round,
+						Type:    tmproto.PrecommitType,
+						BlockID: maj23,
+					}))
 					time.Sleep(conR.conS.config.PeerQueryMaj23SleepDuration)
 				}
 			}
@@ -860,16 +832,12 @@ OUTER_LOOP:
 			prs := ps.GetRoundState()
 			if rs.Height == prs.Height && prs.ProposalPOLRound >= 0 {
 				if maj23, ok := rs.Votes.Prevotes(prs.ProposalPOLRound).TwoThirdsMajority(); ok {
-
-					peer.TrySend(p2p.Envelope{
-						ChannelID: StateChannel,
-						Message: &tmcons.VoteSetMaj23{
-							Height:  prs.Height,
-							Round:   prs.ProposalPOLRound,
-							Type:    tmproto.PrevoteType,
-							BlockID: maj23.ToProto(),
-						},
-					})
+					peer.TrySend(StateChannel, MustEncode(&VoteSetMaj23Message{
+						Height:  prs.Height,
+						Round:   prs.ProposalPOLRound,
+						Type:    tmproto.PrevoteType,
+						BlockID: maj23,
+					}))
 					time.Sleep(conR.conS.config.PeerQueryMaj23SleepDuration)
 				}
 			}
@@ -884,20 +852,19 @@ OUTER_LOOP:
 			if prs.CatchupCommitRound != -1 && prs.Height > 0 && prs.Height <= conR.conS.blockStore.Height() &&
 				prs.Height >= conR.conS.blockStore.Base() {
 				if commit := conR.conS.LoadCommit(prs.Height); commit != nil {
-					peer.TrySend(p2p.Envelope{
-						ChannelID: StateChannel,
-						Message: &tmcons.VoteSetMaj23{
-							Height:  prs.Height,
-							Round:   commit.Round,
-							Type:    tmproto.PrecommitType,
-							BlockID: commit.BlockID.ToProto(),
-						},
-					})
+					peer.TrySend(StateChannel, MustEncode(&VoteSetMaj23Message{
+						Height:  prs.Height,
+						Round:   commit.Round,
+						Type:    tmproto.PrecommitType,
+						BlockID: commit.BlockID,
+					}))
 					time.Sleep(conR.conS.config.PeerQueryMaj23SleepDuration)
 				}
 			}
 		}
 
+		time.Sleep(conR.conS.config.PeerQueryMaj23SleepDuration)
+
 		continue OUTER_LOOP
 	}
 }
@@ -1104,13 +1071,9 @@ func (ps *PeerState) SetHasProposalBlockPart(height int64, round int32, index in
 // Returns true if vote was sent.
 func (ps *PeerState) PickSendVote(votes types.VoteSetReader) bool {
 	if vote, ok := ps.PickVoteToSend(votes); ok {
+		msg := &VoteMessage{vote}
 		ps.logger.Debug("Sending vote message", "ps", ps, "vote", vote)
-		if ps.peer.Send(p2p.Envelope{
-			ChannelID: VoteChannel,
-			Message: &tmcons.Vote{
-				Vote: vote.ToProto(),
-			},
-		}) {
+		if ps.peer.Send(VoteChannel, MustEncode(msg)) {
 			ps.SetHasVote(vote)
 			return true
 		}
@@ -1476,6 +1439,15 @@ func init() {
 	tmjson.RegisterType(&VoteSetBitsMessage{}, "tendermint/VoteSetBits")
 }
 
+func decodeMsg(bz []byte) (msg Message, err error) {
+	pb := &tmcons.Message{}
+	if err = proto.Unmarshal(bz, pb); err != nil {
+		return msg, err
+	}
+
+	return MsgFromProto(pb)
+}
+
 //-------------------------------------
 
 // NewRoundStepMessage is sent for every step taken in the ConsensusState.

consensus/reactor_test.go

@@ -33,7 +33,6 @@ import (
 	mempoolv1 "github.com/tendermint/tendermint/mempool/v1"
 	"github.com/tendermint/tendermint/p2p"
 	p2pmock "github.com/tendermint/tendermint/p2p/mock"
-	tmcons "github.com/tendermint/tendermint/proto/tendermint/consensus"
 	tmproto "github.com/tendermint/tendermint/proto/tendermint/types"
 	sm "github.com/tendermint/tendermint/state"
 	statemocks "github.com/tendermint/tendermint/state/mocks"
@@ -55,8 +54,9 @@ func startConsensusNet(t *testing.T, css []*State, n int) (
 	blocksSubs := make([]types.Subscription, 0)
 	eventBuses := make([]*types.EventBus, n)
 	for i := 0; i < n; i++ {
-		// Note, we dont start the consensus states
-		reactors[i] = NewReactor(css[i])
+		/*logger, err := tmflags.ParseLogLevel("consensus:info,*:error", logger, "info")
+		if err != nil {	t.Fatal(err)}*/
+		reactors[i] = NewReactor(css[i], true) // so we dont start the consensus states
 		reactors[i].SetLogger(css[i].Logger)
 
 		// eventBus is already started with the cs
@@ -87,8 +87,7 @@ func startConsensusNet(t *testing.T, css []*State, n int) (
 	// TODO: is this still true with new pubsub?
 	for i := 0; i < n; i++ {
 		s := reactors[i].conS.GetState()
-		err := reactors[i].SwitchToConsensus(s, false)
-		require.NoError(t, err)
+		reactors[i].SwitchToConsensus(s, false)
 	}
 	return reactors, blocksSubs, eventBuses
 }
@@ -113,7 +112,7 @@ func stopConsensusNet(logger log.Logger, reactors []*Reactor, eventBuses []*type
 // Ensure a testnet makes blocks
 func TestReactorBasic(t *testing.T) {
 	N := 4
-	css, cleanup := randConsensusNet(t, N, "consensus_reactor_test", newMockTickerFunc(true), newKVStore)
+	css, cleanup := randConsensusNet(N, "consensus_reactor_test", newMockTickerFunc(true), newKVStore)
 	defer cleanup()
 	reactors, blocksSubs, eventBuses := startConsensusNet(t, css, N)
 	defer stopConsensusNet(log.TestingLogger(), reactors, eventBuses)
@@ -135,8 +134,6 @@ func TestReactorWithEvidence(t *testing.T) {
 	// css := randConsensusNet(N, "consensus_reactor_test", newMockTickerFunc(true), newKVStore)
 
 	genDoc, privVals := randGenesisDoc(nValidators, false, 30)
-	state, err := sm.MakeGenesisState(genDoc)
-	require.NoError(t, err)
 	css := make([]*State, nValidators)
 	logger := consensusLogger()
 	for i := 0; i < nValidators; i++ {
@@ -144,6 +141,7 @@ func TestReactorWithEvidence(t *testing.T) {
 		stateStore := sm.NewStore(stateDB, sm.StoreOptions{
 			DiscardABCIResponses: false,
 		})
+		state, _ := stateStore.LoadFromDBOrGenesisDoc(genDoc)
 		thisConfig := ResetConfig(fmt.Sprintf("%s_%d", testName, i))
 		defer os.RemoveAll(thisConfig.RootDir)
 		ensureDir(path.Dir(thisConfig.Consensus.WalFile()), 0700) // dir for wal
@@ -204,7 +202,7 @@ func TestReactorWithEvidence(t *testing.T) {
 
 		// Make State
 		blockExec := sm.NewBlockExecutor(stateStore, log.TestingLogger(), proxyAppConnCon, mempool, evpool, blockStore)
-		cs := NewState(thisConfig.Consensus, blockExec, blockStore, mempool, evpool2, WithState(state.Copy()))
+		cs := NewState(thisConfig.Consensus, state, blockExec, blockStore, mempool, evpool2)
 		cs.SetLogger(log.TestingLogger().With("module", "consensus"))
 		cs.SetPrivValidator(pv)
 
@@ -238,7 +236,7 @@ func TestReactorWithEvidence(t *testing.T) {
 // Ensure a testnet makes blocks when there are txs
 func TestReactorCreatesBlockWhenEmptyBlocksFalse(t *testing.T) {
 	N := 4
-	css, cleanup := randConsensusNet(t, N, "consensus_reactor_test", newMockTickerFunc(true), newKVStore,
+	css, cleanup := randConsensusNet(N, "consensus_reactor_test", newMockTickerFunc(true), newKVStore,
 		func(c *cfg.Config) {
 			c.Consensus.CreateEmptyBlocks = false
 		})
@@ -259,7 +257,7 @@ func TestReactorCreatesBlockWhenEmptyBlocksFalse(t *testing.T) {
 
 func TestReactorReceiveDoesNotPanicIfAddPeerHasntBeenCalledYet(t *testing.T) {
 	N := 1
-	css, cleanup := randConsensusNet(t, N, "consensus_reactor_test", newMockTickerFunc(true), newKVStore)
+	css, cleanup := randConsensusNet(N, "consensus_reactor_test", newMockTickerFunc(true), newKVStore)
 	defer cleanup()
 	reactors, _, eventBuses := startConsensusNet(t, css, N)
 	defer stopConsensusNet(log.TestingLogger(), reactors, eventBuses)
@@ -267,25 +265,22 @@ func TestReactorReceiveDoesNotPanicIfAddPeerHasntBeenCalledYet(t *testing.T) {
 	var (
 		reactor = reactors[0]
 		peer    = p2pmock.NewPeer(nil)
+		msg     = MustEncode(&HasVoteMessage{Height: 1,
+			Round: 1, Index: 1, Type: tmproto.PrevoteType})
 	)
 
 	reactor.InitPeer(peer)
 
 	// simulate switch calling Receive before AddPeer
 	assert.NotPanics(t, func() {
-		reactor.Receive(p2p.Envelope{
-			ChannelID: StateChannel,
-			Src:       peer,
-			Message: &tmcons.HasVote{Height: 1,
-				Round: 1, Index: 1, Type: tmproto.PrevoteType},
-		})
+		reactor.Receive(StateChannel, peer, msg)
 		reactor.AddPeer(peer)
 	})
 }
 
 func TestReactorReceivePanicsIfInitPeerHasntBeenCalledYet(t *testing.T) {
 	N := 1
-	css, cleanup := randConsensusNet(t, N, "consensus_reactor_test", newMockTickerFunc(true), newKVStore)
+	css, cleanup := randConsensusNet(N, "consensus_reactor_test", newMockTickerFunc(true), newKVStore)
 	defer cleanup()
 	reactors, _, eventBuses := startConsensusNet(t, css, N)
 	defer stopConsensusNet(log.TestingLogger(), reactors, eventBuses)
@@ -293,25 +288,22 @@ func TestReactorReceivePanicsIfInitPeerHasntBeenCalledYet(t *testing.T) {
 	var (
 		reactor = reactors[0]
 		peer    = p2pmock.NewPeer(nil)
+		msg     = MustEncode(&HasVoteMessage{Height: 1,
+			Round: 1, Index: 1, Type: tmproto.PrevoteType})
 	)
 
 	// we should call InitPeer here
 
 	// simulate switch calling Receive before AddPeer
 	assert.Panics(t, func() {
-		reactor.Receive(p2p.Envelope{
-			ChannelID: StateChannel,
-			Src:       peer,
-			Message: &tmcons.HasVote{Height: 1,
-				Round: 1, Index: 1, Type: tmproto.PrevoteType},
-		})
+		reactor.Receive(StateChannel, peer, msg)
 	})
 }
 
 // Test we record stats about votes and block parts from other peers.
 func TestReactorRecordsVotesAndBlockParts(t *testing.T) {
 	N := 4
-	css, cleanup := randConsensusNet(t, N, "consensus_reactor_test", newMockTickerFunc(true), newKVStore)
+	css, cleanup := randConsensusNet(N, "consensus_reactor_test", newMockTickerFunc(true), newKVStore)
 	defer cleanup()
 	reactors, blocksSubs, eventBuses := startConsensusNet(t, css, N)
 	defer stopConsensusNet(log.TestingLogger(), reactors, eventBuses)
@@ -337,7 +329,6 @@ func TestReactorVotingPowerChange(t *testing.T) {
 	nVals := 4
 	logger := log.TestingLogger()
 	css, cleanup := randConsensusNet(
-		t,
 		nVals,
 		"consensus_voting_power_changes_test",
 		newMockTickerFunc(true),
@@ -533,7 +524,7 @@ func TestReactorValidatorSetChanges(t *testing.T) {
 // Check we can make blocks with skip_timeout_commit=false
 func TestReactorWithTimeoutCommit(t *testing.T) {
 	N := 4
-	css, cleanup := randConsensusNet(t, N, "consensus_reactor_with_timeout_commit_test", newMockTickerFunc(false), newKVStore)
+	css, cleanup := randConsensusNet(N, "consensus_reactor_with_timeout_commit_test", newMockTickerFunc(false), newKVStore)
 	defer cleanup()
 	// override default SkipTimeoutCommit == true for tests
 	for i := 0; i < N; i++ {

consensus/replay_file.go

@@ -129,8 +129,8 @@ func (pb *playback) replayReset(count int, newStepSub types.Subscription) error
 	}
 	pb.cs.Wait()
 
-	newCS := NewState(pb.cs.config, pb.cs.blockExec,
-		pb.cs.blockStore, pb.cs.txNotifier, pb.cs.evpool, WithState(pb.genesisState.Copy()))
+	newCS := NewState(pb.cs.config, pb.genesisState.Copy(), pb.cs.blockExec,
+		pb.cs.blockStore, pb.cs.txNotifier, pb.cs.evpool)
 	newCS.SetEventBus(pb.cs.eventBus)
 	newCS.startForReplay()
 
@@ -332,8 +332,8 @@ func newConsensusStateForReplay(config cfg.BaseConfig, csConfig *cfg.ConsensusCo
 	mempool, evpool := emptyMempool{}, sm.EmptyEvidencePool{}
 	blockExec := sm.NewBlockExecutor(stateStore, log.TestingLogger(), proxyApp.Consensus(), mempool, evpool, blockStore)
 
-	consensusState := NewState(csConfig, blockExec,
-		blockStore, mempool, evpool, WithState(state.Copy()))
+	consensusState := NewState(csConfig, state.Copy(), blockExec,
+		blockStore, mempool, evpool)
 
 	consensusState.SetEventBus(eventBus)
 	return consensusState

consensus/replay_test.go

@@ -67,8 +67,7 @@ func TestMain(m *testing.M) {
 func startNewStateAndWaitForBlock(t *testing.T, consensusReplayConfig *cfg.Config,
 	lastBlockHeight int64, blockDB dbm.DB, stateStore sm.Store) {
 	logger := log.TestingLogger()
-	state, err := stateStore.LoadFromDBOrGenesisFile(consensusReplayConfig.GenesisFile())
-	require.NoError(t, err)
+	state, _ := stateStore.LoadFromDBOrGenesisFile(consensusReplayConfig.GenesisFile())
 	privValidator := loadPrivValidator(consensusReplayConfig)
 	cs := newStateWithConfigAndBlockStore(
 		consensusReplayConfig,
@@ -82,7 +81,7 @@ func startNewStateAndWaitForBlock(t *testing.T, consensusReplayConfig *cfg.Confi
 	bytes, _ := os.ReadFile(cs.config.WalFile())
 	t.Logf("====== WAL: \n\r%X\n", bytes)
 
-	err = cs.Start()
+	err := cs.Start()
 	require.NoError(t, err)
 	defer func() {
 		if err := cs.Stop(); err != nil {
@@ -556,40 +555,40 @@ func TestSimulateValidatorsChange(t *testing.T) {
 // Sync from scratch
 func TestHandshakeReplayAll(t *testing.T) {
 	for _, m := range modes {
-		testHandshakeReplay(t, 0, m, false)
+		testHandshakeReplay(t, config, 0, m, false)
 	}
 	for _, m := range modes {
-		testHandshakeReplay(t, 0, m, true)
+		testHandshakeReplay(t, config, 0, m, true)
 	}
 }
 
 // Sync many, not from scratch
 func TestHandshakeReplaySome(t *testing.T) {
 	for _, m := range modes {
-		testHandshakeReplay(t, 2, m, false)
+		testHandshakeReplay(t, config, 2, m, false)
 	}
 	for _, m := range modes {
-		testHandshakeReplay(t, 2, m, true)
+		testHandshakeReplay(t, config, 2, m, true)
 	}
 }
 
 // Sync from lagging by one
 func TestHandshakeReplayOne(t *testing.T) {
 	for _, m := range modes {
-		testHandshakeReplay(t, numBlocks-1, m, false)
+		testHandshakeReplay(t, config, numBlocks-1, m, false)
 	}
 	for _, m := range modes {
-		testHandshakeReplay(t, numBlocks-1, m, true)
+		testHandshakeReplay(t, config, numBlocks-1, m, true)
 	}
 }
 
 // Sync from caught up
 func TestHandshakeReplayNone(t *testing.T) {
 	for _, m := range modes {
-		testHandshakeReplay(t, numBlocks, m, false)
+		testHandshakeReplay(t, config, numBlocks, m, false)
 	}
 	for _, m := range modes {
-		testHandshakeReplay(t, numBlocks, m, true)
+		testHandshakeReplay(t, config, numBlocks, m, true)
 	}
 }
 
@@ -661,27 +660,25 @@ 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, testValidatorsChange bool) {
-	var (
-		chain        []*types.Block
-		commits      []*types.Commit
-		store        *mockBlockStore
-		stateDB      dbm.DB
-		genesisState sm.State
-		config       *cfg.Config
-	)
+func testHandshakeReplay(t *testing.T, config *cfg.Config, nBlocks int, mode uint, testValidatorsChange bool) {
+	var chain []*types.Block
+	var commits []*types.Commit
+	var store *mockBlockStore
+	var stateDB dbm.DB
+	var genesisState sm.State
 	if testValidatorsChange {
-		config = ResetConfig(fmt.Sprintf("%s_%v_m", t.Name(), mode))
-		defer os.RemoveAll(config.RootDir)
+		testConfig := ResetConfig(fmt.Sprintf("%s_%v_m", t.Name(), mode))
+		defer os.RemoveAll(testConfig.RootDir)
 		stateDB = dbm.NewMemDB()
 
 		genesisState = sim.GenesisState
+		config = sim.Config
 		chain = append([]*types.Block{}, sim.Chain...) // copy chain
 		commits = sim.Commits
 		store = newMockBlockStore(t, config, genesisState.ConsensusParams)
 	} else { // test single node
-		config = ResetConfig(fmt.Sprintf("%s_%v_s", t.Name(), mode))
-		defer os.RemoveAll(config.RootDir)
+		testConfig := ResetConfig(fmt.Sprintf("%s_%v_s", t.Name(), mode))
+		defer os.RemoveAll(testConfig.RootDir)
 		walBody, err := WALWithNBlocks(t, numBlocks)
 		require.NoError(t, err)
 		walFile := tempWALWithData(walBody)
@@ -738,7 +735,7 @@ func testHandshakeReplay(t *testing.T, nBlocks int, mode uint, testValidatorsCha
 	// Prune block store if requested
 	expectError := false
 	if mode == 3 {
-		pruned, _, err := store.PruneBlocks(2, state)
+		pruned, err := store.PruneBlocks(2)
 		require.NoError(t, err)
 		require.EqualValues(t, 1, pruned)
 		expectError = int64(nBlocks) < 2
@@ -814,11 +811,14 @@ func buildAppStateFromChain(t *testing.T, proxyApp proxy.AppConns, stateStore sm
 
 	state.Version.Consensus.App = kvstore.ProtocolVersion // simulate handshake, receive app version
 	validators := types.TM2PB.ValidatorUpdates(state.Validators)
-	_, err := proxyApp.Consensus().InitChainSync(abci.RequestInitChain{
+	if _, err := proxyApp.Consensus().InitChainSync(abci.RequestInitChain{
 		Validators: validators,
-	})
-	require.NoError(t, err)
-	require.NoError(t, stateStore.Save(state))
+	}); err != nil {
+		panic(err)
+	}
+	if err := stateStore.Save(state); err != nil { // save height 1's validatorsInfo
+		panic(err)
+	}
 	switch mode {
 	case 0:
 		for i := 0; i < nBlocks; i++ {
@@ -1185,8 +1185,7 @@ func (bs *mockBlockStore) LoadSeenCommit(height int64) *types.Commit {
 	return bs.commits[height-1]
 }
 
-func (bs *mockBlockStore) PruneBlocks(height int64, state sm.State) (uint64, int64, error) {
-	evidencePoint := height
+func (bs *mockBlockStore) PruneBlocks(height int64) (uint64, error) {
 	pruned := uint64(0)
 	for i := int64(0); i < height-1; i++ {
 		bs.chain[i] = nil
@@ -1194,7 +1193,7 @@ func (bs *mockBlockStore) PruneBlocks(height int64, state sm.State) (uint64, int
 		pruned++
 	}
 	bs.base = height
-	return pruned, evidencePoint, nil
+	return pruned, nil
 }
 
 func (bs *mockBlockStore) DeleteLatestBlock() error { return nil }

consensus/state.go

@@ -148,6 +148,7 @@ type StateOption func(*State)
 // NewState returns a new State.
 func NewState(
 	config *cfg.ConsensusConfig,
+	state sm.State,
 	blockExec *sm.BlockExecutor,
 	blockStore sm.BlockStore,
 	txNotifier txNotifier,
@@ -176,6 +177,13 @@ func NewState(
 	cs.doPrevote = cs.defaultDoPrevote
 	cs.setProposal = cs.defaultSetProposal
 
+	// We have no votes, so reconstruct LastCommit from SeenCommit.
+	if state.LastBlockHeight > 0 {
+		cs.reconstructLastCommit(state)
+	}
+
+	cs.updateToState(state)
+
 	// NOTE: we do not call scheduleRound0 yet, we do that upon Start()
 
 	cs.BaseService = *service.NewBaseService(nil, "State", cs)
@@ -199,19 +207,10 @@ func (cs *State) SetEventBus(b *types.EventBus) {
 }
 
 // StateMetrics sets the metrics.
-func WithMetrics(metrics *Metrics) StateOption {
+func StateMetrics(metrics *Metrics) StateOption {
 	return func(cs *State) { cs.metrics = metrics }
 }
 
-func WithState(state sm.State) StateOption {
-	return func(cs *State) {
-		if state.LastBlockHeight > 0 {
-			cs.reconstructLastCommit(state)
-		}
-		cs.updateToState(state)
-	}
-}
-
 // String returns a string.
 func (cs *State) String() string {
 	// better not to access shared variables
@@ -298,10 +297,6 @@ func (cs *State) LoadCommit(height int64) *types.Commit {
 // OnStart loads the latest state via the WAL, and starts the timeout and
 // receive routines.
 func (cs *State) OnStart() error {
-	if cs.state.IsEmpty() {
-		return errors.New("no state to commence consensus on")
-	}
-
 	// We may set the WAL in testing before calling Start, so only OpenWAL if its
 	// still the nilWAL.
 	if _, ok := cs.wal.(nilWAL); ok {
@@ -617,7 +612,7 @@ func (cs *State) updateToState(state sm.State) {
 		// signal the new round step, because other services (eg. txNotifier)
 		// depend on having an up-to-date peer state!
 		if state.LastBlockHeight <= cs.state.LastBlockHeight {
-			cs.Logger.Info(
+			cs.Logger.Debug(
 				"ignoring updateToState()",
 				"new_height", state.LastBlockHeight+1,
 				"old_height", cs.state.LastBlockHeight+1,
@@ -2280,10 +2275,11 @@ func (cs *State) signAddVote(msgType tmproto.SignedMsgType, hash []byte, header
 		return nil
 	}
 
+	// TODO: pass pubKey to signVote
 	vote, err := cs.signVote(msgType, hash, header)
 	if err == nil {
 		cs.sendInternalMessage(msgInfo{&VoteMessage{vote}, ""})
-		cs.Logger.Info("signed and pushed vote", "height", cs.Height, "round", cs.Round, "vote", vote)
+		cs.Logger.Debug("signed and pushed vote", "height", cs.Height, "round", cs.Round, "vote", vote)
 		return vote
 	}
 

consensus/types/height_vote_set.go

@@ -121,7 +121,7 @@ func (hvs *HeightVoteSet) AddVote(vote *types.Vote, peerID p2p.ID) (added bool,
 		return
 	}
 	voteSet := hvs.getVoteSet(vote.Round, vote.Type)
-	if voteSet.IsEmpty() {
+	if voteSet == nil {
 		if rndz := hvs.peerCatchupRounds[peerID]; len(rndz) < 2 {
 			hvs.addRound(vote.Round)
 			voteSet = hvs.getVoteSet(vote.Round, vote.Type)
@@ -166,7 +166,7 @@ func (hvs *HeightVoteSet) POLInfo() (polRound int32, polBlockID types.BlockID) {
 func (hvs *HeightVoteSet) getVoteSet(round int32, voteType tmproto.SignedMsgType) *types.VoteSet {
 	rvs, ok := hvs.roundVoteSets[round]
 	if !ok {
-		return &types.VoteSet{}
+		return nil
 	}
 	switch voteType {
 	case tmproto.PrevoteType:

consensus/types/height_vote_set_test.go

@@ -5,7 +5,6 @@ import (
 	"os"
 	"testing"
 
-	"github.com/stretchr/testify/require"
 	cfg "github.com/tendermint/tendermint/config"
 	"github.com/tendermint/tendermint/crypto/tmhash"
 	"github.com/tendermint/tendermint/internal/test"
@@ -31,23 +30,30 @@ func TestPeerCatchupRounds(t *testing.T) {
 
 	vote999_0 := makeVoteHR(t, 1, 0, 999, privVals)
 	added, err := hvs.AddVote(vote999_0, "peer1")
-	require.NoError(t, err)
-	require.True(t, added)
+	if !added || err != nil {
+		t.Error("Expected to successfully add vote from peer", added, err)
+	}
 
 	vote1000_0 := makeVoteHR(t, 1, 0, 1000, privVals)
 	added, err = hvs.AddVote(vote1000_0, "peer1")
-	require.NoError(t, err)
-	require.True(t, added)
+	if !added || err != nil {
+		t.Error("Expected to successfully add vote from peer", added, err)
+	}
 
 	vote1001_0 := makeVoteHR(t, 1, 0, 1001, privVals)
 	added, err = hvs.AddVote(vote1001_0, "peer1")
-	require.Error(t, err)
-	require.Equal(t, ErrGotVoteFromUnwantedRound, err)
-	require.False(t, added)
+	if err != ErrGotVoteFromUnwantedRound {
+		t.Errorf("expected GotVoteFromUnwantedRoundError, but got %v", err)
+	}
+	if added {
+		t.Error("Expected to *not* add vote from peer, too many catchup rounds.")
+	}
 
 	added, err = hvs.AddVote(vote1001_0, "peer2")
-	require.NoError(t, err)
-	require.True(t, added)
+	if !added || err != nil {
+		t.Error("Expected to successfully add vote from another peer")
+	}
+
 }
 
 func makeVoteHR(t *testing.T, height int64, valIndex, round int32, privVals []types.PrivValidator) *types.Vote {

consensus/wal_generator.go

@@ -86,7 +86,7 @@ func WALGenerateNBlocks(t *testing.T, wr io.Writer, numBlocks int) (err error) {
 	mempool := emptyMempool{}
 	evpool := sm.EmptyEvidencePool{}
 	blockExec := sm.NewBlockExecutor(stateStore, log.TestingLogger(), proxyApp.Consensus(), mempool, evpool, blockStore)
-	consensusState := NewState(config.Consensus, blockExec, blockStore, mempool, evpool, WithState(state.Copy()))
+	consensusState := NewState(config.Consensus, state.Copy(), blockExec, blockStore, mempool, evpool)
 	consensusState.SetLogger(logger)
 	consensusState.SetEventBus(eventBus)
 	if privValidator != nil {

docs/DOCS_README.md

@@ -99,4 +99,4 @@ configuration file that we can update with PRs.
 Because the build processes are identical (as is the information contained
 herein), this file should be kept in sync as much as possible with its
 [counterpart in the Cosmos SDK
-repo](https://github.com/cosmos/cosmos-sdk/blob/main/docs/README.md).
+repo](https://github.com/cosmos/cosmos-sdk/blob/master/docs/DOCS_README.md).

docs/architecture/adr-071-proposer-based-timestamps.md

@@ -61,7 +61,7 @@ The following protocols and application features require a reliable source of ti
 * Tendermint Light Clients [rely on correspondence between their known time](https://github.com/tendermint/tendermint/blob/main/spec/light-client/verification/README.md#definitions-1) and the block time for block verification.
 * Tendermint Evidence validity is determined [either in terms of heights or in terms of time](https://github.com/tendermint/tendermint/blob/8029cf7a0fcc89a5004e173ec065aa48ad5ba3c8/spec/consensus/evidence.md#verification).
 * Unbonding of staked assets in the Cosmos Hub [occurs after a period of 21 days](https://github.com/cosmos/governance/blob/ce75de4019b0129f6efcbb0e752cd2cc9e6136d3/params-change/Staking.md#unbondingtime).
-* IBC packets can use either a [timestamp or a height to timeout packet delivery](https://docs.cosmos.network/v0.45/ibc/overview.html#acknowledgements)
+* IBC packets can use either a [timestamp or a height to timeout packet delivery](https://docs.cosmos.network/v0.44/ibc/overview.html#acknowledgements)
 
 Finally, inflation distribution in the Cosmos Hub uses an approximation of time to calculate an annual percentage rate.
 This approximation of time is calculated using [block heights with an estimated number of blocks produced in a year](https://github.com/cosmos/governance/blob/master/params-change/Mint.md#blocksperyear).

docs/qa/README.md

@@ -1,23 +0,0 @@
----
-order: 1
-parent:
-  title: Tendermint Quality Assurance
-  description: This is a report on the process followed and results obtained when running v0.34.x on testnets
-  order: 2
----
-
-# Tendermint Quality Assurance
-
-This directory keeps track of the process followed by the Tendermint Core team
-for Quality Assurance before cutting a release.
-This directory is to live in multiple branches. On each release branch,
-the contents of this directory reflect the status of the process
-at the time the Quality Assurance process was applied for that release.
-
-File [method](./method.md) keeps track of the process followed to obtain the results
-used to decide if a release is passing the Quality Assurance process.
-The results obtained in each release are stored in their own directory.
-The following releases have undergone the Quality Assurance process:
-
-* [v0.34.x](./v034/), which was tested just before releasing v0.34.22
-* [v0.37.x](./v037/), with v.34.x acting as a baseline

docs/qa/method.md

@@ -1,214 +0,0 @@
----
-order: 1
-title: Method
----
-
-# Method
-
-This document provides a detailed description of the QA process.
-It is intended to be used by engineers reproducing the experimental setup for future tests of Tendermint.
-
-The (first iteration of the) QA process as described [in the RELEASES.md document][releases]
-was applied to version v0.34.x in order to have a set of results acting as benchmarking baseline.
-This baseline is then compared with results obtained in later versions.
-
-Out of the testnet-based test cases described in [the releases document][releases] we focused on two of them:
-_200 Node Test_, and _Rotating Nodes Test_.
-
-[releases]: https://github.com/tendermint/tendermint/blob/v0.37.x/RELEASES.md#large-scale-testnets
-
-## Software Dependencies
-
-### Infrastructure Requirements to Run the Tests
-
-* An account at Digital Ocean (DO), with a high droplet limit (>202)
-* The machine to orchestrate the tests should have the following installed:
-    * A clone of the [testnet repository][testnet-repo]
-        * This repository contains all the scripts mentioned in the reminder of this section
-    * [Digital Ocean CLI][doctl]
-    * [Terraform CLI][Terraform]
-    * [Ansible CLI][Ansible]
-
-[testnet-repo]: https://github.com/interchainio/tendermint-testnet
-[Ansible]: https://docs.ansible.com/ansible/latest/index.html
-[Terraform]: https://www.terraform.io/docs
-[doctl]: https://docs.digitalocean.com/reference/doctl/how-to/install/
-
-### Requirements for Result Extraction
-
-* Matlab or Octave
-* [Prometheus][prometheus] server installed
-* blockstore DB of one of the full nodes in the testnet
-* Prometheus DB
-
-[prometheus]: https://prometheus.io/
-
-## 200 Node Testnet
-
-### Running the test
-
-This section explains how the tests were carried out for reproducibility purposes.
-
-1. [If you haven't done it before]
-   Follow steps 1-4 of the `README.md` at the top of the testnet repository to configure Terraform, and `doctl`.
-2. Copy file `testnets/testnet200.toml` onto `testnet.toml` (do NOT commit this change)
-3. Set the variable `VERSION_TAG` in the `Makefile` to the git hash that is to be tested.
-4. Follow steps 5-10 of the `README.md` to configure and start the 200 node testnet
-    * WARNING: Do NOT forget to run `make terraform-destroy` as soon as you are done with the tests (see step 9)
-5. As a sanity check, connect to the Prometheus node's web interface and check the graph for the `tendermint_consensus_height` metric.
-   All nodes should be increasing their heights.
-6. `ssh` into the `testnet-load-runner`, then copy script `script/200-node-loadscript.sh` and run it from the load runner node.
-    * Before running it, you need to edit the script to provide the IP address of a full node.
-      This node will receive all transactions from the load runner node.
-    * This script will take about 40 mins to run
-    * It is running 90-seconds-long experiments in a loop with different loads
-7. Run `make retrieve-data` to gather all relevant data from the testnet into the orchestrating machine
-8. Verify that the data was collected without errors
-    * at least one blockstore DB for a Tendermint validator
-    * the Prometheus database from the Prometheus node
-    * for extra care, you can run `zip -T` on the `prometheus.zip` file and (one of) the `blockstore.db.zip` file(s)
-9. **Run `make terraform-destroy`**
-    * Don't forget to type `yes`! Otherwise you're in trouble.
-
-### Result Extraction
-
-The method for extracting the results described here is highly manual (and exploratory) at this stage.
-The Core team should improve it at every iteration to increase the amount of automation.
-
-#### Steps
-
-1. Unzip the blockstore into a directory
-2. Extract the latency report and the raw latencies for all the experiments. Run these commands from the directory containing the blockstore
-    * `go run github.com/tendermint/tendermint/test/loadtime/cmd/report@3ec6e424d --database-type goleveldb --data-dir ./ > results/report.txt`
-    * `go run github.com/tendermint/tendermint/test/loadtime/cmd/report@3ec6e424d --database-type goleveldb --data-dir ./ --csv results/raw.csv`
-3. File `report.txt` contains an unordered list of experiments with varying concurrent connections and transaction rate
-    * Create files `report01.txt`, `report02.txt`, `report04.txt` and, for each experiment in file `report.txt`,
-      copy its related lines to the filename that matches the number of connections.
-    * Sort the experiments in `report01.txt` in ascending tx rate order. Likewise for `report02.txt` and `report04.txt`.
-4. Generate file `report_tabbed.txt` by showing the contents `report01.txt`, `report02.txt`, `report04.txt` side by side
-   * This effectively creates a table where rows are a particular tx rate and columns are a particular number of websocket connections.
-5. Extract the raw latencies from file `raw.csv` using the following bash loop. This creates a `.csv` file and a `.dat` file per experiment.
-   The format of the `.dat` files is amenable to loading them as matrices in Octave
-
-    ```bash
-    uuids=($(cat report01.txt report02.txt report04.txt | grep '^Experiment ID: ' | awk '{ print $3 }'))
-    c=1
-    for i in 01 02 04; do
-      for j in 0025 0050 0100 0200; do
-        echo $i $j $c "${uuids[$c]}"
-        filename=c${i}_r${j}
-        grep ${uuids[$c]} raw.csv > ${filename}.csv
-        cat ${filename}.csv | tr , ' ' | awk '{ print $2, $3 }' > ${filename}.dat
-        c=$(expr $c + 1)
-      done
-    done
-    ```
-
-6. Enter Octave
-7. Load all `.dat` files generated in step 5 into matrices using this Octave code snippet
-
-    ```octave
-    conns =  { "01"; "02"; "04" };
-    rates =  { "0025"; "0050"; "0100"; "0200" };
-    for i = 1:length(conns)
-      for j = 1:length(rates)
-        filename = strcat("c", conns{i}, "_r", rates{j}, ".dat");
-        load("-ascii", filename);
-      endfor
-    endfor
-    ```
-
-8. Set variable release to the current release undergoing QA
-
-    ```octave
-    release = "v0.34.x";
-    ```
-
-9. Generate a plot with all (or some) experiments, where the X axis is the experiment time,
-   and the y axis is the latency of transactions.
-   The following snippet plots all experiments.
-
-    ```octave
-    legends = {};
-    hold off;
-    for i = 1:length(conns)
-      for j = 1:length(rates)
-        data_name = strcat("c", conns{i}, "_r", rates{j});
-        l = strcat("c=", conns{i}, " r=", rates{j});
-        m = eval(data_name); plot((m(:,1) - min(m(:,1))) / 1e+9, m(:,2) / 1e+9, ".");
-        hold on;
-        legends(1, end+1) = l;
-      endfor
-    endfor
-    legend(legends, "location", "northeastoutside");
-    xlabel("experiment time (s)");
-    ylabel("latency (s)");
-    t = sprintf("200-node testnet - %s", release);
-    title(t);
-    ```
-
-10. Consider adjusting the axis, in case you want to compare your results to the baseline, for instance
-
-    ```octave
-    axis([0, 100, 0, 30], "tic");
-    ```
-
-11. Use Octave's GUI menu to save the plot (e.g. as `.png`)
-
-12. Repeat steps 9 and 10 to obtain as many plots as deemed necessary.
-
-13. To generate a latency vs throughput plot, using the raw CSV file generated
-    in step 2, follow the instructions for the [`latency_throughput.py`] script.
-
-[`latency_throughput.py`]: ../../scripts/qa/reporting/README.md
-
-#### Extracting Prometheus Metrics
-
-1. Stop the prometheus server if it is running as a service (e.g. a `systemd` unit).
-2. Unzip the prometheus database retrieved from the testnet, and move it to replace the
-   local prometheus database.
-3. Start the prometheus server and make sure no error logs appear at start up.
-4. Introduce the metrics you want to gather or plot.
-
-## Rotating Node Testnet
-
-### Running the test
-
-This section explains how the tests were carried out for reproducibility purposes.
-
-1. [If you haven't done it before]
-   Follow steps 1-4 of the `README.md` at the top of the testnet repository to configure Terraform, and `doctl`.
-2. Copy file `testnet_rotating.toml` onto `testnet.toml` (do NOT commit this change)
-3. Set variable `VERSION_TAG` to the git hash that is to be tested.
-4. Run `make terraform-apply EPHEMERAL_SIZE=25`
-    * WARNING: Do NOT forget to run `make terraform-destroy` as soon as you are done with the tests
-5. Follow steps 6-10 of the `README.md` to configure and start the "stable" part of the rotating node testnet
-6. As a sanity check, connect to the Prometheus node's web interface and check the graph for the `tendermint_consensus_height` metric.
-   All nodes should be increasing their heights.
-7. On a different shell,
-    * run `make runload ROTATE_CONNECTIONS=X ROTATE_TX_RATE=Y`
-    * `X` and `Y` should reflect a load below the saturation point (see, e.g.,
-      [this paragraph](./v034/README.md#finding-the-saturation-point) for further info)
-8. Run `make rotate` to start the script that creates the ephemeral nodes, and kills them when they are caught up.
-    * WARNING: If you run this command from your laptop, the laptop needs to be up and connected for full length
-      of the experiment.
-9. When the height of the chain reaches 3000, stop the `make rotate` script
-10. When the rotate script has made two iterations (i.e., all ephemeral nodes have caught up twice)
-    after height 3000 was reached, stop `make rotate`
-11. Run `make retrieve-data` to gather all relevant data from the testnet into the orchestrating machine
-12. Verify that the data was collected without errors
-    * at least one blockstore DB for a Tendermint validator
-    * the Prometheus database from the Prometheus node
-    * for extra care, you can run `zip -T` on the `prometheus.zip` file and (one of) the `blockstore.db.zip` file(s)
-13. **Run `make terraform-destroy`**
-
-Steps 8 to 10 are highly manual at the moment and will be improved in next iterations.
-
-### Result Extraction
-
-In order to obtain a latency plot, follow the instructions above for the 200 node experiment, but:
-
-* The `results.txt` file contains only one experiment
-* Therefore, no need for any `for` loops
-
-As for prometheus, the same method as for the 200 node experiment can be applied.

docs/qa/v034/README.md

@@ -1,278 +0,0 @@
----
-order: 1
-parent:
-  title: Tendermint Quality Assurance Results for v0.34.x
-  description: This is a report on the results obtained when running v0.34.x on testnets
-  order: 2
----
-
-# v0.34.x
-
-## 200 Node Testnet
-
-### Finding the Saturation Point
-
-The first goal when examining the results of the tests is identifying the saturation point.
-The saturation point is a setup with a transaction load big enough to prevent the testnet
-from being stable: the load runner tries to produce slightly more transactions than can
-be processed by the testnet.
-
-The following table summarizes the results for v0.34.x, for the different experiments
-(extracted from file [`v034_report_tabbed.txt`](./img/v034_report_tabbed.txt)).
-
-The X axis of this table is `c`, the number of connections created by the load runner process to the target node.
-The Y axis of this table is `r`, the rate or number of transactions issued per second.
-
-|        |  c=1  |  c=2  |  c=4  |
-| :---   | ----: | ----: | ----: |
-| r=25   |  2225 | 4450  | 8900  |
-| r=50   |  4450 | 8900  | 17800 |
-| r=100  |  8900 | 17800 | 35600 |
-| r=200  | 17800 | 35600 | 38660 |
-
-The table shows the number of 1024-byte-long transactions that were produced by the load runner,
-and processed by Tendermint, during the 90 seconds of the experiment's duration.
-Each cell in the table refers to an experiment with a particular number of websocket connections (`c`)
-to a chosen validator, and the number of transactions per second that the load runner
-tries to produce (`r`). Note that the overall load that the tool attempts to generate is $c \cdot r$.
-
-We can see that the saturation point is beyond the diagonal that spans cells
-
-* `r=200,c=2`
-* `r=100,c=4`
-
-given that the total transactions should be close to the product of the rate, the number of connections,
-and the experiment time (89 seconds, since the last batch never gets sent).
-
-All experiments below the saturation diagonal (`r=200,c=4`) have in common that the total
-number of transactions processed is noticeably less than the product $c \cdot r \cdot 89$,
-which is the expected number of transactions when the system is able to deal well with the
-load.
-With `r=200,c=4`, we obtained 38660 whereas the theoretical number of transactions should
-have been $200 \cdot 4 \cdot 89 = 71200$.
-
-At this point, we chose an experiment at the limit of the saturation diagonal,
-in order to further study the performance of this release.
-**The chosen experiment is `r=200,c=2`**.
-
-This is a plot of the CPU load (average over 1 minute, as output by `top`) of the load runner for `r=200,c=2`,
-where we can see that the load stays close to 0 most of the time.
-
-![load-load-runner](./img/v034_r200c2_load-runner.png)
-
-### Examining latencies
-
-The method described [here](../method.md) allows us to plot the latencies of transactions
-for all experiments.
-
-![all-latencies](./img/v034_200node_latencies.png)
-
-As we can see, even the experiments beyond the saturation diagonal managed to keep
-transaction latency stable (i.e. not constantly increasing).
-Our interpretation for this is that contention within Tendermint was propagated,
-via the websockets, to the load runner,
-hence the load runner could not produce the target load, but a fraction of it.
-
-Further examination of the Prometheus data (see below), showed that the mempool contained many transactions
-at steady state, but did not grow much without quickly returning to this steady state. This demonstrates
-that the transactions were able to be processed by the Tendermint network at least as quickly as they
-were submitted to the mempool. Finally, the test script made sure that, at the end of an experiment, the
-mempool was empty so that all transactions submitted to the chain were processed.
-
-Finally, the number of points present in the plot appears to be much less than expected given the
-number of transactions in each experiment, particularly close to or above the saturation diagonal.
-This is a visual effect of the plot; what appear to be points in the plot are actually potentially huge
-clusters of points. To corroborate this, we have zoomed in the plot above by setting (carefully chosen)
-tiny axis intervals. The cluster shown below looks like a single point in the plot above.
-
-![all-latencies-zoomed](./img/v034_200node_latencies_zoomed.png)
-
-The plot of latencies can we used as a baseline to compare with other releases.
-
-The following plot summarizes average latencies versus overall throughputs
-across different numbers of WebSocket connections to the node into which
-transactions are being loaded.
-
-![latency-vs-throughput](./img/v034_latency_throughput.png)
-
-### Prometheus Metrics on the Chosen Experiment
-
-As mentioned [above](#finding-the-saturation-point), the chosen experiment is `r=200,c=2`.
-This section further examines key metrics for this experiment extracted from Prometheus data.
-
-#### Mempool Size
-
-The mempool size, a count of the number of transactions in the mempool, was shown to be stable and homogeneous
-at all full nodes. It did not exhibit any unconstrained growth.
-The plot below shows the evolution over time of the cumulative number of transactions inside all full nodes' mempools
-at a given time.
-The two spikes that can be observed correspond to a period where consensus instances proceeded beyond the initial round
-at some nodes.
-
-![mempool-cumulative](./img/v034_r200c2_mempool_size.png)
-
-The plot below shows evolution of the average over all full nodes, which oscillates between 1500 and 2000
-outstanding transactions.
-
-![mempool-avg](./img/v034_r200c2_mempool_size_avg.png)
-
-The peaks observed coincide with the moments when some nodes proceeded beyond the initial round of consensus (see below).
-
-#### Peers
-
-The number of peers was stable at all nodes.
-It was higher for the seed nodes (around 140) than for the rest (between 21 and 74).
-The fact that non-seed nodes reach more than 50 peers is due to #9548.
-
-![peers](./img/v034_r200c2_peers.png)
-
-#### Consensus Rounds per Height
-
-Most heights took just one round, but some nodes needed to advance to round 1 at some point.
-
-![rounds](./img/v034_r200c2_rounds.png)
-
-#### Blocks Produced per Minute, Transactions Processed per Minute
-
-The blocks produced per minute are the slope of this plot.
-
-![heights](./img/v034_r200c2_heights.png)
-
-Over a period of 2 minutes, the height goes from 530 to 569.
-This results in an average of 19.5 blocks produced per minute.
-
-The transactions processed per minute are the slope of this plot.
-
-![total-txs](./img/v034_r200c2_total-txs.png)
-
-Over a period of 2 minutes, the total goes from 64525 to 100125 transactions,
-resulting in 17800 transactions per minute. However, we can see in the plot that
-all transactions in the load are processed long before the two minutes.
-If we adjust the time window when transactions are processed (approx. 105 seconds),
-we obtain 20343 transactions per minute.
-
-#### Memory Resident Set Size
-
-Resident Set Size of all monitored processes is plotted below.
-
-![rss](./img/v034_r200c2_rss.png)
-
-The average over all processes oscillates around 1.2 GiB and does not demonstrate unconstrained growth.
-
-![rss-avg](./img/v034_r200c2_rss_avg.png)
-
-#### CPU utilization
-
-The best metric from Prometheus to gauge CPU utilization in a Unix machine is `load1`,
-as it usually appears in the
-[output of `top`](https://www.digitalocean.com/community/tutorials/load-average-in-linux).
-
-![load1](./img/v034_r200c2_load1.png)
-
-It is contained in most cases below 5, which is generally considered acceptable load.
-
-### Test Result
-
-**Result: N/A** (v0.34.x is the baseline)
-
-Date: 2022-10-14
-
-Version: 3ec6e424d6ae4c96867c2dcf8310572156068bb6
-
-## Rotating Node Testnet
-
-For this testnet, we will use a load that can safely be considered below the saturation
-point for the size of this testnet (between 13 and 38 full nodes): `c=4,r=800`.
-
-N.B.: The version of Tendermint used for these tests is affected by #9539.
-However, the reduced load that reaches the mempools is orthogonal to functionality
-we are focusing on here.
-
-### Latencies
-
-The plot of all latencies can be seen in the following plot.
-
-![rotating-all-latencies](./img/v034_rotating_latencies.png)
-
-We can observe there are some very high latencies, towards the end of the test.
-Upon suspicion that they are duplicate transactions, we examined the latencies
-raw file and discovered there are more than 100K duplicate transactions.
-
-The following plot shows the latencies file where all duplicate transactions have
-been removed, i.e., only the first occurrence of a duplicate transaction is kept.
-
-![rotating-all-latencies-uniq](./img/v034_rotating_latencies_uniq.png)
-
-This problem, existing in `v0.34.x`, will need to be addressed, perhaps in the same way
-we addressed it when running the 200 node test with high loads: increasing the `cache_size`
-configuration parameter.
-
-### Prometheus Metrics
-
-The set of metrics shown here are less than for the 200 node experiment.
-We are only interested in those for which the catch-up process (blocksync) may have an impact.
-
-#### Blocks and Transactions per minute
-
-Just as shown for the 200 node test, the blocks produced per minute are the gradient of this plot.
-
-![rotating-heights](./img/v034_rotating_heights.png)
-
-Over a period of 5229 seconds, the height goes from 2 to 3638.
-This results in an average of 41 blocks produced per minute.
-
-The following plot shows only the heights reported by ephemeral nodes
-(which are also included in the plot above). Note that the _height_ metric
-is only showed _once the node has switched to consensus_, hence the gaps
-when nodes are killed, wiped out, started from scratch, and catching up.
-
-![rotating-heights-ephe](./img/v034_rotating_heights_ephe.png)
-
-The transactions processed per minute are the gradient of this plot.
-
-![rotating-total-txs](./img/v034_rotating_total-txs.png)
-
-The small lines we see periodically close to `y=0` are the transactions that
-ephemeral nodes start processing when they are caught up.
-
-Over a period of 5229 minutes, the total goes from 0 to 387697 transactions,
-resulting in 4449 transactions per minute. We can see some abrupt changes in
-the plot's gradient. This will need to be investigated.
-
-#### Peers
-
-The plot below shows the evolution in peers throughout the experiment.
-The periodic changes observed are due to the ephemeral nodes being stopped,
-wiped out, and recreated.
-
-![rotating-peers](./img/v034_rotating_peers.png)
-
-The validators' plots are concentrated at the higher part of the graph, whereas the ephemeral nodes
-are mostly at the lower part.
-
-#### Memory Resident Set Size
-
-The average Resident Set Size (RSS) over all processes seems stable, and slightly growing toward the end.
-This might be related to the increased in transaction load observed above.
-
-![rotating-rss-avg](./img/v034_rotating_rss_avg.png)
-
-The memory taken by the validators and the ephemeral nodes (when they are up) is comparable.
-
-#### CPU utilization
-
-The plot shows metric `load1` for all nodes.
-
-![rotating-load1](./img/v034_rotating_load1.png)
-
-It is contained under 5 most of the time, which is considered normal load.
-The purple line, which follows a different pattern is the validator receiving all
-transactions, via RPC, from the load runner process.
-
-### Test Result
-
-**Result: N/A**
-
-Date: 2022-10-10
-
-Version: a28c987f5a604ff66b515dd415270063e6fb069d

docs/qa/v034/img/v034_report_tabbed.txt

@@ -1,52 +0,0 @@
-Experiment ID: 3d5cf4ef-1a1a-4b46-aa2d-da5643d2e81e │Experiment ID: 80e472ec-13a1-4772-a827-3b0c907fb51d │Experiment ID: 07aca6cf-c5a4-4696-988f-e3270fc6333b
-                                                    │                                                    │
-        Connections: 1                              │        Connections: 2                              │        Connections: 4
-        Rate: 25                                    │        Rate: 25                                    │        Rate: 25
-        Size: 1024                                  │        Size: 1024                                  │        Size: 1024
-                                                    │                                                    │
-        Total Valid Tx: 2225                        │        Total Valid Tx: 4450                        │        Total Valid Tx: 8900
-        Total Negative Latencies: 0                 │        Total Negative Latencies: 0                 │        Total Negative Latencies: 0
-        Minimum Latency: 599.404362ms               │        Minimum Latency: 448.145181ms               │        Minimum Latency: 412.485729ms
-        Maximum Latency: 3.539686885s               │        Maximum Latency: 3.237392049s               │        Maximum Latency: 12.026665368s
-        Average Latency: 1.441485349s               │        Average Latency: 1.441267946s               │        Average Latency: 2.150192457s
-        Standard Deviation: 541.049869ms            │        Standard Deviation: 525.040007ms            │        Standard Deviation: 2.233852478s
-                                                    │                                                    │
-Experiment ID: 953dc544-dd40-40e8-8712-20c34c3ce45e │Experiment ID: d31fc258-16e7-45cd-9dc8-13ab87bc0b0a │Experiment ID: 15d90a7e-b941-42f4-b411-2f15f857739e
-                                                    │                                                    │
-        Connections: 1                              │        Connections: 2                              │        Connections: 4
-        Rate: 50                                    │        Rate: 50                                    │        Rate: 50
-        Size: 1024                                  │        Size: 1024                                  │        Size: 1024
-                                                    │                                                    │
-        Total Valid Tx: 4450                        │        Total Valid Tx: 8900                        │        Total Valid Tx: 17800
-        Total Negative Latencies: 0                 │        Total Negative Latencies: 0                 │        Total Negative Latencies: 0
-        Minimum Latency: 482.046942ms               │        Minimum Latency: 435.458913ms               │        Minimum Latency: 510.746448ms
-        Maximum Latency: 3.761483455s               │        Maximum Latency: 7.175583584s               │        Maximum Latency: 6.551497882s
-        Average Latency: 1.450408183s               │        Average Latency: 1.681673116s               │        Average Latency: 1.738083875s
-        Standard Deviation: 587.560056ms            │        Standard Deviation: 1.147902047s            │        Standard Deviation: 943.46522ms
-                                                    │                                                    │
-Experiment ID: 9a0b9980-9ce6-4db5-a80a-65ca70294b87 │Experiment ID: df8fa4f4-80af-4ded-8a28-356d15018b43 │Experiment ID: d0e41c2c-89c0-4f38-8e34-ca07adae593a
-                                                    │                                                    │
-        Connections: 1                              │        Connections: 2                              │        Connections: 4
-        Rate: 100                                   │        Rate: 100                                   │        Rate: 100
-        Size: 1024                                  │        Size: 1024                                  │        Size: 1024
-                                                    │                                                    │
-        Total Valid Tx: 8900                        │        Total Valid Tx: 17800                       │        Total Valid Tx: 35600
-        Total Negative Latencies: 0                 │        Total Negative Latencies: 0                 │        Total Negative Latencies: 0
-        Minimum Latency: 477.417219ms               │        Minimum Latency: 564.29247ms                │        Minimum Latency: 840.71089ms
-        Maximum Latency: 6.63744785s                │        Maximum Latency: 6.988553219s               │        Maximum Latency: 9.555312398s
-        Average Latency: 1.561216103s               │        Average Latency: 1.76419063s                │        Average Latency: 3.200941683s
-        Standard Deviation: 1.011333552s            │        Standard Deviation: 1.068459423s            │        Standard Deviation: 1.732346601s
-                                                    │                                                    │
-Experiment ID: 493df3ee-4a36-4bce-80f8-6d65da66beda │Experiment ID: 13060525-f04f-46f6-8ade-286684b2fe50 │Experiment ID: 1777cbd2-8c96-42e4-9ec7-9b21f2225e4d
-                                                    │                                                    │
-        Connections: 1                              │        Connections: 2                              │        Connections: 4
-        Rate: 200                                   │        Rate: 200                                   │        Rate: 200
-        Size: 1024                                  │        Size: 1024                                  │        Size: 1024
-                                                    │                                                    │
-        Total Valid Tx: 17800                       │        Total Valid Tx: 35600                       │        Total Valid Tx: 38660
-        Total Negative Latencies: 0                 │        Total Negative Latencies: 0                 │        Total Negative Latencies: 0
-        Minimum Latency: 493.705261ms               │        Minimum Latency: 955.090573ms               │        Minimum Latency: 1.9485821s
-        Maximum Latency: 7.440921872s               │        Maximum Latency: 10.086673491s              │        Maximum Latency: 17.73103976s
-        Average Latency: 1.875510582s               │        Average Latency: 3.438130099s               │        Average Latency: 8.143862237s
-        Standard Deviation: 1.304336995s            │        Standard Deviation: 1.966391574s            │        Standard Deviation: 3.943140002s
-

docs/qa/v037/README.md

@@ -1,326 +0,0 @@
----
-order: 1
-parent:
-  title: Tendermint Quality Assurance Results for v0.37.x
-  description: This is a report on the results obtained when running v0.37.x on testnets
-  order: 2
----
-
-# v0.37.x
-
-## Issues discovered
-
-During this iteration of the QA process, the following issues were found:
-
-* (critical, fixed) [\#9533] - This bug caused full nodes to sometimes get stuck
-  when blocksyncing, requiring a manual restart to unblock them. Importantly,
-  this bug was also present in v0.34.x and the fix was also backported in
-  [\#9534].
-* (critical, fixed) [\#9539] - `loadtime` is very likely to include more than
-  one "=" character in transactions, with is rejected by the e2e application.
-* (critical, fixed) [\#9581] - Absent prometheus label makes Tendermint crash
-  when enabling Prometheus metric collection
-* (non-critical, not fixed) [\#9548] - Full nodes can go over 50 connected
-  peers, which is not intended by the default configuration.
-* (non-critical, not fixed) [\#9537] - With the default mempool cache setting,
-  duplicated transactions are not rejected when gossipped and eventually flood
-  all mempools. The 200 node testnets were thus run with a value of 200000 (as
-  opposed to the default 10000)
-
-## 200 Node Testnet
-
-### Finding the Saturation Point
-
-The first goal is to identify the saturation point and compare it with the baseline (v0.34.x).
-For further details, see [this paragraph](../v034/README.md#finding-the-saturation-point)
-in the baseline version.
-
-The following table summarizes the results for v0.37.x, for the different experiments
-(extracted from file [`v037_report_tabbed.txt`](./img/v037_report_tabbed.txt)).
-
-The X axis of this table is `c`, the number of connections created by the load runner process to the target node.
-The Y axis of this table is `r`, the rate or number of transactions issued per second.
-
-|        |  c=1  |  c=2  |  c=4  |
-| :---   | ----: | ----: | ----: |
-| r=25   |  2225 | 4450  | 8900  |
-| r=50   |  4450 | 8900  | 17800 |
-| r=100  |  8900 | 17800 | 35600 |
-| r=200  | 17800 | 35600 | 38660 |
-
-For comparison, this is the table with the baseline version.
-
-|        |  c=1  |  c=2  |  c=4  |
-| :---   | ----: | ----: | ----: |
-| r=25   |  2225 | 4450  | 8900  |
-| r=50   |  4450 | 8900  | 17800 |
-| r=100  |  8900 | 17800 | 35400 |
-| r=200  | 17800 | 35600 | 37358 |
-
-The saturation point is beyond the diagonal:
-
-* `r=200,c=2`
-* `r=100,c=4`
-
-which is at the same place as the baseline. For more details on the saturation point, see
-[this paragraph](../v034/README.md#finding-the-saturation-point) in the baseline version.
-
-The experiment chosen to examine Prometheus metrics is the same as in the baseline:
-**`r=200,c=2`**.
-
-The load runner's CPU load was negligible (near 0) when running `r=200,c=2`.
-
-### Examining latencies
-
-The method described [here](../method.md) allows us to plot the latencies of transactions
-for all experiments.
-
-![all-latencies](./img/v037_200node_latencies.png)
-
-The data seen in the plot is similar to that of the baseline.
-
-![all-latencies-bl](../v034/img/v034_200node_latencies.png)
-
-Therefore, for further details on these plots,
-see [this paragraph](../v034/README.md#examining-latencies) in the baseline version.
-
-The following plot summarizes average latencies versus overall throughputs
-across different numbers of WebSocket connections to the node into which
-transactions are being loaded.
-
-![latency-vs-throughput](./img/v037_latency_throughput.png)
-
-This is similar to that of the baseline plot:
-
-![latency-vs-throughput-bl](../v034/img/v034_latency_throughput.png)
-
-### Prometheus Metrics on the Chosen Experiment
-
-As mentioned [above](#finding-the-saturation-point), the chosen experiment is `r=200,c=2`.
-This section further examines key metrics for this experiment extracted from Prometheus data.
-
-#### Mempool Size
-
-The mempool size, a count of the number of transactions in the mempool, was shown to be stable and homogeneous
-at all full nodes. It did not exhibit any unconstrained growth.
-The plot below shows the evolution over time of the cumulative number of transactions inside all full nodes' mempools
-at a given time.
-
-![mempool-cumulative](./img/v037_r200c2_mempool_size.png)
-
-The plot below shows evolution of the average over all full nodes, which oscillate between 1500 and 2000 outstanding transactions.
-
-![mempool-avg](./img/v037_r200c2_mempool_size_avg.png)
-
-The peaks observed coincide with the moments when some nodes reached round 1 of consensus (see below).
-
-**These plots yield similar results to the baseline**:
-
-![mempool-cumulative-bl](../v034/img/v034_r200c2_mempool_size.png)
-
-![mempool-avg-bl](../v034/img/v034_r200c2_mempool_size_avg.png)
-
-#### Peers
-
-The number of peers was stable at all nodes.
-It was higher for the seed nodes (around 140) than for the rest (between 16 and 78).
-
-![peers](./img/v037_r200c2_peers.png)
-
-Just as in the baseline, the fact that non-seed nodes reach more than 50 peers is due to #9548.
-
-**This plot yields similar results to the baseline**:
-
-![peers-bl](../v034/img/v034_r200c2_peers.png)
-
-#### Consensus Rounds per Height
-
-Most heights took just one round, but some nodes needed to advance to round 1 at some point.
-
-![rounds](./img/v037_r200c2_rounds.png)
-
-**This plot yields slightly better results than the baseline**:
-
-![rounds-bl](../v034/img/v034_r200c2_rounds.png)
-
-#### Blocks Produced per Minute, Transactions Processed per Minute
-
-The blocks produced per minute are the gradient of this plot.
-
-![heights](./img/v037_r200c2_heights.png)
-
-Over a period of 2 minutes, the height goes from 477 to 524.
-This results in an average of 23.5 blocks produced per minute.
-
-The transactions processed per minute are the gradient of this plot.
-
-![total-txs](./img/v037_r200c2_total-txs.png)
-
-Over a period of 2 minutes, the total goes from 64525 to 100125 transactions,
-resulting in 17800 transactions per minute. However, we can see in the plot that
-all transactions in the load are process long before the two minutes.
-If we adjust the time window when transactions are processed (approx. 90 seconds),
-we obtain 23733 transactions per minute.
-
-**These plots yield similar results to the baseline**:
-
-![heights-bl](../v034/img/v034_r200c2_heights.png)
-
-![total-txs](../v034/img/v034_r200c2_total-txs.png)
-
-#### Memory Resident Set Size
-
-Resident Set Size of all monitored processes is plotted below.
-
-![rss](./img/v037_r200c2_rss.png)
-
-The average over all processes oscillates around 380 MiB and does not demonstrate unconstrained growth.
-
-![rss-avg](./img/v037_r200c2_rss_avg.png)
-
-**These plots yield similar results to the baseline**:
-
-![rss-bl](../v034/img/v034_r200c2_rss.png)
-
-![rss-avg-bl](../v034/img/v034_r200c2_rss_avg.png)
-
-#### CPU utilization
-
-The best metric from Prometheus to gauge CPU utilization in a Unix machine is `load1`,
-as it usually appears in the
-[output of `top`](https://www.digitalocean.com/community/tutorials/load-average-in-linux).
-
-![load1](./img/v037_r200c2_load1.png)
-
-It is contained below 5 on most nodes.
-
-**This plot yields similar results to the baseline**:
-
-![load1](../v034/img/v034_r200c2_load1.png)
-
-### Test Result
-
-**Result: PASS**
-
-Date: 2022-10-14
-
-Version: 1cf9d8e276afe8595cba960b51cd056514965fd1
-
-## Rotating Node Testnet
-
-We use the same load as in the baseline: `c=4,r=800`.
-
-Just as in the baseline tests, the version of Tendermint used for these tests is affected by #9539.
-See this paragraph in the [baseline report](../v034/README.md#rotating-node-testnet) for further details.
-Finally, note that this setup allows for a fairer comparison between this version and the baseline.
-
-### Latencies
-
-The plot of all latencies can be seen here.
-
-![rotating-all-latencies](./img/v037_rotating_latencies.png)
-
-Which is similar to the baseline.
-
-![rotating-all-latencies-bl](../v034/img/v034_rotating_latencies_uniq.png)
-
-Note that we are comparing against the baseline plot with _unique_
-transactions. This is because the problem with duplicate transactions
-detected during the baseline experiment did not show up for `v0.37`,
-which is _not_ proof that the problem is not present in `v0.37`.
-
-### Prometheus Metrics
-
-The set of metrics shown here match those shown on the baseline (`v0.34`) for the same experiment.
-We also show the baseline results for comparison.
-
-#### Blocks and Transactions per minute
-
-The blocks produced per minute are the gradient of this plot.
-
-![rotating-heights](./img/v037_rotating_heights.png)
-
-Over a period of 4446 seconds, the height goes from 5 to 3323.
-This results in an average of 45 blocks produced per minute,
-which is similar to the baseline, shown below.
-
-![rotating-heights-bl](../v034/img/v034_rotating_heights.png)
-
-The following two plots show only the heights reported by ephemeral nodes.
-The second plot is the baseline plot for comparison.
-
-![rotating-heights-ephe](./img/v037_rotating_heights_ephe.png)
-
-![rotating-heights-ephe-bl](../v034/img/v034_rotating_heights_ephe.png)
-
-By the length of the segments, we can see that ephemeral nodes in `v0.37`
-catch up slightly faster.
-
-The transactions processed per minute are the gradient of this plot.
-
-![rotating-total-txs](./img/v037_rotating_total-txs.png)
-
-Over a period of 3852 seconds, the total goes from 597 to 267298 transactions in one of the validators,
-resulting in 4154 transactions per minute, which is slightly lower than the baseline,
-although the baseline had to deal with duplicate transactions.
-
-For comparison, this is the baseline plot.
-
-![rotating-total-txs-bl](../v034/img/v034_rotating_total-txs.png)
-
-#### Peers
-
-The plot below shows the evolution of the number of peers throughout the experiment.
-
-![rotating-peers](./img/v037_rotating_peers.png)
-
-This is the baseline plot, for comparison.
-
-![rotating-peers-bl](../v034/img/v034_rotating_peers.png)
-
-The plotted values and their evolution are comparable in both plots.
-
-For further details on these plots, see the baseline report.
-
-#### Memory Resident Set Size
-
-The average Resident Set Size (RSS) over all processes looks slightly more stable
-on `v0.37` (first plot) than on the baseline (second plot).
-
-![rotating-rss-avg](./img/v037_rotating_rss_avg.png)
-
-![rotating-rss-avg-bl](../v034/img/v034_rotating_rss_avg.png)
-
-The memory taken by the validators and the ephemeral nodes when they are up is comparable (not shown in the plots),
-just as observed in the baseline.
-
-#### CPU utilization
-
-The plot shows metric `load1` for all nodes.
-
-![rotating-load1](./img/v037_rotating_load1.png)
-
-This is the baseline plot.
-
-![rotating-load1-bl](../v034/img/v034_rotating_load1.png)
-
-In both cases, it is contained under 5 most of the time, which is considered normal load.
-The green line in the `v0.37` plot and the purple line in the baseline plot (`v0.34`)
-correspond to the validators receiving all transactions, via RPC, from the load runner process.
-In both cases, they oscillate around 5 (normal load). The main difference is that other
-nodes are generally less loaded in `v0.37`.
-
-### Test Result
-
-**Result: PASS**
-
-Date: 2022-10-10
-
-Version: 155110007b9d8b83997a799016c1d0844c8efbaf
-
-[\#9533]: https://github.com/tendermint/tendermint/pull/9533
-[\#9534]: https://github.com/tendermint/tendermint/pull/9534
-[\#9539]: https://github.com/tendermint/tendermint/issues/9539
-[\#9548]: https://github.com/tendermint/tendermint/issues/9548
-[\#9537]: https://github.com/tendermint/tendermint/issues/9537
-[\#9581]: https://github.com/tendermint/tendermint/issues/9581

docs/qa/v037/img/v037_report_tabbed.txt

@@ -1,52 +0,0 @@
-Experiment ID: af129eae-7039-4c76-8c37-cff9ac636a84 │Experiment ID: 0f88bd33-9bf0-4197-8d1d-9a737c301ec6 │Experiment ID: 88227cad-2ba8-4eb6-b493-041d8120b46f
-                                                    │                                                    │
-        Connections: 1                              │        Connections: 2                              │        Connections: 4
-        Rate: 25                                    │        Rate: 25                                    │        Rate: 25
-        Size: 1024                                  │        Size: 1024                                  │        Size: 1024
-                                                    │                                                    │
-        Total Valid Tx: 2225                        │        Total Valid Tx: 4450                        │        Total Valid Tx: 8900
-        Total Negative Latencies: 0                 │        Total Negative Latencies: 0                 │        Total Negative Latencies: 0
-        Minimum Latency: 506.248587ms               │        Minimum Latency: 469.53452ms                │        Minimum Latency: 588.900721ms
-        Maximum Latency: 3.032125789s               │        Maximum Latency: 6.548830955s               │        Maximum Latency: 6.533739843s
-        Average Latency: 1.427767726s               │        Average Latency: 1.448582257s               │        Average Latency: 1.717432341s
-        Standard Deviation: 524.11782ms             │        Standard Deviation: 768.684133ms            │        Standard Deviation: 1.000015768s
-                                                    │                                                    │
-Experiment ID: f03d39bd-0233-4b3c-b461-543445ae1d4b │Experiment ID: 46674f1c-e591-4e36-bb9b-f375c19fc475 │Experiment ID: 5385c159-8d4d-455b-bced-dcd4a3209988
-                                                    │                                                    │
-        Connections: 1                              │        Connections: 2                              │        Connections: 4
-        Rate: 50                                    │        Rate: 50                                    │        Rate: 50
-        Size: 1024                                  │        Size: 1024                                  │        Size: 1024
-                                                    │                                                    │
-        Total Valid Tx: 4450                        │        Total Valid Tx: 8900                        │        Total Valid Tx: 17800
-        Total Negative Latencies: 0                 │        Total Negative Latencies: 0                 │        Total Negative Latencies: 0
-        Minimum Latency: 477.46027ms                │        Minimum Latency: 455.757111ms               │        Minimum Latency: 594.749081ms
-        Maximum Latency: 2.483895394s               │        Maximum Latency: 2.904715695s               │        Maximum Latency: 9.294950389s
-        Average Latency: 1.407374662s               │        Average Latency: 1.397385779s               │        Average Latency: 2.621122536s
-        Standard Deviation: 505.150067ms            │        Standard Deviation: 551.67603ms             │        Standard Deviation: 1.772725794s
-                                                    │                                                    │
-Experiment ID: 9161b4a7-d75c-455f-b82d-2b5235d533cf │Experiment ID: 993a13a8-9db1-4b2b-9c20-71a5b85e4bbf │Experiment ID: ad1eb9e1-f4d6-41fd-9ba7-0f1f7dde1e3e
-                                                    │                                                    │
-        Connections: 1                              │        Connections: 2                              │        Connections: 4
-        Rate: 100                                   │        Rate: 100                                   │        Rate: 100
-        Size: 1024                                  │        Size: 1024                                  │        Size: 1024
-                                                    │                                                    │
-        Total Valid Tx: 8900                        │        Total Valid Tx: 17800                       │        Total Valid Tx: 35400
-        Total Negative Latencies: 0                 │        Total Negative Latencies: 0                 │        Total Negative Latencies: 0
-        Minimum Latency: 448.050467ms               │        Minimum Latency: 605.436195ms               │        Minimum Latency: 1.16816912s
-        Maximum Latency: 3.789711139s               │        Maximum Latency: 7.292770222s               │        Maximum Latency: 11.378681842s
-        Average Latency: 1.451342158s               │        Average Latency: 2.07457999s                │        Average Latency: 3.918384209s
-        Standard Deviation: 644.075973ms            │        Standard Deviation: 1.230204022s            │        Standard Deviation: 2.172400458s
-                                                    │                                                    │
-Experiment ID: 3cbe9c3d-9c43-4c9f-b5ca-b567d20bbd57 │Experiment ID: af836c5e-d9b6-4d5d-971c-2fc7f07aa2a0 │Experiment ID: 77606397-4989-41d4-b13b-f1f4d1af063f
-                                                    │                                                    │
-        Connections: 1                              │        Connections: 2                              │        Connections: 4
-        Rate: 200                                   │        Rate: 200                                   │        Rate: 200
-        Size: 1024                                  │        Size: 1024                                  │        Size: 1024
-                                                    │                                                    │
-        Total Valid Tx: 17800                       │        Total Valid Tx: 35600                       │        Total Valid Tx: 37358
-        Total Negative Latencies: 0                 │        Total Negative Latencies: 0                 │        Total Negative Latencies: 0
-        Minimum Latency: 519.984701ms               │        Minimum Latency: 820.755087ms               │        Minimum Latency: 1.712574804s
-        Maximum Latency: 12.609056712s              │        Maximum Latency: 9.260798095s               │        Maximum Latency: 25.739223696s
-        Average Latency: 2.717853101s               │        Average Latency: 3.477731881s               │        Average Latency: 8.547725264s
-        Standard Deviation: 2.390778155s            │        Standard Deviation: 1.675000913s            │        Standard Deviation: 4.76961569s
-

evidence/reactor.go

@@ -4,7 +4,6 @@ import (
 	"fmt"
 	"time"
 
-	"github.com/cosmos/gogoproto/proto"
 	clist "github.com/tendermint/tendermint/libs/clist"
 	"github.com/tendermint/tendermint/libs/log"
 	"github.com/tendermint/tendermint/p2p"
@@ -56,7 +55,6 @@ func (evR *Reactor) GetChannels() []*p2p.ChannelDescriptor {
 			ID:                  EvidenceChannel,
 			Priority:            6,
 			RecvMessageCapacity: maxMsgSize,
-			MessageType:         &tmproto.EvidenceList{},
 		},
 	}
 }
@@ -68,11 +66,11 @@ func (evR *Reactor) AddPeer(peer p2p.Peer) {
 
 // Receive implements Reactor.
 // It adds any received evidence to the evpool.
-func (evR *Reactor) Receive(e p2p.Envelope) {
-	evis, err := evidenceListFromProto(e.Message)
+func (evR *Reactor) Receive(chID byte, src p2p.Peer, msgBytes []byte) {
+	evis, err := decodeMsg(msgBytes)
 	if err != nil {
-		evR.Logger.Error("Error decoding message", "src", e.Src, "chId", e.ChannelID, "err", err)
-		evR.Switch.StopPeerForError(e.Src, err)
+		evR.Logger.Error("Error decoding message", "src", src, "chId", chID, "err", err)
+		evR.Switch.StopPeerForError(src, err)
 		return
 	}
 
@@ -82,7 +80,7 @@ func (evR *Reactor) Receive(e p2p.Envelope) {
 		case *types.ErrInvalidEvidence:
 			evR.Logger.Error(err.Error())
 			// punish peer
-			evR.Switch.StopPeerForError(e.Src, err)
+			evR.Switch.StopPeerForError(src, err)
 			return
 		case nil:
 		default:
@@ -128,15 +126,11 @@ func (evR *Reactor) broadcastEvidenceRoutine(peer p2p.Peer) {
 		evis := evR.prepareEvidenceMessage(peer, ev)
 		if len(evis) > 0 {
 			evR.Logger.Debug("Gossiping evidence to peer", "ev", ev, "peer", peer)
-			evp, err := evidenceListToProto(evis)
+			msgBytes, err := encodeMsg(evis)
 			if err != nil {
 				panic(err)
 			}
-
-			success := peer.Send(p2p.Envelope{
-				ChannelID: EvidenceChannel,
-				Message:   evp,
-			})
+			success := peer.Send(EvidenceChannel, msgBytes)
 			if !success {
 				time.Sleep(peerRetryMessageIntervalMS * time.Millisecond)
 				continue
@@ -216,7 +210,7 @@ type PeerState interface {
 
 // encodemsg takes a array of evidence
 // returns the byte encoding of the List Message
-func evidenceListToProto(evis []types.Evidence) (*tmproto.EvidenceList, error) {
+func encodeMsg(evis []types.Evidence) ([]byte, error) {
 	evi := make([]tmproto.Evidence, len(evis))
 	for i := 0; i < len(evis); i++ {
 		ev, err := types.EvidenceToProto(evis[i])
@@ -228,13 +222,19 @@ func evidenceListToProto(evis []types.Evidence) (*tmproto.EvidenceList, error) {
 	epl := tmproto.EvidenceList{
 		Evidence: evi,
 	}
-	return &epl, nil
+
+	return epl.Marshal()
 }
 
-func evidenceListFromProto(m proto.Message) ([]types.Evidence, error) {
-	lm := m.(*tmproto.EvidenceList)
+// decodemsg takes an array of bytes
+// returns an array of evidence
+func decodeMsg(bz []byte) (evis []types.Evidence, err error) {
+	lm := tmproto.EvidenceList{}
+	if err := lm.Unmarshal(bz); err != nil {
+		return nil, err
+	}
 
-	evis := make([]types.Evidence, len(lm.Evidence))
+	evis = make([]types.Evidence, len(lm.Evidence))
 	for i := 0; i < len(lm.Evidence); i++ {
 		ev, err := types.EvidenceFromProto(&lm.Evidence[i])
 		if err != nil {

evidence/reactor_test.go

@@ -208,10 +208,7 @@ func TestReactorBroadcastEvidenceMemoryLeak(t *testing.T) {
 	// i.e. broadcastEvidenceRoutine finishes when peer is stopped
 	defer leaktest.CheckTimeout(t, 10*time.Second)()
 
-	p.On("Send", mock.MatchedBy(func(i interface{}) bool {
-		e, ok := i.(p2p.Envelope)
-		return ok && e.ChannelID == evidence.EvidenceChannel
-	})).Return(false)
+	p.On("Send", evidence.EvidenceChannel, mock.AnythingOfType("[]uint8")).Return(false)
 	quitChan := make(<-chan struct{})
 	p.On("Quit").Return(quitChan)
 	ps := peerState{2}

evidence/verify.go

@@ -21,6 +21,7 @@ func (evpool *Pool) verify(evidence types.Evidence) error {
 		state          = evpool.State()
 		height         = state.LastBlockHeight
 		evidenceParams = state.ConsensusParams.Evidence
+		ageNumBlocks   = height - evidence.Height()
 	)
 
 	// verify the time of the evidence
@@ -33,9 +34,10 @@ func (evpool *Pool) verify(evidence types.Evidence) error {
 		return fmt.Errorf("evidence has a different time to the block it is associated with (%v != %v)",
 			evidence.Time(), evTime)
 	}
+	ageDuration := state.LastBlockTime.Sub(evTime)
 
-	// checking if evidence is expired calculated using the block evidence time and height
-	if IsEvidenceExpired(height, state.LastBlockTime, evidence.Height(), evTime, evidenceParams) {
+	// check that the evidence hasn't expired
+	if ageDuration > evidenceParams.MaxAgeDuration && ageNumBlocks > evidenceParams.MaxAgeNumBlocks {
 		return fmt.Errorf(
 			"evidence from height %d (created at: %v) is too old; min height is %d and evidence can not be older than %v",
 			evidence.Height(),
@@ -282,14 +284,3 @@ func getSignedHeader(blockStore BlockStore, height int64) (*types.SignedHeader,
 		Commit: commit,
 	}, nil
 }
-
-// check that the evidence hasn't expired
-func IsEvidenceExpired(heightNow int64, timeNow time.Time, heightEv int64, timeEv time.Time, evidenceParams types.EvidenceParams) bool {
-	ageDuration := timeNow.Sub(timeEv)
-	ageNumBlocks := heightNow - heightEv
-
-	if ageDuration > evidenceParams.MaxAgeDuration && ageNumBlocks > evidenceParams.MaxAgeNumBlocks {
-		return true
-	}
-	return false
-}

go.mod

@@ -3,7 +3,7 @@ module github.com/tendermint/tendermint
 go 1.18
 
 require (
-	github.com/BurntSushi/toml v1.2.1
+	github.com/BurntSushi/toml v1.2.0
 	github.com/adlio/schema v1.3.3
 	github.com/cenkalti/backoff v2.2.1+incompatible // indirect
 	github.com/fortytw2/leaktest v1.3.0
@@ -11,7 +11,7 @@ require (
 	github.com/go-kit/log v0.2.1
 	github.com/go-logfmt/logfmt v0.5.1
 	github.com/golang/protobuf v1.5.2
-	github.com/golangci/golangci-lint v1.50.1
+	github.com/golangci/golangci-lint v1.49.0
 	github.com/google/orderedcode v0.0.1
 	github.com/gorilla/websocket v1.5.0
 	github.com/informalsystems/tm-load-test v1.0.0
@@ -22,42 +22,41 @@ require (
 	github.com/pkg/errors v0.9.1
 	github.com/pointlander/peg v1.0.1
 	github.com/prometheus/client_golang v1.13.0
-	github.com/prometheus/client_model v0.3.0
+	github.com/prometheus/client_model v0.2.0
 	github.com/prometheus/common v0.37.0
 	github.com/rcrowley/go-metrics v0.0.0-20201227073835-cf1acfcdf475
 	github.com/rs/cors v1.8.2
 	github.com/sasha-s/go-deadlock v0.3.1
 	github.com/snikch/goodman v0.0.0-20171125024755-10e37e294daa
-	github.com/spf13/cobra v1.6.1
+	github.com/spf13/cobra v1.5.0
 	github.com/spf13/viper v1.13.0
-	github.com/stretchr/testify v1.8.1
+	github.com/stretchr/testify v1.8.0
 	github.com/tendermint/tm-db v0.6.6
-	golang.org/x/crypto v0.1.0
-	golang.org/x/net v0.1.0
-	google.golang.org/grpc v1.50.1
+	golang.org/x/crypto v0.0.0-20220722155217-630584e8d5aa
+	golang.org/x/net v0.0.0-20220812174116-3211cb980234
+	google.golang.org/grpc v1.49.0
 )
 
 require (
-	github.com/bufbuild/buf v1.9.0
+	github.com/bufbuild/buf v1.8.0
 	github.com/creachadair/taskgroup v0.3.2
 	github.com/syndtr/goleveldb v1.0.1-0.20210819022825-2ae1ddf74ef7
 )
 
 require (
-	github.com/btcsuite/btcd/btcec/v2 v2.3.0
+	github.com/btcsuite/btcd/btcec/v2 v2.2.1
 	github.com/btcsuite/btcd/btcutil v1.1.2
 	github.com/cosmos/gogoproto v1.4.2
 	github.com/gofrs/uuid v4.3.0+incompatible
 	github.com/google/uuid v1.3.0
 	github.com/oasisprotocol/curve25519-voi v0.0.0-20220708102147-0a8a51822cae
-	github.com/vektra/mockery/v2 v2.14.1
+	github.com/vektra/mockery/v2 v2.14.0
 	gonum.org/v1/gonum v0.12.0
-	google.golang.org/protobuf v1.28.2-0.20220831092852-f930b1dc76e8
+	google.golang.org/protobuf v1.28.1
 )
 
 require (
 	4d63.com/gochecknoglobals v0.1.0 // indirect
-	github.com/Abirdcfly/dupword v0.0.7 // indirect
 	github.com/Antonboom/errname v0.1.7 // indirect
 	github.com/Antonboom/nilnil v0.1.1 // indirect
 	github.com/Azure/go-ansiterm v0.0.0-20210617225240-d185dfc1b5a1 // indirect
@@ -65,9 +64,9 @@ require (
 	github.com/Djarvur/go-err113 v0.0.0-20210108212216-aea10b59be24 // indirect
 	github.com/GaijinEntertainment/go-exhaustruct/v2 v2.3.0 // indirect
 	github.com/Masterminds/semver v1.5.0 // indirect
-	github.com/Microsoft/go-winio v0.6.0 // indirect
+	github.com/Microsoft/go-winio v0.5.2 // indirect
 	github.com/Nvveen/Gotty v0.0.0-20120604004816-cd527374f1e5 // indirect
-	github.com/OpenPeeDeeP/depguard v1.1.1 // indirect
+	github.com/OpenPeeDeeP/depguard v1.1.0 // indirect
 	github.com/alexkohler/prealloc v1.0.0 // indirect
 	github.com/alingse/asasalint v0.0.11 // indirect
 	github.com/ashanbrown/forbidigo v1.3.0 // indirect
@@ -78,8 +77,7 @@ require (
 	github.com/bombsimon/wsl/v3 v3.3.0 // indirect
 	github.com/breml/bidichk v0.2.3 // indirect
 	github.com/breml/errchkjson v0.3.0 // indirect
-	github.com/bufbuild/connect-go v1.0.0 // indirect
-	github.com/bufbuild/protocompile v0.1.0 // indirect
+	github.com/bufbuild/connect-go v0.4.0 // indirect
 	github.com/butuzov/ireturn v0.1.1 // indirect
 	github.com/cespare/xxhash v1.1.0 // indirect
 	github.com/cespare/xxhash/v2 v2.1.2 // indirect
@@ -89,8 +87,8 @@ require (
 	github.com/containerd/continuity v0.3.0 // indirect
 	github.com/containerd/typeurl v1.0.2 // indirect
 	github.com/cpuguy83/go-md2man/v2 v2.0.2 // indirect
-	github.com/curioswitch/go-reassign v0.2.0 // indirect
-	github.com/daixiang0/gci v0.8.1 // indirect
+	github.com/curioswitch/go-reassign v0.1.2 // indirect
+	github.com/daixiang0/gci v0.6.3 // indirect
 	github.com/davecgh/go-spew v1.1.1 // indirect
 	github.com/decred/dcrd/dcrec/secp256k1/v4 v4.0.1 // indirect
 	github.com/denis-tingaikin/go-header v0.4.3 // indirect
@@ -98,9 +96,9 @@ require (
 	github.com/dgraph-io/ristretto v0.0.3-0.20200630154024-f66de99634de // indirect
 	github.com/dgryski/go-farm v0.0.0-20190423205320-6a90982ecee2 // indirect
 	github.com/docker/distribution v2.8.1+incompatible // indirect
-	github.com/docker/docker v20.10.19+incompatible // indirect
+	github.com/docker/docker v20.10.17+incompatible // indirect
 	github.com/docker/go-connections v0.4.0 // indirect
-	github.com/docker/go-units v0.5.0 // indirect
+	github.com/docker/go-units v0.4.0 // indirect
 	github.com/dustin/go-humanize v1.0.0 // indirect
 	github.com/esimonov/ifshort v1.0.4 // indirect
 	github.com/ettle/strcase v0.1.1 // indirect
@@ -110,12 +108,12 @@ require (
 	github.com/fsnotify/fsnotify v1.5.4 // indirect
 	github.com/fzipp/gocyclo v0.6.0 // indirect
 	github.com/go-chi/chi/v5 v5.0.7 // indirect
-	github.com/go-critic/go-critic v0.6.5 // indirect
+	github.com/go-critic/go-critic v0.6.4 // indirect
 	github.com/go-logr/logr v1.2.3 // indirect
 	github.com/go-logr/stdr v1.2.2 // indirect
 	github.com/go-toolsmith/astcast v1.0.0 // indirect
-	github.com/go-toolsmith/astcopy v1.0.2 // indirect
-	github.com/go-toolsmith/astequal v1.0.3 // indirect
+	github.com/go-toolsmith/astcopy v1.0.1 // indirect
+	github.com/go-toolsmith/astequal v1.0.2 // indirect
 	github.com/go-toolsmith/astfmt v1.0.0 // indirect
 	github.com/go-toolsmith/astp v1.0.0 // indirect
 	github.com/go-toolsmith/strparse v1.0.0 // indirect
@@ -129,14 +127,14 @@ require (
 	github.com/golangci/check v0.0.0-20180506172741-cfe4005ccda2 // indirect
 	github.com/golangci/dupl v0.0.0-20180902072040-3e9179ac440a // indirect
 	github.com/golangci/go-misc v0.0.0-20220329215616-d24fe342adfe // indirect
-	github.com/golangci/gofmt v0.0.0-20220901101216-f2edd75033f2 // indirect
+	github.com/golangci/gofmt v0.0.0-20190930125516-244bba706f1a // indirect
 	github.com/golangci/lint-1 v0.0.0-20191013205115-297bf364a8e0 // indirect
 	github.com/golangci/maligned v0.0.0-20180506175553-b1d89398deca // indirect
 	github.com/golangci/misspell v0.3.5 // indirect
 	github.com/golangci/revgrep v0.0.0-20220804021717-745bb2f7c2e6 // indirect
 	github.com/golangci/unconvert v0.0.0-20180507085042-28b1c447d1f4 // indirect
 	github.com/google/btree v1.0.0 // indirect
-	github.com/google/go-cmp v0.5.9 // indirect
+	github.com/google/go-cmp v0.5.8 // indirect
 	github.com/gordonklaus/ineffassign v0.0.0-20210914165742-4cc7213b9bc8 // indirect
 	github.com/gostaticanalysis/analysisutil v0.7.1 // indirect
 	github.com/gostaticanalysis/comment v1.4.2 // indirect
@@ -151,14 +149,15 @@ require (
 	github.com/inconshreveable/mousetrap v1.0.1 // indirect
 	github.com/jdxcode/netrc v0.0.0-20210204082910-926c7f70242a // indirect
 	github.com/jgautheron/goconst v1.5.1 // indirect
+	github.com/jhump/protocompile v0.0.0-20220812162104-d108583e055d // indirect
+	github.com/jhump/protoreflect v1.12.1-0.20220721211354-060cc04fc18b // indirect
 	github.com/jingyugao/rowserrcheck v1.1.1 // indirect
 	github.com/jirfag/go-printf-func-name v0.0.0-20200119135958-7558a9eaa5af // indirect
 	github.com/jmhodges/levigo v1.0.0 // indirect
 	github.com/julz/importas v0.1.0 // indirect
 	github.com/kisielk/errcheck v1.6.2 // indirect
 	github.com/kisielk/gotool v1.0.0 // indirect
-	github.com/kkHAIKE/contextcheck v1.1.3 // indirect
-	github.com/klauspost/compress v1.15.11 // indirect
+	github.com/klauspost/compress v1.15.9 // indirect
 	github.com/klauspost/pgzip v1.2.5 // indirect
 	github.com/kulti/thelper v0.6.3 // indirect
 	github.com/kunwardeep/paralleltest v1.0.6 // indirect
@@ -168,7 +167,6 @@ require (
 	github.com/leonklingele/grouper v1.1.0 // indirect
 	github.com/lufeee/execinquery v1.2.1 // indirect
 	github.com/magiconair/properties v1.8.6 // indirect
-	github.com/maratori/testableexamples v1.0.0 // indirect
 	github.com/maratori/testpackage v1.1.0 // indirect
 	github.com/matoous/godox v0.0.0-20210227103229-6504466cf951 // indirect
 	github.com/mattn/go-colorable v0.1.13 // indirect
@@ -176,20 +174,20 @@ require (
 	github.com/mattn/go-runewidth v0.0.9 // indirect
 	github.com/matttproud/golang_protobuf_extensions v1.0.2-0.20181231171920-c182affec369 // indirect
 	github.com/mbilski/exhaustivestruct v1.2.0 // indirect
-	github.com/mgechev/revive v1.2.4 // indirect
+	github.com/mgechev/revive v1.2.3 // indirect
 	github.com/mitchellh/go-homedir v1.1.0 // indirect
 	github.com/mitchellh/mapstructure v1.5.0 // indirect
-	github.com/moby/buildkit v0.10.4 // indirect
+	github.com/moby/buildkit v0.10.3 // indirect
 	github.com/moby/term v0.0.0-20220808134915-39b0c02b01ae // indirect
 	github.com/moricho/tparallel v0.2.1 // indirect
 	github.com/morikuni/aec v1.0.0 // indirect
 	github.com/nakabonne/nestif v0.3.1 // indirect
 	github.com/nbutton23/zxcvbn-go v0.0.0-20210217022336-fa2cb2858354 // indirect
-	github.com/nishanths/exhaustive v0.8.3 // indirect
+	github.com/nishanths/exhaustive v0.8.1 // indirect
 	github.com/nishanths/predeclared v0.2.2 // indirect
 	github.com/olekukonko/tablewriter v0.0.5 // indirect
 	github.com/opencontainers/go-digest v1.0.0 // indirect
-	github.com/opencontainers/image-spec v1.1.0-rc2 // indirect
+	github.com/opencontainers/image-spec v1.0.3-0.20211202183452-c5a74bcca799 // indirect
 	github.com/opencontainers/runc v1.1.3 // indirect
 	github.com/pelletier/go-toml v1.9.5 // indirect
 	github.com/pelletier/go-toml/v2 v2.0.5 // indirect
@@ -200,10 +198,10 @@ require (
 	github.com/pmezard/go-difflib v1.0.0 // indirect
 	github.com/pointlander/compress v1.1.1-0.20190518213731-ff44bd196cc3 // indirect
 	github.com/pointlander/jetset v1.0.1-0.20190518214125-eee7eff80bd4 // indirect
-	github.com/polyfloyd/go-errorlint v1.0.5 // indirect
+	github.com/polyfloyd/go-errorlint v1.0.2 // indirect
 	github.com/prometheus/procfs v0.8.0 // indirect
-	github.com/quasilyte/go-ruleguard v0.3.18 // indirect
-	github.com/quasilyte/gogrep v0.0.0-20220828223005-86e4605de09f // indirect
+	github.com/quasilyte/go-ruleguard v0.3.17 // indirect
+	github.com/quasilyte/gogrep v0.0.0-20220120141003-628d8b3623b5 // indirect
 	github.com/quasilyte/regex/syntax v0.0.0-20200407221936-30656e2c4a95 // indirect
 	github.com/quasilyte/stdinfo v0.0.0-20220114132959-f7386bf02567 // indirect
 	github.com/rs/zerolog v1.27.0 // indirect
@@ -212,7 +210,7 @@ require (
 	github.com/ryanrolds/sqlclosecheck v0.3.0 // indirect
 	github.com/sanposhiho/wastedassign/v2 v2.0.6 // indirect
 	github.com/sashamelentyev/interfacebloat v1.1.0 // indirect
-	github.com/sashamelentyev/usestdlibvars v1.20.0 // indirect
+	github.com/sashamelentyev/usestdlibvars v1.13.0 // indirect
 	github.com/satori/go.uuid v1.2.0 // indirect
 	github.com/securego/gosec/v2 v2.13.1 // indirect
 	github.com/shazow/go-diff v0.0.0-20160112020656-b6b7b6733b8c // indirect
@@ -228,15 +226,16 @@ require (
 	github.com/spf13/pflag v1.0.5 // indirect
 	github.com/ssgreg/nlreturn/v2 v2.2.1 // indirect
 	github.com/stbenjam/no-sprintf-host-port v0.1.1 // indirect
-	github.com/stretchr/objx v0.5.0 // indirect
+	github.com/stretchr/objx v0.4.0 // indirect
 	github.com/subosito/gotenv v1.4.1 // indirect
+	github.com/sylvia7788/contextcheck v1.0.6 // indirect
 	github.com/tdakkota/asciicheck v0.1.1 // indirect
 	github.com/tecbot/gorocksdb v0.0.0-20191217155057-f0fad39f321c // indirect
 	github.com/tetafro/godot v1.4.11 // indirect
 	github.com/timakin/bodyclose v0.0.0-20210704033933-f49887972144 // indirect
-	github.com/timonwong/loggercheck v0.9.3 // indirect
-	github.com/tomarrell/wrapcheck/v2 v2.7.0 // indirect
-	github.com/tommy-muehle/go-mnd/v2 v2.5.1 // indirect
+	github.com/timonwong/logrlint v0.1.0 // indirect
+	github.com/tomarrell/wrapcheck/v2 v2.6.2 // indirect
+	github.com/tommy-muehle/go-mnd/v2 v2.5.0 // indirect
 	github.com/ultraware/funlen v0.0.3 // indirect
 	github.com/ultraware/whitespace v0.0.5 // indirect
 	github.com/uudashr/gocognit v1.0.6 // indirect
@@ -245,27 +244,26 @@ require (
 	gitlab.com/bosi/decorder v0.2.3 // indirect
 	go.etcd.io/bbolt v1.3.6 // indirect
 	go.opencensus.io v0.23.0 // indirect
-	go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.36.3 // indirect
-	go.opentelemetry.io/otel v1.11.0 // indirect
-	go.opentelemetry.io/otel/metric v0.32.3 // indirect
-	go.opentelemetry.io/otel/trace v1.11.0 // indirect
+	go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.34.0 // indirect
+	go.opentelemetry.io/otel v1.9.0 // indirect
+	go.opentelemetry.io/otel/trace v1.9.0 // indirect
 	go.uber.org/atomic v1.10.0 // indirect
 	go.uber.org/multierr v1.8.0 // indirect
-	go.uber.org/zap v1.23.0 // indirect
+	go.uber.org/zap v1.22.0 // indirect
 	golang.org/x/exp v0.0.0-20220722155223-a9213eeb770e // indirect
-	golang.org/x/exp/typeparams v0.0.0-20220827204233-334a2380cb91 // indirect
-	golang.org/x/mod v0.6.0 // indirect
-	golang.org/x/sync v0.0.0-20220929204114-8fcdb60fdcc0 // indirect
-	golang.org/x/sys v0.1.0 // indirect
-	golang.org/x/term v0.1.0 // indirect
-	golang.org/x/text v0.4.0 // indirect
-	golang.org/x/tools v0.2.0 // indirect
-	google.golang.org/genproto v0.0.0-20221014213838-99cd37c6964a // indirect
+	golang.org/x/exp/typeparams v0.0.0-20220613132600-b0d781184e0d // indirect
+	golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4 // indirect
+	golang.org/x/sync v0.0.0-20220819030929-7fc1605a5dde // indirect
+	golang.org/x/sys v0.0.0-20220818161305-2296e01440c6 // indirect
+	golang.org/x/term v0.0.0-20220722155259-a9ba230a4035 // indirect
+	golang.org/x/text v0.3.7 // indirect
+	golang.org/x/tools v0.1.12 // indirect
+	google.golang.org/genproto v0.0.0-20220725144611-272f38e5d71b // indirect
 	gopkg.in/ini.v1 v1.67.0 // indirect
 	gopkg.in/yaml.v2 v2.4.0 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 	honnef.co/go/tools v0.3.3 // indirect
-	mvdan.cc/gofumpt v0.4.0 // indirect
+	mvdan.cc/gofumpt v0.3.1 // indirect
 	mvdan.cc/interfacer v0.0.0-20180901003855-c20040233aed // indirect
 	mvdan.cc/lint v0.0.0-20170908181259-adc824a0674b // indirect
 	mvdan.cc/unparam v0.0.0-20220706161116-678bad134442 // indirect