Merge branch 'main' into cal/local-sync-adr

This change reduces the number of Precommit messages sent to peers by 50%. 

During the `ApplyNewRoundStepMessage`, we update the known state of the peer sending us the message.

We set the value of `ps.PRS.Precommits` to nil in this method if the peer is entering a new height or round.
34ca3fb474/consensus/reactor.go (L1368)

We then assign `ps.PRS.LastCommit = ps.PRS.Precommits` if the peer is entering a new height only - this does not happen during just a round change. This therefore results in `ps.PRS.LastCommit` having the value `nil`. 

When the `LastCommit` bit field is seen as `nil` in the reactor, an empty bit field is initialized.
34ca3fb474/consensus/reactor.go (L1273)

The code responsible for gossiping votes from the previous height uses this `LastCommit` value and, seeing an empty `LastCommit` will resend every `Precommit` from the previous height since it lost the information it previously had detailing which precommits from the previous height the peer had.

This can be seen in the code responsible for gossiping precommits from the previous height:
34ca3fb474/consensus/reactor.go (L773)

Where this code grabs the, previously `nil`, `LastCommit` bit field:
34ca3fb474/consensus/reactor.go (L1204-L1212)

---

#### PR checklist

- [ ] Tests written/updated, or no tests needed
- [ ] `CHANGELOG_PENDING.md` updated, or no changelog entry needed
- [ ] Updated relevant documentation (`docs/`) and code comments, or no
      documentation updates needed

.github/CODEOWNERS

@@ -7,6 +7,6 @@
 # global owners are only requested if there isn't a more specific
 # codeowner specified below. For this reason, the global codeowners
 # are often repeated in package-level definitions.
-*     @ebuchman @tendermint/tendermint-engineering
+*     @ebuchman @tendermint/tendermint-engineering @adizere @lasarojc
 
-/spec @ebuchman @tendermint/tendermint-research @tendermint/tendermint-engineering
+/spec @ebuchman @tendermint/tendermint-research @tendermint/tendermint-engineering @adizere @lasarojc

.github/dependabot.yml

@@ -53,10 +53,10 @@ updates:
   - package-ecosystem: gomod
     directory: "/"
     schedule:
-      interval: weekly
+      interval: daily
     target-branch: "v0.37.x"
-    # Only allow automated security-related dependency updates until we cut the
-    # final v0.37.0 release.
+    # Only allow automated security-related dependency updates on release
+    # branches.
     open-pull-requests-limit: 0
     labels:
       - T:dependencies
@@ -65,9 +65,11 @@ updates:
   - package-ecosystem: gomod
     directory: "/"
     schedule:
-      interval: weekly
+      interval: daily
     target-branch: "v0.34.x"
-    open-pull-requests-limit: 10
+    # Only allow automated security-related dependency updates on release
+    # branches.
+    open-pull-requests-limit: 0
     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@v2.0.0
+        uses: docker/setup-buildx-action@v2.2.1
 
       - name: Login to DockerHub
         if: ${{ github.event_name != 'pull_request' }}
-        uses: docker/login-action@v2.0.0
+        uses: docker/login-action@v2.1.0
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Publish to Docker Hub
-        uses: docker/build-push-action@v3.1.1
+        uses: docker/build-push-action@v3.2.0
         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@v1.22.0
+        uses: slackapi/slack-github-action@v1.23.0
         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> that caused the failure."
+                    "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."
                   }
                 }
               ]

.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@v1.22.0
+        uses: slackapi/slack-github-action@v1.23.0
         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> that caused the failure."
+                    "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."
                   }
                 }
               ]

.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@v1.22.0
+        uses: slackapi/slack-github-action@v1.23.0
         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> that caused the failure."
+                    "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."
                   }
                 }
               ]

.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@v1.22.0
+        uses: slackapi/slack-github-action@v1.23.0
         env:
           SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
           SLACK_WEBHOOK_TYPE: INCOMING_WEBHOOK

.github/workflows/gosec.yml

@@ -1,41 +0,0 @@
-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@0.10.1
+      - uses: styfle/cancel-workflow-action@0.11.0
         with:
           workflow_id: 1041851,1401230,2837803
           access_token: ${{ github.token }}

.github/workflows/lint.yml

@@ -31,10 +31,7 @@ jobs:
             go.sum
       - uses: golangci/golangci-lint-action@v3
         with:
-          # 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
+          version: v1.50.1
           args: --timeout 10m
           github-token: ${{ secrets.github_token }}
         if: env.GIT_DIFF

.github/workflows/markdown-links.yml

@@ -1,23 +1,20 @@
 name: Check Markdown links
 
 on:
-  push:
-    branches:
-      - main
-  pull_request:
-    branches: [main]
+  schedule:
+    # 2am UTC daily
+    - cron: '0 2 * * *'
 
 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:
-          PATTERNS: |
-            **/**.md
-      - uses: creachadair/github-action-markdown-link-check@master
+          ref: ${{ matrix.branch }}
+      - uses: informalsystems/github-action-markdown-link-check@main
         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:
-  goreleaser:
+  prerelease:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
@@ -38,3 +38,28 @@ 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@v1.23.0
+        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@v1.8.0
+      - uses: bufbuild/buf-setup-action@v1.9.0
       - 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:
-  goreleaser:
+  release:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
@@ -35,3 +35,28 @@ 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@v1.23.0
+        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

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

.golangci.yml

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

.md-link-check.json

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

CHANGELOG.md

@@ -2,6 +2,76 @@
 
 Friendly reminder, we have a [bug bounty program](https://hackerone.com/cosmos).
 
+## v0.34.23
+
+*Nov 9, 2022*
+
+This release introduces some new Prometheus metrics to help in determining what
+kinds of messages are consuming the most P2P bandwidth. This builds towards our
+broader goal of optimizing Tendermint bandwidth consumption, and will give us
+meaningful insights once we can establish these metrics for a number of chains.
+
+We now also return `Cache-Control` headers for select RPC endpoints to help
+facilitate caching.
+
+Special thanks to external contributors on this release: @JayT106
+
+### IMPROVEMENTS
+- `[p2p]` [\#9641](https://github.com/tendermint/tendermint/issues/9641) Add new
+  Envelope type and associated methods for sending and receiving Envelopes
+  instead of raw bytes. This also adds new metrics,
+  `tendermint_p2p_message_send_bytes_total` and
+  `tendermint_p2p_message_receive_bytes_total`, that expose how many bytes of
+  each message type have been sent.
+- `[rpc]` [\#9666](https://github.com/tendermint/tendermint/issues/9666) Enable
+  caching of RPC responses (@JayT106)
+
+  The following RPC endpoints will return `Cache-Control` headers with a maximum
+  age of 1 day:
+
+  - `/abci_info`
+  - `/block`, if `height` is supplied
+  - `/block_by_hash`
+  - `/block_results`, if `height` is supplied
+  - `/blockchain`
+  - `/check_tx`
+  - `/commit`, if `height` is supplied
+  - `/consensus_params`, if `height` is supplied
+  - `/genesis`
+  - `/genesis_chunked`
+  - `/tx`
+  - `/validators`, if `height` is supplied
+
+## 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

@@ -11,26 +11,35 @@
 - P2P Protocol
 
 - Go API
+  - [p2p] \#9625 Remove unused p2p/trust package (@cmwaters)
 
 - Blockchain Protocol
 
 - Data Storage
   - [state] \#6541 Move pruneBlocks from consensus/state to state/execution. (@JayT106)
-  
+
 - Tooling
   - [tools/tm-signer-harness] \#6498 Set OS home dir to instead of the hardcoded PATH. (@JayT106)
+  - [metrics] \#9682 move state-syncing and block-syncing metrics to their respective packages (@cmwaters)
+    labels have moved from block_syncing -> blocksync_syncing and state_syncing -> statesync_syncing
 
 ### FEATURES
 
+- [config] \#9680 Introduce `BootstrapPeers` to the config to allow nodes to list peers to be added to
+  the addressbook upon start up (@cmwaters)
+
 ### IMPROVEMENTS
 
 - [pubsub] \#7319 Performance improvements for the event query API (@creachadair)
 - [p2p/pex] \#6509 Improve addrBook.hash performance (@cuonglm)
 - [crypto/merkle] \#6443 & \#6513 Improve HashAlternatives performance (@cuonglm, @marbar3778)
+- [rpc] \#9650 Enable caching of RPC responses (@JayT106)
+- [consensus] \#9760 Save peer LastCommit correctly to achieve 50% reduction in gossiped precommits. (@williambanfield)
 
 ### BUG FIXES
 
 - [docker] \#9462 ensure Docker image uses consistent version of Go
+- [abci-cli] \#9717 fix broken abci-cli help command
 
 ## v0.37.0
 
@@ -96,3 +105,4 @@ Friendly reminder, we have a [bug bounty program](https://hackerone.com/tendermi
 
 - [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 characteristic.
+  race, ethnicity, age, religion, nationality, or other similar characteristics.
 
 * 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 start when looking for places to contribute. If you
+is a good place to 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 effects multiple APIs/users should be recorded multiply - for
+Any change that affects 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 it's
+instructions should be in place for a user on how he/she can upgrade its
 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

@@ -271,7 +271,7 @@ format:
 
 lint:
 	@echo "--> Running linter"
-	@golangci-lint run
+	@go run github.com/golangci/golangci-lint/cmd/golangci-lint run
 .PHONY: lint
 
 DESTINATION = ./index.html.md

README.md

@@ -113,10 +113,15 @@ For more information on upgrading, see [UPGRADING.md](./UPGRADING.md).
 
 ### Supported Versions
 
-Because we are a small core team, we only ship patch updates, including security
-updates, to the most recent minor release and the second-most recent minor
-release. Consequently, we strongly recommend keeping Tendermint up-to-date.
-Upgrading instructions can be found in [UPGRADING.md](./UPGRADING.md).
+Because we are a small core team, we have limited capacity to ship patch
+updates, including security updates. Consequently, we strongly recommend keeping
+Tendermint up-to-date. Upgrading instructions can be found in
+[UPGRADING.md](./UPGRADING.md).
+
+Currently supported versions include:
+
+- v0.34.x
+- v0.37.x (release candidate)
 
 ## Resources
 

STYLE_GUIDE.md

@@ -98,7 +98,7 @@ Sometimes it's necessary to rename libraries to avoid naming collisions or ambig
     * Make use of table driven testing where possible and not-cumbersome
         * [Inspiration](https://dave.cheney.net/2013/06/09/writing-table-driven-tests-in-go)
     * Make use of [assert](https://godoc.org/github.com/stretchr/testify/assert) and [require](https://godoc.org/github.com/stretchr/testify/require)
-* When using mocks, it is recommended to use Testify [mock] (<https://pkg.go.dev/github.com/stretchr/testify/mock>
+* When using mocks, it is recommended to use Testify [mock](<https://pkg.go.dev/github.com/stretchr/testify/mock>
  ) along with [Mockery](https://github.com/vektra/mockery) for autogeneration
 
 ## Errors

UPGRADING.md

@@ -5,6 +5,15 @@ Tendermint Core.
 
 ## Unreleased
 
+## Config Changes
+
+* A new config field, `BootstrapPeers` has been introduced as a means of
+  adding a list of addresses to the addressbook upon initializing a node. This is an
+  alternative to `PersistentPeers`. `PersistentPeers` shold be only used for
+  nodes that you want to keep a constant connection with i.e. sentry nodes
+
+----
+
 ### ABCI Changes
 
 * The `ABCIVersion` is now `1.0.0`.

abci/client/local_client.go

@@ -6,8 +6,6 @@ import (
 	tmsync "github.com/tendermint/tendermint/libs/sync"
 )
 
-var _ Client = (*localClient)(nil)
-
 // NOTE: use defer to unlock mutex because Application might panic (e.g., in
 // case of malicious tx or query). It only makes sense for publicly exposed
 // methods like CheckTx (/broadcast_tx_* RPC endpoint) or Query (/abci_query
@@ -24,8 +22,6 @@ var _ Client = (*localClient)(nil)
 
 // NewLocalClient creates a local client, which will be directly calling the
 // methods of the given app.
-//
-// Both Async and Sync methods ignore the given context.Context parameter.
 func NewLocalClient(mtx *tmsync.Mutex, app types.Application) Client {
 	if mtx == nil {
 		mtx = new(tmsync.Mutex)
@@ -309,7 +305,8 @@ func (app *localClient) OfferSnapshotSync(req types.RequestOfferSnapshot) (*type
 }
 
 func (app *localClient) LoadSnapshotChunkSync(
-	req types.RequestLoadSnapshotChunk) (*types.ResponseLoadSnapshotChunk, error) {
+	req types.RequestLoadSnapshotChunk,
+) (*types.ResponseLoadSnapshotChunk, error) {
 	app.mtx.Lock()
 	defer app.mtx.Unlock()
 
@@ -318,7 +315,8 @@ func (app *localClient) LoadSnapshotChunkSync(
 }
 
 func (app *localClient) ApplySnapshotChunkSync(
-	req types.RequestApplySnapshotChunk) (*types.ResponseApplySnapshotChunk, error) {
+	req types.RequestApplySnapshotChunk,
+) (*types.ResponseApplySnapshotChunk, error) {
 	app.mtx.Lock()
 	defer app.mtx.Unlock()
 

abci/client/unsync_local_client.go

@@ -0,0 +1,263 @@
+package abcicli
+
+import (
+	"sync"
+
+	types "github.com/tendermint/tendermint/abci/types"
+	"github.com/tendermint/tendermint/libs/service"
+)
+
+type unsyncLocalClient struct {
+	service.BaseService
+
+	types.Application
+
+	// This mutex is exclusively used to protect the callback.
+	mtx sync.RWMutex
+	Callback
+}
+
+var _ Client = (*unsyncLocalClient)(nil)
+
+// NewUnsyncLocalClient creates an unsynchronized local client, which will be
+// directly calling the methods of the given app.
+//
+// Unlike NewLocalClient, it does not hold a mutex around the application, so
+// it is up to the application to manage its synchronization properly.
+func NewUnsyncLocalClient(app types.Application) Client {
+	cli := &unsyncLocalClient{
+		Application: app,
+	}
+	cli.BaseService = *service.NewBaseService(nil, "unsyncLocalClient", cli)
+	return cli
+}
+
+func (app *unsyncLocalClient) SetResponseCallback(cb Callback) {
+	app.mtx.Lock()
+	defer app.mtx.Unlock()
+	app.Callback = cb
+}
+
+// TODO: change types.Application to include Error()?
+func (app *unsyncLocalClient) Error() error {
+	return nil
+}
+
+func (app *unsyncLocalClient) FlushAsync() *ReqRes {
+	// Do nothing
+	return newLocalReqRes(types.ToRequestFlush(), nil)
+}
+
+func (app *unsyncLocalClient) EchoAsync(msg string) *ReqRes {
+	return app.callback(
+		types.ToRequestEcho(msg),
+		types.ToResponseEcho(msg),
+	)
+}
+
+func (app *unsyncLocalClient) InfoAsync(req types.RequestInfo) *ReqRes {
+	res := app.Application.Info(req)
+	return app.callback(
+		types.ToRequestInfo(req),
+		types.ToResponseInfo(res),
+	)
+}
+
+func (app *unsyncLocalClient) DeliverTxAsync(params types.RequestDeliverTx) *ReqRes {
+	res := app.Application.DeliverTx(params)
+	return app.callback(
+		types.ToRequestDeliverTx(params),
+		types.ToResponseDeliverTx(res),
+	)
+}
+
+func (app *unsyncLocalClient) CheckTxAsync(req types.RequestCheckTx) *ReqRes {
+	res := app.Application.CheckTx(req)
+	return app.callback(
+		types.ToRequestCheckTx(req),
+		types.ToResponseCheckTx(res),
+	)
+}
+
+func (app *unsyncLocalClient) QueryAsync(req types.RequestQuery) *ReqRes {
+	res := app.Application.Query(req)
+	return app.callback(
+		types.ToRequestQuery(req),
+		types.ToResponseQuery(res),
+	)
+}
+
+func (app *unsyncLocalClient) CommitAsync() *ReqRes {
+	res := app.Application.Commit()
+	return app.callback(
+		types.ToRequestCommit(),
+		types.ToResponseCommit(res),
+	)
+}
+
+func (app *unsyncLocalClient) InitChainAsync(req types.RequestInitChain) *ReqRes {
+	res := app.Application.InitChain(req)
+	return app.callback(
+		types.ToRequestInitChain(req),
+		types.ToResponseInitChain(res),
+	)
+}
+
+func (app *unsyncLocalClient) BeginBlockAsync(req types.RequestBeginBlock) *ReqRes {
+	res := app.Application.BeginBlock(req)
+	return app.callback(
+		types.ToRequestBeginBlock(req),
+		types.ToResponseBeginBlock(res),
+	)
+}
+
+func (app *unsyncLocalClient) EndBlockAsync(req types.RequestEndBlock) *ReqRes {
+	res := app.Application.EndBlock(req)
+	return app.callback(
+		types.ToRequestEndBlock(req),
+		types.ToResponseEndBlock(res),
+	)
+}
+
+func (app *unsyncLocalClient) ListSnapshotsAsync(req types.RequestListSnapshots) *ReqRes {
+	res := app.Application.ListSnapshots(req)
+	return app.callback(
+		types.ToRequestListSnapshots(req),
+		types.ToResponseListSnapshots(res),
+	)
+}
+
+func (app *unsyncLocalClient) OfferSnapshotAsync(req types.RequestOfferSnapshot) *ReqRes {
+	res := app.Application.OfferSnapshot(req)
+	return app.callback(
+		types.ToRequestOfferSnapshot(req),
+		types.ToResponseOfferSnapshot(res),
+	)
+}
+
+func (app *unsyncLocalClient) LoadSnapshotChunkAsync(req types.RequestLoadSnapshotChunk) *ReqRes {
+	res := app.Application.LoadSnapshotChunk(req)
+	return app.callback(
+		types.ToRequestLoadSnapshotChunk(req),
+		types.ToResponseLoadSnapshotChunk(res),
+	)
+}
+
+func (app *unsyncLocalClient) ApplySnapshotChunkAsync(req types.RequestApplySnapshotChunk) *ReqRes {
+	res := app.Application.ApplySnapshotChunk(req)
+	return app.callback(
+		types.ToRequestApplySnapshotChunk(req),
+		types.ToResponseApplySnapshotChunk(res),
+	)
+}
+
+func (app *unsyncLocalClient) PrepareProposalAsync(req types.RequestPrepareProposal) *ReqRes {
+	res := app.Application.PrepareProposal(req)
+	return app.callback(
+		types.ToRequestPrepareProposal(req),
+		types.ToResponsePrepareProposal(res),
+	)
+}
+
+func (app *unsyncLocalClient) ProcessProposalAsync(req types.RequestProcessProposal) *ReqRes {
+	res := app.Application.ProcessProposal(req)
+	return app.callback(
+		types.ToRequestProcessProposal(req),
+		types.ToResponseProcessProposal(res),
+	)
+}
+
+//-------------------------------------------------------
+
+func (app *unsyncLocalClient) FlushSync() error {
+	return nil
+}
+
+func (app *unsyncLocalClient) EchoSync(msg string) (*types.ResponseEcho, error) {
+	return &types.ResponseEcho{Message: msg}, nil
+}
+
+func (app *unsyncLocalClient) InfoSync(req types.RequestInfo) (*types.ResponseInfo, error) {
+	res := app.Application.Info(req)
+	return &res, nil
+}
+
+func (app *unsyncLocalClient) DeliverTxSync(req types.RequestDeliverTx) (*types.ResponseDeliverTx, error) {
+	res := app.Application.DeliverTx(req)
+	return &res, nil
+}
+
+func (app *unsyncLocalClient) CheckTxSync(req types.RequestCheckTx) (*types.ResponseCheckTx, error) {
+	res := app.Application.CheckTx(req)
+	return &res, nil
+}
+
+func (app *unsyncLocalClient) QuerySync(req types.RequestQuery) (*types.ResponseQuery, error) {
+	res := app.Application.Query(req)
+	return &res, nil
+}
+
+func (app *unsyncLocalClient) CommitSync() (*types.ResponseCommit, error) {
+	res := app.Application.Commit()
+	return &res, nil
+}
+
+func (app *unsyncLocalClient) InitChainSync(req types.RequestInitChain) (*types.ResponseInitChain, error) {
+	res := app.Application.InitChain(req)
+	return &res, nil
+}
+
+func (app *unsyncLocalClient) BeginBlockSync(req types.RequestBeginBlock) (*types.ResponseBeginBlock, error) {
+	res := app.Application.BeginBlock(req)
+	return &res, nil
+}
+
+func (app *unsyncLocalClient) EndBlockSync(req types.RequestEndBlock) (*types.ResponseEndBlock, error) {
+	res := app.Application.EndBlock(req)
+	return &res, nil
+}
+
+func (app *unsyncLocalClient) ListSnapshotsSync(req types.RequestListSnapshots) (*types.ResponseListSnapshots, error) {
+	res := app.Application.ListSnapshots(req)
+	return &res, nil
+}
+
+func (app *unsyncLocalClient) OfferSnapshotSync(req types.RequestOfferSnapshot) (*types.ResponseOfferSnapshot, error) {
+	res := app.Application.OfferSnapshot(req)
+	return &res, nil
+}
+
+func (app *unsyncLocalClient) LoadSnapshotChunkSync(
+	req types.RequestLoadSnapshotChunk,
+) (*types.ResponseLoadSnapshotChunk, error) {
+	res := app.Application.LoadSnapshotChunk(req)
+	return &res, nil
+}
+
+func (app *unsyncLocalClient) ApplySnapshotChunkSync(
+	req types.RequestApplySnapshotChunk,
+) (*types.ResponseApplySnapshotChunk, error) {
+	res := app.Application.ApplySnapshotChunk(req)
+	return &res, nil
+}
+
+func (app *unsyncLocalClient) PrepareProposalSync(req types.RequestPrepareProposal) (*types.ResponsePrepareProposal, error) {
+	res := app.Application.PrepareProposal(req)
+	return &res, nil
+}
+
+func (app *unsyncLocalClient) ProcessProposalSync(req types.RequestProcessProposal) (*types.ResponseProcessProposal, error) {
+	res := app.Application.ProcessProposal(req)
+	return &res, nil
+}
+
+//-------------------------------------------------------
+
+func (app *unsyncLocalClient) callback(req *types.Request, res *types.Response) *ReqRes {
+	app.mtx.RLock()
+	defer app.mtx.RUnlock()
+	app.Callback(req, res)
+	rr := newLocalReqRes(req, res)
+	rr.callbackInvoked = true
+	return rr
+}

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

@@ -54,7 +54,7 @@ var RootCmd = &cobra.Command{
 	PersistentPreRunE: func(cmd *cobra.Command, args []string) error {
 
 		switch cmd.Use {
-		case "kvstore", "version":
+		case "kvstore", "version", "help [command]":
 			return nil
 		}
 

abci/tests/test_cli/test.sh

@@ -38,8 +38,34 @@ function testExample() {
 	rm "${INPUT}".out.new
 }
 
+function testHelp() {
+	INPUT=$1
+	APP="$2 $3"
+
+	echo "Test: $APP"
+	$APP &> "${INPUT}.new" &
+	sleep 2
+
+	pre=$(shasum < "${INPUT}")
+	post=$(shasum < "${INPUT}.new")
+
+	if [[ "$pre" != "$post" ]]; then
+		echo "You broke the tutorial"
+		echo "Got:"
+		cat "${INPUT}.new"
+		echo "Expected:"
+		cat "${INPUT}"
+		echo "Diff:"
+		diff "${INPUT}" "${INPUT}.new"
+		exit 1
+	fi
+
+	rm "${INPUT}".new
+}
+
 testExample 1 tests/test_cli/ex1.abci abci-cli kvstore
 testExample 2 tests/test_cli/ex2.abci abci-cli kvstore
+testHelp tests/test_cli/testHelp.out abci-cli help
 
 echo ""
 echo "PASS"

abci/tests/test_cli/testHelp.out

@@ -0,0 +1,30 @@
+the ABCI CLI tool wraps an ABCI client and is used for testing ABCI servers
+
+Usage:
+  abci-cli [command]
+
+Available Commands:
+  batch            run a batch of abci commands against an application
+  check_tx         validate a transaction
+  commit           commit the application state and return the Merkle root hash
+  completion       Generate the autocompletion script for the specified shell
+  console          start an interactive ABCI console for multiple commands
+  deliver_tx       deliver a new transaction to the application
+  echo             have the application echo a message
+  help             Help about any command
+  info             get some info about the application
+  kvstore          ABCI demo example
+  prepare_proposal prepare proposal
+  process_proposal process proposal
+  query            query the application state
+  test             run integration tests
+  version          print ABCI console version
+
+Flags:
+      --abci string        either socket or grpc (default "socket")
+      --address string     address of application socket (default "tcp://0.0.0.0:26658")
+  -h, --help               help for abci-cli
+      --log_level string   set the logger level (default "debug")
+  -v, --verbose            print the command and results as if it were a console session
+
+Use "abci-cli [command] --help" for more information about a command.

abci/types/messages.go

@@ -4,6 +4,7 @@ import (
 	"io"
 
 	"github.com/cosmos/gogoproto/proto"
+
 	"github.com/tendermint/tendermint/libs/protoio"
 )
 

blocksync/metrics.gen.go

@@ -0,0 +1,30 @@
+// 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

@@ -0,0 +1,19 @@
+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

@@ -19,58 +19,6 @@ 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 TestBlockchainMessageVectors(t *testing.T) {
+func TestBlocksyncMessageVectors(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

@@ -32,6 +32,7 @@ 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
@@ -602,7 +603,7 @@ OUTER_LOOP:
 			}
 			peer = bpr.pool.pickIncrAvailablePeer(bpr.height)
 			if peer == nil {
-				// log.Info("No peers available", "height", height)
+				bpr.Logger.Debug("No peers currently available; will retry shortly", "height", bpr.height)
 				time.Sleep(requestIntervalMS * time.Millisecond)
 				continue PICK_PEER_LOOP
 			}
@@ -612,6 +613,7 @@ 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:
@@ -624,6 +626,11 @@ 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

@@ -30,7 +30,7 @@ const (
 )
 
 type consensusReactor interface {
-	// for when we switch from blockchain reactor and block sync to
+	// for when we switch from blocksync reactor and block sync to
 	// the consensus machine
 	SwitchToConsensus(state sm.State, skipWAL bool)
 }
@@ -58,11 +58,13 @@ type Reactor struct {
 
 	requestsCh <-chan BlockRequest
 	errorsCh   <-chan peerError
+
+	metrics *Metrics
 }
 
 // NewReactor returns new reactor instance.
 func NewReactor(state sm.State, blockExec *sm.BlockExecutor, store *store.BlockStore,
-	blockSync bool) *Reactor {
+	blockSync bool, metrics *Metrics) *Reactor {
 
 	if state.LastBlockHeight != store.Height() {
 		panic(fmt.Sprintf("state (%v) and store (%v) height mismatch", state.LastBlockHeight,
@@ -88,6 +90,7 @@ func NewReactor(state sm.State, blockExec *sm.BlockExecutor, store *store.BlockS
 		blockSync:    blockSync,
 		requestsCh:   requestsCh,
 		errorsCh:     errorsCh,
+		metrics:      metrics,
 	}
 	bcR.BaseReactor = *p2p.NewBaseReactor("Reactor", bcR)
 	return bcR
@@ -143,21 +146,20 @@ 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) {
-	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)
+	peer.Send(p2p.Envelope{
+		ChannelID: BlocksyncChannel,
+		Message: &bcproto.StatusResponse{
+			Base:   bcR.store.Base(),
+			Height: bcR.store.Height(),
+		},
+	})
 	// it's OK if send fails. will try later in poolRoutine
 
 	// peer is added to the pool once we receive the first
@@ -182,69 +184,53 @@ func (bcR *Reactor) respondToPeer(msg *bcproto.BlockRequest,
 			return false
 		}
 
-		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)
+		return src.TrySend(p2p.Envelope{
+			ChannelID: BlocksyncChannel,
+			Message:   &bcproto.BlockResponse{Block: bl},
+		})
 	}
 
 	bcR.Logger.Info("Peer asking for a block we don't have", "src", src, "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)
+	return src.TrySend(p2p.Envelope{
+		ChannelID: BlocksyncChannel,
+		Message:   &bcproto.NoBlockResponse{Height: msg.Height},
+	})
 }
 
 // Receive implements Reactor by handling 4 types of messages (look below).
-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)
+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)
 		return
 	}
 
-	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
-	}
+	bcR.Logger.Debug("Receive", "e.Src", e.Src, "chID", e.ChannelID, "msg", e.Message)
 
-	bcR.Logger.Debug("Receive", "src", src, "chID", chID, "msg", msg)
-
-	switch msg := msg.(type) {
+	switch msg := e.Message.(type) {
 	case *bcproto.BlockRequest:
-		bcR.respondToPeer(msg, src)
+		bcR.respondToPeer(msg, e.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(src.ID(), bi, len(msgBytes))
+		bcR.pool.AddBlock(e.Src.ID(), bi, msg.Block.Size())
 	case *bcproto.StatusRequest:
 		// Send peer our state.
-		msgBytes, err := EncodeMsg(&bcproto.StatusResponse{
-			Height: bcR.store.Height(),
-			Base:   bcR.store.Base(),
+		e.Src.TrySend(p2p.Envelope{
+			ChannelID: BlocksyncChannel,
+			Message: &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(src.ID(), msg.Base, msg.Height)
+		bcR.pool.SetPeerRange(e.Src.ID(), msg.Base, msg.Height)
 	case *bcproto.NoBlockResponse:
-		bcR.Logger.Debug("Peer does not have requested block", "peer", src, "height", msg.Height)
+		bcR.Logger.Debug("Peer does not have requested block", "peer", e.Src, "height", msg.Height)
 	default:
 		bcR.Logger.Error(fmt.Sprintf("Unknown message type %v", reflect.TypeOf(msg)))
 	}
@@ -253,6 +239,8 @@ func (bcR *Reactor) Receive(chID byte, src p2p.Peer, msgBytes []byte) {
 // 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()
@@ -285,13 +273,10 @@ func (bcR *Reactor) poolRoutine(stateSynced bool) {
 				if peer == nil {
 					continue
 				}
-				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)
+				queued := peer.TrySend(p2p.Envelope{
+					ChannelID: BlocksyncChannel,
+					Message:   &bcproto.BlockRequest{Height: request.Height},
+				})
 				if !queued {
 					bcR.Logger.Debug("Send queue is full, drop block request", "peer", peer.ID(), "height", request.Height)
 				}
@@ -303,7 +288,7 @@ func (bcR *Reactor) poolRoutine(stateSynced bool) {
 
 			case <-statusUpdateTicker.C:
 				// ask for status updates
-				go bcR.BroadcastStatusRequest() //nolint: errcheck
+				go bcR.BroadcastStatusRequest()
 
 			}
 		}
@@ -429,14 +414,9 @@ FOR_LOOP:
 }
 
 // BroadcastStatusRequest broadcasts `BlockStore` base and height.
-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
+func (bcR *Reactor) BroadcastStatusRequest() {
+	bcR.Switch.Broadcast(p2p.Envelope{
+		ChannelID: BlocksyncChannel,
+		Message:   &bcproto.StatusRequest{},
+	})
 }

blocksync/reactor_test.go

@@ -145,14 +145,14 @@ func newReactor(
 		blockStore.SaveBlock(thisBlock, thisParts, lastCommit)
 	}
 
-	bcReactor := NewReactor(state.Copy(), blockExec, blockStore, fastSync)
-	bcReactor.SetLogger(logger.With("module", "blockchain"))
+	bcReactor := NewReactor(state.Copy(), blockExec, blockStore, fastSync, NopMetrics())
+	bcReactor.SetLogger(logger.With("module", "blocksync"))
 
 	return ReactorPair{bcReactor, proxyApp}
 }
 
 func TestNoBlockResponse(t *testing.T) {
-	config = test.ResetTestRoot("blockchain_reactor_test")
+	config = test.ResetTestRoot("blocksync_reactor_test")
 	defer os.RemoveAll(config.RootDir)
 	genDoc, privVals := randGenesisDoc(1, false, 30)
 
@@ -164,7 +164,7 @@ 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("BLOCKCHAIN", reactorPairs[i].reactor)
+		s.AddReactor("BLOCKSYNC", reactorPairs[i].reactor)
 		return s
 
 	}, p2p.Connect2Switches)
@@ -214,7 +214,7 @@ 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("blockchain_reactor_test")
+	config = test.ResetTestRoot("blocksync_reactor_test")
 	defer os.RemoveAll(config.RootDir)
 	genDoc, privVals := randGenesisDoc(1, false, 30)
 
@@ -239,7 +239,7 @@ 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("BLOCKCHAIN", reactorPairs[i].reactor)
+		s.AddReactor("BLOCKSYNC", reactorPairs[i].reactor)
 		return s
 
 	}, p2p.Connect2Switches)
@@ -278,7 +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("BLOCKCHAIN", reactorPairs[len(reactorPairs)-1].reactor)
+		s.AddReactor("BLOCKSYNC", reactorPairs[len(reactorPairs)-1].reactor)
 		return s
 
 	}, p2p.Connect2Switches)...)

cmd/tendermint/commands/debug/util.go

@@ -67,7 +67,8 @@ 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)
 
-	resp, err := http.Get(endpoint) //nolint: gosec
+	//nolint:gosec,nolintlint
+	resp, err := http.Get(endpoint)
 	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 bool = false
+var removeBlock = false
 
 func init() {
 	RollbackStateCmd.Flags().BoolVar(&removeBlock, "hard", false, "remove last block as well as state")

cmd/tendermint/commands/run_node.go

@@ -66,6 +66,7 @@ func AddNodeFlags(cmd *cobra.Command) {
 	cmd.Flags().String("p2p.external-address", config.P2P.ExternalAddress, "ip:port address to advertise to peers for them to dial")
 	cmd.Flags().String("p2p.seeds", config.P2P.Seeds, "comma-delimited ID@host:port seed nodes")
 	cmd.Flags().String("p2p.persistent_peers", config.P2P.PersistentPeers, "comma-delimited ID@host:port persistent peers")
+	cmd.Flags().String("p2p.bootstrap_peers", config.P2P.BootstrapPeers, "comma-delimited ID@host:port peers to be added to the addressbook on startup")
 	cmd.Flags().String("p2p.unconditional_peer_ids",
 		config.P2P.UnconditionalPeerIDs, "comma-delimited IDs of unconditional peers")
 	cmd.Flags().Bool("p2p.upnp", config.P2P.UPNP, "enable/disable UPNP port forwarding")

config/config.go

@@ -423,6 +423,7 @@ 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"`
 }
 
@@ -506,6 +507,10 @@ 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) {
@@ -543,6 +548,11 @@ type P2PConfig struct { //nolint: maligned
 	// We only use these if we can’t connect to peers in the addrbook
 	Seeds string `mapstructure:"seeds"`
 
+	// Comma separated list of peers to be added to the peer store
+	// on startup. Either BootstrapPeers or PersistentPeers are
+	// needed for peer discovery
+	BootstrapPeers string `mapstructure:"bootstrap_peers"`
+
 	// Comma separated list of nodes to keep persistent connections to
 	PersistentPeers string `mapstructure:"persistent_peers"`
 
@@ -703,14 +713,28 @@ 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"`
-	Broadcast bool   `mapstructure:"broadcast"`
-	WalPath   string `mapstructure:"wal_dir"`
+	Version string `mapstructure:"version"`
+	// RootDir is the root directory for all data. This should be configured via
+	// the $TMHOME env variable or --home cmd flag rather than overriding this
+	// struct field.
+	RootDir string `mapstructure:"home"`
+	// Recheck (default: true) defines whether Tendermint should recheck the
+	// validity for all remaining transaction in the mempool after a block.
+	// Since a block affects the application state, some transactions in the
+	// mempool may become invalid. If this does not apply to your application,
+	// you can disable rechecking.
+	Recheck bool `mapstructure:"recheck"`
+	// Broadcast (default: true) defines whether the mempool should relay
+	// transactions to other peers. Setting this to false will stop the mempool
+	// from relaying transactions to other peers until they are included in a
+	// block. In other words, if Broadcast is disabled, only the peer you send
+	// the tx to will see it until it is included in a block.
+	Broadcast bool `mapstructure:"broadcast"`
+	// WalPath (default: "") configures the location of the Write Ahead Log
+	// (WAL) for the mempool. The WAL is disabled by default. To enable, set
+	// WalPath to where you want the WAL to be written (e.g.
+	// "data/mempool.wal").
+	WalPath string `mapstructure:"wal_dir"`
 	// Maximum number of transactions in the mempool
 	Size int `mapstructure:"size"`
 	// Limit the total size of all txs in the mempool.
@@ -1204,6 +1228,10 @@ func (cfg *InstrumentationConfig) ValidateBasic() error {
 	return nil
 }
 
+func (cfg *InstrumentationConfig) IsPrometheusEnabled() bool {
+	return cfg.Prometheus && cfg.PrometheusListenAddr != ""
+}
+
 //-----------------------------------------------------------------------------
 // Utils
 

config/toml.go

@@ -283,6 +283,11 @@ external_address = "{{ .P2P.ExternalAddress }}"
 # Comma separated list of seed nodes to connect to
 seeds = "{{ .P2P.Seeds }}"
 
+# Comma separated list of peers to be added to the peer store
+# on startup. Either BootstrapPeers or PersistentPeers are
+# needed for peer discovery
+bootstrap_peers = "{{ .P2P.BootstrapPeers }}"
+
 # Comma separated list of nodes to keep persistent connections to
 persistent_peers = "{{ .P2P.PersistentPeers }}"
 
@@ -349,8 +354,24 @@ dial_timeout = "{{ .P2P.DialTimeout }}"
 #   2) "v1" - prioritized mempool.
 version = "{{ .Mempool.Version }}"
 
+# Recheck (default: true) defines whether Tendermint should recheck the
+# validity for all remaining transaction in the mempool after a block.
+# Since a block affects the application state, some transactions in the
+# mempool may become invalid. If this does not apply to your application,
+# you can disable rechecking.
 recheck = {{ .Mempool.Recheck }}
+
+# Broadcast (default: true) defines whether the mempool should relay
+# transactions to other peers. Setting this to false will stop the mempool
+# from relaying transactions to other peers until they are included in a
+# block. In other words, if Broadcast is disabled, only the peer you send
+# the tx to will see it until it is included in a block.
 broadcast = {{ .Mempool.Broadcast }}
+
+# WalPath (default: "") configures the location of the Write Ahead Log
+# (WAL) for the mempool. The WAL is disabled by default. To enable, set
+# WalPath to where you want the WAL to be written (e.g.
+# "data/mempool.wal").
 wal_dir = "{{ js .Mempool.WalPath }}"
 
 # Maximum number of transactions in the mempool
@@ -436,7 +457,7 @@ chunk_fetchers = "{{ .StateSync.ChunkFetchers }}"
 [blocksync]
 
 # Block Sync version to use:
-# 
+#
 # In v0.37, v1 and v2 of the block sync protocols were deprecated.
 # Please use v0 instead.
 #

consensus/byzantine_test.go

@@ -26,6 +26,7 @@ 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"
@@ -165,10 +166,16 @@ 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(VoteChannel, MustEncode(&VoteMessage{prevote1}))
+					peer.Send(p2p.Envelope{
+						Message:   &tmcons.Vote{Vote: prevote1.ToProto()},
+						ChannelID: VoteChannel,
+					})
 				} else {
 					bcs.Logger.Info("Signed and pushed vote", "vote", prevote2, "peer", peer)
-					peer.Send(VoteChannel, MustEncode(&VoteMessage{prevote2}))
+					peer.Send(p2p.Envelope{
+						Message:   &tmcons.Vote{Vote: prevote2.ToProto()},
+						ChannelID: VoteChannel,
+					})
 				}
 			}
 		} else {
@@ -520,18 +527,26 @@ func sendProposalAndParts(
 	parts *types.PartSet,
 ) {
 	// proposal
-	msg := &ProposalMessage{Proposal: proposal}
-	peer.Send(DataChannel, MustEncode(msg))
+	peer.Send(p2p.Envelope{
+		ChannelID: DataChannel,
+		Message:   &tmcons.Proposal{Proposal: *proposal.ToProto()},
+	})
 
 	// parts
 	for i := 0; i < int(parts.Total()); i++ {
 		part := parts.GetPart(i)
-		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,
+		pp, err := part.ToProto()
+		if err != nil {
+			panic(err) // TODO: wbanfield better error handling
 		}
-		peer.Send(DataChannel, MustEncode(msg))
+		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,
+			},
+		})
 	}
 
 	// votes
@@ -539,9 +554,14 @@ func sendProposalAndParts(
 	prevote, _ := cs.signVote(tmproto.PrevoteType, blockHash, parts.Header())
 	precommit, _ := cs.signVote(tmproto.PrecommitType, blockHash, parts.Header())
 	cs.mtx.Unlock()
-
-	peer.Send(VoteChannel, MustEncode(&VoteMessage{prevote}))
-	peer.Send(VoteChannel, MustEncode(&VoteMessage{precommit}))
+	peer.Send(p2p.Envelope{
+		ChannelID: VoteChannel,
+		Message:   &tmcons.Vote{Vote: prevote.ToProto()},
+	})
+	peer.Send(p2p.Envelope{
+		ChannelID: VoteChannel,
+		Message:   &tmcons.Vote{Vote: precommit.ToProto()},
+	})
 }
 
 //----------------------------------------
@@ -579,7 +599,7 @@ func (br *ByzantineReactor) AddPeer(peer p2p.Peer) {
 func (br *ByzantineReactor) RemovePeer(peer p2p.Peer, reason interface{}) {
 	br.reactor.RemovePeer(peer, reason)
 }
-func (br *ByzantineReactor) Receive(chID byte, peer p2p.Peer, msgBytes []byte) {
-	br.reactor.Receive(chID, peer, msgBytes)
+func (br *ByzantineReactor) Receive(e p2p.Envelope) {
+	br.reactor.Receive(e)
 }
 func (br *ByzantineReactor) InitPeer(peer p2p.Peer) p2p.Peer { return peer }

consensus/invalid_test.go

@@ -7,6 +7,7 @@ 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"
 )
@@ -94,7 +95,10 @@ 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(VoteChannel, MustEncode(&VoteMessage{precommit}))
+			peer.Send(p2p.Envelope{
+				Message:   &tmcons.Vote{Vote: precommit.ToProto()},
+				ChannelID: VoteChannel,
+			})
 		}
 	}()
 }

consensus/metrics.gen.go

@@ -118,18 +118,6 @@ 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,
@@ -208,8 +196,6 @@ 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

@@ -61,10 +61,6 @@ 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

@@ -15,173 +15,147 @@ import (
 	"github.com/tendermint/tendermint/types"
 )
 
-// MsgToProto takes a consensus message type and returns the proto defined consensus message
-func MsgToProto(msg Message) (*tmcons.Message, error) {
+// 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) {
 	if msg == nil {
 		return nil, errors.New("consensus: message is nil")
 	}
-	var pb tmcons.Message
+	var pb proto.Message
 
 	switch msg := msg.(type) {
 	case *NewRoundStepMessage:
-		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,
-				},
-			},
+		pb = &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.Message{
-			Sum: &tmcons.Message_NewValidBlock{
-				NewValidBlock: &tmcons.NewValidBlock{
-					Height:             msg.Height,
-					Round:              msg.Round,
-					BlockPartSetHeader: pbPartSetHeader,
-					BlockParts:         pbBits,
-					IsCommit:           msg.IsCommit,
-				},
-			},
+		pb = &tmcons.NewValidBlock{
+			Height:             msg.Height,
+			Round:              msg.Round,
+			BlockPartSetHeader: pbPartSetHeader,
+			BlockParts:         pbBits,
+			IsCommit:           msg.IsCommit,
 		}
+
 	case *ProposalMessage:
 		pbP := msg.Proposal.ToProto()
-		pb = tmcons.Message{
-			Sum: &tmcons.Message_Proposal{
-				Proposal: &tmcons.Proposal{
-					Proposal: *pbP,
-				},
-			},
+		pb = &tmcons.Proposal{
+			Proposal: *pbP,
 		}
+
 	case *ProposalPOLMessage:
 		pbBits := msg.ProposalPOL.ToProto()
-		pb = tmcons.Message{
-			Sum: &tmcons.Message_ProposalPol{
-				ProposalPol: &tmcons.ProposalPOL{
-					Height:           msg.Height,
-					ProposalPolRound: msg.ProposalPOLRound,
-					ProposalPol:      *pbBits,
-				},
-			},
+		pb = &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.Message{
-			Sum: &tmcons.Message_BlockPart{
-				BlockPart: &tmcons.BlockPart{
-					Height: msg.Height,
-					Round:  msg.Round,
-					Part:   *parts,
-				},
-			},
+		pb = &tmcons.BlockPart{
+			Height: msg.Height,
+			Round:  msg.Round,
+			Part:   *parts,
 		}
+
 	case *VoteMessage:
 		vote := msg.Vote.ToProto()
-		pb = tmcons.Message{
-			Sum: &tmcons.Message_Vote{
-				Vote: &tmcons.Vote{
-					Vote: vote,
-				},
-			},
+		pb = &tmcons.Vote{
+			Vote: vote,
 		}
+
 	case *HasVoteMessage:
-		pb = tmcons.Message{
-			Sum: &tmcons.Message_HasVote{
-				HasVote: &tmcons.HasVote{
-					Height: msg.Height,
-					Round:  msg.Round,
-					Type:   msg.Type,
-					Index:  msg.Index,
-				},
-			},
+		pb = &tmcons.HasVote{
+			Height: msg.Height,
+			Round:  msg.Round,
+			Type:   msg.Type,
+			Index:  msg.Index,
 		}
+
 	case *VoteSetMaj23Message:
 		bi := msg.BlockID.ToProto()
-		pb = tmcons.Message{
-			Sum: &tmcons.Message_VoteSetMaj23{
-				VoteSetMaj23: &tmcons.VoteSetMaj23{
-					Height:  msg.Height,
-					Round:   msg.Round,
-					Type:    msg.Type,
-					BlockID: bi,
-				},
-			},
+		pb = &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.Message_VoteSetBits{
-			VoteSetBits: &tmcons.VoteSetBits{
-				Height:  msg.Height,
-				Round:   msg.Round,
-				Type:    msg.Type,
-				BlockID: bi,
-			},
+		vsb := &tmcons.VoteSetBits{
+			Height:  msg.Height,
+			Round:   msg.Round,
+			Type:    msg.Type,
+			BlockID: bi,
 		}
 
 		if bits != nil {
-			vsb.VoteSetBits.Votes = *bits
+			vsb.Votes = *bits
 		}
 
-		pb = tmcons.Message{
-			Sum: vsb,
-		}
+		pb = 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(msg *tmcons.Message) (Message, error) {
-	if msg == nil {
+func MsgFromProto(p proto.Message) (Message, error) {
+	if p == nil {
 		return nil, errors.New("consensus: nil message")
 	}
 	var pb Message
 
-	switch msg := msg.Sum.(type) {
-	case *tmcons.Message_NewRoundStep:
-		rs, err := tmmath.SafeConvertUint8(int64(msg.NewRoundStep.Step))
+	switch msg := p.(type) {
+	case *tmcons.NewRoundStep:
+		rs, err := tmmath.SafeConvertUint8(int64(msg.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.NewRoundStep.Height,
-			Round:                 msg.NewRoundStep.Round,
+			Height:                msg.Height,
+			Round:                 msg.Round,
 			Step:                  cstypes.RoundStepType(rs),
-			SecondsSinceStartTime: msg.NewRoundStep.SecondsSinceStartTime,
-			LastCommitRound:       msg.NewRoundStep.LastCommitRound,
+			SecondsSinceStartTime: msg.SecondsSinceStartTime,
+			LastCommitRound:       msg.LastCommitRound,
 		}
-	case *tmcons.Message_NewValidBlock:
-		pbPartSetHeader, err := types.PartSetHeaderFromProto(&msg.NewValidBlock.BlockPartSetHeader)
+	case *tmcons.NewValidBlock:
+		pbPartSetHeader, err := types.PartSetHeaderFromProto(&msg.BlockPartSetHeader)
 		if err != nil {
 			return nil, fmt.Errorf("parts to proto error: %w", err)
 		}
 
 		pbBits := new(bits.BitArray)
-		pbBits.FromProto(msg.NewValidBlock.BlockParts)
+		pbBits.FromProto(msg.BlockParts)
 
 		pb = &NewValidBlockMessage{
-			Height:             msg.NewValidBlock.Height,
-			Round:              msg.NewValidBlock.Round,
+			Height:             msg.Height,
+			Round:              msg.Round,
 			BlockPartSetHeader: *pbPartSetHeader,
 			BlockParts:         pbBits,
-			IsCommit:           msg.NewValidBlock.IsCommit,
+			IsCommit:           msg.IsCommit,
 		}
-	case *tmcons.Message_Proposal:
-		pbP, err := types.ProposalFromProto(&msg.Proposal.Proposal)
+	case *tmcons.Proposal:
+		pbP, err := types.ProposalFromProto(&msg.Proposal)
 		if err != nil {
 			return nil, fmt.Errorf("proposal msg to proto error: %w", err)
 		}
@@ -189,26 +163,26 @@ func MsgFromProto(msg *tmcons.Message) (Message, error) {
 		pb = &ProposalMessage{
 			Proposal: pbP,
 		}
-	case *tmcons.Message_ProposalPol:
+	case *tmcons.ProposalPOL:
 		pbBits := new(bits.BitArray)
-		pbBits.FromProto(&msg.ProposalPol.ProposalPol)
+		pbBits.FromProto(&msg.ProposalPol)
 		pb = &ProposalPOLMessage{
-			Height:           msg.ProposalPol.Height,
-			ProposalPOLRound: msg.ProposalPol.ProposalPolRound,
+			Height:           msg.Height,
+			ProposalPOLRound: msg.ProposalPolRound,
 			ProposalPOL:      pbBits,
 		}
-	case *tmcons.Message_BlockPart:
-		parts, err := types.PartFromProto(&msg.BlockPart.Part)
+	case *tmcons.BlockPart:
+		parts, err := types.PartFromProto(&msg.Part)
 		if err != nil {
 			return nil, fmt.Errorf("blockpart msg to proto error: %w", err)
 		}
 		pb = &BlockPartMessage{
-			Height: msg.BlockPart.Height,
-			Round:  msg.BlockPart.Round,
+			Height: msg.Height,
+			Round:  msg.Round,
 			Part:   parts,
 		}
-	case *tmcons.Message_Vote:
-		vote, err := types.VoteFromProto(msg.Vote.Vote)
+	case *tmcons.Vote:
+		vote, err := types.VoteFromProto(msg.Vote)
 		if err != nil {
 			return nil, fmt.Errorf("vote msg to proto error: %w", err)
 		}
@@ -216,36 +190,36 @@ func MsgFromProto(msg *tmcons.Message) (Message, error) {
 		pb = &VoteMessage{
 			Vote: vote,
 		}
-	case *tmcons.Message_HasVote:
+	case *tmcons.HasVote:
 		pb = &HasVoteMessage{
-			Height: msg.HasVote.Height,
-			Round:  msg.HasVote.Round,
-			Type:   msg.HasVote.Type,
-			Index:  msg.HasVote.Index,
+			Height: msg.Height,
+			Round:  msg.Round,
+			Type:   msg.Type,
+			Index:  msg.Index,
 		}
-	case *tmcons.Message_VoteSetMaj23:
-		bi, err := types.BlockIDFromProto(&msg.VoteSetMaj23.BlockID)
+	case *tmcons.VoteSetMaj23:
+		bi, err := types.BlockIDFromProto(&msg.BlockID)
 		if err != nil {
 			return nil, fmt.Errorf("voteSetMaj23 msg to proto error: %w", err)
 		}
 		pb = &VoteSetMaj23Message{
-			Height:  msg.VoteSetMaj23.Height,
-			Round:   msg.VoteSetMaj23.Round,
-			Type:    msg.VoteSetMaj23.Type,
+			Height:  msg.Height,
+			Round:   msg.Round,
+			Type:    msg.Type,
 			BlockID: *bi,
 		}
-	case *tmcons.Message_VoteSetBits:
-		bi, err := types.BlockIDFromProto(&msg.VoteSetBits.BlockID)
+	case *tmcons.VoteSetBits:
+		bi, err := types.BlockIDFromProto(&msg.BlockID)
 		if err != nil {
 			return nil, fmt.Errorf("voteSetBits msg to proto error: %w", err)
 		}
 		bits := new(bits.BitArray)
-		bits.FromProto(&msg.VoteSetBits.Votes)
+		bits.FromProto(&msg.Votes)
 
 		pb = &VoteSetBitsMessage{
-			Height:  msg.VoteSetBits.Height,
-			Round:   msg.VoteSetBits.Round,
-			Type:    msg.VoteSetBits.Type,
+			Height:  msg.Height,
+			Round:   msg.Round,
+			Type:    msg.Type,
 			BlockID: *bi,
 			Votes:   bits,
 		}
@@ -260,20 +234,6 @@ func MsgFromProto(msg *tmcons.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
@@ -294,10 +254,14 @@ 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:    *consMsg,
+					Msg:    *cm,
 					PeerID: string(msg.PeerID),
 				},
 			},
@@ -343,7 +307,11 @@ func WALFromProto(msg *tmcons.WALMessage) (WALMessage, error) {
 			Step:   msg.EventDataRoundState.Step,
 		}
 	case *tmcons.WALMessage_MsgInfo:
-		walMsg, err := MsgFromProto(&msg.MsgInfo.Msg)
+		um, err := msg.MsgInfo.Msg.Unwrap()
+		if err != nil {
+			return nil, fmt.Errorf("unwrap message: %w", err)
+		}
+		walMsg, err := MsgFromProto(um)
 		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     *tmcons.Message
+		want     proto.Message
 		wantErr  bool
 	}{
 		{"successful NewRoundStepMessage", &NewRoundStepMessage{
@@ -80,17 +80,15 @@ func TestMsgToProto(t *testing.T) {
 			Step:                  1,
 			SecondsSinceStartTime: 1,
 			LastCommitRound:       2,
-		}, &tmcons.Message{
-			Sum: &tmcons.Message_NewRoundStep{
-				NewRoundStep: &tmcons.NewRoundStep{
-					Height:                2,
-					Round:                 1,
-					Step:                  1,
-					SecondsSinceStartTime: 1,
-					LastCommitRound:       2,
-				},
-			},
-		}, false},
+		}, &tmcons.NewRoundStep{
+			Height:                2,
+			Round:                 1,
+			Step:                  1,
+			SecondsSinceStartTime: 1,
+			LastCommitRound:       2,
+		},
+
+			false},
 
 		{"successful NewValidBlockMessage", &NewValidBlockMessage{
 			Height:             1,
@@ -98,92 +96,78 @@ func TestMsgToProto(t *testing.T) {
 			BlockPartSetHeader: psh,
 			BlockParts:         bits,
 			IsCommit:           false,
-		}, &tmcons.Message{
-			Sum: &tmcons.Message_NewValidBlock{
-				NewValidBlock: &tmcons.NewValidBlock{
-					Height:             1,
-					Round:              1,
-					BlockPartSetHeader: pbPsh,
-					BlockParts:         pbBits,
-					IsCommit:           false,
-				},
-			},
-		}, false},
+		}, &tmcons.NewValidBlock{
+			Height:             1,
+			Round:              1,
+			BlockPartSetHeader: pbPsh,
+			BlockParts:         pbBits,
+			IsCommit:           false,
+		},
+
+			false},
 		{"successful BlockPartMessage", &BlockPartMessage{
 			Height: 100,
 			Round:  1,
 			Part:   &parts,
-		}, &tmcons.Message{
-			Sum: &tmcons.Message_BlockPart{
-				BlockPart: &tmcons.BlockPart{
-					Height: 100,
-					Round:  1,
-					Part:   *pbParts,
-				},
-			},
-		}, false},
+		}, &tmcons.BlockPart{
+			Height: 100,
+			Round:  1,
+			Part:   *pbParts,
+		},
+
+			false},
 		{"successful ProposalPOLMessage", &ProposalPOLMessage{
 			Height:           1,
 			ProposalPOLRound: 1,
 			ProposalPOL:      bits,
-		}, &tmcons.Message{
-			Sum: &tmcons.Message_ProposalPol{
-				ProposalPol: &tmcons.ProposalPOL{
-					Height:           1,
-					ProposalPolRound: 1,
-					ProposalPol:      *pbBits,
-				},
-			}}, false},
+		}, &tmcons.ProposalPOL{
+			Height:           1,
+			ProposalPolRound: 1,
+			ProposalPol:      *pbBits,
+		},
+			false},
 		{"successful ProposalMessage", &ProposalMessage{
 			Proposal: &proposal,
-		}, &tmcons.Message{
-			Sum: &tmcons.Message_Proposal{
-				Proposal: &tmcons.Proposal{
-					Proposal: *pbProposal,
-				},
-			},
-		}, false},
+		}, &tmcons.Proposal{
+			Proposal: *pbProposal,
+		},
+
+			false},
 		{"successful VoteMessage", &VoteMessage{
 			Vote: vote,
-		}, &tmcons.Message{
-			Sum: &tmcons.Message_Vote{
-				Vote: &tmcons.Vote{
-					Vote: pbVote,
-				},
-			},
-		}, false},
+		}, &tmcons.Vote{
+			Vote: pbVote,
+		},
+
+			false},
 		{"successful VoteSetMaj23", &VoteSetMaj23Message{
 			Height:  1,
 			Round:   1,
 			Type:    1,
 			BlockID: bi,
-		}, &tmcons.Message{
-			Sum: &tmcons.Message_VoteSetMaj23{
-				VoteSetMaj23: &tmcons.VoteSetMaj23{
-					Height:  1,
-					Round:   1,
-					Type:    1,
-					BlockID: pbBi,
-				},
-			},
-		}, false},
+		}, &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.Message{
-			Sum: &tmcons.Message_VoteSetBits{
-				VoteSetBits: &tmcons.VoteSetBits{
-					Height:  1,
-					Round:   1,
-					Type:    1,
-					BlockID: pbBi,
-					Votes:   *pbBits,
-				},
-			},
-		}, false},
+		}, &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

@@ -7,8 +7,6 @@ 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"
@@ -121,8 +119,6 @@ func (conR *Reactor) SwitchToConsensus(state sm.State, skipWAL bool) {
 	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
@@ -148,6 +144,7 @@ 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
@@ -156,6 +153,7 @@ func (conR *Reactor) GetChannels() []*p2p.ChannelDescriptor {
 			SendQueueCapacity:   100,
 			RecvBufferCapacity:  50 * 4096,
 			RecvMessageCapacity: maxMsgSize,
+			MessageType:         &tmcons.Message{},
 		},
 		{
 			ID:                  VoteChannel,
@@ -163,6 +161,7 @@ func (conR *Reactor) GetChannels() []*p2p.ChannelDescriptor {
 			SendQueueCapacity:   100,
 			RecvBufferCapacity:  100 * 100,
 			RecvMessageCapacity: maxMsgSize,
+			MessageType:         &tmcons.Message{},
 		},
 		{
 			ID:                  VoteSetBitsChannel,
@@ -170,6 +169,7 @@ func (conR *Reactor) GetChannels() []*p2p.ChannelDescriptor {
 			SendQueueCapacity:   2,
 			RecvBufferCapacity:  1024,
 			RecvMessageCapacity: maxMsgSize,
+			MessageType:         &tmcons.Message{},
 		},
 	}
 }
@@ -223,34 +223,33 @@ 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(chID byte, src p2p.Peer, msgBytes []byte) {
+func (conR *Reactor) Receive(e p2p.Envelope) {
 	if !conR.IsRunning() {
-		conR.Logger.Debug("Receive", "src", src, "chId", chID, "bytes", msgBytes)
+		conR.Logger.Debug("Receive", "src", e.Src, "chId", e.ChannelID)
 		return
 	}
-
-	msg, err := decodeMsg(msgBytes)
+	msg, err := MsgFromProto(e.Message)
 	if err != nil {
-		conR.Logger.Error("Error decoding message", "src", src, "chId", chID, "err", err)
-		conR.Switch.StopPeerForError(src, err)
+		conR.Logger.Error("Error decoding message", "src", e.Src, "chId", e.ChannelID, "err", err)
+		conR.Switch.StopPeerForError(e.Src, err)
 		return
 	}
 
 	if err = msg.ValidateBasic(); err != nil {
-		conR.Logger.Error("Peer sent us invalid msg", "peer", src, "msg", msg, "err", err)
-		conR.Switch.StopPeerForError(src, err)
+		conR.Logger.Error("Peer sent us invalid msg", "peer", e.Src, "msg", e.Message, "err", err)
+		conR.Switch.StopPeerForError(e.Src, err)
 		return
 	}
 
-	conR.Logger.Debug("Receive", "src", src, "chId", chID, "msg", msg)
+	conR.Logger.Debug("Receive", "src", e.Src, "chId", e.ChannelID, "msg", msg)
 
 	// Get peer states
-	ps, ok := src.Get(types.PeerStateKey).(*PeerState)
+	ps, ok := e.Src.Get(types.PeerStateKey).(*PeerState)
 	if !ok {
-		panic(fmt.Sprintf("Peer %v has no state", src))
+		panic(fmt.Sprintf("Peer %v has no state", e.Src))
 	}
 
-	switch chID {
+	switch e.ChannelID {
 	case StateChannel:
 		switch msg := msg.(type) {
 		case *NewRoundStepMessage:
@@ -258,8 +257,8 @@ func (conR *Reactor) Receive(chID byte, src p2p.Peer, msgBytes []byte) {
 			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", src, "msg", msg, "err", err)
-				conR.Switch.StopPeerForError(src, err)
+				conR.Logger.Error("Peer sent us invalid msg", "peer", e.Src, "msg", msg, "err", err)
+				conR.Switch.StopPeerForError(e.Src, err)
 				return
 			}
 			ps.ApplyNewRoundStepMessage(msg)
@@ -278,7 +277,7 @@ func (conR *Reactor) Receive(chID byte, src p2p.Peer, msgBytes []byte) {
 			// 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(src, err)
+				conR.Switch.StopPeerForError(e.Src, err)
 				return
 			}
 			// Respond with a VoteSetBitsMessage showing which votes we have.
@@ -292,13 +291,19 @@ func (conR *Reactor) Receive(chID byte, src p2p.Peer, msgBytes []byte) {
 			default:
 				panic("Bad VoteSetBitsMessage field Type. Forgot to add a check in ValidateBasic?")
 			}
-			src.TrySend(VoteSetBitsChannel, MustEncode(&VoteSetBitsMessage{
+			eMsg := &tmcons.VoteSetBits{
 				Height:  msg.Height,
 				Round:   msg.Round,
 				Type:    msg.Type,
-				BlockID: msg.BlockID,
-				Votes:   ourVotes,
-			}))
+				BlockID: msg.BlockID.ToProto(),
+			}
+			if votes := ourVotes.ToProto(); votes != nil {
+				eMsg.Votes = *votes
+			}
+			e.Src.TrySend(p2p.Envelope{
+				ChannelID: VoteSetBitsChannel,
+				Message:   eMsg,
+			})
 		default:
 			conR.Logger.Error(fmt.Sprintf("Unknown message type %v", reflect.TypeOf(msg)))
 		}
@@ -311,13 +316,13 @@ func (conR *Reactor) Receive(chID byte, src p2p.Peer, msgBytes []byte) {
 		switch msg := msg.(type) {
 		case *ProposalMessage:
 			ps.SetHasProposal(msg.Proposal)
-			conR.conS.peerMsgQueue <- msgInfo{msg, src.ID()}
+			conR.conS.peerMsgQueue <- msgInfo{msg, e.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(src.ID())).Add(1)
-			conR.conS.peerMsgQueue <- msgInfo{msg, src.ID()}
+			conR.Metrics.BlockParts.With("peer_id", string(e.Src.ID())).Add(1)
+			conR.conS.peerMsgQueue <- msgInfo{msg, e.Src.ID()}
 		default:
 			conR.Logger.Error(fmt.Sprintf("Unknown message type %v", reflect.TypeOf(msg)))
 		}
@@ -337,7 +342,7 @@ func (conR *Reactor) Receive(chID byte, src p2p.Peer, msgBytes []byte) {
 			ps.EnsureVoteBitArrays(height-1, lastCommitSize)
 			ps.SetHasVote(msg.Vote)
 
-			cs.peerMsgQueue <- msgInfo{msg, src.ID()}
+			cs.peerMsgQueue <- msgInfo{msg, e.Src.ID()}
 
 		default:
 			// don't punish (leave room for soft upgrades)
@@ -376,7 +381,7 @@ func (conR *Reactor) Receive(chID byte, src p2p.Peer, msgBytes []byte) {
 		}
 
 	default:
-		conR.Logger.Error(fmt.Sprintf("Unknown chId %X", chID))
+		conR.Logger.Error(fmt.Sprintf("Unknown chId %X", e.ChannelID))
 	}
 }
 
@@ -430,29 +435,39 @@ func (conR *Reactor) unsubscribeFromBroadcastEvents() {
 
 func (conR *Reactor) broadcastNewRoundStepMessage(rs *cstypes.RoundState) {
 	nrsMsg := makeRoundStepMessage(rs)
-	conR.Switch.Broadcast(StateChannel, MustEncode(nrsMsg))
+	conR.Switch.Broadcast(p2p.Envelope{
+		ChannelID: StateChannel,
+		Message:   nrsMsg,
+	})
 }
 
 func (conR *Reactor) broadcastNewValidBlockMessage(rs *cstypes.RoundState) {
-	csMsg := &NewValidBlockMessage{
+	psh := rs.ProposalBlockParts.Header()
+	csMsg := &tmcons.NewValidBlock{
 		Height:             rs.Height,
 		Round:              rs.Round,
-		BlockPartSetHeader: rs.ProposalBlockParts.Header(),
-		BlockParts:         rs.ProposalBlockParts.BitArray(),
+		BlockPartSetHeader: psh.ToProto(),
+		BlockParts:         rs.ProposalBlockParts.BitArray().ToProto(),
 		IsCommit:           rs.Step == cstypes.RoundStepCommit,
 	}
-	conR.Switch.Broadcast(StateChannel, MustEncode(csMsg))
+	conR.Switch.Broadcast(p2p.Envelope{
+		ChannelID: StateChannel,
+		Message:   csMsg,
+	})
 }
 
 // Broadcasts HasVoteMessage to peers that care.
 func (conR *Reactor) broadcastHasVoteMessage(vote *types.Vote) {
-	msg := &HasVoteMessage{
+	msg := &tmcons.HasVote{
 		Height: vote.Height,
 		Round:  vote.Round,
 		Type:   vote.Type,
 		Index:  vote.ValidatorIndex,
 	}
-	conR.Switch.Broadcast(StateChannel, MustEncode(msg))
+	conR.Switch.Broadcast(p2p.Envelope{
+		ChannelID: StateChannel,
+		Message:   msg,
+	})
 	/*
 		// TODO: Make this broadcast more selective.
 		for _, peer := range conR.Switch.Peers().List() {
@@ -463,7 +478,11 @@ func (conR *Reactor) broadcastHasVoteMessage(vote *types.Vote) {
 			prs := ps.GetRoundState()
 			if prs.Height == vote.Height {
 				// TODO: Also filter on round?
-				peer.TrySend(StateChannel, struct{ ConsensusMessage }{msg})
+				e := p2p.Envelope{
+					ChannelID: StateChannel, struct{ ConsensusMessage }{msg},
+					Message: p,
+				}
+				peer.TrySend(e)
 			} else {
 				// Height doesn't match
 				// TODO: check a field, maybe CatchupCommitRound?
@@ -473,11 +492,11 @@ func (conR *Reactor) broadcastHasVoteMessage(vote *types.Vote) {
 	*/
 }
 
-func makeRoundStepMessage(rs *cstypes.RoundState) (nrsMsg *NewRoundStepMessage) {
-	nrsMsg = &NewRoundStepMessage{
+func makeRoundStepMessage(rs *cstypes.RoundState) (nrsMsg *tmcons.NewRoundStep) {
+	nrsMsg = &tmcons.NewRoundStep{
 		Height:                rs.Height,
 		Round:                 rs.Round,
-		Step:                  rs.Step,
+		Step:                  uint32(rs.Step),
 		SecondsSinceStartTime: int64(time.Since(rs.StartTime).Seconds()),
 		LastCommitRound:       rs.LastCommit.GetRound(),
 	}
@@ -487,7 +506,10 @@ func makeRoundStepMessage(rs *cstypes.RoundState) (nrsMsg *NewRoundStepMessage)
 func (conR *Reactor) sendNewRoundStepMessage(peer p2p.Peer) {
 	rs := conR.getRoundState()
 	nrsMsg := makeRoundStepMessage(rs)
-	peer.Send(StateChannel, MustEncode(nrsMsg))
+	peer.Send(p2p.Envelope{
+		ChannelID: StateChannel,
+		Message:   nrsMsg,
+	})
 }
 
 func (conR *Reactor) updateRoundStateRoutine() {
@@ -526,13 +548,19 @@ 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)
-				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,
+				parts, err := part.ToProto()
+				if err != nil {
+					panic(err)
 				}
 				logger.Debug("Sending block part", "height", prs.Height, "round", prs.Round)
-				if peer.Send(DataChannel, MustEncode(msg)) {
+				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,
+					},
+				}) {
 					ps.SetHasProposalBlockPart(prs.Height, prs.Round, index)
 				}
 				continue OUTER_LOOP
@@ -578,9 +606,11 @@ 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(DataChannel, MustEncode(msg)) {
+				if peer.Send(p2p.Envelope{
+					ChannelID: DataChannel,
+					Message:   &tmcons.Proposal{Proposal: *rs.Proposal.ToProto()},
+				}) {
 					// NOTE[ZM]: A peer might have received different proposal msg so this Proposal msg will be rejected!
 					ps.SetHasProposal(rs.Proposal)
 				}
@@ -590,13 +620,15 @@ 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(DataChannel, MustEncode(msg))
+				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(),
+					},
+				})
 			}
 			continue OUTER_LOOP
 		}
@@ -633,13 +665,20 @@ func (conR *Reactor) gossipDataForCatchup(logger log.Logger, rs *cstypes.RoundSt
 			return
 		}
 		// Send the part
-		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,
-		}
 		logger.Debug("Sending block part for catchup", "round", prs.Round, "index", index)
-		if peer.Send(DataChannel, MustEncode(msg)) {
+		pp, err := part.ToProto()
+		if err != nil {
+			logger.Error("Could not convert part to proto", "index", index, "error", err)
+			return
+		}
+		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,
+			},
+		}) {
 			ps.SetHasProposalBlockPart(prs.Height, prs.Round, index)
 		} else {
 			logger.Debug("Sending block part for catchup failed")
@@ -798,12 +837,16 @@ OUTER_LOOP:
 			prs := ps.GetRoundState()
 			if rs.Height == prs.Height {
 				if maj23, ok := rs.Votes.Prevotes(prs.Round).TwoThirdsMajority(); ok {
-					peer.TrySend(StateChannel, MustEncode(&VoteSetMaj23Message{
-						Height:  prs.Height,
-						Round:   prs.Round,
-						Type:    tmproto.PrevoteType,
-						BlockID: maj23,
-					}))
+
+					peer.TrySend(p2p.Envelope{
+						ChannelID: StateChannel,
+						Message: &tmcons.VoteSetMaj23{
+							Height:  prs.Height,
+							Round:   prs.Round,
+							Type:    tmproto.PrevoteType,
+							BlockID: maj23.ToProto(),
+						},
+					})
 					time.Sleep(conR.conS.config.PeerQueryMaj23SleepDuration)
 				}
 			}
@@ -815,12 +858,15 @@ OUTER_LOOP:
 			prs := ps.GetRoundState()
 			if rs.Height == prs.Height {
 				if maj23, ok := rs.Votes.Precommits(prs.Round).TwoThirdsMajority(); ok {
-					peer.TrySend(StateChannel, MustEncode(&VoteSetMaj23Message{
-						Height:  prs.Height,
-						Round:   prs.Round,
-						Type:    tmproto.PrecommitType,
-						BlockID: maj23,
-					}))
+					peer.TrySend(p2p.Envelope{
+						ChannelID: StateChannel,
+						Message: &tmcons.VoteSetMaj23{
+							Height:  prs.Height,
+							Round:   prs.Round,
+							Type:    tmproto.PrecommitType,
+							BlockID: maj23.ToProto(),
+						},
+					})
 					time.Sleep(conR.conS.config.PeerQueryMaj23SleepDuration)
 				}
 			}
@@ -832,12 +878,16 @@ OUTER_LOOP:
 			prs := ps.GetRoundState()
 			if rs.Height == prs.Height && prs.ProposalPOLRound >= 0 {
 				if maj23, ok := rs.Votes.Prevotes(prs.ProposalPOLRound).TwoThirdsMajority(); ok {
-					peer.TrySend(StateChannel, MustEncode(&VoteSetMaj23Message{
-						Height:  prs.Height,
-						Round:   prs.ProposalPOLRound,
-						Type:    tmproto.PrevoteType,
-						BlockID: maj23,
-					}))
+
+					peer.TrySend(p2p.Envelope{
+						ChannelID: StateChannel,
+						Message: &tmcons.VoteSetMaj23{
+							Height:  prs.Height,
+							Round:   prs.ProposalPOLRound,
+							Type:    tmproto.PrevoteType,
+							BlockID: maj23.ToProto(),
+						},
+					})
 					time.Sleep(conR.conS.config.PeerQueryMaj23SleepDuration)
 				}
 			}
@@ -852,12 +902,15 @@ 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(StateChannel, MustEncode(&VoteSetMaj23Message{
-						Height:  prs.Height,
-						Round:   commit.Round,
-						Type:    tmproto.PrecommitType,
-						BlockID: commit.BlockID,
-					}))
+					peer.TrySend(p2p.Envelope{
+						ChannelID: StateChannel,
+						Message: &tmcons.VoteSetMaj23{
+							Height:  prs.Height,
+							Round:   commit.Round,
+							Type:    tmproto.PrecommitType,
+							BlockID: commit.BlockID.ToProto(),
+						},
+					})
 					time.Sleep(conR.conS.config.PeerQueryMaj23SleepDuration)
 				}
 			}
@@ -1071,9 +1124,13 @@ 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(VoteChannel, MustEncode(msg)) {
+		if ps.peer.Send(p2p.Envelope{
+			ChannelID: VoteChannel,
+			Message: &tmcons.Vote{
+				Vote: vote.ToProto(),
+			},
+		}) {
 			ps.SetHasVote(vote)
 			return true
 		}
@@ -1294,6 +1351,7 @@ func (ps *PeerState) ApplyNewRoundStepMessage(msg *NewRoundStepMessage) {
 	psRound := ps.PRS.Round
 	psCatchupCommitRound := ps.PRS.CatchupCommitRound
 	psCatchupCommit := ps.PRS.CatchupCommit
+	lastPrecommits := ps.PRS.Precommits
 
 	startTime := tmtime.Now().Add(-1 * time.Duration(msg.SecondsSinceStartTime) * time.Second)
 	ps.PRS.Height = msg.Height
@@ -1321,7 +1379,7 @@ func (ps *PeerState) ApplyNewRoundStepMessage(msg *NewRoundStepMessage) {
 		// Shift Precommits to LastCommit.
 		if psHeight+1 == msg.Height && psRound == msg.LastCommitRound {
 			ps.PRS.LastCommitRound = msg.LastCommitRound
-			ps.PRS.LastCommit = ps.PRS.Precommits
+			ps.PRS.LastCommit = lastPrecommits
 		} else {
 			ps.PRS.LastCommitRound = msg.LastCommitRound
 			ps.PRS.LastCommit = nil
@@ -1439,15 +1497,6 @@ 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

@@ -33,6 +33,7 @@ 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"
@@ -265,15 +266,18 @@ 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(StateChannel, peer, msg)
+		reactor.Receive(p2p.Envelope{
+			ChannelID: StateChannel,
+			Src:       peer,
+			Message: &tmcons.HasVote{Height: 1,
+				Round: 1, Index: 1, Type: tmproto.PrevoteType},
+		})
 		reactor.AddPeer(peer)
 	})
 }
@@ -288,15 +292,18 @@ 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(StateChannel, peer, msg)
+		reactor.Receive(p2p.Envelope{
+			ChannelID: StateChannel,
+			Src:       peer,
+			Message: &tmcons.HasVote{Height: 1,
+				Round: 1, Index: 1, Type: tmproto.PrevoteType},
+		})
 	})
 }
 

consensus/replay.go

@@ -254,7 +254,7 @@ func (h *Handshaker) Handshake(proxyApp proxy.AppConns) error {
 
 	h.logger.Info("ABCI Handshake App Info",
 		"height", blockHeight,
-		"hash", appHash,
+		"hash", log.NewLazySprintf("%X", appHash),
 		"software-version", res.Version,
 		"protocol-version", res.AppVersion,
 	)
@@ -271,7 +271,7 @@ func (h *Handshaker) Handshake(proxyApp proxy.AppConns) error {
 	}
 
 	h.logger.Info("Completed ABCI Handshake - Tendermint and App are synced",
-		"appHeight", blockHeight, "appHash", appHash)
+		"appHeight", blockHeight, "appHash", log.NewLazySprintf("%X", appHash))
 
 	// TODO: (on restart) replay mempool
 

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/master/docs/DOCS_README.md).
+repo](https://github.com/cosmos/cosmos-sdk/blob/main/docs/README.md).

docs/app-dev/abci-cli.md

@@ -27,22 +27,28 @@ Usage:
   abci-cli [command]
 
 Available Commands:
-  batch       Run a batch of abci commands against an application
-  check_tx    Validate a tx
-  commit      Commit the application state and return the Merkle root hash
-  console     Start an interactive abci console for multiple commands
-  deliver_tx  Deliver a new tx to the application
-  kvstore     ABCI demo example
-  echo        Have the application echo a message
-  help        Help about any command
-  info        Get some info about the application
-  query       Query the application state
+  batch            run a batch of abci commands against an application
+  check_tx         validate a transaction
+  commit           commit the application state and return the Merkle root hash
+  completion       Generate the autocompletion script for the specified shell
+  console          start an interactive ABCI console for multiple commands
+  deliver_tx       deliver a new transaction to the application
+  echo             have the application echo a message
+  help             Help about any command
+  info             get some info about the application
+  kvstore          ABCI demo example
+  prepare_proposal prepare proposal
+  process_proposal process proposal
+  query            query the application state
+  test             run integration tests
+  version          print ABCI console version
 
 Flags:
-      --abci string      socket or grpc (default "socket")
-      --address string   address of application socket (default "tcp://127.0.0.1:26658")
-  -h, --help             help for abci-cli
-  -v, --verbose          print the command and results as if it were a console session
+      --abci string        either socket or grpc (default "socket")
+      --address string     address of application socket (default "tcp://0.0.0.0:26658")
+  -h, --help               help for abci-cli
+      --log_level string   set the logger level (default "debug")
+  -v, --verbose            print the command and results as if it were a console session
 
 Use "abci-cli [command] --help" for more information about a command.
 ```
@@ -58,47 +64,51 @@ purposes.
 
 We'll start a kvstore application, which was installed at the same time
 as `abci-cli` above. The kvstore just stores transactions in a merkle
-tree.
-
-Its code can be found
-[here](https://github.com/tendermint/tendermint/blob/v0.34.x/abci/cmd/abci-cli/abci-cli.go)
-and looks like:
+tree. Its code can be found
+[here](https://github.com/tendermint/tendermint/blob/main/abci/cmd/abci-cli/abci-cli.go)
+and looks like the following:
 
 ```go
 func cmdKVStore(cmd *cobra.Command, args []string) error {
-    logger := log.NewTMLogger(log.NewSyncWriter(os.Stdout))
+	logger := log.NewTMLogger(log.NewSyncWriter(os.Stdout))
 
-    // Create the application - in memory or persisted to disk
-    var app types.Application
-    if flagPersist == "" {
-        app = kvstore.NewKVStoreApplication()
-    } else {
-        app = kvstore.NewPersistentKVStoreApplication(flagPersist)
-        app.(*kvstore.PersistentKVStoreApplication).SetLogger(logger.With("module", "kvstore"))
-    }
+	// Create the application - in memory or persisted to disk
+	var app types.Application
+	if flagPersist == "" {
+		var err error
+		flagPersist, err = os.MkdirTemp("", "persistent_kvstore_tmp")
+		if err != nil {
+			return err
+		}
+	}
+	app = kvstore.NewPersistentKVStoreApplication(flagPersist)
+	app.(*kvstore.PersistentKVStoreApplication).SetLogger(logger.With("module", "kvstore"))
 
-    // Start the listener
-    srv, err := server.NewServer(flagAddrD, flagAbci, app)
-    if err != nil {
-        return err
-    }
-    srv.SetLogger(logger.With("module", "abci-server"))
-    if err := srv.Start(); err != nil {
-        return err
-    }
+	// Start the listener
+	srv, err := server.NewServer(flagAddress, flagAbci, app)
+	if err != nil {
+		return err
+	}
+	srv.SetLogger(logger.With("module", "abci-server"))
+	if err := srv.Start(); err != nil {
+		return err
+	}
 
-    // Stop upon receiving SIGTERM or CTRL-C.
-    tmos.TrapSignal(logger, func() {
-        // Cleanup
-        srv.Stop()
-    })
+	// Stop upon receiving SIGTERM or CTRL-C.
+	tmos.TrapSignal(logger, func() {
+		// Cleanup
+		if err := srv.Stop(); err != nil {
+			logger.Error("Error while stopping server", "err", err)
+		}
+	})
 
-    // Run forever.
-    select {}
+	// Run forever.
+	select {}
 }
+
 ```
 
-Start by running:
+Start the application by running:
 
 ```sh
 abci-cli kvstore
@@ -163,32 +173,32 @@ Try running these commands:
 -> data: hello
 -> data.hex: 0x68656C6C6F
 
-> info
+> info 
 -> code: OK
 -> data: {"size":0}
 -> data.hex: 0x7B2273697A65223A307D
 
 > prepare_proposal "abc"
 -> code: OK
--> log: Succeeded. Tx: abc action: UNMODIFIED
+-> log: Succeeded. Tx: abc
 
 > process_proposal "abc"
 -> code: OK
 -> status: ACCEPT
 
-> commit
+> commit 
 -> code: OK
 -> data.hex: 0x0000000000000000
 
 > deliver_tx "abc"
 -> code: OK
 
-> info
+> info 
 -> code: OK
 -> data: {"size":1}
 -> data.hex: 0x7B2273697A65223A317D
 
-> commit
+> commit 
 -> code: OK
 -> data.hex: 0x0200000000000000
 
@@ -204,7 +214,7 @@ Try running these commands:
 > deliver_tx "def=xyz"
 -> code: OK
 
-> commit
+> commit 
 -> code: OK
 -> data.hex: 0x0400000000000000
 
@@ -219,11 +229,9 @@ Try running these commands:
 
 > prepare_proposal "preparedef"
 -> code: OK
--> log: Succeeded. Tx: def action: ADDED
--> code: OK
--> log: Succeeded. Tx: preparedef action: REMOVED
+-> log: Succeeded. Tx: replacedef
 
-> process_proposal "def"
+> process_proposal "replacedef"
 -> code: OK
 -> status: ACCEPT
 
@@ -245,21 +253,21 @@ Try running these commands:
 Note that if we do `deliver_tx "abc"` it will store `(abc, abc)`, but if
 we do `deliver_tx "abc=efg"` it will store `(abc, efg)`.
 
-Similarly, you could put the commands in a file and run
+You could put the commands in a file and run
 `abci-cli --verbose batch < myfile`.
 
+
+Note that the `abci-cli` is designed strictly for testing and debugging. In a real
+deployment, the role of sending messages is taken by Tendermint, which
+connects to the app using three separate connections, each with its own
+pattern of messages.
+
+For examples of running an ABCI app with Tendermint, see the 
+[getting started guide](./getting-started.md).
+
 ## Bounties
 
 Want to write an app in your favorite language?! We'd be happy
 to add you to our [ecosystem](https://github.com/tendermint/awesome#ecosystem)!
 See [funding](https://github.com/interchainio/funding) opportunities from the
 [Interchain Foundation](https://interchain.io) for implementations in new languages and more.
-
-The `abci-cli` is designed strictly for testing and debugging. In a real
-deployment, the role of sending messages is taken by Tendermint, which
-connects to the app using three separate connections, each with its own
-pattern of messages.
-
-For examples of running an ABCI app with
-Tendermint, see the [getting started guide](./getting-started.md).
-Next is the ABCI specification.

docs/app-dev/getting-started.md

@@ -11,9 +11,10 @@ application you want to run. So, to run a complete blockchain that does
 something useful, you must start two programs: one is Tendermint Core,
 the other is your application, which can be written in any programming
 language. Recall from [the intro to
-ABCI](../introduction/what-is-tendermint.md#abci-overview) that Tendermint Core handles all the p2p and consensus stuff, and just forwards transactions to the
+ABCI](../introduction/what-is-tendermint.md#abci-overview) that Tendermint Core
+handles all the p2p and consensus stuff, and just forwards transactions to the
 application when they need to be validated, or when they're ready to be
-committed to a block.
+executed and committed.
 
 In this guide, we show you some examples of how to run an application
 using Tendermint.
@@ -22,7 +23,8 @@ using Tendermint.
 
 The first apps we will work with are written in Go. To install them, you
 need to [install Go](https://golang.org/doc/install), put
-`$GOPATH/bin` in your `$PATH` and enable go modules with these instructions:
+`$GOPATH/bin` in your `$PATH` and enable go modules. If you use `bash`, 
+follow these instructions:
 
 ```bash
 echo export GOPATH=\"\$HOME/go\" >> ~/.bash_profile
@@ -31,17 +33,48 @@ echo export PATH=\"\$PATH:\$GOPATH/bin\" >> ~/.bash_profile
 
 Then run
 
-```sh
+```bash
 go get github.com/tendermint/tendermint
 cd $GOPATH/src/github.com/tendermint/tendermint
 make install_abci
 ```
 
-Now you should have the `abci-cli` installed; you'll notice the `kvstore`
-command, an example application written
-in Go. See below for an application written in JavaScript.
+Now you should have the `abci-cli` installed; run `abci-cli` to see the list of commands:
 
-Now, let's run some apps!
+```
+Usage:
+  abci-cli [command]
+
+Available Commands:
+  batch            run a batch of abci commands against an application
+  check_tx         validate a transaction
+  commit           commit the application state and return the Merkle root hash
+  completion       Generate the autocompletion script for the specified shell
+  console          start an interactive ABCI console for multiple commands
+  deliver_tx       deliver a new transaction to the application
+  echo             have the application echo a message
+  help             Help about any command
+  info             get some info about the application
+  kvstore          ABCI demo example
+  prepare_proposal prepare proposal
+  process_proposal process proposal
+  query            query the application state
+  test             run integration tests
+  version          print ABCI console version
+
+Flags:
+      --abci string        either socket or grpc (default "socket")
+      --address string     address of application socket (default "tcp://0.0.0.0:26658")
+  -h, --help               help for abci-cli
+      --log_level string   set the logger level (default "debug")
+  -v, --verbose            print the command and results as if it were a console session
+
+Use "abci-cli [command] --help" for more information about a command.
+```
+
+You'll notice the `kvstore` command, an example application written in Go.
+
+Now, let's run an app!
 
 ## KVStore - A First Example
 
@@ -68,7 +101,7 @@ tendermint node
 ```
 
 If you have used Tendermint, you may want to reset the data for a new
-blockchain by running `tendermint unsafe_reset_all`. Then you can run
+blockchain by running `tendermint unsafe-reset-all`. Then you can run
 `tendermint node` to start Tendermint, and connect to the app. For more
 details, see [the guide on using Tendermint](../tendermint-core/using-tendermint.md).
 
@@ -164,47 +197,3 @@ curl -s 'localhost:26657/abci_query?data="name"'
 
 Try some other transactions and queries to make sure everything is
 working!
-
-
-## CounterJS - Example in Another Language
-
-We also want to run applications in another language - in this case,
-we'll run a Javascript version of the `counter`. To run it, you'll need
-to [install node](https://nodejs.org/en/download/).
-
-You'll also need to fetch the relevant repository, from
-[here](https://github.com/tendermint/js-abci), then install it:
-
-```sh
-git clone https://github.com/tendermint/js-abci.git
-cd js-abci
-npm install abci
-```
-
-Kill the previous `counter` and `tendermint` processes. Now run the app:
-
-```sh
-node example/counter.js
-```
-
-In another window, reset and start `tendermint`:
-
-```sh
-tendermint unsafe_reset_all
-tendermint node
-```
-
-Once again, you should see blocks streaming by - but now, our
-application is written in Javascript! Try sending some transactions, and
-like before - the results should be the same:
-
-```sh
-# ok
-curl localhost:26657/broadcast_tx_commit?tx=0x00
-# invalid nonce
-curl localhost:26657/broadcast_tx_commit?tx=0x05
-# ok
-curl localhost:26657/broadcast_tx_commit?tx=0x01
-```
-
-Neat, eh?

docs/architecture/README.md

@@ -78,9 +78,11 @@ Note the context/background should be written in the present tense.
 - [ADR-039: Peer-Behaviour](./adr-039-peer-behaviour.md)
 - [ADR-063: Privval-gRPC](./adr-063-privval-grpc.md)
 - [ADR-067: Mempool Refactor](./adr-067-mempool-refactor.md)
+- [ADR-071: Proposer-Based Timestamps](./adr-071-proposer-based-timestamps.md)
 - [ADR-075: RPC Event Subscription Interface](./adr-075-rpc-subscription.md)
 - [ADR-079: Ed25519 Verification](./adr-079-ed25519-verification.md)
 - [ADR-081: Protocol Buffers Management](./adr-081-protobuf-mgmt.md)
+- [ADR-083: Out-of-band Sync](./adr-083-out-band-sync.md)
 
 ### Deprecated
 
@@ -114,7 +116,6 @@ None
 - [ADR-064: Batch Verification](./adr-064-batch-verification.md)
 - [ADR-068: Reverse-Sync](./adr-068-reverse-sync.md)
 - [ADR-069: Node Initialization](./adr-069-flexible-node-initialization.md)
-- [ADR-071: Proposer-Based Timestamps](./adr-071-proposer-based-timestamps.md)
 - [ADR-073: Adopt LibP2P](./adr-073-libp2p.md)
 - [ADR-074: Migrate Timeout Parameters to Consensus Parameters](./adr-074-timeout-params.md)
 - [ADR-080: Reverse Sync](./adr-080-reverse-sync.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/v0.44/ibc/overview.html#acknowledgements)
+* IBC packets can use either a [timestamp or a height to timeout packet delivery](https://docs.cosmos.network/v0.45/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/architecture/adr-083-out-of-band-sync.md

@@ -0,0 +1,73 @@
+# ADR 083: Supporting out of band state sync
+
+## Changelog
+
+- 2022-10-31: Initial Draft (@cmwaters)
+
+## Status
+
+Accepted
+
+## Context
+
+Whenever Tendermint begins, it initiates a handshake with the application via `Info` to gauge version compatibility and receive the last height and app hash of the application. Tendermint then begins a replay protocol which aims to sync the heights of Tendermint's state and block store and the application's current height. 
+
+When initially designed, one invariant was that the applications current height should never exceed
+Tendermint's height. The protocol would error and the node would shut down if this were to happen. It seemed
+appropriate at the time that Tendermint which would provide blocks either through block sync or consensus
+would always be ahead. However, in light of state sync and other protocols for bootstrapping an application to 
+a particular height, this invariant is no longer necessary.
+
+## Decision
+
+Allow applications to start with a bootstrapped state alongside an empty Tendermint instance using
+a subsystem of the state sync protocol. 
+
+## Detailed Design
+
+Tendermint will perform a protocol to bootstrap to the height of the application under the following circumstances:
+
+- The returned application height is greater than Tendermint's blockstore height
+- Tendermint's block store has a height of 0 (i.e. it's empty and we're not overriding an existing instance. This check may be relaxed in the future) 
+- State sync is enabled and the config is valid (i.e it contains at least 2 rpc endpoints and a trusted header and hash)
+
+The bootstrap protocol will be run directly after the handshake. It (currently) does not require the p2p layer and will work by updating the `StateStore` and `BlockStore`. It should be performed instead of statesync, moving to either blocksync or consensus once completed.
+
+The protocol mainly wraps around the `StateProvider` which is derived from the `StateSyncConfig` and currently uses the RPC layer and light client to produce a `State` and `Commit` (to be passed to consensus for the next height)
+
+The pseudocode is as follows:
+```go
+func Bootstrap(sp StateProvider, appHeight int64, appHash []byte, bs BlockStore, ss StateStore) (*State, error) {
+    state, err := sp.State(appHeight)
+    
+    if !bytes.Equal(state.AppHash, appHash) {
+        return errors.New("application state hash mismatches block's app hash")
+    }
+
+    lastCommit, err := sp.Commit(appHeight)
+
+    err = ss.Bootstrap(state)
+
+    err = bs.SaveSeenCommit(lastCommit)
+
+    return state, err
+}
+```
+
+## Consequences
+
+### Positive
+
+- This is a non-breaking change
+- Applications can now use their own state syncing protocols. This is especially useful when the saved snapshot is already from a trusted node.
+- Tendermint will still verify application state in the event that the out of band state does not match the hash of the respective block on chain 
+
+### Negative
+
+### Neutral
+
+- Users will need to have state sync correctly configured and enabled to take advantage of this functionality
+
+## References
+
+- [Initial Issue](https://github.com/tendermint/tendermint/issues/4642)

docs/introduction/what-is-tendermint.md

@@ -6,7 +6,7 @@ order: 4
 
 Tendermint is software for securely and consistently replicating an
 application on many machines. By securely, we mean that Tendermint works
-even if up to 1/3 of machines fail in arbitrary ways. By consistently,
+as long as less than 1/3 of machines fail in arbitrary ways. By consistently,
 we mean that every non-faulty machine sees the same transaction log and
 computes the same state. Secure and consistent replication is a
 fundamental problem in distributed systems; it plays a critical role in
@@ -22,15 +22,14 @@ reformalization of BFT in a more modern setting, with emphasis on
 peer-to-peer networking and cryptographic authentication. The name
 derives from the way transactions are batched in blocks, where each
 block contains a cryptographic hash of the previous one, forming a
-chain. In practice, the blockchain data structure actually optimizes BFT
-design.
+chain. 
 
 Tendermint consists of two chief technical components: a blockchain
 consensus engine and a generic application interface. The consensus
 engine, called Tendermint Core, ensures that the same transactions are
 recorded on every machine in the same order. The application interface,
-called the Application BlockChain Interface (ABCI), enables the
-transactions to be processed in any programming language. Unlike other
+called the Application BlockChain Interface (ABCI), delivers the transactions
+to applications for processing. Unlike other
 blockchain and consensus solutions, which come pre-packaged with built
 in state machines (like a fancy key-value store, or a quirky scripting
 language), developers can use Tendermint for BFT state machine
@@ -51,13 +50,13 @@ Hyperledger's Burrow.
 
 ### Zookeeper, etcd, consul
 
-Zookeeper, etcd, and consul are all implementations of a key-value store
-atop a classical, non-BFT consensus algorithm. Zookeeper uses a version
-of Paxos called Zookeeper Atomic Broadcast, while etcd and consul use
-the Raft consensus algorithm, which is much younger and simpler. A
+Zookeeper, etcd, and consul are all implementations of key-value stores
+atop a classical, non-BFT consensus algorithm. Zookeeper uses an
+algorithm called Zookeeper Atomic Broadcast, while etcd and consul use
+the Raft log replication algorithm. A
 typical cluster contains 3-5 machines, and can tolerate crash failures
-in up to 1/2 of the machines, but even a single Byzantine fault can
-destroy the system.
+in less than 1/2 of the machines (e.g., 1 out of 3 or 2 out of 5), 
+but even a single Byzantine fault can jeopardize the whole system.
 
 Each offering provides a slightly different implementation of a
 featureful key-value store, but all are generally focused around
@@ -66,8 +65,8 @@ configuration, service discovery, locking, leader-election, and so on.
 
 Tendermint is in essence similar software, but with two key differences:
 
-- It is Byzantine Fault Tolerant, meaning it can only tolerate up to a
-  1/3 of failures, but those failures can include arbitrary behavior -
+- It is Byzantine Fault Tolerant, meaning it can only tolerate less than 1/3
+  of machines failing, but those failures can include arbitrary behavior -
   including hacking and malicious attacks. - It does not specify a
   particular application, like a fancy key-value store. Instead, it
   focuses on arbitrary state machine replication, so developers can build
@@ -106,8 +105,8 @@ docker containers, modules it calls "chaincode". It uses an
 implementation of [PBFT](http://pmg.csail.mit.edu/papers/osdi99.pdf).
 from a team at IBM that is [augmented to handle potentially
 non-deterministic
-chaincode](https://drops.dagstuhl.de/opus/volltexte/2017/7093/pdf/LIPIcs-OPODIS-2016-24.pdf) It is
-possible to implement this docker-based behavior as a ABCI app in
+chaincode](https://drops.dagstuhl.de/opus/volltexte/2017/7093/pdf/LIPIcs-OPODIS-2016-24.pdf).
+It is possible to implement this docker-based behavior as an ABCI app in
 Tendermint, though extending Tendermint to handle non-determinism
 remains for future work.
 
@@ -143,24 +142,22 @@ in design and suffers from "spaghetti code".
 Another problem with monolithic design is that it limits you to the
 language of the blockchain stack (or vice versa). In the case of
 Ethereum which supports a Turing-complete bytecode virtual-machine, it
-limits you to languages that compile down to that bytecode; today, those
-are Serpent and Solidity.
+limits you to languages that compile down to that bytecode; while the 
+[list](https://github.com/pirapira/awesome-ethereum-virtual-machine#programming-languages-that-compile-into-evm)
+is growing, it is still very limited.
 
 In contrast, our approach is to decouple the consensus engine and P2P
-layers from the details of the application state of the particular
+layers from the details of the state of the particular
 blockchain application. We do this by abstracting away the details of
 the application to an interface, which is implemented as a socket
 protocol.
 
-Thus we have an interface, the Application BlockChain Interface (ABCI),
-and its primary implementation, the Tendermint Socket Protocol (TSP, or
-Teaspoon).
-
 ### Intro to ABCI
 
-[Tendermint Core](https://github.com/tendermint/tendermint) (the
-"consensus engine") communicates with the application via a socket
-protocol that satisfies the ABCI.
+[Tendermint Core](https://github.com/tendermint/tendermint), the
+"consensus engine", communicates with the application via a socket
+protocol that satisfies the ABCI, the Tendermint Socket Protocol 
+(TSP, or Teaspoon).
 
 To draw an analogy, lets talk about a well-known cryptocurrency,
 Bitcoin. Bitcoin is a cryptocurrency blockchain where each node
@@ -180,7 +177,7 @@ The application will be responsible for
 - Allowing clients to query the UTXO database.
 
 Tendermint is able to decompose the blockchain design by offering a very
-simple API (ie. the ABCI) between the application process and consensus
+simple API (i.e. the ABCI) between the application process and consensus
 process.
 
 The ABCI consists of 3 primary message types that get delivered from the
@@ -239,8 +236,7 @@ Solidity on Ethereum is a great language of choice for blockchain
 applications because, among other reasons, it is a completely
 deterministic programming language. However, it's also possible to
 create deterministic applications using existing popular languages like
-Java, C++, Python, or Go. Game programmers and blockchain developers are
-already familiar with creating deterministic programs by avoiding
+Java, C++, Python, or Go, by avoiding
 sources of non-determinism such as:
 
 - random number generators (without deterministic seeding)
@@ -271,14 +267,15 @@ committed in a chain, with one block at each **height**. A block may
 fail to be committed, in which case the protocol moves to the next
 **round**, and a new validator gets to propose a block for that height.
 Two stages of voting are required to successfully commit a block; we
-call them **pre-vote** and **pre-commit**. A block is committed when
-more than 2/3 of validators pre-commit for the same block in the same
-round.
+call them **pre-vote** and **pre-commit**. 
 
 There is a picture of a couple doing the polka because validators are
 doing something like a polka dance. When more than two-thirds of the
 validators pre-vote for the same block, we call that a **polka**. Every
 pre-commit must be justified by a polka in the same round.
+A block is committed when
+more than 2/3 of validators pre-commit for the same block in the same
+round.
 
 Validators may fail to commit a block for a number of reasons; the
 current proposer may be offline, or the network may be slow. Tendermint

docs/qa/README.md

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

@@ -0,0 +1,214 @@
+---
+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

@@ -0,0 +1,278 @@
+---
+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

@@ -0,0 +1,52 @@
+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

@@ -0,0 +1,326 @@
+---
+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

@@ -0,0 +1,52 @@
+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
+