Prepare changelog for v0.35.1 release. (#7702)

Bumps [github.com/golangci/golangci-lint](https://github.com/golangci/golangci-lint) from 1.43.0 to 1.44.0.
- [Release notes](https://github.com/golangci/golangci-lint/releases)
- [Changelog](https://github.com/golangci/golangci-lint/blob/master/CHANGELOG.md)
- [Commits](https://github.com/golangci/golangci-lint/compare/v1.43.0...v1.44.0)

---
updated-dependencies:
- dependency-name: github.com/golangci/golangci-lint
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>

Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

.github/CODEOWNERS

@@ -7,4 +7,4 @@
 # 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.
-*       @alexanderbez @ebuchman @cmwaters @tessr @tychoish @williambanfield @creachadair
+*      @ebuchman @cmwaters @tychoish @williambanfield @creachadair

.github/codecov.yml

@@ -5,19 +5,14 @@ coverage:
   status:
     project:
       default:
-        threshold: 1%
-    patch: on
+        threshold: 20%
+    patch: off
     changes: off
 
 github_checks:
   annotations: false
 
-comment:
-  layout: "diff, files"
-  behavior: default
-  require_changes: no
-  require_base: no
-  require_head: yes
+comment: false
 
 ignore:
   - "docs"
@@ -25,3 +20,6 @@ ignore:
   - "scripts"
   - "**/*.pb.go"
   - "libs/pubsub/query/query.peg.go"
+  - "*.md"
+  - "*.rst"
+  - "*.yml"

.github/mergify.yml

@@ -1,18 +1,19 @@
-pull_request_rules:
-  - name: Automerge to master
+queue_rules:
+  - name: default
     conditions:
-      - base=master
+      - base=v0.35.x
+      - label=S:automerge
+
+pull_request_rules:
+  - name: Automerge to v0.35.x
+    conditions:
+      - base=v0.35.x
       - label=S:automerge
     actions:
-      merge:
+      queue:
         method: squash
-        strict: true
-        commit_message: title+body
-  - name: backport patches to v0.34.x branch
-    conditions:
-      - base=master
-      - label=S:backport-to-v0.34.x
-    actions:
-      backport:
-        branches:
-          - v0.34.x
+        name: default
+        commit_message_template: |
+          {{ title }} (#{{ number }})
+
+          {{ body }}

.github/workflows/build.yml

@@ -0,0 +1,82 @@
+name: Build
+# Tests runs different tests (test_abci_apps, test_abci_cli, test_apps)
+# This workflow runs on every push to master or release branch and  every pull requests
+# All jobs will pass without running if no *{.go, .mod, .sum} files have been modified
+on:
+  pull_request:
+  push:
+    branches:
+      - master
+      - release/**
+
+jobs:
+  build:
+    name: Build
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        goarch: ["arm", "amd64"]
+        goos: ["linux"]
+    timeout-minutes: 5
+    steps:
+      - uses: actions/setup-go@v2
+        with:
+          go-version: "1.17"
+      - uses: actions/checkout@v2.4.0
+      - uses: technote-space/get-diff-action@v5
+        with:
+          PATTERNS: |
+            **/**.go
+            "!test/"
+            go.mod
+            go.sum
+            Makefile
+      - name: install
+        run: GOOS=${{ matrix.goos }} GOARCH=${{ matrix.goarch }} make build
+        if: "env.GIT_DIFF != ''"
+
+  test_abci_cli:
+    runs-on: ubuntu-latest
+    needs: build
+    timeout-minutes: 5
+    steps:
+      - uses: actions/setup-go@v2
+        with:
+          go-version: "1.17"
+      - uses: actions/checkout@v2.4.0
+      - uses: technote-space/get-diff-action@v5
+        with:
+          PATTERNS: |
+            **/**.go
+            go.mod
+            go.sum
+      - name: install
+        run: make install_abci
+        if: "env.GIT_DIFF != ''"
+      - run: abci/tests/test_cli/test.sh
+        shell: bash
+        if: "env.GIT_DIFF != ''"
+
+  test_apps:
+    runs-on: ubuntu-latest
+    needs: build
+    timeout-minutes: 5
+    steps:
+      - uses: actions/setup-go@v2
+        with:
+          go-version: "1.17"
+      - uses: actions/checkout@v2.4.0
+      - uses: technote-space/get-diff-action@v5
+        with:
+          PATTERNS: |
+            **/**.go
+            go.mod
+            go.sum
+      - name: install
+        run: make install install_abci
+        if: "env.GIT_DIFF != ''"
+      - name: test_apps
+        run: test/app/test.sh
+        shell: bash
+        if: "env.GIT_DIFF != ''"

.github/workflows/coverage.yml

@@ -1,127 +0,0 @@
-name: Test Coverage
-on:
-  pull_request:
-  push:
-    branches:
-      - master
-      - release/**
-
-jobs:
-  split-test-files:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v2.3.4
-      - name: Create a file with all the pkgs
-        run: go list ./... > pkgs.txt
-      - name: Split pkgs into 4 files
-        run: split -d -n l/4 pkgs.txt pkgs.txt.part.
-      # cache multiple
-      - uses: actions/upload-artifact@v2
-        with:
-          name: "${{ github.sha }}-00"
-          path: ./pkgs.txt.part.00
-      - uses: actions/upload-artifact@v2
-        with:
-          name: "${{ github.sha }}-01"
-          path: ./pkgs.txt.part.01
-      - uses: actions/upload-artifact@v2
-        with:
-          name: "${{ github.sha }}-02"
-          path: ./pkgs.txt.part.02
-      - uses: actions/upload-artifact@v2
-        with:
-          name: "${{ github.sha }}-03"
-          path: ./pkgs.txt.part.03
-
-  build-linux:
-    name: Build
-    runs-on: ubuntu-latest
-    strategy:
-      fail-fast: false
-      matrix:
-        goarch: ["arm", "amd64"]
-    timeout-minutes: 5
-    steps:
-      - uses: actions/setup-go@v2
-        with:
-          go-version: "1.16"
-      - uses: actions/checkout@v2.3.4
-      - uses: technote-space/get-diff-action@v5
-        with:
-          PATTERNS: |
-            **/**.go
-            go.mod
-            go.sum
-      - name: install
-        run: GOOS=linux GOARCH=${{ matrix.goarch }} make build
-        if: "env.GIT_DIFF != ''"
-
-  tests:
-    runs-on: ubuntu-latest
-    needs: split-test-files
-    strategy:
-      fail-fast: false
-      matrix:
-        part: ["00", "01", "02", "03"]
-    steps:
-      - uses: actions/setup-go@v2
-        with:
-          go-version: "1.16"
-      - uses: actions/checkout@v2.3.4
-      - uses: technote-space/get-diff-action@v5
-        with:
-          PATTERNS: |
-            **/**.go
-            go.mod
-            go.sum
-      - uses: actions/download-artifact@v2
-        with:
-          name: "${{ github.sha }}-${{ matrix.part }}"
-        if: env.GIT_DIFF
-      - name: Set up Go
-        uses: actions/setup-go@v2
-        with:
-          go-version: 1.16
-      - name: test & coverage report creation
-        run: |
-          cat pkgs.txt.part.${{ matrix.part }} | xargs go test -mod=readonly -timeout 8m -race -coverprofile=${{ matrix.part }}profile.out -covermode=atomic
-        if: env.GIT_DIFF
-      - uses: actions/upload-artifact@v2
-        with:
-          name: "${{ github.sha }}-${{ matrix.part }}-coverage"
-          path: ./${{ matrix.part }}profile.out
-
-  upload-coverage-report:
-    runs-on: ubuntu-latest
-    needs: tests
-    steps:
-      - uses: actions/checkout@v2.3.4
-      - uses: technote-space/get-diff-action@v5
-        with:
-          PATTERNS: |
-            **/**.go
-            go.mod
-            go.sum
-      - uses: actions/download-artifact@v2
-        with:
-          name: "${{ github.sha }}-00-coverage"
-        if: env.GIT_DIFF
-      - uses: actions/download-artifact@v2
-        with:
-          name: "${{ github.sha }}-01-coverage"
-        if: env.GIT_DIFF
-      - uses: actions/download-artifact@v2
-        with:
-          name: "${{ github.sha }}-02-coverage"
-        if: env.GIT_DIFF
-      - uses: actions/download-artifact@v2
-        with:
-          name: "${{ github.sha }}-03-coverage"
-        if: env.GIT_DIFF
-      - run: |
-          cat ./*profile.out | grep -v "mode: atomic" >> coverage.txt
-        if: env.GIT_DIFF
-      - uses: codecov/codecov-action@v2.0.2
-        with:
-          file: ./coverage.txt
-        if: env.GIT_DIFF

.github/workflows/docker.yml

@@ -1,8 +1,7 @@
-name: Build & Push
+name: Docker
 #  Build & Push rebuilds the tendermint docker image on every push to master and creation of tags
 # and pushes the image to https://hub.docker.com/r/interchainio/simapp/tags
 on:
-  pull_request:
   push:
     branches:
       - master
@@ -39,8 +38,8 @@ jobs:
         with:
           platforms: all
 
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v1.5.0
+      - name: Set up Docker Build
+        uses: docker/setup-buildx-action@v1.6.0
 
       - name: Login to DockerHub
         if: ${{ github.event_name != 'pull_request' }}

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

@@ -17,13 +17,13 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        group: ['00', '01', '02', '03']
+        group: ['00', '01']
     runs-on: ubuntu-latest
     timeout-minutes: 60
     steps:
       - uses: actions/setup-go@v2
         with:
-          go-version: '1.16'
+          go-version: '1.17'
 
       - uses: actions/checkout@v2.3.4
         with:
@@ -37,7 +37,7 @@ jobs:
       - name: Generate testnets
         working-directory: test/e2e
         # When changing -g, also change the matrix groups above
-        run: ./build/generator -g 4 -d networks/nightly
+        run: ./build/generator -g 2 -d networks/nightly
 
       - name: Run testnets in group ${{ matrix.group }}
         working-directory: test/e2e

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

@@ -17,25 +17,25 @@ jobs:
       fail-fast: false
       matrix:
         p2p: ['legacy', 'new', 'hybrid']
-        group: ['00', '01']
+        group: ['00', '01', '02', '03']
     runs-on: ubuntu-latest
     timeout-minutes: 60
     steps:
       - uses: actions/setup-go@v2
         with:
-          go-version: '1.16'
+          go-version: '1.17'
 
       - uses: actions/checkout@v2.3.4
 
       - name: Build
         working-directory: test/e2e
         # Run make jobs in parallel, since we can't run steps in parallel.
-        run: make -j2 docker generator runner
+        run: make -j2 docker generator runner tests
 
       - name: Generate testnets
         working-directory: test/e2e
         # When changing -g, also change the matrix groups above
-        run: ./build/generator -g 2 -d networks/nightly/${{ matrix.p2p }} -p ${{ matrix.p2p }}
+        run: ./build/generator -g 4 -d networks/nightly/${{ matrix.p2p }} -p ${{ matrix.p2p }}
 
       - name: Run ${{ matrix.p2p }} p2p testnets in group ${{ matrix.group }}
         working-directory: test/e2e

.github/workflows/e2e.yml

@@ -16,7 +16,7 @@ jobs:
     steps:
       - uses: actions/setup-go@v2
         with:
-          go-version: '1.16'
+          go-version: '1.17'
       - uses: actions/checkout@v2.3.4
       - uses: technote-space/get-diff-action@v5
         with:
@@ -28,7 +28,7 @@ jobs:
       - name: Build
         working-directory: test/e2e
         # Run two make jobs in parallel, since we can't run steps in parallel.
-        run: make -j2 docker runner
+        run: make -j2 docker runner tests
         if: "env.GIT_DIFF != ''"
 
       - name: Run CI testnet

.github/workflows/fuzz-nightly.yml

@@ -1,5 +1,5 @@
 # Runs fuzzing nightly.
-name: fuzz-nightly
+name: Fuzz Tests
 on:
   workflow_dispatch: # allow running workflow manually
   schedule:
@@ -15,7 +15,7 @@ jobs:
     steps:
       - uses: actions/setup-go@v2
         with:
-          go-version: '1.16'
+          go-version: '1.17'
 
       - uses: actions/checkout@v2.3.4
 

.github/workflows/lint.yml

@@ -13,7 +13,7 @@ jobs:
     runs-on: ubuntu-latest
     timeout-minutes: 8
     steps:
-      - uses: actions/checkout@v2.3.4
+      - uses: actions/checkout@v2.4.0
       - uses: technote-space/get-diff-action@v5
         with:
           PATTERNS: |
@@ -23,7 +23,7 @@ jobs:
       - uses: golangci/golangci-lint-action@v2.5.2
         with:
           # Required: the version of golangci-lint is required and must be specified without patch version: we always use the latest patch version.
-          version: v1.38
+          version: v1.42.1
           args: --timeout 10m
           github-token: ${{ secrets.github_token }}
         if: env.GIT_DIFF

.github/workflows/linter.yml

@@ -19,7 +19,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout Code
-        uses: actions/checkout@v2.3.4
+        uses: actions/checkout@v2.4.0
       - name: Lint Code Base
         uses: docker://github/super-linter:v3
         env:

.github/workflows/proto-docker.yml

@@ -34,7 +34,7 @@ jobs:
           echo ::set-output name=tags::${TAGS}
 
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v1.5.0
+        uses: docker/setup-buildx-action@v1.6.0
 
       - name: Login to DockerHub
         uses: docker/login-action@v1.10.0

.github/workflows/release.yml

@@ -2,7 +2,7 @@ name: "Release"
 
 on:
   push:
-    branches: 
+    branches:
       - "RC[0-9]/**"
     tags:
       - "v[0-9]+.[0-9]+.[0-9]+" # Push events to matching v*, i.e. v1.0, v20.15.10
@@ -18,10 +18,7 @@ jobs:
 
       - uses: actions/setup-go@v2
         with:
-          go-version: '1.16'
-
-      - run: echo https://github.com/tendermint/tendermint/blob/${GITHUB_REF#refs/tags/}/CHANGELOG.md#${GITHUB_REF#refs/tags/} > ../release_notes.md 
-        if: startsWith(github.ref, 'refs/tags/')
+          go-version: '1.17'
 
       - name: Build
         uses: goreleaser/goreleaser-action@v2
@@ -35,6 +32,6 @@ jobs:
         if: startsWith(github.ref, 'refs/tags/')
         with:
           version: latest
-          args: release --rm-dist --release-notes=../release_notes.md
+          args: release --rm-dist
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/tests.yml

@@ -1,106 +1,75 @@
-name: Tests
-# Tests runs different tests (test_abci_apps, test_abci_cli, test_apps)
-# This workflow runs on every push to master or release branch and  every pull requests
-# All jobs will pass without running if no *{.go, .mod, .sum} files have been modified
+name: Test
 on:
   pull_request:
   push:
+    paths:
+      - "**.go"
     branches:
       - master
       - release/**
 
 jobs:
-  build:
-    name: Build
+  tests:
     runs-on: ubuntu-latest
-    timeout-minutes: 5
+    strategy:
+      fail-fast: false
+      matrix:
+        part: ["00", "01", "02", "03"]
     steps:
       - uses: actions/setup-go@v2
         with:
-          go-version: "1.16"
+          go-version: "1.17"
       - uses: actions/checkout@v2.3.4
       - uses: technote-space/get-diff-action@v5
         with:
           PATTERNS: |
             **/**.go
+            "!test/"
             go.mod
             go.sum
-      - name: install
-        run: make install install_abci
-        if: "env.GIT_DIFF != ''"
-      - uses: actions/cache@v2.1.6
-        with:
-          path: ~/go/pkg/mod
-          key: ${{ runner.os }}-go-${{ hashFiles('**/go.sum') }}
-          restore-keys: |
-            ${{ runner.os }}-go-
+            Makefile
+      - name: Run Go Tests
+        run: |
+          make test-group-${{ matrix.part }} NUM_SPLIT=4
         if: env.GIT_DIFF
-      # Cache binaries for use by other jobs
-      - uses: actions/cache@v2.1.6
+      - uses: actions/upload-artifact@v2
         with:
-          path: ~/go/bin
-          key: ${{ runner.os }}-${{ github.sha }}-tm-binary
-        if: env.GIT_DIFF
+          name: "${{ github.sha }}-${{ matrix.part }}-coverage"
+          path: ./build/${{ matrix.part }}.profile.out
 
-  test_abci_cli:
+  upload-coverage-report:
     runs-on: ubuntu-latest
-    needs: build
-    timeout-minutes: 5
+    needs: tests
     steps:
-      - uses: actions/setup-go@v2
-        with:
-          go-version: "1.16"
-      - uses: actions/checkout@v2.3.4
+      - uses: actions/checkout@v2.4.0
       - uses: technote-space/get-diff-action@v5
         with:
           PATTERNS: |
             **/**.go
+            "!test/"
             go.mod
             go.sum
-      - uses: actions/cache@v2.1.6
+            Makefile
+      - uses: actions/download-artifact@v2
         with:
-          path: ~/go/pkg/mod
-          key: ${{ runner.os }}-go-${{ hashFiles('**/go.sum') }}
-          restore-keys: |
-            ${{ runner.os }}-go-
+          name: "${{ github.sha }}-00-coverage"
         if: env.GIT_DIFF
-      - uses: actions/cache@v2.1.6
+      - uses: actions/download-artifact@v2
         with:
-          path: ~/go/bin
-          key: ${{ runner.os }}-${{ github.sha }}-tm-binary
+          name: "${{ github.sha }}-01-coverage"
         if: env.GIT_DIFF
-      - run: abci/tests/test_cli/test.sh
-        shell: bash
-        if: env.GIT_DIFF
-
-  test_apps:
-    runs-on: ubuntu-latest
-    needs: build
-    timeout-minutes: 5
-    steps:
-      - uses: actions/setup-go@v2
+      - uses: actions/download-artifact@v2
         with:
-          go-version: "1.16"
-      - uses: actions/checkout@v2.3.4
-      - uses: technote-space/get-diff-action@v5
-        with:
-          PATTERNS: |
-            **/**.go
-            go.mod
-            go.sum
-      - uses: actions/cache@v2.1.6
-        with:
-          path: ~/go/pkg/mod
-          key: ${{ runner.os }}-go-${{ hashFiles('**/go.sum') }}
-          restore-keys: |
-            ${{ runner.os }}-go-
+          name: "${{ github.sha }}-02-coverage"
         if: env.GIT_DIFF
-      - uses: actions/cache@v2.1.6
+      - uses: actions/download-artifact@v2
         with:
-          path: ~/go/bin
-          key: ${{ runner.os }}-${{ github.sha }}-tm-binary
+          name: "${{ github.sha }}-03-coverage"
         if: env.GIT_DIFF
-      - name: test_apps
-        run: test/app/test.sh
-        shell: bash
+      - run: |
+          cat ./*profile.out | grep -v "mode: set" >> coverage.txt
+        if: env.GIT_DIFF
+      - uses: codecov/codecov-action@v2.1.0
+        with:
+          file: ./coverage.txt
         if: env.GIT_DIFF

.gitignore

@@ -25,6 +25,7 @@ docs/_build
 docs/dist
 docs/node_modules/
 docs/spec
+docs/.vuepress/public/rpc
 index.html.md
 libs/pubsub/query/fuzz_test/output
 profile\.out

.golangci.yml

@@ -1,54 +1,51 @@
 linters:
   enable:
+    - asciicheck
     - bodyclose
     - deadcode
     - depguard
     - dogsled
     - dupl
     - errcheck
+    - exportloopref
     # - funlen
     # - gochecknoglobals
     # - gochecknoinits
+    # - gocognit
     - goconst
-    - gocritic
+    # - gocritic
     # - gocyclo
     # - godox
     - gofmt
     - goimports
-    - golint
+    - revive
     - gosec
     - gosimple
     - govet
     - ineffassign
     # - interfacer
-    - lll
-    - misspell
+    # - lll
     # - maligned
+    - misspell
     - nakedret
+    - nolintlint
     - prealloc
-    - scopelint
     - staticcheck
     - structcheck
     - stylecheck
-    - typecheck
+    # - typecheck
     - unconvert
     # - unparam
     - unused
     - varcheck
     # - whitespace
     # - wsl
-    # - gocognit
-    - nolintlint
-    - asciicheck
 
 issues:
   exclude-rules:
     - path: _test\.go
       linters:
         - gosec
-    - linters:
-        - lll
-      source: "https://"
   max-same-issues: 50
 
 linters-settings:

CHANGELOG.md

@@ -1,6 +1,226 @@
 # Changelog
 
-Friendly reminder, we have a [bug bounty program](https://hackerone.com/tendermint).
+Friendly reminder: We have a [bug bounty program](https://hackerone.com/cosmos).
+
+## v0.35.1
+
+January 26, 2022
+
+Special thanks to external contributors on this release: @altergui, @odeke-em,
+@thanethomson
+
+### BREAKING CHANGES
+
+- CLI/RPC/Config
+
+  - [config] [\#7276](https://github.com/tendermint/tendermint/pull/7276) rpc: Add experimental config params to allow for subscription buffer size control (@thanethomson).
+
+- P2P Protocol
+
+  - [p2p] [\#7265](https://github.com/tendermint/tendermint/pull/7265) Peer manager reduces peer score for each failed dial attempts for peers that have not successfully dialed. (@tychoish)
+  - [p2p] [\#7594](https://github.com/tendermint/tendermint/pull/7594) always advertise self, to enable mutual address discovery. (@altergui)
+
+### FEATURES
+
+- [rpc] [\#7270](https://github.com/tendermint/tendermint/pull/7270) Add `header` and `header_by_hash` RPC Client queries. (@fedekunze) (@cmwaters)
+
+### IMPROVEMENTS
+
+- [internal/protoio] [\#7325](https://github.com/tendermint/tendermint/pull/7325) Optimized `MarshalDelimited` by inlining the common case and using a `sync.Pool` in the worst case. (@odeke-em)
+- [\#7338](https://github.com/tendermint/tendermint/pull/7338) pubsub: Performance improvements for the event query API (backport of #7319) (@creachadair)
+- [\#7252](https://github.com/tendermint/tendermint/pull/7252) Add basic metrics to the indexer package. (@creachadair)
+- [\#7338](https://github.com/tendermint/tendermint/pull/7338) Performance improvements for the event query API. (@creachadair)
+
+### BUG FIXES
+
+- [\#7310](https://github.com/tendermint/tendermint/issues/7310) pubsub: Report a non-nil error when shutting down (fixes #7306).
+- [\#7355](https://github.com/tendermint/tendermint/pull/7355) Fix incorrect tests using the PSQL sink. (@creachadair)
+- [\#7683](https://github.com/tendermint/tendermint/pull/7683) rpc: check error code for broadcast_tx_commit. (@tychoish)
+
+## v0.35.0
+
+November 4, 2021
+
+Special thanks to external contributors on this release: @JayT106,
+@bipulprasad, @alessio, @Yawning, @silasdavis, @cuonglm, @tanyabouman,
+@JoeKash, @githubsands, @jeebster, @crypto-facs, @liamsi, and @gotjoshua
+
+### FEATURES
+
+- [cli] [#7033](https://github.com/tendermint/tendermint/pull/7033) Add a `rollback` command to rollback to the previous tendermint state in the event of an incorrect app hash. (@cmwaters)
+- [config] [\#7174](https://github.com/tendermint/tendermint/pull/7174) expose ability to write config to arbitrary paths. (@tychoish)
+- [mempool, rpc] [\#7065](https://github.com/tendermint/tendermint/pull/7065) add removetx rpc method (backport of #7047) (@tychoish).
+- [\#6982](https://github.com/tendermint/tendermint/pull/6982) tendermint binary has built-in suppport for running the e2e application (with state sync support) (@cmwaters).
+- [config] Add `--mode` flag and config variable. See [ADR-52](https://github.com/tendermint/tendermint/blob/master/docs/architecture/adr-052-tendermint-mode.md) @dongsam
+- [rpc] [\#6329](https://github.com/tendermint/tendermint/pull/6329) Don't cap page size in unsafe mode (@gotjoshua, @cmwaters)
+- [pex] [\#6305](https://github.com/tendermint/tendermint/pull/6305) v2 pex reactor with backwards compatability. Introduces two new pex messages to
+  accomodate for the new p2p stack. Removes the notion of seeds and crawling. All peer
+  exchange reactors behave the same. (@cmwaters)
+- [crypto] [\#6376](https://github.com/tendermint/tendermint/pull/6376) Enable sr25519 as a validator key type
+- [mempool] [\#6466](https://github.com/tendermint/tendermint/pull/6466) Introduction of a prioritized mempool. (@alexanderbez)
+  - `Priority` and `Sender` have been introduced into the `ResponseCheckTx` type, where the `priority` will determine the prioritization of
+  the transaction when a proposer reaps transactions for a block proposal. The `sender` field acts as an index.
+  - Operators may toggle between the legacy mempool reactor, `v0`, and the new prioritized reactor, `v1`, by setting the
+  `mempool.version` configuration, where `v1` is the default configuration.
+  - Applications that do not specify a priority, i.e. zero, will have transactions reaped by the order in which they are received by the node.
+  - Transactions are gossiped in FIFO order as they are in `v0`.
+- [config/indexer] [\#6411](https://github.com/tendermint/tendermint/pull/6411) Introduce support for custom event indexing data sources, specifically PostgreSQL. (@JayT106)
+- [blocksync/event] [\#6619](https://github.com/tendermint/tendermint/pull/6619) Emit blocksync status event when switching consensus/blocksync (@JayT106)
+- [statesync/event] [\#6700](https://github.com/tendermint/tendermint/pull/6700) Emit statesync status start/end event (@JayT106)
+- [inspect] [\#6785](https://github.com/tendermint/tendermint/pull/6785) Add a new `inspect` command for introspecting the state and block store of a crashed tendermint node. (@williambanfield)
+
+### BUG FIXES
+
+- [\#7106](https://github.com/tendermint/tendermint/pull/7106) Revert mutex change to ABCI Clients (@tychoish).
+- [\#7142](https://github.com/tendermint/tendermint/pull/7142) mempool: remove panic when recheck-tx was not sent to ABCI application (@williambanfield).
+- [consensus]: [\#7060](https://github.com/tendermint/tendermint/pull/7060)
+  wait until peerUpdates channel is closed to close remaining peers (@williambanfield)
+- [privval] [\#5638](https://github.com/tendermint/tendermint/pull/5638) Increase read/write timeout to 5s and calculate ping interval based on it (@JoeKash)
+- [evidence] [\#6375](https://github.com/tendermint/tendermint/pull/6375) Fix bug with inconsistent LightClientAttackEvidence hashing (cmwaters)
+- [rpc] [\#6507](https://github.com/tendermint/tendermint/pull/6507) Ensure RPC client can handle URLs without ports (@JayT106)
+- [statesync] [\#6463](https://github.com/tendermint/tendermint/pull/6463) Adds Reverse Sync feature to fetch historical light blocks after state sync in order to verify any evidence (@cmwaters)
+- [blocksync] [\#6590](https://github.com/tendermint/tendermint/pull/6590) Update the metrics during blocksync (@JayT106)
+
+### BREAKING CHANGES
+
+- Go API
+
+  - [crypto/armor]: [\#6963](https://github.com/tendermint/tendermint/pull/6963) remove package which is unused, and based on
+    deprecated fundamentals. Downstream users should maintain this
+    library. (@tychoish)
+  - [state] [store] [proxy] [rpc/core]: [\#6937](https://github.com/tendermint/tendermint/pull/6937) move packages to
+    `internal` to prevent consumption of these internal APIs by
+    external users. (@tychoish)
+  - [pubsub] [\#6634](https://github.com/tendermint/tendermint/pull/6634) The `Query#Matches` method along with other pubsub methods, now accepts a `[]abci.Event` instead of `map[string][]string`. (@alexanderbez)
+  - [p2p] [\#6618](https://github.com/tendermint/tendermint/pull/6618) [\#6583](https://github.com/tendermint/tendermint/pull/6583) Move `p2p.NodeInfo`, `p2p.NodeID` and `p2p.NetAddress` into `types` to support use in external packages. (@tychoish)
+  - [node] [\#6540](https://github.com/tendermint/tendermint/pull/6540) Reduce surface area of the `node` package by making most of the implementation details private. (@tychoish)
+  - [p2p] [\#6547](https://github.com/tendermint/tendermint/pull/6547) Move the entire `p2p` package and all reactor implementations into `internal`.  (@tychoish)
+  - [libs/log] [\#6534](https://github.com/tendermint/tendermint/pull/6534) Remove the existing custom Tendermint logger backed by go-kit. The logging interface, `Logger`, remains. Tendermint still provides a default logger backed by the performant zerolog logger. (@alexanderbez)
+  - [libs/time] [\#6495](https://github.com/tendermint/tendermint/pull/6495) Move types/time to libs/time to improve consistency. (@tychoish)
+  - [mempool] [\#6529](https://github.com/tendermint/tendermint/pull/6529) The `Context` field has been removed from the `TxInfo` type. `CheckTx` now requires a `Context` argument. (@alexanderbez)
+  - [abci/client, proxy] [\#5673](https://github.com/tendermint/tendermint/pull/5673) `Async` funcs return an error, `Sync` and `Async` funcs accept `context.Context` (@melekes)
+  - [p2p] Remove unused function `MakePoWTarget`. (@erikgrinaker)
+  - [libs/bits] [\#5720](https://github.com/tendermint/tendermint/pull/5720) Validate `BitArray` in `FromProto`, which now returns an error (@melekes)
+  - [proto/p2p] Rename `DefaultNodeInfo` and `DefaultNodeInfoOther` to `NodeInfo` and `NodeInfoOther` (@erikgrinaker)
+  - [proto/p2p] Rename `NodeInfo.default_node_id` to `node_id` (@erikgrinaker)
+  - [libs/os] Kill() and {Must,}{Read,Write}File() functions have been removed. (@alessio)
+  - [store] [\#5848](https://github.com/tendermint/tendermint/pull/5848) Remove block store state in favor of using the db iterators directly (@cmwaters)
+  - [state] [\#5864](https://github.com/tendermint/tendermint/pull/5864) Use an iterator when pruning state (@cmwaters)
+  - [types] [\#6023](https://github.com/tendermint/tendermint/pull/6023) Remove `tm2pb.Header`, `tm2pb.BlockID`, `tm2pb.PartSetHeader` and `tm2pb.NewValidatorUpdate`.
+	- Each of the above types has a `ToProto` and `FromProto` method or function which replaced this logic.
+  - [light] [\#6054](https://github.com/tendermint/tendermint/pull/6054) Move `MaxRetryAttempt` option from client to provider.
+	- `NewWithOptions` now sets the max retry attempts and timeouts (@cmwaters)
+  - [all] [\#6077](https://github.com/tendermint/tendermint/pull/6077) Change spelling from British English to American (@cmwaters)
+	- Rename "Subscription.Cancelled()" to "Subscription.Canceled()" in libs/pubsub
+	- Rename "behaviour" pkg to "behavior" and internalized it in blocksync v2
+  - [rpc/client/http] [\#6176](https://github.com/tendermint/tendermint/pull/6176) Remove `endpoint` arg from `New`, `NewWithTimeout` and `NewWithClient` (@melekes)
+  - [rpc/client/http] [\#6176](https://github.com/tendermint/tendermint/pull/6176) Unexpose `WSEvents` (@melekes)
+  - [rpc/jsonrpc/client/ws_client] [\#6176](https://github.com/tendermint/tendermint/pull/6176) `NewWS` no longer accepts options (use `NewWSWithOptions` and `OnReconnect` funcs to configure the client) (@melekes)
+  - [internal/libs] [\#6366](https://github.com/tendermint/tendermint/pull/6366) Move `autofile`, `clist`,`fail`,`flowrate`, `protoio`, `sync`, `tempfile`, `test` and `timer` lib packages to an internal folder
+  - [libs/rand] [\#6364](https://github.com/tendermint/tendermint/pull/6364) Remove most of libs/rand in favour of standard lib's `math/rand` (@liamsi)
+  - [mempool] [\#6466](https://github.com/tendermint/tendermint/pull/6466) The original mempool reactor has been versioned as `v0` and moved to a sub-package under the root `mempool` package.
+	Some core types have been kept in the `mempool` package such as `TxCache` and it's implementations, the `Mempool` interface itself
+	and `TxInfo`. (@alexanderbez)
+  - [crypto/sr25519] [\#6526](https://github.com/tendermint/tendermint/pull/6526) Do not re-execute the Ed25519-style key derivation step when doing signing and verification.  The derivation is now done once and only once.  This breaks `sr25519.GenPrivKeyFromSecret` output compatibility. (@Yawning)
+  - [types] [\#6627](https://github.com/tendermint/tendermint/pull/6627) Move `NodeKey` to types to make the type public.
+  - [config] [\#6627](https://github.com/tendermint/tendermint/pull/6627) Extend `config` to contain methods `LoadNodeKeyID` and `LoadorGenNodeKeyID`
+  - [blocksync] [\#6755](https://github.com/tendermint/tendermint/pull/6755) Rename `FastSync` and `Blockchain` package to `BlockSync` (@cmwaters)
+
+- CLI/RPC/Config
+
+  - [pubsub/events] [\#6634](https://github.com/tendermint/tendermint/pull/6634) The `ResultEvent.Events` field is now of type `[]abci.Event` preserving event order instead of `map[string][]string`. (@alexanderbez)
+  - [config] [\#5598](https://github.com/tendermint/tendermint/pull/5598) The `test_fuzz` and `test_fuzz_config` P2P settings have been removed. (@erikgrinaker)
+  - [config] [\#5728](https://github.com/tendermint/tendermint/pull/5728) `fastsync.version = "v1"` is no longer supported (@melekes)
+  - [cli] [\#5772](https://github.com/tendermint/tendermint/pull/5772) `gen_node_key` prints JSON-encoded `NodeKey` rather than ID and does not save it to `node_key.json` (@melekes)
+  - [cli] [\#5777](https://github.com/tendermint/tendermint/pull/5777) use hyphen-case instead of snake_case for all cli commands and config parameters (@cmwaters)
+  - [rpc] [\#6019](https://github.com/tendermint/tendermint/pull/6019) standardise RPC errors and return the correct status code (@bipulprasad & @cmwaters)
+  - [rpc] [\#6168](https://github.com/tendermint/tendermint/pull/6168) Change default sorting to desc for `/tx_search` results (@melekes)
+  - [cli] [\#6282](https://github.com/tendermint/tendermint/pull/6282) User must specify the node mode when using `tendermint init` (@cmwaters)
+  - [state/indexer] [\#6382](https://github.com/tendermint/tendermint/pull/6382) reconstruct indexer, move txindex into the indexer package (@JayT106)
+  - [cli] [\#6372](https://github.com/tendermint/tendermint/pull/6372) Introduce `BootstrapPeers` as part of the new p2p stack. Peers to be connected on  startup (@cmwaters)
+  - [config] [\#6462](https://github.com/tendermint/tendermint/pull/6462) Move `PrivValidator` configuration out of `BaseConfig` into its own section. (@tychoish)
+  - [rpc] [\#6610](https://github.com/tendermint/tendermint/pull/6610) Add MaxPeerBlockHeight into /status rpc call (@JayT106)
+  - [blocksync/rpc] [\#6620](https://github.com/tendermint/tendermint/pull/6620) Add TotalSyncedTime & RemainingTime to SyncInfo in /status RPC  (@JayT106)
+  - [rpc/grpc] [\#6725](https://github.com/tendermint/tendermint/pull/6725) Mark gRPC in the RPC layer as deprecated.
+  - [blocksync/v2] [\#6730](https://github.com/tendermint/tendermint/pull/6730) Fast Sync v2 is deprecated, please use v0
+  - [rpc] Add genesis_chunked method to support paginated and parallel fetching of large genesis documents.
+  - [rpc/jsonrpc/server] [\#6785](https://github.com/tendermint/tendermint/pull/6785) `Listen` function updated to take an `int` argument, `maxOpenConnections`, instead of an entire config object. (@williambanfield)
+  - [rpc] [\#6820](https://github.com/tendermint/tendermint/pull/6820) Update RPC methods to reflect changes in the p2p layer, disabling support for `UnsafeDialPeers` and `UnsafeDialPeers` when used with the new p2p layer, and changing the response format of the peer list in `NetInfo` for all users.
+  - [cli] [\#6854](https://github.com/tendermint/tendermint/pull/6854) Remove deprecated snake case commands. (@tychoish)
+  - [tools] [\#6498](https://github.com/tendermint/tendermint/pull/6498) Set OS home dir to instead of the hardcoded PATH. (@JayT106)
+  - [cli/indexer] [\#6676](https://github.com/tendermint/tendermint/pull/6676) Reindex events command line tooling. (@JayT106)
+
+- Apps
+
+  - [ABCI] [\#6408](https://github.com/tendermint/tendermint/pull/6408) Change the `key` and `value` fields from `[]byte` to `string` in the `EventAttribute` type. (@alexanderbez)
+  - [ABCI] [\#5447](https://github.com/tendermint/tendermint/pull/5447) Remove `SetOption` method from `ABCI.Client` interface
+  - [ABCI] [\#5447](https://github.com/tendermint/tendermint/pull/5447) Reset `Oneof` indexes for  `Request` and `Response`.
+  - [ABCI] [\#5818](https://github.com/tendermint/tendermint/pull/5818) Use protoio for msg length delimitation. Migrates from int64 to uint64 length delimiters.
+  - [ABCI] [\#3546](https://github.com/tendermint/tendermint/pull/3546) Add `mempool_error` field to `ResponseCheckTx`. This field will contain an error string if Tendermint encountered an error while adding a transaction to the mempool. (@williambanfield)
+  - [Version] [\#6494](https://github.com/tendermint/tendermint/pull/6494) `TMCoreSemVer` has been renamed to `TMVersion`.
+	- It is not required any longer to set ldflags to set version strings
+  - [abci/counter] [\#6684](https://github.com/tendermint/tendermint/pull/6684) Delete counter example app
+
+- Data Storage
+  - [store/state/evidence/light] [\#5771](https://github.com/tendermint/tendermint/pull/5771) Use an order-preserving varint key encoding (@cmwaters)
+  - [mempool] [\#6396](https://github.com/tendermint/tendermint/pull/6396) Remove mempool's write ahead log (WAL), (previously unused by the tendermint code). (@tychoish)
+  - [state] [\#6541](https://github.com/tendermint/tendermint/pull/6541) Move pruneBlocks from consensus/state to state/execution. (@JayT106)
+
+### IMPROVEMENTS
+
+- [libs/log] Console log formatting changes as a result of [\#6534](https://github.com/tendermint/tendermint/pull/6534) and [\#6589](https://github.com/tendermint/tendermint/pull/6589). (@tychoish)
+- [statesync] [\#6566](https://github.com/tendermint/tendermint/pull/6566) Allow state sync fetchers and request timeout to be configurable. (@alexanderbez)
+- [types] [\#6478](https://github.com/tendermint/tendermint/pull/6478) Add `block_id` to `newblock` event (@jeebster)
+- [crypto/ed25519] [\#5632](https://github.com/tendermint/tendermint/pull/5632) Adopt zip215 `ed25519` verification. (@marbar3778)
+- [crypto/ed25519] [\#6526](https://github.com/tendermint/tendermint/pull/6526) Use [curve25519-voi](https://github.com/oasisprotocol/curve25519-voi) for `ed25519` signing and verification. (@Yawning)
+- [crypto/sr25519] [\#6526](https://github.com/tendermint/tendermint/pull/6526) Use [curve25519-voi](https://github.com/oasisprotocol/curve25519-voi) for `sr25519` signing and verification. (@Yawning)
+- [privval] [\#5603](https://github.com/tendermint/tendermint/pull/5603) Add `--key` to `init`, `gen_validator`, `testnet` & `unsafe_reset_priv_validator` for use in generating `secp256k1` keys.
+- [privval] [\#5725](https://github.com/tendermint/tendermint/pull/5725) Add gRPC support to private validator.
+- [privval] [\#5876](https://github.com/tendermint/tendermint/pull/5876) `tendermint show-validator` will query the remote signer if gRPC is being used (@marbar3778)
+- [abci/client] [\#5673](https://github.com/tendermint/tendermint/pull/5673) `Async` requests return an error if queue is full (@melekes)
+- [mempool] [\#5673](https://github.com/tendermint/tendermint/pull/5673) Cancel `CheckTx` requests if RPC client disconnects or times out (@melekes)
+- [abci] [\#5706](https://github.com/tendermint/tendermint/pull/5706) Added `AbciVersion` to `RequestInfo` allowing applications to check ABCI version when connecting to Tendermint. (@marbar3778)
+- [blocksync/v1] [\#5728](https://github.com/tendermint/tendermint/pull/5728) Remove blocksync v1 (@melekes)
+- [blocksync/v0] [\#5741](https://github.com/tendermint/tendermint/pull/5741) Relax termination conditions and increase sync timeout (@melekes)
+- [cli] [\#5772](https://github.com/tendermint/tendermint/pull/5772) `gen_node_key` output now contains node ID (`id` field) (@melekes)
+- [blocksync/v2] [\#5774](https://github.com/tendermint/tendermint/pull/5774) Send status request when new peer joins (@melekes)
+- [store] [\#5888](https://github.com/tendermint/tendermint/pull/5888) store.SaveBlock saves using batches instead of transactions for now to improve ACID properties. This is a quick fix for underlying issues around tm-db and ACID guarantees. (@githubsands)
+- [consensus] [\#5987](https://github.com/tendermint/tendermint/pull/5987) and [\#5792](https://github.com/tendermint/tendermint/pull/5792) Remove the `time_iota_ms` consensus parameter. Merge `tmproto.ConsensusParams` and `abci.ConsensusParams`. (@marbar3778, @valardragon)
+- [types] [\#5994](https://github.com/tendermint/tendermint/pull/5994) Reduce the use of protobuf types in core logic. (@marbar3778)
+  - `ConsensusParams`, `BlockParams`, `ValidatorParams`, `EvidenceParams`, `VersionParams`, `sm.Version` and `version.Consensus` have become native types. They still utilize protobuf when being sent over the wire or written to disk.
+- [rpc/client/http] [\#6163](https://github.com/tendermint/tendermint/pull/6163) Do not drop events even if the `out` channel is full (@melekes)
+- [node] [\#6059](https://github.com/tendermint/tendermint/pull/6059) Validate and complete genesis doc before saving to state store (@silasdavis)
+- [state] [\#6067](https://github.com/tendermint/tendermint/pull/6067) Batch save state data (@githubsands & @cmwaters)
+- [crypto] [\#6120](https://github.com/tendermint/tendermint/pull/6120) Implement batch verification interface for ed25519 and sr25519. (@marbar3778)
+- [types] [\#6120](https://github.com/tendermint/tendermint/pull/6120) use batch verification for verifying commits signatures.
+  - If the key type supports the batch verification API it will try to batch verify. If the verification fails we will single verify each signature.
+- [privval/file] [\#6185](https://github.com/tendermint/tendermint/pull/6185) Return error on `LoadFilePV`, `LoadFilePVEmptyState`. Allows for better programmatic control of Tendermint.
+- [privval] [\#6240](https://github.com/tendermint/tendermint/pull/6240) Add `context.Context` to privval interface.
+- [rpc] [\#6265](https://github.com/tendermint/tendermint/pull/6265) set cache control in http-rpc response header (@JayT106)
+- [statesync] [\#6378](https://github.com/tendermint/tendermint/pull/6378) Retry requests for snapshots and add a minimum discovery time (5s) for new snapshots.
+- [node/state] [\#6370](https://github.com/tendermint/tendermint/pull/6370) graceful shutdown in the consensus reactor (@JayT106)
+- [crypto/merkle] [\#6443](https://github.com/tendermint/tendermint/pull/6443) Improve HashAlternatives performance (@cuonglm)
+- [crypto/merkle] [\#6513](https://github.com/tendermint/tendermint/pull/6513) Optimize HashAlternatives (@marbar3778)
+- [p2p/pex] [\#6509](https://github.com/tendermint/tendermint/pull/6509) Improve addrBook.hash performance (@cuonglm)
+- [consensus/metrics] [\#6549](https://github.com/tendermint/tendermint/pull/6549) Change block_size gauge to a histogram for better observability over time (@marbar3778)
+- [statesync] [\#6587](https://github.com/tendermint/tendermint/pull/6587) Increase chunk priority and re-request chunks that don't arrive (@cmwaters)
+- [state/privval] [\#6578](https://github.com/tendermint/tendermint/pull/6578) No GetPubKey retry beyond the proposal/voting window (@JayT106)
+- [rpc] [\#6615](https://github.com/tendermint/tendermint/pull/6615) Add TotalGasUsed to block_results response (@crypto-facs)
+- [cmd/tendermint/commands] [\#6623](https://github.com/tendermint/tendermint/pull/6623) replace `$HOME/.some/test/dir` with `t.TempDir` (@tanyabouman)
+- [statesync] \6807 Implement P2P state provider as an alternative to RPC (@cmwaters)
+
+## v0.34.13
+
+*September 6, 2021*
+
+This release backports improvements to state synchronization and ABCI
+performance under concurrent load, and the PostgreSQL event indexer.
+
+### IMPROVEMENTS
+
+- [statesync] [\#6881](https://github.com/tendermint/tendermint/issues/6881) improvements to stateprovider logic (@cmwaters)
+- [ABCI] [\#6873](https://github.com/tendermint/tendermint/issues/6873) change client to use multi-reader mutexes (@tychoish)
+- [indexing] [\#6906](https://github.com/tendermint/tendermint/issues/6906) enable the PostgreSQL indexer sink (@creachadair)
 
 ## v0.34.12
 

CHANGELOG_PENDING.md

@@ -1,161 +1,27 @@
 # Unreleased Changes
 
+Friendly reminder: We have a [bug bounty program](https://hackerone.com/cosmos).
+
 ## vX.X
 
-Special thanks to external contributors on this release:
+Month, DD, YYYY
 
-Friendly reminder: We have a [bug bounty program](https://hackerone.com/tendermint).
+Special thanks to external contributors on this release:
 
 ### BREAKING CHANGES
 
 - CLI/RPC/Config
-  - [pubsub/events] \#6634 The `ResultEvent.Events` field is now of type `[]abci.Event` preserving event order instead of `map[string][]string`. (@alexanderbez)
-  - [config] \#5598 The `test_fuzz` and `test_fuzz_config` P2P settings have been removed. (@erikgrinaker)
-  - [config] \#5728 `fast_sync = "v1"` is no longer supported (@melekes)
-  - [cli] \#5772 `gen_node_key` prints JSON-encoded `NodeKey` rather than ID and does not save it to `node_key.json` (@melekes)
-  - [cli] \#5777 use hyphen-case instead of snake_case for all cli commands and config parameters (@cmwaters)
-  - [rpc] \#6019 standardise RPC errors and return the correct status code (@bipulprasad & @cmwaters)
-  - [rpc] \#6168 Change default sorting to desc for `/tx_search` results (@melekes)
-  - [cli] \#6282 User must specify the node mode when using `tendermint init` (@cmwaters)
-  - [state/indexer] \#6382 reconstruct indexer, move txindex into the indexer package (@JayT106)
-  - [cli] \#6372 Introduce `BootstrapPeers` as part of the new p2p stack. Peers to be connected on  startup (@cmwaters)
-  - [config] \#6462 Move `PrivValidator` configuration out of `BaseConfig` into its own section. (@tychoish)
-  - [rpc] \#6610 Add MaxPeerBlockHeight into /status rpc call (@JayT106)
-  - [fastsync/rpc] \#6620 Add TotalSyncedTime & RemainingTime to SyncInfo in /status RPC  (@JayT106)
-  - [rpc/grpc] \#6725 Mark gRPC in the RPC layer as deprecated.
-  - [blockchain/v2] \#6730 Fast Sync v2 is deprecated, please use v0
-  - [rpc] \#6820 Update RPC methods to reflect changes in the p2p layer, disabling support for `UnsafeDialPeers` and `UnsafeDialPeers` when used with the new p2p layer, and changing the response format of the peer list in `NetInfo` for all users.
 
 - Apps
-  - [ABCI] \#6408 Change the `key` and `value` fields from `[]byte` to `string` in the `EventAttribute` type. (@alexanderbez)
-  - [ABCI] \#5447 Remove `SetOption` method from `ABCI.Client` interface
-  - [ABCI] \#5447 Reset `Oneof` indexes for  `Request` and `Response`.
-  - [ABCI] \#5818 Use protoio for msg length delimitation. Migrates from int64 to uint64 length delimiters.
-  - [ABCI] \#3546 Add `mempool_error` field to `ResponseCheckTx`. This field will contain an error string if Tendermint encountered an error while adding a transaction to the mempool. (@williambanfield)
-  - [Version] \#6494 `TMCoreSemVer` has been renamed to `TMVersion`.
-	- It is not required any longer to set ldflags to set version strings
-  - [abci/counter] \#6684 Delete counter example app
 
 - P2P Protocol
 
 - Go API
-  - [pubsub] \#6634 The `Query#Matches` method along with other pubsub methods, now accepts a `[]abci.Event` instead of `map[string][]string`. (@alexanderbez)
-  - [p2p] \#6618 Move `p2p.NodeInfo` into `types` to support use of the SDK. (@tychoish)
-  - [p2p] \#6583 Make `p2p.NodeID` and `p2p.NetAddress` exported types to support their use in the RPC layer. (@tychoish)
-  - [node] \#6540 Reduce surface area of the `node` package by making most of the implementation details private. (@tychoish)
-  - [p2p] \#6547 Move the entire `p2p` package and all reactor implementations into `internal`.  (@tychoish)
-  - [libs/log] \#6534 Remove the existing custom Tendermint logger backed by go-kit. The logging interface, `Logger`, remains. Tendermint still provides a default logger backed by the performant zerolog logger. (@alexanderbez)
-  - [libs/time] \#6495 Move types/time to libs/time to improve consistency. (@tychoish)
-  - [mempool] \#6529 The `Context` field has been removed from the `TxInfo` type. `CheckTx` now requires a `Context` argument. (@alexanderbez)
-  - [abci/client, proxy] \#5673 `Async` funcs return an error, `Sync` and `Async` funcs accept `context.Context` (@melekes)
-  - [p2p] Remove unused function `MakePoWTarget`. (@erikgrinaker)
-  - [libs/bits] \#5720 Validate `BitArray` in `FromProto`, which now returns an error (@melekes)
-  - [proto/p2p] Rename `DefaultNodeInfo` and `DefaultNodeInfoOther` to `NodeInfo` and `NodeInfoOther` (@erikgrinaker)
-  - [proto/p2p] Rename `NodeInfo.default_node_id` to `node_id` (@erikgrinaker)
-  - [libs/os] Kill() and {Must,}{Read,Write}File() functions have been removed. (@alessio)
-  - [store] \#5848 Remove block store state in favor of using the db iterators directly (@cmwaters)
-  - [state] \#5864 Use an iterator when pruning state (@cmwaters)
-  - [types] \#6023 Remove `tm2pb.Header`, `tm2pb.BlockID`, `tm2pb.PartSetHeader` and `tm2pb.NewValidatorUpdate`.
-	- Each of the above types has a `ToProto` and `FromProto` method or function which replaced this logic.
-  - [light] \#6054 Move `MaxRetryAttempt` option from client to provider.
-	- `NewWithOptions` now sets the max retry attempts and timeouts (@cmwaters)
-  - [all] \#6077 Change spelling from British English to American (@cmwaters)
-	- Rename "Subscription.Cancelled()" to "Subscription.Canceled()" in libs/pubsub
-	- Rename "behaviour" pkg to "behavior" and internalized it in blockchain v2
-  - [rpc/client/http] \#6176 Remove `endpoint` arg from `New`, `NewWithTimeout` and `NewWithClient` (@melekes)
-  - [rpc/client/http] \#6176 Unexpose `WSEvents` (@melekes)
-  - [rpc/jsonrpc/client/ws_client] \#6176 `NewWS` no longer accepts options (use `NewWSWithOptions` and `OnReconnect` funcs to configure the client) (@melekes)
-  - [internal/libs] \#6366 Move `autofile`, `clist`,`fail`,`flowrate`, `protoio`, `sync`, `tempfile`, `test` and `timer` lib packages to an internal folder
-  - [libs/rand] \#6364 Remove most of libs/rand in favour of standard lib's `math/rand` (@liamsi)
-  - [mempool] \#6466 The original mempool reactor has been versioned as `v0` and moved to a sub-package under the root `mempool` package.
-	Some core types have been kept in the `mempool` package such as `TxCache` and it's implementations, the `Mempool` interface itself
-	and `TxInfo`. (@alexanderbez)
-  - [crypto/sr25519] \#6526 Do not re-execute the Ed25519-style key derivation step when doing signing and verification.  The derivation is now done once and only once.  This breaks `sr25519.GenPrivKeyFromSecret` output compatibility. (@Yawning)
-  - [types] \#6627 Move `NodeKey` to types to make the type public.
-  - [config] \#6627 Extend `config` to contain methods `LoadNodeKeyID` and `LoadorGenNodeKeyID`
-  - [blocksync] \#6755 Rename `FastSync` and `Blockchain` package to `BlockSync`
-	(@cmwaters)
 
 - Blockchain Protocol
 
-- Data Storage
-  - [store/state/evidence/light] \#5771 Use an order-preserving varint key encoding (@cmwaters)
-  - [mempool] \#6396 Remove mempool's write ahead log (WAL), (previously unused by the tendermint code). (@tychoish)
-  - [state] \#6541 Move pruneBlocks from consensus/state to state/execution. (@JayT106)
-
-- Tooling
-  - [tools] \#6498 Set OS home dir to instead of the hardcoded PATH. (@JayT106)
-  - [cli/indexer] \#6676 Reindex events command line tooling. (@JayT106)
-
 ### FEATURES
 
-- [config] Add `--mode` flag and config variable. See [ADR-52](https://github.com/tendermint/tendermint/blob/master/docs/architecture/adr-052-tendermint-mode.md) @dongsam
-- [rpc] \#6329 Don't cap page size in unsafe mode (@gotjoshua, @cmwaters)
-- [pex] \#6305 v2 pex reactor with backwards compatability. Introduces two new pex messages to
-  accomodate for the new p2p stack. Removes the notion of seeds and crawling. All peer
-  exchange reactors behave the same. (@cmwaters)
-- [crypto] \#6376 Enable sr25519 as a validator key
-- [mempool] \#6466 Introduction of a prioritized mempool. (@alexanderbez)
-  - `Priority` and `Sender` have been introduced into the `ResponseCheckTx` type, where the `priority` will determine the prioritization of
-  the transaction when a proposer reaps transactions for a block proposal. The `sender` field acts as an index.
-  - Operators may toggle between the legacy mempool reactor, `v0`, and the new prioritized reactor, `v1`, by setting the
-  `mempool.version` configuration, where `v1` is the default configuration.
-  - Applications that do not specify a priority, i.e. zero, will have transactions reaped by the order in which they are received by the node.
-  - Transactions are gossiped in FIFO order as they are in `v0`.
-- [config/indexer] \#6411 Introduce support for custom event indexing data sources, specifically PostgreSQL. (@JayT106)
-- [fastsync/event] \#6619 Emit fastsync status event when switching consensus/fastsync (@JayT106)
-- [statesync/event] \#6700 Emit statesync status start/end event (@JayT106)
-
 ### IMPROVEMENTS
 
-- [libs/log] Console log formatting changes as a result of \#6534 and \#6589. (@tychoish)
-- [statesync] \#6566 Allow state sync fetchers and request timeout to be configurable. (@alexanderbez)
-- [types] \#6478 Add `block_id` to `newblock` event (@jeebster)
-- [crypto/ed25519] \#5632 Adopt zip215 `ed25519` verification. (@marbar3778)
-- [crypto/ed25519] \#6526 Use [curve25519-voi](https://github.com/oasisprotocol/curve25519-voi) for `ed25519` signing and verification. (@Yawning)
-- [crypto/sr25519] \#6526 Use [curve25519-voi](https://github.com/oasisprotocol/curve25519-voi) for `sr25519` signing and verification. (@Yawning)
-- [privval] \#5603 Add `--key` to `init`, `gen_validator`, `testnet` & `unsafe_reset_priv_validator` for use in generating `secp256k1` keys.
-- [privval] \#5725 Add gRPC support to private validator.
-- [privval] \#5876 `tendermint show-validator` will query the remote signer if gRPC is being used (@marbar3778)
-- [abci/client] \#5673 `Async` requests return an error if queue is full (@melekes)
-- [mempool] \#5673 Cancel `CheckTx` requests if RPC client disconnects or times out (@melekes)
-- [abci] \#5706 Added `AbciVersion` to `RequestInfo` allowing applications to check ABCI version when connecting to Tendermint. (@marbar3778)
-- [blockchain/v1] \#5728 Remove in favor of v2 (@melekes)
-- [blockchain/v0] \#5741 Relax termination conditions and increase sync timeout (@melekes)
-- [cli] \#5772 `gen_node_key` output now contains node ID (`id` field) (@melekes)
-- [blockchain/v2] \#5774 Send status request when new peer joins (@melekes)
-- [consensus] \#5792 Deprecates the `time_iota_ms` consensus parameter, to reduce the bug surface. The parameter is no longer used. (@valardragon)
-- [store] \#5888 store.SaveBlock saves using batches instead of transactions for now to improve ACID properties. This is a quick fix for underlying issues around tm-db and ACID guarantees. (@githubsands)
-- [consensus] \#5987 Remove `time_iota_ms` from consensus params. Merge `tmproto.ConsensusParams` and `abci.ConsensusParams`. (@marbar3778)
-- [types] \#5994 Reduce the use of protobuf types in core logic. (@marbar3778)
-  - `ConsensusParams`, `BlockParams`, `ValidatorParams`, `EvidenceParams`, `VersionParams`, `sm.Version` and `version.Consensus` have become native types. They still utilize protobuf when being sent over the wire or written to disk.
-- [rpc/client/http] \#6163 Do not drop events even if the `out` channel is full (@melekes)
-- [node] \#6059 Validate and complete genesis doc before saving to state store (@silasdavis)
-- [state] \#6067 Batch save state data (@githubsands & @cmwaters)
-- [crypto] \#6120 Implement batch verification interface for ed25519 and sr25519. (@marbar3778)
-- [types] \#6120 use batch verification for verifying commits signatures.
-  - If the key type supports the batch verification API it will try to batch verify. If the verification fails we will single verify each signature.
-- [privval/file] \#6185 Return error on `LoadFilePV`, `LoadFilePVEmptyState`. Allows for better programmatic control of Tendermint.
-- [privval] \#6240 Add `context.Context` to privval interface.
-- [rpc] \#6265 set cache control in http-rpc response header (@JayT106)
-- [statesync] \#6378 Retry requests for snapshots and add a minimum discovery time (5s) for new snapshots.
-- [node/state] \#6370 graceful shutdown in the consensus reactor (@JayT106)
-- [crypto/merkle] \#6443 Improve HashAlternatives performance (@cuonglm)
-- [crypto/merkle] \#6513 Optimize HashAlternatives (@marbar3778)
-- [p2p/pex] \#6509 Improve addrBook.hash performance (@cuonglm)
-- [consensus/metrics] \#6549 Change block_size gauge to a histogram for better observability over time (@marbar3778)
-- [statesync] \#6587 Increase chunk priority and re-request chunks that don't arrive (@cmwaters)
-- [state/privval] \#6578 No GetPubKey retry beyond the proposal/voting window (@JayT106)
-- [rpc] \#6615 Add TotalGasUsed to block_results response (@crypto-facs)
-- [cmd/tendermint/commands] \#6623 replace `$HOME/.some/test/dir` with `t.TempDir` (@tanyabouman)
-
 ### BUG FIXES
-
-- [privval] \#5638 Increase read/write timeout to 5s and calculate ping interval based on it (@JoeKash)
-- [blockchain/v1] [\#5701](https://github.com/tendermint/tendermint/pull/5701) Handle peers without blocks (@melekes)
-- [blockchain/v1] \#5711 Fix deadlock (@melekes)
-- [evidence] \#6375 Fix bug with inconsistent LightClientAttackEvidence hashing (cmwaters)
-- [rpc] \#6507 Ensure RPC client can handle URLs without ports (@JayT106)
-- [statesync] \#6463 Adds Reverse Sync feature to fetch historical light blocks after state sync in order to verify any evidence (@cmwaters)
-- [fastsync] \#6590 Update the metrics during fast-sync (@JayT106)
-- [gitignore] \#6668 Fix gitignore of abci-cli (@tanyabouman)

CONTRIBUTING.md

@@ -249,6 +249,7 @@ The author of the original pull request is responsible for solving the conflicts
 merging the pull request.
 
 #### Creating a backport branch
+
 If this is the first release candidate for a major release, you get to have the honor of creating
 the backport branch!
 
@@ -328,13 +329,20 @@ If there were no release candidates, begin by creating a backport branch, as des
    - Bump TMVersionDefault version in  `version.go`
    - Bump P2P and block protocol versions in  `version.go`, if necessary
    - Bump ABCI protocol version in `version.go`, if necessary
-   - Add any release notes you would like to be added to the body of the release to `release_notes.md`.
 4. Open a PR with these changes against the backport branch.
 5. Once these changes are on the backport branch, push a tag with prepared release details.
    This will trigger the actual release `v0.35.0`.
    - `git tag -a v0.35.0 -m 'Release v0.35.0'`
    - `git push origin v0.35.0`
 7. Make sure that `master` is updated with the latest `CHANGELOG.md`, `CHANGELOG_PENDING.md`, and `UPGRADING.md`.
+8. Add the release to the documentation site generator config (see
+   [DOCS_README.md](./docs/DOCS_README.md) for more details). In summary:
+   - Start on branch `master`.
+   - Add a new line at the bottom of [`docs/versions`](./docs/versions) to
+     ensure the newest release is the default for the landing page.
+   - Add a new entry to `themeConfig.versions` in
+     [`docs/.vuepress/config.js`](./docs/.vuepress/config.js) to include the
+	 release in the dropdown versions menu.
 
 #### Minor release (point releases)
 
@@ -355,7 +363,6 @@ To create a minor release:
    - Bump the ABCI version number, if necessary.
      (Note that ABCI follows semver, and that ABCI versions are the only versions
      which can change during minor releases, and only field additions are valid minor changes.)
-   - Add any release notes you would like to be added to the body of the release to `release_notes.md`.
 4. Open a PR with these changes that will land them back on `v0.35.x`
 5. Once this change has landed on the backport branch, make sure to pull it locally, then push a tag.
    - `git tag -a v0.35.1 -m 'Release v0.35.1'`

Makefile

@@ -1,6 +1,5 @@
 #!/usr/bin/make -f
 
-PACKAGES=$(shell go list ./...)
 BUILDDIR ?= $(CURDIR)/build
 
 BUILD_TAGS?=tendermint
@@ -15,7 +14,9 @@ endif
 LD_FLAGS = -X github.com/tendermint/tendermint/version.TMVersion=$(VERSION)
 BUILD_FLAGS = -mod=readonly -ldflags "$(LD_FLAGS)"
 HTTPS_GIT := https://github.com/tendermint/tendermint.git
-DOCKER_BUF := docker run -v $(shell pwd):/workspace --workdir /workspace bufbuild/buf
+BUILD_IMAGE := ghcr.io/tendermint/docker-build-proto
+BASE_BRANCH := v0.35.x
+DOCKER_PROTO := docker run -v $(shell pwd):/workspace --workdir /workspace $(BUILD_IMAGE)
 CGO_ENABLED ?= 0
 
 # handle nostrip
@@ -83,26 +84,28 @@ proto-all: proto-gen proto-lint proto-check-breaking
 .PHONY: proto-all
 
 proto-gen:
-	@docker pull -q tendermintdev/docker-build-proto
-	@echo "Generating Protobuf files"
-	@docker run -v $(shell pwd):/workspace --workdir /workspace tendermintdev/docker-build-proto sh ./scripts/protocgen.sh
+	@echo "Generating Go packages for .proto files"
+	@$(DOCKER_PROTO) sh ./scripts/protocgen.sh
 .PHONY: proto-gen
 
 proto-lint:
-	@$(DOCKER_BUF) check lint --error-format=json
+	@echo "Running lint checks for .proto files"
+	@$(DOCKER_PROTO) buf lint --error-format=json
 .PHONY: proto-lint
 
 proto-format:
-	@echo "Formatting Protobuf files"
-	docker run -v $(shell pwd):/workspace --workdir /workspace tendermintdev/docker-build-proto find ./ -not -path "./third_party/*" -name *.proto -exec clang-format -i {} \;
+	@echo "Formatting .proto files"
+	@$(DOCKER_PROTO) find ./ -not -path "./third_party/*" -name '*.proto' -exec clang-format -i {} \;
 .PHONY: proto-format
 
 proto-check-breaking:
-	@$(DOCKER_BUF) check breaking --against-input .git#branch=master
+	@echo "Checking for breaking changes in .proto files"
+	@$(DOCKER_PROTO) buf breaking --against .git#branch=$(BASE_BRANCH)
 .PHONY: proto-check-breaking
 
 proto-check-breaking-ci:
-	@$(DOCKER_BUF) check breaking --against-input $(HTTPS_GIT)#branch=master
+	@echo "Checking for breaking changes in .proto files"
+	@$(DOCKER_PROTO) buf breaking --against $(HTTPS_GIT)#branch=$(BASE_BRANCH)
 .PHONY: proto-check-breaking-ci
 
 ###############################################################################
@@ -118,7 +121,7 @@ install_abci:
 .PHONY: install_abci
 
 ###############################################################################
-###                           	Privval Server                              ###
+###				Privval Server                              ###
 ###############################################################################
 
 build_privval_server:
@@ -131,11 +134,11 @@ generate_test_cert:
 	# generate server cerificate
 	@certstrap request-cert -cn server -ip 127.0.0.1
 	# self-sign server cerificate with rootCA
-	@certstrap sign server --CA "root CA" 
+	@certstrap sign server --CA "root CA"
 	# generate client cerificate
 	@certstrap request-cert -cn client -ip 127.0.0.1
 	# self-sign client cerificate with rootCA
-	@certstrap sign client --CA "root CA" 
+	@certstrap sign client --CA "root CA"
 .PHONY: generate_test_cert
 
 ###############################################################################
@@ -214,7 +217,7 @@ DESTINATION = ./index.html.md
 build-docs:
 	@cd docs && \
 	while read -r branch path_prefix; do \
-		(git checkout $${branch} && npm install && VUEPRESS_BASE="/$${path_prefix}/" npm run build) ; \
+		(git checkout $${branch} && npm ci && VUEPRESS_BASE="/$${path_prefix}/" npm run build) ; \
 		mkdir -p ~/output/$${path_prefix} ; \
 		cp -r .vuepress/dist/* ~/output/$${path_prefix}/ ; \
 		cp ~/output/$${path_prefix}/index.html ~/output ; \
@@ -227,13 +230,13 @@ build-docs:
 
 build-docker: build-linux
 	cp $(BUILDDIR)/tendermint DOCKER/tendermint
-	docker build --label=tendermint --tag="tendermint/tendermint" DOCKER
+	docker build --label=tendermint --tag="tendermint/tendermint" -f DOCKER/Dockerfile .
 	rm -rf DOCKER/tendermint
 .PHONY: build-docker
 
 
 ###############################################################################
-###                       Mocks 											###
+###                                Mocks                                    ###
 ###############################################################################
 
 mockery:
@@ -303,3 +306,25 @@ build-reproducible:
 		--name latest-build cosmossdk/rbuilder:latest
 	docker cp -a latest-build:/home/builder/artifacts/ $(CURDIR)/
 .PHONY: build-reproducible
+
+# Implements test splitting and running. This is pulled directly from
+# the github action workflows for better local reproducibility.
+
+GO_TEST_FILES != find $(CURDIR) -name "*_test.go"
+
+# default to four splits by default
+NUM_SPLIT ?= 4
+
+$(BUILDDIR):
+	mkdir -p $@
+
+# The format statement filters out all packages that don't have tests.
+# Note we need to check for both in-package tests (.TestGoFiles) and
+# out-of-package tests (.XTestGoFiles).
+$(BUILDDIR)/packages.txt:$(GO_TEST_FILES) $(BUILDDIR)
+	go list -f "{{ if (or .TestGoFiles .XTestGoFiles) }}{{ .ImportPath }}{{ end }}" ./... | sort > $@
+
+split-test-packages:$(BUILDDIR)/packages.txt
+	split -d -n l/$(NUM_SPLIT) $< $<.
+test-group-%:split-test-packages
+	cat $(BUILDDIR)/packages.txt.$* | xargs go test -mod=readonly -timeout=15m -race -coverprofile=$(BUILDDIR)/$*.profile.out

README.md

@@ -9,7 +9,7 @@ Or [Blockchain](<https://en.wikipedia.org/wiki/Blockchain_(database)>), for shor
 [![version](https://img.shields.io/github/tag/tendermint/tendermint.svg)](https://github.com/tendermint/tendermint/releases/latest)
 [![API Reference](https://camo.githubusercontent.com/915b7be44ada53c290eb157634330494ebe3e30a/68747470733a2f2f676f646f632e6f72672f6769746875622e636f6d2f676f6c616e672f6764646f3f7374617475732e737667)](https://pkg.go.dev/github.com/tendermint/tendermint)
 [![Go version](https://img.shields.io/badge/go-1.16-blue.svg)](https://github.com/moovweb/gvm)
-[![Discord chat](https://img.shields.io/discord/669268347736686612.svg)](https://discord.gg/vcExX9T)
+[![Discord chat](https://img.shields.io/discord/669268347736686612.svg)](https://discord.gg/cosmosnetwork)
 [![license](https://img.shields.io/github/license/tendermint/tendermint.svg)](https://github.com/tendermint/tendermint/blob/master/LICENSE)
 [![tendermint/tendermint](https://tokei.rs/b1/github/tendermint/tendermint?category=lines)](https://github.com/tendermint/tendermint)
 [![Sourcegraph](https://sourcegraph.com/github.com/tendermint/tendermint/-/badge.svg)](https://sourcegraph.com/github.com/tendermint/tendermint?badge)
@@ -29,16 +29,15 @@ see our recent paper, "[The latest gossip on BFT consensus](https://arxiv.org/ab
 
 Please do not depend on master as your production branch. Use [releases](https://github.com/tendermint/tendermint/releases) instead.
 
-Tendermint has been in the production of private and public environments, most notably the blockchains of the Cosmos Network. we haven't released v1.0 yet since we are making breaking changes to the protocol and the APIs. 
+Tendermint has been in the production of private and public environments, most notably the blockchains of the Cosmos Network. we haven't released v1.0 yet since we are making breaking changes to the protocol and the APIs.
 See below for more details about [versioning](#versioning).
 
 In any case, if you intend to run Tendermint in production, we're happy to help. You can
-contact us [over email](mailto:hello@interchain.berlin) or [join the chat](https://discord.gg/vcExX9T).
+contact us [over email](mailto:hello@interchain.berlin) or [join the chat](https://discord.gg/cosmosnetwork).
 
 ## Security
 
-To report a security vulnerability, see our [bug bounty
-program](https://hackerone.com/tendermint). 
+To report a security vulnerability, see our [bug bounty program](https://hackerone.com/cosmos).
 For examples of the kinds of bugs we're looking for, see [our security policy](SECURITY.md).
 
 We also maintain a dedicated mailing list for security updates. We will only ever use this mailing list
@@ -61,8 +60,8 @@ See the [install instructions](/docs/introduction/install.md).
 ### Quick Start
 
 - [Single node](/docs/introduction/quick-start.md)
-- [Local cluster using docker-compose](/docs/networks/docker-compose.md)
-- [Remote cluster using Terraform and Ansible](/docs/networks/terraform-and-ansible.md)
+- [Local cluster using docker-compose](/docs/tools/docker-compose.md)
+- [Remote cluster using Terraform and Ansible](/docs/tools/terraform-and-ansible.md)
 - [Join the Cosmos testnet](https://cosmos.network/testnet)
 
 ## Contributing
@@ -71,7 +70,7 @@ Please abide by the [Code of Conduct](CODE_OF_CONDUCT.md) in all interactions.
 
 Before contributing to the project, please take a look at the [contributing guidelines](CONTRIBUTING.md)
 and the [style guide](STYLE_GUIDE.md). You may also find it helpful to read the
-[specifications](https://github.com/tendermint/spec), watch the [Developer Sessions](/docs/DEV_SESSIONS.md), 
+[specifications](https://github.com/tendermint/spec), watch the [Developer Sessions](/docs/DEV_SESSIONS.md),
 and familiarize yourself with our
 [Architectural Decision Records](https://github.com/tendermint/tendermint/tree/master/docs/architecture).
 
@@ -82,32 +81,12 @@ and familiarize yourself with our
 Tendermint uses [Semantic Versioning](http://semver.org/) to determine when and how the version changes.
 According to SemVer, anything in the public API can change at any time before version 1.0.0
 
-To provide some stability to Tendermint users in these 0.X.X days, the MINOR version is used
-to signal breaking changes across a subset of the total public API. This subset includes all
-interfaces exposed to other processes (cli, rpc, p2p, etc.), but does not
-include the Go APIs.
+To provide some stability to users of 0.X.X versions of Tendermint, the MINOR version is used
+to signal breaking changes across Tendermint's API. This API includes all
+publicly exposed types, functions, and methods in non-internal Go packages as well as
+the types and methods accessible via the Tendermint RPC interface.
 
-That said, breaking changes in the following packages will be documented in the
-CHANGELOG even if they don't lead to MINOR version bumps:
-
-- crypto
-- config
-- libs
-    - bits
-    - bytes
-    - json
-    - log
-    - math
-    - net
-    - os
-    - protoio
-    - rand
-    - sync
-    - strings
-    - service
-- node
-- rpc/client
-- types
+Breaking changes to these public APIs will be documented in the CHANGELOG.
 
 ### Upgrades
 
@@ -115,7 +94,7 @@ In an effort to avoid accumulating technical debt prior to 1.0.0,
 we do not guarantee that breaking changes (ie. bumps in the MINOR version)
 will work with existing Tendermint blockchains. In these cases you will
 have to start a new blockchain, or write something custom to get the old
-data into the new chain. However, any bump in the PATCH version should be 
+data into the new chain. However, any bump in the PATCH version should be
 compatible with existing blockchain histories.
 
 

UPGRADING.md

@@ -2,7 +2,7 @@
 
 This guide provides instructions for upgrading to specific versions of Tendermint Core.
 
-## Unreleased
+## v0.35
 
 ### ABCI Changes
 
@@ -17,7 +17,16 @@ This guide provides instructions for upgrading to specific versions of Tendermin
 
 ### Config Changes
 
-* `fast_sync = "v1"` and `fast_sync = "v2"` are no longer supported. Please use `v0` instead.
+* The configuration file field `[fastsync]` has been renamed to `[blocksync]`.
+
+* The top level configuration file field `fast-sync` has moved under the new `[blocksync]`
+  field as `blocksync.enable`.
+
+* `blocksync.version = "v1"` and `blocksync.version = "v2"` (previously `fastsync`)
+  are no longer supported. Please use `v0` instead. During the v0.35 release cycle, `v0` was
+  determined to suit the existing needs and the cost of maintaining the `v1` and `v2` modules
+  was determined to be greater than necessary.
+
 
 * All config parameters are now hyphen-case (also known as kebab-case) instead of snake_case. Before restarting the node make sure
   you have updated all the variables in your `config.toml` file.
@@ -35,7 +44,7 @@ This guide provides instructions for upgrading to specific versions of Tendermin
 * The fast sync process as well as the blockchain package and service has all
   been renamed to block sync
 
-### Key Format Changes
+### Database Key Format Changes
 
 The format of all tendermint on-disk database keys changes in
 0.35. Upgrading nodes must either re-sync all data or run a migration
@@ -60,6 +69,8 @@ if needed.
 
 * You must now specify the node mode (validator|full|seed) in `tendermint init [mode]`
 
+* The `--fast-sync` command line option has been renamed to `--blocksync.enable`
+
 * If you had previously used `tendermint gen_node_key` to generate a new node
   key, keep in mind that it no longer saves the output to a file. You can use
   `tendermint init validator` or pipe the output of `tendermint gen_node_key` to
@@ -74,8 +85,8 @@ if needed.
 
 ### API Changes
 
-The p2p layer was reimplemented as part of the 0.35 release cycle, and
-all reactors were refactored. As part of that work these
+The p2p layer was reimplemented as part of the 0.35 release cycle and
+all reactors were refactored to accomodate the change. As part of that work these
 implementations moved into the `internal` package and are no longer
 considered part of the public Go API of tendermint. These packages
 are:
@@ -87,7 +98,7 @@ are:
 - `blockchain`
 - `evidence`
 
-Accordingly, the `node` package was changed to reduce access to
+Accordingly, the `node` package changed to reduce access to
 tendermint internals: applications that use tendermint as a library
 will need to change to accommodate these changes. Most notably:
 
@@ -98,13 +109,25 @@ will need to change to accommodate these changes. Most notably:
   longer exported and have been replaced with `node.New` and
   `node.NewDefault` which provide more functional interfaces.
 
-### RPC changes
+To access any of the functionality previously available via the
+`node.Node` type, use the `*local.Local` "RPC" client, that exposes
+the full RPC interface provided as direct function calls. Import the
+`github.com/tendermint/tendermint/rpc/client/local` package and pass
+the node service as in the following: 
 
-#### gRPC Support
+```go
+    node := node.NewDefault() //construct the node object
+    // start and set up the node service 
+
+    client := local.New(node.(local.NodeService))
+    // use client object to interact with the node
+```
+
+### gRPC Support
 
 Mark gRPC in the RPC layer as deprecated and to be removed in 0.36.
 
-#### Peer Management Interface
+### Peer Management Interface
 
 When running with the new P2P Layer, the methods `UnsafeDialSeeds` and
 `UnsafeDialPeers` RPC methods will always return an error. They are
@@ -116,6 +139,58 @@ method changes in this release to accommodate the different way that
 the new stack tracks data about peers. This change affects users of
 both stacks.
 
+### Using the updated p2p library
+
+The P2P library was reimplemented in this release. The new implementation is
+enabled by default in this version of Tendermint. The legacy implementation is still
+included in this version of Tendermint as a backstop to work around unforeseen
+production issues. The new and legacy version are interoperable. If necessary, 
+you can enable the legacy implementation in the server configuration file.
+
+To make use of the legacy P2P implemementation add or update the following field of 
+your server's configuration file under the `[p2p]` section:
+
+```toml
+[p2p]
+...
+use-legacy = true
+...
+```
+
+If you need to do this, please consider filing an issue in the Tendermint repository
+to let us know why. We plan to remove the legacy P2P code in the next (v0.36) release.
+
+#### New p2p queue types
+
+The new p2p implementation enables selection of the queue type to be used for
+passing messages between peers.
+
+The following values may be used when selecting which queue type to use:
+
+* `fifo`: (**default**) An unbuffered and lossless queue that passes messages through
+in the order in which they were received.
+
+* `priority`: A priority queue of messages.
+
+* `wdrr`: A queue implementing the Weighted Deficit Round Robin algorithm. A 
+weighted deficit round robin queue is created per peer. Each queue contains a 
+separate 'flow' for each of the channels of communication that exist between any two
+peers. Tendermint maintains a channel per message type between peers. Each WDRR
+queue maintains a shared buffered with a fixed capacity through which messages on different
+flows are passed.
+For more information on WDRR scheduling, see: https://en.wikipedia.org/wiki/Deficit_round_robin
+
+To select a queue type, add or update the following field under the `[p2p]`
+section of your server's configuration file.
+
+```toml
+[p2p]
+...
+queue-type = wdrr
+...
+```
+
+
 ### Support for Custom Reactor and Mempool Implementations
 
 The changes to p2p layer removed existing support for custom

abci/client/client.go

@@ -1,4 +1,4 @@
-package abcicli
+package abciclient
 
 import (
 	"context"
@@ -87,7 +87,7 @@ type ReqRes struct {
 	*sync.WaitGroup
 	*types.Response // Not set atomically, so be sure to use WaitGroup.
 
-	mtx  tmsync.RWMutex
+	mtx  tmsync.Mutex
 	done bool                  // Gets set to true once *after* WaitGroup.Done().
 	cb   func(*types.Response) // A single callback that may be set.
 }
@@ -137,16 +137,16 @@ func (r *ReqRes) InvokeCallback() {
 //
 // ref: https://github.com/tendermint/tendermint/issues/5439
 func (r *ReqRes) GetCallback() func(*types.Response) {
-	r.mtx.RLock()
-	defer r.mtx.RUnlock()
+	r.mtx.Lock()
+	defer r.mtx.Unlock()
 	return r.cb
 }
 
 // SetDone marks the ReqRes object as done.
 func (r *ReqRes) SetDone() {
 	r.mtx.Lock()
-	defer r.mtx.Unlock()
 	r.done = true
+	r.mtx.Unlock()
 }
 
 func waitGroup1() (wg *sync.WaitGroup) {

abci/client/creators.go

@@ -0,0 +1,35 @@
+package abciclient
+
+import (
+	"fmt"
+
+	"github.com/tendermint/tendermint/abci/types"
+	tmsync "github.com/tendermint/tendermint/internal/libs/sync"
+)
+
+// Creator creates new ABCI clients.
+type Creator func() (Client, error)
+
+// NewLocalCreator returns a Creator for the given app,
+// which will be running locally.
+func NewLocalCreator(app types.Application) Creator {
+	mtx := new(tmsync.Mutex)
+
+	return func() (Client, error) {
+		return NewLocalClient(mtx, app), nil
+	}
+}
+
+// NewRemoteCreator returns a Creator for the given address (e.g.
+// "192.168.0.1") and transport (e.g. "tcp"). Set mustConnect to true if you
+// want the client to connect before reporting success.
+func NewRemoteCreator(addr, transport string, mustConnect bool) Creator {
+	return func() (Client, error) {
+		remoteApp, err := NewClient(addr, transport, mustConnect)
+		if err != nil {
+			return nil, fmt.Errorf("failed to connect to proxy: %w", err)
+		}
+
+		return remoteApp, nil
+	}
+}

abci/client/doc.go

@@ -1,4 +1,4 @@
-// Package abcicli provides an ABCI implementation in Go.
+// Package abciclient provides an ABCI implementation in Go.
 //
 // There are 3 clients available:
 //		1. socket (unix or TCP)
@@ -26,4 +26,4 @@
 //
 // sync: waits for all Async calls to complete (essentially what Flush does in
 // the socket client) and calls Sync method.
-package abcicli
+package abciclient

abci/client/grpc_client.go

@@ -1,4 +1,4 @@
-package abcicli
+package abciclient
 
 import (
 	"context"
@@ -8,6 +8,7 @@ import (
 	"time"
 
 	"google.golang.org/grpc"
+	"google.golang.org/grpc/credentials/insecure"
 
 	"github.com/tendermint/tendermint/abci/types"
 	tmsync "github.com/tendermint/tendermint/internal/libs/sync"
@@ -24,7 +25,7 @@ type grpcClient struct {
 	conn     *grpc.ClientConn
 	chReqRes chan *ReqRes // dispatches "async" responses to callbacks *in order*, needed by mempool
 
-	mtx   tmsync.RWMutex
+	mtx   tmsync.Mutex
 	addr  string
 	err   error
 	resCb func(*types.Request, *types.Response) // listens to all callbacks
@@ -95,7 +96,10 @@ func (cli *grpcClient) OnStart() error {
 
 RETRY_LOOP:
 	for {
-		conn, err := grpc.Dial(cli.addr, grpc.WithInsecure(), grpc.WithContextDialer(dialerFunc))
+		conn, err := grpc.Dial(cli.addr,
+			grpc.WithTransportCredentials(insecure.NewCredentials()),
+			grpc.WithContextDialer(dialerFunc),
+		)
 		if err != nil {
 			if cli.mustConnect {
 				return err
@@ -149,8 +153,8 @@ func (cli *grpcClient) StopForError(err error) {
 }
 
 func (cli *grpcClient) Error() error {
-	cli.mtx.RLock()
-	defer cli.mtx.RUnlock()
+	cli.mtx.Lock()
+	defer cli.mtx.Unlock()
 	return cli.err
 }
 
@@ -158,8 +162,8 @@ func (cli *grpcClient) Error() error {
 // NOTE: callback may get internally generated flush responses.
 func (cli *grpcClient) SetResponseCallback(resCb Callback) {
 	cli.mtx.Lock()
-	defer cli.mtx.Unlock()
 	cli.resCb = resCb
+	cli.mtx.Unlock()
 }
 
 //----------------------------------------

abci/client/local_client.go

@@ -1,4 +1,4 @@
-package abcicli
+package abciclient
 
 import (
 	"context"
@@ -15,7 +15,7 @@ import (
 type localClient struct {
 	service.BaseService
 
-	mtx *tmsync.RWMutex
+	mtx *tmsync.Mutex
 	types.Application
 	Callback
 }
@@ -26,24 +26,22 @@ var _ Client = (*localClient)(nil)
 // methods of the given app.
 //
 // Both Async and Sync methods ignore the given context.Context parameter.
-func NewLocalClient(mtx *tmsync.RWMutex, app types.Application) Client {
+func NewLocalClient(mtx *tmsync.Mutex, app types.Application) Client {
 	if mtx == nil {
-		mtx = &tmsync.RWMutex{}
+		mtx = new(tmsync.Mutex)
 	}
-
 	cli := &localClient{
 		mtx:         mtx,
 		Application: app,
 	}
-
 	cli.BaseService = *service.NewBaseService(nil, "localClient", cli)
 	return cli
 }
 
 func (app *localClient) SetResponseCallback(cb Callback) {
 	app.mtx.Lock()
-	defer app.mtx.Unlock()
 	app.Callback = cb
+	app.mtx.Unlock()
 }
 
 // TODO: change types.Application to include Error()?
@@ -67,8 +65,8 @@ func (app *localClient) EchoAsync(ctx context.Context, msg string) (*ReqRes, err
 }
 
 func (app *localClient) InfoAsync(ctx context.Context, req types.RequestInfo) (*ReqRes, error) {
-	app.mtx.RLock()
-	defer app.mtx.RUnlock()
+	app.mtx.Lock()
+	defer app.mtx.Unlock()
 
 	res := app.Application.Info(req)
 	return app.callback(
@@ -100,8 +98,8 @@ func (app *localClient) CheckTxAsync(ctx context.Context, req types.RequestCheck
 }
 
 func (app *localClient) QueryAsync(ctx context.Context, req types.RequestQuery) (*ReqRes, error) {
-	app.mtx.RLock()
-	defer app.mtx.RUnlock()
+	app.mtx.Lock()
+	defer app.mtx.Unlock()
 
 	res := app.Application.Query(req)
 	return app.callback(
@@ -215,8 +213,8 @@ func (app *localClient) EchoSync(ctx context.Context, msg string) (*types.Respon
 }
 
 func (app *localClient) InfoSync(ctx context.Context, req types.RequestInfo) (*types.ResponseInfo, error) {
-	app.mtx.RLock()
-	defer app.mtx.RUnlock()
+	app.mtx.Lock()
+	defer app.mtx.Unlock()
 
 	res := app.Application.Info(req)
 	return &res, nil
@@ -249,8 +247,8 @@ func (app *localClient) QuerySync(
 	ctx context.Context,
 	req types.RequestQuery,
 ) (*types.ResponseQuery, error) {
-	app.mtx.RLock()
-	defer app.mtx.RUnlock()
+	app.mtx.Lock()
+	defer app.mtx.Unlock()
 
 	res := app.Application.Query(req)
 	return &res, nil

abci/client/mocks/client.go

@@ -5,7 +5,7 @@ package mocks
 import (
 	context "context"
 
-	abcicli "github.com/tendermint/tendermint/abci/client"
+	abciclient "github.com/tendermint/tendermint/abci/client"
 
 	log "github.com/tendermint/tendermint/libs/log"
 
@@ -20,15 +20,15 @@ type Client struct {
 }
 
 // ApplySnapshotChunkAsync provides a mock function with given fields: _a0, _a1
-func (_m *Client) ApplySnapshotChunkAsync(_a0 context.Context, _a1 types.RequestApplySnapshotChunk) (*abcicli.ReqRes, error) {
+func (_m *Client) ApplySnapshotChunkAsync(_a0 context.Context, _a1 types.RequestApplySnapshotChunk) (*abciclient.ReqRes, error) {
 	ret := _m.Called(_a0, _a1)
 
-	var r0 *abcicli.ReqRes
-	if rf, ok := ret.Get(0).(func(context.Context, types.RequestApplySnapshotChunk) *abcicli.ReqRes); ok {
+	var r0 *abciclient.ReqRes
+	if rf, ok := ret.Get(0).(func(context.Context, types.RequestApplySnapshotChunk) *abciclient.ReqRes); ok {
 		r0 = rf(_a0, _a1)
 	} else {
 		if ret.Get(0) != nil {
-			r0 = ret.Get(0).(*abcicli.ReqRes)
+			r0 = ret.Get(0).(*abciclient.ReqRes)
 		}
 	}
 
@@ -66,15 +66,15 @@ func (_m *Client) ApplySnapshotChunkSync(_a0 context.Context, _a1 types.RequestA
 }
 
 // BeginBlockAsync provides a mock function with given fields: _a0, _a1
-func (_m *Client) BeginBlockAsync(_a0 context.Context, _a1 types.RequestBeginBlock) (*abcicli.ReqRes, error) {
+func (_m *Client) BeginBlockAsync(_a0 context.Context, _a1 types.RequestBeginBlock) (*abciclient.ReqRes, error) {
 	ret := _m.Called(_a0, _a1)
 
-	var r0 *abcicli.ReqRes
-	if rf, ok := ret.Get(0).(func(context.Context, types.RequestBeginBlock) *abcicli.ReqRes); ok {
+	var r0 *abciclient.ReqRes
+	if rf, ok := ret.Get(0).(func(context.Context, types.RequestBeginBlock) *abciclient.ReqRes); ok {
 		r0 = rf(_a0, _a1)
 	} else {
 		if ret.Get(0) != nil {
-			r0 = ret.Get(0).(*abcicli.ReqRes)
+			r0 = ret.Get(0).(*abciclient.ReqRes)
 		}
 	}
 
@@ -112,15 +112,15 @@ func (_m *Client) BeginBlockSync(_a0 context.Context, _a1 types.RequestBeginBloc
 }
 
 // CheckTxAsync provides a mock function with given fields: _a0, _a1
-func (_m *Client) CheckTxAsync(_a0 context.Context, _a1 types.RequestCheckTx) (*abcicli.ReqRes, error) {
+func (_m *Client) CheckTxAsync(_a0 context.Context, _a1 types.RequestCheckTx) (*abciclient.ReqRes, error) {
 	ret := _m.Called(_a0, _a1)
 
-	var r0 *abcicli.ReqRes
-	if rf, ok := ret.Get(0).(func(context.Context, types.RequestCheckTx) *abcicli.ReqRes); ok {
+	var r0 *abciclient.ReqRes
+	if rf, ok := ret.Get(0).(func(context.Context, types.RequestCheckTx) *abciclient.ReqRes); ok {
 		r0 = rf(_a0, _a1)
 	} else {
 		if ret.Get(0) != nil {
-			r0 = ret.Get(0).(*abcicli.ReqRes)
+			r0 = ret.Get(0).(*abciclient.ReqRes)
 		}
 	}
 
@@ -158,15 +158,15 @@ func (_m *Client) CheckTxSync(_a0 context.Context, _a1 types.RequestCheckTx) (*t
 }
 
 // CommitAsync provides a mock function with given fields: _a0
-func (_m *Client) CommitAsync(_a0 context.Context) (*abcicli.ReqRes, error) {
+func (_m *Client) CommitAsync(_a0 context.Context) (*abciclient.ReqRes, error) {
 	ret := _m.Called(_a0)
 
-	var r0 *abcicli.ReqRes
-	if rf, ok := ret.Get(0).(func(context.Context) *abcicli.ReqRes); ok {
+	var r0 *abciclient.ReqRes
+	if rf, ok := ret.Get(0).(func(context.Context) *abciclient.ReqRes); ok {
 		r0 = rf(_a0)
 	} else {
 		if ret.Get(0) != nil {
-			r0 = ret.Get(0).(*abcicli.ReqRes)
+			r0 = ret.Get(0).(*abciclient.ReqRes)
 		}
 	}
 
@@ -204,15 +204,15 @@ func (_m *Client) CommitSync(_a0 context.Context) (*types.ResponseCommit, error)
 }
 
 // DeliverTxAsync provides a mock function with given fields: _a0, _a1
-func (_m *Client) DeliverTxAsync(_a0 context.Context, _a1 types.RequestDeliverTx) (*abcicli.ReqRes, error) {
+func (_m *Client) DeliverTxAsync(_a0 context.Context, _a1 types.RequestDeliverTx) (*abciclient.ReqRes, error) {
 	ret := _m.Called(_a0, _a1)
 
-	var r0 *abcicli.ReqRes
-	if rf, ok := ret.Get(0).(func(context.Context, types.RequestDeliverTx) *abcicli.ReqRes); ok {
+	var r0 *abciclient.ReqRes
+	if rf, ok := ret.Get(0).(func(context.Context, types.RequestDeliverTx) *abciclient.ReqRes); ok {
 		r0 = rf(_a0, _a1)
 	} else {
 		if ret.Get(0) != nil {
-			r0 = ret.Get(0).(*abcicli.ReqRes)
+			r0 = ret.Get(0).(*abciclient.ReqRes)
 		}
 	}
 
@@ -250,15 +250,15 @@ func (_m *Client) DeliverTxSync(_a0 context.Context, _a1 types.RequestDeliverTx)
 }
 
 // EchoAsync provides a mock function with given fields: ctx, msg
-func (_m *Client) EchoAsync(ctx context.Context, msg string) (*abcicli.ReqRes, error) {
+func (_m *Client) EchoAsync(ctx context.Context, msg string) (*abciclient.ReqRes, error) {
 	ret := _m.Called(ctx, msg)
 
-	var r0 *abcicli.ReqRes
-	if rf, ok := ret.Get(0).(func(context.Context, string) *abcicli.ReqRes); ok {
+	var r0 *abciclient.ReqRes
+	if rf, ok := ret.Get(0).(func(context.Context, string) *abciclient.ReqRes); ok {
 		r0 = rf(ctx, msg)
 	} else {
 		if ret.Get(0) != nil {
-			r0 = ret.Get(0).(*abcicli.ReqRes)
+			r0 = ret.Get(0).(*abciclient.ReqRes)
 		}
 	}
 
@@ -296,15 +296,15 @@ func (_m *Client) EchoSync(ctx context.Context, msg string) (*types.ResponseEcho
 }
 
 // EndBlockAsync provides a mock function with given fields: _a0, _a1
-func (_m *Client) EndBlockAsync(_a0 context.Context, _a1 types.RequestEndBlock) (*abcicli.ReqRes, error) {
+func (_m *Client) EndBlockAsync(_a0 context.Context, _a1 types.RequestEndBlock) (*abciclient.ReqRes, error) {
 	ret := _m.Called(_a0, _a1)
 
-	var r0 *abcicli.ReqRes
-	if rf, ok := ret.Get(0).(func(context.Context, types.RequestEndBlock) *abcicli.ReqRes); ok {
+	var r0 *abciclient.ReqRes
+	if rf, ok := ret.Get(0).(func(context.Context, types.RequestEndBlock) *abciclient.ReqRes); ok {
 		r0 = rf(_a0, _a1)
 	} else {
 		if ret.Get(0) != nil {
-			r0 = ret.Get(0).(*abcicli.ReqRes)
+			r0 = ret.Get(0).(*abciclient.ReqRes)
 		}
 	}
 
@@ -356,15 +356,15 @@ func (_m *Client) Error() error {
 }
 
 // FlushAsync provides a mock function with given fields: _a0
-func (_m *Client) FlushAsync(_a0 context.Context) (*abcicli.ReqRes, error) {
+func (_m *Client) FlushAsync(_a0 context.Context) (*abciclient.ReqRes, error) {
 	ret := _m.Called(_a0)
 
-	var r0 *abcicli.ReqRes
-	if rf, ok := ret.Get(0).(func(context.Context) *abcicli.ReqRes); ok {
+	var r0 *abciclient.ReqRes
+	if rf, ok := ret.Get(0).(func(context.Context) *abciclient.ReqRes); ok {
 		r0 = rf(_a0)
 	} else {
 		if ret.Get(0) != nil {
-			r0 = ret.Get(0).(*abcicli.ReqRes)
+			r0 = ret.Get(0).(*abciclient.ReqRes)
 		}
 	}
 
@@ -393,15 +393,15 @@ func (_m *Client) FlushSync(_a0 context.Context) error {
 }
 
 // InfoAsync provides a mock function with given fields: _a0, _a1
-func (_m *Client) InfoAsync(_a0 context.Context, _a1 types.RequestInfo) (*abcicli.ReqRes, error) {
+func (_m *Client) InfoAsync(_a0 context.Context, _a1 types.RequestInfo) (*abciclient.ReqRes, error) {
 	ret := _m.Called(_a0, _a1)
 
-	var r0 *abcicli.ReqRes
-	if rf, ok := ret.Get(0).(func(context.Context, types.RequestInfo) *abcicli.ReqRes); ok {
+	var r0 *abciclient.ReqRes
+	if rf, ok := ret.Get(0).(func(context.Context, types.RequestInfo) *abciclient.ReqRes); ok {
 		r0 = rf(_a0, _a1)
 	} else {
 		if ret.Get(0) != nil {
-			r0 = ret.Get(0).(*abcicli.ReqRes)
+			r0 = ret.Get(0).(*abciclient.ReqRes)
 		}
 	}
 
@@ -439,15 +439,15 @@ func (_m *Client) InfoSync(_a0 context.Context, _a1 types.RequestInfo) (*types.R
 }
 
 // InitChainAsync provides a mock function with given fields: _a0, _a1
-func (_m *Client) InitChainAsync(_a0 context.Context, _a1 types.RequestInitChain) (*abcicli.ReqRes, error) {
+func (_m *Client) InitChainAsync(_a0 context.Context, _a1 types.RequestInitChain) (*abciclient.ReqRes, error) {
 	ret := _m.Called(_a0, _a1)
 
-	var r0 *abcicli.ReqRes
-	if rf, ok := ret.Get(0).(func(context.Context, types.RequestInitChain) *abcicli.ReqRes); ok {
+	var r0 *abciclient.ReqRes
+	if rf, ok := ret.Get(0).(func(context.Context, types.RequestInitChain) *abciclient.ReqRes); ok {
 		r0 = rf(_a0, _a1)
 	} else {
 		if ret.Get(0) != nil {
-			r0 = ret.Get(0).(*abcicli.ReqRes)
+			r0 = ret.Get(0).(*abciclient.ReqRes)
 		}
 	}
 
@@ -499,15 +499,15 @@ func (_m *Client) IsRunning() bool {
 }
 
 // ListSnapshotsAsync provides a mock function with given fields: _a0, _a1
-func (_m *Client) ListSnapshotsAsync(_a0 context.Context, _a1 types.RequestListSnapshots) (*abcicli.ReqRes, error) {
+func (_m *Client) ListSnapshotsAsync(_a0 context.Context, _a1 types.RequestListSnapshots) (*abciclient.ReqRes, error) {
 	ret := _m.Called(_a0, _a1)
 
-	var r0 *abcicli.ReqRes
-	if rf, ok := ret.Get(0).(func(context.Context, types.RequestListSnapshots) *abcicli.ReqRes); ok {
+	var r0 *abciclient.ReqRes
+	if rf, ok := ret.Get(0).(func(context.Context, types.RequestListSnapshots) *abciclient.ReqRes); ok {
 		r0 = rf(_a0, _a1)
 	} else {
 		if ret.Get(0) != nil {
-			r0 = ret.Get(0).(*abcicli.ReqRes)
+			r0 = ret.Get(0).(*abciclient.ReqRes)
 		}
 	}
 
@@ -545,15 +545,15 @@ func (_m *Client) ListSnapshotsSync(_a0 context.Context, _a1 types.RequestListSn
 }
 
 // LoadSnapshotChunkAsync provides a mock function with given fields: _a0, _a1
-func (_m *Client) LoadSnapshotChunkAsync(_a0 context.Context, _a1 types.RequestLoadSnapshotChunk) (*abcicli.ReqRes, error) {
+func (_m *Client) LoadSnapshotChunkAsync(_a0 context.Context, _a1 types.RequestLoadSnapshotChunk) (*abciclient.ReqRes, error) {
 	ret := _m.Called(_a0, _a1)
 
-	var r0 *abcicli.ReqRes
-	if rf, ok := ret.Get(0).(func(context.Context, types.RequestLoadSnapshotChunk) *abcicli.ReqRes); ok {
+	var r0 *abciclient.ReqRes
+	if rf, ok := ret.Get(0).(func(context.Context, types.RequestLoadSnapshotChunk) *abciclient.ReqRes); ok {
 		r0 = rf(_a0, _a1)
 	} else {
 		if ret.Get(0) != nil {
-			r0 = ret.Get(0).(*abcicli.ReqRes)
+			r0 = ret.Get(0).(*abciclient.ReqRes)
 		}
 	}
 
@@ -591,15 +591,15 @@ func (_m *Client) LoadSnapshotChunkSync(_a0 context.Context, _a1 types.RequestLo
 }
 
 // OfferSnapshotAsync provides a mock function with given fields: _a0, _a1
-func (_m *Client) OfferSnapshotAsync(_a0 context.Context, _a1 types.RequestOfferSnapshot) (*abcicli.ReqRes, error) {
+func (_m *Client) OfferSnapshotAsync(_a0 context.Context, _a1 types.RequestOfferSnapshot) (*abciclient.ReqRes, error) {
 	ret := _m.Called(_a0, _a1)
 
-	var r0 *abcicli.ReqRes
-	if rf, ok := ret.Get(0).(func(context.Context, types.RequestOfferSnapshot) *abcicli.ReqRes); ok {
+	var r0 *abciclient.ReqRes
+	if rf, ok := ret.Get(0).(func(context.Context, types.RequestOfferSnapshot) *abciclient.ReqRes); ok {
 		r0 = rf(_a0, _a1)
 	} else {
 		if ret.Get(0) != nil {
-			r0 = ret.Get(0).(*abcicli.ReqRes)
+			r0 = ret.Get(0).(*abciclient.ReqRes)
 		}
 	}
 
@@ -670,15 +670,15 @@ func (_m *Client) OnStop() {
 }
 
 // QueryAsync provides a mock function with given fields: _a0, _a1
-func (_m *Client) QueryAsync(_a0 context.Context, _a1 types.RequestQuery) (*abcicli.ReqRes, error) {
+func (_m *Client) QueryAsync(_a0 context.Context, _a1 types.RequestQuery) (*abciclient.ReqRes, error) {
 	ret := _m.Called(_a0, _a1)
 
-	var r0 *abcicli.ReqRes
-	if rf, ok := ret.Get(0).(func(context.Context, types.RequestQuery) *abcicli.ReqRes); ok {
+	var r0 *abciclient.ReqRes
+	if rf, ok := ret.Get(0).(func(context.Context, types.RequestQuery) *abciclient.ReqRes); ok {
 		r0 = rf(_a0, _a1)
 	} else {
 		if ret.Get(0) != nil {
-			r0 = ret.Get(0).(*abcicli.ReqRes)
+			r0 = ret.Get(0).(*abciclient.ReqRes)
 		}
 	}
 
@@ -751,7 +751,7 @@ func (_m *Client) SetLogger(_a0 log.Logger) {
 }
 
 // SetResponseCallback provides a mock function with given fields: _a0
-func (_m *Client) SetResponseCallback(_a0 abcicli.Callback) {
+func (_m *Client) SetResponseCallback(_a0 abciclient.Callback) {
 	_m.Called(_a0)
 }
 

abci/client/socket_client.go

@@ -1,4 +1,4 @@
-package abcicli
+package abciclient
 
 import (
 	"bufio"
@@ -13,7 +13,6 @@ import (
 
 	"github.com/tendermint/tendermint/abci/types"
 	tmsync "github.com/tendermint/tendermint/internal/libs/sync"
-	"github.com/tendermint/tendermint/internal/libs/timer"
 	tmnet "github.com/tendermint/tendermint/libs/net"
 	"github.com/tendermint/tendermint/libs/service"
 )
@@ -22,8 +21,6 @@ const (
 	// reqQueueSize is the max number of queued async requests.
 	// (memory: 256MB max assuming 1MB transactions)
 	reqQueueSize = 256
-	// Don't wait longer than...
-	flushThrottleMS = 20
 )
 
 type reqResWithContext struct {
@@ -40,10 +37,9 @@ type socketClient struct {
 	mustConnect bool
 	conn        net.Conn
 
-	reqQueue   chan *reqResWithContext
-	flushTimer *timer.ThrottleTimer
+	reqQueue chan *reqResWithContext
 
-	mtx     tmsync.RWMutex
+	mtx     tmsync.Mutex
 	err     error
 	reqSent *list.List                            // list of requests sent, waiting for response
 	resCb   func(*types.Request, *types.Response) // called on all requests, if set.
@@ -57,7 +53,6 @@ var _ Client = (*socketClient)(nil)
 func NewSocketClient(addr string, mustConnect bool) Client {
 	cli := &socketClient{
 		reqQueue:    make(chan *reqResWithContext, reqQueueSize),
-		flushTimer:  timer.NewThrottleTimer("socketClient", flushThrottleMS),
 		mustConnect: mustConnect,
 
 		addr:    addr,
@@ -102,14 +97,13 @@ func (cli *socketClient) OnStop() {
 		cli.conn.Close()
 	}
 
-	cli.flushQueue()
-	cli.flushTimer.Stop()
+	cli.drainQueue()
 }
 
 // Error returns an error if the client was stopped abruptly.
 func (cli *socketClient) Error() error {
-	cli.mtx.RLock()
-	defer cli.mtx.RUnlock()
+	cli.mtx.Lock()
+	defer cli.mtx.Unlock()
 	return cli.err
 }
 
@@ -119,45 +113,32 @@ func (cli *socketClient) Error() error {
 // NOTE: callback may get internally generated flush responses.
 func (cli *socketClient) SetResponseCallback(resCb Callback) {
 	cli.mtx.Lock()
-	defer cli.mtx.Unlock()
 	cli.resCb = resCb
+	cli.mtx.Unlock()
 }
 
 //----------------------------------------
 
 func (cli *socketClient) sendRequestsRoutine(conn io.Writer) {
-	w := bufio.NewWriter(conn)
+	bw := bufio.NewWriter(conn)
 	for {
 		select {
 		case reqres := <-cli.reqQueue:
-			// cli.Logger.Debug("Sent request", "requestType", reflect.TypeOf(reqres.Request), "request", reqres.Request)
-
 			if reqres.C.Err() != nil {
 				cli.Logger.Debug("Request's context is done", "req", reqres.R, "err", reqres.C.Err())
 				continue
 			}
-
 			cli.willSendReq(reqres.R)
-			err := types.WriteMessage(reqres.R.Request, w)
-			if err != nil {
+
+			if err := types.WriteMessage(reqres.R.Request, bw); err != nil {
 				cli.stopForError(fmt.Errorf("write to buffer: %w", err))
 				return
 			}
+			if err := bw.Flush(); err != nil {
+				cli.stopForError(fmt.Errorf("flush buffer: %w", err))
+				return
+			}
 
-			// If it's a flush request, flush the current buffer.
-			if _, ok := reqres.R.Request.Value.(*types.Request_Flush); ok {
-				err = w.Flush()
-				if err != nil {
-					cli.stopForError(fmt.Errorf("flush buffer: %w", err))
-					return
-				}
-			}
-		case <-cli.flushTimer.Ch: // flush queue
-			select {
-			case cli.reqQueue <- &reqResWithContext{R: NewReqRes(types.ToRequestFlush()), C: context.Background()}:
-			default:
-				// Probably will fill the buffer, or retry later.
-			}
 		case <-cli.Quit():
 			return
 		}
@@ -492,14 +473,6 @@ func (cli *socketClient) queueRequest(ctx context.Context, req *types.Request, s
 		}
 	}
 
-	// Maybe auto-flush, or unset auto-flush
-	switch req.Value.(type) {
-	case *types.Request_Flush:
-		cli.flushTimer.Unset()
-	default:
-		cli.flushTimer.Set()
-	}
-
 	return reqres, nil
 }
 
@@ -537,7 +510,9 @@ func queueErr(e error) error {
 	return fmt.Errorf("can't queue req: %w", e)
 }
 
-func (cli *socketClient) flushQueue() {
+// drainQueue marks as complete and discards all remaining pending requests
+// from the queue.
+func (cli *socketClient) drainQueue() {
 	cli.mtx.Lock()
 	defer cli.mtx.Unlock()
 
@@ -547,14 +522,17 @@ func (cli *socketClient) flushQueue() {
 		reqres.Done()
 	}
 
-	// mark all queued messages as resolved
-LOOP:
+	// Mark all queued messages as resolved.
+	//
+	// TODO(creachadair): We can't simply range the channel, because it is never
+	// closed, and the writer continues to add work.
+	// See https://github.com/tendermint/tendermint/issues/6996.
 	for {
 		select {
 		case reqres := <-cli.reqQueue:
 			reqres.R.Done()
 		default:
-			break LOOP
+			return
 		}
 	}
 }

abci/client/socket_client_test.go

@@ -1,4 +1,4 @@
-package abcicli_test
+package abciclient_test
 
 import (
 	"context"
@@ -11,7 +11,7 @@ import (
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 
-	abcicli "github.com/tendermint/tendermint/abci/client"
+	abciclient "github.com/tendermint/tendermint/abci/client"
 	"github.com/tendermint/tendermint/abci/server"
 	"github.com/tendermint/tendermint/abci/types"
 	"github.com/tendermint/tendermint/libs/service"
@@ -100,7 +100,7 @@ func TestHangingSyncCalls(t *testing.T) {
 }
 
 func setupClientServer(t *testing.T, app types.Application) (
-	service.Service, abcicli.Client) {
+	service.Service, abciclient.Client) {
 	// some port between 20k and 30k
 	port := 20000 + rand.Int31()%10000
 	addr := fmt.Sprintf("localhost:%d", port)
@@ -110,7 +110,7 @@ func setupClientServer(t *testing.T, app types.Application) (
 	err = s.Start()
 	require.NoError(t, err)
 
-	c := abcicli.NewSocketClient(addr, true)
+	c := abciclient.NewSocketClient(addr, true)
 	err = c.Start()
 	require.NoError(t, err)
 

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

@@ -15,7 +15,7 @@ import (
 	"github.com/tendermint/tendermint/libs/log"
 	tmos "github.com/tendermint/tendermint/libs/os"
 
-	abcicli "github.com/tendermint/tendermint/abci/client"
+	abciclient "github.com/tendermint/tendermint/abci/client"
 	"github.com/tendermint/tendermint/abci/example/code"
 	"github.com/tendermint/tendermint/abci/example/kvstore"
 	"github.com/tendermint/tendermint/abci/server"
@@ -27,7 +27,7 @@ import (
 
 // client is a global variable so it can be reused by the console
 var (
-	client abcicli.Client
+	client abciclient.Client
 	logger log.Logger
 
 	ctx = context.Background()
@@ -67,7 +67,7 @@ var RootCmd = &cobra.Command{
 
 		if client == nil {
 			var err error
-			client, err = abcicli.NewClient(flagAddress, flagAbci, false)
+			client, err = abciclient.NewClient(flagAddress, flagAbci, false)
 			if err != nil {
 				return err
 			}

abci/example/example_test.go

@@ -13,11 +13,12 @@ import (
 	"github.com/stretchr/testify/require"
 
 	"google.golang.org/grpc"
+	"google.golang.org/grpc/credentials/insecure"
 
 	"github.com/tendermint/tendermint/libs/log"
 	tmnet "github.com/tendermint/tendermint/libs/net"
 
-	abcicli "github.com/tendermint/tendermint/abci/client"
+	abciclient "github.com/tendermint/tendermint/abci/client"
 	"github.com/tendermint/tendermint/abci/example/code"
 	"github.com/tendermint/tendermint/abci/example/kvstore"
 	abciserver "github.com/tendermint/tendermint/abci/server"
@@ -61,7 +62,7 @@ func testStream(t *testing.T, app types.Application) {
 	})
 
 	// Connect to the socket
-	client := abcicli.NewSocketClient(socket, false)
+	client := abciclient.NewSocketClient(socket, false)
 	client.SetLogger(log.TestingLogger().With("module", "abci-client"))
 	err = client.Start()
 	require.NoError(t, err)
@@ -129,7 +130,7 @@ func dialerFunc(ctx context.Context, addr string) (net.Conn, error) {
 
 func testGRPCSync(t *testing.T, app types.ABCIApplicationServer) {
 	numDeliverTxs := 2000
-	socketFile := fmt.Sprintf("test-%08x.sock", rand.Int31n(1<<30))
+	socketFile := fmt.Sprintf("/tmp/test-%08x.sock", rand.Int31n(1<<30))
 	defer os.Remove(socketFile)
 	socket := fmt.Sprintf("unix://%v", socketFile)
 
@@ -147,7 +148,10 @@ func testGRPCSync(t *testing.T, app types.ABCIApplicationServer) {
 	})
 
 	// Connect to the socket
-	conn, err := grpc.Dial(socket, grpc.WithInsecure(), grpc.WithContextDialer(dialerFunc))
+	conn, err := grpc.Dial(socket,
+		grpc.WithTransportCredentials(insecure.NewCredentials()),
+		grpc.WithContextDialer(dialerFunc),
+	)
 	if err != nil {
 		t.Fatalf("Error dialing GRPC server: %v", err.Error())
 	}

abci/example/kvstore/kvstore_test.go

@@ -12,7 +12,7 @@ import (
 	"github.com/tendermint/tendermint/libs/log"
 	"github.com/tendermint/tendermint/libs/service"
 
-	abcicli "github.com/tendermint/tendermint/abci/client"
+	abciclient "github.com/tendermint/tendermint/abci/client"
 	"github.com/tendermint/tendermint/abci/example/code"
 	abciserver "github.com/tendermint/tendermint/abci/server"
 	"github.com/tendermint/tendermint/abci/types"
@@ -165,7 +165,7 @@ func TestValUpdates(t *testing.T) {
 
 	makeApplyBlock(t, kvstore, 2, diff, tx1, tx2, tx3)
 
-	vals1 = append(vals[:nInit-2], vals[nInit+1]) // nolint: gocritic
+	vals1 = append(vals[:nInit-2], vals[nInit+1])
 	vals2 = kvstore.Validators()
 	valsEqual(t, vals1, vals2)
 
@@ -229,7 +229,7 @@ func valsEqual(t *testing.T, vals1, vals2 []types.ValidatorUpdate) {
 	}
 }
 
-func makeSocketClientServer(app types.Application, name string) (abcicli.Client, service.Service, error) {
+func makeSocketClientServer(app types.Application, name string) (abciclient.Client, service.Service, error) {
 	// Start the listener
 	socket := fmt.Sprintf("unix://%s.sock", name)
 	logger := log.TestingLogger()
@@ -241,7 +241,7 @@ func makeSocketClientServer(app types.Application, name string) (abcicli.Client,
 	}
 
 	// Connect to the socket
-	client := abcicli.NewSocketClient(socket, false)
+	client := abciclient.NewSocketClient(socket, false)
 	client.SetLogger(logger.With("module", "abci-client"))
 	if err := client.Start(); err != nil {
 		if err = server.Stop(); err != nil {
@@ -253,7 +253,7 @@ func makeSocketClientServer(app types.Application, name string) (abcicli.Client,
 	return client, server, nil
 }
 
-func makeGRPCClientServer(app types.Application, name string) (abcicli.Client, service.Service, error) {
+func makeGRPCClientServer(app types.Application, name string) (abciclient.Client, service.Service, error) {
 	// Start the listener
 	socket := fmt.Sprintf("unix://%s.sock", name)
 	logger := log.TestingLogger()
@@ -265,7 +265,7 @@ func makeGRPCClientServer(app types.Application, name string) (abcicli.Client, s
 		return nil, nil, err
 	}
 
-	client := abcicli.NewGRPCClient(socket, true)
+	client := abciclient.NewGRPCClient(socket, true)
 	client.SetLogger(logger.With("module", "abci-client"))
 	if err := client.Start(); err != nil {
 		if err := server.Stop(); err != nil {
@@ -296,7 +296,7 @@ func TestClientServer(t *testing.T) {
 
 	// set up grpc app
 	kvstore = NewApplication()
-	gclient, gserver, err := makeGRPCClientServer(kvstore, "kvstore-grpc")
+	gclient, gserver, err := makeGRPCClientServer(kvstore, "/tmp/kvstore-grpc")
 	require.NoError(t, err)
 
 	t.Cleanup(func() {
@@ -313,7 +313,7 @@ func TestClientServer(t *testing.T) {
 	runClientTests(t, gclient)
 }
 
-func runClientTests(t *testing.T, client abcicli.Client) {
+func runClientTests(t *testing.T, client abciclient.Client) {
 	// run some tests....
 	key := testKey
 	value := key
@@ -325,7 +325,7 @@ func runClientTests(t *testing.T, client abcicli.Client) {
 	testClient(t, client, tx, key, value)
 }
 
-func testClient(t *testing.T, app abcicli.Client, tx []byte, key, value string) {
+func testClient(t *testing.T, app abciclient.Client, tx []byte, key, value string) {
 	ar, err := app.DeliverTxSync(ctx, types.RequestDeliverTx{Tx: tx})
 	require.NoError(t, err)
 	require.False(t, ar.IsErr(), ar)

abci/example/kvstore/persistent_kvstore.go

@@ -11,9 +11,9 @@ import (
 
 	"github.com/tendermint/tendermint/abci/example/code"
 	"github.com/tendermint/tendermint/abci/types"
-	cryptoenc "github.com/tendermint/tendermint/crypto/encoding"
+	"github.com/tendermint/tendermint/crypto/encoding"
 	"github.com/tendermint/tendermint/libs/log"
-	pc "github.com/tendermint/tendermint/proto/tendermint/crypto"
+	cryptoproto "github.com/tendermint/tendermint/proto/tendermint/crypto"
 )
 
 const (
@@ -30,7 +30,7 @@ type PersistentKVStoreApplication struct {
 	// validator set
 	ValUpdates []types.ValidatorUpdate
 
-	valAddrToPubKeyMap map[string]pc.PublicKey
+	valAddrToPubKeyMap map[string]cryptoproto.PublicKey
 
 	logger log.Logger
 }
@@ -46,7 +46,7 @@ func NewPersistentKVStoreApplication(dbDir string) *PersistentKVStoreApplication
 
 	return &PersistentKVStoreApplication{
 		app:                &Application{state: state},
-		valAddrToPubKeyMap: make(map[string]pc.PublicKey),
+		valAddrToPubKeyMap: make(map[string]cryptoproto.PublicKey),
 		logger:             log.NewNopLogger(),
 	}
 }
@@ -194,8 +194,8 @@ func (app *PersistentKVStoreApplication) Validators() (validators []types.Valida
 	return
 }
 
-func MakeValSetChangeTx(pubkey pc.PublicKey, power int64) []byte {
-	pk, err := cryptoenc.PubKeyFromProto(pubkey)
+func MakeValSetChangeTx(pubkey cryptoproto.PublicKey, power int64) []byte {
+	pk, err := encoding.PubKeyFromProto(pubkey)
 	if err != nil {
 		panic(err)
 	}
@@ -243,7 +243,7 @@ func (app *PersistentKVStoreApplication) execValidatorTx(tx []byte) types.Respon
 
 // add, update, or remove a validator
 func (app *PersistentKVStoreApplication) updateValidator(v types.ValidatorUpdate) types.ResponseDeliverTx {
-	pubkey, err := cryptoenc.PubKeyFromProto(v.PubKey)
+	pubkey, err := encoding.PubKeyFromProto(v.PubKey)
 	if err != nil {
 		panic(fmt.Errorf("can't decode public key: %w", err))
 	}

abci/server/socket_server.go

@@ -240,22 +240,15 @@ func (s *SocketServer) handleRequest(req *types.Request, responses chan<- *types
 
 // Pull responses from 'responses' and write them to conn.
 func (s *SocketServer) handleResponses(closeConn chan error, conn io.Writer, responses <-chan *types.Response) {
-	var count int
-	var bufWriter = bufio.NewWriter(conn)
-	for {
-		var res = <-responses
-		err := types.WriteMessage(res, bufWriter)
-		if err != nil {
+	bw := bufio.NewWriter(conn)
+	for res := range responses {
+		if err := types.WriteMessage(res, bw); err != nil {
 			closeConn <- fmt.Errorf("error writing message: %w", err)
 			return
 		}
-		if _, ok := res.Value.(*types.Response_Flush); ok {
-			err = bufWriter.Flush()
-			if err != nil {
-				closeConn <- fmt.Errorf("error flushing write buffer: %w", err)
-				return
-			}
+		if err := bw.Flush(); err != nil {
+			closeConn <- fmt.Errorf("error flushing write buffer: %w", err)
+			return
 		}
-		count++
 	}
 }

abci/tests/client_server_test.go

@@ -5,7 +5,7 @@ import (
 
 	"github.com/stretchr/testify/assert"
 
-	abciclient "github.com/tendermint/tendermint/abci/client"
+	abciclientent "github.com/tendermint/tendermint/abci/client"
 	"github.com/tendermint/tendermint/abci/example/kvstore"
 	abciserver "github.com/tendermint/tendermint/abci/server"
 )
@@ -20,7 +20,7 @@ func TestClientServerNoAddrPrefix(t *testing.T) {
 	err = server.Start()
 	assert.NoError(t, err, "expected no error on server.Start")
 
-	client, err := abciclient.NewClient(addr, transport, true)
+	client, err := abciclientent.NewClient(addr, transport, true)
 	assert.NoError(t, err, "expected no error on NewClient")
 	err = client.Start()
 	assert.NoError(t, err, "expected no error on client.Start")

abci/tests/server/client.go

@@ -7,14 +7,14 @@ import (
 	"fmt"
 	mrand "math/rand"
 
-	abcicli "github.com/tendermint/tendermint/abci/client"
+	abciclient "github.com/tendermint/tendermint/abci/client"
 	"github.com/tendermint/tendermint/abci/types"
 	tmrand "github.com/tendermint/tendermint/libs/rand"
 )
 
 var ctx = context.Background()
 
-func InitChain(client abcicli.Client) error {
+func InitChain(client abciclient.Client) error {
 	total := 10
 	vals := make([]types.ValidatorUpdate, total)
 	for i := 0; i < total; i++ {
@@ -34,7 +34,7 @@ func InitChain(client abcicli.Client) error {
 	return nil
 }
 
-func Commit(client abcicli.Client, hashExp []byte) error {
+func Commit(client abciclient.Client, hashExp []byte) error {
 	res, err := client.CommitSync(ctx)
 	data := res.Data
 	if err != nil {
@@ -51,7 +51,7 @@ func Commit(client abcicli.Client, hashExp []byte) error {
 	return nil
 }
 
-func DeliverTx(client abcicli.Client, txBytes []byte, codeExp uint32, dataExp []byte) error {
+func DeliverTx(client abciclient.Client, txBytes []byte, codeExp uint32, dataExp []byte) error {
 	res, _ := client.DeliverTxSync(ctx, types.RequestDeliverTx{Tx: txBytes})
 	code, data, log := res.Code, res.Data, res.Log
 	if code != codeExp {
@@ -70,7 +70,7 @@ func DeliverTx(client abcicli.Client, txBytes []byte, codeExp uint32, dataExp []
 	return nil
 }
 
-func CheckTx(client abcicli.Client, txBytes []byte, codeExp uint32, dataExp []byte) error {
+func CheckTx(client abciclient.Client, txBytes []byte, codeExp uint32, dataExp []byte) error {
 	res, _ := client.CheckTxSync(ctx, types.RequestCheckTx{Tx: txBytes})
 	code, data, log := res.Code, res.Data, res.Log
 	if code != codeExp {

abci/types/client.go

@@ -0,0 +1 @@
+package types

abci/types/pubkey.go

@@ -4,7 +4,7 @@ import (
 	fmt "fmt"
 
 	"github.com/tendermint/tendermint/crypto/ed25519"
-	cryptoenc "github.com/tendermint/tendermint/crypto/encoding"
+	"github.com/tendermint/tendermint/crypto/encoding"
 	"github.com/tendermint/tendermint/crypto/secp256k1"
 	"github.com/tendermint/tendermint/crypto/sr25519"
 )
@@ -12,7 +12,7 @@ import (
 func Ed25519ValidatorUpdate(pk []byte, power int64) ValidatorUpdate {
 	pke := ed25519.PubKey(pk)
 
-	pkp, err := cryptoenc.PubKeyToProto(pke)
+	pkp, err := encoding.PubKeyToProto(pke)
 	if err != nil {
 		panic(err)
 	}
@@ -29,7 +29,7 @@ func UpdateValidator(pk []byte, power int64, keyType string) ValidatorUpdate {
 		return Ed25519ValidatorUpdate(pk, power)
 	case secp256k1.KeyType:
 		pke := secp256k1.PubKey(pk)
-		pkp, err := cryptoenc.PubKeyToProto(pke)
+		pkp, err := encoding.PubKeyToProto(pke)
 		if err != nil {
 			panic(err)
 		}
@@ -39,7 +39,7 @@ func UpdateValidator(pk []byte, power int64, keyType string) ValidatorUpdate {
 		}
 	case sr25519.KeyType:
 		pke := sr25519.PubKey(pk)
-		pkp, err := cryptoenc.PubKeyToProto(pke)
+		pkp, err := encoding.PubKeyToProto(pke)
 		if err != nil {
 			panic(err)
 		}

cmd/tendermint/commands/debug/dump.go

@@ -11,7 +11,7 @@ import (
 	"github.com/spf13/cobra"
 	"github.com/spf13/viper"
 
-	cfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tendermint/config"
 	"github.com/tendermint/tendermint/libs/cli"
 	rpchttp "github.com/tendermint/tendermint/rpc/client/http"
 )
@@ -65,9 +65,9 @@ func dumpCmdHandler(_ *cobra.Command, args []string) error {
 	}
 
 	home := viper.GetString(cli.HomeFlag)
-	conf := cfg.DefaultConfig()
+	conf := config.DefaultConfig()
 	conf = conf.SetRoot(home)
-	cfg.EnsureRoot(conf.RootDir)
+	config.EnsureRoot(conf.RootDir)
 
 	dumpDebugData(outDir, conf, rpc)
 
@@ -79,7 +79,7 @@ func dumpCmdHandler(_ *cobra.Command, args []string) error {
 	return nil
 }
 
-func dumpDebugData(outDir string, conf *cfg.Config, rpc *rpchttp.HTTP) {
+func dumpDebugData(outDir string, conf *config.Config, rpc *rpchttp.HTTP) {
 	start := time.Now().UTC()
 
 	tmpDir, err := ioutil.TempDir(outDir, "tendermint_debug_tmp")

cmd/tendermint/commands/debug/kill.go

@@ -14,7 +14,7 @@ import (
 	"github.com/spf13/cobra"
 	"github.com/spf13/viper"
 
-	cfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tendermint/config"
 	"github.com/tendermint/tendermint/libs/cli"
 	rpchttp "github.com/tendermint/tendermint/rpc/client/http"
 )
@@ -50,9 +50,9 @@ func killCmdHandler(cmd *cobra.Command, args []string) error {
 	}
 
 	home := viper.GetString(cli.HomeFlag)
-	conf := cfg.DefaultConfig()
+	conf := config.DefaultConfig()
 	conf = conf.SetRoot(home)
-	cfg.EnsureRoot(conf.RootDir)
+	config.EnsureRoot(conf.RootDir)
 
 	// Create a temporary directory which will contain all the state dumps and
 	// relevant files and directories that will be compressed into a file.

cmd/tendermint/commands/debug/util.go

@@ -9,7 +9,7 @@ import (
 	"path"
 	"path/filepath"
 
-	cfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tendermint/config"
 	rpchttp "github.com/tendermint/tendermint/rpc/client/http"
 )
 
@@ -48,7 +48,7 @@ func dumpConsensusState(rpc *rpchttp.HTTP, dir, filename string) error {
 
 // copyWAL copies the Tendermint node's WAL file. It returns an error if the
 // WAL file cannot be read or copied.
-func copyWAL(conf *cfg.Config, dir string) error {
+func copyWAL(conf *config.Config, dir string) error {
 	walPath := conf.Consensus.WalFile()
 	walFile := filepath.Base(walPath)
 

cmd/tendermint/commands/gen_node_key.go

@@ -12,11 +12,9 @@ import (
 // GenNodeKeyCmd allows the generation of a node key. It prints JSON-encoded
 // NodeKey to the standard output.
 var GenNodeKeyCmd = &cobra.Command{
-	Use:     "gen-node-key",
-	Aliases: []string{"gen_node_key"},
-	Short:   "Generate a new node key",
-	RunE:    genNodeKey,
-	PreRun:  deprecateSnakeCase,
+	Use:   "gen-node-key",
+	Short: "Generate a new node key",
+	RunE:  genNodeKey,
 }
 
 func genNodeKey(cmd *cobra.Command, args []string) error {

cmd/tendermint/commands/gen_validator.go

@@ -13,11 +13,9 @@ import (
 // GenValidatorCmd allows the generation of a keypair for a
 // validator.
 var GenValidatorCmd = &cobra.Command{
-	Use:     "gen-validator",
-	Aliases: []string{"gen_validator"},
-	Short:   "Generate new validator keypair",
-	RunE:    genValidator,
-	PreRun:  deprecateSnakeCase,
+	Use:   "gen-validator",
+	Short: "Generate new validator keypair",
+	RunE:  genValidator,
 }
 
 func init() {

cmd/tendermint/commands/init.go

@@ -121,7 +121,9 @@ func initFilesWithConfig(config *cfg.Config) error {
 	}
 
 	// write config file
-	cfg.WriteConfigFile(config.RootDir, config)
+	if err := cfg.WriteConfigFile(config.RootDir, config); err != nil {
+		return err
+	}
 	logger.Info("Generated config", "mode", config.Mode)
 
 	return nil

cmd/tendermint/commands/inspect.go

@@ -0,0 +1,63 @@
+package commands
+
+import (
+	"context"
+	"os"
+	"os/signal"
+	"syscall"
+
+	"github.com/spf13/cobra"
+
+	"github.com/tendermint/tendermint/internal/inspect"
+)
+
+// InspectCmd is the command for starting an inspect server.
+var InspectCmd = &cobra.Command{
+	Use:   "inspect",
+	Short: "Run an inspect server for investigating Tendermint state",
+	Long: `
+	inspect runs a subset of Tendermint's RPC endpoints that are useful for debugging
+	issues with Tendermint.
+
+	When the Tendermint consensus engine detects inconsistent state, it will crash the
+	tendermint process. Tendermint will not start up while in this inconsistent state. 
+	The inspect command can be used to query the block and state store using Tendermint
+	RPC calls to debug issues of inconsistent state.
+	`,
+
+	RunE: runInspect,
+}
+
+func init() {
+	InspectCmd.Flags().
+		String("rpc.laddr",
+			config.RPC.ListenAddress, "RPC listenener address. Port required")
+	InspectCmd.Flags().
+		String("db-backend",
+			config.DBBackend, "database backend: goleveldb | cleveldb | boltdb | rocksdb | badgerdb")
+	InspectCmd.Flags().
+		String("db-dir", config.DBPath, "database directory")
+}
+
+func runInspect(cmd *cobra.Command, args []string) error {
+	ctx, cancel := context.WithCancel(cmd.Context())
+	defer cancel()
+
+	c := make(chan os.Signal, 1)
+	signal.Notify(c, syscall.SIGTERM, syscall.SIGINT)
+	go func() {
+		<-c
+		cancel()
+	}()
+
+	ins, err := inspect.NewFromConfig(logger, config)
+	if err != nil {
+		return err
+	}
+
+	logger.Info("starting inspect server")
+	if err := ins.Run(ctx); err != nil {
+		return err
+	}
+	return nil
+}

cmd/tendermint/commands/light.go

@@ -11,7 +11,6 @@ import (
 	"time"
 
 	"github.com/spf13/cobra"
-
 	dbm "github.com/tendermint/tm-db"
 
 	"github.com/tendermint/tendermint/libs/log"

cmd/tendermint/commands/probe_upnp.go

@@ -11,11 +11,9 @@ import (
 
 // ProbeUpnpCmd adds capabilities to test the UPnP functionality.
 var ProbeUpnpCmd = &cobra.Command{
-	Use:     "probe-upnp",
-	Aliases: []string{"probe_upnp"},
-	Short:   "Test UPnP functionality",
-	RunE:    probeUpnp,
-	PreRun:  deprecateSnakeCase,
+	Use:   "probe-upnp",
+	Short: "Test UPnP functionality",
+	RunE:  probeUpnp,
 }
 
 func probeUpnp(cmd *cobra.Command, args []string) error {

cmd/tendermint/commands/reindex_event.go

@@ -3,20 +3,22 @@ package commands
 import (
 	"errors"
 	"fmt"
+	"path/filepath"
 	"strings"
 
 	"github.com/spf13/cobra"
-	tmdb "github.com/tendermint/tm-db"
+	dbm "github.com/tendermint/tm-db"
 
 	abcitypes "github.com/tendermint/tendermint/abci/types"
 	tmcfg "github.com/tendermint/tendermint/config"
 	"github.com/tendermint/tendermint/internal/libs/progressbar"
-	ctypes "github.com/tendermint/tendermint/rpc/core/types"
-	"github.com/tendermint/tendermint/state"
-	"github.com/tendermint/tendermint/state/indexer"
-	"github.com/tendermint/tendermint/state/indexer/sink/kv"
-	"github.com/tendermint/tendermint/state/indexer/sink/psql"
-	"github.com/tendermint/tendermint/store"
+	"github.com/tendermint/tendermint/internal/state"
+	"github.com/tendermint/tendermint/internal/state/indexer"
+	"github.com/tendermint/tendermint/internal/state/indexer/sink/kv"
+	"github.com/tendermint/tendermint/internal/state/indexer/sink/psql"
+	"github.com/tendermint/tendermint/internal/store"
+	"github.com/tendermint/tendermint/libs/os"
+	"github.com/tendermint/tendermint/rpc/coretypes"
 	"github.com/tendermint/tendermint/types"
 )
 
@@ -29,11 +31,12 @@ var ReIndexEventCmd = &cobra.Command{
 	Use:   "reindex-event",
 	Short: "reindex events to the event store backends",
 	Long: `
-	reindex-event is an offline tooling to re-index block and tx events to the eventsinks,
-	you can run this command when the event store backend dropped/disconnected or you want to replace the backend.
-	The default start-height is 0, meaning the tooling will start reindex from the base block height(inclusive); and the 
-	default end-height is 0, meaning the tooling will reindex until the latest block height(inclusive). User can omits
-	either or both arguments.
+reindex-event is an offline tooling to re-index block and tx events to the eventsinks,
+you can run this command when the event store backend dropped/disconnected or you want to 
+replace the backend. The default start-height is 0, meaning the tooling will start 
+reindex from the base block height(inclusive); and the default end-height is 0, meaning 
+the tooling will reindex until the latest block height(inclusive). User can omit
+either or both arguments.
 	`,
 	Example: `
 	tendermint reindex-event
@@ -106,7 +109,7 @@ func loadEventSinks(cfg *tmcfg.Config) ([]indexer.EventSink, error) {
 			if conn == "" {
 				return nil, errors.New("the psql connection settings cannot be empty")
 			}
-			es, _, err := psql.NewEventSink(conn, chainID)
+			es, err := psql.NewEventSink(conn, chainID)
 			if err != nil {
 				return nil, err
 			}
@@ -129,17 +132,25 @@ func loadEventSinks(cfg *tmcfg.Config) ([]indexer.EventSink, error) {
 }
 
 func loadStateAndBlockStore(cfg *tmcfg.Config) (*store.BlockStore, state.Store, error) {
-	dbType := tmdb.BackendType(cfg.DBBackend)
+	dbType := dbm.BackendType(cfg.DBBackend)
+
+	if !os.FileExists(filepath.Join(cfg.DBDir(), "blockstore.db")) {
+		return nil, nil, fmt.Errorf("no blockstore found in %v", cfg.DBDir())
+	}
 
 	// Get BlockStore
-	blockStoreDB, err := tmdb.NewDB("blockstore", dbType, cfg.DBDir())
+	blockStoreDB, err := dbm.NewDB("blockstore", dbType, cfg.DBDir())
 	if err != nil {
 		return nil, nil, err
 	}
 	blockStore := store.NewBlockStore(blockStoreDB)
 
+	if !os.FileExists(filepath.Join(cfg.DBDir(), "state.db")) {
+		return nil, nil, fmt.Errorf("no blockstore found in %v", cfg.DBDir())
+	}
+
 	// Get StateStore
-	stateDB, err := tmdb.NewDB("state", dbType, cfg.DBDir())
+	stateDB, err := dbm.NewDB("state", dbType, cfg.DBDir())
 	if err != nil {
 		return nil, nil, err
 	}
@@ -221,14 +232,15 @@ func checkValidHeight(bs state.BlockStore) error {
 	}
 
 	if startHeight < base {
-		return fmt.Errorf("%s (requested start height: %d, base height: %d)", ctypes.ErrHeightNotAvailable, startHeight, base)
+		return fmt.Errorf("%s (requested start height: %d, base height: %d)",
+			coretypes.ErrHeightNotAvailable, startHeight, base)
 	}
 
 	height := bs.Height()
 
 	if startHeight > height {
 		return fmt.Errorf(
-			"%s (requested start height: %d, store height: %d)", ctypes.ErrHeightNotAvailable, startHeight, height)
+			"%s (requested start height: %d, store height: %d)", coretypes.ErrHeightNotAvailable, startHeight, height)
 	}
 
 	if endHeight == 0 || endHeight > height {
@@ -238,13 +250,13 @@ func checkValidHeight(bs state.BlockStore) error {
 
 	if endHeight < base {
 		return fmt.Errorf(
-			"%s (requested end height: %d, base height: %d)", ctypes.ErrHeightNotAvailable, endHeight, base)
+			"%s (requested end height: %d, base height: %d)", coretypes.ErrHeightNotAvailable, endHeight, base)
 	}
 
 	if endHeight < startHeight {
 		return fmt.Errorf(
 			"%s (requested the end height: %d is less than the start height: %d)",
-			ctypes.ErrInvalidRequest, startHeight, endHeight)
+			coretypes.ErrInvalidRequest, startHeight, endHeight)
 	}
 
 	return nil

cmd/tendermint/commands/reindex_event_test.go

@@ -11,10 +11,13 @@ import (
 
 	abcitypes "github.com/tendermint/tendermint/abci/types"
 	tmcfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tendermint/internal/state/indexer"
+	"github.com/tendermint/tendermint/internal/state/mocks"
 	prototmstate "github.com/tendermint/tendermint/proto/tendermint/state"
-	"github.com/tendermint/tendermint/state/indexer"
-	"github.com/tendermint/tendermint/state/mocks"
 	"github.com/tendermint/tendermint/types"
+	dbm "github.com/tendermint/tm-db"
+
+	_ "github.com/lib/pq" // for the psql sink
 )
 
 const (
@@ -107,12 +110,29 @@ func TestLoadEventSink(t *testing.T) {
 }
 
 func TestLoadBlockStore(t *testing.T) {
-	bs, ss, err := loadStateAndBlockStore(tmcfg.TestConfig())
+	testCfg, err := tmcfg.ResetTestRoot(t.Name())
+	require.NoError(t, err)
+	testCfg.DBBackend = "goleveldb"
+	_, _, err = loadStateAndBlockStore(testCfg)
+	// we should return an error because the state store and block store
+	// don't yet exist
+	require.Error(t, err)
+
+	dbType := dbm.BackendType(testCfg.DBBackend)
+	bsdb, err := dbm.NewDB("blockstore", dbType, testCfg.DBDir())
+	require.NoError(t, err)
+	bsdb.Close()
+
+	ssdb, err := dbm.NewDB("state", dbType, testCfg.DBDir())
+	require.NoError(t, err)
+	ssdb.Close()
+
+	bs, ss, err := loadStateAndBlockStore(testCfg)
 	require.NoError(t, err)
 	require.NotNil(t, bs)
 	require.NotNil(t, ss)
-
 }
+
 func TestReIndexEvent(t *testing.T) {
 	mockBlockStore := &mocks.BlockStore{}
 	mockStateStore := &mocks.Store{}

cmd/tendermint/commands/replay.go

@@ -17,11 +17,9 @@ var ReplayCmd = &cobra.Command{
 // ReplayConsoleCmd allows replaying of messages from the WAL in a
 // console.
 var ReplayConsoleCmd = &cobra.Command{
-	Use:     "replay-console",
-	Aliases: []string{"replay_console"},
-	Short:   "Replay messages from WAL in a console",
+	Use:   "replay-console",
+	Short: "Replay messages from WAL in a console",
 	Run: func(cmd *cobra.Command, args []string) {
 		consensus.RunReplayFile(config.BaseConfig, config.Consensus, true)
 	},
-	PreRun: deprecateSnakeCase,
 }

cmd/tendermint/commands/reset_priv_validator.go

@@ -14,11 +14,9 @@ import (
 // ResetAllCmd removes the database of this Tendermint core
 // instance.
 var ResetAllCmd = &cobra.Command{
-	Use:     "unsafe-reset-all",
-	Aliases: []string{"unsafe_reset_all"},
-	Short:   "(unsafe) Remove all the data and WAL, reset this node's validator to genesis state",
-	RunE:    resetAll,
-	PreRun:  deprecateSnakeCase,
+	Use:   "unsafe-reset-all",
+	Short: "(unsafe) Remove all the data and WAL, reset this node's validator to genesis state",
+	RunE:  resetAll,
 }
 
 var keepAddrBook bool
@@ -31,11 +29,9 @@ func init() {
 
 // ResetPrivValidatorCmd resets the private validator files.
 var ResetPrivValidatorCmd = &cobra.Command{
-	Use:     "unsafe-reset-priv-validator",
-	Aliases: []string{"unsafe_reset_priv_validator"},
-	Short:   "(unsafe) Reset this node's validator to genesis state",
-	RunE:    resetPrivValidator,
-	PreRun:  deprecateSnakeCase,
+	Use:   "unsafe-reset-priv-validator",
+	Short: "(unsafe) Reset this node's validator to genesis state",
+	RunE:  resetPrivValidator,
 }
 
 // XXX: this is totally unsafe.

cmd/tendermint/commands/rollback.go

@@ -0,0 +1,50 @@
+package commands
+
+import (
+	"fmt"
+
+	"github.com/spf13/cobra"
+
+	cfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tendermint/internal/state"
+)
+
+var RollbackStateCmd = &cobra.Command{
+	Use:   "rollback",
+	Short: "rollback tendermint state by one height",
+	Long: `
+A state rollback is performed to recover from an incorrect application state transition,
+when Tendermint has persisted an incorrect app hash and is thus unable to make
+progress. Rollback overwrites a state at height n with the state at height n - 1.
+The application should also roll back to height n - 1. No blocks are removed, so upon
+restarting Tendermint the transactions in block n will be re-executed against the
+application.
+`,
+	RunE: func(cmd *cobra.Command, args []string) error {
+		height, hash, err := RollbackState(config)
+		if err != nil {
+			return fmt.Errorf("failed to rollback state: %w", err)
+		}
+
+		fmt.Printf("Rolled back state to height %d and hash %X", height, hash)
+		return nil
+	},
+}
+
+// RollbackState takes the state at the current height n and overwrites it with the state
+// at height n - 1. Note state here refers to tendermint state not application state.
+// Returns the latest state height and app hash alongside an error if there was one.
+func RollbackState(config *cfg.Config) (int64, []byte, error) {
+	// use the parsed config to load the block and state store
+	blockStore, stateStore, err := loadStateAndBlockStore(config)
+	if err != nil {
+		return -1, nil, err
+	}
+	defer func() {
+		_ = blockStore.Close()
+		_ = stateStore.Close()
+	}()
+
+	// rollback the last state
+	return state.Rollback(blockStore, stateStore)
+}

cmd/tendermint/commands/root.go

@@ -2,7 +2,6 @@ package commands
 
 import (
 	"fmt"
-	"strings"
 	"time"
 
 	"github.com/spf13/cobra"
@@ -65,10 +64,3 @@ var RootCmd = &cobra.Command{
 		return nil
 	},
 }
-
-// deprecateSnakeCase is a util function for 0.34.1. Should be removed in 0.35
-func deprecateSnakeCase(cmd *cobra.Command, args []string) {
-	if strings.Contains(cmd.CalledAs(), "_") {
-		fmt.Println("Deprecated: snake_case commands will be replaced by hyphen-case commands in the next major release")
-	}
-}

cmd/tendermint/commands/run_node.go

@@ -3,6 +3,8 @@ package commands
 import (
 	"bytes"
 	"crypto/sha256"
+	"errors"
+	"flag"
 	"fmt"
 	"io"
 	"os"
@@ -33,7 +35,22 @@ func AddNodeFlags(cmd *cobra.Command) {
 		"socket address to listen on for connections from external priv-validator process")
 
 	// node flags
-	cmd.Flags().Bool("fast-sync", config.FastSyncMode, "fast blockchain syncing")
+	cmd.Flags().Bool("blocksync.enable", config.BlockSync.Enable, "enable fast blockchain syncing")
+
+	// TODO (https://github.com/tendermint/tendermint/issues/6908): remove this check after the v0.35 release cycle
+	// This check was added to give users an upgrade prompt to use the new flag for syncing.
+	//
+	// The pflag package does not have a native way to print a depcrecation warning
+	// and return an error. This logic was added to print a deprecation message to the user
+	// and then crash if the user attempts to use the old --fast-sync flag.
+	fs := flag.NewFlagSet("", flag.ExitOnError)
+	fs.Func("fast-sync", "deprecated",
+		func(string) error {
+			return errors.New("--fast-sync has been deprecated, please use --blocksync.enable")
+		})
+	cmd.Flags().AddGoFlagSet(fs)
+
+	cmd.Flags().MarkHidden("fast-sync") //nolint:errcheck
 	cmd.Flags().BytesHexVar(
 		&genesisHash,
 		"genesis-hash",
@@ -48,7 +65,7 @@ func AddNodeFlags(cmd *cobra.Command) {
 		"proxy-app",
 		config.ProxyApp,
 		"proxy app address, or one of: 'kvstore',"+
-			" 'persistent_kvstore' or 'noop' for local testing.")
+			" 'persistent_kvstore', 'e2e' or 'noop' for local testing.")
 	cmd.Flags().String("abci", config.ABCI, "specify abci transport (socket | grpc)")
 
 	// rpc flags
@@ -65,7 +82,7 @@ func AddNodeFlags(cmd *cobra.Command) {
 		"p2p.laddr",
 		config.P2P.ListenAddress,
 		"node listen address. (0.0.0.0:0 means any interface, any port)")
-	cmd.Flags().String("p2p.seeds", config.P2P.Seeds, "comma-delimited ID@host:port seed nodes")
+	cmd.Flags().String("p2p.seeds", config.P2P.Seeds, "comma-delimited ID@host:port seed nodes") //nolint: staticcheck
 	cmd.Flags().String("p2p.persistent-peers", config.P2P.PersistentPeers, "comma-delimited ID@host:port persistent peers")
 	cmd.Flags().String("p2p.unconditional-peer-ids",
 		config.P2P.UnconditionalPeerIDs, "comma-delimited IDs of unconditional peers")
@@ -158,7 +175,7 @@ func checkGenesisHash(config *cfg.Config) error {
 	// Compare with the flag.
 	if !bytes.Equal(genesisHash, actualHash) {
 		return fmt.Errorf(
-			"--genesis_hash=%X does not match %s hash: %X",
+			"--genesis-hash=%X does not match %s hash: %X",
 			genesisHash, config.GenesisFile(), actualHash)
 	}
 

cmd/tendermint/commands/show_node_id.go

@@ -8,11 +8,9 @@ import (
 
 // ShowNodeIDCmd dumps node's ID to the standard output.
 var ShowNodeIDCmd = &cobra.Command{
-	Use:     "show-node-id",
-	Aliases: []string{"show_node_id"},
-	Short:   "Show this node's ID",
-	RunE:    showNodeID,
-	PreRun:  deprecateSnakeCase,
+	Use:   "show-node-id",
+	Short: "Show this node's ID",
+	RunE:  showNodeID,
 }
 
 func showNodeID(cmd *cobra.Command, args []string) error {

cmd/tendermint/commands/show_validator.go

@@ -16,11 +16,9 @@ import (
 
 // ShowValidatorCmd adds capabilities for showing the validator info.
 var ShowValidatorCmd = &cobra.Command{
-	Use:     "show-validator",
-	Aliases: []string{"show_validator"},
-	Short:   "Show this node's validator info",
-	RunE:    showValidator,
-	PreRun:  deprecateSnakeCase,
+	Use:   "show-validator",
+	Short: "Show this node's validator info",
+	RunE:  showValidator,
 }
 
 func showValidator(cmd *cobra.Command, args []string) error {

cmd/tendermint/commands/testnet.go

@@ -240,7 +240,9 @@ func testnetFiles(cmd *cobra.Command, args []string) error {
 		}
 		config.Moniker = moniker(i)
 
-		cfg.WriteConfigFile(nodeDir, config)
+		if err := cfg.WriteConfigFile(nodeDir, config); err != nil {
+			return err
+		}
 	}
 
 	fmt.Printf("Successfully initialized %v node directories\n", nValidators+nNonValidators)

cmd/tendermint/main.go

@@ -6,9 +6,9 @@ import (
 
 	cmd "github.com/tendermint/tendermint/cmd/tendermint/commands"
 	"github.com/tendermint/tendermint/cmd/tendermint/commands/debug"
-	cfg "github.com/tendermint/tendermint/config"
+	"github.com/tendermint/tendermint/config"
 	"github.com/tendermint/tendermint/libs/cli"
-	nm "github.com/tendermint/tendermint/node"
+	"github.com/tendermint/tendermint/node"
 )
 
 func main() {
@@ -28,6 +28,8 @@ func main() {
 		cmd.ShowNodeIDCmd,
 		cmd.GenNodeKeyCmd,
 		cmd.VersionCmd,
+		cmd.InspectCmd,
+		cmd.RollbackStateCmd,
 		cmd.MakeKeyMigrateCommand(),
 		debug.DebugCmd,
 		cli.NewCompletionCmd(rootCmd, true),
@@ -41,12 +43,12 @@ func main() {
 	//	* Provide their own DB implementation
 	// can copy this file and use something other than the
 	// node.NewDefault function
-	nodeFunc := nm.NewDefault
+	nodeFunc := node.NewDefault
 
 	// Create & start node
 	rootCmd.AddCommand(cmd.NewRunNodeCmd(nodeFunc))
 
-	cmd := cli.PrepareBaseCmd(rootCmd, "TM", os.ExpandEnv(filepath.Join("$HOME", cfg.DefaultTendermintDir)))
+	cmd := cli.PrepareBaseCmd(rootCmd, "TM", os.ExpandEnv(filepath.Join("$HOME", config.DefaultTendermintDir)))
 	if err := cmd.Execute(); err != nil {
 		panic(err)
 	}

config/config.go

@@ -64,6 +64,9 @@ var (
 
 	defaultNodeKeyPath  = filepath.Join(defaultConfigDir, defaultNodeKeyName)
 	defaultAddrBookPath = filepath.Join(defaultConfigDir, defaultAddrBookName)
+
+	minSubscriptionBufferSize     = 100
+	defaultSubscriptionBufferSize = 200
 )
 
 // Config defines the top level configuration for a Tendermint node
@@ -76,7 +79,7 @@ type Config struct {
 	P2P             *P2PConfig             `mapstructure:"p2p"`
 	Mempool         *MempoolConfig         `mapstructure:"mempool"`
 	StateSync       *StateSyncConfig       `mapstructure:"statesync"`
-	BlockSync       *BlockSyncConfig       `mapstructure:"fastsync"`
+	BlockSync       *BlockSyncConfig       `mapstructure:"blocksync"`
 	Consensus       *ConsensusConfig       `mapstructure:"consensus"`
 	TxIndex         *TxIndexConfig         `mapstructure:"tx-index"`
 	Instrumentation *InstrumentationConfig `mapstructure:"instrumentation"`
@@ -152,7 +155,7 @@ func (cfg *Config) ValidateBasic() error {
 		return fmt.Errorf("error in [statesync] section: %w", err)
 	}
 	if err := cfg.BlockSync.ValidateBasic(); err != nil {
-		return fmt.Errorf("error in [fastsync] section: %w", err)
+		return fmt.Errorf("error in [blocksync] section: %w", err)
 	}
 	if err := cfg.Consensus.ValidateBasic(); err != nil {
 		return fmt.Errorf("error in [consensus] section: %w", err)
@@ -194,12 +197,6 @@ type BaseConfig struct { //nolint: maligned
 	//   - No priv_validator_key.json, priv_validator_state.json
 	Mode string `mapstructure:"mode"`
 
-	// If this node is many blocks behind the tip of the chain, FastSync
-	// allows them to catchup quickly by downloading blocks in parallel
-	// and verifying their commits
-	// TODO: This should be moved to the blocksync config
-	FastSyncMode bool `mapstructure:"fast-sync"`
-
 	// Database backend: goleveldb | cleveldb | boltdb | rocksdb
 	// * goleveldb (github.com/syndtr/goleveldb - most popular implementation)
 	//   - pure go
@@ -242,23 +239,24 @@ type BaseConfig struct { //nolint: maligned
 	// If true, query the ABCI app on connecting to a new peer
 	// so the app can decide if we should keep the connection or not
 	FilterPeers bool `mapstructure:"filter-peers"` // false
+
+	Other map[string]interface{} `mapstructure:",remain"`
 }
 
 // DefaultBaseConfig returns a default base configuration for a Tendermint node
 func DefaultBaseConfig() BaseConfig {
 	return BaseConfig{
-		Genesis:      defaultGenesisJSONPath,
-		NodeKey:      defaultNodeKeyPath,
-		Mode:         defaultMode,
-		Moniker:      defaultMoniker,
-		ProxyApp:     "tcp://127.0.0.1:26658",
-		ABCI:         "socket",
-		LogLevel:     DefaultLogLevel,
-		LogFormat:    log.LogFormatPlain,
-		FastSyncMode: true,
-		FilterPeers:  false,
-		DBBackend:    "goleveldb",
-		DBPath:       "data",
+		Genesis:     defaultGenesisJSONPath,
+		NodeKey:     defaultNodeKeyPath,
+		Mode:        defaultMode,
+		Moniker:     defaultMoniker,
+		ProxyApp:    "tcp://127.0.0.1:26658",
+		ABCI:        "socket",
+		LogLevel:    DefaultLogLevel,
+		LogFormat:   log.LogFormatPlain,
+		FilterPeers: false,
+		DBBackend:   "goleveldb",
+		DBPath:      "data",
 	}
 }
 
@@ -268,7 +266,6 @@ func TestBaseConfig() BaseConfig {
 	cfg.chainID = "tendermint_test"
 	cfg.Mode = ModeValidator
 	cfg.ProxyApp = "kvstore"
-	cfg.FastSyncMode = false
 	cfg.DBBackend = "memdb"
 	return cfg
 }
@@ -345,6 +342,28 @@ func (cfg BaseConfig) ValidateBasic() error {
 		return fmt.Errorf("unknown mode: %v", cfg.Mode)
 	}
 
+	// TODO (https://github.com/tendermint/tendermint/issues/6908) remove this check after the v0.35 release cycle.
+	// This check was added to give users an upgrade prompt to use the new
+	// configuration option in v0.35. In future release cycles they should no longer
+	// be using this configuration parameter so the check can be removed.
+	// The cfg.Other field can likely be removed at the same time if it is not referenced
+	// elsewhere as it was added to service this check.
+	if fs, ok := cfg.Other["fastsync"]; ok {
+		if _, ok := fs.(map[string]interface{}); ok {
+			return fmt.Errorf("a configuration section named 'fastsync' was found in the " +
+				"configuration file. The 'fastsync' section has been renamed to " +
+				"'blocksync', please update the 'fastsync' field in your configuration file to 'blocksync'")
+		}
+	}
+	if fs, ok := cfg.Other["fast-sync"]; ok {
+		if fs != "" {
+			return fmt.Errorf("a parameter named 'fast-sync' was found in the " +
+				"configuration file. The parameter to enable or disable quickly syncing with a blockchain" +
+				"has moved to the [blocksync] section of the configuration file as blocksync.enable. " +
+				"Please move the 'fast-sync' field in your configuration file to 'blocksync.enable'")
+		}
+	}
+
 	return nil
 }
 
@@ -480,6 +499,29 @@ type RPCConfig struct {
 	// to the estimated maximum number of broadcast_tx_commit calls per block.
 	MaxSubscriptionsPerClient int `mapstructure:"max-subscriptions-per-client"`
 
+	// The number of events that can be buffered per subscription before
+	// returning `ErrOutOfCapacity`.
+	SubscriptionBufferSize int `mapstructure:"experimental-subscription-buffer-size"`
+
+	// The maximum number of responses that can be buffered per WebSocket
+	// client. If clients cannot read from the WebSocket endpoint fast enough,
+	// they will be disconnected, so increasing this parameter may reduce the
+	// chances of them being disconnected (but will cause the node to use more
+	// memory).
+	//
+	// Must be at least the same as `SubscriptionBufferSize`, otherwise
+	// connections may be dropped unnecessarily.
+	WebSocketWriteBufferSize int `mapstructure:"experimental-websocket-write-buffer-size"`
+
+	// If a WebSocket client cannot read fast enough, at present we may
+	// silently drop events instead of generating an error or disconnecting the
+	// client.
+	//
+	// Enabling this parameter will cause the WebSocket connection to be closed
+	// instead if it cannot read fast enough, allowing for greater
+	// predictability in subscription behavior.
+	CloseOnSlowClient bool `mapstructure:"experimental-close-on-slow-client"`
+
 	// How long to wait for a tx to be committed during /broadcast_tx_commit
 	// WARNING: Using a value larger than 10s will result in increasing the
 	// global HTTP write timeout, which applies to all connections and endpoints.
@@ -529,7 +571,9 @@ func DefaultRPCConfig() *RPCConfig {
 
 		MaxSubscriptionClients:    100,
 		MaxSubscriptionsPerClient: 5,
+		SubscriptionBufferSize:    defaultSubscriptionBufferSize,
 		TimeoutBroadcastTxCommit:  10 * time.Second,
+		WebSocketWriteBufferSize:  defaultSubscriptionBufferSize,
 
 		MaxBodyBytes:   int64(1000000), // 1MB
 		MaxHeaderBytes: 1 << 20,        // same as the net/http default
@@ -563,6 +607,18 @@ func (cfg *RPCConfig) ValidateBasic() error {
 	if cfg.MaxSubscriptionsPerClient < 0 {
 		return errors.New("max-subscriptions-per-client can't be negative")
 	}
+	if cfg.SubscriptionBufferSize < minSubscriptionBufferSize {
+		return fmt.Errorf(
+			"experimental-subscription-buffer-size must be >= %d",
+			minSubscriptionBufferSize,
+		)
+	}
+	if cfg.WebSocketWriteBufferSize < cfg.SubscriptionBufferSize {
+		return fmt.Errorf(
+			"experimental-websocket-write-buffer-size must be >= experimental-subscription-buffer-size (%d)",
+			cfg.SubscriptionBufferSize,
+		)
+	}
 	if cfg.TimeoutBroadcastTxCommit < 0 {
 		return errors.New("timeout-broadcast-tx-commit can't be negative")
 	}
@@ -615,9 +671,11 @@ type P2PConfig struct { //nolint: maligned
 
 	// Comma separated list of seed nodes to connect to
 	// We only use these if we can’t connect to peers in the addrbook
-	// NOTE: not used by the new PEX reactor. Please use BootstrapPeers instead.
-	// TODO: Remove once p2p refactor is complete
-	// ref: https://github.com/tendermint/tendermint/issues/5670
+	//
+	// Deprecated: This value is not used by the new PEX reactor. Use
+	// BootstrapPeers instead.
+	//
+	// TODO(#5670): Remove once the p2p refactor is complete.
 	Seeds string `mapstructure:"seeds"`
 
 	// Comma separated list of peers to be added to the peer store
@@ -694,13 +752,14 @@ type P2PConfig struct { //nolint: maligned
 	// Force dial to fail
 	TestDialFail bool `mapstructure:"test-dial-fail"`
 
-	// DisableLegacy is used mostly for testing to enable or disable the legacy
-	// P2P stack.
-	DisableLegacy bool `mapstructure:"disable-legacy"`
+	// UseLegacy enables the "legacy" P2P implementation and
+	// disables the newer default implementation. This flag will
+	// be removed in a future release.
+	UseLegacy bool `mapstructure:"use-legacy"`
 
 	// Makes it possible to configure which queue backend the p2p
 	// layer uses. Options are: "fifo", "priority" and "wdrr",
-	// with the default being "fifo".
+	// with the default being "priority".
 	QueueType string `mapstructure:"queue-type"`
 }
 
@@ -732,6 +791,7 @@ func DefaultP2PConfig() *P2PConfig {
 		DialTimeout:             3 * time.Second,
 		TestDialFail:            false,
 		QueueType:               "priority",
+		UseLegacy:               false,
 	}
 }
 
@@ -882,15 +942,46 @@ func (cfg *MempoolConfig) ValidateBasic() error {
 
 // StateSyncConfig defines the configuration for the Tendermint state sync service
 type StateSyncConfig struct {
-	Enable              bool          `mapstructure:"enable"`
-	TempDir             string        `mapstructure:"temp-dir"`
-	RPCServers          []string      `mapstructure:"rpc-servers"`
-	TrustPeriod         time.Duration `mapstructure:"trust-period"`
-	TrustHeight         int64         `mapstructure:"trust-height"`
-	TrustHash           string        `mapstructure:"trust-hash"`
-	DiscoveryTime       time.Duration `mapstructure:"discovery-time"`
+	// State sync rapidly bootstraps a new node by discovering, fetching, and restoring a
+	// state machine snapshot from peers instead of fetching and replaying historical
+	// blocks. Requires some peers in the network to take and serve state machine
+	// snapshots. State sync is not attempted if the node has any local state
+	// (LastBlockHeight > 0). The node will have a truncated block history, starting from
+	// the height of the snapshot.
+	Enable bool `mapstructure:"enable"`
+
+	// State sync uses light client verification to verify state. This can be done either
+	// through the P2P layer or the RPC layer. Set this to true to use the P2P layer. If
+	// false (default), the RPC layer will be used.
+	UseP2P bool `mapstructure:"use-p2p"`
+
+	// If using RPC, at least two addresses need to be provided. They should be compatible
+	// with net.Dial, for example: "host.example.com:2125".
+	RPCServers []string `mapstructure:"rpc-servers"`
+
+	// The hash and height of a trusted block. Must be within the trust-period.
+	TrustHeight int64  `mapstructure:"trust-height"`
+	TrustHash   string `mapstructure:"trust-hash"`
+
+	// The trust period should be set so that Tendermint can detect and gossip
+	// misbehavior before it is considered expired. For chains based on the Cosmos SDK,
+	// one day less than the unbonding period should suffice.
+	TrustPeriod time.Duration `mapstructure:"trust-period"`
+
+	// Time to spend discovering snapshots before initiating a restore.
+	DiscoveryTime time.Duration `mapstructure:"discovery-time"`
+
+	// Temporary directory for state sync snapshot chunks, defaults to os.TempDir().
+	// The synchronizer will create a new, randomly named directory within this directory
+	// and remove it when the sync is complete.
+	TempDir string `mapstructure:"temp-dir"`
+
+	// The timeout duration before re-requesting a chunk, possibly from a different
+	// peer (default: 15 seconds).
 	ChunkRequestTimeout time.Duration `mapstructure:"chunk-request-timeout"`
-	Fetchers            int32         `mapstructure:"fetchers"`
+
+	// The number of concurrent chunk and block fetchers to run (default: 4).
+	Fetchers int32 `mapstructure:"fetchers"`
 }
 
 func (cfg *StateSyncConfig) TrustHashBytes() []byte {
@@ -919,49 +1010,51 @@ func TestStateSyncConfig() *StateSyncConfig {
 
 // ValidateBasic performs basic validation.
 func (cfg *StateSyncConfig) ValidateBasic() error {
-	if cfg.Enable {
-		if len(cfg.RPCServers) == 0 {
-			return errors.New("rpc-servers is required")
-		}
+	if !cfg.Enable {
+		return nil
+	}
 
+	// If we're not using the P2P stack then we need to validate the
+	// RPCServers
+	if !cfg.UseP2P {
 		if len(cfg.RPCServers) < 2 {
-			return errors.New("at least two rpc-servers entries is required")
+			return errors.New("at least two rpc-servers must be specified")
 		}
 
 		for _, server := range cfg.RPCServers {
-			if len(server) == 0 {
+			if server == "" {
 				return errors.New("found empty rpc-servers entry")
 			}
 		}
+	}
 
-		if cfg.DiscoveryTime != 0 && cfg.DiscoveryTime < 5*time.Second {
-			return errors.New("discovery time must be 0s or greater than five seconds")
-		}
+	if cfg.DiscoveryTime != 0 && cfg.DiscoveryTime < 5*time.Second {
+		return errors.New("discovery time must be 0s or greater than five seconds")
+	}
 
-		if cfg.TrustPeriod <= 0 {
-			return errors.New("trusted-period is required")
-		}
+	if cfg.TrustPeriod <= 0 {
+		return errors.New("trusted-period is required")
+	}
 
-		if cfg.TrustHeight <= 0 {
-			return errors.New("trusted-height is required")
-		}
+	if cfg.TrustHeight <= 0 {
+		return errors.New("trusted-height is required")
+	}
 
-		if len(cfg.TrustHash) == 0 {
-			return errors.New("trusted-hash is required")
-		}
+	if len(cfg.TrustHash) == 0 {
+		return errors.New("trusted-hash is required")
+	}
 
-		_, err := hex.DecodeString(cfg.TrustHash)
-		if err != nil {
-			return fmt.Errorf("invalid trusted-hash: %w", err)
-		}
+	_, err := hex.DecodeString(cfg.TrustHash)
+	if err != nil {
+		return fmt.Errorf("invalid trusted-hash: %w", err)
+	}
 
-		if cfg.ChunkRequestTimeout < 5*time.Second {
-			return errors.New("chunk-request-timeout must be at least 5 seconds")
-		}
+	if cfg.ChunkRequestTimeout < 5*time.Second {
+		return errors.New("chunk-request-timeout must be at least 5 seconds")
+	}
 
-		if cfg.Fetchers <= 0 {
-			return errors.New("fetchers is required")
-		}
+	if cfg.Fetchers <= 0 {
+		return errors.New("fetchers is required")
 	}
 
 	return nil
@@ -970,13 +1063,18 @@ func (cfg *StateSyncConfig) ValidateBasic() error {
 //-----------------------------------------------------------------------------
 
 // BlockSyncConfig (formerly known as FastSync) defines the configuration for the Tendermint block sync service
+// If this node is many blocks behind the tip of the chain, BlockSync
+// allows them to catchup quickly by downloading blocks in parallel
+// and verifying their commits.
 type BlockSyncConfig struct {
+	Enable  bool   `mapstructure:"enable"`
 	Version string `mapstructure:"version"`
 }
 
 // DefaultBlockSyncConfig returns a default configuration for the block sync service
 func DefaultBlockSyncConfig() *BlockSyncConfig {
 	return &BlockSyncConfig{
+		Enable:  true,
 		Version: BlockSyncV0,
 	}
 }

config/config_test.go

@@ -138,7 +138,6 @@ func TestBlockSyncConfigValidateBasic(t *testing.T) {
 }
 
 func TestConsensusConfig_ValidateBasic(t *testing.T) {
-	// nolint: lll
 	testcases := map[string]struct {
 		modify    func(*ConsensusConfig)
 		expectErr bool

config/db.go

@@ -1,9 +1,10 @@
 package config
 
 import (
+	dbm "github.com/tendermint/tm-db"
+
 	"github.com/tendermint/tendermint/libs/log"
 	"github.com/tendermint/tendermint/libs/service"
-	db "github.com/tendermint/tm-db"
 )
 
 // ServiceProvider takes a config and a logger and returns a ready to go Node.
@@ -16,11 +17,11 @@ type DBContext struct {
 }
 
 // DBProvider takes a DBContext and returns an instantiated DB.
-type DBProvider func(*DBContext) (db.DB, error)
+type DBProvider func(*DBContext) (dbm.DB, error)
 
 // DefaultDBProvider returns a database using the DBBackend and DBDir
 // specified in the Config.
-func DefaultDBProvider(ctx *DBContext) (db.DB, error) {
-	dbType := db.BackendType(ctx.Config.DBBackend)
-	return db.NewDB(ctx.ID, dbType, ctx.Config.DBDir())
+func DefaultDBProvider(ctx *DBContext) (dbm.DB, error) {
+	dbType := dbm.BackendType(ctx.Config.DBBackend)
+	return dbm.NewDB(ctx.ID, dbType, ctx.Config.DBDir())
 }

config/toml.go

@@ -45,23 +45,29 @@ func EnsureRoot(rootDir string) {
 
 // WriteConfigFile renders config using the template and writes it to configFilePath.
 // This function is called by cmd/tendermint/commands/init.go
-func WriteConfigFile(rootDir string, config *Config) {
-	var buffer bytes.Buffer
-
-	if err := configTemplate.Execute(&buffer, config); err != nil {
-		panic(err)
-	}
-
-	configFilePath := filepath.Join(rootDir, defaultConfigFilePath)
-
-	mustWriteFile(configFilePath, buffer.Bytes(), 0644)
+func WriteConfigFile(rootDir string, config *Config) error {
+	return config.WriteToTemplate(filepath.Join(rootDir, defaultConfigFilePath))
 }
 
-func writeDefaultConfigFileIfNone(rootDir string) {
+// WriteToTemplate writes the config to the exact file specified by
+// the path, in the default toml template and does not mangle the path
+// or filename at all.
+func (cfg *Config) WriteToTemplate(path string) error {
+	var buffer bytes.Buffer
+
+	if err := configTemplate.Execute(&buffer, cfg); err != nil {
+		return err
+	}
+
+	return writeFile(path, buffer.Bytes(), 0644)
+}
+
+func writeDefaultConfigFileIfNone(rootDir string) error {
 	configFilePath := filepath.Join(rootDir, defaultConfigFilePath)
 	if !tmos.FileExists(configFilePath) {
-		WriteConfigFile(rootDir, DefaultConfig())
+		return WriteConfigFile(rootDir, DefaultConfig())
 	}
+	return nil
 }
 
 // Note: any changes to the comments/variables/mapstructure
@@ -97,11 +103,6 @@ moniker = "{{ .BaseConfig.Moniker }}"
 #   - No priv_validator_key.json, priv_validator_state.json
 mode = "{{ .BaseConfig.Mode }}"
 
-# If this node is many blocks behind the tip of the chain, FastSync
-# allows them to catchup quickly by downloading blocks in parallel
-# and verifying their commits
-fast-sync = {{ .BaseConfig.FastSyncMode }}
-
 # Database backend: goleveldb | cleveldb | boltdb | rocksdb | badgerdb
 # * goleveldb (github.com/syndtr/goleveldb - most popular implementation)
 #   - pure go
@@ -164,15 +165,15 @@ state-file = "{{ js .PrivValidator.State }}"
 # when the listenAddr is prefixed with grpc instead of tcp it will use the gRPC Client
 laddr = "{{ .PrivValidator.ListenAddr }}"
 
-# Client certificate generated while creating needed files for secure connection.
+# Path to the client certificate generated while creating needed files for secure connection.
 # If a remote validator address is provided but no certificate, the connection will be insecure
 client-certificate-file = "{{ js .PrivValidator.ClientCertificate }}"
 
 # Client key generated while creating certificates for secure connection
-validator-client-key-file = "{{ js .PrivValidator.ClientKey }}"
+client-key-file = "{{ js .PrivValidator.ClientKey }}"
 
-# Path Root Certificate Authority used to sign both client and server certificates
-certificate-authority = "{{ js .PrivValidator.RootCA }}"
+# Path to the Root Certificate Authority used to sign both client and server certificates
+root-ca-file = "{{ js .PrivValidator.RootCA }}"
 
 
 #######################################################################
@@ -235,6 +236,33 @@ max-subscription-clients = {{ .RPC.MaxSubscriptionClients }}
 # the estimated # maximum number of broadcast_tx_commit calls per block.
 max-subscriptions-per-client = {{ .RPC.MaxSubscriptionsPerClient }}
 
+# Experimental parameter to specify the maximum number of events a node will
+# buffer, per subscription, before returning an error and closing the
+# subscription. Must be set to at least 100, but higher values will accommodate
+# higher event throughput rates (and will use more memory).
+experimental-subscription-buffer-size = {{ .RPC.SubscriptionBufferSize }}
+
+# Experimental parameter to specify the maximum number of RPC responses that
+# can be buffered per WebSocket client. If clients cannot read from the
+# WebSocket endpoint fast enough, they will be disconnected, so increasing this
+# parameter may reduce the chances of them being disconnected (but will cause
+# the node to use more memory).
+#
+# Must be at least the same as "experimental-subscription-buffer-size",
+# otherwise connections could be dropped unnecessarily. This value should
+# ideally be somewhat higher than "experimental-subscription-buffer-size" to
+# accommodate non-subscription-related RPC responses.
+experimental-websocket-write-buffer-size = {{ .RPC.WebSocketWriteBufferSize }}
+
+# If a WebSocket client cannot read fast enough, at present we may
+# silently drop events instead of generating an error or disconnecting the
+# client.
+#
+# Enabling this experimental parameter will cause the WebSocket connection to
+# be closed instead if it cannot read fast enough, allowing for greater
+# predictability in subscription behavior.
+experimental-close-on-slow-client = {{ .RPC.CloseOnSlowClient }}
+
 # How long to wait for a tx to be committed during /broadcast_tx_commit.
 # WARNING: Using a value larger than 10s will result in increasing the
 # global HTTP write timeout, which applies to all connections and endpoints.
@@ -270,8 +298,8 @@ pprof-laddr = "{{ .RPC.PprofListenAddress }}"
 #######################################################
 [p2p]
 
-# Enable the new p2p layer.
-disable-legacy = {{ .P2P.DisableLegacy }}
+# Enable the legacy p2p layer.
+use-legacy = {{ .P2P.UseLegacy }}
 
 # Select the p2p internal queue
 queue-type = "{{ .P2P.QueueType }}"
@@ -305,6 +333,7 @@ persistent-peers = "{{ .P2P.PersistentPeers }}"
 upnp = {{ .P2P.UPNP }}
 
 # Path to address book
+# TODO: Remove once p2p refactor is complete in favor of peer store.
 addr-book-file = "{{ js .P2P.AddrBook }}"
 
 # Set true for strict address routability rules
@@ -330,21 +359,33 @@ max-connections = {{ .P2P.MaxConnections }}
 max-incoming-connection-attempts = {{ .P2P.MaxIncomingConnectionAttempts }}
 
 # List of node IDs, to which a connection will be (re)established ignoring any existing limits
+# TODO: Remove once p2p refactor is complete.
+# ref: https://github.com/tendermint/tendermint/issues/5670
 unconditional-peer-ids = "{{ .P2P.UnconditionalPeerIDs }}"
 
 # Maximum pause when redialing a persistent peer (if zero, exponential backoff is used)
+# TODO: Remove once p2p refactor is complete
+# ref: https:#github.com/tendermint/tendermint/issues/5670
 persistent-peers-max-dial-period = "{{ .P2P.PersistentPeersMaxDialPeriod }}"
 
 # Time to wait before flushing messages out on the connection
+# TODO: Remove once p2p refactor is complete
+# ref: https:#github.com/tendermint/tendermint/issues/5670
 flush-throttle-timeout = "{{ .P2P.FlushThrottleTimeout }}"
 
 # Maximum size of a message packet payload, in bytes
+# TODO: Remove once p2p refactor is complete
+# ref: https:#github.com/tendermint/tendermint/issues/5670
 max-packet-msg-payload-size = {{ .P2P.MaxPacketMsgPayloadSize }}
 
 # Rate at which packets can be sent, in bytes/second
+# TODO: Remove once p2p refactor is complete
+# ref: https:#github.com/tendermint/tendermint/issues/5670
 send-rate = {{ .P2P.SendRate }}
 
 # Rate at which packets can be received, in bytes/second
+# TODO: Remove once p2p refactor is complete
+# ref: https:#github.com/tendermint/tendermint/issues/5670
 recv-rate = {{ .P2P.RecvRate }}
 
 # Set true to enable the peer-exchange reactor
@@ -426,22 +467,30 @@ ttl-num-blocks = {{ .Mempool.TTLNumBlocks }}
 # starting from the height of the snapshot.
 enable = {{ .StateSync.Enable }}
 
-# RPC servers (comma-separated) for light client verification of the synced state machine and
-# retrieval of state data for node bootstrapping. Also needs a trusted height and corresponding
-# header hash obtained from a trusted source, and a period during which validators can be trusted.
-#
-# For Cosmos SDK-based chains, trust-period should usually be about 2/3 of the unbonding time (~2
-# weeks) during which they can be financially punished (slashed) for misbehavior.
+# State sync uses light client verification to verify state. This can be done either through the
+# P2P layer or RPC layer. Set this to true to use the P2P layer. If false (default), RPC layer
+# will be used.
+use-p2p = {{ .StateSync.UseP2P }}
+
+# If using RPC, at least two addresses need to be provided. They should be compatible with net.Dial,
+# for example: "host.example.com:2125"
 rpc-servers = "{{ StringsJoin .StateSync.RPCServers "," }}"
+
+# The hash and height of a trusted block. Must be within the trust-period.
 trust-height = {{ .StateSync.TrustHeight }}
 trust-hash = "{{ .StateSync.TrustHash }}"
+
+# The trust period should be set so that Tendermint can detect and gossip misbehavior before
+# it is considered expired. For chains based on the Cosmos SDK, one day less than the unbonding
+# period should suffice.
 trust-period = "{{ .StateSync.TrustPeriod }}"
 
 # Time to spend discovering snapshots before initiating a restore.
 discovery-time = "{{ .StateSync.DiscoveryTime }}"
 
-# Temporary directory for state sync snapshot chunks, defaults to the OS tempdir (typically /tmp).
-# Will create a new, randomly named directory within, and remove it when done.
+# Temporary directory for state sync snapshot chunks, defaults to os.TempDir().
+# The synchronizer will create a new, randomly named directory within this directory
+# and remove it when the sync is complete.
 temp-dir = "{{ .StateSync.TempDir }}"
 
 # The timeout duration before re-requesting a chunk, possibly from a different
@@ -454,10 +503,15 @@ fetchers = "{{ .StateSync.Fetchers }}"
 #######################################################
 ###       Block Sync Configuration Connections       ###
 #######################################################
-[fastsync]
+[blocksync]
+
+# If this node is many blocks behind the tip of the chain, BlockSync
+# allows them to catchup quickly by downloading blocks in parallel
+# and verifying their commits
+enable = {{ .BlockSync.Enable }}
 
 # Block Sync version to use:
-#   1) "v0" (default) - the legacy block sync implementation
+#   1) "v0" (default) - the standard Block Sync implementation
 #   2) "v2" - DEPRECATED, please use v0
 version = "{{ .BlockSync.Version }}"
 
@@ -508,7 +562,7 @@ peer-query-maj23-sleep-duration = "{{ .Consensus.PeerQueryMaj23SleepDuration }}"
 [tx-index]
 
 # The backend database list to back the indexer.
-# If list contains null, meaning no indexer service will be used.
+# If list contains "null" or "", meaning no indexer service will be used.
 #
 # The application will set which txs to index. In some cases a node operator will be able
 # to decide which txs to index based on configuration set in the application.
@@ -516,8 +570,8 @@ peer-query-maj23-sleep-duration = "{{ .Consensus.PeerQueryMaj23SleepDuration }}"
 # Options:
 #   1) "null"
 #   2) "kv" (default) - the simplest possible indexer, backed by key-value storage (defaults to levelDB; see DBBackend).
-# 		- When "kv" is chosen "tx.height" and "tx.hash" will always be indexed.
 #   3) "psql" - the indexer services backed by PostgreSQL.
+# When "kv" or "psql" is chosen "tx.height" and "tx.hash" will always be indexed.
 indexer = [{{ range $i, $e := .TxIndex.Indexer }}{{if $i}}, {{end}}{{ printf "%q" $e}}{{end}}]
 
 # The PostgreSQL connection configuration, the connection format:
@@ -549,22 +603,22 @@ namespace = "{{ .Instrumentation.Namespace }}"
 
 /****** these are for test settings ***********/
 
-func ResetTestRoot(testName string) *Config {
+func ResetTestRoot(testName string) (*Config, error) {
 	return ResetTestRootWithChainID(testName, "")
 }
 
-func ResetTestRootWithChainID(testName string, chainID string) *Config {
+func ResetTestRootWithChainID(testName string, chainID string) (*Config, error) {
 	// create a unique, concurrency-safe test directory under os.TempDir()
 	rootDir, err := ioutil.TempDir("", fmt.Sprintf("%s-%s_", chainID, testName))
 	if err != nil {
-		panic(err)
+		return nil, err
 	}
 	// ensure config and data subdirs are created
 	if err := tmos.EnsureDir(filepath.Join(rootDir, defaultConfigDir), DefaultDirPerm); err != nil {
-		panic(err)
+		return nil, err
 	}
 	if err := tmos.EnsureDir(filepath.Join(rootDir, defaultDataDir), DefaultDirPerm); err != nil {
-		panic(err)
+		return nil, err
 	}
 
 	conf := DefaultConfig()
@@ -573,26 +627,36 @@ func ResetTestRootWithChainID(testName string, chainID string) *Config {
 	privStateFilePath := filepath.Join(rootDir, conf.PrivValidator.State)
 
 	// Write default config file if missing.
-	writeDefaultConfigFileIfNone(rootDir)
+	if err := writeDefaultConfigFileIfNone(rootDir); err != nil {
+		return nil, err
+	}
+
 	if !tmos.FileExists(genesisFilePath) {
 		if chainID == "" {
 			chainID = "tendermint_test"
 		}
 		testGenesis := fmt.Sprintf(testGenesisFmt, chainID)
-		mustWriteFile(genesisFilePath, []byte(testGenesis), 0644)
+		if err := writeFile(genesisFilePath, []byte(testGenesis), 0644); err != nil {
+			return nil, err
+		}
 	}
 	// we always overwrite the priv val
-	mustWriteFile(privKeyFilePath, []byte(testPrivValidatorKey), 0644)
-	mustWriteFile(privStateFilePath, []byte(testPrivValidatorState), 0644)
+	if err := writeFile(privKeyFilePath, []byte(testPrivValidatorKey), 0644); err != nil {
+		return nil, err
+	}
+	if err := writeFile(privStateFilePath, []byte(testPrivValidatorState), 0644); err != nil {
+		return nil, err
+	}
 
 	config := TestConfig().SetRoot(rootDir)
-	return config
+	return config, nil
 }
 
-func mustWriteFile(filePath string, contents []byte, mode os.FileMode) {
+func writeFile(filePath string, contents []byte, mode os.FileMode) error {
 	if err := ioutil.WriteFile(filePath, contents, mode); err != nil {
-		tmos.Exit(fmt.Sprintf("failed to write file: %v", err))
+		return fmt.Errorf("failed to write file: %w", err)
 	}
+	return nil
 }
 
 var testGenesisFmt = `{

config/toml_test.go

@@ -24,21 +24,19 @@ func TestEnsureRoot(t *testing.T) {
 
 	// setup temp dir for test
 	tmpDir, err := ioutil.TempDir("", "config-test")
-	require.Nil(err)
+	require.NoError(err)
 	defer os.RemoveAll(tmpDir)
 
 	// create root dir
 	EnsureRoot(tmpDir)
 
-	WriteConfigFile(tmpDir, DefaultConfig())
+	require.NoError(WriteConfigFile(tmpDir, DefaultConfig()))
 
 	// make sure config is set properly
 	data, err := ioutil.ReadFile(filepath.Join(tmpDir, defaultConfigFilePath))
-	require.Nil(err)
+	require.NoError(err)
 
-	if !checkConfig(string(data)) {
-		t.Fatalf("config file missing some information")
-	}
+	checkConfig(t, string(data))
 
 	ensureFiles(t, tmpDir, "data")
 }
@@ -49,7 +47,8 @@ func TestEnsureTestRoot(t *testing.T) {
 	testName := "ensureTestRoot"
 
 	// create root dir
-	cfg := ResetTestRoot(testName)
+	cfg, err := ResetTestRoot(testName)
+	require.NoError(err)
 	defer os.RemoveAll(cfg.RootDir)
 	rootDir := cfg.RootDir
 
@@ -57,9 +56,7 @@ func TestEnsureTestRoot(t *testing.T) {
 	data, err := ioutil.ReadFile(filepath.Join(rootDir, defaultConfigFilePath))
 	require.Nil(err)
 
-	if !checkConfig(string(data)) {
-		t.Fatalf("config file missing some information")
-	}
+	checkConfig(t, string(data))
 
 	// TODO: make sure the cfg returned and testconfig are the same!
 	baseConfig := DefaultBaseConfig()
@@ -67,16 +64,15 @@ func TestEnsureTestRoot(t *testing.T) {
 	ensureFiles(t, rootDir, defaultDataDir, baseConfig.Genesis, pvConfig.Key, pvConfig.State)
 }
 
-func checkConfig(configFile string) bool {
-	var valid bool
-
+func checkConfig(t *testing.T, configFile string) {
+	t.Helper()
 	// list of words we expect in the config
 	var elems = []string{
 		"moniker",
 		"seeds",
 		"proxy-app",
-		"fast_sync",
-		"create_empty_blocks",
+		"blocksync",
+		"create-empty-blocks",
 		"peer",
 		"timeout",
 		"broadcast",
@@ -89,10 +85,7 @@ func checkConfig(configFile string) bool {
 	}
 	for _, e := range elems {
 		if !strings.Contains(configFile, e) {
-			valid = false
-		} else {
-			valid = true
+			t.Errorf("config file was expected to contain %s but did not", e)
 		}
 	}
-	return valid
 }

crypto/armor/armor.go

@@ -1,39 +0,0 @@
-package armor
-
-import (
-	"bytes"
-	"fmt"
-	"io/ioutil"
-
-	"golang.org/x/crypto/openpgp/armor"
-)
-
-func EncodeArmor(blockType string, headers map[string]string, data []byte) string {
-	buf := new(bytes.Buffer)
-	w, err := armor.Encode(buf, blockType, headers)
-	if err != nil {
-		panic(fmt.Errorf("could not encode ascii armor: %s", err))
-	}
-	_, err = w.Write(data)
-	if err != nil {
-		panic(fmt.Errorf("could not encode ascii armor: %s", err))
-	}
-	err = w.Close()
-	if err != nil {
-		panic(fmt.Errorf("could not encode ascii armor: %s", err))
-	}
-	return buf.String()
-}
-
-func DecodeArmor(armorStr string) (blockType string, headers map[string]string, data []byte, err error) {
-	buf := bytes.NewBufferString(armorStr)
-	block, err := armor.Decode(buf)
-	if err != nil {
-		return "", nil, nil, err
-	}
-	data, err = ioutil.ReadAll(block.Body)
-	if err != nil {
-		return "", nil, nil, err
-	}
-	return block.Type, block.Header, data, nil
-}

crypto/armor/armor_test.go

@@ -1,20 +0,0 @@
-package armor
-
-import (
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-)
-
-func TestArmor(t *testing.T) {
-	blockType := "MINT TEST"
-	data := []byte("somedata")
-	armorStr := EncodeArmor(blockType, nil, data)
-
-	// Decode armorStr and test for equivalence.
-	blockType2, _, data2, err := DecodeArmor(armorStr)
-	require.Nil(t, err, "%+v", err)
-	assert.Equal(t, blockType, blockType2)
-	assert.Equal(t, data, data2)
-}

crypto/encoding/codec.go

@@ -8,34 +8,34 @@ import (
 	"github.com/tendermint/tendermint/crypto/secp256k1"
 	"github.com/tendermint/tendermint/crypto/sr25519"
 	"github.com/tendermint/tendermint/libs/json"
-	pc "github.com/tendermint/tendermint/proto/tendermint/crypto"
+	cryptoproto "github.com/tendermint/tendermint/proto/tendermint/crypto"
 )
 
 func init() {
-	json.RegisterType((*pc.PublicKey)(nil), "tendermint.crypto.PublicKey")
-	json.RegisterType((*pc.PublicKey_Ed25519)(nil), "tendermint.crypto.PublicKey_Ed25519")
-	json.RegisterType((*pc.PublicKey_Secp256K1)(nil), "tendermint.crypto.PublicKey_Secp256K1")
+	json.RegisterType((*cryptoproto.PublicKey)(nil), "tendermint.crypto.PublicKey")
+	json.RegisterType((*cryptoproto.PublicKey_Ed25519)(nil), "tendermint.crypto.PublicKey_Ed25519")
+	json.RegisterType((*cryptoproto.PublicKey_Secp256K1)(nil), "tendermint.crypto.PublicKey_Secp256K1")
 }
 
 // PubKeyToProto takes crypto.PubKey and transforms it to a protobuf Pubkey
-func PubKeyToProto(k crypto.PubKey) (pc.PublicKey, error) {
-	var kp pc.PublicKey
+func PubKeyToProto(k crypto.PubKey) (cryptoproto.PublicKey, error) {
+	var kp cryptoproto.PublicKey
 	switch k := k.(type) {
 	case ed25519.PubKey:
-		kp = pc.PublicKey{
-			Sum: &pc.PublicKey_Ed25519{
+		kp = cryptoproto.PublicKey{
+			Sum: &cryptoproto.PublicKey_Ed25519{
 				Ed25519: k,
 			},
 		}
 	case secp256k1.PubKey:
-		kp = pc.PublicKey{
-			Sum: &pc.PublicKey_Secp256K1{
+		kp = cryptoproto.PublicKey{
+			Sum: &cryptoproto.PublicKey_Secp256K1{
 				Secp256K1: k,
 			},
 		}
 	case sr25519.PubKey:
-		kp = pc.PublicKey{
-			Sum: &pc.PublicKey_Sr25519{
+		kp = cryptoproto.PublicKey{
+			Sum: &cryptoproto.PublicKey_Sr25519{
 				Sr25519: k,
 			},
 		}
@@ -46,9 +46,9 @@ func PubKeyToProto(k crypto.PubKey) (pc.PublicKey, error) {
 }
 
 // PubKeyFromProto takes a protobuf Pubkey and transforms it to a crypto.Pubkey
-func PubKeyFromProto(k pc.PublicKey) (crypto.PubKey, error) {
+func PubKeyFromProto(k cryptoproto.PublicKey) (crypto.PubKey, error) {
 	switch k := k.Sum.(type) {
-	case *pc.PublicKey_Ed25519:
+	case *cryptoproto.PublicKey_Ed25519:
 		if len(k.Ed25519) != ed25519.PubKeySize {
 			return nil, fmt.Errorf("invalid size for PubKeyEd25519. Got %d, expected %d",
 				len(k.Ed25519), ed25519.PubKeySize)
@@ -56,7 +56,7 @@ func PubKeyFromProto(k pc.PublicKey) (crypto.PubKey, error) {
 		pk := make(ed25519.PubKey, ed25519.PubKeySize)
 		copy(pk, k.Ed25519)
 		return pk, nil
-	case *pc.PublicKey_Secp256K1:
+	case *cryptoproto.PublicKey_Secp256K1:
 		if len(k.Secp256K1) != secp256k1.PubKeySize {
 			return nil, fmt.Errorf("invalid size for PubKeySecp256k1. Got %d, expected %d",
 				len(k.Secp256K1), secp256k1.PubKeySize)
@@ -64,7 +64,7 @@ func PubKeyFromProto(k pc.PublicKey) (crypto.PubKey, error) {
 		pk := make(secp256k1.PubKey, secp256k1.PubKeySize)
 		copy(pk, k.Secp256K1)
 		return pk, nil
-	case *pc.PublicKey_Sr25519:
+	case *cryptoproto.PublicKey_Sr25519:
 		if len(k.Sr25519) != sr25519.PubKeySize {
 			return nil, fmt.Errorf("invalid size for PubKeySr25519. Got %d, expected %d",
 				len(k.Sr25519), sr25519.PubKeySize)

crypto/secp256k1/secp256k1_nocgo.go

@@ -1,3 +1,4 @@
+//go:build !libsecp256k1
 // +build !libsecp256k1
 
 package secp256k1

crypto/secp256k1/secp256k1_test.go

@@ -5,14 +5,13 @@ import (
 	"math/big"
 	"testing"
 
+	underlyingSecp256k1 "github.com/btcsuite/btcd/btcec"
 	"github.com/btcsuite/btcutil/base58"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 
 	"github.com/tendermint/tendermint/crypto"
 	"github.com/tendermint/tendermint/crypto/secp256k1"
-
-	underlyingSecp256k1 "github.com/btcsuite/btcd/btcec"
 )
 
 type keyData struct {
@@ -36,8 +35,7 @@ func TestPubKeySecp256k1Address(t *testing.T) {
 		addrBbz, _, _ := base58.CheckDecode(d.addr)
 		addrB := crypto.Address(addrBbz)
 
-		var priv secp256k1.PrivKey = secp256k1.PrivKey(privB)
-
+		priv := secp256k1.PrivKey(privB)
 		pubKey := priv.PubKey()
 		pubT, _ := pubKey.(secp256k1.PubKey)
 		pub := pubT

crypto/xchacha20poly1305/xchachapoly_test.go

@@ -2,8 +2,8 @@ package xchacha20poly1305
 
 import (
 	"bytes"
-	cr "crypto/rand"
-	mr "math/rand"
+	crand "crypto/rand"
+	mrand "math/rand"
 	"testing"
 )
 
@@ -19,23 +19,23 @@ func TestRandom(t *testing.T) {
 		var nonce [24]byte
 		var key [32]byte
 
-		al := mr.Intn(128)
-		pl := mr.Intn(16384)
+		al := mrand.Intn(128)
+		pl := mrand.Intn(16384)
 		ad := make([]byte, al)
 		plaintext := make([]byte, pl)
-		_, err := cr.Read(key[:])
+		_, err := crand.Read(key[:])
 		if err != nil {
 			t.Errorf("error on read: %w", err)
 		}
-		_, err = cr.Read(nonce[:])
+		_, err = crand.Read(nonce[:])
 		if err != nil {
 			t.Errorf("error on read: %w", err)
 		}
-		_, err = cr.Read(ad)
+		_, err = crand.Read(ad)
 		if err != nil {
 			t.Errorf("error on read: %w", err)
 		}
-		_, err = cr.Read(plaintext)
+		_, err = crand.Read(plaintext)
 		if err != nil {
 			t.Errorf("error on read: %w", err)
 		}
@@ -59,7 +59,7 @@ func TestRandom(t *testing.T) {
 		}
 
 		if len(ad) > 0 {
-			alterAdIdx := mr.Intn(len(ad))
+			alterAdIdx := mrand.Intn(len(ad))
 			ad[alterAdIdx] ^= 0x80
 			if _, err := aead.Open(nil, nonce[:], ct, ad); err == nil {
 				t.Errorf("random #%d: Open was successful after altering additional data", i)
@@ -67,14 +67,14 @@ func TestRandom(t *testing.T) {
 			ad[alterAdIdx] ^= 0x80
 		}
 
-		alterNonceIdx := mr.Intn(aead.NonceSize())
+		alterNonceIdx := mrand.Intn(aead.NonceSize())
 		nonce[alterNonceIdx] ^= 0x80
 		if _, err := aead.Open(nil, nonce[:], ct, ad); err == nil {
 			t.Errorf("random #%d: Open was successful after altering nonce", i)
 		}
 		nonce[alterNonceIdx] ^= 0x80
 
-		alterCtIdx := mr.Intn(len(ct))
+		alterCtIdx := mrand.Intn(len(ct))
 		ct[alterCtIdx] ^= 0x80
 		if _, err := aead.Open(nil, nonce[:], ct, ad); err == nil {
 			t.Errorf("random #%d: Open was successful after altering ciphertext", i)

docs/.vuepress/config.js

@@ -34,6 +34,10 @@ module.exports = {
         "label": "v0.34",
         "key": "v0.34"
       },
+      {
+        "label": "v0.35",
+        "key": "v0.35"
+      },
       {
         "label": "master",
         "key": "master"
@@ -78,7 +82,7 @@ module.exports = {
     },
     footer: {
       question: {
-        text: 'Chat with Tendermint developers in <a href=\'https://discord.gg/vcExX9T\' target=\'_blank\'>Discord</a> or reach out on the <a href=\'https://forum.cosmos.network/c/tendermint\' target=\'_blank\'>Tendermint Forum</a> to learn more.'
+        text: 'Chat with Tendermint developers in <a href=\'https://discord.gg/cosmosnetwork\' target=\'_blank\'>Discord</a> or reach out on the <a href=\'https://forum.cosmos.network/c/tendermint\' target=\'_blank\'>Tendermint Forum</a> to learn more.'
       },
       logo: '/logo-bw.svg',
       textLink: {

docs/DOCS_README.md

@@ -2,17 +2,27 @@
 
 The documentation for Tendermint Core is hosted at:
 
-- <https://docs.tendermint.com/master/>
+- <https://docs.tendermint.com/>
 
-built from the files in this (`/docs`) directory for
-[master](https://github.com/tendermint/tendermint/tree/master/docs) respectively.
+built from the files in this [`docs` directory for `master`](https://github.com/tendermint/tendermint/tree/master/docs)
+and other supported release branches.
 
 ## How It Works
 
-There is a CircleCI job listening for changes in the `/docs` directory, on both
-the `master` branch. Any updates to files in this directory
-on those branches will automatically trigger a website deployment. Under the hood,
-the private website repository has a `make build-docs` target consumed by a CircleCI job in that repo.
+There is a [GitHub Actions workflow](https://github.com/tendermint/docs/actions/workflows/deployment.yml)
+in the `tendermint/docs` repository that clones and builds the documentation
+site from the contents of this `docs` directory, for `master` and for each
+supported release branch. Under the hood, this workflow runs `make build-docs`
+from the [Makefile](../Makefile#L214).
+
+The list of supported versions are defined in [`config.js`](./.vuepress/config.js),
+which defines the UI menu on the documentation site, and also in
+[`docs/versions`](./versions), which determines which branches are built.
+
+The last entry in the `docs/versions` file determines which version is linked
+by default from the generated `index.html`. This should generally be the most
+recent release, rather than `master`, so that new users are not confused by
+documentation for unreleased features.
 
 ## README
 

docs/app-dev/indexing-transactions.md

@@ -62,7 +62,7 @@ be turned off regardless of other values provided.
 #### KV
 
 The `kv` indexer type is an embedded key-value store supported by the main
-underling Tendermint database. Using the `kv` indexer type allows you to query
+underlying Tendermint database. Using the `kv` indexer type allows you to query
 for block and transaction events directly against Tendermint's RPC. However, the
 query syntax is limited and so this indexer type might be deprecated or removed
 entirely in the future.

docs/architecture/README.md

@@ -98,3 +98,5 @@ Note the context/background should be written in the present tense.
 - [ADR-045: ABCI-Evidence](./adr-045-abci-evidence.md)
 - [ADR-057: RPC](./adr-057-RPC.md)
 - [ADR-069: Node Initialization](./adr-069-flexible-node-initialization.md)
+- [ADR-071: Proposer-Based Timestamps](adr-071-proposer-based-timestamps.md)
+- [ADR-072: Restore Requests for Comments](./adr-072-request-for-comments.md)

docs/architecture/adr-065-custom-event-indexing.md

@@ -24,6 +24,7 @@
 - April 1, 2021: Initial Draft (@alexanderbez)
 - April 28, 2021: Specify search capabilities are only supported through the KV indexer (@marbar3778)
 - May 19, 2021: Update the SQL schema and the eventsink interface (@jayt106)
+- Aug 30, 2021: Update the SQL schema and the psql implementation (@creachadair)
 
 ## Status
 
@@ -145,163 +146,190 @@ The postgres eventsink will not support `tx_search`, `block_search`, `GetTxByHas
 ```sql
 -- Table Definition ----------------------------------------------
 
-CREATE TYPE block_event_type AS ENUM ('begin_block', 'end_block', '');
+-- The blocks table records metadata about each block.
+-- The block record does not include its events or transactions (see tx_results).
+CREATE TABLE blocks (
+  rowid      BIGSERIAL PRIMARY KEY,
 
-CREATE TABLE block_events (
-    id SERIAL PRIMARY KEY,
-    key VARCHAR NOT NULL,
-    value VARCHAR NOT NULL,
-    height INTEGER NOT NULL,
-    type block_event_type,
-    created_at TIMESTAMPTZ NOT NULL,
-    chain_id VARCHAR NOT NULL
+  height     BIGINT NOT NULL,
+  chain_id   VARCHAR NOT NULL,
+
+  -- When this block header was logged into the sink, in UTC.
+  created_at TIMESTAMPTZ NOT NULL,
+
+  UNIQUE (height, chain_id)
 );
 
+-- Index blocks by height and chain, since we need to resolve block IDs when
+-- indexing transaction records and transaction events.
+CREATE INDEX idx_blocks_height_chain ON blocks(height, chain_id);
+
+-- The tx_results table records metadata about transaction results.  Note that
+-- the events from a transaction are stored separately.
 CREATE TABLE tx_results (
-    id SERIAL PRIMARY KEY,
-    tx_result BYTEA NOT NULL,
-    created_at TIMESTAMPTZ NOT NULL
+  rowid BIGSERIAL PRIMARY KEY,
+
+  -- The block to which this transaction belongs.
+  block_id BIGINT NOT NULL REFERENCES blocks(rowid),
+  -- The sequential index of the transaction within the block.
+  index INTEGER NOT NULL,
+  -- When this result record was logged into the sink, in UTC.
+  created_at TIMESTAMPTZ NOT NULL,
+  -- The hex-encoded hash of the transaction.
+  tx_hash VARCHAR NOT NULL,
+  -- The protobuf wire encoding of the TxResult message.
+  tx_result BYTEA NOT NULL,
+
+  UNIQUE (block_id, index)
 );
 
-CREATE TABLE tx_events (
-    id SERIAL PRIMARY KEY,
-    key VARCHAR NOT NULL,
-    value VARCHAR NOT NULL,
-    height INTEGER NOT NULL,
-    hash VARCHAR NOT NULL,
-    tx_result_id SERIAL,
-    created_at TIMESTAMPTZ NOT NULL,
-    chain_id VARCHAR NOT NULL,
-    FOREIGN KEY (tx_result_id)
-        REFERENCES tx_results(id)
-        ON DELETE CASCADE
+-- The events table records events. All events (both block and transaction) are
+-- associated with a block ID; transaction events also have a transaction ID.
+CREATE TABLE events (
+  rowid BIGSERIAL PRIMARY KEY,
+
+  -- The block and transaction this event belongs to.
+  -- If tx_id is NULL, this is a block event.
+  block_id BIGINT NOT NULL REFERENCES blocks(rowid),
+  tx_id    BIGINT NULL REFERENCES tx_results(rowid),
+
+  -- The application-defined type label for the event.
+  type VARCHAR NOT NULL
 );
 
--- Indices -------------------------------------------------------
+-- The attributes table records event attributes.
+CREATE TABLE attributes (
+   event_id      BIGINT NOT NULL REFERENCES events(rowid),
+   key           VARCHAR NOT NULL, -- bare key
+   composite_key VARCHAR NOT NULL, -- composed type.key
+   value         VARCHAR NULL,
 
-CREATE INDEX idx_block_events_key_value ON block_events(key, value);
-CREATE INDEX idx_tx_events_key_value ON tx_events(key, value);
-CREATE INDEX idx_tx_events_hash ON tx_events(hash);
+   UNIQUE (event_id, key)
+);
+
+-- A joined view of events and their attributes. Events that do not have any
+-- attributes are represented as a single row with empty key and value fields.
+CREATE VIEW event_attributes AS
+  SELECT block_id, tx_id, type, key, composite_key, value
+  FROM events LEFT JOIN attributes ON (events.rowid = attributes.event_id);
+
+-- A joined view of all block events (those having tx_id NULL).
+CREATE VIEW block_events AS
+  SELECT blocks.rowid as block_id, height, chain_id, type, key, composite_key, value
+  FROM blocks JOIN event_attributes ON (blocks.rowid = event_attributes.block_id)
+  WHERE event_attributes.tx_id IS NULL;
+
+-- A joined view of all transaction events.
+CREATE VIEW tx_events AS
+  SELECT height, index, chain_id, type, key, composite_key, value, tx_results.created_at
+  FROM blocks JOIN tx_results ON (blocks.rowid = tx_results.block_id)
+  JOIN event_attributes ON (tx_results.rowid = event_attributes.tx_id)
+  WHERE event_attributes.tx_id IS NOT NULL;
 ```
 
 The `PSQLEventSink` will implement the `EventSink` interface as follows
 (some details omitted for brevity):
 
-
 ```go
-func NewPSQLEventSink(connStr string, chainID string) (*PSQLEventSink, error) {
-  db, err := sql.Open("postgres", connStr)
-  if err != nil {
-    return nil, err
-  }
+func NewEventSink(connStr, chainID string) (*EventSink, error) {
+	db, err := sql.Open(driverName, connStr)
+	// ...
 
-  // ...
+	return &EventSink{
+		store:   db,
+		chainID: chainID,
+	}, nil
 }
 
-func (es *PSQLEventSink) IndexBlockEvents(h types.EventDataNewBlockHeader) error {
-  sqlStmt := sq.Insert("block_events").Columns("key", "value", "height", "type", "created_at", "chain_id")
+func (es *EventSink) IndexBlockEvents(h types.EventDataNewBlockHeader) error {
+	ts := time.Now().UTC()
 
-  // index the reserved block height index
-  ts := time.Now()
-  sqlStmt = sqlStmt.Values(types.BlockHeightKey, h.Header.Height, h.Header.Height, "", ts, es.chainID)
+	return runInTransaction(es.store, func(tx *sql.Tx) error {
+		// Add the block to the blocks table and report back its row ID for use
+		// in indexing the events for the block.
+		blockID, err := queryWithID(tx, `
+INSERT INTO blocks (height, chain_id, created_at)
+  VALUES ($1, $2, $3)
+  ON CONFLICT DO NOTHING
+  RETURNING rowid;
+`, h.Header.Height, es.chainID, ts)
+		// ...
 
-  for _, event := range h.ResultBeginBlock.Events {
-    // only index events with a non-empty type
-    if len(event.Type) == 0 {
-      continue
-    }
-
-    for _, attr := range event.Attributes {
-      if len(attr.Key) == 0 {
-        continue
-      }
-
-      // index iff the event specified index:true and it's not a reserved event
-      compositeKey := fmt.Sprintf("%s.%s", event.Type, string(attr.Key))
-      if compositeKey == types.BlockHeightKey {
-        return fmt.Errorf("event type and attribute key \"%s\" is reserved; please use a different key", compositeKey)
-      }
-
-      if attr.GetIndex() {
-        sqlStmt = sqlStmt.Values(compositeKey, string(attr.Value), h.Header.Height, BlockEventTypeBeginBlock, ts, es.chainID)
-      }
-    }
-  }
-
-  // index end_block events...
-  // execute sqlStmt db query...
+		// Insert the special block meta-event for height.
+		if err := insertEvents(tx, blockID, 0, []abci.Event{
+			makeIndexedEvent(types.BlockHeightKey, fmt.Sprint(h.Header.Height)),
+		}); err != nil {
+			return fmt.Errorf("block meta-events: %w", err)
+		}
+		// Insert all the block events. Order is important here,
+		if err := insertEvents(tx, blockID, 0, h.ResultBeginBlock.Events); err != nil {
+			return fmt.Errorf("begin-block events: %w", err)
+		}
+		if err := insertEvents(tx, blockID, 0, h.ResultEndBlock.Events); err != nil {
+			return fmt.Errorf("end-block events: %w", err)
+		}
+		return nil
+	})
 }
 
-func (es *PSQLEventSink) IndexTxEvents(txr []*abci.TxResult) error {
-  sqlStmtEvents := sq.Insert("tx_events").Columns("key", "value", "height", "hash", "tx_result_id", "created_at", "chain_id")
-  sqlStmtTxResult := sq.Insert("tx_results").Columns("tx_result", "created_at")
+func (es *EventSink) IndexTxEvents(txrs []*abci.TxResult) error {
+	ts := time.Now().UTC()
 
-  ts := time.Now()
-  for _, tx := range txr {
-    // store the tx result
-    txBz, err := proto.Marshal(tx)
-    if err != nil {
-      return err
-    }
+	for _, txr := range txrs {
+		// Encode the result message in protobuf wire format for indexing.
+		resultData, err := proto.Marshal(txr)
+		// ...
 
-    sqlStmtTxResult = sqlStmtTxResult.Values(txBz, ts)
+		// Index the hash of the underlying transaction as a hex string.
+		txHash := fmt.Sprintf("%X", types.Tx(txr.Tx).Hash())
 
-    // execute sqlStmtTxResult db query...
-    var txID uint32
-    err = sqlStmtTxResult.QueryRow().Scan(&txID)
-		if err != nil {
+		if err := runInTransaction(es.store, func(tx *sql.Tx) error {
+			// Find the block associated with this transaction.
+			blockID, err := queryWithID(tx, `
+SELECT rowid FROM blocks WHERE height = $1 AND chain_id = $2;
+`, txr.Height, es.chainID)
+			// ...
+
+			// Insert a record for this tx_result and capture its ID for indexing events.
+			txID, err := queryWithID(tx, `
+INSERT INTO tx_results (block_id, index, created_at, tx_hash, tx_result)
+  VALUES ($1, $2, $3, $4, $5)
+  ON CONFLICT DO NOTHING
+  RETURNING rowid;
+`, blockID, txr.Index, ts, txHash, resultData)
+			// ...
+
+			// Insert the special transaction meta-events for hash and height.
+			if err := insertEvents(tx, blockID, txID, []abci.Event{
+				makeIndexedEvent(types.TxHashKey, txHash),
+				makeIndexedEvent(types.TxHeightKey, fmt.Sprint(txr.Height)),
+			}); err != nil {
+				return fmt.Errorf("indexing transaction meta-events: %w", err)
+			}
+			// Index any events packaged with the transaction.
+			if err := insertEvents(tx, blockID, txID, txr.Result.Events); err != nil {
+				return fmt.Errorf("indexing transaction events: %w", err)
+			}
+			return nil
+
+		}); err != nil {
 			return err
 		}
-
-    // index the reserved height and hash indices
-    hash := types.Tx(tx.Tx).Hash()
-    sqlStmtEvents = sqlStmtEvents.Values(types.TxHashKey, hash, tx.Height, hash, txID, ts, es.chainID)
-    sqlStmtEvents = sqlStmtEvents.Values(types.TxHeightKey, tx.Height, tx.Height, hash, txID, ts, es.chainID)
-
-    for _, event := range result.Result.Events {
-      // only index events with a non-empty type
-      if len(event.Type) == 0 {
-        continue
-      }
-
-      for _, attr := range event.Attributes {
-        if len(attr.Key) == 0 {
-          continue
-        }
-
-        // index if `index: true` is set
-        compositeTag := fmt.Sprintf("%s.%s", event.Type, string(attr.Key))
-			
-        // ensure event does not conflict with a reserved prefix key
-        if compositeTag == types.TxHashKey || compositeTag == types.TxHeightKey {
-          return fmt.Errorf("event type and attribute key \"%s\" is reserved; please use a different key", compositeTag)
-        }
-		
-        if attr.GetIndex() {
-          sqlStmtEvents = sqlStmtEvents.Values(compositeKey, string(attr.Value), tx.Height, hash, txID, ts, es.chainID)
-        }
-      }
-    }
-  }
-  
-  // execute sqlStmtEvents db query...
+	}
+	return nil
 }
 
-func (es *PSQLEventSink) SearchBlockEvents(ctx context.Context, q *query.Query) ([]int64, error) {
-  return nil, errors.New("block search is not supported via the postgres event sink")
-}
+// SearchBlockEvents is not implemented by this sink, and reports an error for all queries.
+func (es *EventSink) SearchBlockEvents(ctx context.Context, q *query.Query) ([]int64, error)
 
-func (es *PSQLEventSink) SearchTxEvents(ctx context.Context, q *query.Query) ([]*abci.TxResult, error) {
-  return nil, errors.New("tx search is not supported via the postgres event sink")
-}
+// SearchTxEvents is not implemented by this sink, and reports an error for all queries.
+func (es *EventSink) SearchTxEvents(ctx context.Context, q *query.Query) ([]*abci.TxResult, error)
 
-func (es *PSQLEventSink) GetTxByHash(hash []byte) (*abci.TxResult, error) {
-	return nil, errors.New("getTxByHash is not supported via the postgres event sink")
-}
+// GetTxByHash is not implemented by this sink, and reports an error for all queries.
+func (es *EventSink) GetTxByHash(hash []byte) (*abci.TxResult, error)
 
-func (es *PSQLEventSink) HasBlock(h int64) (bool, error) {
-	return false, errors.New("hasBlock is not supported via the postgres event sink")
-}
+// HasBlock is not implemented by this sink, and reports an error for all queries.
+func (es *EventSink) HasBlock(h int64) (bool, error)
 ```
 
 ### Configuration

docs/architecture/adr-072-request-for-comments.md

@@ -0,0 +1,105 @@
+# ADR 72: Restore Requests for Comments
+
+## Changelog
+
+- 20-Aug-2021: Initial draft (@creachadair)
+
+## Status
+
+Proposed
+
+## Context
+
+In the past, we kept a collection of Request for Comments (RFC) documents in `docs/rfc`.
+Prior to the creation of the ADR process, these documents were used to document
+design and implementation decisions about Tendermint Core. The RFC directory
+was removed in favor of ADRs, in commit 3761aa69 (PR
+[\#6345](https://github.com/tendermint/tendermint/pull/6345)).
+
+For issues where an explicit design decision or implementation change is
+required, an ADR is generally preferable to an open-ended RFC: An ADR is
+relatively narrowly-focused, identifies a specific design or implementation
+question, and documents the consensus answer to that question.
+
+Some discussions are more open-ended, however, or don't require a specific
+decision to be made (yet). Such conversations are still valuable to document,
+and several members of the Tendermint team have been doing so by writing gists
+or Google docs to share them around. That works well enough in the moment, but
+gists do not support any kind of collaborative editing, and both gists and docs
+are hard to discover after the fact. Google docs have much better collaborative
+editing, but are worse for discoverability, especially when contributors span
+different Google accounts.
+
+Discoverability is important, because these kinds of open-ended discussions are
+useful to people who come later -- either as new team members or as outside
+contributors seeking to use and understand the thoughts behind our designs and
+the architectural decisions that arose from those discussion.
+
+With these in mind, I propose that:
+
+-  We re-create a new, initially empty `docs/rfc` directory in the repository,
+   and use it to capture these kinds of open-ended discussions in supplement to
+   ADRs.
+
+-  Unlike in the previous RFC scheme, documents in this new directory will
+   _not_ be used directly for decision-making. This is the key difference
+   between an RFC and an ADR.
+
+   Instead, an RFC will exist to document background, articulate general
+   principles, and serve as a historical record of discussion and motivation.
+
+   In this system, an RFC may _only_ result in a decision indirectly, via ADR
+   documents created in response to the RFC.
+
+   **In short:** If a decision is required, write an ADR; otherwise if a
+   sufficiently broad discussion is needed, write an RFC.
+
+Just so that there is a consistent format, I also propose that:
+
+-  RFC files are named `rfc-XXX-title.{md,rst,txt}` and are written in plain
+   text, Markdown, or ReStructured Text.
+
+-  Like an ADR, an RFC should include a high-level change log at the top of the
+   document, and sections for:
+
+     * Abstract: A brief, high-level synopsis of the topic.
+     * Background: Any background necessary to understand the topic.
+     * Discussion: Detailed discussion of the issue being considered.
+
+-  Unlike an ADR, an RFC does _not_ include sections for Decisions, Detailed
+   Design, or evaluation of proposed solutions. If an RFC leads to a proposal
+   for an actual architectural change, that must be recorded in an ADR in the
+   usual way, and may refer back to the RFC in its References section.
+
+## Alternative Approaches
+
+Leaving aside implementation details, the main alternative to this proposal is
+to leave things as they are now, with ADRs as the only log of record and other
+discussions being held informally in whatever medium is convenient at the time.
+
+## Decision
+
+(pending)
+
+## Detailed Design
+
+- Create a new `docs/rfc` directory in the `tendermint` repository. Note that
+  this proposal intentionally does _not_ pull back the previous contents of
+  that path from Git history, as those documents were appropriately merged into
+  the ADR process.
+
+- Create a `README.md` for RFCs that explains the rules and their relationship
+  to ADRs.
+
+- Create an `rfc-template.md` file for RFC files.
+
+## Consequences
+
+### Positive
+
+- We will have a more discoverable place to record open-ended discussions that
+  do not immediately result in a design change.
+
+### Negative
+
+- Potentially some people could be confused about the RFC/ADR distinction.

docs/networks/README.md

@@ -2,7 +2,7 @@
 order: 1
 parent:
   title: Networks
-  order: 6
+  order: 1
 ---
 
 # Overview

docs/networks/docker-compose.md

@@ -169,7 +169,7 @@ Override the [command](https://github.com/tendermint/tendermint/blob/master/netw
         ipv4_address: 192.167.10.2
 ```
 
-Similarly do for node1, node2 and node3 then [run testnet](https://github.com/tendermint/tendermint/blob/master/docs/networks/docker-compose.md#run-a-testnet)
+Similarly do for node1, node2 and node3 then [run testnet](#run-a-testnet).
 
 ## Logging
 

docs/nodes/configuration.md

@@ -16,8 +16,7 @@ the parameters set with their default values. It will look something
 like the file below, however, double check by inspecting the
 `config.toml` created with your version of `tendermint` installed:
 
-```toml
-# This is a TOML config file.
+```toml# This is a TOML config file.
 # For more information, see https://github.com/toml-lang/toml
 
 # NOTE: Any path below can be absolute (e.g. "/var/myawesomeapp/data") or
@@ -34,18 +33,14 @@ like the file below, however, double check by inspecting the
 proxy-app = "tcp://127.0.0.1:26658"
 
 # A custom human readable name for this node
-moniker = "anonymous"
+moniker = "ape"
 
-# If this node is many blocks behind the tip of the chain, BlockSync
-# allows them to catchup quickly by downloading blocks in parallel
-# and verifying their commits
-fast-sync = true
 
 # Mode of Node: full | validator | seed (default: "validator")
 # * validator node (default)
 #   - all reactors
 #   - with priv_validator_key.json, priv_validator_state.json
-# * full node 
+# * full node
 #   - all reactors
 #   - No priv_validator_key.json, priv_validator_state.json
 # * seed node
@@ -53,6 +48,11 @@ fast-sync = true
 #   - No priv_validator_key.json, priv_validator_state.json
 mode = "validator"
 
+# If this node is many blocks behind the tip of the chain, FastSync
+# allows them to catchup quickly by downloading blocks in parallel
+# and verifying their commits
+fast-sync = true
+
 # Database backend: goleveldb | cleveldb | boltdb | rocksdb | badgerdb
 # * goleveldb (github.com/syndtr/goleveldb - most popular implementation)
 #   - pure go
@@ -88,16 +88,6 @@ log-format = "plain"
 # Path to the JSON file containing the initial validator set and other meta data
 genesis-file = "config/genesis.json"
 
-# Path to the JSON file containing the private key to use as a validator in the consensus protocol
-priv-validator-key-file = "config/priv_validator_key.json"
-
-# Path to the JSON file containing the last sign state of a validator
-priv-validator-state-file = "data/priv_validator_state.json"
-
-# TCP or UNIX socket address for Tendermint to listen on for
-# connections from an external PrivValidator process
-priv-validator-laddr = ""
-
 # Path to the JSON file containing the private key to use for node authentication in the p2p protocol
 node-key-file = "config/node_key.json"
 
@@ -109,6 +99,33 @@ abci = "socket"
 filter-peers = false
 
 
+#######################################################
+###       Priv Validator Configuration              ###
+#######################################################
+[priv-validator]
+
+# Path to the JSON file containing the private key to use as a validator in the consensus protocol
+key-file = "config/priv_validator_key.json"
+
+# Path to the JSON file containing the last sign state of a validator
+state-file = "data/priv_validator_state.json"
+
+# TCP or UNIX socket address for Tendermint to listen on for
+# connections from an external PrivValidator process
+# when the listenAddr is prefixed with grpc instead of tcp it will use the gRPC Client
+laddr = ""
+
+# Path to the client certificate generated while creating needed files for secure connection.
+# If a remote validator address is provided but no certificate, the connection will be insecure
+client-certificate-file = ""
+
+# Client key generated while creating certificates for secure connection
+validator-client-key-file = ""
+
+# Path to the Root Certificate Authority used to sign both client and server certificates
+certificate-authority = ""
+
+
 #######################################################################
 ###                 Advanced Configuration Options                  ###
 #######################################################################
@@ -134,6 +151,7 @@ cors-allowed-headers = ["Origin", "Accept", "Content-Type", "X-Requested-With",
 
 # TCP or UNIX socket address for the gRPC server to listen on
 # NOTE: This server only supports /broadcast_tx_commit
+# Deprecated gRPC  in the RPC layer of Tendermint will be deprecated in 0.36.
 grpc-laddr = ""
 
 # Maximum number of simultaneous connections.
@@ -143,9 +161,10 @@ grpc-laddr = ""
 # 0 - unlimited.
 # Should be < {ulimit -Sn} - {MaxNumInboundPeers} - {MaxNumOutboundPeers} - {N of wal, db and other open files}
 # 1024 - 40 - 10 - 50 = 924 = ~900
+# Deprecated gRPC  in the RPC layer of Tendermint will be deprecated in 0.36.
 grpc-max-open-connections = 900
 
-# Activate unsafe RPC commands like /dial_seeds and /unsafe_flush_mempool
+# Activate unsafe RPC commands like /dial-seeds and /unsafe-flush-mempool
 unsafe = false
 
 # Maximum number of simultaneous connections (including WebSocket).
@@ -202,18 +221,34 @@ pprof-laddr = ""
 #######################################################
 [p2p]
 
+# Enable the legacy p2p layer.
+use-legacy = false
+
+# Select the p2p internal queue
+queue-type = "priority"
+
 # Address to listen for incoming connections
 laddr = "tcp://0.0.0.0:26656"
 
 # Address to advertise to peers for them to dial
 # If empty, will use the same port as the laddr,
 # and will introspect on the listener or use UPnP
-# to figure out the address.
+# to figure out the address. ip and port are required
+# example: 159.89.10.97:26656
 external-address = ""
 
 # Comma separated list of seed nodes to connect to
+# We only use these if we can’t connect to peers in the addrbook
+# NOTE: not used by the new PEX reactor. Please use BootstrapPeers instead.
+# TODO: Remove once p2p refactor is complete
+# ref: https:#github.com/tendermint/tendermint/issues/5670
 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 = ""
+
 # Comma separated list of nodes to keep persistent connections to
 persistent-peers = ""
 
@@ -221,6 +256,8 @@ persistent-peers = ""
 upnp = false
 
 # Path to address book
+# TODO: Remove once p2p refactor is complete
+# ref: https:#github.com/tendermint/tendermint/issues/5670
 addr-book-file = "config/addrbook.json"
 
 # Set true for strict address routability rules
@@ -228,9 +265,15 @@ addr-book-file = "config/addrbook.json"
 addr-book-strict = true
 
 # Maximum number of inbound peers
+#
+# TODO: Remove once p2p refactor is complete in favor of MaxConnections.
+# ref: https://github.com/tendermint/tendermint/issues/5670
 max-num-inbound-peers = 40
 
 # Maximum number of outbound peers to connect to, excluding persistent peers
+#
+# TODO: Remove once p2p refactor is complete in favor of MaxConnections.
+# ref: https://github.com/tendermint/tendermint/issues/5670
 max-num-outbound-peers = 10
 
 # Maximum number of connections (inbound and outbound).
@@ -240,27 +283,40 @@ max-connections = 64
 max-incoming-connection-attempts = 100
 
 # List of node IDs, to which a connection will be (re)established ignoring any existing limits
+# TODO: Remove once p2p refactor is complete
+# ref: https:#github.com/tendermint/tendermint/issues/5670
 unconditional-peer-ids = ""
 
 # Maximum pause when redialing a persistent peer (if zero, exponential backoff is used)
+# TODO: Remove once p2p refactor is complete
+# ref: https:#github.com/tendermint/tendermint/issues/5670
 persistent-peers-max-dial-period = "0s"
 
 # Time to wait before flushing messages out on the connection
+# TODO: Remove once p2p refactor is complete
+# ref: https:#github.com/tendermint/tendermint/issues/5670
 flush-throttle-timeout = "100ms"
 
 # Maximum size of a message packet payload, in bytes
-max-packet-msg-payload-size = 1024
+# TODO: Remove once p2p refactor is complete
+# ref: https:#github.com/tendermint/tendermint/issues/5670
+max-packet-msg-payload-size = 1400
 
 # Rate at which packets can be sent, in bytes/second
+# TODO: Remove once p2p refactor is complete
+# ref: https:#github.com/tendermint/tendermint/issues/5670
 send-rate = 5120000
 
 # Rate at which packets can be received, in bytes/second
+# TODO: Remove once p2p refactor is complete
+# ref: https:#github.com/tendermint/tendermint/issues/5670
 recv-rate = 5120000
 
 # Set true to enable the peer-exchange reactor
 pex = true
 
 # Comma separated list of peer IDs to keep private (will not be gossiped to other peers)
+# Warning: IPs will be exposed at /net_info, for more information https://github.com/tendermint/tendermint/issues/3055
 private-peer-ids = ""
 
 # Toggle to disable guard against peers connecting from the same ip.
@@ -353,14 +409,26 @@ discovery-time = "15s"
 # Will create a new, randomly named directory within, and remove it when done.
 temp-dir = ""
 
+# The timeout duration before re-requesting a chunk, possibly from a different
+# peer (default: 15 seconds).
+chunk-request-timeout = "15s"
+
+# The number of concurrent chunk and block fetchers to run (default: 4).
+fetchers = "4"
+
 #######################################################
-###       BlockSync Configuration Connections       ###
+###       Block Sync Configuration Connections       ###
 #######################################################
-[fastsync]
+[blocksync]
+
+# If this node is many blocks behind the tip of the chain, BlockSync
+# allows them to catchup quickly by downloading blocks in parallel
+# and verifying their commits
+enable = true
 
 # Block Sync version to use:
-#   1) "v0" (default) - the legacy block sync implementation
-#   2) "v2" - complete redesign of v0, optimized for testability & readability
+#   1) "v0" (default) - the standard block sync implementation
+#   2) "v2" - DEPRECATED, please use v0
 version = "v0"
 
 #######################################################
@@ -409,7 +477,8 @@ peer-query-maj23-sleep-duration = "2s"
 #######################################################
 [tx-index]
 
-# What indexer to use for transactions
+# The backend database list to back the indexer.
+# If list contains "null" or "", meaning no indexer service will be used.
 #
 # The application will set which txs to index. In some cases a node operator will be able
 # to decide which txs to index based on configuration set in the application.
@@ -417,8 +486,13 @@ peer-query-maj23-sleep-duration = "2s"
 # Options:
 #   1) "null"
 #   2) "kv" (default) - the simplest possible indexer, backed by key-value storage (defaults to levelDB; see DBBackend).
-#   - When "kv" is chosen "tx.height" and "tx.hash" will always be indexed.
-indexer = "kv"
+#   3) "psql" - the indexer services backed by PostgreSQL.
+# When "kv" or "psql" is chosen "tx.height" and "tx.hash" will always be indexed.
+indexer = ["kv"]
+
+# The PostgreSQL connection configuration, the connection format:
+#   postgresql://<user>:<password>@<host>:<port>/<db>?<opts>
+psql-conn = ""
 
 #######################################################
 ###       Instrumentation Configuration Options     ###
@@ -519,10 +593,61 @@ This section will cover settings within the p2p section of the `config.toml`.
 
 - `external-address` = is the address that will be advertised for other nodes to use. We recommend setting this field with your public IP and p2p port.
   - > We recommend setting an external address. When used in a private network, Tendermint Core currently doesn't advertise the node's public address. There is active and ongoing work to improve the P2P system, but this is a helpful workaround for now.
-- `seeds` = is a list of comma separated seed nodes that you will connect upon a start and ask for peers. A seed node is a node that does not participate in consensus but only helps propagate peers to nodes in the networks
 - `persistent-peers` = is a list of comma separated peers that you will always want to be connected to. If you're already connected to the maximum number of peers, persistent peers will not be added.
-- `max-num-inbound-peers` = is the maximum number of peers you will accept inbound connections from at one time (where they dial your address and initiate the connection).
-- `max-num-outbound-peers` = is the maximum number of peers you will initiate outbound connects to at one time (where you dial their address and initiate the connection).
-- `unconditional-peer-ids` = is similar to `persistent-peers` except that these peers will be connected to even if you are already connected to the maximum number of peers. This can be a validator node ID on your sentry node.
 - `pex` = turns the peer exchange reactor on or off. Validator node will want the `pex` turned off so it would not begin gossiping to unknown peers on the network. PeX can also be turned off for statically configured networks with fixed network connectivity. For full nodes on open, dynamic networks, it should be turned on.
 - `private-peer-ids` = is a comma-separated list of node ids that will _not_ be exposed to other peers (i.e., you will not tell other peers about the ids in this list). This can be filled with a validator's node id.
+
+Recently the Tendermint Team conducted a refactor of the p2p layer. This lead to multiple config paramters being deprecated and/or replaced. 
+
+We will cover the new and deprecated parameters below.
+### New Parameters
+
+There are three new parameters, which are enabled if use-legacy is set to false.
+
+- `queue-type` = sets a type of queue to use in the p2p layer. There are three options available `fifo`, `priority` and `wdrr`. The default is priority
+- `bootstrap-peers` = is a list of comma seperated peers which will be used to bootstrap the address book. 
+- `max-connections` = is the max amount of allowed inbound and outbound connections.
+### Deprecated Parameters
+
+> Note: For Tendermint 0.35, there are two p2p implementations. The old version is used by deafult with the deprecated fields. The new implementation uses different config parameters, explained above.
+
+- `max-num-inbound-peers` = is the maximum number of peers you will accept inbound connections from at one time (where they dial your address and initiate the connection). *This was replaced by `max-connections`*
+- `max-num-outbound-peers` = is the maximum number of peers you will initiate outbound connects to at one time (where you dial their address and initiate the connection).*This was replaced by `max-connections`*
+- `unconditional-peer-ids` = is similar to `persistent-peers` except that these peers will be connected to even if you are already connected to the maximum number of peers. This can be a validator node ID on your sentry node. *Deprecated*
+- `seeds` = is a list of comma separated seed nodes that you will connect upon a start and ask for peers. A seed node is a node that does not participate in consensus but only helps propagate peers to nodes in the networks *Deprecated, replaced by bootstrap peers*
+
+## Indexing Settings
+
+Operators can configure indexing via the `[tx_index]` section. The `indexer`
+field takes a series of supported indexers. If `null` is included, indexing will
+be turned off regardless of other values provided.
+
+### Supported Indexers
+
+#### KV
+
+The `kv` indexer type is an embedded key-value store supported by the main
+underlying Tendermint database. Using the `kv` indexer type allows you to query
+for block and transaction events directly against Tendermint's RPC. However, the
+query syntax is limited and so this indexer type might be deprecated or removed
+entirely in the future.
+
+#### PostgreSQL
+
+The `psql` indexer type allows an operator to enable block and transaction event
+indexing by proxying it to an external PostgreSQL instance allowing for the events
+to be stored in relational models. Since the events are stored in a RDBMS, operators
+can leverage SQL to perform a series of rich and complex queries that are not
+supported by the `kv` indexer type. Since operators can leverage SQL directly,
+searching is not enabled for the `psql` indexer type via Tendermint's RPC -- any
+such query will fail.
+
+Note, the SQL schema is stored in `state/indexer/sink/psql/schema.sql` and operators
+must explicitly create the relations prior to starting Tendermint and enabling
+the `psql` indexer type.
+
+Example:
+
+```shell
+$ psql ... -f state/indexer/sink/psql/schema.sql
+```

docs/nodes/metrics.md

@@ -20,6 +20,7 @@ The following metrics are available:
 
 | **Name**                               | **Type**  | **Tags**      | **Description**                                                        |
 | -------------------------------------- | --------- | ------------- | ---------------------------------------------------------------------- |
+| abci_connection_method_timing          | Histogram | method, type  | Timings for each of the ABCI methods                                   |
 | consensus_height                       | Gauge     |               | Height of the chain                                                    |
 | consensus_validators                   | Gauge     |               | Number of validators                                                   |
 | consensus_validators_power             | Gauge     |               | Total voting power of all validators                                   |
@@ -55,6 +56,16 @@ The following metrics are available:
 
 Percentage of missing + byzantine validators:
 
-```md
-((consensus\_byzantine\_validators\_power + consensus\_missing\_validators\_power) / consensus\_validators\_power) * 100
+```prometheus
+((consensus_byzantine_validators_power + consensus_missing_validators_power) / consensus_validators_power) * 100
+```
+
+Rate at which the application is responding to each ABCI method call.
+```
+sum(rate(tendermint_abci_connection_method_timing_count[5m])) by (method)
+```
+
+The 95th percentile response time for the application to the `deliver_tx` ABCI method call.
+```
+histogram_quantile(0.95, sum by(le) (rate(tendermint_abci_connection_method_timing_bucket{method="deliver_tx"}[5m])))
 ```

docs/rfc/README.md

@@ -0,0 +1,47 @@
+---
+order: 1
+parent:
+  order: false
+---
+
+# Requests for Comments
+
+A Request for Comments (RFC) is a record of discussion on an open-ended topic
+related to the design and implementation of Tendermint Core, for which no
+immediate decision is required.
+
+The purpose of an RFC is to serve as a historical record of a high-level
+discussion that might otherwise only be recorded in an ad hoc way (for example,
+via gists or Google docs) that are difficult to discover for someone after the
+fact. An RFC _may_ give rise to more specific architectural _decisions_ for
+Tendermint, but those decisions must be recorded separately in [Architecture
+Decision Records (ADR)](./../architecture).
+
+As a rule of thumb, if you can articulate a specific question that needs to be
+answered, write an ADR. If you need to explore the topic and get input from
+others to know what questions need to be answered, an RFC may be appropriate.
+
+## RFC Content
+
+An RFC should provide:
+
+- A **changelog**, documenting when and how the RFC has changed.
+- An **abstract**, briefly summarizing the topic so the reader can quickly tell
+  whether it is relevant to their interest.
+- Any **background** a reader will need to understand and participate in the
+  substance of the discussion (links to other documents are fine here).
+- The **discussion**, the primary content of the document.
+
+The [rfc-template.md](./rfc-template.md) file includes placeholders for these
+sections.
+
+## Table of Contents
+
+- [RFC-000: P2P Roadmap](./rfc-000-p2p-roadmap.rst)
+- [RFC-001: Storage Engines](./rfc-001-storage-engine.rst)
+- [RFC-002: Interprocess Communication](./rfc-002-ipc-ecosystem.md)
+- [RFC-003: Performance Taxonomy](./rfc-003-performance-questions.md)
+- [RFC-004: E2E Test Framework Enhancements](./rfc-004-e2e-framework.md)
+- [RFC-005: Event System](./rfc-005-event-system.rst)
+
+<!-- - [RFC-NNN: Title](./rfc-NNN-title.md) -->

docs/rfc/rfc-000-p2p-roadmap.rst

@@ -0,0 +1,316 @@
+====================
+RFC 000: P2P Roadmap
+====================
+
+Changelog
+---------
+
+- 2021-08-20: Completed initial draft and distributed via a gist
+- 2021-08-25: Migrated as an RFC and changed format
+
+Abstract
+--------
+
+This document discusses the future of peer network management in Tendermint, with
+a particular focus on features, semantics, and a proposed roadmap.
+Specifically, we consider libp2p as a tool kit for implementing some fundamentals.
+
+Background
+----------
+
+For the 0.35 release cycle the switching/routing layer of Tendermint was
+replaced. This work was done "in place," and produced a version of Tendermint
+that was backward-compatible and interoperable with previous versions of the
+software. While there are new p2p/peer management constructs in the new
+version (e.g. ``PeerManager`` and ``Router``), the main effect of this change
+was to simplify the ways that other components within Tendermint interacted with
+the peer management layer, and to make it possible for higher-level components
+(specifically the reactors), to be used and tested more independently.
+
+This refactoring, which was a major undertaking, was entirely necessary to
+enable areas for future development and iteration on this aspect of
+Tendermint. There are also a number of potential user-facing features that
+depend heavily on the p2p layer: additional transport protocols, transport
+compression, improved resilience to network partitions. These improvements to
+modularity, stability, and reliability of the p2p system will also make
+ongoing maintenance and feature development easier in the rest of Tendermint.
+
+Critique of Current Peer-to-Peer Infrastructure
+---------------------------------------
+
+The current (refactored) P2P stack is an improvement on the previous iteration
+(legacy), but as of 0.35, there remains room for improvement in the design and
+implementation of the P2P layer.
+
+Some limitations of the current stack include:
+
+- heavy reliance on buffering to avoid backups in the flow of components,
+  which is fragile to maintain and can lead to unexpected memory usage
+  patterns and forces the routing layer to make decisions about when messages
+  should be discarded.
+
+- the current p2p stack relies on convention (rather than the compiler) to
+  enforce the API boundaries and conventions between reactors and the router,
+  making it very easy to write "wrong" reactor code or introduce a bad
+  dependency.
+
+- the current stack is probably more complex and difficult to maintain because
+  the legacy system must coexist with the new components in 0.35. When the
+  legacy stack is removed there are some simple changes that will become
+  possible and could reduce the complexity of the new system. (e.g. `#6598
+  <https://github.com/tendermint/tendermint/issues/6598>`_.)
+
+- the current stack encapsulates a lot of information about peers, and makes it
+  difficult to expose that information to monitoring/observability tools. This
+  general opacity also makes it difficult to interact with the peer system
+  from other areas of the code base (e.g. tests, reactors).
+
+- the legacy stack provided some control to operators to force the system to
+  dial new peers or seed nodes or manipulate the topology of the system _in
+  situ_. The current stack can't easily provide this, and while the new stack
+  may have better behavior, it does leave operators hands tied.
+
+Some of these issues will be resolved early in the 0.36 cycle, with the
+removal of the legacy components.
+
+The 0.36 release also provides the opportunity to make changes to the
+protocol, as the release will not be compatible with previous releases.
+
+Areas for Development
+---------------------
+
+These sections describe features that may make sense to include in a Phase 2 of
+a P2P project.
+
+Internal Message Passing
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+Currently, there's no provision for intranode communication using the P2P
+layer, which means when two reactors need to interact with each other they
+have to have dependencies on each other's interfaces, and
+initialization. Changing these interactions (e.g. transitions between
+blocksync and consensus) from procedure calls to message passing.
+
+This is a relatively simple change and could be implemented with the following
+components:
+
+- a constant to represent "local" delivery as  the ``To`` field on
+  ``p2p.Envelope``.
+
+- special path for routing local messages that doesn't require message
+  serialization (protobuf marshalling/unmarshaling).
+
+Adding these semantics, particularly if in conjunction with synchronous
+semantics provides a solution to dependency graph problems currently present
+in the Tendermint codebase, which will simplify development, make it possible
+to isolate components for testing.
+
+Eventually, this will also make it possible to have a logical Tendermint node
+running in multiple processes or in a collection of containers, although the
+usecase of this may be debatable.
+
+Synchronous Semantics (Paired Request/Response)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+In the current system, all messages are sent with fire-and-forget semantics,
+and there's no coupling between a request sent via the p2p layer, and a
+response. These kinds of semantics would simplify the implementation of
+state and block sync reactors, and make intra-node message passing more
+powerful.
+
+For some interactions, like gossiping transactions between the mempools of
+different nodes, fire-and-forget semantics make sense, but for other
+operations the missing link between requests/responses leads to either
+inefficiency when a node fails to respond or becomes unavailable, or code that
+is just difficult to follow.
+
+To support this kind of work, the protocol would need to accommodate some kind
+of request/response ID to allow identifying out-of-order responses over a
+single connection. Additionally, expanded the programming model of the
+``p2p.Channel`` to accommodate some kind of _future_ or similar paradigm to
+make it viable to write reactor code without needing for the reactor developer
+to wrestle with lower level concurrency constructs.
+
+
+Timeout Handling (QoS)
+~~~~~~~~~~~~~~~~~~~~~~
+
+Currently, all timeouts, buffering, and QoS features are handled at the router
+layer, and the reactors are implemented in ways that assume/require
+asynchronous operation. This both increases the required complexity at the
+routing layer, and means that misbehavior at the reactor level is difficult to
+detect or attribute. Additionally, the current system provides three main
+parameters to control quality of service:
+
+- buffer sizes for channels and queues.
+
+- priorities for channels
+
+- queue implementation details for shedding load.
+
+These end up being quite coarse controls, and changing the settings are
+difficult because as the queues and channels are able to buffer large numbers
+of messages it can be hard to see the impact of a given change, particularly
+in our extant test environment. In general, we should endeavor to:
+
+- set real timeouts, via contexts, on most message send operations, so that
+  senders rather than queues can be responsible for timeout
+  logic. Additionally, this will make it possible to avoid sending messages
+  during shutdown.
+
+- reduce (to the greatest extent possible) the amount of buffering in
+  channels and the queues, to more readily surface backpressure and reduce the
+  potential for buildup of stale messages.
+
+Stream Based Connection Handling
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Currently the transport layer is message based, which makes sense from a
+mental model of how the protocol works, but makes it more difficult to
+implement transports and connection types, as it forces a higher level view of
+the connection and interaction which makes it harder to implement for novel
+transport types and makes it more likely that message-based caching and rate
+limiting will be implemented at the transport layer rather than at a more
+appropriate level.
+
+The transport then, would be responsible for negotiating the connection and the
+handshake and otherwise behave like a socket/file descriptor with ``Read`` and
+``Write`` methods.
+
+While this was included in the initial design for the new P2P layer, it may be
+obviated entirely if the transport and peer layer is replaced with libp2p,
+which is primarily stream based.
+
+Service Discovery
+~~~~~~~~~~~~~~~~~
+
+In the current system, Tendermint assumes that all nodes in a network are
+largely equivalent, and nodes tend to be "chatty" making many requests of
+large numbers of peers and waiting for peers to (hopefully) respond. While
+this works and has allowed Tendermint to get to a certain point, this both
+produces a theoretical scaling bottle neck and makes it harder to test and
+verify components of the system.
+
+In addition to peer's identity and connection information, peers should be
+able to advertise a number of services or capabilities, and node operators or
+developers should be able to specify peer capability requirements (e.g. target
+at least <x>-percent of peers with <y> capability.)
+
+These capabilities may be useful in selecting peers to send messages to, it
+may make sense to extend Tendermint's message addressing capability to allow
+reactors to send messages to groups of peers based on role rather than only
+allowing addressing to one or all peers.
+
+Having a good service discovery mechanism may pair well with the synchronous
+semantics (request/response) work, as it allows reactors to "make a request of
+a peer with <x> capability and wait for the response," rather force the
+reactors to need to track the capabilities or state of specific peers.
+
+Solutions
+---------
+
+Continued Homegrown Implementation
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The current peer system is homegrown and is conceptually compatible with the
+needs of the project, and while there are limitations to the system, the p2p
+layer is not (currently as of 0.35) a major source of bugs or friction during
+development.
+
+However, the current implementation makes a number of allowances for
+interoperability, and there are a collection of iterative improvements that
+should be considered in the next couple of releases. To maintain the current
+implementation, upcoming work would include:
+
+- change the ``Transport`` mechanism to facilitate easier implementations.
+
+- implement different ``Transport`` handlers to be able to manage peer
+  connections using different protocols (e.g. QUIC, etc.)
+
+- entirely remove the constructs and implementations of the legacy peer
+  implementation.
+
+- establish and enforce clearer chains of responsibility for connection
+  establishment (e.g. handshaking, setup,) which is currently shared between
+  three components.
+
+- report better metrics regarding the into the state of peers and network
+  connectivity, which are opaque outside of the system. This is constrained at
+  the moment as a side effect of the split responsibility for connection
+  establishment.
+
+- extend the PEX system to include service information so that nodes in the
+  network weren't necessarily homogeneous.
+
+While maintaining a bespoke peer management layer would seem to distract from
+development of core functionality, the truth is that (once the legacy code is
+removed,) the scope of the peer layer is relatively small from a maintenance
+perspective, and having control at this layer might actually afford the
+project with the ability to more rapidly iterate on some features.
+
+LibP2P
+~~~~~~
+
+LibP2P provides components that, approximately, account for the
+``PeerManager`` and ``Transport`` components of the current (new) P2P
+stack. The Go APIs seem reasonable, and being able to externalize the
+implementation details of peer and connection management seems like it could
+provide a lot of benefits, particularly in supporting a more active ecosystem.
+
+In general the API provides the kind of stream-based, multi-protocol
+supporting, and idiomatic baseline for implementing a peer layer. Additionally
+because it handles peer exchange and connection management at a lower
+level, by using libp2p it'd be possible to remove a good deal of code in favor
+of just using libp2p. Having said that, Tendermint's P2P layer covers a
+greater scope (e.g. message routing to different peers) and that layer is
+something that Tendermint might want to retain.
+
+The are a number of unknowns that require more research including how much of
+a peer database the Tendermint engine itself needs to maintain, in order to
+support higher level operations (consensus, statesync), but it might be the
+case that our internal systems need to know much less about peers than
+otherwise specified. Similarly, the current system has a notion of peer
+scoring that cannot be communicated to libp2p, which may be fine as this is
+only used to support peer exchange (PEX,) which would become a property libp2p
+and not expressed in it's current higher-level form.
+
+In general, the effort to switch to libp2p would involve:
+
+- timing it during an appropriate protocol-breaking window, as it doesn't seem
+  viable to support both libp2p *and* the current p2p protocol.
+
+- providing some in-memory testing network to support the use case that the
+  current ``p2p.MemoryNetwork`` provides.
+
+- re-homing the ``p2p.Router`` implementation on top of libp2p components to
+  be able to maintain the current reactor implementations.
+
+Open question include:
+
+- how much local buffering should we be doing? It sort of seems like we should
+  figure out what the expected behavior is for libp2p for QoS-type
+  functionality, and if our requirements mean that we should be implementing
+  this on top of things ourselves?
+
+- if Tendermint was going to use libp2p, how would libp2p's stability
+  guarantees (protocol, etc.) impact/constrain Tendermint's stability
+  guarantees?
+
+- what kind of introspection does libp2p provide, and to what extend would
+  this change or constrain the kind of observability that Tendermint is able
+  to provide?
+
+- how do efforts to select "the best" (healthy, close, well-behaving, etc.)
+  peers work out if Tendermint is not maintaining a local peer database?
+
+- would adding additional higher level semantics (internal message passing,
+  request/response pairs, service discovery, etc.) facilitate removing some of
+  the direct linkages between constructs/components in the system and reduce
+  the need for Tendermint nodes to maintain state about its peers?
+
+References
+----------
+
+- `Tracking Ticket for P2P Refactor Project <https://github.com/tendermint/tendermint/issues/5670>`_
+- `ADR 61: P2P Refactor Scope <../architecture/adr-061-p2p-refactor-scope.md>`_
+- `ADR 62: P2P Architecture and Abstraction <../architecture/adr-061-p2p-architecture.md>`_

docs/rfc/rfc-001-storage-engine.rst

@@ -0,0 +1,179 @@
+===========================================
+RFC 001: Storage Engines and Database Layer
+===========================================
+
+Changelog
+---------
+
+- 2021-04-19: Initial Draft (gist)
+- 2021-09-02: Migrated to RFC folder, with some updates  
+
+Abstract
+--------
+
+The aspect of Tendermint that's responsible for persistence and storage (often
+"the database" internally) represents a bottle neck in the architecture of the
+platform, that the 0.36 release presents a good opportunity to correct. The
+current storage engine layer provides a great deal of flexibility that is
+difficult for users to leverage or benefit from, while also making it harder
+for Tendermint Core developers to deliver improvements on storage engine. This
+RFC discusses the possible improvements to this layer of the system.
+
+Background
+----------
+
+Tendermint has a very thin common wrapper that makes Tendermint itself
+(largely) agnostic to the data storage layer (within the realm of the popular
+key-value/embedded databases.) This flexibility is not particularly useful:
+the benefits of a specific database engine in the context of Tendermint is not
+particularly well understood, and the maintenance burden for multiple backends
+is not commensurate with the benefit provided. Additionally, because the data
+storage layer is handled generically, and most tests run with an in-memory
+framework, it's difficult to take advantage of any higher-level features of a
+database engine.
+
+Ideally, developers within Tendermint will be able to interact with persisted
+data via an interface that can function, approximately like an object
+store, and this storage interface will be able to accommodate all existing
+persistence workloads (e.g. block storage, local peer management information
+like the "address book", crash-recovery log like the WAL.) In addition to
+providing a more ergonomic interface and new semantics, by selecting a single
+storage engine tendermint can use native durability and atomicity features of
+the storage engine and simplify its own implementations. 
+
+Data Access Patterns
+~~~~~~~~~~~~~~~~~~~~
+
+Tendermint's data access patterns have the following characteristics:
+
+- aggregate data size often exceeds memory.
+
+- data is rarely mutated after it's written for most data (e.g. blocks), but
+  small amounts of working data is persisted by nodes and is frequently
+  mutated (e.g. peer information, validator information.)
+
+- read patterns can be quite random.
+
+- crash resistance and crash recovery, provided by write-ahead-logs (in
+  consensus, and potentially for the mempool) should allow the system to
+  resume work after an unexpected shut down.
+
+Project Goals
+~~~~~~~~~~~~~
+
+As we think about replacing the current persistence layer, we should consider
+the following high level goals: 
+
+- drop dependencies on storage engines that have a CGo dependency.
+
+- encapsulate data format and data storage from higher-level services
+  (e.g. reactors) within tendermint.
+
+- select a storage engine that does not incur any additional operational
+  complexity (e.g. database should be embedded.)
+
+- provide database semantics with sufficient ACID, snapshots, and
+  transactional support.
+
+Open Questions
+~~~~~~~~~~~~~~
+
+The following questions remain:
+
+- what kind of data-access concurrency does tendermint require?
+
+- would tendermint users SDK/etc. benefit from some shared database
+  infrastructure?
+  
+  - In earlier conversations it seemed as if the SDK has selected Badger and
+    RocksDB for their storage engines, and it might make sense to be able to
+    (optionally) pass a handle to a Badger instance between the libraries in
+    some cases.
+
+- what are typical data sizes, and what kinds of memory sizes can we expect
+  operators to be able to provide?
+
+- in addition to simple persistence, what kind of additional semantics would
+  tendermint like to enjoy (e.g. transactional semantics, unique constraints,
+  indexes, in-place-updates, etc.)?
+
+Decision Framework
+~~~~~~~~~~~~~~~~~~
+
+Given the constraint of removing the CGo dependency, the decision is between
+"badger" and "boltdb" (in the form of the etcd/CoreOS fork,) as low level. On
+top of this and somewhat orthogonally, we must also decide on the interface to
+the database and how the larger application will have to interact with the
+database layer. Users of the data layer shouldn't ever need to interact with
+raw byte slices from the database, and should mostly have the experience of
+interacting with Go-types.
+
+Badger is more consistently developed and has a broader feature set than
+Bolt. At the same time, Badger is likely more memory intensive and may have
+more overhead in terms of open file handles given it's model. At first glance,
+Badger is the obvious choice: it's actively developed and it has a lot of
+features that could be useful. Bolt is not without some benefits: it's stable
+and is maintained by the etcd folks, it's simpler model (single memory mapped
+file, etc,) may be easier to reason about.
+
+I propose that we consider the following specific questions about storage
+engines:
+
+- does Badger's evolving development, which may result in data file format
+  changes in the future, and could restrict our access to using the latest
+  version of the library between major upgrades, present a problem?
+
+- do we do we have goals/concerns about memory footprint that Badger may
+  prevent us from hitting, particularly as data sets grow over time?
+
+- what kind of additional tooling might we need/like to build (dump/restore,
+  etc.)?
+
+- do we want to run unit/integration tests against a data files on disk rather
+  than relying exclusively on the memory database?
+
+Project Scope
+~~~~~~~~~~~~~
+
+This project will consist of the following aspects:
+
+- selecting a storage engine, and modifying the tendermint codebase to
+  disallow any configuration of the storage engine outside of the tendermint. 
+
+- remove the dependency on the current tm-db interfaces and replace with some
+  internalized, safe, and ergonomic interface for data persistence with all
+  required database semantics.
+
+- update core tendermint code to use the new interface and data tools.
+
+Next Steps
+~~~~~~~~~~
+
+- circulate the RFC, and discuss options with appropriate stakeholders. 
+  
+- write brief ADR to summarize decisions around technical decisions reached
+  during the RFC phase. 
+
+References
+----------
+
+- `bolddb <https://github.com/etcd-io/bbolt>`_
+- `badger <https://github.com/dgraph-io/badger>`_
+- `badgerdb overview <https://dbdb.io/db/badgerdb>`_
+- `botldb overview <https://dbdb.io/db/boltdb>`_
+- `boltdb vs badger <https://tech.townsourced.com/post/boltdb-vs-badger>`_
+- `bolthold <https://github.com/timshannon/bolthold>`_
+- `badgerhold <https://github.com/timshannon/badgerhold>`_
+- `Pebble <https://github.com/cockroachdb/pebble>`_
+- `SDK Issue Regarding IVAL <https://github.com/cosmos/cosmos-sdk/issues/7100>`_
+- `SDK Discussion about SMT/IVAL <https://github.com/cosmos/cosmos-sdk/discussions/8297>`_
+
+Discussion
+----------
+
+- All things being equal, my tendency would be to use badger, with badgerhold
+  (if that makes sense) for its ergonomics and indexing capabilities, which
+  will require some small selection of wrappers for better write transaction
+  support. This is a weakly held tendency/belief and I think it would be
+  useful for the RFC process to build consensus (or not) around this basic
+  assumption.

docs/rfc/rfc-002-ipc-ecosystem.md

@@ -0,0 +1,420 @@
+# RFC 002: Interprocess Communication (IPC) in Tendermint
+
+## Changelog
+
+- 08-Sep-2021: Initial draft (@creachadair).
+
+
+## Abstract
+
+Communication in Tendermint among consensus nodes, applications, and operator
+tools all use different message formats and transport mechanisms.  In some
+cases there are multiple options. Having all these options complicates both the
+code and the developer experience, and hides bugs. To support a more robust,
+trustworthy, and usable system, we should document which communication paths
+are essential, which could be removed or reduced in scope, and what we can
+improve for the most important use cases.
+
+This document proposes a variety of possible improvements of varying size and
+scope. Specific design proposals should get their own documentation.
+
+
+## Background
+
+The Tendermint state replication engine has a complex IPC footprint.
+
+1. Consensus nodes communicate with each other using a networked peer-to-peer
+   message-passing protocol.
+
+2. Consensus nodes communicate with the application whose state is being
+   replicated via the [Application BlockChain Interface (ABCI)][abci].
+
+3. Consensus nodes export a network-accessible [RPC service][rpc-service] to
+   support operations (bootstrapping, debugging) and synchronization of [light clients][light-client].
+   This interface is also used by the [`tendermint` CLI][tm-cli].
+
+4. Consensus nodes export a gRPC service exposing a subset of the methods of
+   the RPC service described by (3). This was intended to simplify the
+   implementation of tools that already use gRPC to communicate with an
+   application (via the Cosmos SDK), and wanted to also talk to the consensus
+   node without implementing yet another RPC protocol.
+
+   The gRPC interface to the consensus node has been deprecated and is slated
+   for removal in the forthcoming Tendermint v0.36 release.
+
+5. Consensus nodes may optionally communicate with a "remote signer" that holds
+   a validator key and can provide public keys and signatures to the consensus
+   node. One of the stated goals of this configuration is to allow the signer
+   to be run on a private network, separate from the consensus node, so that a
+   compromise of the consensus node from the public network would be less
+   likely to expose validator keys.
+
+## Discussion: Transport Mechanisms
+
+### Remote Signer Transport
+
+A remote signer communicates with the consensus node in one of two ways:
+
+1. "Raw": Using a TCP or Unix-domain socket which carries varint-prefixed
+   protocol buffer messages. In this mode, the consensus node is the server,
+   and the remote signer is the client.
+
+   This mode has been deprecated, and is intended to be removed.
+
+2. gRPC: This mode uses the same protobuf messages as "Raw" node, but uses a
+   standard encrypted gRPC HTTP/2 stub as the transport. In this mode, the
+   remote signer is the server and the consensus node is the client.
+
+
+### ABCI Transport
+
+In ABCI, the _application_ is the server, and the Tendermint consensus engine
+is the client.  Most applications implement the server using the [Cosmos SDK][cosmos-sdk],
+which handles low-level details of the ABCI interaction and provides a
+higher-level interface to the rest of the application. The SDK is written in Go.
+
+Beneath the SDK, the application communicates with Tendermint core in one of
+two ways:
+
+- In-process direct calls (for applications written in Go and compiled against
+  the Tendermint code).  This is an optimization for the common case where an
+  application is written in Go, to save on the overhead of marshaling and
+  unmarshaling requests and responses within the same process:
+  [`abci/client/local_client.go`][local-client]
+
+- A custom remote procedure protocol built on wire-format protobuf messages
+  using a socket (the "socket protocol"): [`abci/server/socket_server.go`][socket-server]
+
+The SDK also provides a [gRPC service][sdk-grpc] accessible from outside the
+application, allowing transactions to be broadcast to the network, look up
+transactions, and simulate transaction costs.
+
+
+### RPC Transport
+
+The consensus node RPC service allows callers to query consensus parameters
+(genesis data, transactions, commits), node status (network info, health
+checks), application state (abci_query, abci_info), mempool state, and other
+attributes of the node and its application. The service also provides methods
+allowing transactions and evidence to be injected ("broadcast") into the
+blockchain.
+
+The RPC service is exposed in several ways:
+
+- HTTP GET: Queries may be sent as URI parameters, with method names in the path.
+
+- HTTP POST: Queries may be sent as JSON-RPC request messages in the body of an
+  HTTP POST request.  The server uses a custom implementation of JSON-RPC that
+  is not fully compatible with the [JSON-RPC 2.0 spec][json-rpc], but handles
+  the common cases.
+
+- Websocket: Queries may be sent as JSON-RPC request messages via a websocket.
+  This transport uses more or less the same JSON-RPC plumbing as the HTTP POST
+  handler.
+
+  The websocket endpoint also includes three methods that are _only_ exported
+  via websocket, which appear to support event subscription.
+
+- gRPC: A subset of queries may be issued in protocol buffer format to the gRPC
+  interface described above under (4). As noted, this endpoint is deprecated
+  and will be removed in v0.36.
+
+### Opportunities for Simplification
+
+**Claim:** There are too many IPC mechanisms.
+
+The preponderance of ABCI usage is via the Cosmos SDK, which means the
+application and the consensus node are compiled together into a single binary,
+and the consensus node calls the ABCI methods of the application directly as Go
+functions.
+
+We also need a true IPC transport to support ABCI applications _not_ written in
+Go.  There are also several known applications written in Rust, for example
+(including [Anoma](https://github.com/anoma/anoma), Penumbra,
+[Oasis](https://github.com/oasisprotocol/oasis-core), Twilight, and
+[Nomic](https://github.com/nomic-io/nomic)). Ideally we will have at most one
+such transport "built-in": More esoteric cases can be handled by a custom proxy.
+Pragmatically, gRPC is probably the right choice here.
+
+The primary consumers of the multi-headed "RPC service" today are the light
+client and the `tendermint` command-line client. There is probably some local
+use via curl, but I expect that is mostly ad hoc. Ethan reports that nodes are
+often configured with the ports to the RPC service blocked, which is good for
+security but complicates use by the light client.
+
+### Context: Remote Signer Issues
+
+Since the remote signer needs a secure communication channel to exchange keys
+and signatures, and is expected to run truly remotely from the node (i.e., on a
+separate physical server), there is not a whole lot we can do here. We should
+finish the deprecation and removal of the "raw" socket protocol between the
+consensus node and remote signers, but the use of gRPC is appropriate.
+
+The main improvement we can make is to simplify the implementation quite a bit,
+once we no longer need to support both "raw" and gRPC transports.
+
+### Context: ABCI Issues
+
+In the original design of ABCI, the presumption was that all access to the
+application should be mediated by the consensus node. The idea is that outside
+access could change application state and corrupt the consensus process, which
+relies on the application to be deterministic. Of course, even without outside
+access an application could behave nondeterministically, but allowing other
+programs to send it requests was seen as courting trouble.
+
+Conversely, users noted that most of the time, tools written for a particular
+application don't want to talk to the consensus module directly. The
+application "owns" the state machine the consensus engine is replicating, so
+tools that care about application state should talk to the application.
+Otherwise, they would have to bake in knowledge about Tendermint (e.g., its
+interfaces and data structures) just because of the mediation.
+
+For clients to talk directly to the application, however, there is another
+concern: The consensus node is the ABCI _client_, so it is inconvenient for the
+application to "push" work into the consensus module via ABCI itself.  The
+current implementation works around this by calling the consensus node's RPC
+service, which exposes an `ABCIQuery` kitchen-sink method that allows the
+application a way to poke ABCI messages in the other direction.
+
+Without this RPC method, you could work around this (at least in principle) by
+having the consensus module "poll" the application for work that needs done,
+but that has unsatisfactory implications for performance and robustness, as
+well as being harder to understand.
+
+There has apparently been discussion about trying to make a more bidirectional
+communication between the consensus node and the application, but this issue
+seems to still be unresolved.
+
+Another complication of ABCI is that it requires the application (server) to
+maintain [four separate connections][abci-conn]: One for "consensus" operations
+(BeginBlock, EndBlock, DeliverTx, Commit), one for "mempool" operations, one
+for "query" operations, and one for "snapshot" (state synchronization) operations.
+The rationale seems to have been that these groups of operations should be able
+to proceed concurrently with each other. In practice, it results in a very complex
+state management problem to coordinate state updates between the separate streams.
+While application authors in Go are mostly insulated from that complexity by the
+Cosmos SDK, the plumbing to maintain those separate streams is complicated, hard
+to understand, and we suspect it contains concurrency bugs and/or lock contention
+issues affecting performance that are subtle and difficult to pin down.
+
+Even without changing the semantics of any ABCI operations, this code could be
+made smaller and easier to debug by separating the management of concurrency
+and locking from the IPC transport: If all requests and responses are routed
+through one connection, the server can explicitly maintain priority queues for
+requests and responses, and make less-conservative decisions about when locks
+are (or aren't) required to synchronize state access. With independent queues,
+the server must lock conservatively, and no optimistic scheduling is practical.
+
+This would be a tedious implementation change, but should be achievable without
+breaking any of the existing interfaces. More importantly, it could potentially
+address a lot of difficult concurrency and performance problems we currently
+see anecdotally but have difficultly isolating because of how intertwined these
+separate message streams are at runtime.
+
+TODO: Impact of ABCI++ for this topic?
+
+### Context: RPC Issues
+
+The RPC system serves several masters, and has a complex surface area. I
+believe there are some improvements that can be exposed by separating some of
+these concerns.
+
+The Tendermint light client currently uses the RPC service to look up blocks
+and transactions, and to forward ABCI queries to the application.  The light
+client proxy uses the RPC service via a websocket. The Cosmos IBC relayer also
+uses the RPC service via websocket to watch for transaction events, and uses
+the `ABCIQuery` method to fetch information and proofs for posted transactions.
+
+Some work is already underway toward using P2P message passing rather than RPC
+to synchronize light client state with the rest of the network.  IBC relaying,
+however, requires access to the event system, which is currently not accessible
+except via the RPC interface. Event subscription _could_ be exposed via P2P,
+but that is a larger project since it adds P2P communication load, and might
+thus have an impact on the performance of consensus.
+
+If event subscription can be moved into the P2P network, we could entirely
+remove the websocket transport, even for clients that still need access to the
+RPC service. Until then, we may still be able to reduce the scope of the
+websocket endpoint to _only_ event subscription, by moving uses of the RPC
+server as a proxy to ABCI over to the gRPC interface.
+
+Having the RPC server still makes sense for local bootstrapping and operations,
+but can be further simplified. Here are some specific proposals:
+
+- Remove the HTTP GET interface entirely.
+
+- Simplify JSON-RPC plumbing to remove unnecessary reflection and wrapping.
+
+- Remove the gRPC interface (this is already planned for v0.36).
+
+- Separate the websocket interface from the rest of the RPC service, and
+  restrict it to only event subscription.
+
+  Eventually we should try to emove the websocket interface entirely, but we
+  will need to revisit that (probably in a new RFC) once we've done some of the
+  easier things.
+
+These changes would preserve the ability of operators to issue queries with
+curl (but would require using JSON-RPC instead of URI parameters). That would
+be a little less user-friendly, but for a use case that should not be that
+prevalent.
+
+These changes would also preserve compatibility with existing JSON-RPC based
+code paths like the `tendermint` CLI and the light client (even ahead of
+further work to remove that dependency).
+
+**Design goal:** An operator should be able to disable non-local access to the
+RPC server on any node in the network without impairing the ability of the
+network to function for service of state replication, including light clients.
+
+**Design principle:** All communication required to implement and monitor the
+consensus network should use P2P, including the various synchronizations.
+
+### Options for ABCI Transport
+
+The majority of current usage is in Go, and the majority of that is mediated by
+the Cosmos SDK, which uses the "direct call" interface. There is probably some
+opportunity to clean up the implementation of that code, notably by inverting
+which interface is at the "top" of the abstraction stack (currently it acts
+like an RPC interface, and escape-hatches into the direct call). However, this
+general approach works fine and doesn't need to be fundamentally changed.
+
+For applications _not_ written in Go, the two remaining options are the
+"socket" protocol (another variation on varint-prefixed protobuf messages over
+an unstructured stream) and gRPC. It would be nice if we could get rid of one
+of these to reduce (unneeded?) optionality.
+
+Since both the socket protocol and gRPC depend on protocol buffers, the
+"socket" protocol is the most obvious choice to remove. While gRPC is more
+complex, the set of languages that _have_ protobuf support but _lack_ gRPC
+support is small. Moreover, gRPC is already widely used in the rest of the
+ecosystem (including the Cosmos SDK).
+
+If some use case did arise later that can't work with gRPC, it would not be too
+difficult for that application author to write a little proxy (in Go) that
+bridges the convenient SDK APIs into a simpler protocol than gRPC.
+
+**Design principle:** It is better for an uncommon special case to carry the
+burdens of its specialness, than to bake an escape hatch into the infrastructure.
+
+**Recommendation:** We should deprecate and remove the socket protocol.
+
+### Options for RPC Transport
+
+[ADR 057][adr-57] proposes using gRPC for the Tendermint RPC implementation.
+This is still possible, but if we are able to simplify and decouple the
+concerns as described above, I do not think it should be necessary.
+
+While JSON-RPC is not the best possible RPC protocol for all situations, it has
+some advantages over gRPC for our domain. Specifically:
+
+- It is easy to call JSON-RPC manually from the command-line, which helps with
+  a common concern for the RPC service, local debugging and operations.
+
+  Relatedly: JSON is relatively easy for humans to read and write, and it can
+  be easily copied and pasted to share sample queries and debugging results in
+  chat, issue comments, and so on. Ideally, the RPC service will not be used
+  for activities where the costs of a text protocol are important compared to
+  its legibility and manual usability benefits.
+
+- gRPC has an enormous dependency footprint for both clients and servers, and
+  many of the features it provides to support security and performance
+  (encryption, compression, streaming, etc.) are mostly irrelevant to local
+  use. Tendermint already needs to include a gRPC client for the remote signer,
+  but if we can avoid the need for a _client_ to depend on gRPC, that is a win
+  for usability.
+
+- If we intend to migrate light clients off RPC to use P2P entirely, there is
+  no advantage to forcing a temporary migration to gRPC along the way; and once
+  the light client is not dependent on the RPC service, the efficiency of the
+  protocol is much less important.
+
+- We can still get the benefits of generated data types using protocol buffers, even
+  without using gRPC:
+
+  - Protobuf defines a standard JSON encoding for all message types so
+    languages with protobuf support do not need to worry about type mapping
+    oddities.
+
+  - Using JSON means that even languages _without_ good protobuf support can
+    implement the protocol with a bit more work, and I expect this situation to
+    be rare.
+
+Even if a language lacks a good standard JSON-RPC mechanism, the protocol is
+lightweight and can be implemented by simple send/receive over TCP or
+Unix-domain sockets with no need for code generation, encryption, etc. gRPC
+uses a complex HTTP/2 based transport that is not easily replicated.
+
+### Future Work
+
+The background and proposals sketched above focus on the existing structure of
+Tendermint and improvements we can make in the short term. It is worthwhile to
+also consider options for longer-term broader changes to the IPC ecosystem.
+The following outlines some ideas at a high level:
+
+- **Consensus service:** Today, the application and the consensus node are
+  nominally connected only via ABCI. Tendermint was originally designed with
+  the assumption that all communication with the application should be mediated
+  by the consensus node.  Based on further experience, however, the design goal
+  is now that the _application_ should be the mediator of application state.
+
+  As noted above, however, ABCI is a client/server protocol, with the
+  application as the server. For outside clients that turns out to have been a
+  good choice, but it complicates the relationship between the application and
+  the consensus node: Previously transactions were entered via the node, now
+  they are entered via the app.
+
+  We have worked around this by using the Tendermint RPC service to give the
+  application a "back channel" to the consensus node, so that it can push
+  transactions back into the consensus network. But the RPC service exposes a
+  lot of other functionality, too, including event subscription, block and
+  transaction queries, and a lot of node status information.
+
+  Even if we can't easily "fix" the orientation of the ABCI relationship, we
+  could improve isolation by splitting out the parts of the RPC service that
+  the application needs as a back-channel, and sharing those _only_ with the
+  application. By defining a "consensus service", we could give the application
+  a way to talk back limited to only the capabilities it needs. This approach
+  has the benefit that we could do it without breaking existing use, and if we
+  later did "fix" the ABCI directionality, we could drop the special case
+  without disrupting the rest of the RPC interface.
+
+- **Event service:** Right now, the IBC relayer relies on the Tendermint RPC
+  service to provide a stream of block and transaction events, which it uses to
+  discover which transactions need relaying to other chains.  While I think
+  that event subscription should eventually be handled via P2P, we could gain
+  some immediate benefit by splitting out event subscription from the rest of
+  the RPC service.
+
+  In this model, an event subscription service would be exposed on the public
+  network, but on a different endpoint. This would remove the need for the RPC
+  service to support the websocket protocol, and would allow operators to
+  isolate potentially sensitive status query results from the public network.
+
+  At the moment the relayers also use the RPC service to get block data for
+  synchronization, but work is already in progress to handle that concern via
+  the P2P layer. Once that's done, event subscription could be separated.
+
+Separating parts of the existing RPC service is not without cost: It might
+require additional connection endpoints, for example, though it is also not too
+difficult for multiple otherwise-independent services to share a connection.
+
+In return, though, it would become easier to reduce transport options and for
+operators to independently control access to sensitive data. Considering the
+viability and implications of these ideas is beyond the scope of this RFC, but
+they are documented here since they follow from the background we have already
+discussed.
+
+## References
+
+[abci]: https://github.com/tendermint/spec/tree/95cf253b6df623066ff7cd4074a94e7a3f147c7a/spec/abci
+[rpc-service]: https://docs.tendermint.com/master/rpc/
+[light-client]: https://docs.tendermint.com/master/tendermint-core/light-client.html
+[tm-cli]: https://github.com/tendermint/tendermint/tree/master/cmd/tendermint
+[cosmos-sdk]: https://github.com/cosmos/cosmos-sdk/
+[local-client]: https://github.com/tendermint/tendermint/blob/master/abci/client/local_client.go
+[socket-server]: https://github.com/tendermint/tendermint/blob/master/abci/server/socket_server.go
+[sdk-grpc]: https://pkg.go.dev/github.com/cosmos/cosmos-sdk/types/tx#ServiceServer
+[json-rpc]: https://www.jsonrpc.org/specification
+[abci-conn]: https://github.com/tendermint/spec/blob/master/spec/abci/apps.md#state
+[adr-57]: https://github.com/tendermint/tendermint/blob/master/docs/architecture/adr-057-RPC.md

docs/rfc/rfc-003-performance-questions.md

@@ -0,0 +1,283 @@
+# RFC 003: Taxonomy of potential performance issues in Tendermint 
+
+## Changelog
+
+- 2021-09-02: Created initial draft (@wbanfield)
+- 2021-09-14: Add discussion of the event system (@wbanfield)
+
+## Abstract
+
+This document discusses the various sources of performance issues in Tendermint and
+attempts to clarify what work may be required to understand and address them.
+
+## Background
+
+Performance, loosely defined as the ability of a software process to perform its work
+quickly and efficiently under load and within reasonable resource limits, is a frequent
+topic of discussion in the Tendermint project.
+To effectively address any issues with Tendermint performance we need to
+categorize the various issues, understand their potential sources, and gauge their
+impact on users.
+
+Categorizing the different known performance issues will allow us to discuss and fix them
+more systematically. This document proposes a rough taxonomy of performance issues
+and highlights areas where more research into potential performance problems is required.
+
+Understanding Tendermint's performance limitations will also be critically important
+as we make changes to many of its subsystems. Performance is a central concern for
+upcoming decisions regarding the `p2p` protocol, RPC message encoding and structure,
+database usage and selection, and consensus protocol updates.
+
+
+## Discussion
+
+This section attempts to delineate the different sections of Tendermint functionality
+that are often cited as having performance issues. It raises questions and suggests
+lines of inquiry that may be valuable for better understanding Tendermint's performance issues.
+
+As a note: We should avoid quickly adding many microbenchmarks or package level benchmarks. 
+These are prone to being worse than useless as they can obscure what _should_ be
+focused on: performance of the system from the perspective of a user. We should,
+instead, tune performance with an eye towards user needs and actions users make. These users comprise
+both operators of Tendermint chains and the people generating transactions for
+Tendermint chains. Both of these sets of users are largely aligned in wanting an end-to-end
+system that operates quickly and efficiently.
+
+REQUEST: The list below may be incomplete, if there are additional sections that are often
+cited as creating poor performance, please comment so that they may be included.
+
+### P2P
+
+#### Claim: Tendermint cannot scale to large numbers of nodes
+
+A complaint has been reported that Tendermint networks cannot scale to large numbers of nodes.
+The listed number of nodes a user reported as causing issue was in the thousands.
+We don't currently have evidence about what the upper-limit of nodes that Tendermint's
+P2P stack can scale to.
+
+We need to more concretely understand the source of issues and determine what layer
+is causing a problem. It's possible that the P2P layer, in the absence of any reactors
+sending data, is perfectly capable of managing thousands of peer connections. For
+a reasonable networking and application setup, thousands of connections should not present any
+issue for the application.
+
+We need more data to understand the problem directly. We want to drive the popularity
+and adoption of Tendermint and this will mean allowing for chains with more validators.
+We should follow up with users experiencing this issue. We may then want to add
+a series of metrics to the P2P layer to better understand the inefficiencies it produces.
+
+The following metrics can help us understand the sources of latency in the Tendermint P2P stack:
+
+* Number of messages sent and received per second
+* Time of a message spent on the P2P layer send and receive queues
+
+The following metrics exist and should be leveraged in addition to those added:
+
+* Number of peers node's connected to
+* Number of bytes per channel sent and received from each peer
+
+### Sync
+
+#### Claim: Block Syncing is slow
+
+Bootstrapping a new node in a network to the height of the rest of the network is believed to
+take longer than users would like. Block sync requires fetching all of the blocks from
+peers and placing them into the local disk for storage. A useful line of inquiry
+is understanding how quickly a perfectly tuned system _could_ fetch all of the state
+over a network so that we understand how much overhead Tendermint actually adds.
+
+The operation is likely to be _incredibly_ dependent on the environment in which
+the node is being run. The factors that will influence syncing include:
+1. Number of peers that a syncing node may fetch from.
+2. Speed of the disk that a validator is writing to.
+3. Speed of the network connection between the different peers that node is
+syncing from.
+
+We should calculate how quickly this operation _could possibly_ complete for common chains and nodes.
+To calculate how quickly this operation could possibly complete, we should assume that
+a node is reading at line-rate of the NIC and writing at the full drive speed to its
+local storage. Comparing this theoretical upper-limit to the actual sync times
+observed by node operators will give us a good point of comparison for understanding
+how much overhead Tendermint incurs.
+
+We should additionally add metrics to the blocksync operation to more clearly pinpoint
+slow operations. The following metrics should be added to the block syncing operation:
+
+* Time to fetch and validate each block
+* Time to execute a block
+* Blocks sync'd per unit time
+
+### Application
+
+Applications performing complex state transitions have the potential to bottleneck
+the Tendermint node.
+
+#### Claim: ABCI block delivery could cause slowdown
+
+ABCI delivers blocks in several methods: `BeginBlock`, `DeliverTx`, `EndBlock`, `Commit`.
+
+Tendermint delivers transactions one-by-one via the `DeliverTx` call. Most of the 
+transaction delivery in Tendermint occurs asynchronously and therefore appears unlikely to
+form a bottleneck in ABCI.
+
+After delivering all transactions, Tendermint then calls the `Commit` ABCI method.
+Tendermint [locks all access to the mempool][abci-commit-description] while `Commit`
+proceeds. This means that an application that is slow to execute all of its
+transactions or finalize state during the `Commit` method will prevent any new
+transactions from being added to the mempool.  Apps that are slow to commit will
+prevent consensus from proceeded to the next consensus height since Tendermint
+cannot validate block proposals or produce block proposals without the
+AppHash obtained from the `Commit` method. We should add a metric for each
+step in the ABCI protocol to track the amount of time that a node spends communicating
+with the application at each step.
+
+#### Claim: ABCI serialization overhead causes slowdown
+
+The most common way to run a Tendermint application is using the Cosmos-SDK.
+The Cosmos-SDK runs the ABCI application within the same process as Tendermint.
+When an application is run in the same process as Tendermint, a serialization penalty
+is not paid. This is because the local ABCI client does not serialize method calls
+and instead passes the protobuf type through directly. This can be seen
+in [local_client.go][abci-local-client-code].
+
+Serialization and deserialization in the gRPC and socket protocol ABCI methods
+may cause slowdown. While these may cause issue, they are not part of the primary
+usecase of Tendermint and do not necessarily need to be addressed at this time.
+
+### RPC
+
+#### Claim: The Query API is slow.
+
+The query API locks a mutex across the ABCI connections. This causes consensus to
+slow during queries, as ABCI is no longer able to make progress. This is known
+to be causing issue in the cosmos-sdk and is being addressed [in the sdk][sdk-query-fix]
+but a more robust solution may be required. Adding metrics to each ABCI client connection
+and message as described in the Application section of this document would allow us
+to further introspect the issue here. 
+
+#### Claim: RPC Serialization may cause slowdown
+
+The Tendermint RPC uses a modified version of JSON-RPC. This RPC powers the `broadcast_tx_*` methods,
+which is a critical method for adding transactions to Tendermint at the moment. This method is
+likely invoked quite frequently on popular networks. Being able to perform efficiently
+on this common and critical operation is very important. The current JSON-RPC implementation
+relies heavily on type introspection via reflection, which is known to be very slow in
+Go. We should therefore produce benchmarks of this method to determine how much overhead
+we are adding to what, is likely to be, a very common operation.
+
+The other JSON-RPC methods are much less critical to the core functionality of Tendermint.
+While there may other points of performance consideration within the RPC, methods that do not
+receive high volumes of requests should not be prioritized for performance consideration.
+
+NOTE: Previous discussion of the RPC framework was done in [ADR 57][adr-57] and 
+there is ongoing work to inspect and alter the JSON-RPC framework in [RFC 002][rfc-002]. 
+Much of these RPC-related performance considerations can either wait until the work of RFC 002 work is done or be
+considered concordantly with the in-flight changes to the JSON-RPC.
+
+### Protocol
+
+#### Claim: Gossiping messages is a slow process
+
+Currently, for any validator to successfully vote in a consensus _step_, it must
+receive votes from greater than 2/3 of the validators on the network. In many cases,
+it's preferable to receive as many votes as possible from correct validators.
+
+This produces a quadratic increase in messages that are communicated as more validators join the network.
+(Each of the N validators must communicate with all other N-1 validators).
+
+This large number of messages communicated per step has been identified to impact
+performance of the protocol. Given that the number of messages communicated has been
+identified as a bottleneck, it would be extremely valuable to gather data on how long
+it takes for popular chains with many validators to gather all votes within a step.
+
+Metrics that would improve visibility into this include:
+
+* Amount of time for a node to gather votes in a step.
+* Amount of time for a node to gather all block parts.
+* Number of votes each node sends to gossip (i.e. not its own votes, but votes it is
+transmitting for a peer).
+* Total number of votes each node sends to receives (A node may receive duplicate votes
+so understanding how frequently this occurs will be valuable in evaluating the performance
+of the gossip system).
+
+#### Claim: Hashing Txs causes slowdown in Tendermint
+
+Using a faster hash algorithm for Tx hashes is currently a point of discussion
+in Tendermint. Namely, it is being considered as part of the [modular hashing proposal][modular-hashing].
+It is currently unknown if hashing transactions in the Mempool forms a significant bottleneck.
+Although it does not appear to be documented as slow, there are a few open github
+issues that indicate a possible user preference for a faster hashing algorithm,
+including [issue 2187][issue-2187] and [issue 2186][issue-2186]. 
+
+It is likely worth investigating what order of magnitude Tx hashing takes in comparison to other
+aspects of adding a Tx to the mempool. It is not currently clear if the rate of adding Tx
+to the mempool is a source of user pain. We should not endeavor to make large changes to
+consensus critical components without first being certain that the change is highly
+valuable and impactful.
+
+### Digital Signatures
+
+#### Claim: Verification of digital signatures may cause slowdown in Tendermint
+
+Working with cryptographic signatures can be computationally expensive. The cosmos
+hub uses [ed25519 signatures][hub-signature]. The library performing signature
+verification in Tendermint on votes is [benchmarked][ed25519-bench] to be able to perform an `ed25519`
+signature in 75μs on a decently fast CPU. A validator in the Cosmos Hub performs
+3 sets of verifications on the signatures of the 140 validators in the Hub
+in a consensus round, during block verification, when verifying the prevotes, and
+when verifying the precommits. With no batching, this would be roughly `3ms` per
+round. It is quite unlikely, therefore, that this accounts for any serious amount
+of the ~7 seconds of block time per height in the Hub.
+
+This may cause slowdown when syncing, since the process needs to constantly verify
+signatures. It's possible that improved signature aggregation will lead to improved
+light client or other syncing performance. In general, a metric should be added
+to track block rate while blocksyncing.
+
+#### Claim: Our use of digital signatures in the consensus protocol contributes to performance issue
+
+Currently, Tendermint's digital signature verification requires that all validators
+receive all vote messages. Each validator must receive the complete digital signature
+along with the vote message that it corresponds to. This means that all N validators
+must receive messages from at least 2/3 of the N validators in each consensus
+round. Given the potential for oddly shaped network topologies and the expected
+variable network roundtrip times of a few hundred milliseconds in a blockchain,
+it is highly likely that this amount of gossiping is leading to a significant amount
+of the slowdown in the Cosmos Hub and in Tendermint consensus.
+
+### Tendermint Event System
+
+#### Claim: The event system is a bottleneck in Tendermint
+
+The Tendermint Event system is used to communicate and store information about
+internal Tendermint execution. The system uses channels internally to send messages
+to different subscribers. Sending an event [blocks on the internal channel][event-send].
+The default configuration is to [use an unbuffered channel for event publishes][event-buffer-capacity].
+Several consumers of the event system also use an unbuffered channel for reads.
+An example of this is the [event indexer][event-indexer-unbuffered], which takes an
+unbuffered subscription to the event system. The result is that these unbuffered readers
+can cause writes to the event system to block or slow down depending on contention in the
+event system. This has implications for the consensus system, which [publishes events][consensus-event-send].
+To better understand the performance of the event system, we should add metrics to track the timing of
+event sends. The following metrics would be a good start for tracking this performance:
+
+* Time in event send, labeled by Event Type
+* Time in event receive, labeled by subscriber
+* Event throughput, measured in events per unit time.
+
+### References
+[modular-hashing]: https://github.com/tendermint/tendermint/pull/6773
+[issue-2186]: https://github.com/tendermint/tendermint/issues/2186
+[issue-2187]: https://github.com/tendermint/tendermint/issues/2187
+[rfc-002]: https://github.com/tendermint/tendermint/pull/6913
+[adr-57]: https://github.com/tendermint/tendermint/blob/master/docs/architecture/adr-057-RPC.md
+[issue-1319]: https://github.com/tendermint/tendermint/issues/1319
+[abci-commit-description]: https://github.com/tendermint/spec/blob/master/spec/abci/apps.md#commit
+[abci-local-client-code]: https://github.com/tendermint/tendermint/blob/511bd3eb7f037855a793a27ff4c53c12f085b570/abci/client/local_client.go#L84
+[hub-signature]: https://github.com/cosmos/gaia/blob/0ecb6ed8a244d835807f1ced49217d54a9ca2070/docs/resources/genesis.md#consensus-parameters
+[ed25519-bench]: https://github.com/oasisprotocol/curve25519-voi/blob/d2e7fc59fe38c18ca990c84c4186cba2cc45b1f9/PERFORMANCE.md
+[event-send]: https://github.com/tendermint/tendermint/blob/5bd3b286a2b715737f6d6c33051b69061d38f8ef/libs/pubsub/pubsub.go#L338
+[event-buffer-capacity]: https://github.com/tendermint/tendermint/blob/5bd3b286a2b715737f6d6c33051b69061d38f8ef/types/event_bus.go#L14
+[event-indexer-unbuffered]: https://github.com/tendermint/tendermint/blob/5bd3b286a2b715737f6d6c33051b69061d38f8ef/state/indexer/indexer_service.go#L39
+[consensus-event-send]: https://github.com/tendermint/tendermint/blob/5bd3b286a2b715737f6d6c33051b69061d38f8ef/internal/consensus/state.go#L1573
+[sdk-query-fix]: https://github.com/cosmos/cosmos-sdk/pull/10045

docs/rfc/rfc-004-e2e-framework.rst

@@ -0,0 +1,213 @@
+========================================
+RFC 004: E2E Test Framework Enhancements
+========================================
+
+Changelog
+---------
+
+- 2021-09-14: started initial draft (@tychoish)
+
+Abstract
+--------
+
+This document discusses a series of improvements to the e2e test framework
+that we can consider during the next few releases to help boost confidence in
+Tendermint releases, and improve developer efficiency.
+
+Background
+----------
+
+During the 0.35 release cycle, the E2E tests were a source of great
+value, helping to identify a number of bugs before release. At the same time,
+the tests were not consistently passing during this time, thereby reducing
+their value, and forcing the core development team to allocate time and energy
+to maintaining and chasing down issues with the e2e tests and the test
+harness. The experience of this release cycle calls to mind a series of
+improvements to the test framework, and this document attempts to capture
+these improvements, along with motivations, and potential for impact.
+
+Projects
+--------
+
+Flexible Workload Generation
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Presently the e2e suite contains a single workload generation pattern, which
+exists simply to ensure that the test networks have some work during their
+runs. However, the shape and volume of the work is very consistent and is very
+gentle to help ensure test reliability.
+
+We don't need a complex workload generation framework, but being able to have 
+a few different workload shapes available for test networks, both generated and
+hand-crafted, would be useful.
+
+Workload patterns/configurations might include:
+
+- transaction targeting patterns (include light nodes, round robin, target
+  individual nodes)
+
+- variable transaction size over time.
+
+- transaction broadcast option (synchronously, checked, fire-and-forget,
+  mixed).
+
+- number of transactions to submit.
+
+- non-transaction workloads: (evidence submission, query, event subscription.)
+
+Configurable Generator
+~~~~~~~~~~~~~~~~~~~~~~
+
+The nightly e2e suite is defined by the `testnet generator
+<https://github.com/tendermint/tendermint/blob/master/test/e2e/generator/generate.go#L13-L65>`_,
+and it's difficult to add dimensions or change the focus of the test suite in
+any way without modifying the implementation of the generator. If the
+generator were more configurable, potentially via a file rather than in
+the Go implementation, we could modify the focus of the test suite on the
+fly.
+
+Features that we might want to configure:
+
+- number of test networks to generate of various topologies, to improve
+  coverage of different configurations.
+
+- test application configurations (to modify the latency of ABCI calls, etc.)
+
+- size of test networks.
+
+- workload shape and behavior.
+
+- initial sync and catch-up configurations.
+
+The workload generator currently provides runtime options for limiting the
+generator to specific types of P2P stacks, and for generating multiple groups
+of test cases to support parallelism. The goal is to extend this pattern and
+avoid hardcoding the matrix of test cases in the generator code.  Once the
+testnet configuration generation behavior is configurable at runtime,
+developers may be able to use the e2e framework to validate changes before
+landing changes that break e2e tests a day later.
+
+In addition to the autogenerated suite, it might make sense to maintain a
+small collection of hand-crafted cases that exercise configurations of
+concern, to run as part of the nightly (or less frequent) loop.
+
+Implementation Plan Structure
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+As a development team, we should determine the features should impact the e2e
+testing early in the development cycle, and if we intend to modify the e2e
+tests to exercise a feature, we should identify this early and begin the
+integration process as early as possible.
+
+To facilitate this, we should adopt a practice whereby we exercise specific
+features that are currently under development more rigorously in the e2e
+suite, and then as development stabilizes we can reduce the number or weight
+of these features in the suite.
+
+As of 0.35 there are essentially two end to end tests: the suite of 64
+generated test networks, and the hand crafted `ci.toml` test case. The
+generated test cases help provide systemtic coverage, while the `ci` run 
+provides coverage for a large number of features. 
+
+Reduce Cycle Time
+~~~~~~~~~~~~~~~~~
+
+One of the barriers to leveraging the e2e framework, and one of the challenges
+in debugging failures, is the cycle time of running a single test iteration is
+quite high: 5 minutes to build the docker image, plus the time to run the test
+or tests.
+
+There are a number of improvements and enhancements that can reduce the cycle
+time in practice:
+
+- reduce the amount of time required to build the docker image used in these
+  tests. Without the dependency on CGo, the tendermint binaries could be
+  (cross) compiled outside of the docker container and then injected into
+  them, which would take better advantage of docker's native caching,
+  although, without the dependency on CGo there would be no hard requirement
+  for the e2e tests to use docker.
+
+- support test parallelism. Because of the way the testnets are orchestrated
+  a single system can really only run one network at a time. For executions
+  (local or remote) with more resources, there's no reason to run a few
+  networks in parallel to reduce the feedback time.
+
+- prune testnet configurations that are unlikely to provide good signal, to
+  shorten the time to feedback.
+
+- apply some kind of tiered approach to test execution, to improve the
+  legibility of the test result. For example order tests by the dependency of
+  their features, or run test networks without perturbations before running
+  that configuration with perturbations, to be able to isolate the impact of
+  specific features.
+
+- orchestrate the test harness directly from go test rather than via a special
+  harness and shell scripts so e2e tests may more naively fit into developers
+  existing workflows.
+
+Many of these improvements, particularly, reducing the build time will also
+reduce the time to get feedback during automated builds.
+
+Deeper Insights
+~~~~~~~~~~~~~~~
+
+When a test network fails, it's incredibly difficult to understand _why_ the
+network failed, as the current system provides very little insight into the
+system outside of the process logs. When a test network stalls or fails
+developers should be able to quickly and easily get a sense of the state of
+the network and all nodes.
+
+Improvements in persuit of this goal, include functionality that would help
+node operators in production environments by improving the quality and utility
+of the logging messages and other reported metrics, but also provide some
+tools to collect and aggregate this data for developers in the context of test
+networks.
+
+- Interleave messages from all nodes in the network to be able to correlate
+  events during the test run.
+
+- Collect structured metrics of the system operation (CPU/MEM/IO) during the
+  test run, as well as from each tendermint/application process.
+
+- Build (simple) tools to be able to render and summarize the data collected
+  during the test run to answer basic questions about test outcome.
+
+Flexible Assertions
+~~~~~~~~~~~~~~~~~~~
+
+Currently, all assertions run for every test network, which makes the
+assertions pretty bland, and the framework primarily useful as a smoke-test
+framework, but it might be useful to be able to write and run different
+tests for different configurations. This could allow us to test outside of the
+happy-path.
+
+In general our existing assertions occupy a fraction of the total test time,
+so the relative cost of adding a few extra test assertions would be of limited
+cost, and could help build confidence.
+
+Additional Kinds of Testing
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The existing e2e suite, exercises networks of nodes that have homogeneous
+tendermint version, stable configuration, that are expected to make
+progress. There are many other possible test configurations that may be
+interesting to engage with. These could include dimensions, such as:
+
+- Multi-version testing to exercise our compatibility guarantees for networks
+  that might have different tendermint versions.
+
+- As a flavor or mult-version testing, include upgrade testing, to build
+  confidence in migration code and procedures.
+
+- Additional test applications, particularly practical-type applciations
+  including some that use gaiad and/or the cosmos-sdk. Test-only applications
+  that simulate other kinds of applications (e.g. variable application
+  operation latency.)
+
+- Tests of "non-viable" configurations that ensure that forbidden combinations
+  lead to halts.
+
+References
+----------
+
+- `ADR 66: End-to-End Testing <../architecture/adr-66-e2e-testing.md>`_

docs/rfc/rfc-005-event-system.rst

@@ -0,0 +1,122 @@
+=====================
+RFC 005: Event System
+=====================
+
+Changelog
+---------
+
+- 2021-09-17: Initial Draft (@tychoish)
+
+Abstract
+--------
+
+The event system within Tendermint, which supports a lot of core
+functionality, also represents a major infrastructural liability. As part of
+our upcoming review of the RPC interfaces and our ongoing thoughts about
+stability and performance, as well as the preparation for Tendermint 1.0, we
+should revisit the design and implementation of the event system. This
+document discusses both the current state of the system and potential
+directions for future improvement.
+
+Background
+----------
+
+Current State of Events
+~~~~~~~~~~~~~~~~~~~~~~~
+
+The event system makes it possible for clients, both internal and external,
+to receive notifications of state replication events, such as new blocks,
+new transactions, validator set changes, as well as intermediate events during
+consensus. Because the event system is very cross cutting, the behavior and
+performance of the event publication and subscription system has huge impacts
+for all of Tendermint.
+
+The subscription service is exposed over the RPC interface, but also powers
+the indexing (e.g. to an external database,) and is the mechanism by which
+`BroadcastTxCommit` is able to wait for transactions to land in a block.
+
+The current pubsub mechanism relies on a couple of buffered channels,
+primarily between all event creators and subscribers, but also for each
+subscription. The result of this design is that, in some situations with the
+right collection of slow subscription consumers the event system can put
+backpressure on the consensus state machine and message gossiping in the
+network, thereby causing nodes to lag.
+
+Improvements
+~~~~~~~~~~~~
+
+The current system relies on implicit, bounded queues built by the buffered channels,
+and though threadsafe, can force all activity within Tendermint to serialize,
+which does not need to happen. Additionally, timeouts for subscription
+consumers related to the implementation of the RPC layer, may complicate the
+use of the system.
+
+References
+~~~~~~~~~~
+
+- Legacy Implementation
+  - `publication of events <https://github.com/tendermint/tendermint/blob/master/libs/pubsub/pubsub.go#L333-L345>`_ 
+  - `send operation <https://github.com/tendermint/tendermint/blob/master/libs/pubsub/pubsub.go#L489-L527>`_ 
+  - `send loop <https://github.com/tendermint/tendermint/blob/master/libs/pubsub/pubsub.go#L381-L402>`_
+- Related RFCs 
+  - `RFC 002: IPC Ecosystem <./rfc-002-ipc-ecosystem.md>`_ 
+  - `RFC 003: Performance Questions <./rfc-003-performance-questions.md>`_ 
+
+Discussion
+----------
+
+Changes to Published Events
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+As part of this process, the Tendermint team should do a study of the existing
+event types and ensure that there are viable production use cases for
+subscriptions to all event types. Instinctively it seems plausible that some
+of the events may not be useable outside of tendermint, (e.g. ``TimeoutWait``
+or ``NewRoundStep``) and it might make sense to remove them. Certainly, it
+would be good to make sure that we don't maintain infrastructure for unused or
+un-useful message indefinitely.
+
+Blocking Subscription
+~~~~~~~~~~~~~~~~~~~~~
+
+The blocking subscription mechanism makes it possible to have *send*
+operations into the subscription channel be un-buffered (the event processing
+channel is still buffered.) In the blocking case, events from one subscription
+can block processing that event for other non-blocking subscriptions. The main
+case, it seems for blocking subscriptions is ensuring that a transaction has
+been committed to a block for ``BroadcastTxCommit``. Removing blocking
+subscriptions entirely, and potentially finding another way to implement
+``BroadcastTxCommit``, could lead to important simplifications and
+improvements to throughput without requiring large changes.
+
+Subscription Identification
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Before `#6386 <https://github.com/tendermint/tendermint/pull/6386>`_, all
+subscriptions were identified by the combination of a client ID and a query,
+and with that change, it became possible to identify all subscription given
+only an ID, but compatibility with the legacy identification means that there's a
+good deal of legacy code as well as client side efficiency that could be
+improved. 
+
+Pubsub Changes
+~~~~~~~~~~~~~~
+
+The pubsub core should be implemented in a way that removes the possibility of
+backpressure from the event system to impact the core system *or* for one
+subscription to impact the behavior of another area of the
+system. Additionally, because the current system is implemented entirely in
+terms of a collection of buffered channels, the event system (and large
+numbers of subscriptions) can be a source of memory pressure. 
+
+These changes could include: 
+
+- explicit cancellation and timeouts promulgated from callers (e.g. RPC end
+  points, etc,) this should be done using contexts.
+
+- subscription system should be able to spill to disk to avoid putting memory
+  pressure on the core behavior of the node (consensus, gossip).
+  
+- subscriptions implemented as cursors rather than channels, with either
+  condition variables to simulate the existing "push" API or a client side
+  iterator API with some kind of long polling-type interface. 

docs/rfc/rfc-template.md

@@ -0,0 +1,35 @@
+# RFC {RFC-NUMBER}: {TITLE}
+
+## Changelog
+
+- {date}: {changelog}
+
+## Abstract
+
+> A brief high-level synopsis of the topic of discussion for this RFC, ideally
+> just a few sentences.  This should help the reader quickly decide whether the
+> rest of the discussion is relevant to their interest.
+
+## Background
+
+> Any context or orientation needed for a reader to understand and participate
+> in the substance of the Discussion. If necessary, this section may include
+> links to other documentation or sources rather than restating existing
+> material, but should provide enough detail that the reader can tell what they
+> need to read to be up-to-date.
+
+### References
+
+> Links to external materials needed to follow the discussion may be added here.
+>
+> In addition, if the discussion in a request for comments leads to any design
+> decisions, it may be helpful to add links to the ADR documents here after the
+> discussion has settled.
+
+## Discussion
+
+> This section contains the core of the discussion.
+>
+> There is no fixed format for this section, but ideally changes to this
+> section should be updated before merging to reflect any discussion that took
+> place on the PR that made those changes.

docs/roadmap/README.md

@@ -0,0 +1,6 @@
+---
+order: false
+parent:
+  title: Roadmap
+  order: 7
+---

docs/roadmap/roadmap.md

@@ -0,0 +1,97 @@
+---
+order: 1
+---
+
+# Tendermint Roadmap
+
+*Last Updated: Friday 8 October 2021*
+
+This document endeavours to inform the wider Tendermint community about development plans and priorities for Tendermint Core, and when we expect features to be delivered. It is intended to broadly inform all users of Tendermint, including application developers, node operators, integrators, and the engineering and research teams.
+
+Anyone wishing to propose work to be a part of this roadmap should do so by opening an [issue](https://github.com/tendermint/spec/issues/new/choose) in the spec. Bug reports and other implementation concerns should be brought up in the [core repository](https://github.com/tendermint/tendermint).
+
+This roadmap should be read as a high-level guide to plans and priorities, rather than a commitment to schedules and deliverables. Features earlier on the roadmap will generally be more specific and detailed than those later on. We will update this document periodically to reflect the current status.
+
+The upgrades are split into two components: **Epics**, the features that define a release and to a large part dictate the timing of releases; and **minors**, features of smaller scale and lower priority, that could land in neighboring releases.
+
+## V0.35 (completed Q3 2021)
+
+### Prioritized Mempool
+
+Transactions were previously added to blocks in the order with which they arrived to the mempool. Adding a priority field via `CheckTx` gives applications more control over which transactions make it into a block. This is important in the presence of transaction fees. [More](https://github.com/tendermint/tendermint/blob/master/docs/architecture/adr-067-mempool-refactor.md)
+
+### Refactor of the P2P Framework
+
+The Tendermint P2P system is undergoing a large redesign to improve its performance and reliability. The first phase of this redesign is included in 0.35. This phase cleans and decouples abstractions, improves peer lifecycle management, peer address handling and enables pluggable transports. It is implemented to be protocol-compatible with the previous implementation. [More](https://github.com/tendermint/tendermint/blob/master/docs/architecture/adr-062-p2p-architecture.md)
+
+### State Sync Improvements
+
+Following the initial version of state sync, several improvements have been made. These include the addition of [Reverse Sync](https://github.com/tendermint/tendermint/blob/master/docs/architecture/adr-068-reverse-sync.md) needed for evidence handling, the introduction of a [P2P State Provider](https://github.com/tendermint/tendermint/pull/6807) as an alternative to RPC endpoints, new configuration parameters to adjust throughput, and several bug fixes.
+
+### Custom event indexing + PSQL Indexer
+
+Added a new `EventSink` interface to allow alternatives to Tendermint's proprietary transaction indexer. We also added a PostgreSQL Indexer implementation, allowing rich SQL-based index queries. [More](https://github.com/tendermint/tendermint/blob/master/docs/architecture/adr-065-custom-event-indexing.md)
+
+### Minor Works
+
+- Several Go packages were reorganized to make the distinction between public APIs and implementation details more clear.
+- Block indexer to index begin-block and end-block events. [More](https://github.com/tendermint/tendermint/pull/6226)
+- Block, state, evidence, and light storage keys were reworked to preserve lexicographic order. This change requires a database migration. [More](https://github.com/tendermint/tendermint/pull/5771)
+- Introduciton of Tendermint modes. Part of this change includes the possibility to run a separate seed node that runs the PEX reactor only. [More](https://github.com/tendermint/tendermint/blob/master/docs/architecture/adr-052-tendermint-mode.md)
+
+## V0.36 (expected Q1 2022)
+
+### ABCI++
+
+An overhaul of the existing interface between the application and consensus, to give the application more control over block construction. ABCI++ adds new hooks allowing modification of transactions before they get into a block, verification of a block before voting, injection of signed information into votes, and more compact delivery of blocks after agreement (to allow for concurrent execution). [More](https://github.com/tendermint/spec/blob/master/rfc/004-abci%2B%2B.md)
+
+### Proposer-Based Timestamps
+
+Proposer-based timestamps are a replacement of [BFT time](https://docs.tendermint.com/master/spec/consensus/bft-time.html), whereby the proposer chooses a timestamp and validators vote on the block only if the timestamp is considered *timely*. This increases reliance on an accurate local clock, but in exchange makes block time more reliable and resistant to faults. This has important use cases in light clients, IBC relayers, CosmosHub inflation and enabling signature aggregation. [More](https://github.com/tendermint/tendermint/blob/master/docs/architecture/adr-071-proposer-based-timestamps.md)
+
+### Soft Upgrades
+
+We are working on a suite of tools and patterns to make it easier for both node operators and application developers to quickly and safely upgrade to newer versions of Tendermint. [More](https://github.com/tendermint/spec/pull/222)
+
+### Minor Works
+
+- Remove the "legacy" P2P framework, and clean up of P2P package. [More](https://github.com/tendermint/tendermint/issues/5670)
+- Remove the global mutex from the local ABCI client to enable application-controlled concurrency. [More](https://github.com/tendermint/tendermint/issues/7073)
+- Enable P2P support for light clients
+- Node orchestration of services + Node initialization and composibility
+- Remove redundancy in several data structures. Remove unused components such as the block sync v2 reactor, gRPC in the RPC layer, and the socket-based remote signer.
+- Improve node visibility by introducing more metrics
+
+## V0.37 (expected Q3 2022)
+
+### Complete P2P Refactor
+
+Finish the final phase of the P2P system. Ongoing research and planning is taking place to decide whether to adopt [libp2p](https://libp2p.io/), alternative transports to `MConn` such as [QUIC](https://en.wikipedia.org/wiki/QUIC) and handshake/authentication protocols such as [Noise](https://noiseprotocol.org/). Research into more advanced gossiping techniques.
+
+### Streamline Storage Engine
+
+Tendermint currently has an abstraction to allow support for multiple database backends. This generality incurs maintenance overhead and interferes with application-specific optimizations that Tendermint could use (ACID guarantees, etc.). We plan to converge on a single database and streamline the Tendermint storage engine. [More](https://github.com/tendermint/tendermint/pull/6897)
+
+### Evaluate Interprocess Communication
+
+Tendermint nodes currently have multiple areas of communication with other processes (ABCI, remote-signer, P2P, JSONRPC, websockets, events as examples). Many of these have multiple implementations in which a single suffices. Consolidate and clean up IPC. [More](https://github.com/tendermint/tendermint/blob/master/docs/rfc/rfc-002-ipc-ecosystem.md)
+
+### Minor Works
+
+- Amnesia attack handling. [More](https://github.com/tendermint/tendermint/issues/5270)
+- Remove / Update Consensus WAL. [More](https://github.com/tendermint/tendermint/issues/6397)
+- Signature Aggregation. [More](https://github.com/tendermint/tendermint/issues/1319)
+- Remove gogoproto dependency. [More](https://github.com/tendermint/tendermint/issues/5446)
+
+## V1.0 (expected Q4 2022)
+
+Has the same feature set as V0.37 but with a focus towards testing, protocol correctness and minor tweaks to ensure a stable product. Such work might include extending the [consensus testing framework](https://github.com/tendermint/tendermint/issues/5920), the use of canary/long-lived testnets and greater integration tests.
+
+## Post 1.0 Work
+
+- Improved block propagation with erasure coding and/or compact blocks. [More](https://github.com/tendermint/spec/issues/347)
+- Consensus engine refactor
+- Bidirectional ABCI
+- Randomized Leader Election
+- ZK proofs / other cryptographic primitives
+- Multichain Tendermint

docs/tendermint-core/README.md

@@ -14,7 +14,12 @@ This section dives into the internals of Go-Tendermint.
 - [Subscribing to events](./subscription.md)
 - [Block Structure](./block-structure.md)
 - [RPC](./rpc.md)
-- [Block Sync](./block-sync.md)
-- [State Sync](./state-sync.md)
-- [Mempool](./mempool.md)
+- [Block Sync](./block-sync/README.md)
+- [State Sync](./state-sync/README.md)
+- [Mempool](./mempool/README.md)
 - [Light Client](./light-client.md)
+- [Consensus](./consensus/README.md)
+- [Peer Exachange (PEX)](./pex/README.md)
+- [Evidence](./evidence/README.md)
+
+For full specifications refer to the [spec repo](https://github.com/tendermint/spec).

docs/tendermint-core/block-sync/README.md

@@ -1,7 +1,11 @@
 ---
-order: 10
+order: 1
+parent:
+  title: Block Sync
+  order: 6
 ---
 
+
 # Block Sync
 *Formerly known as Fast Sync*
 
@@ -17,9 +21,9 @@ consensus gossip protocol.
 
 ## Using Block Sync
 
-To support faster syncing, Tendermint offers a `fast-sync` mode, which
+To support faster syncing, Tendermint offers a `blocksync` mode, which
 is enabled by default, and can be toggled in the `config.toml` or via
-`--fast_sync=false`.
+`--blocksync.enable=false`.
 
 In this mode, the Tendermint daemon will sync hundreds of times faster
 than if it used the real-time consensus process. Once caught up, the
@@ -29,18 +33,23 @@ has at least one peer and it's height is at least as high as the max
 reported peer height. See [the IsCaughtUp
 method](https://github.com/tendermint/tendermint/blob/b467515719e686e4678e6da4e102f32a491b85a0/blockchain/pool.go#L128).
 
-Note: There are two versions of Block Sync. We recommend using v0 as v2 is still in beta.
+Note: There are multiple versions of Block Sync. Please use v0 as the other versions are no longer supported.
   If you would like to use a different version you can do so by changing the version in the `config.toml`:
 
 ```toml
 #######################################################
 ###       Block Sync Configuration Connections       ###
 #######################################################
-[fastsync]
+[blocksync]
+
+# If this node is many blocks behind the tip of the chain, BlockSync
+# allows them to catchup quickly by downloading blocks in parallel
+# and verifying their commits
+enable = true
 
 # Block Sync version to use:
-#   1) "v0" (default) - the legacy Block Sync implementation
-#   2) "v2" - complete redesign of v0, optimized for testability & readability
+#   1) "v0" (default) - the standard Block Sync implementation
+#   2) "v2" - DEPRECATED, please use v0
 version = "v0"
 ```
 
@@ -55,4 +64,8 @@ the network best height, it will switches to the state sync mechanism and then e
 another event for exposing the fast-sync `complete` status and the state `height`.
 
 The user can query the events by subscribing `EventQueryBlockSyncStatus`
-Please check [types](https://pkg.go.dev/github.com/tendermint/tendermint/types?utm_source=godoc#pkg-constants) for the details.
+Please check [types](https://pkg.go.dev/github.com/tendermint/tendermint/types?utm_source=godoc#pkg-constants) for the details.
+
+## Implementation
+
+To read more on the implamentation please see the [reactor doc](./reactor.md) and the [implementation doc](./implementation.md)

docs/tendermint-core/block-sync/implementation.md

@@ -0,0 +1,47 @@
+---
+order: 3
+---
+
+# Implementation
+
+## Blocksync Reactor
+
+- coordinates the pool for syncing
+- coordinates the store for persistence
+- coordinates the playing of blocks towards the app using a sm.BlockExecutor
+- handles switching between fastsync and consensus
+- it is a p2p.BaseReactor
+- starts the pool.Start() and its poolRoutine()
+- registers all the concrete types and interfaces for serialisation
+
+### poolRoutine
+
+- listens to these channels:
+    - pool requests blocks from a specific peer by posting to requestsCh, block reactor then sends
+    a &bcBlockRequestMessage for a specific height
+    - pool signals timeout of a specific peer by posting to timeoutsCh
+    - switchToConsensusTicker to periodically try and switch to consensus
+    - trySyncTicker to periodically check if we have fallen behind and then catch-up sync
+        - if there aren't any new blocks available on the pool it skips syncing
+- tries to sync the app by taking downloaded blocks from the pool, gives them to the app and stores
+  them on disk
+- implements Receive which is called by the switch/peer
+    - calls AddBlock on the pool when it receives a new block from a peer
+
+## Block Pool
+
+- responsible for downloading blocks from peers
+- makeRequestersRoutine()
+    - removes timeout peers
+    - starts new requesters by calling makeNextRequester()
+- requestRoutine():
+    - picks a peer and sends the request, then blocks until:
+        - pool is stopped by listening to pool.Quit
+        - requester is stopped by listening to Quit
+        - request is redone
+        - we receive a block
+            - gotBlockCh is strange
+
+## Go Routines in Blocksync Reactor
+
+![Go Routines Diagram](img/bc-reactor-routines.png)

docs/tendermint-core/block-sync/reactor.md

@@ -0,0 +1,278 @@
+---
+order: 2
+---
+# Reactor
+
+The Blocksync Reactor's high level responsibility is to enable peers who are
+far behind the current state of the consensus to quickly catch up by downloading
+many blocks in parallel, verifying their commits, and executing them against the
+ABCI application.
+
+Tendermint full nodes run the Blocksync Reactor as a service to provide blocks
+to new nodes. New nodes run the Blocksync Reactor in "fast_sync" mode,
+where they actively make requests for more blocks until they sync up.
+Once caught up, "fast_sync" mode is disabled and the node switches to
+using (and turns on) the Consensus Reactor.
+
+## Architecture and algorithm
+
+The Blocksync reactor is organised as a set of concurrent tasks:
+
+- Receive routine of Blocksync Reactor
+- Task for creating Requesters
+- Set of Requesters tasks and - Controller task.
+
+![Blocksync Reactor Architecture Diagram](img/bc-reactor.png)
+
+### Data structures
+
+These are the core data structures necessarily to provide the Blocksync Reactor logic.
+
+Requester data structure is used to track assignment of request for `block` at position `height` to a peer with id equals to `peerID`.
+
+```go
+type Requester {
+  mtx          Mutex
+  block        Block
+  height       int64
+  peerID       p2p.ID
+  redoChannel  chan p2p.ID //redo may send multi-time; peerId is used to identify repeat
+}
+```
+
+Pool is a core data structure that stores last executed block (`height`), assignment of requests to peers (`requesters`), current height for each peer and number of pending requests for each peer (`peers`), maximum peer height, etc.
+
+```go
+type Pool {
+  mtx                Mutex
+  requesters         map[int64]*Requester
+  height             int64
+  peers              map[p2p.ID]*Peer
+  maxPeerHeight      int64
+  numPending         int32
+  store              BlockStore
+  requestsChannel    chan<- BlockRequest
+  errorsChannel      chan<- peerError
+}
+```
+
+Peer data structure stores for each peer current `height` and number of pending requests sent to the peer (`numPending`), etc.
+
+```go
+type Peer struct {
+  id           p2p.ID
+  height       int64
+  numPending   int32
+  timeout      *time.Timer
+  didTimeout   bool
+}
+```
+
+BlockRequest is internal data structure used to denote current mapping of request for a block at some `height` to a peer (`PeerID`).
+
+```go
+type BlockRequest {
+  Height int64
+  PeerID p2p.ID
+}
+```
+
+### Receive routine of Blocksync Reactor
+
+It is executed upon message reception on the BlocksyncChannel inside p2p receive routine. There is a separate p2p receive routine (and therefore receive routine of the Blocksync Reactor) executed for each peer. Note that try to send will not block (returns immediately) if outgoing buffer is full.
+
+```go
+handleMsg(pool, m):
+    upon receiving bcBlockRequestMessage m from peer p:
+      block = load block for height m.Height from pool.store
+      if block != nil then
+        try to send BlockResponseMessage(block) to p
+      else
+        try to send bcNoBlockResponseMessage(m.Height) to p
+
+    upon receiving bcBlockResponseMessage m from peer p:
+      pool.mtx.Lock()
+      requester = pool.requesters[m.Height]
+      if requester == nil then
+        error("peer sent us a block we didn't expect")
+        continue
+
+      if requester.block == nil and requester.peerID == p then
+        requester.block = m
+        pool.numPending -= 1  // atomic decrement
+        peer = pool.peers[p]
+        if peer != nil then
+          peer.numPending--
+          if peer.numPending == 0 then
+            peer.timeout.Stop()
+            // NOTE: we don't send Quit signal to the corresponding requester task!
+        else
+          trigger peer timeout to expire after peerTimeout
+      pool.mtx.Unlock()
+
+
+    upon receiving bcStatusRequestMessage m from peer p:
+      try to send bcStatusResponseMessage(pool.store.Height)
+
+    upon receiving bcStatusResponseMessage m from peer p:
+      pool.mtx.Lock()
+      peer = pool.peers[p]
+      if peer != nil then
+        peer.height = m.height
+      else
+        peer = create new Peer data structure with id = p and height = m.Height
+        pool.peers[p] = peer
+
+      if m.Height > pool.maxPeerHeight then
+        pool.maxPeerHeight = m.Height
+      pool.mtx.Unlock()
+
+onTimeout(p):
+  send error message to pool error channel
+  peer = pool.peers[p]
+  peer.didTimeout = true
+```
+
+### Requester tasks
+
+Requester task is responsible for fetching a single block at position `height`.
+
+```go
+fetchBlock(height, pool):
+  while true do {
+    peerID = nil
+    block = nil
+    peer = pickAvailablePeer(height)
+    peerID = peer.id
+
+    enqueue BlockRequest(height, peerID) to pool.requestsChannel
+    redo = false
+    while !redo do
+      select {
+        upon receiving Quit message do
+          return
+        upon receiving redo message with id on redoChannel do
+          if peerID == id {
+            mtx.Lock()
+            pool.numPending++
+            redo = true
+            mtx.UnLock()
+          }
+      }
+    }
+
+pickAvailablePeer(height):
+  selectedPeer = nil
+  while selectedPeer = nil do
+    pool.mtx.Lock()
+    for each peer in pool.peers do
+      if !peer.didTimeout and peer.numPending < maxPendingRequestsPerPeer and peer.height >= height then
+        peer.numPending++
+        selectedPeer = peer
+        break
+    pool.mtx.Unlock()
+
+    if selectedPeer = nil then
+      sleep requestIntervalMS
+
+  return selectedPeer
+```
+
+sleep for requestIntervalMS
+
+### Task for creating Requesters
+
+This task is responsible for continuously creating and starting Requester tasks.
+
+```go
+createRequesters(pool):
+  while true do
+    if !pool.isRunning then break
+    if pool.numPending < maxPendingRequests or size(pool.requesters) < maxTotalRequesters then
+      pool.mtx.Lock()
+      nextHeight = pool.height + size(pool.requesters)
+      requester = create new requester for height nextHeight
+      pool.requesters[nextHeight] = requester
+      pool.numPending += 1 // atomic increment
+      start requester task
+      pool.mtx.Unlock()
+    else
+      sleep requestIntervalMS
+      pool.mtx.Lock()
+      for each peer in pool.peers do
+        if !peer.didTimeout && peer.numPending > 0 && peer.curRate < minRecvRate then
+          send error on pool error channel
+          peer.didTimeout = true
+        if peer.didTimeout then
+          for each requester in pool.requesters do
+            if requester.getPeerID() == peer then
+              enqueue msg on requestor's redoChannel
+          delete(pool.peers, peerID)
+      pool.mtx.Unlock()
+```
+
+### Main blocksync reactor controller task
+
+```go
+main(pool):
+  create trySyncTicker with interval trySyncIntervalMS
+  create statusUpdateTicker with interval statusUpdateIntervalSeconds
+  create switchToConsensusTicker with interval switchToConsensusIntervalSeconds
+
+  while true do
+    select {
+   upon receiving BlockRequest(Height, Peer) on pool.requestsChannel:
+     try to send bcBlockRequestMessage(Height) to Peer
+
+   upon receiving error(peer) on errorsChannel:
+     stop peer for error
+
+   upon receiving message on statusUpdateTickerChannel:
+     broadcast bcStatusRequestMessage(bcR.store.Height) // message sent in a separate routine
+
+   upon receiving message on switchToConsensusTickerChannel:
+     pool.mtx.Lock()
+     receivedBlockOrTimedOut = pool.height > 0 || (time.Now() - pool.startTime) > 5 Seconds
+     ourChainIsLongestAmongPeers = pool.maxPeerHeight == 0 || pool.height >= pool.maxPeerHeight
+     haveSomePeers = size of pool.peers > 0
+     pool.mtx.Unlock()
+     if haveSomePeers && receivedBlockOrTimedOut && ourChainIsLongestAmongPeers then
+       switch to consensus mode
+
+          upon receiving message on trySyncTickerChannel:
+            for i = 0; i < 10; i++ do
+              pool.mtx.Lock()
+              firstBlock = pool.requesters[pool.height].block
+              secondBlock = pool.requesters[pool.height].block
+              if firstBlock == nil or secondBlock == nil then continue
+              pool.mtx.Unlock()
+              verify firstBlock using LastCommit from secondBlock
+              if verification failed
+                pool.mtx.Lock()
+                peerID = pool.requesters[pool.height].peerID
+                redoRequestsForPeer(peerId)
+                delete(pool.peers, peerID)
+                stop peer peerID for error
+                pool.mtx.Unlock()
+              else
+                delete(pool.requesters, pool.height)
+                save firstBlock to store
+                pool.height++
+                execute firstBlock
+    }
+
+redoRequestsForPeer(pool, peerId):
+  for each requester in pool.requesters do
+    if requester.getPeerID() == peerID
+     enqueue msg on redoChannel for requester
+```
+
+## Channels
+
+Defines `maxMsgSize` for the maximum size of incoming messages,
+`SendQueueCapacity` and `RecvBufferCapacity` for maximum sending and
+receiving buffers respectively. These are supposed to prevent amplification
+attacks by setting up the upper limit on how much data we can receive & send to
+a peer.
+
+Sending incorrectly encoded data will result in stopping the peer.

docs/tendermint-core/consensus/README.md

@@ -0,0 +1,42 @@
+---
+order: 1
+parent:
+  title: Consensus
+  order: 6
+---
+
+# Consensus
+
+Tendermint Consensus is a distributed protocol executed by validator processes to agree on
+the next block to be added to the Tendermint blockchain. The protocol proceeds in rounds, where
+each round is a try to reach agreement on the next block. A round starts by having a dedicated
+process (called proposer) suggesting to other processes what should be the next block with
+the `ProposalMessage`.
+The processes respond by voting for a block with `VoteMessage` (there are two kinds of vote
+messages, prevote and precommit votes). Note that a proposal message is just a suggestion what the
+next block should be; a validator might vote with a `VoteMessage` for a different block. If in some
+round, enough number of processes vote for the same block, then this block is committed and later
+added to the blockchain. `ProposalMessage` and `VoteMessage` are signed by the private key of the
+validator. The internals of the protocol and how it ensures safety and liveness properties are
+explained in a forthcoming document.
+
+For efficiency reasons, validators in Tendermint consensus protocol do not agree directly on the
+block as the block size is big, i.e., they don't embed the block inside `Proposal` and
+`VoteMessage`. Instead, they reach agreement on the `BlockID` (see `BlockID` definition in
+[Blockchain](https://github.com/tendermint/spec/blob/master/spec/core/data_structures.md#blockid) section)
+that uniquely identifies each block. The block itself is
+disseminated to validator processes using peer-to-peer gossiping protocol. It starts by having a
+proposer first splitting a block into a number of block parts, that are then gossiped between
+processes using `BlockPartMessage`.
+
+Validators in Tendermint communicate by peer-to-peer gossiping protocol. Each validator is connected
+only to a subset of processes called peers. By the gossiping protocol, a validator send to its peers
+all needed information (`ProposalMessage`, `VoteMessage` and `BlockPartMessage`) so they can
+reach agreement on some block, and also obtain the content of the chosen block (block parts). As
+part of the gossiping protocol, processes also send auxiliary messages that inform peers about the
+executed steps of the core consensus algorithm (`NewRoundStepMessage` and `NewValidBlockMessage`), and
+also messages that inform peers what votes the process has seen (`HasVoteMessage`,
+`VoteSetMaj23Message` and `VoteSetBitsMessage`). These messages are then used in the gossiping
+protocol to determine what messages a process should send to its peers.
+
+We now describe the content of each message exchanged during Tendermint consensus protocol.

docs/tendermint-core/consensus/reactor.md

@@ -0,0 +1,370 @@
+---
+order: 2
+---
+
+# Reactor
+
+Consensus Reactor defines a reactor for the consensus service. It contains the ConsensusState service that
+manages the state of the Tendermint consensus internal state machine.
+When Consensus Reactor is started, it starts Broadcast Routine which starts ConsensusState service.
+Furthermore, for each peer that is added to the Consensus Reactor, it creates (and manages) the known peer state
+(that is used extensively in gossip routines) and starts the following three routines for the peer p:
+Gossip Data Routine, Gossip Votes Routine and QueryMaj23Routine. Finally, Consensus Reactor is responsible
+for decoding messages received from a peer and for adequate processing of the message depending on its type and content.
+The processing normally consists of updating the known peer state and for some messages
+(`ProposalMessage`, `BlockPartMessage` and `VoteMessage`) also forwarding message to ConsensusState module
+for further processing. In the following text we specify the core functionality of those separate unit of executions
+that are part of the Consensus Reactor.
+
+## ConsensusState service
+
+Consensus State handles execution of the Tendermint BFT consensus algorithm. It processes votes and proposals,
+and upon reaching agreement, commits blocks to the chain and executes them against the application.
+The internal state machine receives input from peers, the internal validator and from a timer.
+
+Inside Consensus State we have the following units of execution: Timeout Ticker and Receive Routine.
+Timeout Ticker is a timer that schedules timeouts conditional on the height/round/step that are processed
+by the Receive Routine.
+
+### Receive Routine of the ConsensusState service
+
+Receive Routine of the ConsensusState handles messages which may cause internal consensus state transitions.
+It is the only routine that updates RoundState that contains internal consensus state.
+Updates (state transitions) happen on timeouts, complete proposals, and 2/3 majorities.
+It receives messages from peers, internal validators and from Timeout Ticker
+and invokes the corresponding handlers, potentially updating the RoundState.
+The details of the protocol (together with formal proofs of correctness) implemented by the Receive Routine are
+discussed in separate document. For understanding of this document
+it is sufficient to understand that the Receive Routine manages and updates RoundState data structure that is
+then extensively used by the gossip routines to determine what information should be sent to peer processes.
+
+## Round State
+
+RoundState defines the internal consensus state. It contains height, round, round step, a current validator set,
+a proposal and proposal block for the current round, locked round and block (if some block is being locked), set of
+received votes and last commit and last validators set.
+
+```go
+type RoundState struct {
+ Height             int64
+ Round              int
+ Step               RoundStepType
+ Validators         ValidatorSet
+ Proposal           Proposal
+ ProposalBlock      Block
+ ProposalBlockParts PartSet
+ LockedRound        int
+ LockedBlock        Block
+ LockedBlockParts   PartSet
+ Votes              HeightVoteSet
+ LastCommit         VoteSet
+ LastValidators     ValidatorSet
+}
+```
+
+Internally, consensus will run as a state machine with the following states:
+
+- RoundStepNewHeight
+- RoundStepNewRound
+- RoundStepPropose
+- RoundStepProposeWait
+- RoundStepPrevote
+- RoundStepPrevoteWait
+- RoundStepPrecommit
+- RoundStepPrecommitWait
+- RoundStepCommit
+
+## Peer Round State
+
+Peer round state contains the known state of a peer. It is being updated by the Receive routine of
+Consensus Reactor and by the gossip routines upon sending a message to the peer.
+
+```golang
+type PeerRoundState struct {
+ Height                   int64               // Height peer is at
+ Round                    int                 // Round peer is at, -1 if unknown.
+ Step                     RoundStepType       // Step peer is at
+ Proposal                 bool                // True if peer has proposal for this round
+ ProposalBlockPartsHeader PartSetHeader
+ ProposalBlockParts       BitArray
+ ProposalPOLRound         int                 // Proposal's POL round. -1 if none.
+ ProposalPOL              BitArray            // nil until ProposalPOLMessage received.
+ Prevotes                 BitArray            // All votes peer has for this round
+ Precommits               BitArray            // All precommits peer has for this round
+ LastCommitRound          int                 // Round of commit for last height. -1 if none.
+ LastCommit               BitArray            // All commit precommits of commit for last height.
+ CatchupCommitRound       int                 // Round that we have commit for. Not necessarily unique. -1 if none.
+ CatchupCommit            BitArray            // All commit precommits peer has for this height & CatchupCommitRound
+}
+```
+
+## Receive method of Consensus reactor
+
+The entry point of the Consensus reactor is a receive method. When a message is
+received from a peer p, normally the peer round state is updated
+correspondingly, and some messages are passed for further processing, for
+example to ConsensusState service. We now specify the processing of messages in
+the receive method of Consensus reactor for each message type. In the following
+message handler, `rs` and `prs` denote `RoundState` and `PeerRoundState`,
+respectively.
+
+### NewRoundStepMessage handler
+
+```go
+handleMessage(msg):
+    if msg is from smaller height/round/step then return
+    // Just remember these values.
+    prsHeight = prs.Height
+    prsRound = prs.Round
+    prsCatchupCommitRound = prs.CatchupCommitRound
+    prsCatchupCommit = prs.CatchupCommit
+
+    Update prs with values from msg
+    if prs.Height or prs.Round has been updated then
+        reset Proposal related fields of the peer state
+    if prs.Round has been updated and msg.Round == prsCatchupCommitRound then
+        prs.Precommits = psCatchupCommit
+    if prs.Height has been updated then
+        if prsHeight+1 == msg.Height && prsRound == msg.LastCommitRound then
+            prs.LastCommitRound = msg.LastCommitRound
+         prs.LastCommit = prs.Precommits
+        } else {
+            prs.LastCommitRound = msg.LastCommitRound
+         prs.LastCommit = nil
+        }
+        Reset prs.CatchupCommitRound and prs.CatchupCommit
+```
+
+### NewValidBlockMessage handler
+
+```go
+handleMessage(msg):
+    if prs.Height != msg.Height then return
+
+    if prs.Round != msg.Round && !msg.IsCommit then return
+
+    prs.ProposalBlockPartsHeader = msg.BlockPartsHeader
+    prs.ProposalBlockParts = msg.BlockParts
+```
+
+The number of block parts is limited to 1601 (`types.MaxBlockPartsCount`) to
+protect the node against DOS attacks.
+
+### HasVoteMessage handler
+
+```go
+handleMessage(msg):
+    if prs.Height == msg.Height then
+        prs.setHasVote(msg.Height, msg.Round, msg.Type, msg.Index)
+```
+
+### VoteSetMaj23Message handler
+
+```go
+handleMessage(msg):
+    if prs.Height == msg.Height then
+        Record in rs that a peer claim to have ⅔ majority for msg.BlockID
+        Send VoteSetBitsMessage showing votes node has for that BlockId
+```
+
+### ProposalMessage handler
+
+```go
+handleMessage(msg):
+    if prs.Height != msg.Height || prs.Round != msg.Round || prs.Proposal then return
+    prs.Proposal = true
+    if prs.ProposalBlockParts == empty set then // otherwise it is set in NewValidBlockMessage handler
+      prs.ProposalBlockPartsHeader = msg.BlockPartsHeader
+    prs.ProposalPOLRound = msg.POLRound
+    prs.ProposalPOL = nil
+    Send msg through internal peerMsgQueue to ConsensusState service
+```
+
+### ProposalPOLMessage handler
+
+```go
+handleMessage(msg):
+    if prs.Height != msg.Height or prs.ProposalPOLRound != msg.ProposalPOLRound then return
+    prs.ProposalPOL = msg.ProposalPOL
+```
+
+The number of votes is limited to 10000 (`types.MaxVotesCount`) to protect the
+node against DOS attacks.
+
+### BlockPartMessage handler
+
+```go
+handleMessage(msg):
+    if prs.Height != msg.Height || prs.Round != msg.Round then return
+    Record in prs that peer has block part msg.Part.Index
+    Send msg trough internal peerMsgQueue to ConsensusState service
+```
+
+### VoteMessage handler
+
+```go
+handleMessage(msg):
+    Record in prs that a peer knows vote with index msg.vote.ValidatorIndex for particular height and round
+    Send msg trough internal peerMsgQueue to ConsensusState service
+```
+
+### VoteSetBitsMessage handler
+
+```go
+handleMessage(msg):
+    Update prs for the bit-array of votes peer claims to have for the msg.BlockID
+```
+
+The number of votes is limited to 10000 (`types.MaxVotesCount`) to protect the
+node against DOS attacks.
+
+## Gossip Data Routine
+
+It is used to send the following messages to the peer: `BlockPartMessage`, `ProposalMessage` and
+`ProposalPOLMessage` on the DataChannel. The gossip data routine is based on the local RoundState (`rs`)
+and the known PeerRoundState (`prs`). The routine repeats forever the logic shown below:
+
+```go
+1a) if rs.ProposalBlockPartsHeader == prs.ProposalBlockPartsHeader and the peer does not have all the proposal parts then
+        Part = pick a random proposal block part the peer does not have
+        Send BlockPartMessage(rs.Height, rs.Round, Part) to the peer on the DataChannel
+        if send returns true, record that the peer knows the corresponding block Part
+     Continue
+
+1b) if (0 < prs.Height) and (prs.Height < rs.Height) then
+        help peer catch up using gossipDataForCatchup function
+        Continue
+
+1c) if (rs.Height != prs.Height) or (rs.Round != prs.Round) then
+        Sleep PeerGossipSleepDuration
+        Continue
+
+//  at this point rs.Height == prs.Height and rs.Round == prs.Round
+1d) if (rs.Proposal != nil and !prs.Proposal) then
+        Send ProposalMessage(rs.Proposal) to the peer
+        if send returns true, record that the peer knows Proposal
+     if 0 <= rs.Proposal.POLRound then
+     polRound = rs.Proposal.POLRound
+        prevotesBitArray = rs.Votes.Prevotes(polRound).BitArray()
+        Send ProposalPOLMessage(rs.Height, polRound, prevotesBitArray)
+        Continue
+
+2)  Sleep PeerGossipSleepDuration
+```
+
+### Gossip Data For Catchup
+
+This function is responsible for helping peer catch up if it is at the smaller height (prs.Height < rs.Height).
+The function executes the following logic:
+
+```go
+    if peer does not have all block parts for prs.ProposalBlockPart then
+        blockMeta =  Load Block Metadata for height prs.Height from blockStore
+        if (!blockMeta.BlockID.PartsHeader == prs.ProposalBlockPartsHeader) then
+            Sleep PeerGossipSleepDuration
+     return
+        Part = pick a random proposal block part the peer does not have
+        Send BlockPartMessage(prs.Height, prs.Round, Part) to the peer on the DataChannel
+        if send returns true, record that the peer knows the corresponding block Part
+        return
+    else Sleep PeerGossipSleepDuration
+```
+
+## Gossip Votes Routine
+
+It is used to send the following message: `VoteMessage` on the VoteChannel.
+The gossip votes routine is based on the local RoundState (`rs`)
+and the known PeerRoundState (`prs`). The routine repeats forever the logic shown below:
+
+```go
+1a) if rs.Height == prs.Height then
+        if prs.Step == RoundStepNewHeight then
+            vote = random vote from rs.LastCommit the peer does not have
+            Send VoteMessage(vote) to the peer
+            if send returns true, continue
+
+        if prs.Step <= RoundStepPrevote and prs.Round != -1 and prs.Round <= rs.Round then
+            Prevotes = rs.Votes.Prevotes(prs.Round)
+            vote = random vote from Prevotes the peer does not have
+            Send VoteMessage(vote) to the peer
+            if send returns true, continue
+
+        if prs.Step <= RoundStepPrecommit and prs.Round != -1 and prs.Round <= rs.Round then
+          Precommits = rs.Votes.Precommits(prs.Round)
+            vote = random vote from Precommits the peer does not have
+            Send VoteMessage(vote) to the peer
+            if send returns true, continue
+
+        if prs.ProposalPOLRound != -1 then
+            PolPrevotes = rs.Votes.Prevotes(prs.ProposalPOLRound)
+            vote = random vote from PolPrevotes the peer does not have
+            Send VoteMessage(vote) to the peer
+            if send returns true, continue
+
+1b)  if prs.Height != 0 and rs.Height == prs.Height+1 then
+        vote = random vote from rs.LastCommit peer does not have
+        Send VoteMessage(vote) to the peer
+        if send returns true, continue
+
+1c)  if prs.Height != 0 and rs.Height >= prs.Height+2 then
+        Commit = get commit from BlockStore for prs.Height
+        vote = random vote from Commit the peer does not have
+        Send VoteMessage(vote) to the peer
+        if send returns true, continue
+
+2)   Sleep PeerGossipSleepDuration
+```
+
+## QueryMaj23Routine
+
+It is used to send the following message: `VoteSetMaj23Message`. `VoteSetMaj23Message` is sent to indicate that a given
+BlockID has seen +2/3 votes. This routine is based on the local RoundState (`rs`) and the known PeerRoundState
+(`prs`). The routine repeats forever the logic shown below.
+
+```go
+1a) if rs.Height == prs.Height then
+        Prevotes = rs.Votes.Prevotes(prs.Round)
+        if there is a ⅔ majority for some blockId in Prevotes then
+        m = VoteSetMaj23Message(prs.Height, prs.Round, Prevote, blockId)
+        Send m to peer
+        Sleep PeerQueryMaj23SleepDuration
+
+1b) if rs.Height == prs.Height then
+        Precommits = rs.Votes.Precommits(prs.Round)
+        if there is a ⅔ majority for some blockId in Precommits then
+        m = VoteSetMaj23Message(prs.Height,prs.Round,Precommit,blockId)
+        Send m to peer
+        Sleep PeerQueryMaj23SleepDuration
+
+1c) if rs.Height == prs.Height and prs.ProposalPOLRound >= 0 then
+        Prevotes = rs.Votes.Prevotes(prs.ProposalPOLRound)
+        if there is a ⅔ majority for some blockId in Prevotes then
+        m = VoteSetMaj23Message(prs.Height,prs.ProposalPOLRound,Prevotes,blockId)
+        Send m to peer
+        Sleep PeerQueryMaj23SleepDuration
+
+1d) if prs.CatchupCommitRound != -1 and 0 < prs.Height and
+        prs.Height <= blockStore.Height() then
+        Commit = LoadCommit(prs.Height)
+        m = VoteSetMaj23Message(prs.Height,Commit.Round,Precommit,Commit.BlockID)
+        Send m to peer
+        Sleep PeerQueryMaj23SleepDuration
+
+2)  Sleep PeerQueryMaj23SleepDuration
+```
+
+## Broadcast routine
+
+The Broadcast routine subscribes to an internal event bus to receive new round steps and votes messages, and broadcasts messages to peers upon receiving those
+events.
+It broadcasts `NewRoundStepMessage` or `CommitStepMessage` upon new round state event. Note that
+broadcasting these messages does not depend on the PeerRoundState; it is sent on the StateChannel.
+Upon receiving VoteMessage it broadcasts `HasVoteMessage` message to its peers on the StateChannel.
+
+## Channels
+
+Defines 4 channels: state, data, vote and vote_set_bits. Each channel
+has `SendQueueCapacity` and `RecvBufferCapacity` and
+`RecvMessageCapacity` set to `maxMsgSize`.
+
+Sending incorrectly encoded data will result in stopping the peer.