mirrors/tendermint
1
0
Fork 0
mirror of https://github.com/tendermint/tendermint.git synced 2026-01-06 05:25:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into rpc-header

Browse Source
This commit is contained in:
samricotta
2022-08-08 13:38:03 +02:00
committed by GitHub
parent f9552f9f62 ef4e37b532
commit 3b4196b2da
23 changed files with 418 additions and 133 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
.github/workflows/docs-toc.yml vendored
View File

@@ -1,21 +1,20 @@
# TODO(thane): Re-enable once we've pulled in the ADRs and RFCs from master.
# Verify that important design docs have ToC entries.
#name: Check documentation ToC
#on:
# pull_request:
# push:
# branches:
# - main
#
#jobs:
# check:
# runs-on: ubuntu-latest
# steps:
# - uses: actions/checkout@v3
# - uses: technote-space/get-diff-action@v6
# with:
# PATTERNS: |
# docs/architecture/**
# docs/rfc/**
# - run: ./docs/presubmit.sh
# if: env.GIT_DIFF
name: Check documentation ToC
on:
pull_request:
push:
branches:
- main
jobs:
check:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- uses: technote-space/get-diff-action@v6
with:
PATTERNS: |
docs/architecture/**
docs/rfc/**
- run: make check-docs-toc
if: env.GIT_DIFF

62
.github/workflows/e2e-nightly-34x.yml vendored
View File

@@ -27,6 +27,12 @@ jobs:
with:
ref: 'v0.34.x'
- name: Capture git repo info
id: git-info
run: |
echo "::set-output name=branch::`git branch --show-current`"
echo "::set-output name=commit::`git rev-parse HEAD`"
- name: Build
working-directory: test/e2e
# Run make jobs in parallel, since we can't run steps in parallel.
@@ -41,18 +47,58 @@ jobs:
working-directory: test/e2e
run: ./run-multiple.sh networks/nightly/*-group${{ matrix.group }}-*.toml
outputs:
git-branch: ${{ steps.git-info.outputs.branch }}
git-commit: ${{ steps.git-info.outputs.commit }}
e2e-nightly-fail:
needs: e2e-nightly-test
if: ${{ failure() }}
runs-on: ubuntu-latest
steps:
- name: Notify Slack on failure
uses: rtCamp/action-slack-notify@12e36fc18b0689399306c2e0b3e0f2978b7f1ee7
uses: slackapi/slack-github-action@v1.21.0
env:
SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
SLACK_CHANNEL: tendermint-internal
SLACK_USERNAME: Nightly E2E Tests
SLACK_ICON_EMOJI: ':skull:'
SLACK_COLOR: danger
SLACK_MESSAGE: Nightly E2E tests failed on v0.34.x
SLACK_FOOTER: ''
SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
SLACK_WEBHOOK_TYPE: INCOMING_WEBHOOK
BRANCH: ${{ needs.e2e-nightly-test.outputs.git-branch }}
RUN_URL: "${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
COMMIT_URL: "${{ github.server_url }}/${{ github.repository }}/commit/${{ needs.e2e-nightly-test.outputs.git-commit }}"
with:
payload: |
{
"blocks": [
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": ":skull: Nightly E2E tests for `${{ env.BRANCH }}` failed. See the <${{ env.RUN_URL }}|run details> and the <${{ env.COMMIT_URL }}|commit> that caused the failure."
}
}
]
}
e2e-nightly-success: # may turn this off once they seem to pass consistently
needs: e2e-nightly-test
if: ${{ success() }}
runs-on: ubuntu-latest
steps:
- name: Notify Slack on success
uses: slackapi/slack-github-action@v1.21.0
env:
SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
SLACK_WEBHOOK_TYPE: INCOMING_WEBHOOK
BRANCH: ${{ needs.e2e-nightly-test.outputs.git-branch }}
with:
payload: |
{
"blocks": [
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": ":white_check_mark: Nightly E2E tests for `${{ env.BRANCH }}` passed."
}
}
]
}

52
.github/workflows/e2e-nightly-main.yml vendored
View File

@@ -46,15 +46,26 @@ jobs:
runs-on: ubuntu-latest
steps:
- name: Notify Slack on failure
uses: rtCamp/action-slack-notify@12e36fc18b0689399306c2e0b3e0f2978b7f1ee7
uses: slackapi/slack-github-action@v1.21.0
env:
SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
SLACK_CHANNEL: tendermint-internal
SLACK_USERNAME: Nightly E2E Tests
SLACK_ICON_EMOJI: ':skull:'
SLACK_COLOR: danger
SLACK_MESSAGE: Nightly E2E tests failed on main
SLACK_FOOTER: ''
SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
SLACK_WEBHOOK_TYPE: INCOMING_WEBHOOK
BRANCH: ${{ github.ref_name }}
RUN_URL: "${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
COMMIT_URL: "${{ github.server_url }}/${{ github.repository }}/commit/${{ github.sha }}"
with:
payload: |
{
"blocks": [
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": ":skull: Nightly E2E tests for `${{ env.BRANCH }}` failed. See the <${{ env.RUN_URL }}|run details> and the <${{ env.COMMIT_URL }}|commit> that caused the failure."
}
}
]
}
e2e-nightly-success: # may turn this off once they seem to pass consistently
needs: e2e-nightly-test
@@ -62,12 +73,21 @@ jobs:
runs-on: ubuntu-latest
steps:
- name: Notify Slack on success
uses: rtCamp/action-slack-notify@12e36fc18b0689399306c2e0b3e0f2978b7f1ee7
uses: slackapi/slack-github-action@v1.21.0
env:
SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
SLACK_CHANNEL: tendermint-internal
SLACK_USERNAME: Nightly E2E Tests
SLACK_ICON_EMOJI: ':white_check_mark:'
SLACK_COLOR: good
SLACK_MESSAGE: Nightly E2E tests passed on main
SLACK_FOOTER: ''
SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
SLACK_WEBHOOK_TYPE: INCOMING_WEBHOOK
BRANCH: ${{ github.ref_name }}
with:
payload: |
{
"blocks": [
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": ":white_check_mark: Nightly E2E tests for `${{ env.BRANCH }}` passed."
}
}
]
}

29
.github/workflows/fuzz-nightly.yml vendored
View File

@@ -75,13 +75,24 @@ jobs:
if: ${{ needs.fuzz-nightly-test.outputs.crashers-count != 0 }}
runs-on: ubuntu-latest
steps:
- name: Notify Slack if any crashers
uses: rtCamp/action-slack-notify@12e36fc18b0689399306c2e0b3e0f2978b7f1ee7
- name: Notify Slack on failure
uses: slackapi/slack-github-action@v1.21.0
env:
SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
SLACK_CHANNEL: tendermint-internal
SLACK_USERNAME: Nightly Fuzz Tests
SLACK_ICON_EMOJI: ':firecracker:'
SLACK_COLOR: danger
SLACK_MESSAGE: Crashers found in Nightly Fuzz tests
SLACK_FOOTER: ''
SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}
SLACK_WEBHOOK_TYPE: INCOMING_WEBHOOK
BRANCH: ${{ github.ref_name }}
CRASHERS: ${{ needs.fuzz-nightly-test.outputs.crashers-count }}
RUN_URL: "${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
with:
payload: |
{
"blocks": [
{
"type": "section",
"text": {
"type": "mrkdwn",
"text": ":skull: Nightly fuzz tests for `${{ env.BRANCH }}` failed with ${{ env.CRASHERS }} crasher(s). See the <${{ env.RUN_URL }}|run details>."
}
}
]
}

5
Makefile
View File

@@ -289,6 +289,11 @@ sync-docs:
aws cloudfront create-invalidation --distribution-id ${CF_DISTRIBUTION_ID} --profile terraform --path "/*" ;
.PHONY: sync-docs
# Verify that important design docs have ToC entries.
check-docs-toc:
@./docs/presubmit.sh
.PHONY: check-docs-toc
###############################################################################
### Docker image ###
###############################################################################

2
blockchain/reactor_test.go
View File

@@ -62,7 +62,7 @@ func newReactor(
app := &testApp{}
cc := proxy.NewLocalClientCreator(app)
proxyApp := proxy.NewAppConns(cc)
proxyApp := proxy.NewAppConns(cc, proxy.NopMetrics())
err := proxyApp.Start()
if err != nil {
panic(fmt.Errorf("error start app: %w", err))

66
consensus/metrics.go
View File

@@ -1,8 +1,13 @@
package consensus
import (
"strings"
"time"
"github.com/go-kit/kit/metrics"
"github.com/go-kit/kit/metrics/discard"
cstypes "github.com/tendermint/tendermint/consensus/types"
"github.com/tendermint/tendermint/types"
prometheus "github.com/go-kit/kit/metrics/prometheus"
stdprometheus "github.com/prometheus/client_golang/prometheus"
@@ -25,6 +30,9 @@ type Metrics struct {
// Number of rounds.
Rounds metrics.Gauge
// Histogram of round duration.
RoundDuration metrics.Histogram
// Number of validators.
Validators metrics.Gauge
// Total power of all validators.
@@ -61,6 +69,14 @@ type Metrics struct {
// Number of blockparts transmitted by peer.
BlockParts metrics.Counter
// Histogram of step duration.
StepDuration metrics.Histogram
stepStart time.Time
// Number of block parts received by the node, separated by whether the part
// was relevant to the block the node is trying to gather or not.
BlockGossipPartsReceived metrics.Counter
// QuroumPrevoteMessageDelay is the interval in seconds between the proposal
// timestamp and the timestamp of the earliest prevote that achieved a quorum
// during the prevote step.
@@ -99,7 +115,13 @@ func PrometheusMetrics(namespace string, labelsAndValues ...string) *Metrics {
Name: "rounds",
Help: "Number of rounds.",
}, labels).With(labelsAndValues...),
RoundDuration: prometheus.NewHistogramFrom(stdprometheus.HistogramOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "round_duration_seconds",
Help: "Time spent in a round.",
Buckets: stdprometheus.ExponentialBucketsRange(0.1, 100, 8),
}, labels).With(labelsAndValues...),
Validators: prometheus.NewGaugeFrom(stdprometheus.GaugeOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
@@ -202,6 +224,20 @@ func PrometheusMetrics(namespace string, labelsAndValues ...string) *Metrics {
Name: "block_parts",
Help: "Number of blockparts transmitted by peer.",
}, append(labels, "peer_id")).With(labelsAndValues...),
BlockGossipPartsReceived: prometheus.NewCounterFrom(stdprometheus.CounterOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "block_gossip_parts_received",
Help: "Number of block parts received by the node, labeled by whether the " +
"part was relevant to the block the node was currently gathering or not.",
}, append(labels, "matches_current")).With(labelsAndValues...),
StepDuration: prometheus.NewHistogramFrom(stdprometheus.HistogramOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "step_duration_seconds",
Help: "Time spent per step.",
Buckets: stdprometheus.ExponentialBucketsRange(0.1, 100, 8),
}, append(labels, "step")).With(labelsAndValues...),
QuorumPrevoteMessageDelay: prometheus.NewGaugeFrom(stdprometheus.GaugeOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
@@ -226,7 +262,9 @@ func NopMetrics() *Metrics {
ValidatorLastSignedHeight: discard.NewGauge(),
Rounds: discard.NewGauge(),
Rounds: discard.NewGauge(),
RoundDuration: discard.NewHistogram(),
StepDuration: discard.NewHistogram(),
Validators: discard.NewGauge(),
ValidatorsPower: discard.NewGauge(),
@@ -246,7 +284,31 @@ func NopMetrics() *Metrics {
FastSyncing: discard.NewGauge(),
StateSyncing: discard.NewGauge(),
BlockParts: discard.NewCounter(),
BlockGossipPartsReceived: discard.NewCounter(),
QuorumPrevoteMessageDelay: discard.NewGauge(),
FullPrevoteMessageDelay: discard.NewGauge(),
}
}
// RecordConsMetrics uses for recording the block related metrics during fast-sync.
func (m *Metrics) RecordConsMetrics(block *types.Block) {
m.NumTxs.Set(float64(len(block.Data.Txs)))
m.TotalTxs.Add(float64(len(block.Data.Txs)))
m.BlockSizeBytes.Set(float64(block.Size()))
m.CommittedHeight.Set(float64(block.Height))
}
func (m *Metrics) MarkRound(r int32, st time.Time) {
m.Rounds.Set(float64(r))
roundTime := time.Since(st).Seconds()
m.RoundDuration.Observe(roundTime)
}
func (m *Metrics) MarkStep(s cstypes.RoundStepType) {
if !m.stepStart.IsZero() {
stepTime := time.Since(m.stepStart).Seconds()
stepName := strings.TrimPrefix(s.String(), "RoundStep")
m.StepDuration.With("step", stepName).Observe(stepTime)
}
m.stepStart = time.Now()
}

2
consensus/replay_file.go
View File

@@ -309,7 +309,7 @@ func newConsensusStateForReplay(config cfg.BaseConfig, csConfig *cfg.ConsensusCo
// Create proxyAppConn connection (consensus, mempool, query)
clientCreator := proxy.DefaultClientCreator(config.ProxyApp, config.ABCI, config.DBDir())
proxyApp := proxy.NewAppConns(clientCreator)
proxyApp := proxy.NewAppConns(clientCreator, proxy.NopMetrics())
err = proxyApp.Start()
if err != nil {
tmos.Exit(fmt.Sprintf("Error starting proxy app conns: %v", err))

2
consensus/replay_stubs.go
View File

@@ -66,7 +66,7 @@ func newMockProxyApp(appHash []byte, abciResponses *tmstate.ABCIResponses) proxy
if err != nil {
panic(err)
}
return proxy.NewAppConnConsensus(cli)
return proxy.NewAppConnConsensus(cli, proxy.NopMetrics())
}
type mockProxyApp struct {

12
consensus/replay_test.go
View File

@@ -710,7 +710,7 @@ func testHandshakeReplay(t *testing.T, config *cfg.Config, nBlocks int, mode uin
if nBlocks > 0 {
// run nBlocks against a new client to build up the app state.
// use a throwaway tendermint state
proxyApp := proxy.NewAppConns(clientCreator2)
proxyApp := proxy.NewAppConns(clientCreator2, proxy.NopMetrics())
stateDB1 := dbm.NewMemDB()
stateStore := sm.NewStore(stateDB1)
err := stateStore.Save(genesisState)
@@ -730,7 +730,7 @@ func testHandshakeReplay(t *testing.T, config *cfg.Config, nBlocks int, mode uin
// now start the app using the handshake - it should sync
genDoc, _ := sm.MakeGenesisDocFromFile(config.GenesisFile())
handshaker := NewHandshaker(stateStore, state, store, genDoc)
proxyApp := proxy.NewAppConns(clientCreator2)
proxyApp := proxy.NewAppConns(clientCreator2, proxy.NopMetrics())
if err := proxyApp.Start(); err != nil {
t.Fatalf("Error starting proxy app connections: %v", err)
}
@@ -839,7 +839,7 @@ func buildTMStateFromChain(
clientCreator := proxy.NewLocalClientCreator(
kvstore.NewPersistentKVStoreApplication(
filepath.Join(config.DBDir(), fmt.Sprintf("replay_test_%d_%d_t", nBlocks, mode))))
proxyApp := proxy.NewAppConns(clientCreator)
proxyApp := proxy.NewAppConns(clientCreator, proxy.NopMetrics())
if err := proxyApp.Start(); err != nil {
panic(err)
}
@@ -905,7 +905,7 @@ func TestHandshakePanicsIfAppReturnsWrongAppHash(t *testing.T) {
{
app := &badApp{numBlocks: 3, allHashesAreWrong: true}
clientCreator := proxy.NewLocalClientCreator(app)
proxyApp := proxy.NewAppConns(clientCreator)
proxyApp := proxy.NewAppConns(clientCreator, proxy.NopMetrics())
err := proxyApp.Start()
require.NoError(t, err)
t.Cleanup(func() {
@@ -929,7 +929,7 @@ func TestHandshakePanicsIfAppReturnsWrongAppHash(t *testing.T) {
{
app := &badApp{numBlocks: 3, onlyLastHashIsWrong: true}
clientCreator := proxy.NewLocalClientCreator(app)
proxyApp := proxy.NewAppConns(clientCreator)
proxyApp := proxy.NewAppConns(clientCreator, proxy.NopMetrics())
err := proxyApp.Start()
require.NoError(t, err)
t.Cleanup(func() {
@@ -1233,7 +1233,7 @@ func TestHandshakeUpdatesValidators(t *testing.T) {
// now start the app using the handshake - it should sync
genDoc, _ := sm.MakeGenesisDocFromFile(config.GenesisFile())
handshaker := NewHandshaker(stateStore, state, store, genDoc)
proxyApp := proxy.NewAppConns(clientCreator)
proxyApp := proxy.NewAppConns(clientCreator, proxy.NopMetrics())
if err := proxyApp.Start(); err != nil {
t.Fatalf("Error starting proxy app connections: %v", err)
}

23
consensus/state.go
View File

@@ -4,7 +4,7 @@ import (
"bytes"
"errors"
"fmt"
"io/ioutil"
"io"
"os"
"runtime/debug"
"sort"
@@ -523,6 +523,14 @@ func (cs *State) updateHeight(height int64) {
}
func (cs *State) updateRoundStep(round int32, step cstypes.RoundStepType) {
if !cs.replayMode {
if round != cs.Round || round == 0 && step == cstypes.RoundStepNewRound {
cs.metrics.MarkRound(cs.Round, cs.StartTime)
}
if cs.Step != step {
cs.metrics.MarkStep(cs.Step)
}
}
cs.Round = round
cs.Step = step
}
@@ -1021,9 +1029,6 @@ func (cs *State) enterNewRound(height int64, round int32) {
if err := cs.eventBus.PublishEventNewRound(cs.NewRoundEvent()); err != nil {
cs.Logger.Error("failed publishing new round", "err", err)
}
cs.metrics.Rounds.Set(float64(round))
// Wait for txs to be available in the mempool
// before we enterPropose in round 0. If the last block changed the app hash,
// we may need an empty "proof" block, and enterPropose immediately.
@@ -1854,11 +1859,13 @@ func (cs *State) addProposalBlockPart(msg *BlockPartMessage, peerID p2p.ID) (add
// Blocks might be reused, so round mismatch is OK
if cs.Height != height {
cs.Logger.Debug("received block part from wrong height", "height", height, "round", round)
cs.metrics.BlockGossipPartsReceived.With("matches_current", "false").Add(1)
return false, nil
}
// We're not expecting a block part.
if cs.ProposalBlockParts == nil {
cs.metrics.BlockGossipPartsReceived.With("matches_current", "false").Add(1)
// NOTE: this can happen when we've gone to a higher round and
// then receive parts from the previous round - not necessarily a bad peer.
cs.Logger.Debug(
@@ -1873,15 +1880,21 @@ func (cs *State) addProposalBlockPart(msg *BlockPartMessage, peerID p2p.ID) (add
added, err = cs.ProposalBlockParts.AddPart(part)
if err != nil {
if errors.Is(err, types.ErrPartSetInvalidProof) || errors.Is(err, types.ErrPartSetUnexpectedIndex) {
cs.metrics.BlockGossipPartsReceived.With("matches_current", "false").Add(1)
}
return added, err
}
cs.metrics.BlockGossipPartsReceived.With("matches_current", "true").Add(1)
if cs.ProposalBlockParts.ByteSize() > cs.state.ConsensusParams.Block.MaxBytes {
return added, fmt.Errorf("total size of proposal block parts exceeds maximum block bytes (%d > %d)",
cs.ProposalBlockParts.ByteSize(), cs.state.ConsensusParams.Block.MaxBytes,
)
}
if added && cs.ProposalBlockParts.IsComplete() {
bz, err := ioutil.ReadAll(cs.ProposalBlockParts.GetReader())
bz, err := io.ReadAll(cs.ProposalBlockParts.GetReader())
if err != nil {
return added, err
}

2
consensus/wal_generator.go
View File

@@ -59,7 +59,7 @@ func WALGenerateNBlocks(t *testing.T, wr io.Writer, numBlocks int) (err error) {
blockStore := store.NewBlockStore(blockStoreDB)
proxyApp := proxy.NewAppConns(proxy.NewLocalClientCreator(app))
proxyApp := proxy.NewAppConns(proxy.NewLocalClientCreator(app), proxy.NopMetrics())
proxyApp.SetLogger(logger.With("module", "proxy"))
if err := proxyApp.Start(); err != nil {
return fmt.Errorf("failed to start proxy app connections: %w", err)

2
docs/architecture/README.md
View File

@@ -77,7 +77,7 @@ Note the context/background should be written in the present tense.
- [ADR-006: Trust-Metric](./adr-006-trust-metric.md)
- [ADR-024: Sign-Bytes](./adr-024-sign-bytes.md)
- [ADR-035: Documentation](./adr-035-documentation.md)
- [ADR-039: Peer-Behaviour](./adr-039-peer-behavior.md)
- [ADR-039: Peer-Behaviour](./adr-039-peer-behaviour.md)
- [ADR-060: Go-API-Stability](./adr-060-go-api-stability.md)
- [ADR-061: P2P-Refactor-Scope](./adr-061-p2p-refactor-scope.md)
- [ADR-065: Custom Event Indexing](./adr-065-custom-event-indexing.md)

39
docs/presubmit.sh Executable file
View File

@@ -0,0 +1,39 @@
#!/bin/bash
#
# This script verifies that each document in the docs and architecture
# directory has a corresponding table-of-contents entry in its README file.
#
# This can be run manually from the command line.
# It is also run in CI via the docs-toc.yml workflow.
#
set -euo pipefail
readonly base="$(dirname $0)"
cd "$base"
readonly workdir="$(mktemp -d)"
trap "rm -fr -- '$workdir'" EXIT
checktoc() {
local dir="$1"
local tag="$2"'-*-*'
local out="$workdir/${dir}.out.txt"
(
cd "$dir" >/dev/null
find . -maxdepth 1 -type f -name "$tag" -not -exec grep -q "({})" README.md ';' -print
) > "$out"
if [[ -s "$out" ]] ; then
echo "-- The following files in $dir lack a ToC entry:
"
cat "$out"
return 1
fi
}
err=0
# Verify that each RFC and ADR has a ToC entry in its README file.
checktoc architecture adr || ((err++))
checktoc rfc rfc || ((err++))
exit $err

68
docs/tendermint-core/metrics.md
View File

@@ -18,38 +18,42 @@ Listen address can be changed in the config file (see
The following metrics are available:
| **Name** | **Type** | **Tags** | **Description** |
| -------------------------------------- | --------- | ------------- | ---------------------------------------------------------------------- |
| consensus_height | Gauge | | Height of the chain |
| consensus_validators | Gauge | | Number of validators |
| consensus_validators_power | Gauge | | Total voting power of all validators |
| consensus_validator_power | Gauge | | Voting power of the node if in the validator set |
| consensus_validator_last_signed_height | Gauge | | Last height the node signed a block, if the node is a validator |
| consensus_validator_missed_blocks | Gauge | | Total amount of blocks missed for the node, if the node is a validator |
| consensus_missing_validators | Gauge | | Number of validators who did not sign |
| consensus_missing_validators_power | Gauge | | Total voting power of the missing validators |
| consensus_byzantine_validators | Gauge | | Number of validators who tried to double sign |
| consensus_byzantine_validators_power | Gauge | | Total voting power of the byzantine validators |
| consensus_block_interval_seconds | Histogram | | Time between this and last block (Block.Header.Time) in seconds |
| consensus_rounds | Gauge | | Number of rounds |
| consensus_num_txs | Gauge | | Number of transactions |
| consensus_total_txs | Gauge | | Total number of transactions committed |
| consensus_block_parts | counter | peer_id | number of blockparts transmitted by peer |
| consensus_latest_block_height | gauge | | /status sync_info number |
| consensus_fast_syncing | gauge | | either 0 (not fast syncing) or 1 (syncing) |
| consensus_state_syncing | gauge | | either 0 (not state syncing) or 1 (syncing) |
| consensus_block_size_bytes | Gauge | | Block size in bytes |
| p2p_peers | Gauge | | Number of peers node's connected to |
| p2p_peer_receive_bytes_total | counter | peer_id, chID | number of bytes per channel received from a given peer |
| p2p_peer_send_bytes_total | counter | peer_id, chID | number of bytes per channel sent to a given peer |
| p2p_peer_pending_send_bytes | gauge | peer_id | number of pending bytes to be sent to a given peer |
| p2p_num_txs | gauge | peer_id | number of transactions submitted by each peer_id |
| p2p_pending_send_bytes | gauge | peer_id | amount of data pending to be sent to peer |
| mempool_size | Gauge | | Number of uncommitted transactions |
| mempool_tx_size_bytes | histogram | | transaction sizes in bytes |
| mempool_failed_txs | counter | | number of failed transactions |
| mempool_recheck_times | counter | | number of transactions rechecked in the mempool |
| state_block_processing_time | histogram | | time between BeginBlock and EndBlock in ms |
| **Name** | **Type** | **Tags** | **Description** |
|----------------------------------------|-----------|-----------------|--------------------------------------------------------------------------------------------------------------------------------------------|
| abci_connection_method_timing_seconds | 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 |
| consensus_validator_power | Gauge | | Voting power of the node if in the validator set |
| consensus_validator_last_signed_height | Gauge | | Last height the node signed a block, if the node is a validator |
| consensus_validator_missed_blocks | Gauge | | Total amount of blocks missed for the node, if the node is a validator |
| consensus_missing_validators | Gauge | | Number of validators who did not sign |
| consensus_missing_validators_power | Gauge | | Total voting power of the missing validators |
| consensus_byzantine_validators | Gauge | | Number of validators who tried to double sign |
| consensus_byzantine_validators_power | Gauge | | Total voting power of the byzantine validators |
| consensus_block_interval_seconds | Histogram | | Time between this and last block (Block.Header.Time) in seconds |
| consensus_rounds | Gauge | | Number of rounds |
| consensus_num_txs | Gauge | | Number of transactions |
| consensus_total_txs | Gauge | | Total number of transactions committed |
| consensus_block_parts | counter | peer_id | number of blockparts transmitted by peer |
| consensus_latest_block_height | gauge | | /status sync_info number |
| consensus_fast_syncing | gauge | | either 0 (not fast syncing) or 1 (syncing) |
| consensus_state_syncing | gauge | | either 0 (not state syncing) or 1 (syncing) |
| consensus_block_size_bytes | Gauge | | Block size in bytes |
| consensus_step_duration | Histogram | step | Histogram of durations for each step in the consensus protocol |
| consensus_round_duration | Histogram | | Histogram of durations for all the rounds that have occurred since the process started |
| consensus_block_gossip_parts_received | Counter | matches_current | Number of block parts received by the node |
| p2p_peers | Gauge | | Number of peers node's connected to |
| p2p_peer_receive_bytes_total | counter | peer_id, chID | number of bytes per channel received from a given peer |
| p2p_peer_send_bytes_total | counter | peer_id, chID | number of bytes per channel sent to a given peer |
| p2p_peer_pending_send_bytes | gauge | peer_id | number of pending bytes to be sent to a given peer |
| p2p_num_txs | gauge | peer_id | number of transactions submitted by each peer_id |
| p2p_pending_send_bytes | gauge | peer_id | amount of data pending to be sent to peer |
| mempool_size | Gauge | | Number of uncommitted transactions |
| mempool_tx_size_bytes | histogram | | transaction sizes in bytes |
| mempool_failed_txs | counter | | number of failed transactions |
| mempool_recheck_times | counter | | number of transactions rechecked in the mempool |
| state_block_processing_time | histogram | | time between BeginBlock and EndBlock in ms |
## Useful queries

19
node/node.go
View File

@@ -113,19 +113,20 @@ func DefaultNewNode(config *cfg.Config, logger log.Logger) (*Node, error) {
}
// MetricsProvider returns a consensus, p2p and mempool Metrics.
type MetricsProvider func(chainID string) (*cs.Metrics, *p2p.Metrics, *mempl.Metrics, *sm.Metrics)
type MetricsProvider func(chainID string) (*cs.Metrics, *p2p.Metrics, *mempl.Metrics, *sm.Metrics, *proxy.Metrics)
// DefaultMetricsProvider returns Metrics build using Prometheus client library
// if Prometheus is enabled. Otherwise, it returns no-op Metrics.
func DefaultMetricsProvider(config *cfg.InstrumentationConfig) MetricsProvider {
return func(chainID string) (*cs.Metrics, *p2p.Metrics, *mempl.Metrics, *sm.Metrics) {
return func(chainID string) (*cs.Metrics, *p2p.Metrics, *mempl.Metrics, *sm.Metrics, *proxy.Metrics) {
if config.Prometheus {
return cs.PrometheusMetrics(config.Namespace, "chain_id", chainID),
p2p.PrometheusMetrics(config.Namespace, "chain_id", chainID),
mempl.PrometheusMetrics(config.Namespace, "chain_id", chainID),
sm.PrometheusMetrics(config.Namespace, "chain_id", chainID)
sm.PrometheusMetrics(config.Namespace, "chain_id", chainID),
proxy.PrometheusMetrics(config.Namespace, "chain_id", chainID)
}
return cs.NopMetrics(), p2p.NopMetrics(), mempl.NopMetrics(), sm.NopMetrics()
return cs.NopMetrics(), p2p.NopMetrics(), mempl.NopMetrics(), sm.NopMetrics(), proxy.NopMetrics()
}
}
@@ -246,8 +247,8 @@ func initDBs(config *cfg.Config, dbProvider DBProvider) (blockStore *store.Block
return
}
func createAndStartProxyAppConns(clientCreator proxy.ClientCreator, logger log.Logger) (proxy.AppConns, error) {
proxyApp := proxy.NewAppConns(clientCreator)
func createAndStartProxyAppConns(clientCreator proxy.ClientCreator, logger log.Logger, metrics *proxy.Metrics) (proxy.AppConns, error) {
proxyApp := proxy.NewAppConns(clientCreator, metrics)
proxyApp.SetLogger(logger.With("module", "proxy"))
if err := proxyApp.Start(); err != nil {
return nil, fmt.Errorf("error starting proxy app connections: %v", err)
@@ -720,8 +721,10 @@ func NewNode(config *cfg.Config,
return nil, err
}
csMetrics, p2pMetrics, memplMetrics, smMetrics, abciMetrics := metricsProvider(genDoc.ChainID)
// Create the proxyApp and establish connections to the ABCI app (consensus, mempool, query).
proxyApp, err := createAndStartProxyAppConns(clientCreator, logger)
proxyApp, err := createAndStartProxyAppConns(clientCreator, logger, abciMetrics)
if err != nil {
return nil, err
}
@@ -786,8 +789,6 @@ func NewNode(config *cfg.Config,
logNodeStartupInfo(state, pubKey, logger, consensusLogger)
csMetrics, p2pMetrics, memplMetrics, smMetrics := metricsProvider(genDoc.ChainID)
// Make MempoolReactor
mempool, mempoolReactor := createMempoolAndMempoolReactor(config, proxyApp, state, memplMetrics, logger)

4
node/node_test.go
View File

@@ -226,7 +226,7 @@ func TestCreateProposalBlock(t *testing.T) {
config := cfg.ResetTestRoot("node_create_proposal")
defer os.RemoveAll(config.RootDir)
cc := proxy.NewLocalClientCreator(kvstore.NewApplication())
proxyApp := proxy.NewAppConns(cc)
proxyApp := proxy.NewAppConns(cc, proxy.NopMetrics())
err := proxyApp.Start()
require.Nil(t, err)
defer proxyApp.Stop() //nolint:errcheck // ignore for tests
@@ -331,7 +331,7 @@ func TestMaxProposalBlockSize(t *testing.T) {
config := cfg.ResetTestRoot("node_create_proposal")
defer os.RemoveAll(config.RootDir)
cc := proxy.NewLocalClientCreator(kvstore.NewApplication())
proxyApp := proxy.NewAppConns(cc)
proxyApp := proxy.NewAppConns(cc, proxy.NopMetrics())
err := proxyApp.Start()
require.Nil(t, err)
defer proxyApp.Stop() //nolint:errcheck // ignore for tests

44
proxy/app_conn.go
View File

@@ -1,6 +1,9 @@
package proxy
import (
"time"
"github.com/go-kit/kit/metrics"
abcicli "github.com/tendermint/tendermint/abci/client"
"github.com/tendermint/tendermint/abci/types"
)
@@ -56,11 +59,13 @@ type AppConnSnapshot interface {
// Implements AppConnConsensus (subset of abcicli.Client)
type appConnConsensus struct {
metrics *Metrics
appConn abcicli.Client
}
func NewAppConnConsensus(appConn abcicli.Client) AppConnConsensus {
func NewAppConnConsensus(appConn abcicli.Client, metrics *Metrics) AppConnConsensus {
return &appConnConsensus{
metrics: metrics,
appConn: appConn,
}
}
@@ -74,22 +79,27 @@ func (app *appConnConsensus) Error() error {
}
func (app *appConnConsensus) InitChainSync(req types.RequestInitChain) (*types.ResponseInitChain, error) {
defer addTimeSample(app.metrics.MethodTiming.With("method", "init_chain", "type", "sync"))()
return app.appConn.InitChainSync(req)
}
func (app *appConnConsensus) BeginBlockSync(req types.RequestBeginBlock) (*types.ResponseBeginBlock, error) {
defer addTimeSample(app.metrics.MethodTiming.With("method", "begin_block", "type", "sync"))()
return app.appConn.BeginBlockSync(req)
}
func (app *appConnConsensus) DeliverTxAsync(req types.RequestDeliverTx) *abcicli.ReqRes {
defer addTimeSample(app.metrics.MethodTiming.With("method", "deliver_tx", "type", "async"))()
return app.appConn.DeliverTxAsync(req)
}
func (app *appConnConsensus) EndBlockSync(req types.RequestEndBlock) (*types.ResponseEndBlock, error) {
defer addTimeSample(app.metrics.MethodTiming.With("method", "end_block", "type", "sync"))()
return app.appConn.EndBlockSync(req)
}
func (app *appConnConsensus) CommitSync() (*types.ResponseCommit, error) {
defer addTimeSample(app.metrics.MethodTiming.With("method", "commit", "type", "sync"))()
return app.appConn.CommitSync()
}
@@ -97,11 +107,13 @@ func (app *appConnConsensus) CommitSync() (*types.ResponseCommit, error) {
// Implements AppConnMempool (subset of abcicli.Client)
type appConnMempool struct {
metrics *Metrics
appConn abcicli.Client
}
func NewAppConnMempool(appConn abcicli.Client) AppConnMempool {
func NewAppConnMempool(appConn abcicli.Client, metrics *Metrics) AppConnMempool {
return &appConnMempool{
metrics: metrics,
appConn: appConn,
}
}
@@ -115,18 +127,22 @@ func (app *appConnMempool) Error() error {
}
func (app *appConnMempool) FlushAsync() *abcicli.ReqRes {
defer addTimeSample(app.metrics.MethodTiming.With("method", "flush", "type", "async"))()
return app.appConn.FlushAsync()
}
func (app *appConnMempool) FlushSync() error {
defer addTimeSample(app.metrics.MethodTiming.With("method", "flush", "type", "sync"))()
return app.appConn.FlushSync()
}
func (app *appConnMempool) CheckTxAsync(req types.RequestCheckTx) *abcicli.ReqRes {
defer addTimeSample(app.metrics.MethodTiming.With("method", "check_tx", "type", "async"))()
return app.appConn.CheckTxAsync(req)
}
func (app *appConnMempool) CheckTxSync(req types.RequestCheckTx) (*types.ResponseCheckTx, error) {
defer addTimeSample(app.metrics.MethodTiming.With("method", "check_tx", "type", "sync"))()
return app.appConn.CheckTxSync(req)
}
@@ -134,11 +150,13 @@ func (app *appConnMempool) CheckTxSync(req types.RequestCheckTx) (*types.Respons
// Implements AppConnQuery (subset of abcicli.Client)
type appConnQuery struct {
metrics *Metrics
appConn abcicli.Client
}
func NewAppConnQuery(appConn abcicli.Client) AppConnQuery {
func NewAppConnQuery(appConn abcicli.Client, metrics *Metrics) AppConnQuery {
return &appConnQuery{
metrics: metrics,
appConn: appConn,
}
}
@@ -148,14 +166,17 @@ func (app *appConnQuery) Error() error {
}
func (app *appConnQuery) EchoSync(msg string) (*types.ResponseEcho, error) {
defer addTimeSample(app.metrics.MethodTiming.With("method", "echo", "type", "sync"))()
return app.appConn.EchoSync(msg)
}
func (app *appConnQuery) InfoSync(req types.RequestInfo) (*types.ResponseInfo, error) {
defer addTimeSample(app.metrics.MethodTiming.With("method", "info", "type", "sync"))()
return app.appConn.InfoSync(req)
}
func (app *appConnQuery) QuerySync(reqQuery types.RequestQuery) (*types.ResponseQuery, error) {
defer addTimeSample(app.metrics.MethodTiming.With("method", "query", "type", "sync"))()
return app.appConn.QuerySync(reqQuery)
}
@@ -163,11 +184,13 @@ func (app *appConnQuery) QuerySync(reqQuery types.RequestQuery) (*types.Response
// Implements AppConnSnapshot (subset of abcicli.Client)
type appConnSnapshot struct {
metrics *Metrics
appConn abcicli.Client
}
func NewAppConnSnapshot(appConn abcicli.Client) AppConnSnapshot {
func NewAppConnSnapshot(appConn abcicli.Client, metrics *Metrics) AppConnSnapshot {
return &appConnSnapshot{
metrics: metrics,
appConn: appConn,
}
}
@@ -177,19 +200,32 @@ func (app *appConnSnapshot) Error() error {
}
func (app *appConnSnapshot) ListSnapshotsSync(req types.RequestListSnapshots) (*types.ResponseListSnapshots, error) {
defer addTimeSample(app.metrics.MethodTiming.With("method", "list_snapshots", "type", "sync"))()
return app.appConn.ListSnapshotsSync(req)
}
func (app *appConnSnapshot) OfferSnapshotSync(req types.RequestOfferSnapshot) (*types.ResponseOfferSnapshot, error) {
defer addTimeSample(app.metrics.MethodTiming.With("method", "offer_snapshot", "type", "sync"))()
return app.appConn.OfferSnapshotSync(req)
}
func (app *appConnSnapshot) LoadSnapshotChunkSync(
req types.RequestLoadSnapshotChunk) (*types.ResponseLoadSnapshotChunk, error) {
defer addTimeSample(app.metrics.MethodTiming.With("method", "load_snapshot_chunk", "type", "sync"))()
return app.appConn.LoadSnapshotChunkSync(req)
}
func (app *appConnSnapshot) ApplySnapshotChunkSync(
req types.RequestApplySnapshotChunk) (*types.ResponseApplySnapshotChunk, error) {
defer addTimeSample(app.metrics.MethodTiming.With("method", "apply_snapshot_chunk", "type", "sync"))()
return app.appConn.ApplySnapshotChunkSync(req)
}
// addTimeSample returns a function that, when called, adds an observation to m.
// The observation added to m is the number of seconds ellapsed since addTimeSample
// was initially called. addTimeSample is meant to be called in a defer to calculate
// the amount of time a function takes to complete.
func addTimeSample(m metrics.Histogram) func() {
start := time.Now()
return func() { m.Observe(time.Since(start).Seconds()) }
}

47
proxy/metrics.go Normal file
View File

@@ -0,0 +1,47 @@
package proxy
import (
"github.com/go-kit/kit/metrics"
"github.com/go-kit/kit/metrics/discard"
"github.com/go-kit/kit/metrics/prometheus"
stdprometheus "github.com/prometheus/client_golang/prometheus"
)
const (
// MetricsSubsystem is a subsystem shared by all metrics exposed by this
// package.
MetricsSubsystem = "abci_connection"
)
// Metrics contains the prometheus metrics exposed by the proxy package.
type Metrics struct {
MethodTiming metrics.Histogram
}
// PrometheusMetrics constructs a Metrics instance that collects metrics samples.
// The resulting metrics will be prefixed with namespace and labeled with the
// defaultLabelsAndValues. defaultLabelsAndValues must be a list of string pairs
// where the first of each pair is the label and the second is the value.
func PrometheusMetrics(namespace string, defaultLabelsAndValues ...string) *Metrics {
defaultLabels := []string{}
for i := 0; i < len(defaultLabelsAndValues); i += 2 {
defaultLabels = append(defaultLabels, defaultLabelsAndValues[i])
}
return &Metrics{
MethodTiming: prometheus.NewHistogramFrom(stdprometheus.HistogramOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "method_timing_seconds",
Help: "ABCI Method Timing",
Buckets: []float64{.0001, .0004, .002, .009, .02, .1, .65, 2, 6, 25},
}, append(defaultLabels, []string{"method", "type"}...)).With(defaultLabelsAndValues...),
}
}
// NopMetrics constructs a Metrics instance that discards all samples and is suitable
// for testing.
func NopMetrics() *Metrics {
return &Metrics{
MethodTiming: discard.NewHistogram(),
}
}

16
proxy/multi_app_conn.go
View File

@@ -32,8 +32,8 @@ type AppConns interface {
}
// NewAppConns calls NewMultiAppConn.
func NewAppConns(clientCreator ClientCreator) AppConns {
return NewMultiAppConn(clientCreator)
func NewAppConns(clientCreator ClientCreator, metrics *Metrics) AppConns {
return NewMultiAppConn(clientCreator, metrics)
}
// multiAppConn implements AppConns.
@@ -44,6 +44,7 @@ func NewAppConns(clientCreator ClientCreator) AppConns {
type multiAppConn struct {
service.BaseService
metrics *Metrics
consensusConn AppConnConsensus
mempoolConn AppConnMempool
queryConn AppConnQuery
@@ -58,8 +59,9 @@ type multiAppConn struct {
}
// NewMultiAppConn makes all necessary abci connections to the application.
func NewMultiAppConn(clientCreator ClientCreator) AppConns {
func NewMultiAppConn(clientCreator ClientCreator, metrics *Metrics) AppConns {
multiAppConn := &multiAppConn{
metrics: metrics,
clientCreator: clientCreator,
}
multiAppConn.BaseService = *service.NewBaseService(nil, "multiAppConn", multiAppConn)
@@ -88,7 +90,7 @@ func (app *multiAppConn) OnStart() error {
return err
}
app.queryConnClient = c
app.queryConn = NewAppConnQuery(c)
app.queryConn = NewAppConnQuery(c, app.metrics)
c, err = app.abciClientFor(connSnapshot)
if err != nil {
@@ -96,7 +98,7 @@ func (app *multiAppConn) OnStart() error {
return err
}
app.snapshotConnClient = c
app.snapshotConn = NewAppConnSnapshot(c)
app.snapshotConn = NewAppConnSnapshot(c, app.metrics)
c, err = app.abciClientFor(connMempool)
if err != nil {
@@ -104,7 +106,7 @@ func (app *multiAppConn) OnStart() error {
return err
}
app.mempoolConnClient = c
app.mempoolConn = NewAppConnMempool(c)
app.mempoolConn = NewAppConnMempool(c, app.metrics)
c, err = app.abciClientFor(connConsensus)
if err != nil {
@@ -112,7 +114,7 @@ func (app *multiAppConn) OnStart() error {
return err
}
app.consensusConnClient = c
app.consensusConn = NewAppConnConsensus(c)
app.consensusConn = NewAppConnConsensus(c, app.metrics)
// Kill Tendermint if the ABCI application crashes.
go app.killTMOnClientError()

4
proxy/multi_app_conn_test.go
View File

@@ -28,7 +28,7 @@ func TestAppConns_Start_Stop(t *testing.T) {
clientCreatorMock.On("NewABCIClient").Return(clientMock, nil).Times(4)
appConns := NewAppConns(clientCreatorMock)
appConns := NewAppConns(clientCreatorMock, NopMetrics())
err := appConns.Start()
require.NoError(t, err)
@@ -68,7 +68,7 @@ func TestAppConns_Failure(t *testing.T) {
clientCreatorMock.On("NewABCIClient").Return(clientMock, nil)
appConns := NewAppConns(clientCreatorMock)
appConns := NewAppConns(clientCreatorMock, NopMetrics())
err := appConns.Start()
require.NoError(t, err)

10
state/execution_test.go
View File

@@ -35,7 +35,7 @@ var (
func TestApplyBlock(t *testing.T) {
app := &testApp{}
cc := proxy.NewLocalClientCreator(app)
proxyApp := proxy.NewAppConns(cc)
proxyApp := proxy.NewAppConns(cc, proxy.NopMetrics())
err := proxyApp.Start()
require.Nil(t, err)
defer proxyApp.Stop() //nolint:errcheck // ignore for tests
@@ -61,7 +61,7 @@ func TestApplyBlock(t *testing.T) {
func TestBeginBlockValidators(t *testing.T) {
app := &testApp{}
cc := proxy.NewLocalClientCreator(app)
proxyApp := proxy.NewAppConns(cc)
proxyApp := proxy.NewAppConns(cc, proxy.NopMetrics())
err := proxyApp.Start()
require.Nil(t, err)
defer proxyApp.Stop() //nolint:errcheck // no need to check error again
@@ -124,7 +124,7 @@ func TestBeginBlockValidators(t *testing.T) {
func TestBeginBlockByzantineValidators(t *testing.T) {
app := &testApp{}
cc := proxy.NewLocalClientCreator(app)
proxyApp := proxy.NewAppConns(cc)
proxyApp := proxy.NewAppConns(cc, proxy.NopMetrics())
err := proxyApp.Start()
require.Nil(t, err)
defer proxyApp.Stop() //nolint:errcheck // ignore for tests
@@ -348,7 +348,7 @@ func TestUpdateValidators(t *testing.T) {
func TestEndBlockValidatorUpdates(t *testing.T) {
app := &testApp{}
cc := proxy.NewLocalClientCreator(app)
proxyApp := proxy.NewAppConns(cc)
proxyApp := proxy.NewAppConns(cc, proxy.NopMetrics())
err := proxyApp.Start()
require.Nil(t, err)
defer proxyApp.Stop() //nolint:errcheck // ignore for tests
@@ -419,7 +419,7 @@ func TestEndBlockValidatorUpdates(t *testing.T) {
func TestEndBlockValidatorUpdatesResultingInEmptySet(t *testing.T) {
app := &testApp{}
cc := proxy.NewLocalClientCreator(app)
proxyApp := proxy.NewAppConns(cc)
proxyApp := proxy.NewAppConns(cc, proxy.NopMetrics())
err := proxyApp.Start()
require.Nil(t, err)
defer proxyApp.Stop() //nolint:errcheck // ignore for tests

2
state/helpers_test.go
View File

@@ -27,7 +27,7 @@ type paramsChangeTestCase struct {
func newTestApp() proxy.AppConns {
app := &testApp{}
cc := proxy.NewLocalClientCreator(app)
return proxy.NewAppConns(cc)
return proxy.NewAppConns(cc, proxy.NopMetrics())
}
func makeAndCommitGoodBlock(