Files
tendermint/consensus/metrics.go
mergify[bot] f36cc80568 consensus: calculate prevote message delay metric (backport #7551) (#7617)
* consensus: calculate prevote message delay metric (#7551)

## What does this pull request do?
This pull requests adds two metrics intended for use in calculating an experimental value for `MessageDelay`.

The metrics are as follows:
```
# HELP tendermint_consensus_complete_prevote_message_delay Difference in seconds between the proposal timestamp and the timestamp of the prevote that achieved 100% of the voting power in the prevote step.
# TYPE tendermint_consensus_complete_prevote_message_delay gauge
tendermint_consensus_complete_prevote_message_delay{chain_id="test-chain-aZbwF1"} 0.013025505

# HELP tendermint_consensus_quorum_prevote_message_delay Difference in seconds between the proposal timestamp and the timestamp of the prevote that achieved a quorum in the prevote step.
# TYPE tendermint_consensus_quorum_prevote_message_delay gauge
tendermint_consensus_quorum_prevote_message_delay{chain_id="test-chain-aZbwF1"} 0.013025505
```

## Why this change?

 For more information on what these metrics are calculating, see #7202. The aim is to merge to backport these metrics to v0.34 and run nodes on a few popular chains with these metrics to determine the experimental values for `MessageDelay` on these popular chains and use these to select our default `SynchronyParams.MessageDelay` value.

## Why Gauges for the metrics?
Gauges allow us to overwrite the metric on each successive observation. We can then capture these metrics over time to track the highest and lowest observed value.

(cherry picked from commit 0c82ceaa5f)

# Conflicts:
#	consensus/metrics.go
#	consensus/state.go

* fix merge conflicts

Co-authored-by: William Banfield <4561443+williambanfield@users.noreply.github.com>
Co-authored-by: William Banfield <wbanfield@gmail.com>
2022-01-19 12:10:18 -05:00

253 lines
9.4 KiB
Go

package consensus
import (
"github.com/go-kit/kit/metrics"
"github.com/go-kit/kit/metrics/discard"
prometheus "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 = "consensus"
)
// Metrics contains metrics exposed by this package.
type Metrics struct {
// Height of the chain.
Height metrics.Gauge
// ValidatorLastSignedHeight of a validator.
ValidatorLastSignedHeight metrics.Gauge
// Number of rounds.
Rounds metrics.Gauge
// Number of validators.
Validators metrics.Gauge
// Total power of all validators.
ValidatorsPower metrics.Gauge
// Power of a validator.
ValidatorPower metrics.Gauge
// Amount of blocks missed by a validator.
ValidatorMissedBlocks metrics.Gauge
// Number of validators who did not sign.
MissingValidators metrics.Gauge
// Total power of the missing validators.
MissingValidatorsPower metrics.Gauge
// Number of validators who tried to double sign.
ByzantineValidators metrics.Gauge
// Total power of the byzantine validators.
ByzantineValidatorsPower metrics.Gauge
// Time between this and the last block.
BlockIntervalSeconds metrics.Histogram
// Number of transactions.
NumTxs metrics.Gauge
// Size of the block.
BlockSizeBytes metrics.Gauge
// Total number of transactions.
TotalTxs metrics.Gauge
// The latest block height.
CommittedHeight metrics.Gauge
// Whether or not a node is fast syncing. 1 if yes, 0 if no.
FastSyncing metrics.Gauge
// Whether or not a node is state syncing. 1 if yes, 0 if no.
StateSyncing metrics.Gauge
// Number of blockparts transmitted by peer.
BlockParts 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.
//
// To compute it, sum the voting power over each prevote received, in increasing
// order of timestamp. The timestamp of the first prevote to increase the sum to
// be above 2/3 of the total voting power of the network defines the endpoint
// the endpoint of the interval. Subtract the proposal timestamp from this endpoint
// to obtain the quorum delay.
QuorumPrevoteMessageDelay metrics.Gauge
// FullPrevoteMessageDelay is the interval in seconds between the proposal
// timestamp and the timestamp of the latest prevote in a round where 100%
// of the voting power on the network issued prevotes.
FullPrevoteMessageDelay metrics.Gauge
}
// PrometheusMetrics returns Metrics build using Prometheus client library.
// Optionally, labels can be provided along with their values ("foo",
// "fooValue").
func PrometheusMetrics(namespace string, labelsAndValues ...string) *Metrics {
labels := []string{}
for i := 0; i < len(labelsAndValues); i += 2 {
labels = append(labels, labelsAndValues[i])
}
return &Metrics{
Height: prometheus.NewGaugeFrom(stdprometheus.GaugeOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "height",
Help: "Height of the chain.",
}, labels).With(labelsAndValues...),
Rounds: prometheus.NewGaugeFrom(stdprometheus.GaugeOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "rounds",
Help: "Number of rounds.",
}, labels).With(labelsAndValues...),
Validators: prometheus.NewGaugeFrom(stdprometheus.GaugeOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "validators",
Help: "Number of validators.",
}, labels).With(labelsAndValues...),
ValidatorLastSignedHeight: prometheus.NewGaugeFrom(stdprometheus.GaugeOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "validator_last_signed_height",
Help: "Last signed height for a validator",
}, append(labels, "validator_address")).With(labelsAndValues...),
ValidatorMissedBlocks: prometheus.NewGaugeFrom(stdprometheus.GaugeOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "validator_missed_blocks",
Help: "Total missed blocks for a validator",
}, append(labels, "validator_address")).With(labelsAndValues...),
ValidatorsPower: prometheus.NewGaugeFrom(stdprometheus.GaugeOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "validators_power",
Help: "Total power of all validators.",
}, labels).With(labelsAndValues...),
ValidatorPower: prometheus.NewGaugeFrom(stdprometheus.GaugeOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "validator_power",
Help: "Power of a validator",
}, append(labels, "validator_address")).With(labelsAndValues...),
MissingValidators: prometheus.NewGaugeFrom(stdprometheus.GaugeOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "missing_validators",
Help: "Number of validators who did not sign.",
}, labels).With(labelsAndValues...),
MissingValidatorsPower: prometheus.NewGaugeFrom(stdprometheus.GaugeOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "missing_validators_power",
Help: "Total power of the missing validators.",
}, labels).With(labelsAndValues...),
ByzantineValidators: prometheus.NewGaugeFrom(stdprometheus.GaugeOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "byzantine_validators",
Help: "Number of validators who tried to double sign.",
}, labels).With(labelsAndValues...),
ByzantineValidatorsPower: prometheus.NewGaugeFrom(stdprometheus.GaugeOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "byzantine_validators_power",
Help: "Total power of the byzantine validators.",
}, labels).With(labelsAndValues...),
BlockIntervalSeconds: prometheus.NewHistogramFrom(stdprometheus.HistogramOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "block_interval_seconds",
Help: "Time between this and the last block.",
}, labels).With(labelsAndValues...),
NumTxs: prometheus.NewGaugeFrom(stdprometheus.GaugeOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "num_txs",
Help: "Number of transactions.",
}, labels).With(labelsAndValues...),
BlockSizeBytes: prometheus.NewGaugeFrom(stdprometheus.GaugeOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "block_size_bytes",
Help: "Size of the block.",
}, labels).With(labelsAndValues...),
TotalTxs: prometheus.NewGaugeFrom(stdprometheus.GaugeOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "total_txs",
Help: "Total number of transactions.",
}, labels).With(labelsAndValues...),
CommittedHeight: prometheus.NewGaugeFrom(stdprometheus.GaugeOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "latest_block_height",
Help: "The latest block height.",
}, labels).With(labelsAndValues...),
FastSyncing: prometheus.NewGaugeFrom(stdprometheus.GaugeOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "fast_syncing",
Help: "Whether or not a node is fast syncing. 1 if yes, 0 if no.",
}, labels).With(labelsAndValues...),
StateSyncing: prometheus.NewGaugeFrom(stdprometheus.GaugeOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "state_syncing",
Help: "Whether or not a node is state syncing. 1 if yes, 0 if no.",
}, labels).With(labelsAndValues...),
BlockParts: prometheus.NewCounterFrom(stdprometheus.CounterOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "block_parts",
Help: "Number of blockparts transmitted by peer.",
}, append(labels, "peer_id")).With(labelsAndValues...),
QuorumPrevoteMessageDelay: prometheus.NewGaugeFrom(stdprometheus.GaugeOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "quorum_prevote_message_delay",
Help: "Difference in seconds between the proposal timestamp and the timestamp " +
"of the latest prevote that achieved a quorum in the prevote step.",
}, labels).With(labelsAndValues...),
FullPrevoteMessageDelay: prometheus.NewGaugeFrom(stdprometheus.GaugeOpts{
Namespace: namespace,
Subsystem: MetricsSubsystem,
Name: "full_prevote_message_delay",
Help: "Difference in seconds between the proposal timestamp and the timestamp " +
"of the latest prevote that achieved 100% of the voting power in the prevote step.",
}, labels).With(labelsAndValues...),
}
}
// NopMetrics returns no-op Metrics.
func NopMetrics() *Metrics {
return &Metrics{
Height: discard.NewGauge(),
ValidatorLastSignedHeight: discard.NewGauge(),
Rounds: discard.NewGauge(),
Validators: discard.NewGauge(),
ValidatorsPower: discard.NewGauge(),
ValidatorPower: discard.NewGauge(),
ValidatorMissedBlocks: discard.NewGauge(),
MissingValidators: discard.NewGauge(),
MissingValidatorsPower: discard.NewGauge(),
ByzantineValidators: discard.NewGauge(),
ByzantineValidatorsPower: discard.NewGauge(),
BlockIntervalSeconds: discard.NewHistogram(),
NumTxs: discard.NewGauge(),
BlockSizeBytes: discard.NewGauge(),
TotalTxs: discard.NewGauge(),
CommittedHeight: discard.NewGauge(),
FastSyncing: discard.NewGauge(),
StateSyncing: discard.NewGauge(),
BlockParts: discard.NewCounter(),
QuorumPrevoteMessageDelay: discard.NewGauge(),
FullPrevoteMessageDelay: discard.NewGauge(),
}
}