Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Exports block query errors to prometheus metrics (counter) #1239

Merged
merged 5 commits into from
Jul 25, 2023
Merged

Exports block query errors to prometheus metrics (counter) #1239

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
3e58d53
separate by type
boojamya Jul 12, 2023
2e798f2
add help info
boojamya Jul 12, 2023
3b69d5a
remove new line in help and fix readme
boojamya Jul 12, 2023
72a4ef6
feedback
boojamya Jul 20, 2023
d52f0b5
Merge branch 'main' into dan/prom-errors
boojamya Jul 25, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion docs/advanced_usage.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
**Prometheus exporter**

If you started `rly` with the default `--debug-addr` argument,
you can use `http://$IP:7597/relayer/metrics` as a target for your prometheus scraper.
you can use `http://$IP:5183/relayer/metrics` as a target for your prometheus scraper.

**Example metrics**

Expand Down
6 changes: 6 additions & 0 deletions relayer/chains/cosmos/cosmos_chain_processor.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -386,12 +386,18 @@ func (ccp *CosmosChainProcessor) queryCycle(ctx context.Context, persistence *qu
queryCtx, cancelQueryCtx := context.WithTimeout(ctx, blockResultsQueryTimeout)
defer cancelQueryCtx()
blockRes, err = ccp.chainProvider.RPCClient.BlockResults(queryCtx, &i)
if err != nil && ccp.metrics != nil {
boojamya marked this conversation as resolved.
Show resolved Hide resolved
ccp.metrics.IncBlockQueryFailure(chainID, "RPC Client")
}
return err
})
eg.Go(func() (err error) {
queryCtx, cancelQueryCtx := context.WithTimeout(ctx, queryTimeout)
defer cancelQueryCtx()
ibcHeader, err = ccp.chainProvider.QueryIBCHeader(queryCtx, i)
if err != nil && ccp.metrics != nil {
ccp.metrics.IncBlockQueryFailure(chainID, "IBC Header")
}
return err
})

Expand Down
10 changes: 10 additions & 0 deletions relayer/processor/metrics.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@ type PrometheusMetrics struct {
LatestHeightGauge *prometheus.GaugeVec
WalletBalance *prometheus.GaugeVec
FeesSpent *prometheus.GaugeVec
BlockQueryFailure *prometheus.CounterVec
ClientExpiration *prometheus.GaugeVec
}

Expand Down Expand Up @@ -41,9 +42,14 @@ func (m *PrometheusMetrics) SetClientExpiration(pathName, chain, clientID, trust
m.ClientExpiration.WithLabelValues(pathName, chain, clientID, trustingPeriod).Set(timeToExpiration.Seconds())
}

func (m *PrometheusMetrics) IncBlockQueryFailure(chain, err string) {
m.BlockQueryFailure.WithLabelValues(chain, err).Inc()
}

func NewPrometheusMetrics() *PrometheusMetrics {
packetLabels := []string{"path", "chain", "channel", "port", "type"}
heightLabels := []string{"chain"}
blockQueryFailureLabels := []string{"chain", "type"}
walletLabels := []string{"chain", "gas_price", "key", "address", "denom"}
clientExpirationLables := []string{"path_name", "chain", "client_id", "trusting_period"}
registry := prometheus.NewRegistry()
Expand All @@ -70,6 +76,10 @@ func NewPrometheusMetrics() *PrometheusMetrics {
Name: "cosmos_relayer_fees_spent",
Help: "The amount of fees spent from the relayer's wallet",
}, walletLabels),
BlockQueryFailure: registerer.NewCounterVec(prometheus.CounterOpts{
Name: "cosmos_relayer_block_query_errors_total",
Help: "The total number of block query failures. The failures are separated into two catagories: 'RPC Client' and 'IBC Header'",
}, blockQueryFailureLabels),
ClientExpiration: registerer.NewGaugeVec(prometheus.GaugeOpts{
Name: "cosmos_relayer_client_expiration_seconds",
Help: "Seconds until the client expires",
Expand Down
Loading