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.

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

feat: add optional native histogram support to latency metrics #3737

Merged
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
10 changes: 7 additions & 3 deletions cluster/channel.go
Original file line number Diff line number Diff line change
Expand Up @@ -70,9 +70,13 @@ func NewChannel(
ConstLabels: prometheus.Labels{"key": key},
})
oversizeGossipDuration := prometheus.NewHistogram(prometheus.HistogramOpts{
Name: "alertmanager_oversize_gossip_message_duration_seconds",
Help: "Duration of oversized gossip message requests.",
ConstLabels: prometheus.Labels{"key": key},
Name: "alertmanager_oversize_gossip_message_duration_seconds",
Help: "Duration of oversized gossip message requests.",
ConstLabels: prometheus.Labels{"key": key},
Buckets: prometheus.DefBuckets,
NativeHistogramBucketFactor: 1.1,
NativeHistogramMaxBucketNumber: 100,
NativeHistogramMinResetDuration: 1 * time.Hour,
})

reg.MustRegister(oversizeGossipDuration, oversizeGossipMessageFailureTotal, oversizeGossipMessageDroppedTotal, oversizeGossipMessageSentTotal)
Expand Down
9 changes: 6 additions & 3 deletions cluster/delegate.go
Original file line number Diff line number Diff line change
Expand Up @@ -104,9 +104,12 @@ func newDelegate(l log.Logger, reg prometheus.Registerer, p *Peer, retransmit in
}, []string{"peer"},
)
nodePingDuration := prometheus.NewHistogramVec(prometheus.HistogramOpts{
Name: "alertmanager_cluster_pings_seconds",
Help: "Histogram of latencies for ping messages.",
Buckets: []float64{.005, .01, .025, .05, .1, .25, .5},
Name: "alertmanager_cluster_pings_seconds",
Help: "Histogram of latencies for ping messages.",
Buckets: []float64{.005, .01, .025, .05, .1, .25, .5},
NativeHistogramBucketFactor: 1.1,
NativeHistogramMaxBucketNumber: 100,
NativeHistogramMinResetDuration: 1 * time.Hour,
}, []string{"peer"},
)

Expand Down
9 changes: 6 additions & 3 deletions cmd/alertmanager/main.go
Original file line number Diff line number Diff line change
Expand Up @@ -64,9 +64,12 @@ import (
var (
requestDuration = prometheus.NewHistogramVec(
prometheus.HistogramOpts{
Name: "alertmanager_http_request_duration_seconds",
Help: "Histogram of latencies for HTTP requests.",
Buckets: []float64{.05, 0.1, .25, .5, .75, 1, 2, 5, 20, 60},
Name: "alertmanager_http_request_duration_seconds",
Help: "Histogram of latencies for HTTP requests.",
Buckets: []float64{.05, 0.1, .25, .5, .75, 1, 2, 5, 20, 60},
NativeHistogramBucketFactor: 1.1,
NativeHistogramMaxBucketNumber: 100,
NativeHistogramMinResetDuration: 1 * time.Hour,
},
[]string{"handler", "method"},
)
Expand Down
8 changes: 6 additions & 2 deletions nflog/nflog.go
Original file line number Diff line number Diff line change
Expand Up @@ -139,8 +139,12 @@ func newMetrics(r prometheus.Registerer) *metrics {
Help: "Number notification log received queries that failed.",
})
m.queryDuration = prometheus.NewHistogram(prometheus.HistogramOpts{
Name: "alertmanager_nflog_query_duration_seconds",
Help: "Duration of notification log query evaluation.",
Name: "alertmanager_nflog_query_duration_seconds",
Help: "Duration of notification log query evaluation.",
Buckets: prometheus.DefBuckets,
NativeHistogramBucketFactor: 1.1,
NativeHistogramMaxBucketNumber: 100,
NativeHistogramMinResetDuration: 1 * time.Hour,
})
m.propagatedMessagesTotal = prometheus.NewCounter(prometheus.CounterOpts{
Name: "alertmanager_nflog_gossip_messages_propagated_total",
Expand Down
11 changes: 7 additions & 4 deletions notify/notify.go
Original file line number Diff line number Diff line change
Expand Up @@ -291,10 +291,13 @@ func NewMetrics(r prometheus.Registerer, ff featurecontrol.Flagger) *Metrics {
Help: "The total number of notifications suppressed for being silenced, inhibited, outside of active time intervals or within muted time intervals.",
}, []string{"reason"}),
notificationLatencySeconds: prometheus.NewHistogramVec(prometheus.HistogramOpts{
Namespace: "alertmanager",
Name: "notification_latency_seconds",
Help: "The latency of notifications in seconds.",
Buckets: []float64{1, 5, 10, 15, 20},
Namespace: "alertmanager",
Name: "notification_latency_seconds",
Help: "The latency of notifications in seconds.",
Buckets: []float64{1, 5, 10, 15, 20},
NativeHistogramBucketFactor: 1.1,
NativeHistogramMaxBucketNumber: 100,
NativeHistogramMinResetDuration: 1 * time.Hour,
}, labels),
ff: ff,
}
Expand Down
8 changes: 6 additions & 2 deletions silence/silence.go
Original file line number Diff line number Diff line change
Expand Up @@ -271,8 +271,12 @@ func newMetrics(r prometheus.Registerer, s *Silences) *metrics {
Help: "How many silence received queries did not succeed.",
})
m.queryDuration = prometheus.NewHistogram(prometheus.HistogramOpts{
Name: "alertmanager_silences_query_duration_seconds",
Help: "Duration of silence query evaluation.",
Name: "alertmanager_silences_query_duration_seconds",
Help: "Duration of silence query evaluation.",
Buckets: prometheus.DefBuckets,
NativeHistogramBucketFactor: 1.1,
NativeHistogramMaxBucketNumber: 100,
NativeHistogramMinResetDuration: 1 * time.Hour,
})
m.propagatedMessagesTotal = prometheus.NewCounter(prometheus.CounterOpts{
Name: "alertmanager_silences_gossip_messages_propagated_total",
Expand Down
Loading