Skip to content

Fix: Reduce histogram bucket cardinality from 500 to 12 #799

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

Merged
lalitadithya merged 3 commits into from
Feb 4, 2026
Merged

Fix: Reduce histogram bucket cardinality from 500 to 12 #799

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
af1d46a
Reduce histogram bucket cardinality from 500 to 12
jtschelling Feb 4, 2026
1603f42
Merge branch 'main' into fix/histogram-bucket-cardinality
jtschelling Feb 4, 2026
3434d63
fix: workqueue uses seconds, need to account for float values
jtschelling Feb 4, 2026
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
4 changes: 2 additions & 2 deletions platform-connectors/pkg/connectors/kubernetes/metrics.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,12 +46,12 @@ var (
nodeConditionUpdateDuration = promauto.NewHistogram(prometheus.HistogramOpts{
Name: "k8s_platform_connector_node_condition_update_duration_milliseconds",
Help: "Duration of node condition updates in milliseconds",
Buckets: prometheus.LinearBuckets(0, 10, 500),
Buckets: prometheus.ExponentialBuckets(10, 2, 12),
})

nodeEventUpdateCreateDuration = promauto.NewHistogram(prometheus.HistogramOpts{
Name: "k8s_platform_connector_node_event_update_create_duration_milliseconds",
Help: "Duration of node event updates/creations in milliseconds",
Buckets: prometheus.LinearBuckets(0, 10, 500),
Buckets: prometheus.ExponentialBuckets(10, 2, 12),
})
)
4 changes: 2 additions & 2 deletions platform-connectors/pkg/ringbuffer/metrics.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,15 +42,15 @@ func (prometheusMetricsProvider) NewLatencyMetric(name string) workqueue.Histogr
return promauto.NewHistogramVec(prometheus.HistogramOpts{
Name: "platform_connector_workqueue_latency_seconds_" + name,
Help: "How long an item stays in Platform connector workqueue before being requested",
Buckets: prometheus.LinearBuckets(0, 10, 500),
Buckets: prometheus.ExponentialBuckets(10, 2, 12),
}, []string{workqueueLabel}).WithLabelValues(name)
}

func (prometheusMetricsProvider) NewWorkDurationMetric(name string) workqueue.HistogramMetric {
return promauto.NewHistogramVec(prometheus.HistogramOpts{
Name: "platform_connector_workqueue_work_duration_seconds_" + name,
Help: "How long processing an item from Platform connector workqueue takes",
Buckets: prometheus.LinearBuckets(0, 10, 500),
Buckets: prometheus.ExponentialBuckets(10, 2, 12),
}, []string{workqueueLabel}).WithLabelValues(name)
}

Expand Down
1 change: 1 addition & 0 deletions platform-connectors/pkg/ringbuffer/ring_buffer.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,6 +62,7 @@ func NewRingBuffer(ringBufferName string, ctx context.Context, opts ...Option) *
}

workqueue.SetProvider(prometheusMetricsProvider{})

rateLimiter := workqueue.NewTypedItemExponentialFailureRateLimiter[*protos.HealthEvents](
cfg.baseDelay,
cfg.maxDelay,
Expand Down
Loading