Skip to content

query: Add metric to track healthy/unhealthy endpoints #8492

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

Draft
wants to merge 3 commits into
base: main
Choose a base branch
from
Draft

query: Add metric to track healthy/unhealthy endpoints #8492

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
59a5e5b
Add metric to track healthy/unhealthy endpoints in query
codesome Sep 15, 2025
cf2c305
Fix lint
codesome Sep 16, 2025
58dace7
more lint
codesome Sep 16, 2025
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
24 changes: 21 additions & 3 deletions pkg/query/endpointset.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@ import (
"github.com/go-kit/log/level"
"github.com/pkg/errors"
"github.com/prometheus/client_golang/prometheus"
"github.com/prometheus/client_golang/prometheus/promauto"
"github.com/prometheus/prometheus/model/labels"
"google.golang.org/grpc"
"google.golang.org/grpc/codes"
Expand Down Expand Up @@ -217,9 +218,10 @@ type EndpointSet struct {

updateMtx sync.Mutex

endpointsMtx sync.RWMutex
endpoints map[string]*endpointRef
endpointsMetric *endpointSetNodeCollector
endpointsMtx sync.RWMutex
endpoints map[string]*endpointRef
endpointsMetric *endpointSetNodeCollector
endpointsStatusCount *prometheus.GaugeVec

// Track if the first update has completed
firstUpdateOnce sync.Once
Expand Down Expand Up @@ -270,6 +272,13 @@ func NewEndpointSet(
},
endpoints: make(map[string]*endpointRef),
firstUpdateChan: make(chan struct{}),
endpointsStatusCount: promauto.With(reg).NewGaugeVec(
prometheus.GaugeOpts{
Name: "thanos_query_endpoints",
Help: "Number of endpoints connected to the querier categorized by healthy/unhealthy. Strict endpoints are never considered as unhealthy.",
},
[]string{"status"},
),
}
}

Expand Down Expand Up @@ -394,6 +403,15 @@ func (e *EndpointSet) Update(ctx context.Context) {

e.endpointsMetric.Update(stats)

activeCount := len(e.endpoints)
specsCount := len(e.endpointSpecs())
inactiveCount := specsCount - activeCount
if inactiveCount < 0 {
inactiveCount = 0
}
e.endpointsStatusCount.WithLabelValues("healthy").Set(float64(activeCount))
e.endpointsStatusCount.WithLabelValues("unhealthy").Set(float64(inactiveCount))

// Signal that the first update has completed
e.firstUpdateOnce.Do(func() {
close(e.firstUpdateChan)
Expand Down
Loading