IntenseWebs/grafana
3
0
Fork 0
mirror of https://github.com/grafana/grafana.git synced 2025-02-25 18:55:37 -06:00
Code Issues Packages Projects Releases Wiki Activity

Convert some metrics to Histograms (#50420)

Browse Source 
Because Summary metrics can not be aggreated, convert them to histograms
so that users with HA deployments can use these metrics.
* Convert metrics registration to promauto.
* Improve help text style.

Signed-off-by: SuperQ <superq@gmail.com>
This commit is contained in:
Ben Kochie
2022-06-15 13:19:43 +02:00
committed by GitHub
parent 390b7d084e
commit 68691d7775
4 changed files with 70 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
pkg/services/ngalert/metrics/ngalert.go
View File

@@ -50,7 +50,7 @@ type Scheduler struct {
BehindSeconds prometheus.Gauge
EvalTotal *prometheus.CounterVec
EvalFailures *prometheus.CounterVec
EvalDuration *prometheus.SummaryVec
EvalDuration *prometheus.HistogramVec
SchedulePeriodicDuration prometheus.Histogram
SchedulableAlertRules prometheus.Gauge
SchedulableAlertRulesHash prometheus.Gauge
@@ -156,13 +156,13 @@ func newSchedulerMetrics(r prometheus.Registerer) *Scheduler {
},
[]string{"org"},
),
EvalDuration: promauto.With(r).NewSummaryVec(
prometheus.SummaryOpts{
Namespace: Namespace,
Subsystem: Subsystem,
Name: "rule_evaluation_duration_seconds",
Help: "The duration for a rule to execute.",
Objectives: map[float64]float64{0.5: 0.05, 0.9: 0.01, 0.99: 0.001},
EvalDuration: promauto.With(r).NewHistogramVec(
prometheus.HistogramOpts{
Namespace: Namespace,
Subsystem: Subsystem,
Name: "rule_evaluation_duration_seconds",
Help: "The duration for a rule to execute.",
Buckets: []float64{.005, .01, .025, .05, .1, .25, .5, 1, 2.5, 5, 10, 25, 50, 100},
},
[]string{"org"},
),

20
pkg/services/ngalert/schedule/schedule_unit_test.go
View File

@@ -441,10 +441,22 @@ func TestSchedule_ruleRoutine(t *testing.T) {
// duration metric has 0 values because of mocked clock that do not advance
expectedMetric := fmt.Sprintf(
`# HELP grafana_alerting_rule_evaluation_duration_seconds The duration for a rule to execute.
# TYPE grafana_alerting_rule_evaluation_duration_seconds summary
grafana_alerting_rule_evaluation_duration_seconds{org="%[1]d",quantile="0.5"} 0
grafana_alerting_rule_evaluation_duration_seconds{org="%[1]d",quantile="0.9"} 0
grafana_alerting_rule_evaluation_duration_seconds{org="%[1]d",quantile="0.99"} 0
# TYPE grafana_alerting_rule_evaluation_duration_seconds histogram
grafana_alerting_rule_evaluation_duration_seconds_bucket{org="%[1]d",le="0.005"} 1
grafana_alerting_rule_evaluation_duration_seconds_bucket{org="%[1]d",le="0.01"} 1
grafana_alerting_rule_evaluation_duration_seconds_bucket{org="%[1]d",le="0.025"} 1
grafana_alerting_rule_evaluation_duration_seconds_bucket{org="%[1]d",le="0.05"} 1
grafana_alerting_rule_evaluation_duration_seconds_bucket{org="%[1]d",le="0.1"} 1
grafana_alerting_rule_evaluation_duration_seconds_bucket{org="%[1]d",le="0.25"} 1
grafana_alerting_rule_evaluation_duration_seconds_bucket{org="%[1]d",le="0.5"} 1
grafana_alerting_rule_evaluation_duration_seconds_bucket{org="%[1]d",le="1"} 1
grafana_alerting_rule_evaluation_duration_seconds_bucket{org="%[1]d",le="2.5"} 1
grafana_alerting_rule_evaluation_duration_seconds_bucket{org="%[1]d",le="5"} 1
grafana_alerting_rule_evaluation_duration_seconds_bucket{org="%[1]d",le="10"} 1
grafana_alerting_rule_evaluation_duration_seconds_bucket{org="%[1]d",le="25"} 1
grafana_alerting_rule_evaluation_duration_seconds_bucket{org="%[1]d",le="50"} 1
grafana_alerting_rule_evaluation_duration_seconds_bucket{org="%[1]d",le="100"} 1
grafana_alerting_rule_evaluation_duration_seconds_bucket{org="%[1]d",le="+Inf"} 1
grafana_alerting_rule_evaluation_duration_seconds_sum{org="%[1]d"} 0
grafana_alerting_rule_evaluation_duration_seconds_count{org="%[1]d"} 1
# HELP grafana_alerting_rule_evaluation_failures_total The total number of rule evaluation failures.