Skip to content

Make iterations metric per rule_group #4121

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
merged 2 commits into from
Apr 29, 2021
Merged

Make iterations metric per rule_group #4121

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7ea009a
Make iterations metric per rule_group
gouthamve Apr 26, 2021
ae3ae82
Add per rule_group to iterations in test
gouthamve Apr 26, 2021
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
9 changes: 4 additions & 5 deletions pkg/ruler/manager_metrics.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,13 +44,13 @@ func NewManagerMetrics() *ManagerMetrics {
IterationsMissed: prometheus.NewDesc(
"cortex_prometheus_rule_group_iterations_missed_total",
"The total number of rule group evaluations missed due to slow rule group evaluation.",
[]string{"user"},
[]string{"user", "rule_group"},
nil,
),
IterationsScheduled: prometheus.NewDesc(
"cortex_prometheus_rule_group_iterations_total",
"The total number of scheduled rule group evaluations, whether executed or missed.",
[]string{"user"},
[]string{"user", "rule_group"},
nil,
),
EvalTotal: prometheus.NewDesc(
Expand Down Expand Up @@ -134,9 +134,8 @@ func (m *ManagerMetrics) Collect(out chan<- prometheus.Metric) {
data.SendSumOfSummariesPerUser(out, m.EvalDuration, "prometheus_rule_evaluation_duration_seconds")
data.SendSumOfSummariesPerUser(out, m.IterationDuration, "prometheus_rule_group_duration_seconds")

data.SendSumOfCountersPerUser(out, m.IterationsMissed, "prometheus_rule_group_iterations_missed_total")
data.SendSumOfCountersPerUser(out, m.IterationsScheduled, "prometheus_rule_group_iterations_total")

data.SendSumOfCountersPerUserWithLabels(out, m.IterationsMissed, "prometheus_rule_group_iterations_missed_total", "rule_group")
data.SendSumOfCountersPerUserWithLabels(out, m.IterationsScheduled, "prometheus_rule_group_iterations_total", "rule_group")
data.SendSumOfCountersPerUserWithLabels(out, m.EvalTotal, "prometheus_rule_evaluations_total", "rule_group")
data.SendSumOfCountersPerUserWithLabels(out, m.EvalFailures, "prometheus_rule_evaluation_failures_total", "rule_group")
data.SendSumOfGaugesPerUserWithLabels(out, m.GroupInterval, "prometheus_rule_group_interval_seconds", "rule_group")
Expand Down
50 changes: 32 additions & 18 deletions pkg/ruler/manager_metrics_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,14 +92,20 @@ cortex_prometheus_rule_group_duration_seconds_sum{user="user3"} 100
cortex_prometheus_rule_group_duration_seconds_count{user="user3"} 1
# HELP cortex_prometheus_rule_group_iterations_missed_total The total number of rule group evaluations missed due to slow rule group evaluation.
# TYPE cortex_prometheus_rule_group_iterations_missed_total counter
cortex_prometheus_rule_group_iterations_missed_total{user="user1"} 1
cortex_prometheus_rule_group_iterations_missed_total{user="user2"} 10
cortex_prometheus_rule_group_iterations_missed_total{user="user3"} 100
cortex_prometheus_rule_group_iterations_missed_total{rule_group="group_one",user="user1"} 1
cortex_prometheus_rule_group_iterations_missed_total{rule_group="group_one",user="user2"} 10
cortex_prometheus_rule_group_iterations_missed_total{rule_group="group_one",user="user3"} 100
cortex_prometheus_rule_group_iterations_missed_total{rule_group="group_two",user="user1"} 1
cortex_prometheus_rule_group_iterations_missed_total{rule_group="group_two",user="user2"} 10
cortex_prometheus_rule_group_iterations_missed_total{rule_group="group_two",user="user3"} 100
# HELP cortex_prometheus_rule_group_iterations_total The total number of scheduled rule group evaluations, whether executed or missed.
# TYPE cortex_prometheus_rule_group_iterations_total counter
cortex_prometheus_rule_group_iterations_total{user="user1"} 1
cortex_prometheus_rule_group_iterations_total{user="user2"} 10
cortex_prometheus_rule_group_iterations_total{user="user3"} 100
cortex_prometheus_rule_group_iterations_total{rule_group="group_one",user="user1"} 1
cortex_prometheus_rule_group_iterations_total{rule_group="group_one",user="user2"} 10
cortex_prometheus_rule_group_iterations_total{rule_group="group_one",user="user3"} 100
cortex_prometheus_rule_group_iterations_total{rule_group="group_two",user="user1"} 1
cortex_prometheus_rule_group_iterations_total{rule_group="group_two",user="user2"} 10
cortex_prometheus_rule_group_iterations_total{rule_group="group_two",user="user3"} 100
# HELP cortex_prometheus_rule_group_last_duration_seconds The duration of the last rule group evaluation.
# TYPE cortex_prometheus_rule_group_last_duration_seconds gauge
cortex_prometheus_rule_group_last_duration_seconds{rule_group="group_one",user="user1"} 1000
Expand Down Expand Up @@ -135,9 +141,11 @@ func populateManager(base float64) *prometheus.Registry {

metrics.evalDuration.Observe(base)
metrics.iterationDuration.Observe(base)
metrics.iterationsMissed.Add(base)
metrics.iterationsScheduled.Add(base)

metrics.iterationsScheduled.WithLabelValues("group_one").Add(base)
metrics.iterationsScheduled.WithLabelValues("group_two").Add(base)
metrics.iterationsMissed.WithLabelValues("group_one").Add(base)
metrics.iterationsMissed.WithLabelValues("group_two").Add(base)
metrics.evalTotal.WithLabelValues("group_one").Add(base)
metrics.evalTotal.WithLabelValues("group_two").Add(base)
metrics.evalFailures.WithLabelValues("group_one").Add(base)
Expand All @@ -162,8 +170,8 @@ func populateManager(base float64) *prometheus.Registry {
type groupMetrics struct {
evalDuration prometheus.Summary
iterationDuration prometheus.Summary
iterationsMissed prometheus.Counter
iterationsScheduled prometheus.Counter
iterationsMissed *prometheus.CounterVec
iterationsScheduled *prometheus.CounterVec
evalTotal *prometheus.CounterVec
evalFailures *prometheus.CounterVec
groupInterval *prometheus.GaugeVec
Expand All @@ -186,14 +194,20 @@ func newGroupMetrics(r prometheus.Registerer) *groupMetrics {
Help: "The duration of rule group evaluations.",
Objectives: map[float64]float64{0.01: 0.001, 0.05: 0.005, 0.5: 0.05, 0.90: 0.01, 0.99: 0.001},
}),
iterationsMissed: promauto.With(r).NewCounter(prometheus.CounterOpts{
Name: "prometheus_rule_group_iterations_missed_total",
Help: "The total number of rule group evaluations missed due to slow rule group evaluation.",
}),
iterationsScheduled: promauto.With(r).NewCounter(prometheus.CounterOpts{
Name: "prometheus_rule_group_iterations_total",
Help: "The total number of scheduled rule group evaluations, whether executed or missed.",
}),
iterationsMissed: promauto.With(r).NewCounterVec(
prometheus.CounterOpts{
Name: "prometheus_rule_group_iterations_missed_total",
Help: "The total number of rule group evaluations missed due to slow rule group evaluation.",
},
[]string{"rule_group"},
),
iterationsScheduled: promauto.With(r).NewCounterVec(
prometheus.CounterOpts{
Name: "prometheus_rule_group_iterations_total",
Help: "The total number of scheduled rule group evaluations, whether executed or missed.",
},
[]string{"rule_group"},
),
evalTotal: promauto.With(r).NewCounterVec(
prometheus.CounterOpts{
Name: "prometheus_rule_evaluations_total",
Expand Down