Skip to content

Add AM aggregation group metrics #5592

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 1 commit into from
Oct 7, 2023
Merged

Add AM aggregation group metrics #5592

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
1 change: 1 addition & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,7 @@
* [FEATURE] Query Frontend: Add `-frontend.retry-on-too-many-outstanding-requests` to re-enqueue 429 requests if there are multiple query-schedulers available. #5496
* [FEATURE] Store Gateway: Add `-blocks-storage.bucket-store.max-inflight-requests` for store gateways to reject further requests upon reaching the limit. #5553
* [FEATURE] Store Gateway: Add `cortex_bucket_store_block_load_duration_seconds` histogram to track time to load blocks. #5580
* [FEATURE] AlertManager: Add `cortex_alertmanager_dispatcher_aggregation_groups` and `cortex_alertmanager_dispatcher_alert_processing_duration_seconds` metrics for dispatcher. #5592
* [ENHANCEMENT] Distributor/Ingester: Add span on push path #5319
* [ENHANCEMENT] Support object storage backends for runtime configuration file. #5292
* [ENHANCEMENT] Query Frontend: Reject subquery with too small step size. #5323
Expand Down
14 changes: 14 additions & 0 deletions pkg/alertmanager/alertmanager_metrics.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,6 +60,8 @@ type alertmanagerMetrics struct {
persistFailed *prometheus.Desc

notificationRateLimited *prometheus.Desc
dispatcherAggregationGroups *prometheus.Desc
dispatcherProcessingDuration *prometheus.Desc
dispatcherAggregationGroupsLimitReached *prometheus.Desc
insertAlertFailures *prometheus.Desc
alertsLimiterAlertsCount *prometheus.Desc
Expand Down Expand Up @@ -217,6 +219,14 @@ func newAlertmanagerMetrics() *alertmanagerMetrics {
"cortex_alertmanager_dispatcher_aggregation_group_limit_reached_total",
"Number of times when dispatcher failed to create new aggregation group due to limit.",
[]string{"user"}, nil),
dispatcherAggregationGroups: prometheus.NewDesc(
"cortex_alertmanager_dispatcher_aggregation_groups",
"Number of active aggregation groups.",
[]string{"user"}, nil),
dispatcherProcessingDuration: prometheus.NewDesc(
"cortex_alertmanager_dispatcher_alert_processing_duration_seconds",
"Summary of latencies for the processing of alerts.",
[]string{"user"}, nil),
insertAlertFailures: prometheus.NewDesc(
"cortex_alertmanager_alerts_insert_limited_total",
"Total number of failures to store alert due to hitting alertmanager limits.",
Expand Down Expand Up @@ -279,6 +289,8 @@ func (m *alertmanagerMetrics) Describe(out chan<- *prometheus.Desc) {
out <- m.persistTotal
out <- m.persistFailed
out <- m.notificationRateLimited
out <- m.dispatcherAggregationGroups
out <- m.dispatcherProcessingDuration
out <- m.dispatcherAggregationGroupsLimitReached
out <- m.insertAlertFailures
out <- m.alertsLimiterAlertsCount
Expand Down Expand Up @@ -330,6 +342,8 @@ func (m *alertmanagerMetrics) Collect(out chan<- prometheus.Metric) {
data.SendSumOfCounters(out, m.persistFailed, "alertmanager_state_persist_failed_total")

data.SendSumOfCountersPerUserWithLabels(out, m.notificationRateLimited, "alertmanager_notification_rate_limited_total", "integration")
data.SendSumOfGaugesPerUser(out, m.dispatcherAggregationGroups, "alertmanager_dispatcher_aggregation_groups")
data.SendSumOfSummariesPerUser(out, m.dispatcherProcessingDuration, "alertmanager_dispatcher_alert_processing_duration_seconds")
data.SendSumOfCountersPerUser(out, m.dispatcherAggregationGroupsLimitReached, "alertmanager_dispatcher_aggregation_group_limit_reached_total")
data.SendSumOfCountersPerUser(out, m.insertAlertFailures, "alertmanager_alerts_insert_limited_total")
data.SendSumOfGaugesPerUser(out, m.alertsLimiterAlertsCount, "alertmanager_alerts_limiter_current_alerts")
Expand Down
22 changes: 22 additions & 0 deletions pkg/alertmanager/alertmanager_metrics_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,6 +60,14 @@ func TestAlertmanagerMetricsStore(t *testing.T) {
cortex_alertmanager_config_hash{user="user1"} 0
cortex_alertmanager_config_hash{user="user2"} 0
cortex_alertmanager_config_hash{user="user3"} 0
# HELP cortex_alertmanager_dispatcher_alert_processing_duration_seconds Summary of latencies for the processing of alerts.
# TYPE cortex_alertmanager_dispatcher_alert_processing_duration_seconds summary
cortex_alertmanager_dispatcher_alert_processing_duration_seconds_sum{user="user1"} 0
cortex_alertmanager_dispatcher_alert_processing_duration_seconds_count{user="user1"} 0
cortex_alertmanager_dispatcher_alert_processing_duration_seconds_sum{user="user2"} 0
cortex_alertmanager_dispatcher_alert_processing_duration_seconds_count{user="user2"} 0
cortex_alertmanager_dispatcher_alert_processing_duration_seconds_sum{user="user3"} 0
cortex_alertmanager_dispatcher_alert_processing_duration_seconds_count{user="user3"} 0
# HELP cortex_alertmanager_nflog_gc_duration_seconds Duration of the last notification log garbage collection cycle.
# TYPE cortex_alertmanager_nflog_gc_duration_seconds summary
cortex_alertmanager_nflog_gc_duration_seconds_sum 111
Expand Down Expand Up @@ -354,6 +362,14 @@ func TestAlertmanagerMetricsRemoval(t *testing.T) {
cortex_alertmanager_config_hash{user="user1"} 0
cortex_alertmanager_config_hash{user="user2"} 0
cortex_alertmanager_config_hash{user="user3"} 0
# HELP cortex_alertmanager_dispatcher_alert_processing_duration_seconds Summary of latencies for the processing of alerts.
# TYPE cortex_alertmanager_dispatcher_alert_processing_duration_seconds summary
cortex_alertmanager_dispatcher_alert_processing_duration_seconds_sum{user="user1"} 0
cortex_alertmanager_dispatcher_alert_processing_duration_seconds_count{user="user1"} 0
cortex_alertmanager_dispatcher_alert_processing_duration_seconds_sum{user="user2"} 0
cortex_alertmanager_dispatcher_alert_processing_duration_seconds_count{user="user2"} 0
cortex_alertmanager_dispatcher_alert_processing_duration_seconds_sum{user="user3"} 0
cortex_alertmanager_dispatcher_alert_processing_duration_seconds_count{user="user3"} 0

# HELP cortex_alertmanager_nflog_gc_duration_seconds Duration of the last notification log garbage collection cycle.
# TYPE cortex_alertmanager_nflog_gc_duration_seconds summary
Expand Down Expand Up @@ -649,6 +665,12 @@ func TestAlertmanagerMetricsRemoval(t *testing.T) {
# TYPE cortex_alertmanager_config_hash gauge
cortex_alertmanager_config_hash{user="user1"} 0
cortex_alertmanager_config_hash{user="user2"} 0
# HELP cortex_alertmanager_dispatcher_alert_processing_duration_seconds Summary of latencies for the processing of alerts.
# TYPE cortex_alertmanager_dispatcher_alert_processing_duration_seconds summary
cortex_alertmanager_dispatcher_alert_processing_duration_seconds_sum{user="user1"} 0
cortex_alertmanager_dispatcher_alert_processing_duration_seconds_count{user="user1"} 0
cortex_alertmanager_dispatcher_alert_processing_duration_seconds_sum{user="user2"} 0
cortex_alertmanager_dispatcher_alert_processing_duration_seconds_count{user="user2"} 0

# HELP cortex_alertmanager_nflog_gc_duration_seconds Duration of the last notification log garbage collection cycle.
# TYPE cortex_alertmanager_nflog_gc_duration_seconds summary
Expand Down