diff --git a/doc/admin/observability/alert_solutions.md b/doc/admin/observability/alert_solutions.md index a5165651d12654..0df7cf658593b7 100644 --- a/doc/admin/observability/alert_solutions.md +++ b/doc/admin/observability/alert_solutions.md @@ -3150,7 +3150,7 @@ with your code hosts connections or networking issues affecting communication wi **Descriptions:** -- critical repo-updater: 0+ rate of growth of update queue length over 5 minutes for 30m0s +- critical repo-updater: 0+ rate of growth of update queue length over 5 minutes for 2h0m0s **Possible solutions:** diff --git a/monitoring/definitions/repo_updater.go b/monitoring/definitions/repo_updater.go index 7a301702ff3fd6..aa9d338c3a33b9 100644 --- a/monitoring/definitions/repo_updater.go +++ b/monitoring/definitions/repo_updater.go @@ -184,7 +184,7 @@ func RepoUpdater() *monitoring.Container { Description: "rate of growth of update queue length over 5 minutes", Query: `max(deriv(src_repoupdater_sched_update_queue_length[5m]))`, // Alert if the derivative is positive for longer than 30 minutes - Critical: monitoring.Alert().Greater(0).For(30 * time.Minute), + Critical: monitoring.Alert().Greater(0).For(120 * time.Minute), Panel: monitoring.Panel().Unit(monitoring.Number), Owner: monitoring.ObservableOwnerCloud, PossibleSolutions: "Check repo-updater logs for indications that the queue is not being processed. The queue length should trend downwards over time as items are sent to GitServer",