Skip to content
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

Jump to bottom

tempo-mixin: regenerate yamls/ #956

Merged
merged 1 commit into from
Sep 14, 2021
Merged

tempo-mixin: regenerate yamls/ #956

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
46 changes: 42 additions & 4 deletions operations/tempo-mixin/yamls/alerts.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,14 +47,52 @@
"message": "Greater than 2 compactions have failed in the past hour."
"runbook_url": "https://github.com/grafana/tempo/tree/main/operations/tempo-mixin/runbook.md#TempoCompactionsFailing"
"expr": |
sum by (cluster, namespace) (increase(tempodb_compaction_errors_total{}[1h])) > 2
sum by (cluster, namespace) (increase(tempodb_compaction_errors_total{}[1h])) > 2 and
sum by (cluster, namespace) (increase(tempodb_compaction_errors_total{}[5m])) > 0
"labels":
"severity": "critical"
- "alert": "TempoFlushesFailing"
- "alert": "TempoIngesterFlushesFailing"
"annotations":
"message": "Greater than 2 flushes have failed in the past hour."
"runbook_url": "https://github.com/grafana/tempo/tree/main/operations/tempo-mixin/runbook.md#TempoFlushesFailing"
"runbook_url": "https://github.com/grafana/tempo/tree/main/operations/tempo-mixin/runbook.md#TempoIngesterFlushesFailing"
"expr": |
sum by (cluster, namespace) (increase(tempo_ingester_failed_flushes_total{}[1h])) > 2
sum by (cluster, namespace) (increase(tempo_ingester_failed_flushes_total{}[1h])) > 2 and
sum by (cluster, namespace) (increase(tempo_ingester_failed_flushes_total{}[5m])) > 0
"labels":
"severity": "critical"
- "alert": "TempoPollsFailing"
"annotations":
"message": "Greater than 2 polls have failed in the past hour."
"runbook_url": "https://github.com/grafana/tempo/tree/main/operations/tempo-mixin/runbook.md#TempoPollsFailing"
"expr": |
sum by (cluster, namespace) (increase(tempodb_blocklist_poll_errors_total{}[1h])) > 2 and
sum by (cluster, namespace) (increase(tempodb_blocklist_poll_errors_total{}[5m])) > 0
"labels":
"severity": "critical"
- "alert": "TempoTenantIndexFailures"
"annotations":
"message": "Greater than 2 tenant index failures in the past hour."
"runbook_url": "https://github.com/grafana/tempo/tree/main/operations/tempo-mixin/runbook.md#TempoTenantIndexFailures"
"expr": |
sum by (cluster, namespace) (increase(tempodb_blocklist_tenant_index_errors_total{}[1h])) > 2 and
sum by (cluster, namespace) (increase(tempodb_blocklist_tenant_index_errors_total{}[5m])) > 0
"labels":
"severity": "critical"
- "alert": "TempoNoTenantIndexBuilders"
"annotations":
"message": "No tenant index builders. Tenant index is out of date."
"runbook_url": "https://github.com/grafana/tempo/tree/main/operations/tempo-mixin/runbook.md#TempoNoTenantIndexBuilders"
"expr": |
sum by (cluster, namespace) (tempodb_blocklist_tenant_index_builder{}) == 0
"for": "5m"
"labels":
"severity": "critical"
- "alert": "TempoTenantIndexTooOld"
"annotations":
"message": "Tenant index age is 600 seconds old."
"runbook_url": "https://github.com/grafana/tempo/tree/main/operations/tempo-mixin/runbook.md#TempoTenantIndexTooOld"
"expr": |
max by (cluster, namespace) (tempodb_blocklist_tenant_index_age_seconds{}) > 600
"for": "5m"
"labels":
"severity": "critical"
Loading