From aca6d4d8247f675113b906f76c48918bd4424805 Mon Sep 17 00:00:00 2001 From: CharlesCheung Date: Fri, 10 Nov 2023 17:08:57 +0800 Subject: [PATCH] add cdc_resolvedts_high_delay alert --- metrics/alertmanager/ticdc.rules.yml | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/metrics/alertmanager/ticdc.rules.yml b/metrics/alertmanager/ticdc.rules.yml index 3c80ccda154..acf51f932b7 100644 --- a/metrics/alertmanager/ticdc.rules.yml +++ b/metrics/alertmanager/ticdc.rules.yml @@ -51,6 +51,18 @@ groups: value: '{{ $value }}' summary: cdc owner checkpoint delay more than 10 minutes + - alert: cdc_resolvedts_high_delay + expr: ticdc_owner_resolved_ts_lag > 300 + for: 1m + labels: + env: ENV_LABELS_ENV + level: critical + expr: ticdc_owner_resolved_ts_lag > 300 + annotations: + description: 'cluster: ENV_LABELS_ENV, instance: {{ $labels.instance }}, values: {{ $value }}' + value: '{{ $value }}' + summary: cdc owner resolved ts delay more than 5 minutes + - alert: ticdc_sink_execution_error expr: changes(ticdc_sink_execution_error[1m]) > 0 for: 1m