From a4144d6cf87bf5bb189299c7b96bd667f8095449 Mon Sep 17 00:00:00 2001 From: ibizaman Date: Mon, 22 Dec 2025 22:46:37 +0100 Subject: [PATCH] monitoring: try late backup rule without false positive --- modules/blocks/monitoring/rules.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/modules/blocks/monitoring/rules.json b/modules/blocks/monitoring/rules.json index 9d77fa0..8e050e6 100644 --- a/modules/blocks/monitoring/rules.json +++ b/modules/blocks/monitoring/rules.json @@ -275,7 +275,7 @@ }, "editorMode": "code", "exemplar": false, - "expr": "(\n # No run in the last 24 hours\n systemd_timer_last_trigger_seconds{name=~\".*backup.*.timer\"}\n ==\n systemd_timer_last_trigger_seconds{name=~\".*backup.*.timer\"} offset 24h\n)\nOR\n(\n # All runs in last 24 hours failed\n label_replace((\n time()\n -\n systemd_timer_last_trigger_seconds{name=~\".*backup.*.timer\"}\n ) < 24*60*60, \"name\", \"$1.service\", \"name\", \"(.*).timer\")\n AND on(name)\n (\n max_over_time(systemd_unit_state{name=~\".*backup.*.service\", state=\"failed\"}[24h]) > 0\n )\n)", + "expr": "(\n # Timer triggered at least once in the last 24h\n label_replace((\n time()\n -\n systemd_timer_last_trigger_seconds{name=~\".*backup.*.timer\"}\n ) < 24*60*60, \"name\", \"$1.service\", \"name\", \"(.*).timer\")\n AND on(name)\n # At least one failure in the last 24h\n (\n max_over_time(systemd_unit_state{name=~\".*backup.*.service\", state=\"failed\"}[24h]) > 0\n )\n AND on(name)\n # No successes in the last 24h\n (\n max_over_time(systemd_unit_state{name=~\".*backup.*.service\", state=\"inactive\"}[24h]) == 0\n )\n)", "instant": false, "interval": "", "intervalMs": 15000,