From 804f6c187bcf99434490e13b930fee7fa5d61a1c Mon Sep 17 00:00:00 2001 From: Frederic Branczyk <fbranczyk@gmail.com> Date: Tue, 30 May 2017 17:07:13 -0700 Subject: [PATCH] kube-prometheus: add dead man's switch --- assets/alertmanager/alertmanager.yaml | 10 ++++++---- assets/prometheus/rules/general.rules | 12 ++++++++++++ manifests/alertmanager/alertmanager-config.yaml | 2 +- manifests/prometheus/prometheus-k8s-rules.yaml | 12 ++++++++++++ 4 files changed, 31 insertions(+), 5 deletions(-) diff --git a/assets/alertmanager/alertmanager.yaml b/assets/alertmanager/alertmanager.yaml index f08a2106..6b5789b5 100644 --- a/assets/alertmanager/alertmanager.yaml +++ b/assets/alertmanager/alertmanager.yaml @@ -5,8 +5,10 @@ route: group_wait: 30s group_interval: 5m repeat_interval: 12h - receiver: 'webhook' + receiver: 'null' + routes: + - match: + alertname: DeadMansSwitch + receiver: 'null' receivers: -- name: 'webhook' - webhook_configs: - - url: 'http://alertmanagerwh:30500/' +- name: 'null' diff --git a/assets/prometheus/rules/general.rules b/assets/prometheus/rules/general.rules index 9a8f931f..ac782297 100644 --- a/assets/prometheus/rules/general.rules +++ b/assets/prometheus/rules/general.rules @@ -11,6 +11,18 @@ Alert TargetDown description = "A target of type {{ $labels.job }} is down." } +### Dead man's switch ### + +ALERT DeadMansSwitch + IF vector(1) + LABELS { + severity = "none", + } + ANNOTATIONS { + summary = "Alerting DeadMansSwitch", + description = "This is a DeadMansSwitch meant to ensure that the entire Alerting pipeline is functional.", + } + ### File descriptor alerts ### ALERT TooManyOpenFiles diff --git a/manifests/alertmanager/alertmanager-config.yaml b/manifests/alertmanager/alertmanager-config.yaml index eee36b33..62d39016 100644 --- a/manifests/alertmanager/alertmanager-config.yaml +++ b/manifests/alertmanager/alertmanager-config.yaml @@ -3,4 +3,4 @@ kind: Secret metadata: name: alertmanager-main data: - alertmanager.yaml: Z2xvYmFsOgogIHJlc29sdmVfdGltZW91dDogNW0Kcm91dGU6CiAgZ3JvdXBfYnk6IFsnam9iJ10KICBncm91cF93YWl0OiAzMHMKICBncm91cF9pbnRlcnZhbDogNW0KICByZXBlYXRfaW50ZXJ2YWw6IDEyaAogIHJlY2VpdmVyOiAnd2ViaG9vaycKcmVjZWl2ZXJzOgotIG5hbWU6ICd3ZWJob29rJwogIHdlYmhvb2tfY29uZmlnczoKICAtIHVybDogJ2h0dHA6Ly9hbGVydG1hbmFnZXJ3aDozMDUwMC8nCg== + alertmanager.yaml: Z2xvYmFsOgogIHJlc29sdmVfdGltZW91dDogNW0Kcm91dGU6CiAgZ3JvdXBfYnk6IFsnam9iJ10KICBncm91cF93YWl0OiAzMHMKICBncm91cF9pbnRlcnZhbDogNW0KICByZXBlYXRfaW50ZXJ2YWw6IDEyaAogIHJlY2VpdmVyOiAnbnVsbCcKICByb3V0ZXM6CiAgLSBtYXRjaDoKICAgICAgYWxlcnRuYW1lOiBEZWFkTWFuc1N3aXRjaAogICAgcmVjZWl2ZXI6ICdudWxsJwpyZWNlaXZlcnM6Ci0gbmFtZTogJ251bGwnCg== diff --git a/manifests/prometheus/prometheus-k8s-rules.yaml b/manifests/prometheus/prometheus-k8s-rules.yaml index f57b6785..c157909f 100644 --- a/manifests/prometheus/prometheus-k8s-rules.yaml +++ b/manifests/prometheus/prometheus-k8s-rules.yaml @@ -235,6 +235,18 @@ data: description = "A target of type {{ $labels.job }} is down." } + ### Dead man's switch ### + + ALERT DeadMansSwitch + IF vector(1) + LABELS { + severity = "none", + } + ANNOTATIONS { + summary = "Alerting DeadMansSwitch", + description = "This is a DeadMansSwitch meant to ensure that the entire Alerting pipeline is functional.", + } + ### File descriptor alerts ### ALERT TooManyOpenFiles -- GitLab