# HG changeset patch # User drewp@bigasterisk.com # Date 1707968575 28800 # Node ID e1db51416e7315c54e677fbf1b9a8a4d52fb5a41 # Parent ccb6a2889e73d9996de053827c7d7b492176b9b5 cleanup some silenced errs and the new featurenode labels diff -r ccb6a2889e73 -r e1db51416e73 alert_rules.py --- a/alert_rules.py Wed Feb 14 19:11:13 2024 -0800 +++ b/alert_rules.py Wed Feb 14 19:42:55 2024 -0800 @@ -119,8 +119,6 @@ "interval": "1m", "rules": k8sRules(), }, - # - # any presence of starlette_request_duration_seconds_created{app_name="starlette",method="GET",path="/",status_code="200"} 1.6460176156784086e+09 means someone forgot to set app name { "name": "Outages", diff -r ccb6a2889e73 -r e1db51416e73 config/scrape_main.yaml --- a/config/scrape_main.yaml Wed Feb 14 19:11:13 2024 -0800 +++ b/config/scrape_main.yaml Wed Feb 14 19:42:55 2024 -0800 @@ -31,6 +31,8 @@ kubernetes_sd_configs: [{ role: node }] relabel_configs: + - action: labeldrop + regex: "__meta_kubernetes_node_label_(feature_node|nvidia_com_|beta_kubernetes_io_arch|beta_kubernetes_io_instance_type|beta_kubernetes_io_os|node_kubernetes_io_instance_type|kubernetes_io_os).*" - action: labelmap regex: __meta_kubernetes_node_label_(.+) @@ -45,8 +47,8 @@ kubernetes_sd_configs: [{ role: node }] relabel_configs: - - action: labelmap - regex: __meta_kubernetes_node_label_(.+) + - action: labeldrop + regex: "(feature_node|nvidia_com_gpu|beta_kubernetes_io_arch|beta_kubernetes_io_instance_type|beta_kubernetes_io_os|node_kubernetes_io_instance_type|kubernetes_io_os).*" - job_name: "k8services" kubernetes_sd_configs: [{ role: endpoints }] @@ -194,8 +196,8 @@ - job_name: "racc" scrape_interval: 30s static_configs: - - targets: - - dash:5150 - - dot:5150 - - plus:5150 - - Kelsis-iMac:5150 + - targets: [] + # - dash:5150 + # - dot:5150 + # - plus:5150 + # - Kelsis-iMac:5150