diff --git a/jsonnetfile.lock.json b/jsonnetfile.lock.json index 6fa938e1454433d9e715f4c662fc8b0ed8c398c6..dc43f6cf655719469cb2d9b26572fdfbf1253b8e 100644 --- a/jsonnetfile.lock.json +++ b/jsonnetfile.lock.json @@ -119,8 +119,8 @@ "subdir": "docs/node-mixin" } }, - "version": "a3aaf63bb1262aada3cd9ca1fe59ffc3ea32e9e2", - "sum": "zpo4/qvCbAmfJXGjwrdzXcfsvg4fxZD6wi5af/kt+8g=" + "version": "9c9c63630572ac706dcd0bd0e79dc03179f6d02c", + "sum": "GE8EJdQvnaaj31avW1OaJGY6xP+Vd6MqMu7/GgudRDQ=" }, { "source": { diff --git a/manifests/prometheus-rules.yaml b/manifests/prometheus-rules.yaml index 31ba10b0ea3dc6d9d8525b3f7ca38e4685452040..beb31ba0a4afdbfb7eb40b06e47845bcb4a4a1c7 100644 --- a/manifests/prometheus-rules.yaml +++ b/manifests/prometheus-rules.yaml @@ -936,7 +936,7 @@ spec: runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodenetworkreceiveerrs summary: Network interface is reporting many receive errors. expr: | - increase(node_network_receive_errs_total[2m]) > 10 + rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01 for: 1h labels: severity: warning @@ -946,7 +946,7 @@ spec: runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodenetworktransmiterrs summary: Network interface is reporting many transmit errors. expr: | - increase(node_network_transmit_errs_total[2m]) > 10 + rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01 for: 1h labels: severity: warning @@ -995,6 +995,8 @@ spec: summary: Clock not synchronising. expr: | min_over_time(node_timex_sync_status[5m]) == 0 + and + node_timex_maxerror_seconds >= 16 for: 10m labels: severity: warning