Updated libraries

manifests/prometheus-adapter-configMap.yaml

@@ -4,7 +4,7 @@ data:
     resourceRules:
       cpu:
         containerQuery: sum(rate(container_cpu_usage_seconds_total{<<.LabelMatchers>>}[1m])) by (<<.GroupBy>>)
-        nodeQuery: sum(rate(container_cpu_usage_seconds_total{<<.LabelMatchers>>, id='/'}[1m])) by (<<.GroupBy>>)
+        nodeQuery: sum(1 - rate(node_cpu_seconds_total{mode="idle"}[1m]) * on(namespace, pod) group_left(node) node_namespace_pod:kube_pod_info:{<<.LabelMatchers>>}) by (<<.GroupBy>>)
         resources:
           overrides:
             node:
@@ -16,7 +16,7 @@ data:
         containerLabel: container_name
       memory:
         containerQuery: sum(container_memory_working_set_bytes{<<.LabelMatchers>>}) by (<<.GroupBy>>)
-        nodeQuery: sum(container_memory_working_set_bytes{<<.LabelMatchers>>,id='/'}) by (<<.GroupBy>>)
+        nodeQuery: sum(node:node_memory_bytes_total:sum{<<.LabelMatchers>>} - node:node_memory_bytes_available:sum{<<.LabelMatchers>>}) by (<<.GroupBy>>)
         resources:
           overrides:
             node:

manifests/prometheus-rules.yaml

@@ -225,21 +225,21 @@ spec:
         )
       record: node:node_memory_swap_io_bytes:sum_rate
     - expr: |
-        avg(irate(node_disk_io_time_seconds_total{job="node-exporter",device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+"}[1m]))
+        avg(irate(node_disk_io_time_seconds_total{job="node-exporter",device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+"}[1m]))
       record: :node_disk_utilisation:avg_irate
     - expr: |
         avg by (node) (
-          irate(node_disk_io_time_seconds_total{job="node-exporter",device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+"}[1m])
+          irate(node_disk_io_time_seconds_total{job="node-exporter",device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+"}[1m])
         * on (namespace, pod) group_left(node)
           node_namespace_pod:kube_pod_info:
         )
       record: node:node_disk_utilisation:avg_irate
     - expr: |
-        avg(irate(node_disk_io_time_weighted_seconds_total{job="node-exporter",device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+"}[1m]) / 1e3)
+        avg(irate(node_disk_io_time_weighted_seconds_total{job="node-exporter",device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+"}[1m]) / 1e3)
       record: :node_disk_saturation:avg_irate
     - expr: |
         avg by (node) (
-          irate(node_disk_io_time_weighted_seconds_total{job="node-exporter",device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+"}[1m]) / 1e3
+          irate(node_disk_io_time_weighted_seconds_total{job="node-exporter",device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+"}[1m]) / 1e3
         * on (namespace, pod) group_left(node)
           node_namespace_pod:kube_pod_info:
         )
@@ -795,9 +795,9 @@ spec:
         message: API server is returning errors for {{ $value }}% of requests.
         runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh
       expr: |
-        sum(rate(apiserver_request_count{job="apiserver",code=~"^(?:5..)$"}[5m])) without(instance, pod)
+        sum(rate(apiserver_request_count{job="apiserver",code=~"^(?:5..)$"}[5m]))
           /
-        sum(rate(apiserver_request_count{job="apiserver"}[5m])) without(instance, pod) * 100 > 10
+        sum(rate(apiserver_request_count{job="apiserver"}[5m])) * 100 > 3
       for: 10m
       labels:
         severity: critical
@@ -806,9 +806,33 @@ spec:
         message: API server is returning errors for {{ $value }}% of requests.
         runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh
       expr: |
-        sum(rate(apiserver_request_count{job="apiserver",code=~"^(?:5..)$"}[5m])) without(instance, pod)
+        sum(rate(apiserver_request_count{job="apiserver",code=~"^(?:5..)$"}[5m]))
           /
-        sum(rate(apiserver_request_count{job="apiserver"}[5m])) without(instance, pod) * 100 > 5
+        sum(rate(apiserver_request_count{job="apiserver"}[5m])) * 100 > 1
+      for: 10m
+      labels:
+        severity: warning
+    - alert: KubeAPIErrorsHigh
+      annotations:
+        message: API server is returning errors for {{ $value }}% of requests for
+          {{ $labels.verb }} {{ $labels.resource }} {{ $labels.subresource }}.
+        runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh
+      expr: |
+        sum(rate(apiserver_request_count{job="apiserver",code=~"^(?:5..)$"}[5m])) by (resource,subresource,verb)
+          /
+        sum(rate(apiserver_request_count{job="apiserver"}[5m])) by (resource,subresource,verb) * 100 > 10
+      for: 10m
+      labels:
+        severity: critical
+    - alert: KubeAPIErrorsHigh
+      annotations:
+        message: API server is returning errors for {{ $value }}% of requests for
+          {{ $labels.verb }} {{ $labels.resource }} {{ $labels.subresource }}.
+        runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh
+      expr: |
+        sum(rate(apiserver_request_count{job="apiserver",code=~"^(?:5..)$"}[5m])) by (resource,subresource,verb)
+          /
+        sum(rate(apiserver_request_count{job="apiserver"}[5m])) by (resource,subresource,verb) * 100 > 5
       for: 10m
       labels:
         severity: warning
@@ -977,7 +1001,7 @@ spec:
           log (WAL).'
         summary: Prometheus write-ahead log is corrupted
       expr: |
-        tsdb_wal_corruptions_total{job="prometheus-k8s",namespace="monitoring"} > 0
+        prometheus_tsdb_wal_corruptions_total{job="prometheus-k8s",namespace="monitoring"} > 0
       for: 4h
       labels:
         severity: warning