Merge pull request #193 from s-urbaniak/bump-kubernetes-mixin

jsonnet: bump kubernetes mixin

jsonnetfile.lock.json

@@ -27,7 +27,7 @@
                     "subdir": ""
                 }
             },
-            "version": "0afc72e70df6048c6b65fd3e4968e53b0812b30c"
+            "version": "24ea0d6e33a415e07ec7b675d74dea3cf01fde73"
         },
         {
             "name": "grafonnet",
@@ -98,6 +98,16 @@
                 }
             },
             "version": "154d59dee72b894f7245d8d78c9344d1211d521f"
+        },
+        {
+            "name": "promgrafonnet",
+            "source": {
+                "git": {
+                    "remote": "https://github.com/kubernetes-monitoring/kubernetes-mixin",
+                    "subdir": "lib/promgrafonnet"
+                }
+            },
+            "version": "24ea0d6e33a415e07ec7b675d74dea3cf01fde73"
         }
     ]
 }

manifests/grafana-deployment.yaml

@@ -48,12 +48,6 @@ spec:
         - mountPath: /grafana-dashboard-definitions/0/controller-manager
           name: grafana-dashboard-controller-manager
           readOnly: false
-        - mountPath: /grafana-dashboard-definitions/0/k8s-cluster-rsrc-use
-          name: grafana-dashboard-k8s-cluster-rsrc-use
-          readOnly: false
-        - mountPath: /grafana-dashboard-definitions/0/k8s-node-rsrc-use
-          name: grafana-dashboard-k8s-node-rsrc-use
-          readOnly: false
         - mountPath: /grafana-dashboard-definitions/0/k8s-resources-cluster
           name: grafana-dashboard-k8s-resources-cluster
           readOnly: false
@@ -123,12 +117,6 @@ spec:
       - configMap:
           name: grafana-dashboard-controller-manager
         name: grafana-dashboard-controller-manager
-      - configMap:
-          name: grafana-dashboard-k8s-cluster-rsrc-use
-        name: grafana-dashboard-k8s-cluster-rsrc-use
-      - configMap:
-          name: grafana-dashboard-k8s-node-rsrc-use
-        name: grafana-dashboard-k8s-node-rsrc-use
       - configMap:
           name: grafana-dashboard-k8s-resources-cluster
         name: grafana-dashboard-k8s-resources-cluster

manifests/prometheus-rules.yaml

@@ -82,13 +82,6 @@ spec:
     - expr: |
         sum(container_memory_usage_bytes{job="kubelet", image!="", container!="POD"}) by (namespace)
       record: namespace:container_memory_usage_bytes:sum
-    - expr: |
-        sum by (namespace, label_name) (
-            sum(container_memory_usage_bytes{job="kubelet",image!="", container!="POD"}) by (pod, namespace)
-          * on (namespace, pod)
-            group_left(label_name) kube_pod_labels{job="kube-state-metrics"}
-        )
-      record: namespace:container_memory_usage_bytes:sum
     - expr: |
         sum by (namespace, label_name) (
             sum(kube_pod_container_resource_requests_memory_bytes{job="kube-state-metrics"} * on (endpoint, instance, job, namespace, pod, service) group_left(phase) (kube_pod_status_phase{phase=~"^(Pending|Running)$"} == 1)) by (namespace, pod)
@@ -214,177 +207,9 @@ spec:
           node_namespace_pod:kube_pod_info:
         ))
       record: node:node_num_cpu:sum
-    - expr: |
-        1 - avg(rate(node_cpu_seconds_total{job="node-exporter",mode="idle"}[1m]))
-      record: :node_cpu_utilisation:avg1m
-    - expr: |
-        1 - avg by (node) (
-          rate(node_cpu_seconds_total{job="node-exporter",mode="idle"}[1m])
-        * on (namespace, pod) group_left(node)
-          node_namespace_pod:kube_pod_info:)
-      record: node:node_cpu_utilisation:avg1m
-    - expr: |
-        node:node_cpu_utilisation:avg1m
-          *
-        node:node_num_cpu:sum
-          /
-        scalar(sum(node:node_num_cpu:sum))
-      record: node:cluster_cpu_utilisation:ratio
-    - expr: |
-        sum(node_load1{job="node-exporter"})
-        /
-        sum(node:node_num_cpu:sum)
-      record: ':node_cpu_saturation_load1:'
-    - expr: |
-        sum by (node) (
-          node_load1{job="node-exporter"}
-        * on (namespace, pod) group_left(node)
-          node_namespace_pod:kube_pod_info:
-        )
-        /
-        node:node_num_cpu:sum
-      record: 'node:node_cpu_saturation_load1:'
-    - expr: |
-        1 -
-        sum(node_memory_MemFree_bytes{job="node-exporter"} + node_memory_Cached_bytes{job="node-exporter"} + node_memory_Buffers_bytes{job="node-exporter"})
-        /
-        sum(node_memory_MemTotal_bytes{job="node-exporter"})
-      record: ':node_memory_utilisation:'
     - expr: |
         sum(node_memory_MemFree_bytes{job="node-exporter"} + node_memory_Cached_bytes{job="node-exporter"} + node_memory_Buffers_bytes{job="node-exporter"})
       record: :node_memory_MemFreeCachedBuffers_bytes:sum
-    - expr: |
-        sum(node_memory_MemTotal_bytes{job="node-exporter"})
-      record: :node_memory_MemTotal_bytes:sum
-    - expr: |
-        sum by (node) (
-          (node_memory_MemFree_bytes{job="node-exporter"} + node_memory_Cached_bytes{job="node-exporter"} + node_memory_Buffers_bytes{job="node-exporter"})
-          * on (namespace, pod) group_left(node)
-            node_namespace_pod:kube_pod_info:
-        )
-      record: node:node_memory_bytes_available:sum
-    - expr: |
-        sum by (node) (
-          node_memory_MemTotal_bytes{job="node-exporter"}
-          * on (namespace, pod) group_left(node)
-            node_namespace_pod:kube_pod_info:
-        )
-      record: node:node_memory_bytes_total:sum
-    - expr: |
-        (node:node_memory_bytes_total:sum - node:node_memory_bytes_available:sum)
-        /
-        node:node_memory_bytes_total:sum
-      record: node:node_memory_utilisation:ratio
-    - expr: |
-        (node:node_memory_bytes_total:sum - node:node_memory_bytes_available:sum)
-        /
-        scalar(sum(node:node_memory_bytes_total:sum))
-      record: node:cluster_memory_utilisation:ratio
-    - expr: |
-        1e3 * sum(
-          (rate(node_vmstat_pgpgin{job="node-exporter"}[1m])
-         + rate(node_vmstat_pgpgout{job="node-exporter"}[1m]))
-        )
-      record: :node_memory_swap_io_bytes:sum_rate
-    - expr: |
-        1 -
-        sum by (node) (
-          (node_memory_MemFree_bytes{job="node-exporter"} + node_memory_Cached_bytes{job="node-exporter"} + node_memory_Buffers_bytes{job="node-exporter"})
-        * on (namespace, pod) group_left(node)
-          node_namespace_pod:kube_pod_info:
-        )
-        /
-        sum by (node) (
-          node_memory_MemTotal_bytes{job="node-exporter"}
-        * on (namespace, pod) group_left(node)
-          node_namespace_pod:kube_pod_info:
-        )
-      record: 'node:node_memory_utilisation:'
-    - expr: |
-        1 - (node:node_memory_bytes_available:sum / node:node_memory_bytes_total:sum)
-      record: 'node:node_memory_utilisation_2:'
-    - expr: |
-        1e3 * sum by (node) (
-          (rate(node_vmstat_pgpgin{job="node-exporter"}[1m])
-         + rate(node_vmstat_pgpgout{job="node-exporter"}[1m]))
-         * on (namespace, pod) group_left(node)
-           node_namespace_pod:kube_pod_info:
-        )
-      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.+|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.+|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.+|dm-.+"}[1m]))
-      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.+|dm-.+"}[1m])
-        * on (namespace, pod) group_left(node)
-          node_namespace_pod:kube_pod_info:
-        )
-      record: node:node_disk_saturation:avg_irate
-    - expr: |
-        max by (instance, namespace, pod, device) ((node_filesystem_size_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"}
-        - node_filesystem_avail_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"})
-        / node_filesystem_size_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"})
-      record: 'node:node_filesystem_usage:'
-    - expr: |
-        max by (instance, namespace, pod, device) (node_filesystem_avail_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"} / node_filesystem_size_bytes{fstype=~"ext[234]|btrfs|xfs|zfs"})
-      record: 'node:node_filesystem_avail:'
-    - expr: |
-        sum(irate(node_network_receive_bytes_total{job="node-exporter",device!~"veth.+"}[1m])) +
-        sum(irate(node_network_transmit_bytes_total{job="node-exporter",device!~"veth.+"}[1m]))
-      record: :node_net_utilisation:sum_irate
-    - expr: |
-        sum by (node) (
-          (irate(node_network_receive_bytes_total{job="node-exporter",device!~"veth.+"}[1m]) +
-          irate(node_network_transmit_bytes_total{job="node-exporter",device!~"veth.+"}[1m]))
-        * on (namespace, pod) group_left(node)
-          node_namespace_pod:kube_pod_info:
-        )
-      record: node:node_net_utilisation:sum_irate
-    - expr: |
-        sum(irate(node_network_receive_drop_total{job="node-exporter",device!~"veth.+"}[1m])) +
-        sum(irate(node_network_transmit_drop_total{job="node-exporter",device!~"veth.+"}[1m]))
-      record: :node_net_saturation:sum_irate
-    - expr: |
-        sum by (node) (
-          (irate(node_network_receive_drop_total{job="node-exporter",device!~"veth.+"}[1m]) +
-          irate(node_network_transmit_drop_total{job="node-exporter",device!~"veth.+"}[1m]))
-        * on (namespace, pod) group_left(node)
-          node_namespace_pod:kube_pod_info:
-        )
-      record: node:node_net_saturation:sum_irate
-    - expr: |
-        max(
-          max(
-            kube_pod_info{job="kube-state-metrics", host_ip!=""}
-          ) by (node, host_ip)
-          * on (host_ip) group_right (node)
-          label_replace(
-            (max(node_filesystem_files{job="node-exporter", mountpoint="/"}) by (instance)), "host_ip", "$1", "instance", "(.*):.*"
-          )
-        ) by (node)
-      record: 'node:node_inodes_total:'
-    - expr: |
-        max(
-          max(
-            kube_pod_info{job="kube-state-metrics", host_ip!=""}
-          ) by (node, host_ip)
-          * on (host_ip) group_right (node)
-          label_replace(
-            (max(node_filesystem_files_free{job="node-exporter", mountpoint="/"}) by (instance)), "host_ip", "$1", "instance", "(.*):.*"
-          )
-        ) by (node)
-      record: 'node:node_inodes_free:'
   - name: kube-prometheus-node-recording.rules
     rules:
     - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait"}[3m])) BY
@@ -663,17 +488,17 @@ spec:
         runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodcrashlooping
       expr: |
         rate(kube_pod_container_status_restarts_total{job="kube-state-metrics"}[15m]) * 60 * 5 > 0
-      for: 1h
+      for: 15m
       labels:
         severity: critical
     - alert: KubePodNotReady
       annotations:
         message: Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready
-          state for longer than an hour.
+          state for longer than 15 minutes.
         runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodnotready
       expr: |
         sum by (namespace, pod) (kube_pod_status_phase{job="kube-state-metrics", phase=~"Failed|Pending|Unknown"}) > 0
-      for: 1h
+      for: 15m
       labels:
         severity: critical
     - alert: KubeDeploymentGenerationMismatch
@@ -692,13 +517,13 @@ spec:
     - alert: KubeDeploymentReplicasMismatch
       annotations:
         message: Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has not
-          matched the expected number of replicas for longer than an hour.
+          matched the expected number of replicas for longer than 15 minutes.
         runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentreplicasmismatch
       expr: |
         kube_deployment_spec_replicas{job="kube-state-metrics"}
           !=
         kube_deployment_status_replicas_available{job="kube-state-metrics"}
-      for: 1h
+      for: 15m
       labels:
         severity: critical
     - alert: KubeStatefulSetReplicasMismatch
@@ -806,7 +631,7 @@ spec:
         runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobfailed
       expr: |
         kube_job_status_failed{job="kube-state-metrics"}  > 0
-      for: 1h
+      for: 15m
       labels:
         severity: warning
   - name: kubernetes-resources
@@ -940,7 +765,7 @@ spec:
         runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodenotready
       expr: |
         kube_node_status_condition{job="kube-state-metrics",condition="Ready",status="true"} == 0
-      for: 1h
+      for: 15m
       labels:
         severity: warning
     - alert: KubeVersionMismatch
@@ -950,7 +775,7 @@ spec:
         runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeversionmismatch
       expr: |
         count(count by (gitVersion) (label_replace(kubernetes_build_info{job!~"kube-dns|coredns"},"gitVersion","$1","gitVersion","(v[0-9]*.[0-9]*.[0-9]*).*"))) > 1
-      for: 1h
+      for: 15m
       labels:
         severity: warning
     - alert: KubeClientErrors