Merge pull request #2649 from simonpasquier/bump-jsonnet-deps

NO-JIRA: chore: bump jsonnet dependencies

Author: openshift-merge-bot[bot]

assets/control-plane/minimal-service-monitor-kubelet.yaml

@@ -2,6 +2,7 @@ apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   labels:
+    app.kubernetes.io/component: kubernetes
     app.kubernetes.io/managed-by: cluster-monitoring-operator
     app.kubernetes.io/name: kubelet
     app.kubernetes.io/part-of: openshift-monitoring

assets/control-plane/prometheus-rule.yaml

@@ -2,6 +2,7 @@ apiVersion: monitoring.coreos.com/v1
 kind: PrometheusRule
 metadata:
   labels:
+    app.kubernetes.io/component: kubernetes
     app.kubernetes.io/managed-by: cluster-monitoring-operator
     app.kubernetes.io/name: kube-prometheus
     app.kubernetes.io/part-of: openshift-monitoring
@@ -243,20 +244,33 @@ spec:
     rules:
     - alert: KubeCPUOvercommit
       annotations:
-        description: Cluster has overcommitted CPU resource requests for Pods by {{ $value }} CPU shares and cannot tolerate node failure.
+        description: Cluster has overcommitted CPU resource requests for Pods by {{ printf "%.2f" $value }} CPU shares and cannot tolerate node failure.
         summary: Cluster has overcommitted CPU resource requests.
       expr: |
-        (sum(namespace_cpu:kube_pod_container_resource_requests:sum{}) -
-        sum(kube_node_status_allocatable{resource="cpu", job="kube-state-metrics"}) > 0
-        and
-        count(max by (node) (kube_node_role{job="kube-state-metrics", role="control-plane"})) < 3)
+        # Non-HA clusters.
+        (
+          (
+            sum(namespace_cpu:kube_pod_container_resource_requests:sum{})
+            -
+            sum(kube_node_status_allocatable{resource="cpu", job="kube-state-metrics"}) > 0
+          )
+          and
+          count(max by (node) (kube_node_role{job="kube-state-metrics", role="control-plane"})) < 3
+        )
         or
-        (sum(namespace_cpu:kube_pod_container_resource_requests:sum{}) -
-        (sum(kube_node_status_allocatable{resource="cpu", job="kube-state-metrics"}) -
-        max(kube_node_status_allocatable{resource="cpu", job="kube-state-metrics"})) > 0
-        and
-        (sum(kube_node_status_allocatable{resource="cpu", job="kube-state-metrics"}) -
-        max(kube_node_status_allocatable{resource="cpu", job="kube-state-metrics"})) > 0)
+        # HA clusters.
+        (
+          sum(namespace_cpu:kube_pod_container_resource_requests:sum{})
+          -
+          (
+            # Skip clusters with only one allocatable node.
+            (
+              sum(kube_node_status_allocatable{resource="cpu", job="kube-state-metrics"})
+              -
+              max(kube_node_status_allocatable{resource="cpu", job="kube-state-metrics"})
+            ) > 0
+          ) > 0
+        )
       for: 10m
       labels:
         namespace: kube-system
@@ -266,17 +280,30 @@ spec:
         description: Cluster has overcommitted memory resource requests for Pods by {{ $value | humanize }} bytes and cannot tolerate node failure.
         summary: Cluster has overcommitted memory resource requests.
       expr: |
-        (sum(namespace_memory:kube_pod_container_resource_requests:sum{}) -
-        sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) > 0
-        and
-        count(max by (node) (kube_node_role{job="kube-state-metrics", role="control-plane"})) < 3)
+        # Non-HA clusters.
+        (
+          (
+            sum(namespace_memory:kube_pod_container_resource_requests:sum{})
+            -
+            sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) > 0
+          )
+          and
+          count(max by (node) (kube_node_role{job="kube-state-metrics", role="control-plane"})) < 3
+        )
         or
-        (sum(namespace_memory:kube_pod_container_resource_requests:sum{}) -
-        (sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) -
-        max(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"})) > 0
-        and
-        (sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) -
-        max(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"})) > 0)
+        # HA clusters.
+        (
+          sum(namespace_memory:kube_pod_container_resource_requests:sum{})
+          -
+          (
+            # Skip clusters with only one allocatable node.
+            (
+              sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"})
+              -
+              max(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"})
+            ) > 0
+          ) > 0
+        )
       for: 10m
       labels:
         namespace: kube-system
@@ -468,7 +495,18 @@ spec:
         description: Kubelet Pod startup 99th percentile latency is {{ $value }} seconds on node {{ $labels.node }}.
         summary: Kubelet Pod startup latency is too high.
       expr: |
-        histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le)) * on(cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"} > 60
+        histogram_quantile(0.99,
+          sum by (cluster, instance, le) (
+            topk by (cluster, instance, le, operation_type) (1,
+              rate(kubelet_pod_worker_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])
+            )
+          )
+        )
+        * on(cluster, instance) group_left(node)
+        topk by (cluster, instance, node) (1,
+          kubelet_node_name{job="kubelet", metrics_path="/metrics"}
+        )
+        > 60
       for: 15m
       labels:
         namespace: kube-system

assets/control-plane/service-monitor-kubelet.yaml

@@ -2,6 +2,7 @@ apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   labels:
+    app.kubernetes.io/component: kubernetes
     app.kubernetes.io/managed-by: cluster-monitoring-operator
     app.kubernetes.io/name: kubelet
     app.kubernetes.io/part-of: openshift-monitoring

assets/node-exporter/daemonset.yaml

@@ -32,9 +32,10 @@ spec:
       automountServiceAccountToken: true
       containers:
       - args:
-        - --web.listen-address=127.0.0.1:9100
+        - --web.listen-address=127.0.0.1:9101
         - --path.sysfs=/host/sys
         - --path.rootfs=/host/root
+        - --path.procfs=/host/root/proc
         - --path.udev.data=/host/root/run/udev/data
         - --no-collector.wifi
         - --collector.filesystem.mount-points-exclude=^/(dev|proc|sys|run/k3s/containerd/.+|var/lib/docker/.+|var/lib/kubelet/pods/.+)($|/)
@@ -86,7 +87,7 @@ spec:
       - args:
         - --secure-listen-address=[$(IP)]:9100
         - --tls-cipher-suites=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305,TLS_ECDHE_ECDSA_WITH_CHACHA20_POLY1305
-        - --upstream=http://127.0.0.1:9100/
+        - --upstream=http://127.0.0.1:9101/
         - --tls-cert-file=/etc/tls/private/tls.crt
         - --tls-private-key-file=/etc/tls/private/tls.key
         - --client-ca-file=/etc/tls/client/client-ca.crt

assets/node-exporter/prometheus-rule.yaml

@@ -155,7 +155,7 @@ spec:
         severity: warning
     - alert: NodeHighNumberConntrackEntriesUsed
       annotations:
-        description: '{{ $value | humanizePercentage }} of conntrack entries are used.'
+        description: '{{ $labels.instance }} {{ $value | humanizePercentage }} of conntrack entries are used.'
         summary: Number of conntrack are getting close to the limit.
       expr: |
         (node_nf_conntrack_entries{job="node-exporter"} / node_nf_conntrack_entries_limit) > 0.75

hack/build-jsonnet.sh

@@ -43,11 +43,6 @@ done
 wait
 
 
-# shellcheck disable=SC1003
-# Produce dashboard definitions in format understandable by CVO (it doesn't accept ConfigMapList)
-grep -E -v '^apiVersion: v1|^items:|^kind: ConfigMapList' "${prefix}/dashboards/console-dashboard-definitions.yaml" | sed 's/^\ \ //g;s/- apiVersion: v1/---\'$'\n''apiVersion: v1/g' > "manifests/0000_90_cluster-monitoring-operator_01-dashboards.yaml"
-rm -rf "${prefix}/dashboards"
-
 grep -H 'kind: CustomResourceDefinition' assets/{cluster-monitoring,prometheus}-operator/* | cut -d: -f1 | while IFS= read -r f; do
   mv "$f" "manifests/0000_50_cluster-monitoring-operator_00_$(basename "$f")"
 done