[UPGRADE] Metric monitoring components upgraded; dashboards migrated …

…to Grafana 11+ (#656)

CHANGELOG.md

@@ -1,5 +1,26 @@
 # SAS Viya Monitoring for Kubernetes
 
+## Unreleased
+* **Metrics**
+  * [CHANGE] Grafana dashboards for RabbitMQ upgraded to newer versions
+  * [CHANGE] All Grafana dashboards (maintained as part of this project) migrated to Grafana 11
+  * [CHANGE] Some Grafana dashboards inherited from the Kube-Prometheus Stack Helm chart do not
+work with Grafana 11.x due to Angular migration or other issues. As a **temporary** fix, we have
+removed these dashboards and replaced them with our versions of them.  **This fix will be removed when these issues have been resolved.**
+  * [UPGRADE] Kube-Prometheus Stack Helm chart has been upgraded from 56.6.2 to 61.1.1.
+  * [UPGRADE] Grafana Helm Chart (for OpenShift deployments) has been upgraded from 7.3.0 to 8.2.1.
+  * [UPGRADE] Prometheus Pushgateway Helm chart has been upgraded from 2.6.0 to 2.13.0.
+  * [UPGRADE] Alertmanager has been upgraded from 0.26.0 to 0.27.0.
+  * [UPGRADE] The config-reloader has been upgraded from 0.71.2 to 0.75.0.
+  * [UPGRADE] Grafana has been upgraded from 10.3.3 to 11.1.0.
+  * [UPGRADE] The k8s-sidecar has been upgraded from 1.25.4 to 1.26.1.
+  * [UPGRADE] Kube-State-Metrics has been upgraded from 2.10.1 to 2.12.0.
+  * [UPGRADE] Node-Exporter has been upgraded from 1.7.0 to 1.8.1.
+  * [UPGRADE] Prometheus has been upgraded from 2.49.1 to 2.53.0.
+  * [UPGRADE] Prometheus Operator has been upgraded from 0.71.2 to 0.75.0.
+  * [UPGRADE] Prometheus Pushgateway has been upgraded from 1.7.0 to 1.8.0.
+
+
 ## Version 1.2.26 (18JUN2024)
 * **Overall**
   * [CHANGE] Eliminated use of `--short` option (deprecated in Kubernetes 1.28) from `kubectl version` commands

component_versions.env

@@ -36,33 +36,33 @@ OSD_FULL_IMAGE="docker.io/opensearchproject/opensearch-dashboards:2.12.0"
 #Grafana (when deployed on OpenShift)
 OPENSHIFT_GRAFANA_CHART_REPO=grafana
 OPENSHIFT_GRAFANA_CHART_NAME=grafana
-OPENSHIFT_GRAFANA_CHART_VERSION=7.3.0
+OPENSHIFT_GRAFANA_CHART_VERSION=8.2.1
 OPENSHIFT_OAUTHPROXY_FULL_IMAGE="registry.redhat.io/openshift4/ose-oauth-proxy:latest"
 
 #Grafana (everywhere)
-GRAFANA_FULL_IMAGE="docker.io/grafana/grafana:10.3.3"
-GRAFANA_SIDECAR_FULL_IMAGE="quay.io/kiwigrid/k8s-sidecar:1.25.4"
+GRAFANA_FULL_IMAGE="docker.io/grafana/grafana:11.1.0"
+GRAFANA_SIDECAR_FULL_IMAGE="quay.io/kiwigrid/k8s-sidecar:1.26.1"
 
 #Kube-Prometheus Stack
 KUBE_PROM_STACK_CHART_REPO=prometheus-community
 KUBE_PROM_STACK_CHART_NAME=kube-prometheus-stack
-KUBE_PROM_STACK_CHART_VERSION=56.6.2
-ALERTMANAGER_FULL_IMAGE="quay.io/prometheus/alertmanager:v0.26.0"
+KUBE_PROM_STACK_CHART_VERSION=61.1.1
+ALERTMANAGER_FULL_IMAGE="quay.io/prometheus/alertmanager:v0.27.0"
 ADMWEBHOOK_FULL_IMAGE="registry.k8s.io/ingress-nginx/kube-webhook-certgen:v20221220-controller-v1.5.1-58-g787ea74b6"
-KSM_FULL_IMAGE="registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.10.1"
-NODEXPORT_FULL_IMAGE="quay.io/prometheus/node-exporter:v1.7.0"
-PROMETHEUS_FULL_IMAGE="quay.io/prometheus/prometheus:v2.49.1"
-PROMOP_FULL_IMAGE="quay.io/prometheus-operator/prometheus-operator:v0.71.2"
-CONFIGRELOAD_FULL_IMAGE="quay.io/prometheus-operator/prometheus-config-reloader:v0.71.2" 
+KSM_FULL_IMAGE="registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.12.0"
+NODEXPORT_FULL_IMAGE="quay.io/prometheus/node-exporter:v1.8.1"
+PROMETHEUS_FULL_IMAGE="quay.io/prometheus/prometheus:v2.53.0"
+PROMOP_FULL_IMAGE="quay.io/prometheus-operator/prometheus-operator:v0.75.0"
+CONFIGRELOAD_FULL_IMAGE="quay.io/prometheus-operator/prometheus-config-reloader:v0.75.0" 
 
 #Pushgateway
 PUSHGATEWAY_CHART_REPO=prometheus-community
 PUSHGATEWAY_CHART_NAME=prometheus-pushgateway
-PUSHGATEWAY_CHART_VERSION=2.6.0
-PUSHGATEWAY_FULL_IMAGE="quay.io/prometheus/pushgateway:v1.7.0"
+PUSHGATEWAY_CHART_VERSION=2.13.0
+PUSHGATEWAY_FULL_IMAGE="quay.io/prometheus/pushgateway:v1.8.0"
 
 #Prometheus Operator CRD
-PROM_OPERATOR_CRD_VERSION=v0.71.2
+PROM_OPERATOR_CRD_VERSION=v0.75.0
 
 #Tempo
 TEMPO_CHART_REPO=grafana

monitoring/bin/deploy_monitoring_cluster.sh

@@ -324,6 +324,27 @@ fi
 echo ""
 monitoring/bin/deploy_dashboards.sh
 
+# 01JUL24 Temporary Fix
+# Some Grafana dashboards inherited from the Kube-Prometheus Stack Helm
+# chart do not work with Grafana 11 due to Angular migration or other
+# issues.  As a **temporary** fix, we will remove these dashboards and
+# replace them with our versions of them.  This fix will be removed
+# when these issues have been resolved.
+V4M_TEMP_REPLACE_PROBLEMATIC_MIXIN_DASHBOARDS="${V4M_TEMP_REPLACE_PROBLEMATIC_MIXIN_DASHBOARDS:-true}"
+if [ "$V4M_TEMP_REPLACE_PROBLEMATIC_MIXIN_DASHBOARDS" == "true" ]; then
+   log_info "Replacing some Kube-Prometheus Stack-supplied Grafana dashboards with our own versions due to incompatabilities."
+
+   # remove configMaps definining exising Grafana dashboards
+   kubectl -n $MON_NS delete configmap  v4m-cluster-total         --ignore-not-found
+   kubectl -n $MON_NS delete configmap  v4m-namespace-by-pod      --ignore-not-found
+   kubectl -n $MON_NS delete configmap  v4m-namespace-by-workload --ignore-not-found
+   kubectl -n $MON_NS delete configmap  v4m-prometheus            --ignore-not-found
+
+   # deploy our versions of these dashboards
+   monitoring/bin/deploy_dashboards.sh monitoring/dashboards/mixinfixes
+
+fi
+
 set +e
 # call function to get HTTP/HTTPS ports from ingress controller
 get_ingress_ports