From b7cb059bbf9b1d5bb0cbc30c348ee5b0891c1114 Mon Sep 17 00:00:00 2001 From: gsmith-sas <65406958+gsmith-sas@users.noreply.github.com> Date: Tue, 22 Jul 2025 18:04:47 -0400 Subject: [PATCH 1/4] Upgrade metric monitoring stack --- CHANGELOG.md | 16 ++++++++++++++++ component_versions.env | 20 ++++++++++---------- 2 files changed, 26 insertions(+), 10 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 9a4c2873..9b68ddfc 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,19 @@ # SAS Viya Monitoring for Kubernetes +## unreleased +* **Metrics** + * [UPGRADE] Kube-Prometheus Stack Helm chart has been upgraded from 70.8.0 to 75.12.0. + * [UPGRADE] Grafana Helm Chart (for OpenShift deployments) has been upgraded fom 8.13.1 to 9.2.10. + * [UPGRADE] Prometheus Pushgateway Helm chart has been upgraded from 3.1.0 to 3.4.0. + * [UPGRADE] The config-reloader has been upgraded from 0.81.0 to 0.83.0. + * [UPGRADE] Grafana has been upgraded from 11.6.1 to 12.0.2. + * [UPGRADE] The k8s-sidecar has been upgraded from 1.30.0 to 1.30.3. + * [UPGRADE] Kube-State-Metrics has been upgraded from 2.15.0 to 2.16.0. + * [UPGRADE] Prometheus has been upgraded from 3.2.1 to 3.5.0. + * [UPGRADE] Prometheus Operator has been upgraded from 0.81.0 to 0.83.0. + * [UPGRADE] OpenSearch Data Source Plugin to Grafana upgraded from 2.26.1 to 2.28.0 + + ## Version 1.2.40 (15JULY2025) * **Overall** * [REMOVAL] Removed the previously deprecated TLS sample. Deploying with TLS enabled has been the default since version @@ -10,6 +24,7 @@ * **Metrics** * [FIX] Resolved an issue where some Grafana dashboards failed to load due to hardcoded Prometheus datasource references. In the previous release, the Prometheus datasource UID was standardized to `prometheus` to support the Grafana alerting system and provisioned alerts. However, some dashboards still contained hardcoded UIDs pointing to the old datasource configuration. This fix updates those references to use the correct UID, ensuring all dashboards now load and function as expected. + ## Version 1.2.38 (17JUN2025) * **Logging** * [ANNOUNCEMENT] The [OpenDistro for Elasticsearch (ODFE) project](https://opendistro.github.io/for-elasticsearch/) reached end-of-line in May of 2022 and our project moved to @@ -33,6 +48,7 @@ SAS Viya Workload node placement strategy. * **Metrics** * [FEATURE] A set of SAS Viya specific alerts is now deployed with Grafana. Administrators can configure notifiers (which trigger messages via e-mail, Slack, SMS, etc. based on these alerts) and additional alerts via the Grafana web application after deployment. Or, alternatively, notifiers and/or additional alerts can be defined prior to running the monitoring deployment script ( `deploy_monitoring_cluster.sh` ) by placing yaml files in `$USER_DIR/monitoring/alerting/` Note: Due to Grafana's use of a single folder namespace, the folders used to organize these new Alerts will also appear when viewing Dashboards and will appear to be empty. When working with Dashboards, these folders can be ignored. + ## Version 1.2.37 (13MAY2025) * **Metrics** * [UPGRADE] Kube-Prometheus Stack Helm chart has been upgraded from 68.3.0 to 70.8.0. diff --git a/component_versions.env b/component_versions.env index 144b583c..7d2646dd 100644 --- a/component_versions.env +++ b/component_versions.env @@ -37,30 +37,30 @@ OSD_FULL_IMAGE="docker.io/opensearchproject/opensearch-dashboards:2.19.2" #Grafana (when deployed on OpenShift) OPENSHIFT_GRAFANA_CHART_REPO=grafana OPENSHIFT_GRAFANA_CHART_NAME=grafana -OPENSHIFT_GRAFANA_CHART_VERSION=8.13.1 +OPENSHIFT_GRAFANA_CHART_VERSION=9.2.10 OPENSHIFT_OAUTHPROXY_FULL_IMAGE="registry.redhat.io/openshift4/ose-oauth-proxy:latest" #Grafana (everywhere) -GRAFANA_FULL_IMAGE="docker.io/grafana/grafana:11.6.1" -GRAFANA_SIDECAR_FULL_IMAGE="quay.io/kiwigrid/k8s-sidecar:1.30.0" -GRAFANA_DATASOURCE_PLUGIN_VERSION="2.26.1" +GRAFANA_FULL_IMAGE="docker.io/grafana/grafana:12.0.2" +GRAFANA_SIDECAR_FULL_IMAGE="quay.io/kiwigrid/k8s-sidecar:1.30.3" +GRAFANA_DATASOURCE_PLUGIN_VERSION="2.28.0" #Kube-Prometheus Stack KUBE_PROM_STACK_CHART_REPO=prometheus-community KUBE_PROM_STACK_CHART_NAME=kube-prometheus-stack -KUBE_PROM_STACK_CHART_VERSION=70.8.0 +KUBE_PROM_STACK_CHART_VERSION=75.12.0 ALERTMANAGER_FULL_IMAGE="quay.io/prometheus/alertmanager:v0.28.1" ADMWEBHOOK_FULL_IMAGE="registry.k8s.io/ingress-nginx/kube-webhook-certgen:v1.5.2" -KSM_FULL_IMAGE="registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.15.0" +KSM_FULL_IMAGE="registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.16.0" NODEXPORT_FULL_IMAGE="quay.io/prometheus/node-exporter:v1.9.1" -PROMETHEUS_FULL_IMAGE="quay.io/prometheus/prometheus:v3.2.1" -PROMOP_FULL_IMAGE="quay.io/prometheus-operator/prometheus-operator:v0.81.0" -CONFIGRELOAD_FULL_IMAGE="quay.io/prometheus-operator/prometheus-config-reloader:v0.81.0" +PROMETHEUS_FULL_IMAGE="quay.io/prometheus/prometheus:v3.5.0" +PROMOP_FULL_IMAGE="quay.io/prometheus-operator/prometheus-operator:v0.83.0" +CONFIGRELOAD_FULL_IMAGE="quay.io/prometheus-operator/prometheus-config-reloader:v0.83.0" #Pushgateway PUSHGATEWAY_CHART_REPO=prometheus-community PUSHGATEWAY_CHART_NAME=prometheus-pushgateway -PUSHGATEWAY_CHART_VERSION=3.1.0 +PUSHGATEWAY_CHART_VERSION=3.4.0 PUSHGATEWAY_FULL_IMAGE="quay.io/prometheus/pushgateway:v1.11.1" #Prometheus Operator CRD From 2278182c4059b822f5a56c90eb9cd5759819a72a Mon Sep 17 00:00:00 2001 From: gsmith-sas <65406958+gsmith-sas@users.noreply.github.com> Date: Fri, 25 Jul 2025 13:58:40 -0400 Subject: [PATCH 2/4] Revised versions to latest --- CHANGELOG.md | 8 ++++---- component_versions.env | 6 +++--- 2 files changed, 7 insertions(+), 7 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 9b68ddfc..5c3bb781 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -2,11 +2,11 @@ ## unreleased * **Metrics** - * [UPGRADE] Kube-Prometheus Stack Helm chart has been upgraded from 70.8.0 to 75.12.0. - * [UPGRADE] Grafana Helm Chart (for OpenShift deployments) has been upgraded fom 8.13.1 to 9.2.10. - * [UPGRADE] Prometheus Pushgateway Helm chart has been upgraded from 3.1.0 to 3.4.0. + * [UPGRADE] Kube-Prometheus Stack Helm chart has been upgraded from 70.8.0 to 75.15.0. + * [UPGRADE] Grafana Helm Chart (for OpenShift deployments) has been upgraded fom 8.13.1 to 9.3.0. + * [UPGRADE] Prometheus Pushgateway Helm chart has been upgraded from 3.1.0 to 3.4.1. * [UPGRADE] The config-reloader has been upgraded from 0.81.0 to 0.83.0. - * [UPGRADE] Grafana has been upgraded from 11.6.1 to 12.0.2. + * [UPGRADE] Grafana has been upgraded from 11.6.1 to 12.1.0. * [UPGRADE] The k8s-sidecar has been upgraded from 1.30.0 to 1.30.3. * [UPGRADE] Kube-State-Metrics has been upgraded from 2.15.0 to 2.16.0. * [UPGRADE] Prometheus has been upgraded from 3.2.1 to 3.5.0. diff --git a/component_versions.env b/component_versions.env index 7d2646dd..37d0fca6 100644 --- a/component_versions.env +++ b/component_versions.env @@ -37,18 +37,18 @@ OSD_FULL_IMAGE="docker.io/opensearchproject/opensearch-dashboards:2.19.2" #Grafana (when deployed on OpenShift) OPENSHIFT_GRAFANA_CHART_REPO=grafana OPENSHIFT_GRAFANA_CHART_NAME=grafana -OPENSHIFT_GRAFANA_CHART_VERSION=9.2.10 +OPENSHIFT_GRAFANA_CHART_VERSION=9.3.0 OPENSHIFT_OAUTHPROXY_FULL_IMAGE="registry.redhat.io/openshift4/ose-oauth-proxy:latest" #Grafana (everywhere) -GRAFANA_FULL_IMAGE="docker.io/grafana/grafana:12.0.2" +GRAFANA_FULL_IMAGE="docker.io/grafana/grafana:12.1.0" GRAFANA_SIDECAR_FULL_IMAGE="quay.io/kiwigrid/k8s-sidecar:1.30.3" GRAFANA_DATASOURCE_PLUGIN_VERSION="2.28.0" #Kube-Prometheus Stack KUBE_PROM_STACK_CHART_REPO=prometheus-community KUBE_PROM_STACK_CHART_NAME=kube-prometheus-stack -KUBE_PROM_STACK_CHART_VERSION=75.12.0 +KUBE_PROM_STACK_CHART_VERSION=75.15.0 ALERTMANAGER_FULL_IMAGE="quay.io/prometheus/alertmanager:v0.28.1" ADMWEBHOOK_FULL_IMAGE="registry.k8s.io/ingress-nginx/kube-webhook-certgen:v1.5.2" KSM_FULL_IMAGE="registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.16.0" From bbcc02e0aa1cb05dca515b906351c1c2fe656c3a Mon Sep 17 00:00:00 2001 From: gsmith-sas <65406958+gsmith-sas@users.noreply.github.com> Date: Fri, 25 Jul 2025 16:03:36 -0400 Subject: [PATCH 3/4] Bump version for admission webhook --- component_versions.env | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/component_versions.env b/component_versions.env index 37d0fca6..e49f985c 100644 --- a/component_versions.env +++ b/component_versions.env @@ -50,7 +50,7 @@ KUBE_PROM_STACK_CHART_REPO=prometheus-community KUBE_PROM_STACK_CHART_NAME=kube-prometheus-stack KUBE_PROM_STACK_CHART_VERSION=75.15.0 ALERTMANAGER_FULL_IMAGE="quay.io/prometheus/alertmanager:v0.28.1" -ADMWEBHOOK_FULL_IMAGE="registry.k8s.io/ingress-nginx/kube-webhook-certgen:v1.5.2" +ADMWEBHOOK_FULL_IMAGE="registry.k8s.io/ingress-nginx/kube-webhook-certgen:v1.6.0" KSM_FULL_IMAGE="registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.16.0" NODEXPORT_FULL_IMAGE="quay.io/prometheus/node-exporter:v1.9.1" PROMETHEUS_FULL_IMAGE="quay.io/prometheus/prometheus:v3.5.0" From f141f81afe28dc614a3e6897eca76f88fbfdab16 Mon Sep 17 00:00:00 2001 From: gsmith-sas <65406958+gsmith-sas@users.noreply.github.com> Date: Mon, 4 Aug 2025 10:54:36 -0400 Subject: [PATCH 4/4] Update CHANGELOG.md to match tested components --- CHANGELOG.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 5c3bb781..e7094a8f 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -4,7 +4,7 @@ * **Metrics** * [UPGRADE] Kube-Prometheus Stack Helm chart has been upgraded from 70.8.0 to 75.15.0. * [UPGRADE] Grafana Helm Chart (for OpenShift deployments) has been upgraded fom 8.13.1 to 9.3.0. - * [UPGRADE] Prometheus Pushgateway Helm chart has been upgraded from 3.1.0 to 3.4.1. + * [UPGRADE] Prometheus Pushgateway Helm chart has been upgraded from 3.1.0 to 3.4.0. * [UPGRADE] The config-reloader has been upgraded from 0.81.0 to 0.83.0. * [UPGRADE] Grafana has been upgraded from 11.6.1 to 12.1.0. * [UPGRADE] The k8s-sidecar has been upgraded from 1.30.0 to 1.30.3.