From be4fa93e8eae69f009ac8e0621bc0e54544b5f31 Mon Sep 17 00:00:00 2001
From: Yuriy Bezsonov <bezsonov@amazon.de>
Date: Fri, 3 Jul 2026 17:07:16 +0200
Subject: [PATCH 1/2] fix(monitoring): Migrate Grafana Helm chart to
 grafana-community repo

The grafana chart in grafana.github.io/helm-charts is now deprecated
(frozen at chart 10.5.15 / Grafana 12.3.1, marked deprecated: true) after
Grafana Labs forked the charts to grafana-community/helm-charts on
March 16, 2026. Installs emit "WARNING: This chart is deprecated".

Point the grafana chart at the maintained community repo
(grafana-community/grafana, chart 12.7.2 / Grafana 13.1.0) in both
monitoring.sh and perf-platform.sh. All values keys used by the scripts
(admin, service, persistence, resources, sidecar, plugins, grafana.ini)
remain valid in the new chart.

The pyroscope chart was not moved, so perf-platform.sh keeps the original
grafana repo alongside the new grafana-community repo for grafana/pyroscope.
---
 infra/scripts/setup/monitoring.sh    | 4 ++--
 infra/scripts/setup/perf-platform.sh | 3 ++-
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/infra/scripts/setup/monitoring.sh b/infra/scripts/setup/monitoring.sh
index 9274bc9e..d018da78 100755
--- a/infra/scripts/setup/monitoring.sh
+++ b/infra/scripts/setup/monitoring.sh
@@ -44,7 +44,7 @@ trap cleanup EXIT
 # Setup
 kubectl create namespace "$NAMESPACE" 2>/dev/null || true
 helm repo add prometheus-community https://prometheus-community.github.io/helm-charts || true
-helm repo add grafana https://grafana.github.io/helm-charts || true
+helm repo add grafana-community https://grafana-community.github.io/helm-charts || true
 helm repo update
 
 # Grafana secret
@@ -152,7 +152,7 @@ grafana.ini:
 EOF
 
 log_info "Deploying Grafana..."
-helm upgrade --install grafana grafana/grafana \
+helm upgrade --install grafana grafana-community/grafana \
   --namespace "$NAMESPACE" \
   --values "$GRAFANA_VALUES_FILE"
 
diff --git a/infra/scripts/setup/perf-platform.sh b/infra/scripts/setup/perf-platform.sh
index 5c9c98ba..6152ff17 100755
--- a/infra/scripts/setup/perf-platform.sh
+++ b/infra/scripts/setup/perf-platform.sh
@@ -41,6 +41,7 @@ kubectl get namespace "${NAMESPACE}" >/dev/null 2>&1 || {
 }
 
 helm repo add grafana https://grafana.github.io/helm-charts >/dev/null 2>&1 || true
+helm repo add grafana-community https://grafana-community.github.io/helm-charts >/dev/null 2>&1 || true
 helm repo update >/dev/null
 
 CLUSTER_NAME="${PREFIX}-eks"
@@ -288,7 +289,7 @@ GRAFANA_URL="http://${GRAFANA_LB}"
 
 # Install Profiles Drilldown plugin (idempotent).
 log_info "Installing Grafana Profiles Drilldown plugin..."
-helm upgrade --install grafana grafana/grafana \
+helm upgrade --install grafana grafana-community/grafana \
     --namespace "${NAMESPACE}" \
     --reuse-values \
     --set "plugins={grafana-pyroscope-app}" \

From f990da5a2d82ef3ea2055919788543bdece918e8 Mon Sep 17 00:00:00 2001
From: Yuriy Bezsonov <bezsonov@amazon.de>
Date: Fri, 3 Jul 2026 17:56:38 +0200
Subject: [PATCH 2/2] fix(monitoring): Use Recreate strategy for Grafana to
 avoid PVC deadlock

The Grafana chart defaults to deploymentStrategy RollingUpdate, but the
workshop enables persistence on a gp3 EBS volume (ReadWriteOnce). On the
plugin upgrade in perf-platform.sh, RollingUpdate starts a new pod before
deleting the old one; the new pod cannot attach the RWO volume still held
by the old pod, so it hangs with a Multi-Attach error until helm --wait
hits its deadline (UPGRADE FAILED: context deadline exceeded at line 292).

Set deploymentStrategy.type: Recreate in the Grafana values so the old pod
is terminated first and releases the volume. The value is persisted on the
release, so perf-platform.sh picks it up via --reuse-values.

Also raise the plugin-install --timeout from 5m to 10m to allow for the
EBS detach/reattach cycle plus plugin download on the Recreate path.
---
 infra/scripts/setup/monitoring.sh    | 7 +++++++
 infra/scripts/setup/perf-platform.sh | 2 +-
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/infra/scripts/setup/monitoring.sh b/infra/scripts/setup/monitoring.sh
index d018da78..5293c3f9 100755
--- a/infra/scripts/setup/monitoring.sh
+++ b/infra/scripts/setup/monitoring.sh
@@ -116,6 +116,13 @@ persistence:
   storageClassName: gp3
   size: 10Gi
 
+# The PVC above is ReadWriteOnce (EBS). RollingUpdate (the chart default)
+# starts the new pod before the old one is deleted, so the new pod cannot
+# attach the volume still held by the old pod and the upgrade deadlocks.
+# Recreate terminates the old pod first, releasing the volume.
+deploymentStrategy:
+  type: Recreate
+
 resources:
   requests:
     cpu: 100m
diff --git a/infra/scripts/setup/perf-platform.sh b/infra/scripts/setup/perf-platform.sh
index 6152ff17..22c3acd9 100755
--- a/infra/scripts/setup/perf-platform.sh
+++ b/infra/scripts/setup/perf-platform.sh
@@ -293,7 +293,7 @@ helm upgrade --install grafana grafana-community/grafana \
     --namespace "${NAMESPACE}" \
     --reuse-values \
     --set "plugins={grafana-pyroscope-app}" \
-    --wait --timeout 5m
+    --wait --timeout 10m
 log_success "Profiles Drilldown plugin installed"
 
 # Wait for Grafana API to be ready after the helm upgrade restarts the pod.