Fix/perf push timeout

apps/unicorn-store-spring/scripts/build.sh

@@ -60,6 +60,12 @@ docker build \
   --secret id=db-password,env=DB_PASS \
   "${EXTRA_ARGS[@]}" \
   -t "${REPO}:${TAG}" -f "$DOCKERFILE" .
-docker push "${REPO}:${TAG}"
+# A push can stall without output (seen once: 20 min for two layers that usually take
+# seconds). Bound each attempt and retry; layers already uploaded are not sent again.
+for attempt in 1 2 3; do
+    if timeout 180 docker push "${REPO}:${TAG}"; then break; fi
+    [ "${attempt}" = 3 ] && { echo "[build] push failed 3 times" >&2; exit 1; }
+    echo "[build] push did not finish in 180 s, retrying (${attempt}/3)..." >&2
+done
 echo "[build] pushed ${REPO}:${TAG}" >&2
 echo "${REPO}:${TAG}"

infra/scripts/deploy/java-performance/platform-placement.sh

@@ -6,28 +6,77 @@
 # workloads have no selector, so Karpenter places them wherever there is room, usually on
 # the app's 4-vCPU node. There the app shares physical cores (SMT) with Prometheus,
 # Pyroscope and Kyverno, and the session's measurements move with that load (startup and
-# steady CPU 10–60 % higher in a test run). This script pins every platform Deployment and
-# StatefulSet to the Auto Mode built-in `general-purpose` NodePool, so the `workshop` node
-# carries only the app and the DaemonSets. The app manifest is unchanged.
+# steady CPU 10–60 % higher in a test run). This script creates a `platform` NodePool and
+# pins every platform Deployment and StatefulSet to it, so the `workshop` node carries only
+# the app and the DaemonSets. The app manifest is unchanged.
+#
+# The pool admits only instances with at least 4 vCPU and 8 GiB (c6a.xlarge is the cheapest
+# match): the platform requests about 1.5 vCPU and 4.4 GiB, so one node holds all of it. On
+# the built-in general-purpose pool Karpenter started a c6a.large per batch of pending pods
+# and kept two (do-not-disrupt blocks the merge), at more cost than one c6a.xlarge.
 #
 # Namespaces: monitoring (Prometheus, Grafana, Pyroscope, Alloy, sensor), kyverno,
 # kube-startup-cpu-boost-system, and metrics-server in kube-system. Pods move once, at
 # bootstrap; Prometheus, Grafana and Pyroscope keep their data on their PVCs. The pods are
-# marked do-not-disrupt, so consolidation does not move them later.
-# Idempotent. Run after the platform installs (template stage E). A later `helm upgrade`
+# marked do-not-disrupt and the pool consolidates only when empty, so nothing moves them later.
+# Idempotent. `platform-placement.sh pool` creates only the NodePool (template stage B, so
+# monitoring.sh installs onto it via MONITORING_NODEPOOL); without an argument it also pins
+# the workloads (after stage E). A later `helm upgrade`
 # of one of these releases drops the selector: run this script again afterwards.
 # =============================================================================
 set -uo pipefail
 
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 source "${SCRIPT_DIR}/../../lib/common.sh"
 
-POOL="${PLATFORM_NODEPOOL:-general-purpose}"
-kubectl get nodepool "${POOL}" >/dev/null 2>&1 || { log_error "NodePool ${POOL} not found (EKS Auto Mode built-in pools disabled?)"; exit 1; }
+POOL="${PLATFORM_NODEPOOL:-platform}"
+
+kubectl apply -f - <<EOF >/dev/null || { log_error "NodePool ${POOL} could not be created"; exit 1; }
+apiVersion: karpenter.sh/v1
+kind: NodePool
+metadata:
+  name: ${POOL}
+spec:
+  template:
+    spec:
+      nodeClassRef:
+        group: eks.amazonaws.com
+        kind: NodeClass
+        name: default
+      requirements:
+        - key: karpenter.sh/capacity-type
+          operator: In
+          values: ["on-demand"]
+        - key: kubernetes.io/arch
+          operator: In
+          values: ["amd64"]
+        - key: kubernetes.io/os
+          operator: In
+          values: ["linux"]
+        - key: eks.amazonaws.com/instance-category
+          operator: In
+          values: ["c", "m"]
+        - key: eks.amazonaws.com/instance-generation
+          operator: Gt
+          values: ["5"]
+        - key: eks.amazonaws.com/instance-cpu
+          operator: Gt
+          values: ["3"]
+        - key: eks.amazonaws.com/instance-memory
+          operator: Gt
+          values: ["8000"]
+  limits:
+    cpu: "16"
+  disruption:
+    consolidationPolicy: WhenEmpty
+    consolidateAfter: 5m
+EOF
+log_info "NodePool ${POOL}: at least 4 vCPU and 8 GiB, consolidation WhenEmpty"
+# `pool`: only the NodePool (template stage B, before monitoring.sh installs onto it).
+[ "${1:-}" = pool ] && exit 0
 
-# do-not-disrupt: the general-purpose pool consolidates underutilized nodes after 30 s. A
-# consolidation during the session would move the sensor or Kyverno in the middle of a
-# checklist or an admission; the annotation keeps their nodes until the pods go.
+# do-not-disrupt: a consolidation during the session would move the sensor or Kyverno in
+# the middle of a checklist or an admission; the annotation keeps their node until the pods go.
 PATCH="{\"spec\":{\"template\":{\"metadata\":{\"annotations\":{\"karpenter.sh/do-not-disrupt\":\"true\"}},\"spec\":{\"nodeSelector\":{\"karpenter.sh/nodepool\":\"${POOL}\"}}}}}"
 RC=0
 pin() {   # pin NAMESPACE KIND/NAME...

infra/scripts/setup/monitoring.sh

@@ -38,6 +38,17 @@ DATASOURCE_FILE="grafana-datasource.yaml"
 GRAFANA_VALUES_FILE="grafana-values.yaml"
 
 WORK=""
+
+# Optional NodePool for the stack: MONITORING_NODEPOOL, set by a workshop template that keeps
+# the platform off its app's node (java-performance). Applied at install, so the PVCs of
+# Prometheus, Pyroscope and Grafana bind in that pool's zone from the start. Unset: no
+# selector, the charts install as before.
+PROM_POOL=(); PYRO_POOL=(); GRAFANA_POOL=()
+if [ -n "${MONITORING_NODEPOOL:-}" ]; then
+    PROM_POOL=(--set-string "server.nodeSelector.karpenter\\.sh/nodepool=${MONITORING_NODEPOOL}")
+    PYRO_POOL=(--set-string "pyroscope.nodeSelector.karpenter\\.sh/nodepool=${MONITORING_NODEPOOL}")
+    GRAFANA_POOL=(--set-string "nodeSelector.karpenter\\.sh/nodepool=${MONITORING_NODEPOOL}")
+fi
 cleanup() {
   rm -f "$VALUES_FILE" "$DATASOURCE_FILE" "$GRAFANA_VALUES_FILE"
   [[ -n "$WORK" ]] && rm -rf "$WORK"
@@ -79,7 +90,7 @@ EOF
 
 log_info "Deploying Prometheus..."
 helm upgrade --install prometheus prometheus-community/prometheus \
-  --namespace "$NAMESPACE" \
+  --namespace "$NAMESPACE" ${PROM_POOL[@]+"${PROM_POOL[@]}"} \
   --values "$VALUES_FILE" >>"$LOG" 2>&1 \
   || { log_error "Prometheus helm install failed — last 40 lines of $LOG:"; tail -n 40 "$LOG"; exit 1; }
 
@@ -203,7 +214,7 @@ pyroscope:
 EOF
 
 helm upgrade --install pyroscope grafana/pyroscope \
-    --namespace "${NAMESPACE}" \
+    --namespace "${NAMESPACE}" ${PYRO_POOL[@]+"${PYRO_POOL[@]}"} \
     --values "${WORK}/pyroscope-values.yaml" >>"$LOG" 2>&1 \
     || { log_error "Pyroscope helm install failed — last 40 lines of $LOG:"; tail -n 40 "$LOG"; exit 1; }
 log_info "Pyroscope install submitted (readiness checked after Grafana)"
@@ -291,7 +302,7 @@ EOF
 
 log_info "Deploying Grafana..."
 helm upgrade --install grafana grafana-community/grafana \
-  --namespace "$NAMESPACE" \
+  --namespace "$NAMESPACE" ${GRAFANA_POOL[@]+"${GRAFANA_POOL[@]}"} \
   --values "$GRAFANA_VALUES_FILE" >>"$LOG" 2>&1 \
   || { log_error "Grafana helm install failed — last 40 lines of $LOG:"; tail -n 40 "$LOG"; exit 1; }
 

infra/scripts/templates/java-performance.sh

@@ -15,7 +15,7 @@
 #      --- wait for A ---
 #   D  app          app-deploy (namespace, Pod Identity, manifests)      } in
 #   E  platform     perf-profiler install, startup-cpu-boost, perf-sensor } parallel
-#      placement    platform Deployments/StatefulSets → general-purpose NodePool
+#      placement    platform Deployments/StatefulSets → own platform NodePool
 #   F  verify       ALB answers, sensor measures, Claude wiring present
 #
 # Each stage script is idempotent and runnable on its own from the IDE.
@@ -65,10 +65,12 @@ A_PID=$!
 stage "B: EKS cluster"
 run "EKS cluster configured"        "$SETUP/eks.sh"
 try "NodePool pinned to m6a"        "$DEPLOY/nodepool-pin.sh"
+run "Platform NodePool created"     "$DEPLOY/platform-placement.sh" pool
 try "metrics-server installed"      "$DEPLOY/metrics-server.sh"
 
 # --- C: monitoring ---------------------------------------------------------------------
 stage "C: monitoring (Prometheus, Pyroscope, Grafana)"
+export MONITORING_NODEPOOL=platform   # monitoring.sh installs the stack onto the platform pool
 run "Monitoring stack deployed"     "$SETUP/monitoring.sh"
 
 # --- wait for A -------------------------------------------------------------------------
@@ -101,7 +103,7 @@ cat "$D_LOG"; cat "$E_LOG"
 [ "$E_RC" -eq 0 ] && log_success "$(stamp)Stage E done (profiler, boost, sensor)" || { log_error "$(stamp)Stage E FAILED"; exit 1; }
 
 # --- platform placement: platform pods off the app's node ------------------------------
-run "Platform on the general-purpose NodePool" "$DEPLOY/platform-placement.sh"
+run "Platform on its own NodePool" "$DEPLOY/platform-placement.sh"
 
 # --- F: verify --------------------------------------------------------------------------
 stage "F: verify"