orchestratord test: Fix upgrades

.gitignore

@@ -60,3 +60,5 @@ flake.lock
 /known-docker-images.txt
 /test/sqllogictest/sqlite
 my-local-mz/
+/test/orchestratord/cluster.yaml
+uv.lock

ci/nightly/pipeline.template.yml

@@ -2367,6 +2367,7 @@ steps:
     steps:
       - id: orchestratord-defaults
         label: "Orchestratord test (defaults from documentation)"
+        artifact_paths: ["mz_debug_*.zip"]
         depends_on: devel-docker-tags
         timeout_in_minutes: 120
         plugins:
@@ -2379,6 +2380,7 @@ steps:
 
       - id: orchestratord-default-properties
         label: "Orchestratord test (defaults for properties)"
+        artifact_paths: ["mz_debug_*.zip"]
         depends_on: devel-docker-tags
         timeout_in_minutes: 120
         plugins:
@@ -2391,6 +2393,7 @@ steps:
 
       - id: orchestratord-individual
         label: "Orchestratord test (individual properties)"
+        artifact_paths: ["mz_debug_*.zip"]
         depends_on: devel-docker-tags
         timeout_in_minutes: 120
         plugins:
@@ -2403,76 +2406,65 @@ steps:
 
       - id: orchestratord-combine
         label: "Orchestratord test (combine properties)"
+        artifact_paths: ["mz_debug_*.zip"]
         depends_on: build-aarch64
         timeout_in_minutes: 120
         plugins:
           - ./ci/plugins/mzcompose:
               composition: orchestratord
-              args: [--action=noop, --properties=combine, --runtime=3600, --recreate-cluster]
+              args: [--action=noop, --properties=combine, --runtime=1800, --recreate-cluster]
               ci-builder: stable
         agents:
           queue: hetzner-aarch64-16cpu-32gb
 
       - id: orchestratord-upgrade-individual
         label: "Orchestratord test (upgrade, individual props)"
+        artifact_paths: ["mz_debug_*.zip"]
         depends_on: devel-docker-tags
         timeout_in_minutes: 120
         plugins:
           - ./ci/plugins/mzcompose:
               composition: orchestratord
-              args: [--action=upgrade, --properties=individual, --runtime=3600, --recreate-cluster]
+              args: [--action=upgrade, --properties=individual, --runtime=1800, --recreate-cluster]
               ci-builder: stable
-        env:
-          # Old versions are not on GHCR yet
-          MZ_GHCR: 0
         agents:
-          queue: hetzner-aarch64-8cpu-16gb
-        skip: "https://github.com/MaterializeInc/materialize/pull/34214"
+          queue: hetzner-aarch64-16cpu-32gb
 
       - id: orchestratord-upgrade-combine
         label: "Orchestratord test (upgrade, combine props)"
+        artifact_paths: ["mz_debug_*.zip"]
         depends_on: devel-docker-tags
         timeout_in_minutes: 120
         plugins:
           - ./ci/plugins/mzcompose:
               composition: orchestratord
-              args: [--action=upgrade, --properties=combine, --runtime=3600, --recreate-cluster]
+              args: [--action=upgrade, --properties=combine, --runtime=1800, --recreate-cluster]
               ci-builder: stable
-        env:
-          # Old versions are not on GHCR yet
-          MZ_GHCR: 0
         agents:
-          queue: hetzner-aarch64-8cpu-16gb
-        skip: "https://github.com/MaterializeInc/materialize/pull/34214"
+          queue: hetzner-aarch64-16cpu-32gb
 
       - id: orchestratord-upgrade-chain-individual
         label: "Orchestratord test (upgrade chain, individual props)"
+        artifact_paths: ["mz_debug_*.zip"]
         depends_on: devel-docker-tags
         timeout_in_minutes: 120
         plugins:
           - ./ci/plugins/mzcompose:
               composition: orchestratord
-              args: [--action=upgrade-chain, --properties=individual, --runtime=3600, --recreate-cluster]
+              args: [--action=upgrade-chain, --properties=individual, --runtime=1800, --recreate-cluster]
               ci-builder: stable
-        env:
-          # Old versions are not on GHCR yet
-          MZ_GHCR: 0
         agents:
-          queue: hetzner-aarch64-8cpu-16gb
-        skip: "https://github.com/MaterializeInc/materialize/pull/34214"
+          queue: hetzner-aarch64-16cpu-32gb
 
       - id: orchestratord-upgrade-chain-combine
         label: "Orchestratord test (upgrade chain, combine props)"
+        artifact_paths: ["mz_debug_*.zip"]
         depends_on: devel-docker-tags
         timeout_in_minutes: 120
         plugins:
           - ./ci/plugins/mzcompose:
               composition: orchestratord
-              args: [--action=upgrade-chain, --properties=combine, --runtime=3600, --recreate-cluster]
+              args: [--action=upgrade-chain, --properties=combine, --runtime=1800, --recreate-cluster]
               ci-builder: stable
-        env:
-          # Old versions are not on GHCR yet
-          MZ_GHCR: 0
         agents:
           queue: hetzner-aarch64-16cpu-32gb
-        skip: "https://github.com/MaterializeInc/materialize/pull/34214"

test/orchestratord/cluster.yaml → test/orchestratord/cluster.yaml.tmpl

@@ -11,6 +11,14 @@
 
 kind: Cluster
 apiVersion: kind.x-k8s.io/v1alpha4
+# Allow access to the registry from both inside and outside kubernetes
+containerdConfigPatches:
+  - |-
+    [plugins."io.containerd.grpc.v1.cri".registry.mirrors."docker.io"]
+      endpoint = ["http://proxy-docker-hub:5000"]
+  - |-
+    [plugins."io.containerd.grpc.v1.cri".registry.mirrors."ghcr.io"]
+      endpoint = ["http://proxy-ghcr:5000"]
 # Constrain the node port range to something relatively small, then forward all
 # those ports from the host. This makes services running in Kubernetes
 # accessible at localhost:$NODEPORT without requiring manual port forwarding.
@@ -23,6 +31,9 @@ kubeadmConfigPatches:
 nodes:
   - role: control-plane
     image: kindest/node:v1.32.5
+    extraMounts:
+      - containerPath: /var/lib/kubelet/config.json
+        hostPath: "$DOCKER_CONFIG/config.json"
     extraPortMappings:
       - containerPort: 32000
         hostPort: 32000
@@ -160,10 +171,17 @@ nodes:
       materialize.cloud/availability-zone: "1"
       topology.kubernetes.io/zone: "1"
       workload: "materialize-instance"
+    extraMounts:
+      - containerPath: /var/lib/kubelet/config.json
+        hostPath: "$DOCKER_CONFIG/config.json"
   - role: worker
     image: kindest/node:v1.32.5
     labels:
       materialize.cloud/scratch-fs: "true"
+      materialize.cloud/disk: "true"
       materialize.cloud/availability-zone: "2"
       topology.kubernetes.io/zone: "2"
       workload: "materialize-instance"
+    extraMounts:
+      - containerPath: /var/lib/kubelet/config.json
+        hostPath: "$DOCKER_CONFIG/config.json"