birbit stack

* Remove invalid dashboard and panel ids from alert rules

* Pin grafana and prometheus versions

* Configure custom grafana server URL

.gitea/workflows/test-k8s-deploy.yml

@@ -1,23 +1,16 @@
 name: K8s Deploy Test
 
 on:
-  pull_request:
-    branches: '*'
   push:
-    branches:
-      - main
-      - ci-test
-    paths-ignore:
-      - '.gitea/workflows/triggers/*'
-
-# Needed until we can incorporate docker startup into the executor container
-env:
-  DOCKER_HOST: unix:///var/run/dind.sock
+    branches: '*'
+    paths:
+      - '!**'
+      - '.gitea/workflows/triggers/fixturenet-laconicd-test'
 
 jobs:
   test:
-    name: "Run deploy test suite"
-    runs-on: ubuntu-latest
+    name: "Run deploy test suite on kind/k8s"
+    runs-on: ubuntu-22.04-with-syn-ethdb
     steps:
       - name: "Clone project repository"
         uses: actions/checkout@v3
@@ -41,15 +34,9 @@ jobs:
         run: ./scripts/create_build_tag_file.sh
       - name: "Build local shiv package"
         run: ./scripts/build_shiv_package.sh
-      - name: Start dockerd # Also needed until we can incorporate into the executor
-        run: |
-          dockerd -H $DOCKER_HOST --userland-proxy=false &
-          sleep 5
-      - name: "Install Go"
-        uses: actions/setup-go@v4
-        with:
-          go-version: '1.21'
-      - name: "Install Kind"
-        run: go install sigs.k8s.io/kind@v0.20.0
-      - name: "Debug Kind"
-        run: kind create cluster --retain && docker logs kind-control-plane
+      - name: "Install kind"
+        run: ./tests/scripts/install-kind.sh
+      - name: "Install Kubectl"
+        run: ./tests/scripts/install-kubectl.sh
+      - name: "Run k8s deployment test"
+        run: ./tests/k8s-deploy/run-deploy-test.sh

.gitea/workflows/triggers/test-k8s-deploy

@@ -0,0 +1 @@
+Change this file to trigger running the test-k8s-deploy CI job

stack_orchestrator/data/compose/docker-compose-fixturenet-laconicd.yml

@@ -2,7 +2,7 @@ services:
   laconicd:
     restart: unless-stopped
     image: cerc/laconicd:local
-    command: ["sh", "/docker-entrypoint-scripts.d/create-fixturenet.sh"]
+    entrypoint: ["sh", "/docker-entrypoint-scripts.d/create-fixturenet.sh"]
     volumes:
       # The cosmos-sdk node's database directory:
       - laconicd-data:/root/.laconicd
@@ -15,12 +15,12 @@ services:
       - "6060"
       - "26657"
       - "26656"
-      - "9473"
+      - "9473:9473"
       - "8545"
       - "8546"
       - "9090"
       - "9091"
-      - "1317"
+      - "1317:1317"
   cli:
     image: cerc/laconic-registry-cli:local
     volumes:

stack_orchestrator/data/compose/docker-compose-geojson.yml

@@ -0,0 +1,8 @@
+version: "3.2"
+
+services:
+  geojson:
+    image: cerc/geojson:local
+    restart: always
+    ports:
+      - 0.0.0.0:8080:8080

stack_orchestrator/data/compose/docker-compose-grafana.yml

@@ -2,8 +2,10 @@ version: "3.7"
 
 services:
   grafana:
-    image: grafana/grafana
+    image: grafana/grafana:10.2.2
     restart: always
+    environment:
+      GF_SERVER_ROOT_URL: ${GF_SERVER_ROOT_URL}
     volumes:
       - ../config/monitoring/grafana/provisioning:/etc/grafana/provisioning
       - ../config/monitoring/grafana/dashboards:/etc/grafana/dashboards

stack_orchestrator/data/compose/docker-compose-osmosis-front-end-urbit.yml

@@ -6,6 +6,7 @@ services:
     restart: on-failure
     environment:
       - NEXT_PUBLIC_WEB_API_BASE_URL=${CERC_WEB_API_BASE_URL}
+      - ASSET_LIST_COMMIT_HASH=a326bcefc51372b4912be5a2a2fa84a5d142a438
       - NEXT_PUBLIC_BASEPATH=/apps/osmosis
       - NEXT_PUBLIC_URBIT_DEPLOYMENT=true
     working_dir: /app/packages/web

stack_orchestrator/data/compose/docker-compose-osmosis-front-end.yml

@@ -6,6 +6,7 @@ services:
     restart: on-failure
     environment:
       - NEXT_PUBLIC_WEB_API_BASE_URL=${CERC_WEB_API_BASE_URL}
+      - ASSET_LIST_COMMIT_HASH=a326bcefc51372b4912be5a2a2fa84a5d142a438
     working_dir: /app/packages/web
     command: ["./build-app.sh"]
     volumes:

stack_orchestrator/data/compose/docker-compose-prom-server.yml

@@ -2,7 +2,7 @@ version: "3.7"
 
 services:
   prometheus:
-    image: prom/prometheus
+    image: prom/prometheus:v2.49.1
     restart: always
     volumes:
       - ../config/monitoring/prometheus:/etc/prometheus

stack_orchestrator/data/config/monitoring/watcher-alert-rules.yml

@@ -95,14 +95,10 @@ groups:
               maxDataPoints: 43200
               refId: condition
               type: math
-        dashboardUid: cb9b746a-9abc-482e-9214-5231e0dd75ca
-        panelId: 24
         noDataState: Alerting
         execErrState: Alerting
         for: 15m
         annotations:
-          __dashboardUid__: cb9b746a-9abc-482e-9214-5231e0dd75ca
-          __panelId__: "24"
           summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
         isPaused: false
       - uid: censures_diff_external
@@ -191,14 +187,10 @@ groups:
               maxDataPoints: 43200
               refId: condition
               type: math
-        dashboardUid: cb9b746a-9abc-482e-9214-5231e0dd75ca
-        panelId: 24
         noDataState: Alerting
         execErrState: Alerting
         for: 15m
         annotations:
-          __dashboardUid__: cb9b746a-9abc-482e-9214-5231e0dd75ca
-          __panelId__: "24"
           summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
         isPaused: false
       - uid: claims_diff_external
@@ -287,14 +279,10 @@ groups:
               maxDataPoints: 43200
               refId: condition
               type: math
-        dashboardUid: cb9b746a-9abc-482e-9214-5231e0dd75ca
-        panelId: 24
         noDataState: Alerting
         execErrState: Alerting
         for: 15m
         annotations:
-          __dashboardUid__: cb9b746a-9abc-482e-9214-5231e0dd75ca
-          __panelId__: "24"
           summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
         isPaused: false
       - uid: conditional_star_release_diff_external
@@ -383,14 +371,10 @@ groups:
               maxDataPoints: 43200
               refId: condition
               type: math
-        dashboardUid: cb9b746a-9abc-482e-9214-5231e0dd75ca
-        panelId: 24
         noDataState: Alerting
         execErrState: Alerting
         for: 15m
         annotations:
-          __dashboardUid__: cb9b746a-9abc-482e-9214-5231e0dd75ca
-          __panelId__: "24"
           summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
         isPaused: false
       - uid: delegated_sending_diff_external
@@ -479,14 +463,10 @@ groups:
               maxDataPoints: 43200
               refId: condition
               type: math
-        dashboardUid: cb9b746a-9abc-482e-9214-5231e0dd75ca
-        panelId: 24
         noDataState: Alerting
         execErrState: Alerting
         for: 15m
         annotations:
-          __dashboardUid__: cb9b746a-9abc-482e-9214-5231e0dd75ca
-          __panelId__: "24"
           summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
         isPaused: false
       - uid: ecliptic_diff_external
@@ -575,14 +555,10 @@ groups:
               maxDataPoints: 43200
               refId: condition
               type: math
-        dashboardUid: cb9b746a-9abc-482e-9214-5231e0dd75ca
-        panelId: 24
         noDataState: Alerting
         execErrState: Alerting
         for: 15m
         annotations:
-          __dashboardUid__: cb9b746a-9abc-482e-9214-5231e0dd75ca
-          __panelId__: "24"
           summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
         isPaused: false
       - uid: linear_star_release_diff_external
@@ -671,14 +647,10 @@ groups:
               maxDataPoints: 43200
               refId: condition
               type: math
-        dashboardUid: cb9b746a-9abc-482e-9214-5231e0dd75ca
-        panelId: 24
         noDataState: Alerting
         execErrState: Alerting
         for: 15m
         annotations:
-          __dashboardUid__: cb9b746a-9abc-482e-9214-5231e0dd75ca
-          __panelId__: "24"
           summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
         isPaused: false
       - uid: polls_diff_external
@@ -767,14 +739,10 @@ groups:
               maxDataPoints: 43200
               refId: condition
               type: math
-        dashboardUid: cb9b746a-9abc-482e-9214-5231e0dd75ca
-        panelId: 24
         noDataState: Alerting
         execErrState: Alerting
         for: 15m
         annotations:
-          __dashboardUid__: cb9b746a-9abc-482e-9214-5231e0dd75ca
-          __panelId__: "24"
           summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
         isPaused: false
 
@@ -865,14 +833,10 @@ groups:
               maxDataPoints: 43200
               refId: condition
               type: math
-        dashboardUid: cb9b746a-9abc-482e-9214-5231e0dd75ca
-        panelId: 24
         noDataState: Alerting
         execErrState: Alerting
         for: 15m
         annotations:
-          __dashboardUid__: cb9b746a-9abc-482e-9214-5231e0dd75ca
-          __panelId__: "24"
           summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
         isPaused: false
       - uid: merkl_sushiswap_diff_external
@@ -961,13 +925,9 @@ groups:
               maxDataPoints: 43200
               refId: condition
               type: math
-        dashboardUid: cb9b746a-9abc-482e-9214-5231e0dd75ca
-        panelId: 24
         noDataState: Alerting
         execErrState: Alerting
         for: 15m
         annotations:
-          __dashboardUid__: cb9b746a-9abc-482e-9214-5231e0dd75ca
-          __panelId__: "24"
           summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
         isPaused: false

stack_orchestrator/data/container-build/cerc-birbit/build.sh

@@ -0,0 +1,4 @@
+#!/usr/bin/env bash
+# Build the birbit image
+source ${CERC_CONTAINER_BASE_DIR}/build-base.sh
+docker build -t cerc/birbit:local -f ${CERC_REPO_BASE_DIR}/birbit/Dockerfile ${build_command_args} ${CERC_REPO_BASE_DIR}/birbit

stack_orchestrator/data/container-build/cerc-geojson/Dockerfile

@@ -0,0 +1,11 @@
+FROM node:14
+
+WORKDIR /app
+
+COPY . .
+
+RUN npm install && npm run build
+
+EXPOSE 8080
+
+CMD ["npm", "run", "serve"]

stack_orchestrator/data/container-build/cerc-geojson/build.sh

@@ -0,0 +1,5 @@
+#!/usr/bin/env bash
+# Build the geojson image
+source ${CERC_CONTAINER_BASE_DIR}/build-base.sh
+docker build -t cerc/geojson:local -f ${CERC_CONTAINER_BASE_DIR}/cerc-geojson/Dockerfile ${build_command_args} ${CERC_REPO_BASE_DIR}/geojson.io
+#docker build -t cerc/geojson:local -f ${CERC_REPO_BASE_DIR}/geojson.io/Dockerfile ${build_command_args} ${CERC_REPO_BASE_DIR}/geojson.io

stack_orchestrator/data/container-build/cerc-nextjs-base/scripts/build-app.sh

@@ -21,6 +21,11 @@ WORK_DIR="${1:-/app}"
 
 cd "${WORK_DIR}" || exit 1
 
+# If this file doesn't exist at all, we'll get errors below.
+if [ ! -f "next.config.js" ]; then
+  touch next.config.js
+fi
+
 if [ ! -f "next.config.dist" ]; then
   cp next.config.js next.config.dist
 fi

stack_orchestrator/data/stacks/act-runner/stack.yml

@@ -3,7 +3,7 @@ name: act-runner
 description: "Local act-runner"
 repos:
   - git.vdb.to/cerc-io/hosting
-  - gitea.com/gitea/act_runner
+  - gitea.com/telackey/act_runner@telackey/entrypoint
 containers:
   - cerc/act-runner
   - cerc/act-runner-task-executor

stack_orchestrator/data/stacks/birbit/README.md

@@ -0,0 +1,3 @@
+# birbit
+
+takes geo-tagged images, publishes the metadata on chain, then generates a geojson front end of that geo data

stack_orchestrator/data/stacks/birbit/stack.yml

@@ -0,0 +1,19 @@
+version: "0.1"
+name: birbit
+repos:
+  #- github.com/zramsay/birbit
+  - github.com/mapbox/geojson.io
+containers:
+  #- cerc/birbit
+  - cerc/geojson
+pods:
+    # configurable process that reads from chain and generates a view for the front end
+    # for MVP is basically does nothing, b/c FE view is  reading all records
+    # imagine a 'watcher' for a specific view
+    #- birbit
+    # front end, gets its file from kubo;
+    # https://github.com/mapbox/geojson.io/blob/main/API.md#datadatatextx-url
+    # deployed via kubernetes
+  - geojson
+    # hosts all the dot geojson files that are required to generated views
+  - kubo

stack_orchestrator/data/stacks/monitoring/README.md

@@ -140,6 +140,10 @@ Set the following env variables in the deployment env config file (`monitoring-d
   # External ETH RPC endpoint (filecoin)
   # (Optional, default: https://api.node.glif.io/rpc/v1)
   CERC_FIL_RPC_ENDPOINT=
+
+  # Grafana server host URL (used in various links in alerts, etc.)
+  # (Optional, default: http://localhost:3000)
+  GF_SERVER_ROOT_URL=
   ```
 
 ## Start the stack

stack_orchestrator/data/stacks/monitoring/monitoring-watchers.md

@@ -130,6 +130,10 @@ Set the following env variables in the deployment env config file (`monitoring-w
   ```bash
   # Infura key to be used
   CERC_INFURA_KEY=
+
+  # Grafana server host URL to be used
+  # (Optional, default: http://localhost:3000)
+  GF_SERVER_ROOT_URL=
   ```
 
 ## Start the stack

stack_orchestrator/data/stacks/package-registry/stack.yml

@@ -2,11 +2,9 @@ version: "1.1"
 name: package-registry
 description: "Local Package Registry"
 repos:
-  - github.com/telackey/gitea@telackey/entrypoint
-  - git.vdb.to/cerc-io/hosting@dboreham/fix-dind
+  - git.vdb.to/cerc-io/hosting
   - gitea.com/telackey/act_runner@telackey/entrypoint
 containers:
-  - cerc/gitea
   - cerc/act-runner
   - cerc/act-runner-task-executor
 pods:

stack_orchestrator/deploy/k8s/cluster_info.py

@@ -168,8 +168,8 @@ class ClusterInfo:
             result.append(pv)
         return result
 
-    # to suit the deployment, and also annotate the container specs to point at said volumes
-    def get_deployment(self):
+    # TODO: put things like image pull policy into an object-scope struct
+    def get_deployment(self, image_pull_policy: str = None):
         containers = []
         for pod_name in self.parsed_pod_yaml_map:
             pod = self.parsed_pod_yaml_map[pod_name]
@@ -189,7 +189,7 @@ class ClusterInfo:
                 container = client.V1Container(
                     name=container_name,
                     image=image_to_use,
-                    image_pull_policy="Always",
+                    image_pull_policy=image_pull_policy,
                     env=envs_from_environment_variables_map(self.environment_variables.map),
                     ports=[client.V1ContainerPort(container_port=port)],
                     volume_mounts=volume_mounts,

stack_orchestrator/deploy/k8s/deploy_k8s.py

@@ -111,7 +111,7 @@ class K8sDeployer(Deployer):
                 print("PVCs created:")
                 print(f"{pvc_resp}")
         # Process compose files into a Deployment
-        deployment = self.cluster_info.get_deployment()
+        deployment = self.cluster_info.get_deployment(image_pull_policy=None if self.is_kind() else "Always")
         # Create the k8s objects
         if opts.o.debug:
             print(f"Sending this deployment: {deployment}")
@@ -132,18 +132,18 @@ class K8sDeployer(Deployer):
             print("Service created:")
             print(f"{service_resp}")
 
-        # TODO: disable ingress for kind
-        ingress: client.V1Ingress = self.cluster_info.get_ingress()
+        if not self.is_kind():
+            ingress: client.V1Ingress = self.cluster_info.get_ingress()
 
-        if opts.o.debug:
-            print(f"Sending this ingress: {ingress}")
-        ingress_resp = self.networking_api.create_namespaced_ingress(
-            namespace=self.k8s_namespace,
-            body=ingress
-        )
-        if opts.o.debug:
-            print("Ingress created:")
-            print(f"{ingress_resp}")
+            if opts.o.debug:
+                print(f"Sending this ingress: {ingress}")
+            ingress_resp = self.networking_api.create_namespaced_ingress(
+                namespace=self.k8s_namespace,
+                body=ingress
+            )
+            if opts.o.debug:
+                print("Ingress created:")
+                print(f"{ingress_resp}")
 
     def down(self, timeout, volumes):
         self.connect_api()
@@ -196,16 +196,16 @@ class K8sDeployer(Deployer):
         except client.exceptions.ApiException as e:
             _check_delete_exception(e)
 
-        # TODO: disable ingress for kind
-        ingress: client.V1Ingress = self.cluster_info.get_ingress()
-        if opts.o.debug:
-            print(f"Deleting this ingress: {ingress}")
-        try:
-            self.networking_api.delete_namespaced_ingress(
-                name=ingress.metadata.name, namespace=self.k8s_namespace
-            )
-        except client.exceptions.ApiException as e:
-            _check_delete_exception(e)
+        if not self.is_kind():
+            ingress: client.V1Ingress = self.cluster_info.get_ingress()
+            if opts.o.debug:
+                print(f"Deleting this ingress: {ingress}")
+            try:
+                self.networking_api.delete_namespaced_ingress(
+                    name=ingress.metadata.name, namespace=self.k8s_namespace
+                )
+            except client.exceptions.ApiException as e:
+                _check_delete_exception(e)
 
         if self.is_kind():
             # Destroy the kind cluster
@@ -219,7 +219,7 @@ class K8sDeployer(Deployer):
 
         if all_pods.items:
             for p in all_pods.items:
-                if self.cluster_info.app_name in p.metadata.name:
+                if f"{self.cluster_info.app_name}-deployment" in p.metadata.name:
                     pods.append(p)
 
         if not pods:
@@ -266,7 +266,7 @@ class K8sDeployer(Deployer):
         ret = []
 
         for p in pods.items:
-            if self.cluster_info.app_name in p.metadata.name:
+            if f"{self.cluster_info.app_name}-deployment" in p.metadata.name:
                 pod_ip = p.status.pod_ip
                 ports = AttrDict()
                 for c in p.spec.containers:
@@ -299,11 +299,20 @@ class K8sDeployer(Deployer):
 
     def logs(self, services, tail, follow, stream):
         self.connect_api()
-        pods = pods_in_deployment(self.core_api, "test-deployment")
+        pods = pods_in_deployment(self.core_api, self.cluster_info.app_name)
         if len(pods) > 1:
             print("Warning: more than one pod in the deployment")
-        k8s_pod_name = pods[0]
-        log_data = self.core_api.read_namespaced_pod_log(k8s_pod_name, namespace="default", container="test")
+        if len(pods) == 0:
+            log_data = "******* Pods not running ********\n"
+        else:
+            k8s_pod_name = pods[0]
+            # If the pod is not yet started, the logs request below will throw an exception
+            try:
+                log_data = self.core_api.read_namespaced_pod_log(k8s_pod_name, namespace="default", container="test")
+            except client.exceptions.ApiException as e:
+                if opts.o.debug:
+                    print(f"Error from read_namespaced_pod_log: {e}")
+                log_data = "******* No logs available ********\n"
         return log_stream_from_string(log_data)
 
     def update(self):

stack_orchestrator/deploy/k8s/helpers.py

@@ -21,6 +21,7 @@ from typing import Set, Mapping, List
 
 from stack_orchestrator.opts import opts
 from stack_orchestrator.deploy.deploy_util import parsed_pod_files_map_from_file_names
+from stack_orchestrator.deploy.deployer import DeployerException
 
 
 def _run_command(command: str):
@@ -29,10 +30,13 @@ def _run_command(command: str):
     result = subprocess.run(command, shell=True)
     if opts.o.debug:
         print(f"Result: {result}")
+    return result
 
 
 def create_cluster(name: str, config_file: str):
-    _run_command(f"kind create cluster --name {name} --config {config_file}")
+    result = _run_command(f"kind create cluster --name {name} --config {config_file}")
+    if result.returncode != 0:
+        raise DeployerException(f"kind create cluster failed: {result}")
 
 
 def destroy_cluster(name: str):
@@ -41,12 +45,14 @@ def destroy_cluster(name: str):
 
 def load_images_into_kind(kind_cluster_name: str, image_set: Set[str]):
     for image in image_set:
-        _run_command(f"kind load docker-image {image} --name {kind_cluster_name}")
+        result = _run_command(f"kind load docker-image {image} --name {kind_cluster_name}")
+        if result.returncode != 0:
+            raise DeployerException(f"kind create cluster failed: {result}")
 
 
 def pods_in_deployment(core_api: client.CoreV1Api, deployment_name: str):
     pods = []
-    pod_response = core_api.list_namespaced_pod(namespace="default", label_selector="app=test-app")
+    pod_response = core_api.list_namespaced_pod(namespace="default", label_selector=f"app={deployment_name}")
     if opts.o.debug:
         print(f"pod_response: {pod_response}")
     for pod_info in pod_response.items:

tests/k8s-deploy/run-deploy-test.sh

@@ -1,14 +1,59 @@
 #!/usr/bin/env bash
 set -e
 if [ -n "$CERC_SCRIPT_DEBUG" ]; then
-  set -x
+    set -x
+    # Dump environment variables for debugging
+    echo "Environment variables:"
+    env
 fi
+
+# Helper functions: TODO move into a separate file
+wait_for_pods_started () {
+    for i in {1..5}
+    do
+        local ps_output=$( $TEST_TARGET_SO deployment --dir $test_deployment_dir ps )
+
+        if [[ "$ps_output" == *"Running containers:"* ]]; then
+            # if ready, return
+            return
+        else
+            # if not ready, wait
+            sleep 5
+        fi
+    done
+    # Timed out, error exit
+    echo "waiting for pods to start: FAILED"
+    delete_cluster_exit
+}
+
+wait_for_log_output () {
+    for i in {1..5}
+    do
+
+        local log_output=$( $TEST_TARGET_SO deployment --dir $test_deployment_dir logs )
+
+        if [[ ! -z "$log_output" ]]; then
+            # if ready, return
+            return
+        else
+            # if not ready, wait
+            sleep 5
+        fi
+    done
+    # Timed out, error exit
+    echo "waiting for pods log content: FAILED"
+    delete_cluster_exit
+}
+
+
+delete_cluster_exit () {
+    $TEST_TARGET_SO deployment --dir $test_deployment_dir stop --delete-volumes
+    exit 1
+}
+
 # Note: eventually this test should be folded into ../deploy/
 # but keeping it separate for now for convenience
 TEST_TARGET_SO=$( ls -t1 ./package/laconic-so* | head -1 )
-# Dump environment variables for debugging
-echo "Environment variables:"
-env
 # Set a non-default repo dir
 export CERC_REPO_BASE_DIR=~/stack-orchestrator-test/repo-base-dir
 echo "Testing this package: $TEST_TARGET_SO"
@@ -18,7 +63,9 @@ echo "Version reported is: ${reported_version_string}"
 echo "Cloning repositories into: $CERC_REPO_BASE_DIR"
 rm -rf $CERC_REPO_BASE_DIR
 mkdir -p $CERC_REPO_BASE_DIR
-# Test basic stack-orchestrator deploy
+$TEST_TARGET_SO --stack test setup-repositories
+$TEST_TARGET_SO --stack test build-containers
+# Test basic stack-orchestrator deploy to k8s
 test_deployment_dir=$CERC_REPO_BASE_DIR/test-deployment-dir
 test_deployment_spec=$CERC_REPO_BASE_DIR/test-deployment-spec.yml
 $TEST_TARGET_SO --stack test deploy --deploy-to k8s-kind init --output $test_deployment_spec --config CERC_TEST_PARAM_1=PASSED
@@ -53,23 +100,36 @@ fi
 echo "deploy create output file test: passed"
 # Try to start the deployment
 $TEST_TARGET_SO deployment --dir $test_deployment_dir start
-# TODO: add a check to see if the container is up
-# Sleep because k8s not up yet
-sleep 30
+wait_for_pods_started
 # Check logs command works
+wait_for_log_output
 log_output_3=$( $TEST_TARGET_SO deployment --dir $test_deployment_dir logs )
 if [[ "$log_output_3" == *"Filesystem is fresh"* ]]; then
     echo "deployment logs test: passed"
 else
     echo "deployment logs test: FAILED"
-    exit 1
+    delete_cluster_exit
 fi
 # Check the config variable CERC_TEST_PARAM_1 was passed correctly
 if [[ "$log_output_3" == *"Test-param-1: PASSED"* ]]; then
     echo "deployment config test: passed"
 else
     echo "deployment config test: FAILED"
-    exit 1
+    delete_cluster_exit
+fi
+# Stop then start again and check the volume was preserved
+$TEST_TARGET_SO deployment --dir $test_deployment_dir stop
+# Sleep a bit just in case
+sleep 2
+$TEST_TARGET_SO deployment --dir $test_deployment_dir start
+wait_for_pods_started
+wait_for_log_output
+log_output_4=$( $TEST_TARGET_SO deployment --dir $test_deployment_dir logs )
+if [[ "$log_output_4" == *"Filesystem is old"* ]]; then
+    echo "Retain volumes test: passed"
+else
+    echo "Retain volumes test: FAILED"
+    delete_cluster_exit
 fi
 # Stop and clean up
 $TEST_TARGET_SO deployment --dir $test_deployment_dir stop --delete-volumes

tests/scripts/install-kind.sh

@@ -0,0 +1,5 @@
+#!/usr/bin/env bash
+# TODO: handle ARM
+curl --silent -Lo ./kind https://kind.sigs.k8s.io/dl/v0.20.0/kind-linux-amd64
+chmod +x ./kind
+mv ./kind /usr/local/bin

tests/scripts/install-kubectl.sh

@@ -0,0 +1,5 @@
+#!/usr/bin/env bash
+# TODO: handle ARM
+curl --silent -LO "https://dl.k8s.io/release/$(curl -L -s https://dl.k8s.io/release/stable.txt)/bin/linux/amd64/kubectl"
+chmod +x ./kubectl
+mv ./kubectl /usr/local/bin