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:
+    branches: '*'
-      - main
+    paths:
-      - ci-test
+      - '!**'
-    paths-ignore:
+      - '.gitea/workflows/triggers/fixturenet-laconicd-test'
-      - '.gitea/workflows/triggers/*'
-
-# Needed until we can incorporate docker startup into the executor container
-env:
-  DOCKER_HOST: unix:///var/run/dind.sock
 
 jobs:
   test:
-    name: "Run deploy test suite"
+    name: "Run deploy test suite on kind/k8s"
-    runs-on: ubuntu-latest
+    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
+      - name: "Install kind"
-        run: |
+        run: ./tests/scripts/install-kind.sh
-          dockerd -H $DOCKER_HOST --userland-proxy=false &
+      - name: "Install Kubectl"
-          sleep 5
+        run: ./tests/scripts/install-kubectl.sh
-      - name: "Install Go"
+      - name: "Run k8s deployment test"
-        uses: actions/setup-go@v4
+        run: ./tests/k8s-deploy/run-deploy-test.sh
-        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

.gitea/workflows/test-webapp.yml

@@ -41,6 +41,8 @@ jobs:
         run: ./scripts/create_build_tag_file.sh
       - name: "Build local shiv package"
         run: ./scripts/build_shiv_package.sh
+      - name: "Install wget" # 20240109 - Only needed until the executors are updated.
+        run: apt update && apt install -y wget
       - name: Start dockerd # Also needed until we can incorporate into the executor
         run: |
           dockerd -H $DOCKER_HOST --userland-proxy=false &

.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-node-exporter.yml

@@ -5,12 +5,11 @@ services:
     image: prom/node-exporter:latest
     restart: unless-stopped
     command:
+      - '--web.listen-address=:9100'
       - '--path.rootfs=/host'
       - '--collector.systemd'
       - '--collector.processes'
     network_mode: host
     pid: host
-    ports:
-      - 9100
     volumes:
       - '/:/host:ro,rslave'

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/grafana/provisioning/alerting/contactpoints.yml

@@ -0,0 +1,14 @@
+# https://www.clever-cloud.com/blog/features/2021/12/03/slack-alerts-for-grafana/
+
+apiVersion: 1
+
+contactPoints:
+  - orgId: 1
+    name: SlackNotifier
+    receivers:
+      - uid: a71b06e3-58b6-41fe-af65-fbbb29653951
+        type: slack
+        settings:
+          # Slack hook URL (see https://api.slack.com/messaging/webhooks)
+          url: <YOUR_SLACK_HOOK_URL>
+        disableResolveMessage: false

stack_orchestrator/data/config/monitoring/grafana/provisioning/alerting/policies.yml

@@ -0,0 +1,15 @@
+# https://grafana.com/docs/grafana/latest/alerting/alerting-rules/create-notification-policy/
+
+apiVersion: 1
+
+policies:
+  - orgId: 1
+    receiver: grafana-default-email
+    group_by:
+      - grafana_folder
+      - alertname
+    routes:
+      - receiver: SlackNotifier
+        object_matchers:
+          # Add matchers below
+          # - ['grafana_folder', '=', 'MyAlerts']

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

@@ -0,0 +1,933 @@
+# https://grafana.com/docs/grafana/latest/alerting/alerting-rules/create-grafana-managed-rule/
+
+apiVersion: 1
+
+groups:
+  - orgId: 1
+    name: watcher
+    folder: WatcherAlerts
+    interval: 30s
+    rules:
+      # Azimuth
+      - uid: azimuth_diff_external
+        title: azimuth_watcher_head_tracking
+        condition: condition
+        data:
+          - refId: diff
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              disableTextWrap: false
+              editorMode: code
+              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="azimuth", instance="azimuth", kind="latest_indexed"}
+              fullMetaSearch: false
+              includeNullMetadata: true
+              instant: true
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: false
+              refId: diff
+              useBackend: false
+          - refId: latest_external
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: latest_block_number{chain="ethereum"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_external
+          - refId: latest_indexed
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: sync_status_block_number{job="azimuth", instance="azimuth", kind="latest_indexed"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_indexed
+          - refId: condition
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params: []
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: condition
+              type: math
+        noDataState: Alerting
+        execErrState: Alerting
+        for: 15m
+        annotations:
+          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
+        title: censures_watcher_head_tracking
+        condition: condition
+        data:
+          - refId: diff
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              disableTextWrap: false
+              editorMode: code
+              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="azimuth", instance="censures", kind="latest_indexed"}
+              fullMetaSearch: false
+              includeNullMetadata: true
+              instant: true
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: false
+              refId: diff
+              useBackend: false
+          - refId: latest_external
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: latest_block_number{chain="ethereum"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_external
+          - refId: latest_indexed
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: sync_status_block_number{job="azimuth", instance="censures", kind="latest_indexed"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_indexed
+          - refId: condition
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params: []
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: condition
+              type: math
+        noDataState: Alerting
+        execErrState: Alerting
+        for: 15m
+        annotations:
+          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
+        title: claims_watcher_head_tracking
+        condition: condition
+        data:
+          - refId: diff
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              disableTextWrap: false
+              editorMode: code
+              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="azimuth", instance="claims", kind="latest_indexed"}
+              fullMetaSearch: false
+              includeNullMetadata: true
+              instant: true
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: false
+              refId: diff
+              useBackend: false
+          - refId: latest_external
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: latest_block_number{chain="ethereum"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_external
+          - refId: latest_indexed
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: sync_status_block_number{job="azimuth", instance="claims", kind="latest_indexed"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_indexed
+          - refId: condition
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params: []
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: condition
+              type: math
+        noDataState: Alerting
+        execErrState: Alerting
+        for: 15m
+        annotations:
+          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
+        title: conditional_star_release_watcher_head_tracking
+        condition: condition
+        data:
+          - refId: diff
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              disableTextWrap: false
+              editorMode: code
+              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="azimuth", instance="conditional_star_release", kind="latest_indexed"}
+              fullMetaSearch: false
+              includeNullMetadata: true
+              instant: true
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: false
+              refId: diff
+              useBackend: false
+          - refId: latest_external
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: latest_block_number{chain="ethereum"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_external
+          - refId: latest_indexed
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: sync_status_block_number{job="azimuth", instance="conditional_star_release", kind="latest_indexed"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_indexed
+          - refId: condition
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params: []
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: condition
+              type: math
+        noDataState: Alerting
+        execErrState: Alerting
+        for: 15m
+        annotations:
+          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
+        title: delegated_sending_watcher_head_tracking
+        condition: condition
+        data:
+          - refId: diff
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              disableTextWrap: false
+              editorMode: code
+              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="azimuth", instance="delegated_sending", kind="latest_indexed"}
+              fullMetaSearch: false
+              includeNullMetadata: true
+              instant: true
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: false
+              refId: diff
+              useBackend: false
+          - refId: latest_external
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: latest_block_number{chain="ethereum"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_external
+          - refId: latest_indexed
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: sync_status_block_number{job="azimuth", instance="delegated_sending", kind="latest_indexed"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_indexed
+          - refId: condition
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params: []
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: condition
+              type: math
+        noDataState: Alerting
+        execErrState: Alerting
+        for: 15m
+        annotations:
+          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
+        title: ecliptic_watcher_head_tracking
+        condition: condition
+        data:
+          - refId: diff
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              disableTextWrap: false
+              editorMode: code
+              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="azimuth", instance="ecliptic", kind="latest_indexed"}
+              fullMetaSearch: false
+              includeNullMetadata: true
+              instant: true
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: false
+              refId: diff
+              useBackend: false
+          - refId: latest_external
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: latest_block_number{chain="ethereum"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_external
+          - refId: latest_indexed
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: sync_status_block_number{job="azimuth", instance="ecliptic", kind="latest_indexed"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_indexed
+          - refId: condition
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params: []
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: condition
+              type: math
+        noDataState: Alerting
+        execErrState: Alerting
+        for: 15m
+        annotations:
+          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
+        title: linear_star_release_watcher_head_tracking
+        condition: condition
+        data:
+          - refId: diff
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              disableTextWrap: false
+              editorMode: code
+              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="azimuth", instance="linear_star_release", kind="latest_indexed"}
+              fullMetaSearch: false
+              includeNullMetadata: true
+              instant: true
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: false
+              refId: diff
+              useBackend: false
+          - refId: latest_external
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: latest_block_number{chain="ethereum"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_external
+          - refId: latest_indexed
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: sync_status_block_number{job="azimuth", instance="azimuth", kind="latest_indexed"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_indexed
+          - refId: condition
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params: []
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: condition
+              type: math
+        noDataState: Alerting
+        execErrState: Alerting
+        for: 15m
+        annotations:
+          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
+        title: polls_watcher_head_tracking
+        condition: condition
+        data:
+          - refId: diff
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              disableTextWrap: false
+              editorMode: code
+              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="azimuth", instance="polls", kind="latest_indexed"}
+              fullMetaSearch: false
+              includeNullMetadata: true
+              instant: true
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: false
+              refId: diff
+              useBackend: false
+          - refId: latest_external
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: latest_block_number{chain="ethereum"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_external
+          - refId: latest_indexed
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: sync_status_block_number{job="azimuth", instance="polls", kind="latest_indexed"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_indexed
+          - refId: condition
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params: []
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: condition
+              type: math
+        noDataState: Alerting
+        execErrState: Alerting
+        for: 15m
+        annotations:
+          summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
+        isPaused: false
+
+      # Sushi
+      - uid: sushiswap_diff_external
+        title: sushiswap_watcher_head_tracking
+        condition: condition
+        data:
+          - refId: diff
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              disableTextWrap: false
+              editorMode: code
+              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="sushi", instance="sushiswap", kind="latest_indexed"}
+              fullMetaSearch: false
+              includeNullMetadata: true
+              instant: true
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: false
+              refId: diff
+              useBackend: false
+          - refId: latest_external
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: latest_block_number{chain="filecoin"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_external
+          - refId: latest_indexed
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: sync_status_block_number{job="sushi", instance="sushiswap", kind="latest_indexed"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_indexed
+          - refId: condition
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params: []
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: condition
+              type: math
+        noDataState: Alerting
+        execErrState: Alerting
+        for: 15m
+        annotations:
+          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
+        title: merkl_sushiswap_watcher_head_tracking
+        condition: condition
+        data:
+          - refId: diff
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              disableTextWrap: false
+              editorMode: code
+              expr: latest_block_number - on(chain) group_right sync_status_block_number{job="sushi", instance="merkl_sushiswap", kind="latest_indexed"}
+              fullMetaSearch: false
+              includeNullMetadata: true
+              instant: true
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: false
+              refId: diff
+              useBackend: false
+          - refId: latest_external
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: latest_block_number{chain="filecoin"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_external
+          - refId: latest_indexed
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                type: prometheus
+                uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: sync_status_block_number{job="sushi", instance="merkl_sushiswap", kind="latest_indexed"}
+              hide: false
+              instant: true
+              legendFormat: __auto
+              range: false
+              refId: latest_indexed
+          - refId: condition
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: __expr__
+            model:
+              conditions:
+                - evaluator:
+                    params:
+                      - 0
+                      - 0
+                    type: gt
+                  operator:
+                    type: and
+                  query:
+                    params: []
+                  reducer:
+                    params: []
+                    type: avg
+                  type: query
+              datasource:
+                name: Expression
+                type: __expr__
+                uid: __expr__
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: condition
+              type: math
+        noDataState: Alerting
+        execErrState: Alerting
+        for: 15m
+        annotations:
+          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-act-runner-task-executor/build.sh

@@ -2,4 +2,6 @@
 # Build a local version of the task executor for act-runner
 source ${CERC_CONTAINER_BASE_DIR}/build-base.sh
 SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
-docker build -t cerc/act-runner-task-executor:local -f ${CERC_REPO_BASE_DIR}/hosting/act-runner/Dockerfile.task-executor ${build_command_args} ${SCRIPT_DIR}
+
+cd ${CERC_REPO_BASE_DIR}/hosting/act-runner
+docker build -t cerc/act-runner-task-executor:local -f Dockerfile.task-executor ${build_command_args} .

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/merkl-sushiswap-v3/stack.yml

@@ -2,7 +2,7 @@ version: "1.0"
 name: merkl-sushiswap-v3
 description: "SushiSwap v3 watcher stack"
 repos:
-  - github.com/cerc-io/merkl-sushiswap-v3-watcher-ts@v0.1.4
+  - github.com/cerc-io/merkl-sushiswap-v3-watcher-ts@v0.1.6
 containers:
   - cerc/watcher-merkl-sushiswap-v3
 pods:

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

@@ -35,6 +35,8 @@ laconic-so --stack monitoring deploy create --spec-file monitoring-watchers-spec
 
 ## Configure
 
+### Prometheus scrape config
+
 Add the following scrape configs to prometheus config file (`monitoring-watchers-deployment/config/monitoring/prometheus/prometheus.yml`) in the deployment folder:
 
   ```yml
@@ -100,6 +102,27 @@ Add the following scrape configs to prometheus config file (`monitoring-watchers
 
 Add scrape config as done above for any additional watcher to add it to the Watchers dashboard.
 
+### Grafana alerts config
+
+Place the pre-configured watcher alerts rules in Grafana provisioning directory:
+
+  ```bash
+  cp monitoring-watchers-deployment/config/monitoring/watcher-alert-rules.yml monitoring-watchers-deployment/config/monitoring/grafana/provisioning/alerting/
+  ```
+
+Update the alerting contact points config (`monitoring-watchers-deployment/config/monitoring/grafana/provisioning/alerting/contactpoints.yml`) with desired contact points
+
+Add corresponding routes to the notification policies config (`monitoring-watchers-deployment/monitoring/grafana/provisioning/alerting/policies.yaml`) with appropriate object-matchers:
+
+  ```yml
+  ...
+    routes:
+      - receiver: SlackNotifier
+      object_matchers:
+        # Add matchers below
+        - ['grafana_folder', '=', 'WatcherAlerts']
+  ```
+
 ### Env
 
 Set the following env variables in the deployment env config file (`monitoring-watchers-deployment/config.env`):
@@ -107,6 +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

@@ -3,7 +3,7 @@ name: package-registry
 description: "Local Package Registry"
 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/sushiswap-v3/stack.yml

@@ -2,7 +2,7 @@ version: "1.0"
 name: sushiswap-v3
 description: "SushiSwap v3 watcher stack"
 repos:
-  - github.com/cerc-io/sushiswap-v3-watcher-ts@v0.1.5
+  - github.com/cerc-io/sushiswap-v3-watcher-ts@v0.1.6
 containers:
   - cerc/watcher-sushiswap-v3
 pods:

stack_orchestrator/deploy/deployment_create.py

@@ -444,7 +444,7 @@ def create_operation(deployment_command_context, spec_file, deployment_dir, netw
     deployer_config_generator = getDeployerConfigGenerator(deployment_type)
     # TODO: make deployment_dir_path a Path above
     deployer_config_generator.generate(deployment_dir_path)
-    call_stack_deploy_create(deployment_context, [network_dir, initial_peers])
+    call_stack_deploy_create(deployment_context, [network_dir, initial_peers, deployment_command_context])
 
 
 # TODO: this code should be in the stack .py files but

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
+    # TODO: put things like image pull policy into an object-scope struct
-    def get_deployment(self):
+    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
+        if not self.is_kind():
-        ingress: client.V1Ingress = self.cluster_info.get_ingress()
+            ingress: client.V1Ingress = self.cluster_info.get_ingress()
 
-        if opts.o.debug:
+            if opts.o.debug:
-            print(f"Sending this ingress: {ingress}")
+                print(f"Sending this ingress: {ingress}")
-        ingress_resp = self.networking_api.create_namespaced_ingress(
+            ingress_resp = self.networking_api.create_namespaced_ingress(
-            namespace=self.k8s_namespace,
+                namespace=self.k8s_namespace,
-            body=ingress
+                body=ingress
-        )
+            )
-        if opts.o.debug:
+            if opts.o.debug:
-            print("Ingress created:")
+                print("Ingress created:")
-            print(f"{ingress_resp}")
+                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
+        if not self.is_kind():
-        ingress: client.V1Ingress = self.cluster_info.get_ingress()
+            ingress: client.V1Ingress = self.cluster_info.get_ingress()
-        if opts.o.debug:
+            if opts.o.debug:
-            print(f"Deleting this ingress: {ingress}")
+                print(f"Deleting this ingress: {ingress}")
-        try:
+            try:
-            self.networking_api.delete_namespaced_ingress(
+                self.networking_api.delete_namespaced_ingress(
-                name=ingress.metadata.name, namespace=self.k8s_namespace
+                    name=ingress.metadata.name, namespace=self.k8s_namespace
-            )
+                )
-        except client.exceptions.ApiException as e:
+            except client.exceptions.ApiException as e:
-            _check_delete_exception(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]
+        if len(pods) == 0:
-        log_data = self.core_api.read_namespaced_pod_log(k8s_pod_name, namespace="default", container="test")
+            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:

stack_orchestrator/deploy/webapp/deploy_webapp_from_registry.py

@@ -26,7 +26,8 @@ from stack_orchestrator.deploy.webapp import deploy_webapp
 from stack_orchestrator.deploy.webapp.util import (LaconicRegistryClient,
                                                    build_container_image, push_container_image,
                                                    file_hash, deploy_to_k8s, publish_deployment,
-                                                   hostname_for_deployment_request, generate_hostname_for_app)
+                                                   hostname_for_deployment_request, generate_hostname_for_app,
+                                                   match_owner)
 
 
 def process_app_deployment_request(
@@ -57,19 +58,12 @@ def process_app_deployment_request(
     dns_crn = f"{dns_record_namespace}/{fqdn}"
     dns_record = laconic.get_record(dns_crn)
     if dns_record:
-        dns_record_owners = dns_record.owners
+        matched_owner = match_owner(app_deployment_request, dns_record)
-        dns_request_owners = []
+        if not matched_owner and dns_record.request:
-        if dns_record.request:
+            matched_owner = match_owner(app_deployment_request, laconic.get_record(dns_record.request, require=True))
-            prev_request = laconic.get_record(dns_record.request, require=True)
-            dns_request_owners = prev_request.owners
 
-        owner_match = None
+        if matched_owner:
-
+            print("Matched DnsRecord ownership:", matched_owner)
-        for owner in app_deployment_request.owners:
-            if owner in dns_request_owners or owner in dns_record_owners:
-                owner_match = owner
-        if owner_match:
-            print("Matched DnsRecord ownership to", owner)
         else:
             raise Exception("Unable to confirm ownership of DnsRecord %s for request %s" %
                             (dns_record.id, app_deployment_request.id))
@@ -153,7 +147,6 @@ def dump_known_requests(filename, requests):
 
 @click.command()
 @click.option("--kube-config", help="Provide a config file for a k8s deployment")
-@click.option("--kube-config", help="Provide a config file for a k8s deployment")
 @click.option("--laconic-config", help="Provide a config file for laconicd", required=True)
 @click.option("--image-registry", help="Provide a container image registry url for this k8s cluster")
 @click.option("--deployment-parent-dir", help="Create deployment directories beneath this directory", required=True)
@@ -237,9 +230,20 @@ def command(ctx, kube_config, laconic_config, image_registry, deployment_parent_
         if d.attributes.request:
             deployments_by_request[d.attributes.request] = d
 
+    # Find removal requests.
+    cancellation_requests = {}
+    removal_requests = laconic.app_deployment_removal_requests()
+    for r in removal_requests:
+        if r.attributes.request:
+            cancellation_requests[r.attributes.request] = r
+
     requests_to_execute = []
     for r in requests_by_name.values():
-        if r.id not in deployments_by_request:
+        if r.id in cancellation_requests and match_owner(cancellation_requests[r.id], r):
+            print(f"Found deployment cancellation request for {r.id} at {cancellation_requests[r.id].id}")
+        elif r.id in deployments_by_request:
+            print(f"Found satisfied request for {r.id} at {deployments_by_request[r.id].id}")
+        else:
             if r.id not in previous_requests:
                 print(f"Request {r.id} needs to processed.")
                 requests_to_execute.append(r)
@@ -247,8 +251,6 @@ def command(ctx, kube_config, laconic_config, image_registry, deployment_parent_
                 print(
                     f"Skipping unsatisfied request {r.id} because we have seen it before."
                 )
-        else:
-            print(f"Found satisfied request {r.id} at {deployments_by_request[r.id].names[0]}")
 
     print("Found %d unsatisfied request(s) to process." % len(requests_to_execute))
 

stack_orchestrator/deploy/webapp/undeploy_webapp_from_registry.py

@@ -0,0 +1,189 @@
+# Copyright ©2023 Vulcanize
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <http:#www.gnu.org/licenses/>.
+
+import json
+import os
+import shutil
+import subprocess
+import sys
+
+import click
+
+from stack_orchestrator.deploy.webapp.util import LaconicRegistryClient, match_owner
+
+
+def process_app_removal_request(ctx,
+                                laconic: LaconicRegistryClient,
+                                app_removal_request,
+                                deployment_parent_dir,
+                                delete_volumes,
+                                delete_names):
+    deployment_record = laconic.get_record(app_removal_request.attributes.deployment, require=True)
+    dns_record = laconic.get_record(deployment_record.attributes.dns, require=True)
+    deployment_dir = os.path.join(deployment_parent_dir, dns_record.attributes.name)
+
+    if not os.path.exists(deployment_dir):
+        raise Exception("Deployment directory %s does not exist." % deployment_dir)
+
+    # Check if the removal request is from the owner of the DnsRecord or deployment record.
+    matched_owner = match_owner(app_removal_request, deployment_record, dns_record)
+
+    # Or of the original deployment request.
+    if not matched_owner and deployment_record.request:
+        matched_owner = match_owner(app_removal_request, laconic.get_record(deployment_record.request, require=True))
+
+    if matched_owner:
+        print("Matched deployment ownership:", matched_owner)
+    else:
+        raise Exception("Unable to confirm ownership of deployment %s for removal request %s" %
+                        (deployment_record.id, app_removal_request.id))
+
+    # TODO(telackey): Call the function directly.  The easiest way to build the correct click context is to
+    # exec the process, but it would be better to refactor so we could just call down_operation with the
+    # necessary parameters
+    down_command = [sys.argv[0], "deployment", "--dir", deployment_dir, "down"]
+    if delete_volumes:
+        down_command.append("--delete-volumes")
+    result = subprocess.run(down_command)
+    result.check_returncode()
+
+    removal_record = {
+        "record": {
+            "type": "ApplicationDeploymentRemovalRecord",
+            "version": "1.0.0",
+            "request": app_removal_request.id,
+            "deployment": deployment_record.id,
+        }
+    }
+    laconic.publish(removal_record)
+
+    if delete_names:
+        if deployment_record.names:
+            for name in deployment_record.names:
+                laconic.delete_name(name)
+
+        if dns_record.names:
+            for name in dns_record.names:
+                laconic.delete_name(name)
+
+    if delete_volumes:
+        shutil.rmtree(deployment_dir)
+
+
+def load_known_requests(filename):
+    if filename and os.path.exists(filename):
+        return json.load(open(filename, "r"))
+    return {}
+
+
+def dump_known_requests(filename, requests):
+    if not filename:
+        return
+    known_requests = load_known_requests(filename)
+    for r in requests:
+        known_requests[r.id] = r.createTime
+    json.dump(known_requests, open(filename, "w"))
+
+
+@click.command()
+@click.option("--laconic-config", help="Provide a config file for laconicd", required=True)
+@click.option("--deployment-parent-dir", help="Create deployment directories beneath this directory", required=True)
+@click.option("--request-id", help="The ApplicationDeploymentRemovalRequest to process")
+@click.option("--discover", help="Discover and process all pending ApplicationDeploymentRemovalRequests",
+              is_flag=True, default=False)
+@click.option("--state-file", help="File to store state about previously seen requests.")
+@click.option("--only-update-state", help="Only update the state file, don't process any requests anything.", is_flag=True)
+@click.option("--delete-names/--preserve-names", help="Delete all names associated with removed deployments.", default=True)
+@click.option("--delete-volumes/--preserve-volumes", default=True, help="delete data volumes")
+@click.option("--dry-run", help="Don't do anything, just report what would be done.", is_flag=True)
+@click.pass_context
+def command(ctx, laconic_config, deployment_parent_dir,
+            request_id, discover, state_file, only_update_state,
+            delete_names, delete_volumes, dry_run):
+    if request_id and discover:
+        print("Cannot specify both --request-id and --discover", file=sys.stderr)
+        sys.exit(2)
+
+    if not request_id and not discover:
+        print("Must specify either --request-id or --discover", file=sys.stderr)
+        sys.exit(2)
+
+    if only_update_state and not state_file:
+        print("--only-update-state requires --state-file", file=sys.stderr)
+        sys.exit(2)
+
+    laconic = LaconicRegistryClient(laconic_config)
+
+    # Find deployment removal requests.
+    # single request
+    if request_id:
+        requests = [laconic.get_record(request_id, require=True)]
+        # TODO: assert record type
+    # all requests
+    elif discover:
+        requests = laconic.app_deployment_removal_requests()
+
+    if only_update_state:
+        if not dry_run:
+            dump_known_requests(state_file, requests)
+        return
+
+    previous_requests = load_known_requests(state_file)
+    requests.sort(key=lambda r: r.createTime)
+
+    # Find deployments.
+    deployments = {}
+    for d in laconic.app_deployments(all=True):
+        deployments[d.id] = d
+
+    # Find removal requests.
+    removals_by_deployment = {}
+    removals_by_request = {}
+    for r in laconic.app_deployment_removals():
+        if r.attributes.deployment:
+            # TODO: should we handle CRNs?
+            removals_by_deployment[r.attributes.deployment] = r
+
+    requests_to_execute = []
+    for r in requests:
+        if not r.attributes.deployment:
+            print(f"Skipping removal request {r.id} since it was a cancellation.")
+        elif r.id in removals_by_request:
+            print(f"Found satisfied request for {r.id} at {removals_by_request[r.id].id}")
+        elif r.attributes.deployment in removals_by_deployment:
+            print(
+                f"Found removal record for indicated deployment {r.attributes.deployment} at "
+                f"{removals_by_deployment[r.attributes.deployment].id}")
+        else:
+            if r.id not in previous_requests:
+                print(f"Request {r.id} needs to processed.")
+                requests_to_execute.append(r)
+            else:
+                print(f"Skipping unsatisfied request {r.id} because we have seen it before.")
+
+    print("Found %d unsatisfied request(s) to process." % len(requests_to_execute))
+
+    if not dry_run:
+        for r in requests_to_execute:
+            try:
+                process_app_removal_request(
+                    ctx,
+                    laconic,
+                    r,
+                    os.path.abspath(deployment_parent_dir),
+                    delete_volumes,
+                    delete_names
+                )
+            finally:
+                dump_known_requests(state_file, [r])

stack_orchestrator/deploy/webapp/util.py

@@ -49,6 +49,14 @@ def cmd(*vargs):
         raise err
 
 
+def match_owner(recordA, *records):
+    for owner in recordA.owners:
+        for otherRecord in records:
+            if owner in otherRecord.owners:
+                return owner
+    return None
+
+
 class LaconicRegistryClient:
     def __init__(self, config_file):
         self.config_file = config_file
@@ -146,11 +154,17 @@ class LaconicRegistryClient:
             raise Exception("Cannot locate record:", name_or_id)
         return None
 
-    def app_deployment_requests(self):
+    def app_deployment_requests(self, all=True):
-        return self.list_records({"type": "ApplicationDeploymentRequest"}, True)
+        return self.list_records({"type": "ApplicationDeploymentRequest"}, all)
 
-    def app_deployments(self):
+    def app_deployments(self, all=True):
-        return self.list_records({"type": "ApplicationDeploymentRecord"})
+        return self.list_records({"type": "ApplicationDeploymentRecord"}, all)
+
+    def app_deployment_removal_requests(self, all=True):
+        return self.list_records({"type": "ApplicationDeploymentRemovalRequest"}, all)
+
+    def app_deployment_removals(self, all=True):
+        return self.list_records({"type": "ApplicationDeploymentRemovalRecord"}, all)
 
     def publish(self, record, names=[]):
         tmpdir = tempfile.mkdtemp()
@@ -165,11 +179,17 @@ class LaconicRegistryClient:
                 cmd("laconic", "-c", self.config_file, "cns", "record", "publish", "--filename", record_fname)
             )["id"]
             for name in names:
-                cmd("laconic", "-c", self.config_file, "cns", "name", "set", name, new_record_id)
+                self.set_name(name, new_record_id)
             return new_record_id
         finally:
             cmd("rm", "-rf", tmpdir)
 
+    def set_name(self, name, record_id):
+        cmd("laconic", "-c", self.config_file, "cns", "name", "set", name, record_id)
+
+    def delete_name(self, name):
+        cmd("laconic", "-c", self.config_file, "cns", "name", "delete", name)
+
 
 def file_hash(filename):
     return hashlib.sha1(open(filename).read().encode()).hexdigest()
@@ -187,9 +207,11 @@ def build_container_image(app_record, tag, extra_build_args=[]):
         print(f"Cloning repository {repo} to {clone_dir} ...")
         if ref:
             # TODO: Determing branch or hash, and use depth 1 if we can.
-            result = subprocess.run(["git", "clone", repo, clone_dir])
+            git_env = dict(os.environ.copy())
-            result.check_returncode()
+            # Never prompt
-            subprocess.check_call(["git", "checkout", ref], cwd=clone_dir)
+            git_env["GIT_TERMINAL_PROMPT"] = "0"
+            subprocess.check_call(["git", "clone", repo, clone_dir], env=git_env)
+            subprocess.check_call(["git", "checkout", ref], cwd=clone_dir, env=git_env)
         else:
             result = subprocess.run(["git", "clone", "--depth", "1", repo, clone_dir])
             result.check_returncode()

stack_orchestrator/main.py

@@ -20,7 +20,10 @@ from stack_orchestrator.repos import setup_repositories
 from stack_orchestrator.build import build_containers
 from stack_orchestrator.build import build_npms
 from stack_orchestrator.build import build_webapp
-from stack_orchestrator.deploy.webapp import run_webapp, deploy_webapp, deploy_webapp_from_registry
+from stack_orchestrator.deploy.webapp import (run_webapp,
+                                              deploy_webapp,
+                                              deploy_webapp_from_registry,
+                                              undeploy_webapp_from_registry)
 from stack_orchestrator.deploy import deploy
 from stack_orchestrator import version
 from stack_orchestrator.deploy import deployment
@@ -54,6 +57,7 @@ cli.add_command(build_webapp.command, "build-webapp")
 cli.add_command(run_webapp.command, "run-webapp")
 cli.add_command(deploy_webapp.command, "deploy-webapp")
 cli.add_command(deploy_webapp_from_registry.command, "deploy-webapp-from-registry")
+cli.add_command(undeploy_webapp_from_registry.command, "undeploy-webapp-from-registry")
 cli.add_command(deploy.command, "deploy")  # deploy is an alias for deploy-system
 cli.add_command(deploy.command, "deploy-system")
 cli.add_command(deployment.command, "deployment")

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 $test_deployment_dir start
-# TODO: add a check to see if the container is up
+wait_for_pods_started
-# Sleep because k8s not up yet
-sleep 30
 # Check logs command works
+wait_for_log_output
 log_output_3=$( $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