Configure prometheus alert manager with Slack notifications

Part of [Investigate subgraph watchers lagging behind head](https://www.notion.so/Investigate-subgraph-watchers-lagging-behind-head-01b72294ca8e4f658e4c0e86b36d19e2)

Co-authored-by: Nabarun <nabarun@deepstacksoft.com>
Reviewed-on: cerc-io/stack-orchestrator#827
Co-authored-by: Prathamesh Musale <prathamesh.musale0@gmail.com>
Co-committed-by: Prathamesh Musale <prathamesh.musale0@gmail.com>

.gitea/workflows/fixturenet-eth-plugeth-arm-test.yml

@@ -9,10 +9,6 @@ on:
   schedule: # Note: coordinate with other tests to not overload runners at the same time of day
     - cron: '2 14 * * *'
 
-# Needed until we can incorporate docker startup into the executor container
-env:
-  DOCKER_HOST: unix:///var/run/dind.sock
-
 
 jobs:
   test:

.gitea/workflows/fixturenet-eth-plugeth-test.yml

@@ -9,10 +9,6 @@ on:
   schedule: # Note: coordinate with other tests to not overload runners at the same time of day
     - cron: '2 14 * * *'
 
-# Needed until we can incorporate docker startup into the executor container
-env:
-  DOCKER_HOST: unix:///var/run/dind.sock
-
 
 jobs:
   test:
@@ -41,10 +37,6 @@ 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: "Run fixturenet-eth tests"
         run: ./tests/fixturenet-eth-plugeth/run-test.sh
       - name: Notify Vulcanize Slack on CI failure

.gitea/workflows/fixturenet-eth-test.yml

@@ -7,10 +7,6 @@ on:
       - '!**'
       - '.gitea/workflows/triggers/fixturenet-eth-test'
 
-# Needed until we can incorporate docker startup into the executor container
-env:
-  DOCKER_HOST: unix:///var/run/dind.sock
-
 
 jobs:
   test:
@@ -39,10 +35,6 @@ 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: "Run fixturenet-eth tests"
         run: ./tests/fixturenet-eth/run-test.sh
       - name: Notify Vulcanize Slack on CI failure

.gitea/workflows/test-deploy.yml

@@ -10,9 +10,6 @@ on:
     paths-ignore:
       - '.gitea/workflows/triggers/*'
 
-# Needed until we can incorporate docker startup into the executor container
-env:
-  DOCKER_HOST: unix:///var/run/dind.sock
 
 jobs:
   test:
@@ -41,10 +38,6 @@ 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: "Run deploy tests"
         run: ./tests/deploy/run-deploy-test.sh
       - name: Notify Vulcanize Slack on CI failure

.gitea/workflows/test-external-stack.yml

@@ -0,0 +1,58 @@
+name: External Stack Test
+
+on:
+  push:
+    branches: '*'
+    paths:
+      - '!**'
+      - '.gitea/workflows/triggers/test-external-stack'
+      - '.gitea/workflows/test-external-stack.yml'
+      - 'tests/external-stack/run-test.sh'
+  schedule: # Note: coordinate with other tests to not overload runners at the same time of day
+    - cron: '8 19 * * *'
+
+jobs:
+  test:
+    name: "Run external stack test suite"
+    runs-on: ubuntu-latest
+    steps:
+      - name: "Clone project repository"
+        uses: actions/checkout@v3
+      # At present the stock setup-python action fails on Linux/aarch64
+      # Conditional steps below workaroud this by using deadsnakes for that case only
+      - name: "Install Python for ARM on Linux"
+        if: ${{ runner.arch == 'arm64' && runner.os == 'Linux' }}
+        uses: deadsnakes/action@v3.0.1
+        with:
+          python-version: '3.8'
+      - name: "Install Python cases other than ARM on Linux"
+        if: ${{ ! (runner.arch == 'arm64' && runner.os == 'Linux') }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.8'
+      - name: "Print Python version"
+        run: python3 --version
+      - name: "Install shiv"
+        run: pip install shiv
+      - name: "Generate build version file"
+        run: ./scripts/create_build_tag_file.sh
+      - name: "Build local shiv package"
+        run: ./scripts/build_shiv_package.sh
+      - name: "Run external stack tests"
+        run: ./tests/external-stack/run-test.sh
+      - name: Notify Vulcanize Slack on CI failure
+        if: ${{ always() && github.ref_name == 'main' }}
+        uses: ravsamhq/notify-slack-action@v2
+        with:
+          status: ${{ job.status }}
+          notify_when: 'failure'
+        env:
+          SLACK_WEBHOOK_URL: ${{ secrets.VULCANIZE_SLACK_CI_ALERTS }}
+      - name: Notify DeepStack Slack on CI failure
+        if: ${{ always() && github.ref_name == 'main' }}
+        uses: ravsamhq/notify-slack-action@v2
+        with:
+          status: ${{ job.status }}
+          notify_when: 'failure'
+        env:
+          SLACK_WEBHOOK_URL: ${{ secrets.DEEPSTACK_SLACK_CI_ALERTS }}

.gitea/workflows/test-webapp.yml

@@ -10,10 +10,6 @@ on:
     paths-ignore:
       - '.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 webapp test suite"
@@ -43,10 +39,6 @@ jobs:
         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 &
-          sleep 5
       - name: "Run webapp tests"
         run: ./tests/webapp-test/run-webapp-test.sh
       - name: Notify Vulcanize Slack on CI failure

.gitea/workflows/test.yml

@@ -10,9 +10,6 @@ on:
     paths-ignore:
       - '.gitea/workflows/triggers/*'
 
-# Needed until we can incorporate docker startup into the executor container
-env:
-  DOCKER_HOST: unix:///var/run/dind.sock
 
 jobs:
   test:
@@ -41,10 +38,6 @@ 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: "Run smoke tests"
         run: ./tests/smoke-test/run-smoke-test.sh
       - name: Notify Vulcanize Slack on CI failure

.gitea/workflows/triggers/test-external-stack

@@ -0,0 +1,2 @@
+Change this file to trigger running the external-stack CI job
+trigger

stack_orchestrator/build/build_containers.py

@@ -71,7 +71,7 @@ def process_container(build_context: BuildContext) -> bool:
 
     # Check if this is in an external stack
     if stack_is_external(build_context.stack):
-        container_parent_dir = Path(build_context.stack).joinpath("container-build")
+        container_parent_dir = Path(build_context.stack).parent.parent.joinpath("container-build")
         temp_build_dir = container_parent_dir.joinpath(build_context.container.replace("/", "-"))
         temp_build_script_filename = temp_build_dir.joinpath("build.sh")
         # Now check if the container exists in the external stack.

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

@@ -6,10 +6,16 @@ services:
     restart: always
     environment:
       GF_SERVER_ROOT_URL: ${GF_SERVER_ROOT_URL}
+      CERC_GRAFANA_ALERTS_SUBGRAPH_IDS: ${CERC_GRAFANA_ALERTS_SUBGRAPH_IDS}
     volumes:
       - ../config/monitoring/grafana/provisioning:/etc/grafana/provisioning
       - ../config/monitoring/grafana/dashboards:/etc/grafana/dashboards
+      - ../config/monitoring/update-grafana-alerts-config.sh:/update-grafana-alerts-config.sh
       - grafana_storage:/var/lib/grafana
+    user: root
+    entrypoint: ["bash", "-c"]
+    command: |
+      "/update-grafana-alerts-config.sh && /run.sh"
     ports:
       - "3000"
     healthcheck:

stack_orchestrator/data/compose/docker-compose-graph-node.yml

@@ -16,8 +16,12 @@ services:
       postgres_pass: password
       postgres_db: graph-node
       ethereum: ${ETH_NETWORKS:-lotus-fixturenet:http://lotus-node-1:1234/rpc/v1}
+      # Env varaibles reference: https://git.vdb.to/cerc-io/graph-node/src/branch/master/docs/environment-variables.md
       GRAPH_LOG: debug
       ETHEREUM_REORG_THRESHOLD: 3
+      GRAPH_ETHEREUM_JSON_RPC_TIMEOUT: ${GRAPH_ETHEREUM_JSON_RPC_TIMEOUT:-180}
+      GRAPH_ETHEREUM_REQUEST_RETRIES: ${GRAPH_ETHEREUM_REQUEST_RETRIES:-10}
+      GRAPH_ETHEREUM_MAX_BLOCK_RANGE_SIZE: ${GRAPH_ETHEREUM_MAX_BLOCK_RANGE_SIZE:-2000}
     entrypoint: ["bash", "-c"]
     # Wait for ETH RPC endpoint to be up when running with fixturenet-lotus
     command: |

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

@@ -18,6 +18,14 @@ services:
     extra_hosts:
       - "host.docker.internal:host-gateway"
 
+  alert-manager:
+    image: prom/alertmanager
+    volumes:
+      - ../config/monitoring/alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml
+      - alertmanager_data:/data
+    ports:
+      - "9093"
+
   blackbox:
     image: prom/blackbox-exporter:latest
     restart: always
@@ -55,3 +63,4 @@ services:
 
 volumes:
   prometheus_data:
+  alertmanager_data:

stack_orchestrator/data/compose/docker-compose-watcher-ajna.yml

@@ -29,7 +29,7 @@ services:
     image: cerc/watcher-ajna:local
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_ETH_RPC_ENDPOINT: ${CERC_ETH_RPC_ENDPOINT}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
     command: ["bash", "./start-job-runner.sh"]
     volumes:
       - ../config/watcher-ajna/watcher-config-template.toml:/app/environments/watcher-config-template.toml
@@ -37,7 +37,7 @@ services:
     ports:
       - "9000"
     healthcheck:
-      test: ["CMD", "nc", "-v", "localhost", "9000"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "9000"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -55,7 +55,7 @@ services:
     image: cerc/watcher-ajna:local
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_ETH_RPC_ENDPOINT: ${CERC_ETH_RPC_ENDPOINT}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
     command: ["bash", "./start-server.sh"]
     volumes:
       - ../config/watcher-ajna/watcher-config-template.toml:/app/environments/watcher-config-template.toml
@@ -64,7 +64,7 @@ services:
       - "3008"
       - "9001"
     healthcheck:
-      test: ["CMD", "nc", "-v", "localhost", "3008"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "3008"]
       interval: 20s
       timeout: 5s
       retries: 15

stack_orchestrator/data/compose/docker-compose-watcher-azimuth.yml

@@ -32,8 +32,8 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
       CERC_HISTORICAL_BLOCK_RANGE: 500
       CONTRACT_ADDRESS: 0x223c067F8CF28ae173EE5CafEa60cA44C335fecB
       CONTRACT_NAME: Azimuth
@@ -47,7 +47,7 @@ services:
     ports:
       - "9000"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "9000"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "9000"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -66,8 +66,8 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
     working_dir: /app/packages/azimuth-watcher
     command: "./start-server.sh"
     volumes:
@@ -77,7 +77,7 @@ services:
     ports:
       - "3001"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "3001"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "3001"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -94,8 +94,8 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
       CONTRACT_ADDRESS: 0x325f68d32BdEe6Ed86E7235ff2480e2A433D6189
       CONTRACT_NAME: Censures
       STARTING_BLOCK: 6784954
@@ -108,7 +108,7 @@ services:
     ports:
       - "9002"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "9002"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "9002"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -127,8 +127,8 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
     working_dir: /app/packages/censures-watcher
     command: "./start-server.sh"
     volumes:
@@ -138,7 +138,7 @@ services:
     ports:
       - "3002"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "3002"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "3002"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -155,8 +155,8 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
       CONTRACT_ADDRESS: 0xe7e7f69b34D7d9Bd8d61Fb22C33b22708947971A
       CONTRACT_NAME: Claims
       STARTING_BLOCK: 6784941
@@ -169,7 +169,7 @@ services:
     ports:
       - "9004"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "9004"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "9004"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -188,8 +188,8 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
     working_dir: /app/packages/claims-watcher
     command: "./start-server.sh"
     volumes:
@@ -199,7 +199,7 @@ services:
     ports:
       - "3003"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "3003"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "3003"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -216,8 +216,8 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
       CONTRACT_ADDRESS: 0x8C241098C3D3498Fe1261421633FD57986D74AeA
       CONTRACT_NAME: ConditionalStarRelease
       STARTING_BLOCK: 6828004
@@ -230,7 +230,7 @@ services:
     ports:
       - "9006"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "9006"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "9006"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -249,8 +249,8 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
     working_dir: /app/packages/conditional-star-release-watcher
     command: "./start-server.sh"
     volumes:
@@ -260,7 +260,7 @@ services:
     ports:
       - "3004"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "3004"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "3004"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -277,8 +277,8 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
       CONTRACT_ADDRESS: 0xf6b461fE1aD4bd2ce25B23Fe0aff2ac19B3dFA76
       CONTRACT_NAME: DelegatedSending
       STARTING_BLOCK: 6784956
@@ -291,7 +291,7 @@ services:
     ports:
       - "9008"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "9008"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "9008"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -310,8 +310,8 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
     working_dir: /app/packages/delegated-sending-watcher
     command: "./start-server.sh"
     volumes:
@@ -321,7 +321,7 @@ services:
     ports:
       - "3005"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "3005"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "3005"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -338,8 +338,8 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
       CONTRACT_ADDRESS: 0x33EeCbf908478C10614626A9D304bfe18B78DD73
       CONTRACT_NAME: Ecliptic
       STARTING_BLOCK: 13692129
@@ -352,7 +352,7 @@ services:
     ports:
       - "9010"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "9010"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "9010"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -371,8 +371,8 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
     working_dir: /app/packages/ecliptic-watcher
     command: "./start-server.sh"
     volumes:
@@ -382,7 +382,7 @@ services:
     ports:
       - "3006"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "3006"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "3006"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -399,8 +399,8 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
       CONTRACT_ADDRESS: 0x86cd9cd0992F04231751E3761De45cEceA5d1801
       CONTRACT_NAME: LinearStarRelease
       STARTING_BLOCK: 6784943
@@ -413,7 +413,7 @@ services:
     ports:
       - "9012"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "9012"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "9012"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -432,8 +432,8 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
     working_dir: /app/packages/linear-star-release-watcher
     command: "./start-server.sh"
     volumes:
@@ -443,7 +443,7 @@ services:
     ports:
       - "3007"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "3007"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "3007"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -460,8 +460,8 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
       CONTRACT_ADDRESS: 0x7fEcaB617c868Bb5996d99D95200D2Fa708218e4
       CONTRACT_NAME: Polls
       STARTING_BLOCK: 6784912
@@ -474,7 +474,7 @@ services:
     ports:
       - "9014"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "9014"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "9014"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -493,8 +493,8 @@ services:
         condition: service_healthy
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_IPLD_ETH_RPC: ${CERC_IPLD_ETH_RPC}
-      CERC_IPLD_ETH_GQL: ${CERC_IPLD_ETH_GQL}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
+      CERC_IPLD_ETH_GQL_ENDPOINT: ${CERC_IPLD_ETH_GQL_ENDPOINT}
     working_dir: /app/packages/polls-watcher
     command: "./start-server.sh"
     volumes:
@@ -504,7 +504,7 @@ services:
     ports:
       - "3008"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "3008"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "3008"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -542,7 +542,7 @@ services:
     ports:
       - "0.0.0.0:4000:4000"
     healthcheck:
-      test: ["CMD", "nc", "-vz", "localhost", "4000"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "4000"]
       interval: 20s
       timeout: 5s
       retries: 15

stack_orchestrator/data/compose/docker-compose-watcher-merkl-sushiswap-v3.yml

@@ -29,7 +29,7 @@ services:
     image: cerc/watcher-merkl-sushiswap-v3:local
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_ETH_RPC_ENDPOINT: ${CERC_ETH_RPC_ENDPOINT}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
     command: ["bash", "./start-job-runner.sh"]
     volumes:
       - ../config/watcher-merkl-sushiswap-v3/watcher-config-template.toml:/app/environments/watcher-config-template.toml
@@ -37,7 +37,7 @@ services:
     ports:
       - "9002:9000"
     healthcheck:
-      test: ["CMD", "nc", "-v", "localhost", "9000"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "9000"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -55,7 +55,7 @@ services:
     image: cerc/watcher-merkl-sushiswap-v3:local
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_ETH_RPC_ENDPOINT: ${CERC_ETH_RPC_ENDPOINT}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
     command: ["bash", "./start-server.sh"]
     volumes:
       - ../config/watcher-merkl-sushiswap-v3/watcher-config-template.toml:/app/environments/watcher-config-template.toml
@@ -64,7 +64,7 @@ services:
       - "127.0.0.1:3007:3008"
       - "9003:9001"
     healthcheck:
-      test: ["CMD", "nc", "-v", "localhost", "3008"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "3008"]
       interval: 20s
       timeout: 5s
       retries: 15

stack_orchestrator/data/compose/docker-compose-watcher-sushiswap-v3.yml

@@ -29,7 +29,7 @@ services:
     image: cerc/watcher-sushiswap-v3:local
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_ETH_RPC_ENDPOINT: ${CERC_ETH_RPC_ENDPOINT}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
     command: ["bash", "./start-job-runner.sh"]
     volumes:
       - ../config/watcher-sushiswap-v3/watcher-config-template.toml:/app/environments/watcher-config-template.toml
@@ -37,7 +37,7 @@ services:
     ports:
       - "9000:9000"
     healthcheck:
-      test: ["CMD", "nc", "-v", "localhost", "9000"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "9000"]
       interval: 20s
       timeout: 5s
       retries: 15
@@ -55,7 +55,7 @@ services:
     image: cerc/watcher-sushiswap-v3:local
     environment:
       CERC_SCRIPT_DEBUG: ${CERC_SCRIPT_DEBUG}
-      CERC_ETH_RPC_ENDPOINT: ${CERC_ETH_RPC_ENDPOINT}
+      CERC_ETH_RPC_ENDPOINTS: ${CERC_ETH_RPC_ENDPOINTS}
     command: ["bash", "./start-server.sh"]
     volumes:
       - ../config/watcher-sushiswap-v3/watcher-config-template.toml:/app/environments/watcher-config-template.toml
@@ -64,7 +64,7 @@ services:
       - "127.0.0.1:3008:3008"
       - "9001:9001"
     healthcheck:
-      test: ["CMD", "nc", "-v", "localhost", "3008"]
+      test: ["CMD", "nc", "-vz", "127.0.0.1", "3008"]
       interval: 20s
       timeout: 5s
       retries: 15

stack_orchestrator/data/config/monitoring/alertmanager/alertmanager.yml

@@ -0,0 +1,10 @@
+route:
+  receiver: 'slack'
+  # group_by: [ alertname ]
+
+receivers:
+  - name: 'slack'
+    slack_configs:
+      - send_resolved: true
+        api_url: <YOUR_SLACK_WEBHOOK_URL>
+        channel: <YOUR_SLACK_CHANNEL>

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

@@ -1,147 +0,0 @@
-apiVersion: 1
-groups:
-    - orgId: 1
-      name: blackbox
-      folder: BlackboxAlerts
-      interval: 30s
-      rules:
-        # Azimuth Gateway endpoint
-        - uid: azimuth_gateway
-          title: azimuth_gateway_endpoint_tracking
-          condition: condition
-          data:
-            - refId: probe
-              relativeTimeRange:
-                from: 600
-                to: 0
-              datasourceUid: PBFA97CFB590B2093
-              model:
-                editorMode: code
-                expr: probe_success{destination="azimuth_gateway"}
-                instant: true
-                intervalMs: 1000
-                legendFormat: __auto
-                maxDataPoints: 43200
-                range: false
-                refId: probe
-            - refId: http_status_code
-              relativeTimeRange:
-                from: 600
-                to: 0
-              datasourceUid: PBFA97CFB590B2093
-              model:
-                editorMode: code
-                expr: probe_http_status_code{destination="azimuth_gateway"}
-                instant: true
-                intervalMs: 1000
-                legendFormat: __auto
-                maxDataPoints: 43200
-                range: false
-                refId: http_status_code
-            - 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: ${probe} != 1 ||  ${http_status_code} != 200
-                intervalMs: 1000
-                maxDataPoints: 43200
-                refId: condition
-                type: math
-          noDataState: Alerting
-          execErrState: Alerting
-          for: 5m
-          annotations:
-            summary: Probe failed for Azimuth gateway endpoint
-          labels:
-            probe_success: '{{ index $values "probe" }}'
-          isPaused: false
-        # Laconicd GQL endpoint
-        - uid: laconicd_gql
-          title: laconicd_gql_endpoint_tracking
-          condition: condition
-          data:
-            - refId: probe
-              relativeTimeRange:
-                from: 600
-                to: 0
-              datasourceUid: PBFA97CFB590B2093
-              model:
-                editorMode: code
-                expr: probe_success{destination="laconicd_gql"}
-                instant: true
-                intervalMs: 1000
-                legendFormat: __auto
-                maxDataPoints: 43200
-                range: false
-                refId: probe
-            - refId: http_status_code
-              relativeTimeRange:
-                from: 600
-                to: 0
-              datasourceUid: PBFA97CFB590B2093
-              model:
-                editorMode: code
-                expr: probe_http_status_code{destination="laconicd_gql"}
-                instant: true
-                intervalMs: 1000
-                legendFormat: __auto
-                maxDataPoints: 43200
-                range: false
-                refId: http_status_code
-            - 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: ${probe} != 1 ||  ${http_status_code} != 200
-                intervalMs: 1000
-                maxDataPoints: 43200
-                refId: condition
-                type: math
-          noDataState: Alerting
-          execErrState: Alerting
-          for: 5m
-          annotations:
-            summary: Probe failed for Laconicd GQL endpoint
-          labels:
-            probe_success: '{{ index $values "probe" }}'
-          isPaused: false

stack_orchestrator/data/config/monitoring/grafana/dashboards/laconicd-dashboard.json

@@ -49,7 +49,7 @@
       },
       "gridPos": {
         "h": 3,
-        "w": 4,
+        "w": 3,
         "x": 0,
         "y": 0
       },

stack_orchestrator/data/config/monitoring/grafana/dashboards/watcher-dashboard.json

@@ -18,7 +18,7 @@
   "editable": true,
   "fiscalYearStartMonth": 0,
   "graphTooltip": 0,
-  "id": 4,
+  "id": 6,
   "links": [
     {
       "asDropdown": false,
@@ -55,7 +55,7 @@
         "x": 0,
         "y": 0
       },
-      "id": 1,
+      "id": 29,
       "panels": [
         {
           "datasource": {
@@ -103,7 +103,7 @@
             "textMode": "auto",
             "wideLayout": true
           },
-          "pluginVersion": "10.2.2",
+          "pluginVersion": "10.2.3",
           "targets": [
             {
               "datasource": {
@@ -173,7 +173,7 @@
             "textMode": "auto",
             "wideLayout": true
           },
-          "pluginVersion": "10.2.2",
+          "pluginVersion": "10.2.3",
           "targets": [
             {
               "datasource": {
@@ -242,7 +242,7 @@
             "textMode": "auto",
             "wideLayout": true
           },
-          "pluginVersion": "10.2.2",
+          "pluginVersion": "10.2.3",
           "targets": [
             {
               "datasource": {
@@ -438,7 +438,7 @@
             "textMode": "auto",
             "wideLayout": true
           },
-          "pluginVersion": "10.2.2",
+          "pluginVersion": "10.2.3",
           "targets": [
             {
               "datasource": {
@@ -518,7 +518,7 @@
             "textMode": "auto",
             "wideLayout": true
           },
-          "pluginVersion": "10.2.2",
+          "pluginVersion": "10.2.3",
           "targets": [
             {
               "datasource": {
@@ -629,7 +629,7 @@
             "textMode": "auto",
             "wideLayout": true
           },
-          "pluginVersion": "10.2.2",
+          "pluginVersion": "10.2.3",
           "targets": [
             {
               "datasource": {
@@ -730,7 +730,7 @@
             "textMode": "auto",
             "wideLayout": true
           },
-          "pluginVersion": "10.2.2",
+          "pluginVersion": "10.2.3",
           "targets": [
             {
               "datasource": {
@@ -854,7 +854,7 @@
             "textMode": "auto",
             "wideLayout": true
           },
-          "pluginVersion": "10.2.2",
+          "pluginVersion": "10.2.3",
           "targets": [
             {
               "datasource": {
@@ -1025,7 +1025,7 @@
             "textMode": "auto",
             "wideLayout": true
           },
-          "pluginVersion": "10.2.2",
+          "pluginVersion": "10.2.3",
           "targets": [
             {
               "datasource": {
@@ -1111,7 +1111,7 @@
             "textMode": "auto",
             "wideLayout": true
           },
-          "pluginVersion": "10.2.2",
+          "pluginVersion": "10.2.3",
           "targets": [
             {
               "datasource": {
@@ -1146,6 +1146,230 @@
           "title": "DB size (MB)",
           "type": "stat"
         },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "PBFA97CFB590B2093"
+          },
+          "description": "",
+          "fieldConfig": {
+            "defaults": {
+              "color": {
+                "mode": "thresholds"
+              },
+              "custom": {
+                "axisBorderShow": false,
+                "axisCenteredZero": false,
+                "axisColorMode": "text",
+                "axisLabel": "",
+                "axisPlacement": "auto",
+                "barAlignment": 0,
+                "drawStyle": "line",
+                "fillOpacity": 0,
+                "gradientMode": "none",
+                "hideFrom": {
+                  "legend": false,
+                  "tooltip": false,
+                  "viz": false
+                },
+                "insertNulls": false,
+                "lineInterpolation": "linear",
+                "lineWidth": 1,
+                "pointSize": 5,
+                "scaleDistribution": {
+                  "type": "linear"
+                },
+                "showPoints": "auto",
+                "spanNulls": false,
+                "stacking": {
+                  "group": "A",
+                  "mode": "none"
+                },
+                "thresholdsStyle": {
+                  "mode": "off"
+                }
+              },
+              "mappings": [],
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {
+                    "color": "dark-green",
+                    "value": null
+                  },
+                  {
+                    "color": "dark-orange",
+                    "value": 8
+                  },
+                  {
+                    "color": "dark-red",
+                    "value": 16
+                  }
+                ]
+              }
+            },
+            "overrides": [
+              {
+                "matcher": {
+                  "id": "byName",
+                  "options": "diff_external"
+                },
+                "properties": [
+                  {
+                    "id": "color",
+                    "value": {
+                      "mode": "thresholds",
+                      "seriesBy": "last"
+                    }
+                  }
+                ]
+              },
+              {
+                "matcher": {
+                  "id": "byName",
+                  "options": "diff_external"
+                },
+                "properties": [
+                  {
+                    "id": "thresholds",
+                    "value": {
+                      "mode": "absolute",
+                      "steps": [
+                        {
+                          "color": "green",
+                          "value": null
+                        },
+                        {
+                          "color": "orange",
+                          "value": 8
+                        },
+                        {
+                          "color": "red",
+                          "value": 16
+                        }
+                      ]
+                    }
+                  }
+                ]
+              }
+            ]
+          },
+          "gridPos": {
+            "h": 6,
+            "w": 12,
+            "x": 0,
+            "y": 12
+          },
+          "id": 33,
+          "options": {
+            "legend": {
+              "calcs": [],
+              "displayMode": "list",
+              "placement": "bottom",
+              "showLegend": true
+            },
+            "tooltip": {
+              "mode": "single",
+              "sort": "none"
+            }
+          },
+          "pluginVersion": "10.2.3",
+          "targets": [
+            {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "PBFA97CFB590B2093"
+              },
+              "disableTextWrap": false,
+              "editorMode": "code",
+              "expr": "latest_upstream_block_number{job=~\"$job\", instance=~\"$watcher\"}",
+              "fullMetaSearch": false,
+              "hide": false,
+              "includeNullMetadata": true,
+              "instant": false,
+              "legendFormat": "{{__name__}}",
+              "range": true,
+              "refId": "A",
+              "useBackend": false
+            },
+            {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "PBFA97CFB590B2093"
+              },
+              "editorMode": "code",
+              "expr": "sync_status_block_number{job=~\"$job\", instance=~\"$watcher\", kind=\"latest_indexed\"}",
+              "hide": false,
+              "instant": false,
+              "legendFormat": "{{__name__}}",
+              "range": true,
+              "refId": "B"
+            },
+            {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "PBFA97CFB590B2093"
+              },
+              "editorMode": "code",
+              "expr": "latest_block_number{job=\"chain_heads\", chain=\"$target_chain\"}",
+              "hide": false,
+              "instant": false,
+              "legendFormat": "{{__name__}}",
+              "range": true,
+              "refId": "C"
+            }
+          ],
+          "title": "diff",
+          "transformations": [
+            {
+              "id": "calculateField",
+              "options": {
+                "alias": "diff_upstream",
+                "binary": {
+                  "left": "latest_upstream_block_number",
+                  "operator": "-",
+                  "right": "sync_status_block_number"
+                },
+                "mode": "binary",
+                "reduce": {
+                  "reducer": "sum"
+                },
+                "replaceFields": false
+              }
+            },
+            {
+              "id": "calculateField",
+              "options": {
+                "alias": "diff_external",
+                "binary": {
+                  "left": "latest_block_number",
+                  "operator": "-",
+                  "right": "sync_status_block_number"
+                },
+                "mode": "binary",
+                "reduce": {
+                  "reducer": "sum"
+                },
+                "replaceFields": false
+              }
+            },
+            {
+              "id": "organize",
+              "options": {
+                "excludeByName": {
+                  "Time": false,
+                  "latest_block_number": true,
+                  "latest_upstream_block_number": true,
+                  "sync_status_block_number": true
+                },
+                "includeByName": {},
+                "indexByName": {},
+                "renameByName": {}
+              }
+            }
+          ],
+          "type": "timeseries"
+        },
         {
           "datasource": {
             "type": "prometheus",
@@ -1208,8 +1432,8 @@
           },
           "gridPos": {
             "h": 6,
-            "w": 12,
-            "x": 0,
+            "w": 6,
+            "x": 12,
             "y": 12
           },
           "id": 5,
@@ -1310,8 +1534,8 @@
           },
           "gridPos": {
             "h": 6,
-            "w": 12,
-            "x": 12,
+            "w": 6,
+            "x": 18,
             "y": 12
           },
           "id": 15,
@@ -1350,6 +1574,436 @@
           "title": "Num event-processing jobs",
           "type": "timeseries"
         },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "PBFA97CFB590B2093"
+          },
+          "description": "Total number of failed ETH RPC requests by method and provider endpoint ",
+          "fieldConfig": {
+            "defaults": {
+              "color": {
+                "mode": "palette-classic"
+              },
+              "custom": {
+                "axisBorderShow": false,
+                "axisCenteredZero": false,
+                "axisColorMode": "text",
+                "axisLabel": "",
+                "axisPlacement": "auto",
+                "barAlignment": 0,
+                "drawStyle": "line",
+                "fillOpacity": 0,
+                "gradientMode": "none",
+                "hideFrom": {
+                  "legend": false,
+                  "tooltip": false,
+                  "viz": false
+                },
+                "insertNulls": false,
+                "lineInterpolation": "linear",
+                "lineWidth": 1,
+                "pointSize": 5,
+                "scaleDistribution": {
+                  "type": "linear"
+                },
+                "showPoints": "auto",
+                "spanNulls": false,
+                "stacking": {
+                  "group": "A",
+                  "mode": "none"
+                },
+                "thresholdsStyle": {
+                  "mode": "off"
+                }
+              },
+              "mappings": [],
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {
+                    "color": "green",
+                    "value": null
+                  }
+                ]
+              }
+            },
+            "overrides": []
+          },
+          "gridPos": {
+            "h": 7,
+            "w": 12,
+            "x": 0,
+            "y": 18
+          },
+          "id": 28,
+          "options": {
+            "legend": {
+              "calcs": [],
+              "displayMode": "list",
+              "placement": "bottom",
+              "showLegend": true
+            },
+            "tooltip": {
+              "mode": "single",
+              "sort": "none"
+            }
+          },
+          "pluginVersion": "10.2.3",
+          "targets": [
+            {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "PBFA97CFB590B2093"
+              },
+              "disableTextWrap": false,
+              "editorMode": "code",
+              "exemplar": false,
+              "expr": "watcher_eth_rpc_errors{job=~\"$job\", instance=~\"$watcher\"}",
+              "format": "time_series",
+              "fullMetaSearch": false,
+              "includeNullMetadata": true,
+              "instant": false,
+              "legendFormat": "{{method}}, {{provider}}",
+              "range": true,
+              "refId": "A",
+              "useBackend": false
+            }
+          ],
+          "title": "ETH RPC request failures",
+          "type": "timeseries"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "PBFA97CFB590B2093"
+          },
+          "description": "Time taken by last ETH RPC requests by method and provider endpoint",
+          "fieldConfig": {
+            "defaults": {
+              "color": {
+                "mode": "palette-classic"
+              },
+              "custom": {
+                "axisBorderShow": false,
+                "axisCenteredZero": false,
+                "axisColorMode": "text",
+                "axisLabel": "",
+                "axisPlacement": "auto",
+                "barAlignment": 0,
+                "drawStyle": "line",
+                "fillOpacity": 0,
+                "gradientMode": "none",
+                "hideFrom": {
+                  "legend": false,
+                  "tooltip": false,
+                  "viz": false
+                },
+                "insertNulls": false,
+                "lineInterpolation": "linear",
+                "lineStyle": {
+                  "fill": "solid"
+                },
+                "lineWidth": 1,
+                "pointSize": 5,
+                "scaleDistribution": {
+                  "type": "linear"
+                },
+                "showPoints": "auto",
+                "spanNulls": false,
+                "stacking": {
+                  "group": "A",
+                  "mode": "none"
+                },
+                "thresholdsStyle": {
+                  "mode": "off"
+                }
+              },
+              "mappings": [],
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {
+                    "color": "green",
+                    "value": null
+                  }
+                ]
+              },
+              "unit": "s"
+            },
+            "overrides": []
+          },
+          "gridPos": {
+            "h": 7,
+            "w": 12,
+            "x": 12,
+            "y": 18
+          },
+          "id": 26,
+          "options": {
+            "legend": {
+              "calcs": [],
+              "displayMode": "list",
+              "placement": "bottom",
+              "showLegend": true
+            },
+            "tooltip": {
+              "mode": "single",
+              "sort": "none"
+            }
+          },
+          "targets": [
+            {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "PBFA97CFB590B2093"
+              },
+              "editorMode": "code",
+              "expr": "watcher_eth_rpc_request_duration{job=~\"$job\", instance=~\"$watcher\"}",
+              "instant": false,
+              "legendFormat": "{{method}}, {{provider}}",
+              "range": true,
+              "refId": "A"
+            }
+          ],
+          "title": "ETH RPC request durations",
+          "type": "timeseries"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "PBFA97CFB590B2093"
+          },
+          "description": "Total number of failed ETH RPC requests by method and provider endpoint  (across all watchers)",
+          "fieldConfig": {
+            "defaults": {
+              "color": {
+                "mode": "palette-classic"
+              },
+              "custom": {
+                "axisBorderShow": false,
+                "axisCenteredZero": false,
+                "axisColorMode": "text",
+                "axisLabel": "",
+                "axisPlacement": "auto",
+                "barAlignment": 0,
+                "drawStyle": "line",
+                "fillOpacity": 0,
+                "gradientMode": "none",
+                "hideFrom": {
+                  "legend": false,
+                  "tooltip": false,
+                  "viz": false
+                },
+                "insertNulls": false,
+                "lineInterpolation": "linear",
+                "lineWidth": 1,
+                "pointSize": 5,
+                "scaleDistribution": {
+                  "type": "linear"
+                },
+                "showPoints": "auto",
+                "spanNulls": false,
+                "stacking": {
+                  "group": "A",
+                  "mode": "none"
+                },
+                "thresholdsStyle": {
+                  "mode": "off"
+                }
+              },
+              "mappings": [],
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {
+                    "color": "green",
+                    "value": null
+                  }
+                ]
+              }
+            },
+            "overrides": []
+          },
+          "gridPos": {
+            "h": 7,
+            "w": 12,
+            "x": 0,
+            "y": 25
+          },
+          "id": 30,
+          "options": {
+            "legend": {
+              "calcs": [],
+              "displayMode": "list",
+              "placement": "bottom",
+              "showLegend": true
+            },
+            "tooltip": {
+              "mode": "single",
+              "sort": "none"
+            }
+          },
+          "pluginVersion": "10.2.3",
+          "targets": [
+            {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "PBFA97CFB590B2093"
+              },
+              "disableTextWrap": false,
+              "editorMode": "code",
+              "exemplar": false,
+              "expr": "sum by (method, provider) (watcher_eth_rpc_errors{chain=\"$target_chain\"})",
+              "format": "time_series",
+              "fullMetaSearch": false,
+              "includeNullMetadata": true,
+              "instant": false,
+              "legendFormat": "{{method}}, {{provider}}",
+              "range": true,
+              "refId": "A",
+              "useBackend": false
+            }
+          ],
+          "title": "Total ETH RPC request failures (across all watchers)",
+          "type": "timeseries"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "PBFA97CFB590B2093"
+          },
+          "description": "Configured upstream ETH RPC endpoints",
+          "fieldConfig": {
+            "defaults": {
+              "color": {
+                "fixedColor": "blue",
+                "mode": "palette-classic"
+              },
+              "custom": {
+                "align": "auto",
+                "cellOptions": {
+                  "type": "auto"
+                },
+                "filterable": false,
+                "inspect": false
+              },
+              "mappings": [
+                {
+                  "options": {
+                    "0": {
+                      "color": "red",
+                      "index": 0,
+                      "text": "inactive"
+                    },
+                    "1": {
+                      "color": "green",
+                      "index": 1,
+                      "text": "active"
+                    }
+                  },
+                  "type": "value"
+                }
+              ],
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {
+                    "color": "blue",
+                    "value": null
+                  }
+                ]
+              }
+            },
+            "overrides": [
+              {
+                "matcher": {
+                  "id": "byName",
+                  "options": "status"
+                },
+                "properties": [
+                  {
+                    "id": "custom.cellOptions",
+                    "value": {
+                      "type": "color-text"
+                    }
+                  }
+                ]
+              }
+            ]
+          },
+          "gridPos": {
+            "h": 7,
+            "w": 12,
+            "x": 12,
+            "y": 25
+          },
+          "id": 32,
+          "options": {
+            "cellHeight": "sm",
+            "footer": {
+              "countRows": false,
+              "enablePagination": false,
+              "fields": "",
+              "reducer": [
+                "sum"
+              ],
+              "show": false
+            },
+            "frameIndex": 0,
+            "showHeader": true,
+            "sortBy": [
+              {
+                "desc": true,
+                "displayName": "status"
+              }
+            ]
+          },
+          "pluginVersion": "10.2.3",
+          "targets": [
+            {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "PBFA97CFB590B2093"
+              },
+              "editorMode": "code",
+              "exemplar": false,
+              "expr": "watcher_config_upstream_endpoints{job=~\"$job\", instance=~\"$watcher\"}",
+              "format": "table",
+              "instant": true,
+              "legendFormat": "__auto",
+              "range": false,
+              "refId": "A"
+            }
+          ],
+          "title": "Configured upstream endpoints",
+          "transformations": [
+            {
+              "id": "labelsToFields",
+              "options": {
+                "mode": "columns"
+              }
+            },
+            {
+              "id": "organize",
+              "options": {
+                "excludeByName": {
+                  "Time": true,
+                  "__name__": true,
+                  "chain": true,
+                  "instance": true,
+                  "job": true
+                },
+                "includeByName": {},
+                "indexByName": {},
+                "renameByName": {
+                  "Value": "status"
+                }
+              }
+            }
+          ],
+          "type": "table"
+        },
         {
           "datasource": {
             "type": "prometheus",
@@ -1377,7 +2031,8 @@
                 "mode": "absolute",
                 "steps": [
                   {
-                    "color": "green"
+                    "color": "green",
+                    "value": null
                   }
                 ]
               }
@@ -1388,7 +2043,7 @@
             "h": 5,
             "w": 8,
             "x": 0,
-            "y": 18
+            "y": 32
           },
           "id": 18,
           "options": {
@@ -1410,7 +2065,7 @@
             "textMode": "auto",
             "wideLayout": true
           },
-          "pluginVersion": "10.2.2",
+          "pluginVersion": "10.2.3",
           "targets": [
             {
               "datasource": {
@@ -1522,7 +2177,8 @@
                 "mode": "absolute",
                 "steps": [
                   {
-                    "color": "green"
+                    "color": "green",
+                    "value": null
                   }
                 ]
               }
@@ -1533,7 +2189,7 @@
             "h": 5,
             "w": 8,
             "x": 8,
-            "y": 18
+            "y": 32
           },
           "id": 17,
           "options": {
@@ -1555,7 +2211,7 @@
             "textMode": "value_and_name",
             "wideLayout": true
           },
-          "pluginVersion": "10.2.2",
+          "pluginVersion": "10.2.3",
           "targets": [
             {
               "datasource": {
@@ -1669,7 +2325,8 @@
                 "mode": "absolute",
                 "steps": [
                   {
-                    "color": "green"
+                    "color": "green",
+                    "value": null
                   }
                 ]
               }
@@ -1680,7 +2337,7 @@
             "h": 5,
             "w": 8,
             "x": 16,
-            "y": 18
+            "y": 32
           },
           "id": 19,
           "options": {
@@ -1702,7 +2359,7 @@
             "textMode": "auto",
             "wideLayout": true
           },
-          "pluginVersion": "10.2.2",
+          "pluginVersion": "10.2.3",
           "targets": [
             {
               "datasource": {
@@ -1792,7 +2449,6 @@
             "uid": "PBFA97CFB590B2093"
           },
           "description": "Total number of subgraph entities loaded in event processing",
-          "hide": true,
           "fieldConfig": {
             "defaults": {
               "color": {
@@ -1836,7 +2492,8 @@
                 "mode": "absolute",
                 "steps": [
                   {
-                    "color": "green"
+                    "color": "green",
+                    "value": null
                   }
                 ]
               }
@@ -1847,8 +2504,9 @@
             "h": 6,
             "w": 8,
             "x": 0,
-            "y": 23
+            "y": 37
           },
+          "hide": true,
           "id": 8,
           "options": {
             "legend": {
@@ -1932,7 +2590,8 @@
                 "mode": "absolute",
                 "steps": [
                   {
-                    "color": "green"
+                    "color": "green",
+                    "value": null
                   }
                 ]
               }
@@ -1943,7 +2602,7 @@
             "h": 6,
             "w": 8,
             "x": 8,
-            "y": 23
+            "y": 37
           },
           "id": 9,
           "options": {
@@ -2028,7 +2687,8 @@
                 "mode": "absolute",
                 "steps": [
                   {
-                    "color": "green"
+                    "color": "green",
+                    "value": null
                   }
                 ]
               }
@@ -2039,7 +2699,7 @@
             "h": 6,
             "w": 8,
             "x": 16,
-            "y": 23
+            "y": 37
           },
           "id": 10,
           "options": {
@@ -2084,7 +2744,7 @@
     }
   ],
   "refresh": "10s",
-  "schemaVersion": 38,
+  "schemaVersion": 39,
   "tags": [
     "watcher"
   ],
@@ -2182,6 +2842,6 @@
   "timepicker": {},
   "timezone": "",
   "title": "Watchers",
-  "version": 1,
+  "version": 3,
   "weekStart": ""
 }

stack_orchestrator/data/config/monitoring/prometheus/prometheus.yml

@@ -3,8 +3,13 @@ global:
   evaluation_interval: 15s
 
 rule_files:
-  # - "first.rules"
-  # - "second.rules"
+  - rules.yml
+
+alerting:
+  alertmanagers:
+   - static_configs:
+     - targets:
+        - alert-manager:9093
 
 scrape_configs:
   - job_name: prometheus
@@ -24,10 +29,9 @@ scrape_configs:
     params:
       module: [http_2xx]
     static_configs:
-      # Add URLs for targets to be monitored below
-      # - targets: [https://github.com]
-      #   labels:
-      #     destination: 'github'
+      # Add URLs to be monitored below
+      - targets:
+        # - https://github.com
     relabel_configs:
       - source_labels: [__address__]
         regex: (.*)(:80)?

stack_orchestrator/data/config/monitoring/prometheus/rules.yml

@@ -0,0 +1,10 @@
+groups:
+  - name: WatcherAlerts
+    rules:
+      - alert: SushiswapWatcherHeadTracking
+        expr: latest_block_number - on(chain) group_right sync_status_block_number{job="sushi", instance="sushiswap", kind="latest_indexed"} > 16
+        for: 5m
+        labels:
+          severity: 'critical'
+        annotations:
+          summary: 'Watcher {{ $labels.instance }} of job {{ $labels.job }} is falling behind external head'

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

@@ -0,0 +1,64 @@
+apiVersion: 1
+groups:
+  - orgId: 1
+    name: subgraph
+    folder: SubgraphAlerts
+    interval: 30s
+    rules:
+      - uid: b2a9144b-6104-46fc-92b5-352f4e643c4c
+        title: subgraph_head_tracking
+        condition: condition
+        data:
+          - refId: diff
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: PBFA97CFB590B2093
+            model:
+              datasource:
+                  type: prometheus
+                  uid: PBFA97CFB590B2093
+              editorMode: code
+              expr: ethereum_chain_head_number - on(network) group_right deployment_head{deployment=~"REPLACE_WITH_SUBGRAPH_IDS"}
+              instant: true
+              intervalMs: 1000
+              legendFormat: __auto
+              maxDataPoints: 43200
+              range: false
+              refId: diff
+          - refId: condition
+            relativeTimeRange:
+              from: 600
+              to: 0
+            datasourceUid: __expr__
+            model:
+              conditions:
+                  - evaluator:
+                      params:
+                          - 15
+                          - 0
+                      type: gt
+                    operator:
+                      type: and
+                    query:
+                      params: []
+                    reducer:
+                      params: []
+                      type: avg
+                    type: query
+              datasource:
+                  name: Expression
+                  type: __expr__
+                  uid: __expr__
+              expression: diff
+              intervalMs: 1000
+              maxDataPoints: 43200
+              refId: condition
+              type: threshold
+        noDataState: OK
+        execErrState: Alerting
+        for: 5m
+        annotations:
+          summary: Subgraph deployment {{ index $labels "deployment" }} is falling behind head by {{ index $values "diff" }}
+        labels: {}
+        isPaused: false

stack_orchestrator/data/config/monitoring/update-grafana-alerts-config.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+echo Using CERC_GRAFANA_ALERTS_SUBGRAPH_IDS ${CERC_GRAFANA_ALERTS_SUBGRAPH_IDS}
+
+# Replace subgraph ids in subgraph alerting config
+# Note: Requires the grafana container to be run with user root
+sed -i "s/REPLACE_WITH_SUBGRAPH_IDS/$CERC_GRAFANA_ALERTS_SUBGRAPH_IDS/g" /etc/grafana/provisioning/alerting/subgraph-alert-rules.yml

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

@@ -59,29 +59,29 @@ groups:
               conditions:
                 - evaluator:
                     params:
-                      - 15
+                      - 0
                       - 0
                     type: gt
                   operator:
-                    type: when
+                    type: and
                   query:
-                    params:
-                      - diff
+                    params: []
                   reducer:
                     params: []
-                    type: last
+                    type: avg
                   type: query
               datasource:
                 name: Expression
                 type: __expr__
                 uid: __expr__
-              expression: ""
-              hide: false
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
               refId: condition
-              type: classic_conditions
+              type: math
         noDataState: Alerting
         execErrState: Alerting
-        for: 5m
+        for: 15m
         annotations:
           summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
         isPaused: false
@@ -135,29 +135,29 @@ groups:
               conditions:
                 - evaluator:
                     params:
-                      - 15
+                      - 0
                       - 0
                     type: gt
                   operator:
-                    type: when
+                    type: and
                   query:
-                    params:
-                      - diff
+                    params: []
                   reducer:
                     params: []
-                    type: last
+                    type: avg
                   type: query
               datasource:
                 name: Expression
                 type: __expr__
                 uid: __expr__
-              expression: ""
-              hide: false
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
               refId: condition
-              type: classic_conditions
+              type: math
         noDataState: Alerting
         execErrState: Alerting
-        for: 5m
+        for: 15m
         annotations:
           summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
         isPaused: false
@@ -202,7 +202,7 @@ groups:
               legendFormat: __auto
               range: false
               refId: latest_external
-           - refId: condition
+          - refId: condition
             relativeTimeRange:
               from: 600
               to: 0
@@ -211,29 +211,29 @@ groups:
               conditions:
                 - evaluator:
                     params:
-                      - 15
+                      - 0
                       - 0
                     type: gt
                   operator:
-                    type: when
+                    type: and
                   query:
-                    params:
-                      - diff
+                    params: []
                   reducer:
                     params: []
-                    type: last
+                    type: avg
                   type: query
               datasource:
                 name: Expression
                 type: __expr__
                 uid: __expr__
-              expression: ""
-              hide: false
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
               refId: condition
-              type: classic_conditions
+              type: math
         noDataState: Alerting
         execErrState: Alerting
-        for: 5m
+        for: 15m
         annotations:
           summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
         isPaused: false
@@ -278,7 +278,7 @@ groups:
               legendFormat: __auto
               range: false
               refId: latest_external
-           - refId: condition
+          - refId: condition
             relativeTimeRange:
               from: 600
               to: 0
@@ -287,29 +287,29 @@ groups:
               conditions:
                 - evaluator:
                     params:
-                      - 15
+                      - 0
                       - 0
                     type: gt
                   operator:
-                    type: when
+                    type: and
                   query:
-                    params:
-                      - diff
+                    params: []
                   reducer:
                     params: []
-                    type: last
+                    type: avg
                   type: query
               datasource:
                 name: Expression
                 type: __expr__
                 uid: __expr__
-              expression: ""
-              hide: false
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
               refId: condition
-              type: classic_conditions
+              type: math
         noDataState: Alerting
         execErrState: Alerting
-        for: 5m
+        for: 15m
         annotations:
           summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
         isPaused: false
@@ -363,29 +363,29 @@ groups:
               conditions:
                 - evaluator:
                     params:
-                      - 15
+                      - 0
                       - 0
                     type: gt
                   operator:
-                    type: when
+                    type: and
                   query:
-                    params:
-                      - diff
+                    params: []
                   reducer:
                     params: []
-                    type: last
+                    type: avg
                   type: query
               datasource:
                 name: Expression
                 type: __expr__
                 uid: __expr__
-              expression: ""
-              hide: false
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
               refId: condition
-              type: classic_conditions
+              type: math
         noDataState: Alerting
         execErrState: Alerting
-        for: 5m
+        for: 15m
         annotations:
           summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
         isPaused: false
@@ -439,29 +439,29 @@ groups:
               conditions:
                 - evaluator:
                     params:
-                      - 15
+                      - 0
                       - 0
                     type: gt
                   operator:
-                    type: when
+                    type: and
                   query:
-                    params:
-                      - diff
+                    params: []
                   reducer:
                     params: []
-                    type: last
+                    type: avg
                   type: query
               datasource:
                 name: Expression
                 type: __expr__
                 uid: __expr__
-              expression: ""
-              hide: false
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
               refId: condition
-              type: classic_conditions
+              type: math
         noDataState: Alerting
         execErrState: Alerting
-        for: 5m
+        for: 15m
         annotations:
           summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
         isPaused: false
@@ -515,29 +515,29 @@ groups:
               conditions:
                 - evaluator:
                     params:
-                      - 15
+                      - 0
                       - 0
                     type: gt
                   operator:
-                    type: when
+                    type: and
                   query:
-                    params:
-                      - diff
+                    params: []
                   reducer:
                     params: []
-                    type: last
+                    type: avg
                   type: query
               datasource:
                 name: Expression
                 type: __expr__
                 uid: __expr__
-              expression: ""
-              hide: false
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
               refId: condition
-              type: classic_conditions
+              type: math
         noDataState: Alerting
         execErrState: Alerting
-        for: 5m
+        for: 15m
         annotations:
           summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
         isPaused: false
@@ -591,29 +591,29 @@ groups:
               conditions:
                 - evaluator:
                     params:
-                      - 15
+                      - 0
                       - 0
                     type: gt
                   operator:
-                    type: when
+                    type: and
                   query:
-                    params:
-                      - diff
+                    params: []
                   reducer:
                     params: []
-                    type: last
+                    type: avg
                   type: query
               datasource:
                 name: Expression
                 type: __expr__
                 uid: __expr__
-              expression: ""
-              hide: false
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
               refId: condition
-              type: classic_conditions
+              type: math
         noDataState: Alerting
         execErrState: Alerting
-        for: 5m
+        for: 15m
         annotations:
           summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
         isPaused: false
@@ -669,29 +669,29 @@ groups:
               conditions:
                 - evaluator:
                     params:
-                      - 15
+                      - 0
                       - 0
                     type: gt
                   operator:
-                    type: when
+                    type: and
                   query:
-                    params:
-                      - diff
+                    params: []
                   reducer:
                     params: []
-                    type: last
+                    type: avg
                   type: query
               datasource:
                 name: Expression
                 type: __expr__
                 uid: __expr__
-              expression: ""
-              hide: false
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
               refId: condition
-              type: classic_conditions
+              type: math
         noDataState: Alerting
         execErrState: Alerting
-        for: 5m
+        for: 15m
         annotations:
           summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
         isPaused: false
@@ -745,29 +745,29 @@ groups:
               conditions:
                 - evaluator:
                     params:
-                      - 15
+                      - 0
                       - 0
                     type: gt
                   operator:
-                    type: when
+                    type: and
                   query:
-                    params:
-                      - diff
+                    params: []
                   reducer:
                     params: []
-                    type: last
+                    type: avg
                   type: query
               datasource:
                 name: Expression
                 type: __expr__
                 uid: __expr__
-              expression: ""
-              hide: false
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
               refId: condition
-              type: classic_conditions
+              type: math
         noDataState: Alerting
         execErrState: Alerting
-        for: 5m
+        for: 15m
         annotations:
           summary: Watcher {{ index $labels "instance" }} of group {{ index $labels "job" }} is falling behind external head by {{ index $values "diff" }}
         isPaused: false
@@ -823,29 +823,29 @@ groups:
               conditions:
                 - evaluator:
                     params:
-                      - 15
+                      - 0
                       - 0
                     type: gt
                   operator:
-                    type: when
+                    type: and
                   query:
-                    params:
-                      - diff
+                    params: []
                   reducer:
                     params: []
-                    type: last
+                    type: avg
                   type: query
               datasource:
                 name: Expression
                 type: __expr__
                 uid: __expr__
-              expression: ""
-              hide: false
+              expression: ${diff} >= 16
+              intervalMs: 1000
+              maxDataPoints: 43200
               refId: condition
-              type: classic_conditions
+              type: math
         noDataState: Alerting
         execErrState: Alerting
-        for: 5m
+        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/config/watcher-ajna/start-job-runner.sh

@@ -6,12 +6,16 @@ if [ -n "$CERC_SCRIPT_DEBUG" ]; then
 fi
 set -u
 
-echo "Using ETH RPC endpoint ${CERC_ETH_RPC_ENDPOINT}"
+echo "Using ETH RPC endpoints ${CERC_ETH_RPC_ENDPOINTS}"
 
 # Read in the config template TOML file and modify it
 WATCHER_CONFIG_TEMPLATE=$(cat environments/watcher-config-template.toml)
+
+# Convert the comma-separated list in CERC_ETH_RPC_ENDPOINTS to a JSON array
+RPC_ENDPOINTS_ARRAY=$(echo "$CERC_ETH_RPC_ENDPOINTS" | tr ',' '\n' | awk '{print "\"" $0 "\""}' | paste -sd, - | sed 's/^/[/; s/$/]/')
+
 WATCHER_CONFIG=$(echo "$WATCHER_CONFIG_TEMPLATE" | \
-  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINT|${CERC_ETH_RPC_ENDPOINT}| ")
+  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINTS|${RPC_ENDPOINTS_ARRAY}| ")
 
 # Write the modified content to a new file
 echo "$WATCHER_CONFIG" > environments/local.toml

stack_orchestrator/data/config/watcher-ajna/start-server.sh

@@ -6,12 +6,16 @@ if [ -n "$CERC_SCRIPT_DEBUG" ]; then
 fi
 set -u
 
-echo "Using ETH RPC endpoint ${CERC_ETH_RPC_ENDPOINT}"
+echo "Using ETH RPC endpoints ${CERC_ETH_RPC_ENDPOINTS}"
 
 # Read in the config template TOML file and modify it
 WATCHER_CONFIG_TEMPLATE=$(cat environments/watcher-config-template.toml)
+
+# Convert the comma-separated list in CERC_ETH_RPC_ENDPOINTS to a JSON array
+RPC_ENDPOINTS_ARRAY=$(echo "$CERC_ETH_RPC_ENDPOINTS" | tr ',' '\n' | awk '{print "\"" $0 "\""}' | paste -sd, - | sed 's/^/[/; s/$/]/')
+
 WATCHER_CONFIG=$(echo "$WATCHER_CONFIG_TEMPLATE" | \
-  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINT|${CERC_ETH_RPC_ENDPOINT}| ")
+  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINTS|${RPC_ENDPOINTS_ARRAY}| ")
 
 # Write the modified content to a new file
 echo "$WATCHER_CONFIG" > environments/local.toml

stack_orchestrator/data/config/watcher-ajna/watcher-config-template.toml

@@ -58,7 +58,7 @@
 
 [upstream]
   [upstream.ethServer]
-    rpcProviderEndpoint = "REPLACE_WITH_CERC_ETH_RPC_ENDPOINT"
+    rpcProviderEndpoints = REPLACE_WITH_CERC_ETH_RPC_ENDPOINTS
 
     # Boolean flag to specify if rpc-eth-client should be used for RPC endpoint instead of ipld-eth-client (ipld-eth-server GQL client)
     rpcClient = true
@@ -96,3 +96,6 @@
   # Max block range of historical processing after which it waits for completion of events processing
   # If set to -1 historical processing does not wait for events processing and completes till latest canonical block
   historicalMaxFetchAhead = 10000
+
+  # Max number of retries to fetch new block after which watcher will failover to other RPC endpoints
+  maxNewBlockRetries = 3

stack_orchestrator/data/config/watcher-azimuth/start-job-runner.sh

@@ -4,16 +4,19 @@ if [ -n "$CERC_SCRIPT_DEBUG" ]; then
   set -x
 fi
 
-echo "Using IPLD ETH RPC endpoint ${CERC_IPLD_ETH_RPC}"
-echo "Using IPLD GQL endpoint ${CERC_IPLD_ETH_GQL}"
+echo "Using ETH RPC endpoints ${CERC_ETH_RPC_ENDPOINTS}"
+echo "Using IPLD GQL endpoint ${CERC_IPLD_ETH_GQL_ENDPOINT}"
 echo "Using historicalLogsBlockRange ${CERC_HISTORICAL_BLOCK_RANGE:-2000}"
 
+# Convert the comma-separated list in CERC_ETH_RPC_ENDPOINTS to a JSON array
+RPC_ENDPOINTS_ARRAY=$(echo "$CERC_ETH_RPC_ENDPOINTS" | tr ',' '\n' | awk '{print "\"" $0 "\""}' | paste -sd, - | sed 's/^/[/; s/$/]/')
+
 # Replace env variables in template TOML file
 # Read in the config template TOML file and modify it
 WATCHER_CONFIG_TEMPLATE=$(cat environments/watcher-config-template.toml)
 WATCHER_CONFIG=$(echo "$WATCHER_CONFIG_TEMPLATE" | \
-  sed -E "s|REPLACE_WITH_CERC_IPLD_ETH_RPC|${CERC_IPLD_ETH_RPC}|g; \
-          s|REPLACE_WITH_CERC_IPLD_ETH_GQL|${CERC_IPLD_ETH_GQL}|g; \
+  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINTS|${RPC_ENDPOINTS_ARRAY}|g; \
+          s|REPLACE_WITH_CERC_IPLD_ETH_GQL_ENDPOINT|${CERC_IPLD_ETH_GQL_ENDPOINT}|g; \
           s|REPLACE_WITH_CERC_HISTORICAL_BLOCK_RANGE|${CERC_HISTORICAL_BLOCK_RANGE:-2000}| ")
 
 # Write the modified content to a new file

stack_orchestrator/data/config/watcher-azimuth/start-server.sh

@@ -4,16 +4,19 @@ if [ -n "$CERC_SCRIPT_DEBUG" ]; then
   set -x
 fi
 
-echo "Using IPLD ETH RPC endpoint ${CERC_IPLD_ETH_RPC}"
-echo "Using IPLD GQL endpoint ${CERC_IPLD_ETH_GQL}"
+echo "Using ETH RPC endpoints ${CERC_ETH_RPC_ENDPOINTS}"
+echo "Using IPLD GQL endpoint ${CERC_IPLD_ETH_GQL_ENDPOINT}"
 echo "Using historicalLogsBlockRange ${CERC_HISTORICAL_BLOCK_RANGE:-2000}"
 
+# Convert the comma-separated list in CERC_ETH_RPC_ENDPOINTS to a JSON array
+RPC_ENDPOINTS_ARRAY=$(echo "$CERC_ETH_RPC_ENDPOINTS" | tr ',' '\n' | awk '{print "\"" $0 "\""}' | paste -sd, - | sed 's/^/[/; s/$/]/')
+
 # Replace env variables in template TOML file
 # Read in the config template TOML file and modify it
 WATCHER_CONFIG_TEMPLATE=$(cat environments/watcher-config-template.toml)
 WATCHER_CONFIG=$(echo "$WATCHER_CONFIG_TEMPLATE" | \
-  sed -E "s|REPLACE_WITH_CERC_IPLD_ETH_RPC|${CERC_IPLD_ETH_RPC}|g; \
-          s|REPLACE_WITH_CERC_IPLD_ETH_GQL|${CERC_IPLD_ETH_GQL}|g; \
+  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINTS|${RPC_ENDPOINTS_ARRAY}|g; \
+          s|REPLACE_WITH_CERC_IPLD_ETH_GQL_ENDPOINT|${CERC_IPLD_ETH_GQL_ENDPOINT}|g; \
           s|REPLACE_WITH_CERC_HISTORICAL_BLOCK_RANGE|${CERC_HISTORICAL_BLOCK_RANGE:-2000}| ")
 
 # Write the modified content to a new file

stack_orchestrator/data/config/watcher-azimuth/watcher-config-template.toml

@@ -13,8 +13,8 @@
 
 [upstream]
   [upstream.ethServer]
-    gqlApiEndpoint = "REPLACE_WITH_CERC_IPLD_ETH_GQL"
-    rpcProviderEndpoint = "REPLACE_WITH_CERC_IPLD_ETH_RPC"
+    gqlApiEndpoint = "REPLACE_WITH_CERC_IPLD_ETH_GQL_ENDPOINT"
+    rpcProviderEndpoints = REPLACE_WITH_CERC_ETH_RPC_ENDPOINTS
 
 [jobQueue]
   historicalLogsBlockRange = REPLACE_WITH_CERC_HISTORICAL_BLOCK_RANGE

stack_orchestrator/data/config/watcher-merkl-sushiswap-v3/start-job-runner.sh

@@ -6,12 +6,16 @@ if [ -n "$CERC_SCRIPT_DEBUG" ]; then
 fi
 set -u
 
-echo "Using ETH RPC endpoint ${CERC_ETH_RPC_ENDPOINT}"
+echo "Using ETH RPC endpoints ${CERC_ETH_RPC_ENDPOINTS}"
 
 # Read in the config template TOML file and modify it
 WATCHER_CONFIG_TEMPLATE=$(cat environments/watcher-config-template.toml)
+
+# Convert the comma-separated list in CERC_ETH_RPC_ENDPOINTS to a JSON array
+RPC_ENDPOINTS_ARRAY=$(echo "$CERC_ETH_RPC_ENDPOINTS" | tr ',' '\n' | awk '{print "\"" $0 "\""}' | paste -sd, - | sed 's/^/[/; s/$/]/')
+
 WATCHER_CONFIG=$(echo "$WATCHER_CONFIG_TEMPLATE" | \
-  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINT|${CERC_ETH_RPC_ENDPOINT}| ")
+  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINTS|${RPC_ENDPOINTS_ARRAY}| ")
 
 # Write the modified content to a new file
 echo "$WATCHER_CONFIG" > environments/local.toml

stack_orchestrator/data/config/watcher-merkl-sushiswap-v3/start-server.sh

@@ -6,12 +6,16 @@ if [ -n "$CERC_SCRIPT_DEBUG" ]; then
 fi
 set -u
 
-echo "Using ETH RPC endpoint ${CERC_ETH_RPC_ENDPOINT}"
+echo "Using ETH RPC endpoints ${CERC_ETH_RPC_ENDPOINTS}"
 
 # Read in the config template TOML file and modify it
 WATCHER_CONFIG_TEMPLATE=$(cat environments/watcher-config-template.toml)
+
+# Convert the comma-separated list in CERC_ETH_RPC_ENDPOINTS to a JSON array
+RPC_ENDPOINTS_ARRAY=$(echo "$CERC_ETH_RPC_ENDPOINTS" | tr ',' '\n' | awk '{print "\"" $0 "\""}' | paste -sd, - | sed 's/^/[/; s/$/]/')
+
 WATCHER_CONFIG=$(echo "$WATCHER_CONFIG_TEMPLATE" | \
-  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINT|${CERC_ETH_RPC_ENDPOINT}| ")
+  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINTS|${RPC_ENDPOINTS_ARRAY}| ")
 
 # Write the modified content to a new file
 echo "$WATCHER_CONFIG" > environments/local.toml

stack_orchestrator/data/config/watcher-merkl-sushiswap-v3/watcher-config-template.toml

@@ -58,7 +58,7 @@
 
 [upstream]
   [upstream.ethServer]
-    rpcProviderEndpoint = "REPLACE_WITH_CERC_ETH_RPC_ENDPOINT"
+    rpcProviderEndpoints = REPLACE_WITH_CERC_ETH_RPC_ENDPOINTS
 
     # Boolean flag to specify if rpc-eth-client should be used for RPC endpoint instead of ipld-eth-client (ipld-eth-server GQL client)
     rpcClient = true
@@ -69,7 +69,7 @@
     # Boolean flag to filter event logs by contracts
     filterLogsByAddresses = true
     # Boolean flag to filter event logs by topics
-    filterLogsByTopics = false
+    filterLogsByTopics = true
 
   [upstream.cache]
     name = "requests"
@@ -96,3 +96,6 @@
   # Max block range of historical processing after which it waits for completion of events processing
   # If set to -1 historical processing does not wait for events processing and completes till latest canonical block
   historicalMaxFetchAhead = 10000
+
+  # Max number of retries to fetch new block after which watcher will failover to other RPC endpoints
+  maxNewBlockRetries = 3

stack_orchestrator/data/config/watcher-sushiswap-v3/start-job-runner.sh

@@ -6,12 +6,16 @@ if [ -n "$CERC_SCRIPT_DEBUG" ]; then
 fi
 set -u
 
-echo "Using ETH RPC endpoint ${CERC_ETH_RPC_ENDPOINT}"
+echo "Using ETH RPC endpoints ${CERC_ETH_RPC_ENDPOINTS}"
 
 # Read in the config template TOML file and modify it
 WATCHER_CONFIG_TEMPLATE=$(cat environments/watcher-config-template.toml)
+
+# Convert the comma-separated list in CERC_ETH_RPC_ENDPOINTS to a JSON array
+RPC_ENDPOINTS_ARRAY=$(echo "$CERC_ETH_RPC_ENDPOINTS" | tr ',' '\n' | awk '{print "\"" $0 "\""}' | paste -sd, - | sed 's/^/[/; s/$/]/')
+
 WATCHER_CONFIG=$(echo "$WATCHER_CONFIG_TEMPLATE" | \
-  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINT|${CERC_ETH_RPC_ENDPOINT}| ")
+  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINTS|${RPC_ENDPOINTS_ARRAY}| ")
 
 # Write the modified content to a new file
 echo "$WATCHER_CONFIG" > environments/local.toml

stack_orchestrator/data/config/watcher-sushiswap-v3/start-server.sh

@@ -6,12 +6,16 @@ if [ -n "$CERC_SCRIPT_DEBUG" ]; then
 fi
 set -u
 
-echo "Using ETH RPC endpoint ${CERC_ETH_RPC_ENDPOINT}"
+echo "Using ETH RPC endpoints ${CERC_ETH_RPC_ENDPOINTS}"
 
 # Read in the config template TOML file and modify it
 WATCHER_CONFIG_TEMPLATE=$(cat environments/watcher-config-template.toml)
+
+# Convert the comma-separated list in CERC_ETH_RPC_ENDPOINTS to a JSON array
+RPC_ENDPOINTS_ARRAY=$(echo "$CERC_ETH_RPC_ENDPOINTS" | tr ',' '\n' | awk '{print "\"" $0 "\""}' | paste -sd, - | sed 's/^/[/; s/$/]/')
+
 WATCHER_CONFIG=$(echo "$WATCHER_CONFIG_TEMPLATE" | \
-  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINT|${CERC_ETH_RPC_ENDPOINT}| ")
+  sed -E "s|REPLACE_WITH_CERC_ETH_RPC_ENDPOINTS|${RPC_ENDPOINTS_ARRAY}| ")
 
 # Write the modified content to a new file
 echo "$WATCHER_CONFIG" > environments/local.toml

stack_orchestrator/data/config/watcher-sushiswap-v3/watcher-config-template.toml

@@ -58,7 +58,7 @@
 
 [upstream]
   [upstream.ethServer]
-    rpcProviderEndpoint = "REPLACE_WITH_CERC_ETH_RPC_ENDPOINT"
+    rpcProviderEndpoints = REPLACE_WITH_CERC_ETH_RPC_ENDPOINTS
 
     # Boolean flag to specify if rpc-eth-client should be used for RPC endpoint instead of ipld-eth-client (ipld-eth-server GQL client)
     rpcClient = true
@@ -96,3 +96,6 @@
   # Max block range of historical processing after which it waits for completion of events processing
   # If set to -1 historical processing does not wait for events processing and completes till latest canonical block
   historicalMaxFetchAhead = 10000
+
+  # Max number of retries to fetch new block after which watcher will failover to other RPC endpoints
+  maxNewBlockRetries = 3

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

@@ -2,4 +2,4 @@
 # Build cerc/test-container
 source ${CERC_CONTAINER_BASE_DIR}/build-base.sh
 SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
-docker build -t cerc/test-container:local -f ${SCRIPT_DIR}/Dockerfile ${build_command_args} $SCRIPT_DIR
+docker build -t cerc/test-container:local -f ${SCRIPT_DIR}/Dockerfile ${build_command_args} $SCRIPT_DIR

stack_orchestrator/data/container-build/cerc-webapp-base/scripts/start-serving-app.sh

@@ -8,21 +8,27 @@ CERC_WEBAPP_FILES_DIR="${CERC_WEBAPP_FILES_DIR:-/data}"
 CERC_ENABLE_CORS="${CERC_ENABLE_CORS:-false}"
 CERC_SINGLE_PAGE_APP="${CERC_SINGLE_PAGE_APP}"
 
-if [ -z "${CERC_SINGLE_PAGE_APP}" ]; then
-  if [ 1 -eq $(find "${CERC_WEBAPP_FILES_DIR}" -name '*.html' | wc -l) ] && [ -d "${CERC_WEBAPP_FILES_DIR}/static" ]; then
+if [ -z "${CERC_SINGLE_PAGE_APP}" ]; then 
+  # If there is only one HTML file, assume an SPA.
+  if [ 1 -eq $(find "${CERC_WEBAPP_FILES_DIR}" -name '*.html' | wc -l) ]; then
     CERC_SINGLE_PAGE_APP=true
   else
     CERC_SINGLE_PAGE_APP=false
   fi
 fi
 
-if [ "true" == "$CERC_ENABLE_CORS" ]; then
+# ${var,,} is a lower-case comparison
+if [ "true" == "${CERC_ENABLE_CORS,,}" ]; then
   CERC_HTTP_EXTRA_ARGS="$CERC_HTTP_EXTRA_ARGS --cors"
 fi
 
-if [ "true" == "$CERC_SINGLE_PAGE_APP" ]; then
+# ${var,,} is a lower-case comparison
+if [ "true" == "${CERC_SINGLE_PAGE_APP,,}" ]; then
+  echo "Serving content as single-page app.  If this is wrong, set 'CERC_SINGLE_PAGE_APP=false'"
   # Create a catchall redirect back to /
   CERC_HTTP_EXTRA_ARGS="$CERC_HTTP_EXTRA_ARGS --proxy http://localhost:${CERC_LISTEN_PORT}?"
+else
+  echo "Serving content normally.  If this is a single-page app, set 'CERC_SINGLE_PAGE_APP=true'"
 fi
 
 LACONIC_HOSTED_CONFIG_FILE=${LACONIC_HOSTED_CONFIG_FILE}
@@ -39,4 +45,4 @@ if [ -f "${LACONIC_HOSTED_CONFIG_FILE}" ]; then
 fi
 
 /scripts/apply-runtime-env.sh ${CERC_WEBAPP_FILES_DIR}
-http-server $CERC_HTTP_EXTRA_ARGS -p ${CERC_LISTEN_PORT} "${CERC_WEBAPP_FILES_DIR}"
+http-server $CERC_HTTP_EXTRA_ARGS -p ${CERC_LISTEN_PORT} "${CERC_WEBAPP_FILES_DIR}"

stack_orchestrator/data/stacks/ajna/README.md

@@ -53,7 +53,7 @@ Inside deployment directory, open the `config.env` file  and set following env v
 
 ```bash
 # External Filecoin (ETH RPC) endpoint to point the watcher to
-CERC_ETH_RPC_ENDPOINT=https://example-lotus-endpoint/rpc/v1
+CERC_ETH_RPC_ENDPOINTS=https://example-lotus-endpoint-1/rpc/v1,https://example-lotus-endpoint-2/rpc/v1
 ```
 
 ### Start the deployment

stack_orchestrator/data/stacks/ajna/stack.yml

@@ -2,7 +2,7 @@ version: "1.0"
 name: ajna
 description: "Ajna watcher stack"
 repos:
-  - git.vdb.to/cerc-io/ajna-watcher-ts@v0.1.1
+  - git.vdb.to/cerc-io/ajna-watcher-ts@v0.1.9
 containers:
   - cerc/watcher-ajna
 pods:

stack_orchestrator/data/stacks/azimuth/README.md

@@ -4,7 +4,7 @@ Instructions to setup and deploy Azimuth Watcher stack
 
 ## Setup
 
-Prerequisite: `ipld-eth-server` RPC and GQL endpoints
+Prerequisite: External RPC endpoints
 
 Clone required repositories:
 
@@ -94,7 +94,7 @@ Inside the deployment directory, open the file `config.env` and add variable to
 
   ```bash
   # External RPC endpoints
-  CERC_IPLD_ETH_RPC=
+  CERC_ETH_RPC_ENDPOINTS=https://example-rpc-endpoint-1,https://example-rpc-endpoint-2
   ```
 
 * NOTE: If RPC endpoint is on the host machine, use `host.docker.internal` as the hostname to access the host port, or use the `ip a` command to find the IP address of the `docker0` interface (this will usually be something like `172.17.0.1` or `172.18.0.1`)
@@ -120,4 +120,7 @@ To stop all azimuth services and also delete data:
 
 ```bash
 laconic-so deployment --dir azimuth-deployment stop --delete-volumes
+
+# Remove deployment directory (deployment will have to be recreated for a re-run)
+rm -r azimuth-deployment
 ```

stack_orchestrator/data/stacks/azimuth/stack.yml

@@ -1,7 +1,7 @@
 version: "1.0"
 name: azimuth
 repos:
-  - github.com/cerc-io/azimuth-watcher-ts@v0.1.3
+  - github.com/cerc-io/azimuth-watcher-ts@v0.1.4
 containers:
   - cerc/watcher-azimuth
 pods:

stack_orchestrator/data/stacks/graph-node/README.md

@@ -76,6 +76,19 @@ export ETH_RPC_PORT=
 # The etherum network(s) graph-node will connect to
 # Set this to a space-separated list of the networks where each entry has the form NAME:URL
 export ETH_NETWORKS=
+
+# Optional:
+
+# Timeout for ETH RPC requests in seconds (default: 180s)
+export GRAPH_ETHEREUM_JSON_RPC_TIMEOUT=
+
+# Number of times to retry ETH RPC requests (default: 10)
+export GRAPH_ETHEREUM_REQUEST_RETRIES=
+
+# Maximum number of blocks to scan for triggers in each request (default: 2000)
+export GRAPH_ETHEREUM_MAX_BLOCK_RANGE_SIZE=
+
+# Ref: https://git.vdb.to/cerc-io/graph-node/src/branch/master/docs/environment-variables.md
 ```
 
 Example env file:
@@ -85,6 +98,10 @@ export ETH_RPC_HOST=filecoin.chainup.net
 export ETH_RPC_PORT=443
 
 export ETH_NETWORKS=filecoin:https://filecoin.chainup.net/rpc/v1
+
+export GRAPH_ETHEREUM_JSON_RPC_TIMEOUT=360
+export GRAPH_ETHEREUM_REQUEST_RETRIES=5
+export GRAPH_ETHEREUM_MAX_BLOCK_RANGE_SIZE=50
 ```
 
 Set the environment variables:

stack_orchestrator/data/stacks/merkl-sushiswap-v3/README.md

@@ -53,7 +53,7 @@ Inside deployment directory, open the `config.env` file  and set following env v
 
 ```bash
 # External Filecoin (ETH RPC) endpoint to point the watcher to
-CERC_ETH_RPC_ENDPOINT=https://example-lotus-endpoint/rpc/v1
+CERC_ETH_RPC_ENDPOINTS=https://example-lotus-endpoint-1/rpc/v1,https://example-lotus-endpoint-2/rpc/v1
 ```
 
 ### Start the deployment

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@v0.1.7
+  - github.com/cerc-io/merkl-sushiswap-v3-watcher-ts@v0.1.11
 containers:
   - cerc/watcher-merkl-sushiswap-v3
 pods:

stack_orchestrator/data/stacks/monitoring/README.md

@@ -123,9 +123,8 @@ laconic-so --stack monitoring deploy create --spec-file monitoring-spec.yml --de
   ```yml
   ...
   - job_name: laconicd
-    ...
-    static_configs:
-      - targets: ['example-host:1317']
+  static_configs:
+    - targets: ['example-host:1317']
   ...
   ```
 

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

@@ -44,18 +44,13 @@ Add the following scrape configs to prometheus config file (`monitoring-watchers
   - job_name: 'blackbox'
     ...
     static_configs:
-      - targets: [<AZIMUTH_GATEWAY_GQL_ENDPOINT>]
-        labels:
-          # Add destination label for pre-configured alerts
-          destination: 'azimuth_gateway'
-      - targets: [<LACONICD_GQL_ENDPOINT>]
-        labels:
-          destination: 'laconicd_gql'
+      - targets:
+        - <AZIMUTH_GATEWAY_GQL_ENDPOINT>
+        - <LACONICD_GQL_ENDPOINT>
   ...
   - job_name: laconicd
-    ...
-    static_configs:
-      - targets: ['LACONICD_REST_HOST:LACONICD_REST_PORT']
+  static_configs:
+    - targets: ['LACONICD_REST_HOST:LACONICD_REST_PORT']
   ...
   - job_name: azimuth
     scrape_interval: 10s
@@ -118,23 +113,31 @@ Add the following scrape configs to prometheus config file (`monitoring-watchers
         labels:
           instance: 'ajna'
           chain: 'filecoin'
+
+  - job_name: graph-node
+    metrics_path: /metrics
+    scrape_interval: 30s
+    static_configs:
+      - targets: ['GRAPH_NODE_HOST:GRAPH_NODE_HOST_METRICS_PORT']
   ```
 
 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 and blackbox endpoint alerts rules in Grafana provisioning directory:
+Place the pre-configured alerts rules in Grafana provisioning directory:
 
   ```bash
+  # watcher alert rules
   cp monitoring-watchers-deployment/config/monitoring/watcher-alert-rules.yml monitoring-watchers-deployment/config/monitoring/grafana/provisioning/alerting/
 
-  cp monitoring-watchers-deployment/config/monitoring/blackbox-alert-rules.yml monitoring-watchers-deployment/config/monitoring/grafana/provisioning/alerting/
+  # subgraph alert rules
+  cp monitoring-watchers-deployment/config/monitoring/subgraph-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:
+Add corresponding routes to the notification policies config (`monitoring-watchers-deployment/config/monitoring/grafana/provisioning/alerting/policies.yml`) with appropriate object-matchers:
 
   ```yml
   ...
@@ -142,7 +145,7 @@ Add corresponding routes to the notification policies config (`monitoring-watche
       - receiver: SlackNotifier
       object_matchers:
         # Add matchers below
-        - ['grafana_folder', '=~', 'WatcherAlerts|BlackboxAlerts']
+        - ['grafana_folder', '=~', 'WatcherAlerts|SubgraphAlerts']
   ```
 
 ### Env
@@ -156,6 +159,9 @@ Set the following env variables in the deployment env config file (`monitoring-w
   # Grafana server host URL to be used
   # (Optional, default: http://localhost:3000)
   GF_SERVER_ROOT_URL=
+
+  # List of subgraph ids to configure alerts for (separated by |)
+  CERC_GRAFANA_ALERTS_SUBGRAPH_IDS=
   ```
 
 ## Start the stack

stack_orchestrator/data/stacks/sushiswap-v3/README.md

@@ -53,7 +53,7 @@ Inside deployment directory, open the `config.env` file  and set following env v
 
 ```bash
 # External Filecoin (ETH RPC) endpoint to point the watcher to
-CERC_ETH_RPC_ENDPOINT=https://example-lotus-endpoint/rpc/v1
+CERC_ETH_RPC_ENDPOINTS=https://example-lotus-endpoint-1/rpc/v1,https://example-lotus-endpoint-2/rpc/v1
 ```
 
 ### Start the deployment

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@v0.1.7
+  - github.com/cerc-io/sushiswap-v3-watcher-ts@v0.1.11
 containers:
   - cerc/watcher-sushiswap-v3
 pods:

stack_orchestrator/data/stacks/webapp-deployer-backend/stack.yml

@@ -2,10 +2,10 @@ version: "1.0"
 name: webapp-deployer-backend
 description: "Deployer for webapps"
 repos:
-  - git.vdb.to/telackey/webapp-deployment-status-api
+  - git.vdb.to/cerc-io/webapp-deployment-status-api
 containers:
   - cerc/webapp-deployer-backend
 pods:
   - name: webapp-deployer-backend
-    repository: git.vdb.to/telackey/webapp-deployment-status-api
+    repository: git.vdb.to/cerc-io/webapp-deployment-status-api
     path: ./

stack_orchestrator/deploy/deploy.py

@@ -27,6 +27,7 @@ from pathlib import Path
 from stack_orchestrator import constants
 from stack_orchestrator.opts import opts
 from stack_orchestrator.util import include_exclude_check, get_parsed_stack_config, global_options2, get_dev_root_path
+from stack_orchestrator.util import resolve_compose_file
 from stack_orchestrator.deploy.deployer import Deployer, DeployerException
 from stack_orchestrator.deploy.deployer_factory import getDeployer
 from stack_orchestrator.deploy.deploy_types import ClusterContext, DeployCommandContext
@@ -324,7 +325,10 @@ def _make_cluster_context(ctx, stack, include, exclude, cluster, env_file):
         pod_path = pod["path"]
         if include_exclude_check(pod_name, include, exclude):
             if pod_repository is None or pod_repository == "internal":
-                compose_file_name = os.path.join(compose_dir, f"docker-compose-{pod_path}.yml")
+                if deployment:
+                    compose_file_name = os.path.join(compose_dir, f"docker-compose-{pod_path}.yml")
+                else:
+                    compose_file_name = resolve_compose_file(stack, pod_name)
             else:
                 if deployment:
                     compose_file_name = os.path.join(compose_dir, f"docker-compose-{pod_name}.yml")
@@ -336,6 +340,7 @@ def _make_cluster_context(ctx, stack, include, exclude, cluster, env_file):
                     if pod_post_start_command is not None:
                         post_start_commands.append(os.path.join(script_dir, pod_post_start_command))
                 else:
+                    # TODO: fix this code for external stack with scripts
                     pod_root_dir = os.path.join(dev_root_path, pod_repository.split("/")[-1], pod["path"])
                     compose_file_name = os.path.join(pod_root_dir, f"docker-compose-{pod_name}.yml")
                     pod_pre_start_command = pod.get("pre_start_command")

stack_orchestrator/deploy/deploy_util.py

@@ -16,7 +16,7 @@
 import os
 from typing import List, Any
 from stack_orchestrator.deploy.deploy_types import DeployCommandContext, VolumeMapping
-from stack_orchestrator.util import get_parsed_stack_config, get_yaml, get_compose_file_dir, get_pod_list
+from stack_orchestrator.util import get_parsed_stack_config, get_yaml, get_pod_list, resolve_compose_file
 from stack_orchestrator.opts import opts
 
 
@@ -27,7 +27,7 @@ def _container_image_from_service(stack: str, service: str):
     pods = get_pod_list(parsed_stack)
     yaml = get_yaml()
     for pod in pods:
-        pod_file_path = os.path.join(get_compose_file_dir(), f"docker-compose-{pod}.yml")
+        pod_file_path = resolve_compose_file(stack, pod)
         parsed_pod_file = yaml.load(open(pod_file_path, "r"))
         if "services" in parsed_pod_file:
             services = parsed_pod_file["services"]

stack_orchestrator/deploy/deployment_create.py

@@ -26,7 +26,8 @@ from stack_orchestrator import constants
 from stack_orchestrator.opts import opts
 from stack_orchestrator.util import (get_stack_file_path, get_parsed_deployment_spec, get_parsed_stack_config,
                                      global_options, get_yaml, get_pod_list, get_pod_file_path, pod_has_scripts,
-                                     get_pod_script_paths, get_plugin_code_paths, error_exit, env_var_map_from_file)
+                                     get_pod_script_paths, get_plugin_code_paths, error_exit, env_var_map_from_file,
+                                     resolve_config_dir)
 from stack_orchestrator.deploy.spec import Spec
 from stack_orchestrator.deploy.deploy_types import LaconicStackSetupCommand
 from stack_orchestrator.deploy.deployer_factory import getDeployerConfigGenerator
@@ -43,7 +44,7 @@ def _get_ports(stack):
     pods = get_pod_list(parsed_stack)
     yaml = get_yaml()
     for pod in pods:
-        pod_file_path = get_pod_file_path(parsed_stack, pod)
+        pod_file_path = get_pod_file_path(stack, parsed_stack, pod)
         parsed_pod_file = yaml.load(open(pod_file_path, "r"))
         if "services" in parsed_pod_file:
             for svc_name, svc in parsed_pod_file["services"].items():
@@ -79,7 +80,7 @@ def _get_named_volumes(stack):
         return ret
 
     for pod in pods:
-        pod_file_path = get_pod_file_path(parsed_stack, pod)
+        pod_file_path = get_pod_file_path(stack, parsed_stack, pod)
         parsed_pod_file = yaml.load(open(pod_file_path, "r"))
         if "volumes" in parsed_pod_file:
             volumes = parsed_pod_file["volumes"]
@@ -480,10 +481,9 @@ def create_operation(deployment_command_context, spec_file, deployment_dir, netw
     os.mkdir(destination_compose_dir)
     destination_pods_dir = deployment_dir_path.joinpath("pods")
     os.mkdir(destination_pods_dir)
-    data_dir = Path(__file__).absolute().parent.parent.joinpath("data")
     yaml = get_yaml()
     for pod in pods:
-        pod_file_path = get_pod_file_path(parsed_stack, pod)
+        pod_file_path = get_pod_file_path(stack_name, parsed_stack, pod)
         parsed_pod_file = yaml.load(open(pod_file_path, "r"))
         extra_config_dirs = _find_extra_config_dirs(parsed_pod_file, pod)
         destination_pod_dir = destination_pods_dir.joinpath(pod)
@@ -497,7 +497,7 @@ def create_operation(deployment_command_context, spec_file, deployment_dir, netw
         config_dirs = {pod}
         config_dirs = config_dirs.union(extra_config_dirs)
         for config_dir in config_dirs:
-            source_config_dir = data_dir.joinpath("config", config_dir)
+            source_config_dir = resolve_config_dir(stack_name, config_dir)
             if os.path.exists(source_config_dir):
                 destination_config_dir = deployment_dir_path.joinpath("config", config_dir)
                 # If the same config dir appears in multiple pods, it may already have been copied

stack_orchestrator/deploy/webapp/deploy_webapp_from_registry.py

@@ -39,11 +39,12 @@ def process_app_deployment_request(
     app_deployment_request,
     deployment_record_namespace,
     dns_record_namespace,
-    dns_suffix,
+    default_dns_suffix,
     deployment_parent_dir,
     kube_config,
     image_registry,
     force_rebuild,
+    fqdn_policy,
     logger
 ):
     logger.log("BEGIN - process_app_deployment_request")
@@ -56,14 +57,15 @@ def process_app_deployment_request(
     requested_name = hostname_for_deployment_request(app_deployment_request, laconic)
     logger.log(f"Determined requested name: {requested_name}")
 
-    # HACK
     if "." in requested_name:
-        raise Exception("Only unqualified hostnames allowed at this time.")
-
-    fqdn = f"{requested_name}.{dns_suffix}"
+        if "allow" == fqdn_policy or "preexisting" == fqdn_policy:
+            fqdn = requested_name
+        else:
+            raise Exception(f"{requested_name} is invalid: only unqualified hostnames are allowed.")
+    else:
+        fqdn = f"{requested_name}.{default_dns_suffix}"
 
     # 3. check ownership of existing dnsrecord vs this request
-    # TODO: Support foreign DNS
     dns_crn = f"{dns_record_namespace}/{fqdn}"
     dns_record = laconic.get_record(dns_crn)
     if dns_record:
@@ -75,7 +77,9 @@ def process_app_deployment_request(
             logger.log(f"Matched DnsRecord ownership: {matched_owner}")
         else:
             raise Exception("Unable to confirm ownership of DnsRecord %s for request %s" %
-                            (dns_record.id, app_deployment_request.id))
+                            (dns_crn, app_deployment_request.id))
+    elif "preexisting" == fqdn_policy:
+        raise Exception(f"No pre-existing DnsRecord {dns_crn} could be found for request {app_deployment_request.id}.")
 
     # 4. get build and runtime config from request
     env_filename = None
@@ -191,6 +195,7 @@ def dump_known_requests(filename, requests, status="SEEN"):
 @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("--dns-suffix", help="DNS domain to use eg, laconic.servesthe.world")
+@click.option("--fqdn-policy", help="How to handle requests with an FQDN: prohibit, allow, preexisting", default="prohibit")
 @click.option("--record-namespace-dns", help="eg, crn://laconic/dns")
 @click.option("--record-namespace-deployments", help="eg, crn://laconic/deployments")
 @click.option("--dry-run", help="Don't do anything, just report what would be done.", is_flag=True)
@@ -201,7 +206,7 @@ def dump_known_requests(filename, requests, status="SEEN"):
 @click.pass_context
 def command(ctx, kube_config, laconic_config, image_registry, deployment_parent_dir,  # noqa: C901
             request_id, discover, state_file, only_update_state,
-            dns_suffix, record_namespace_dns, record_namespace_deployments, dry_run,
+            dns_suffix, fqdn_policy, record_namespace_dns, record_namespace_deployments, dry_run,
             include_tags, exclude_tags, force_rebuild, log_dir):
     if request_id and discover:
         print("Cannot specify both --request-id and --discover", file=sys.stderr)
@@ -220,6 +225,10 @@ def command(ctx, kube_config, laconic_config, image_registry, deployment_parent_
             print("--dns-suffix, --record-namespace-dns, and --record-namespace-deployments are all required", file=sys.stderr)
             sys.exit(2)
 
+    if fqdn_policy not in ["prohibit", "allow", "preexisting"]:
+        print("--fqdn-policy must be one of 'prohibit', 'allow', or 'preexisting'", file=sys.stderr)
+        sys.exit(2)
+
     # Split CSV and clean up values.
     include_tags = [tag.strip() for tag in include_tags.split(",") if tag]
     exclude_tags = [tag.strip() for tag in exclude_tags.split(",") if tag]
@@ -247,7 +256,10 @@ def command(ctx, kube_config, laconic_config, image_registry, deployment_parent_
     requests_by_name = {}
     skipped_by_name = {}
     for r in requests:
-        # TODO: Do this _after_ filtering deployments and cancellations to minimize round trips.
+        if r.id in previous_requests and previous_requests[r.id].get("status", "") != "RETRY":
+            print(f"Skipping request {r.id}, we've already seen it.")
+            continue
+
         app = laconic.get_record(r.attributes.application)
         if not app:
             print("Skipping request %s, cannot locate app." % r.id)
@@ -334,6 +346,7 @@ def command(ctx, kube_config, laconic_config, image_registry, deployment_parent_
                     kube_config,
                     image_registry,
                     force_rebuild,
+                    fqdn_policy,
                     logger
                 )
                 status = "DEPLOYED"

stack_orchestrator/main.py

@@ -17,6 +17,7 @@ import click
 
 from stack_orchestrator.command_types import CommandOptions
 from stack_orchestrator.repos import setup_repositories
+from stack_orchestrator.repos import fetch_stack
 from stack_orchestrator.build import build_containers, fetch_containers
 from stack_orchestrator.build import build_npms
 from stack_orchestrator.build import build_webapp
@@ -50,6 +51,7 @@ def cli(ctx, stack, quiet, verbose, dry_run, local_stack, debug, continue_on_err
     ctx.obj = command_options
 
 
+cli.add_command(fetch_stack.command, "fetch-stack")
 cli.add_command(setup_repositories.command, "setup-repositories")
 cli.add_command(build_containers.command, "build-containers")
 cli.add_command(fetch_containers.command, "fetch-containers")

stack_orchestrator/repos/fetch_stack.py

@@ -0,0 +1,45 @@
+# Copyright © 2022, 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/>.
+
+# env vars:
+# CERC_REPO_BASE_DIR defaults to ~/cerc
+
+
+import click
+import os
+
+from decouple import config
+from git import exc
+
+from stack_orchestrator.opts import opts
+from stack_orchestrator.repos.setup_repositories import process_repo
+from stack_orchestrator.util import error_exit
+
+
+@click.command()
+@click.argument('stack-locator')
+@click.option('--git-ssh', is_flag=True, default=False)
+@click.option('--check-only', is_flag=True, default=False)
+@click.option('--pull', is_flag=True, default=False)
+@click.pass_context
+def command(ctx, stack_locator, git_ssh, check_only, pull):
+    '''optionally resolve then git clone a repository containing one or more stack definitions'''
+    dev_root_path = os.path.expanduser(config("CERC_REPO_BASE_DIR", default="~/cerc"))
+    if not opts.o.quiet:
+        print(f"Dev Root is: {dev_root_path}")
+    try:
+        process_repo(pull, check_only, git_ssh, dev_root_path, None, stack_locator)
+    except exc.GitCommandError as error:
+        error_exit(f"\n******* git command returned error exit status:\n{error}")

stack_orchestrator/repos/setup_repositories.py

@@ -26,6 +26,7 @@ import importlib.resources
 from pathlib import Path
 import yaml
 from stack_orchestrator.constants import stack_file_name
+from stack_orchestrator.opts import opts
 from stack_orchestrator.util import include_exclude_check, stack_is_external, error_exit, warn_exit
 
 
@@ -87,8 +88,8 @@ def _get_repo_current_branch_or_tag(full_filesystem_repo_path):
 
 
 # TODO: fix the messy arg list here
-def process_repo(verbose, quiet, dry_run, pull, check_only, git_ssh, dev_root_path, branches_array, fully_qualified_repo):
-    if verbose:
+def process_repo(pull, check_only, git_ssh, dev_root_path, branches_array, fully_qualified_repo):
+    if opts.o.verbose:
         print(f"Processing repo: {fully_qualified_repo}")
     repo_host, repo_path, repo_branch = host_and_path_for_repo(fully_qualified_repo)
     git_ssh_prefix = f"git@{repo_host}:"
@@ -100,7 +101,7 @@ def process_repo(verbose, quiet, dry_run, pull, check_only, git_ssh, dev_root_pa
     (current_repo_branch_or_tag, is_branch) = _get_repo_current_branch_or_tag(
         full_filesystem_repo_path
         ) if is_present else (None, None)
-    if not quiet:
+    if not opts.o.quiet:
         present_text = f"already exists active {'branch' if is_branch else 'tag'}: {current_repo_branch_or_tag}" if is_present \
             else 'Needs to be fetched'
         print(f"Checking: {full_filesystem_repo_path}: {present_text}")
@@ -111,25 +112,25 @@ def process_repo(verbose, quiet, dry_run, pull, check_only, git_ssh, dev_root_pa
             sys.exit(1)
         else:
             if pull:
-                if verbose:
+                if opts.o.verbose:
                     print(f"Running git pull for {full_filesystem_repo_path}")
                 if not check_only:
                     if is_branch:
                         git_repo = git.Repo(full_filesystem_repo_path)
                         origin = git_repo.remotes.origin
-                        origin.pull(progress=None if quiet else GitProgress())
+                        origin.pull(progress=None if opts.o.quiet else GitProgress())
                     else:
                         print("skipping pull because this repo checked out a tag")
                 else:
                     print("(git pull skipped)")
     if not is_present:
         # Clone
-        if verbose:
+        if opts.o.verbose:
             print(f'Running git clone for {full_github_repo_path} into {full_filesystem_repo_path}')
-        if not dry_run:
+        if not opts.o.dry_run:
             git.Repo.clone_from(full_github_repo_path,
                                 full_filesystem_repo_path,
-                                progress=None if quiet else GitProgress())
+                                progress=None if opts.o.quiet else GitProgress())
         else:
             print("(git clone skipped)")
     # Checkout the requested branch, if one was specified
@@ -150,13 +151,13 @@ def process_repo(verbose, quiet, dry_run, pull, check_only, git_ssh, dev_root_pa
             current_repo_branch_or_tag and (
                 current_repo_branch_or_tag != branch_to_checkout)
                 ):
-            if not quiet:
+            if not opts.o.quiet:
                 print(f"switching to branch {branch_to_checkout} in repo {repo_path}")
             git_repo = git.Repo(full_filesystem_repo_path)
             # git checkout works for both branches and tags
             git_repo.git.checkout(branch_to_checkout)
         else:
-            if verbose:
+            if opts.o.verbose:
                 print(f"repo {repo_path} is already on branch/tag {branch_to_checkout}")
 
 
@@ -182,36 +183,18 @@ def parse_branches(branches_string):
 @click.option('--check-only', is_flag=True, default=False)
 @click.option('--pull', is_flag=True, default=False)
 @click.option("--branches", help="override branches for repositories")
-@click.option('--branches-file', help="checkout branches specified in this file")
 @click.pass_context
-def command(ctx, include, exclude, git_ssh, check_only, pull, branches, branches_file):
+def command(ctx, include, exclude, git_ssh, check_only, pull, branches):
     '''git clone the set of repositories required to build the complete system from source'''
 
-    quiet = ctx.obj.quiet
-    verbose = ctx.obj.verbose
-    dry_run = ctx.obj.dry_run
-    stack = ctx.obj.stack
+    quiet = opts.o.quiet
+    verbose = opts.o.verbose
+    stack = opts.o.stack
 
     branches_array = []
 
-    # TODO: branches file needs to be re-worked in the context of stacks
-    if branches_file:
-        if branches:
-            print("Error: can't specify both --branches and --branches-file")
-            sys.exit(1)
-        else:
-            if verbose:
-                print(f"loading branches from: {branches_file}")
-            with open(branches_file) as branches_file_open:
-                branches_array = branches_file_open.read().splitlines()
-
-    print(f"branches: {branches}")
     if branches:
-        if branches_file:
-            print("Error: can't specify both --branches and --branches-file")
-            sys.exit(1)
-        else:
-            branches_array = parse_branches(branches)
+        branches_array = parse_branches(branches)
 
     if branches_array and verbose:
         print(f"Branches are: {branches_array}")
@@ -271,7 +254,6 @@ def command(ctx, include, exclude, git_ssh, check_only, pull, branches, branches
 
     for repo in repos:
         try:
-            process_repo(verbose, quiet, dry_run, pull, check_only, git_ssh, dev_root_path, branches_array, repo)
+            process_repo(pull, check_only, git_ssh, dev_root_path, branches_array, repo)
         except git.exc.GitCommandError as error:
-            print(f"\n******* git command returned error exit status:\n{error}")
-            sys.exit(1)
+            error_exit(f"\n******* git command returned error exit status:\n{error}")

stack_orchestrator/util.py

@@ -94,10 +94,38 @@ def get_plugin_code_paths(stack) -> List[Path]:
     return list(result)
 
 
-def get_pod_file_path(parsed_stack, pod_name: str):
+# # Find a config directory, looking first in any external stack
+# and if not found there, internally
+def resolve_config_dir(stack, config_dir_name: str):
+    if stack_is_external(stack):
+        # First try looking in the external stack for the compose file
+        config_base = Path(stack).parent.parent.joinpath("config")
+        proposed_dir = config_base.joinpath(config_dir_name)
+        if proposed_dir.exists():
+            return proposed_dir
+        # If we don't find it fall through to the internal case
+    config_base = get_internal_config_dir()
+    return config_base.joinpath(config_dir_name)
+
+
+# Find a compose file, looking first in any external stack
+# and if not found there, internally
+def resolve_compose_file(stack, pod_name: str):
+    if stack_is_external(stack):
+        # First try looking in the external stack for the compose file
+        compose_base = Path(stack).parent.parent.joinpath("compose")
+        proposed_file = compose_base.joinpath(f"docker-compose-{pod_name}.yml")
+        if proposed_file.exists():
+            return proposed_file
+        # If we don't find it fall through to the internal case
+    compose_base = get_internal_compose_file_dir()
+    return compose_base.joinpath(f"docker-compose-{pod_name}.yml")
+
+
+def get_pod_file_path(stack, parsed_stack, pod_name: str):
     pods = parsed_stack["pods"]
     if type(pods[0]) is str:
-        result = os.path.join(get_compose_file_dir(), f"docker-compose-{pod_name}.yml")
+        result = resolve_compose_file(stack, pod_name)
     else:
         for pod in pods:
             if pod["name"] == pod_name:
@@ -131,7 +159,7 @@ def pod_has_scripts(parsed_stack, pod_name: str):
     return result
 
 
-def get_compose_file_dir():
+def get_internal_compose_file_dir():
     # TODO: refactor to use common code with deploy command
     # See: https://stackoverflow.com/questions/25389095/python-get-path-of-root-project-structure
     data_dir = Path(__file__).absolute().parent.joinpath("data")
@@ -139,7 +167,7 @@ def get_compose_file_dir():
     return source_compose_dir
 
 
-def get_config_file_dir():
+def get_internal_config_dir():
     # TODO: refactor to use common code with deploy command
     data_dir = Path(__file__).absolute().parent.joinpath("data")
     source_config_dir = data_dir.joinpath("config")

tests/external-stack/run-test.sh

@@ -0,0 +1,185 @@
+#!/usr/bin/env bash
+set -e
+if [ -n "$CERC_SCRIPT_DEBUG" ]; then
+  set -x
+fi
+# Dump environment variables for debugging
+echo "Environment variables:"
+env
+
+if [ "$1" == "from-path" ]; then
+    TEST_TARGET_SO="laconic-so"
+else
+    TEST_TARGET_SO=$( ls -t1 ./package/laconic-so* | head -1 )
+fi
+
+delete_cluster_exit () {
+    $TEST_TARGET_SO deployment --dir $test_deployment_dir stop --delete-volumes
+    exit 1
+}
+
+# Test basic stack-orchestrator deploy
+echo "Running stack-orchestrator external stack deploy test"
+# Set a non-default repo dir
+export CERC_REPO_BASE_DIR=~/stack-orchestrator-test/repo-base-dir
+echo "Testing this package: $TEST_TARGET_SO"
+echo "Test version command"
+reported_version_string=$( $TEST_TARGET_SO version )
+echo "Version reported is: ${reported_version_string}"
+echo "Cloning repositories into: $CERC_REPO_BASE_DIR"
+rm -rf $CERC_REPO_BASE_DIR
+mkdir -p $CERC_REPO_BASE_DIR
+# Clone the external test stack
+$TEST_TARGET_SO fetch-stack git.vdb.to/cerc-io/test-external-stack
+stack_name="$CERC_REPO_BASE_DIR/test-external-stack/stack-orchestrator/stacks/test-external-stack"
+TEST_TARGET_SO_STACK="$TEST_TARGET_SO --stack ${stack_name}"
+# Test bringing the test container up and down
+# with and without volume removal
+$TEST_TARGET_SO_STACK setup-repositories
+$TEST_TARGET_SO_STACK build-containers
+# Test deploy command execution
+$TEST_TARGET_SO_STACK deploy setup $CERC_REPO_BASE_DIR
+# Check that we now have the expected output directory
+container_output_dir=$CERC_REPO_BASE_DIR/container-output-dir
+if [ ! -d "$container_output_dir" ]; then
+    echo "deploy setup test: output directory not present"
+    echo "deploy setup test: FAILED"
+    exit 1
+fi
+if [ ! -f "$container_output_dir/output-file" ]; then
+    echo "deploy setup test: output file not present"
+    echo "deploy setup test: FAILED"
+    exit 1
+fi
+output_file_content=$(<$container_output_dir/output-file)
+if [ ! "$output_file_content" == "output-data"  ]; then
+    echo "deploy setup test: output file contents not correct"
+    echo "deploy setup test: FAILED"
+    exit 1
+fi
+# Check that we now have the expected output file
+$TEST_TARGET_SO_STACK deploy up
+# Test deploy port command
+deploy_port_output=$( $TEST_TARGET_SO_STACK deploy port test 80 )
+if [[ "$deploy_port_output" =~ ^0.0.0.0:[1-9][0-9]* ]]; then
+    echo "Deploy port test: passed"
+else
+    echo "Deploy port test: FAILED"
+    exit 1
+fi
+$TEST_TARGET_SO_STACK deploy down
+# The next time we bring the container up the volume will be old (from the previous run above)
+$TEST_TARGET_SO_STACK deploy up
+log_output_1=$( $TEST_TARGET_SO_STACK deploy logs )
+if [[ "$log_output_1" == *"filesystem is old"* ]]; then
+    echo "Retain volumes test: passed"
+else
+    echo "Retain volumes test: FAILED"
+    exit 1
+fi
+$TEST_TARGET_SO_STACK deploy down --delete-volumes
+# Now when we bring the container up the volume will be new again
+$TEST_TARGET_SO_STACK deploy up
+log_output_2=$( $TEST_TARGET_SO_STACK deploy logs )
+if [[ "$log_output_2" == *"filesystem is fresh"* ]]; then
+    echo "Delete volumes test: passed"
+else
+    echo "Delete volumes test: FAILED"
+    exit 1
+fi
+$TEST_TARGET_SO_STACK deploy down --delete-volumes
+# Basic test of creating a deployment
+test_deployment_dir=$CERC_REPO_BASE_DIR/test-deployment-dir
+test_deployment_spec=$CERC_REPO_BASE_DIR/test-deployment-spec.yml
+$TEST_TARGET_SO_STACK deploy init --output $test_deployment_spec --config CERC_TEST_PARAM_1=PASSED,CERC_TEST_PARAM_3=FAST
+# Check the file now exists
+if [ ! -f "$test_deployment_spec" ]; then
+    echo "deploy init test: spec file not present"
+    echo "deploy init test: FAILED"
+    exit 1
+fi
+echo "deploy init test: passed"
+$TEST_TARGET_SO_STACK deploy create --spec-file $test_deployment_spec --deployment-dir $test_deployment_dir
+# Check the deployment dir exists
+if [ ! -d "$test_deployment_dir" ]; then
+    echo "deploy create test: deployment directory not present"
+    echo "deploy create test: FAILED"
+    exit 1
+fi
+echo "deploy create test: passed"
+# Check the file writted by the create command in the stack now exists
+if [ ! -f "$test_deployment_dir/create-file" ]; then
+    echo "deploy create test: create output file not present"
+    echo "deploy create test: FAILED"
+    exit 1
+fi
+# And has the right content
+create_file_content=$(<$test_deployment_dir/create-file)
+if [ ! "$create_file_content" == "create-command-output-data"  ]; then
+    echo "deploy create test: create output file contents not correct"
+    echo "deploy create test: FAILED"
+    exit 1
+fi
+
+# Add a config file to be picked up by the ConfigMap before starting.
+echo "dbfc7a4d-44a7-416d-b5f3-29842cc47650" > $test_deployment_dir/data/test-config/test_config
+
+echo "deploy create output file test: passed"
+# Try to start the deployment
+$TEST_TARGET_SO deployment --dir $test_deployment_dir start
+# Check logs command works
+log_output_3=$( $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
+fi
+# Check the config variable CERC_TEST_PARAM_1 was passed correctly
+if [[ "$log_output_3" == *"Test-param-1: PASSED"* ]]; then
+    echo "deployment config test: passed"
+else
+    echo "deployment config test: FAILED"
+    exit 1
+fi
+# Check the config variable CERC_TEST_PARAM_2 was passed correctly from the compose file
+if [[ "$log_output_3" == *"Test-param-2: CERC_TEST_PARAM_2_VALUE"* ]]; then
+    echo "deployment compose config test: passed"
+else
+    echo "deployment compose config test: FAILED"
+    exit 1
+fi
+# Check the config variable CERC_TEST_PARAM_3 was passed correctly
+if [[ "$log_output_3" == *"Test-param-3: FAST"* ]]; then
+    echo "deployment config test: passed"
+else
+    echo "deployment config test: FAILED"
+    exit 1
+fi
+
+# Check that the ConfigMap is mounted and contains the expected content.
+log_output_4=$( $TEST_TARGET_SO deployment --dir $test_deployment_dir logs )
+if [[ "$log_output_4" == *"/config/test_config:"* ]] && [[ "$log_output_4" == *"dbfc7a4d-44a7-416d-b5f3-29842cc47650"* ]]; then
+    echo "deployment ConfigMap test: passed"
+else
+    echo "deployment ConfigMap test: FAILED"
+    delete_cluster_exit
+fi
+
+# Stop then start again and check the volume was preserved
+$TEST_TARGET_SO deployment --dir $test_deployment_dir stop
+# Sleep a bit just in case
+# sleep for longer to check if that's why the subsequent create cluster fails
+sleep 20
+$TEST_TARGET_SO deployment --dir $test_deployment_dir start
+log_output_5=$( $TEST_TARGET_SO deployment --dir $test_deployment_dir logs )
+if [[ "$log_output_5" == *"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
+echo "Test passed"