Configure prometheus alert manager with Slack notifications

Upgrade watchers and their config (#827 )
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>
2024-05-31 20:22:25 +05:30 · 2024-05-23 04:12:31 +00:00 · 2024-05-22 19:00:42 +00:00 · 2024-05-22 18:31:57 +00:00 · 2024-05-22 18:18:27 +00:00 · 2024-05-22 17:42:28 +00:00
42 changed files with 974 additions and 183 deletions
@@ -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:
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -1 +1,2 @@
 Change this file to trigger running the external-stack CI job
+trigger
@@ -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:
@@ -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:
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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>
@@ -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": ""
 }
@@ -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
@@ -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'
@@ -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
@@ -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
@@ -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 "$WATCHER_CONFIG" > environments/local.toml
@@ -6,12 +6,16 @@ if [ -n "$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
@@ -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
@@ -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
@@ -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
@@ -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
@@ -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 "$WATCHER_CONFIG" > environments/local.toml
@@ -6,12 +6,16 @@ if [ -n "$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
@@ -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
@@ -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 "$WATCHER_CONFIG" > environments/local.toml
@@ -6,12 +6,16 @@ if [ -n "$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
@@ -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
@@ -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}"
@@ -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
@@ -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:
@@ -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
 ```
@@ -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:
@@ -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
@@ -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:
@@ -113,21 +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 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/
+
+  # 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
  ...
@@ -135,7 +145,7 @@ Add corresponding routes to the notification policies config (`monitoring-watche
      - receiver: SlackNotifier
      object_matchers:
        # Add matchers below
-        - ['grafana_folder', '=', 'WatcherAlerts']
+        - ['grafana_folder', '=~', 'WatcherAlerts|SubgraphAlerts']
  ```

 ### Env
@@ -149,6 +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
@@ -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
@@ -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:
@@ -31,7 +31,7 @@ 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/stacks/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
Author	SHA1	Message	Date
prathamesh	b036e26087	Configure prometheus alert manager with Slack notifications	2024-05-31 20:22:25 +05:30
prathameshandnabarun	ed8914b8d3	Upgrade watchers and their config (#827 ) 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>	2024-05-23 04:12:31 +00:00
telackey	fef7649683	Refactor SPA check. (#831 ) Reviewed-on: cerc-io/stack-orchestrator#831 Co-authored-by: Thomas E Lackey <telackey@bozemanpass.com> Co-committed-by: Thomas E Lackey <telackey@bozemanpass.com>	2024-05-22 19:00:42 +00:00
telackey	579b402f2f	Make the SPA detection even simpler. (#830 ) Reviewed-on: cerc-io/stack-orchestrator#830 Co-authored-by: Thomas E Lackey <telackey@bozemanpass.com> Co-committed-by: Thomas E Lackey <telackey@bozemanpass.com>	2024-05-22 18:31:57 +00:00
telackey	25d0bc8a98	Case insensitive comparison (#829 ) Reviewed-on: cerc-io/stack-orchestrator#829 Co-authored-by: Thomas E Lackey <telackey@bozemanpass.com> Co-committed-by: Thomas E Lackey <telackey@bozemanpass.com>	2024-05-22 18:18:27 +00:00
telackey	855288368c	Add messages around the SPA auto-detect. (#828 ) Tweak the auto-detection logic slightly for single-page apps, and also print the results. Reviewed-on: cerc-io/stack-orchestrator#828 Co-authored-by: Thomas E Lackey <telackey@bozemanpass.com> Co-committed-by: Thomas E Lackey <telackey@bozemanpass.com>	2024-05-22 17:42:28 +00:00
prathamesh	8f2da38183	Add alerts for graph-node subgraphs (#821 ) Part of [Deploy v2 and updated v3 sushiswap subgraphs](https://www.notion.so/Deploy-v2-and-updated-v3-sushiswap-subgraphs-e331945fdeea487c890706fc22c6cc94) Reviewed-on: cerc-io/stack-orchestrator#821 Co-authored-by: Prathamesh Musale <prathamesh.musale0@gmail.com> Co-committed-by: Prathamesh Musale <prathamesh.musale0@gmail.com>	2024-05-17 04:01:41 +00:00
dboreham	254f95e59f	Merge pull request 'Remove legacy commands for docker startup' (#826 ) from dboreham/remove-old-docker-ci into main Reviewed-on: cerc-io/stack-orchestrator#826	2024-05-15 16:09:09 +00:00
dboreham	0acb6ea6bc	Remove legacy commands for docker startup	2024-05-15 09:04:19 -06:00
prathamesh	b9369a13e6	Update watcher dashboard with panels for ETH RPC request failures and durations (#825 ) Part of [Regenerate ajna watcher with updated subgraph config ](https://www.notion.so/Regenerate-ajna-watcher-with-updated-subgraph-config-c9bbecb033024c13a7515c7f1efc3363) Requires [Add metrics to monitor errors and duration for ETH RPC requests](https://github.com/cerc-io/watcher-ts/pull/507) Reviewed-on: cerc-io/stack-orchestrator#825 Co-authored-by: Prathamesh Musale <prathamesh.musale0@gmail.com> Co-committed-by: Prathamesh Musale <prathamesh.musale0@gmail.com>	2024-05-15 13:52:18 +00:00
prathamesh	0b1eb8eb0f	Update ajna-watcher version in ajna stack (#824 ) Part of [Regenerate ajna watcher with updated subgraph config](https://www.notion.so/Regenerate-ajna-watcher-with-updated-subgraph-config-c9bbecb033024c13a7515c7f1efc3363) Reviewed-on: cerc-io/stack-orchestrator#824 Co-authored-by: Prathamesh Musale <prathamesh.musale0@gmail.com> Co-committed-by: Prathamesh Musale <prathamesh.musale0@gmail.com>	2024-05-14 08:27:59 +00:00
nabarun	78092f5793	Update subgraph watcher stacks to configure multiple RPC endpoints (#822 ) Part of [Ability to configure watchers with multiple RPC endpoints](https://www.notion.so/Ability-to-configure-watchers-with-multiple-RPC-endpoints-dc8d3ff4d647404ab718dfd5a4c9035c) Reviewed-on: cerc-io/stack-orchestrator#822 Co-authored-by: Nabarun <nabarun@deepstacksoft.com> Co-committed-by: Nabarun <nabarun@deepstacksoft.com>	2024-05-10 04:58:30 +00:00
prathameshandnabarun	247dbdd2f0	Update subgraph watcher versions for improved `eth_getLogs` calls (#820 ) 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#820 Co-authored-by: Prathamesh Musale <prathamesh.musale0@gmail.com> Co-committed-by: Prathamesh Musale <prathamesh.musale0@gmail.com>	2024-05-07 04:18:45 +00:00
dboreham	30db1f58d0	Refactor for new external stack directory layout under common parent (#815 ) Reviewed-on: cerc-io/stack-orchestrator#815 Co-authored-by: David Boreham <david@bozemanpass.com> Co-committed-by: David Boreham <david@bozemanpass.com>	2024-04-29 23:03:20 +00:00