Merge remote-tracking branch 'origin/dev' into Add-kafka-messages-con…

…sumer-to-the-Framework

.github/workflows/control.yml

@@ -34,7 +34,7 @@ jobs:
       - run: (cd Control; npm run coverage )
       - run: (cd Control; ./node_modules/.bin/nyc report --reporter=text-lcov > coverage.lcov)
       - name: Send codecov report for Control
-        uses: codecov/codecov-action@v4
+        uses: codecov/codecov-action@v5
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
           flags: control

.github/workflows/framework.yml

@@ -34,7 +34,7 @@ jobs:
       - run: (cd Framework; npm run coverage )
       - run: (cd Framework; ./node_modules/.bin/nyc report --reporter=text-lcov > coverage.lcov)
       - name: Send codecov report for Framework
-        uses: codecov/codecov-action@v4
+        uses: codecov/codecov-action@v5
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
           flags: framework

.github/workflows/infologger.yml

@@ -32,7 +32,7 @@ jobs:
       - run: (cd InfoLogger; npm run coverage )
       - run: (cd InfoLogger; ./node_modules/.bin/nyc report --reporter=text-lcov > coverage.lcov)
       - name: Send codecov report for InfoLogger
-        uses: codecov/codecov-action@v4
+        uses: codecov/codecov-action@v5
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
           flags: infologger

.github/workflows/qc.yml

@@ -10,32 +10,44 @@ on:
       - 'dev'
 
 jobs:
+  lint-check:
+    name: Check eslint rules on ubuntu-latest
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Setup node
+        uses: actions/setup-node@v4
+        with:
+          node-version: '20.x'
+      - run: (cd QualityControl; npm ci )
+      - run: (cd QualityControl; npm run lint )
   test:
-    name: Tests on ubuntu-latest
+    name: Tests on ubuntu-latest only if lint-check passes
+    runs-on: ubuntu-latest
+    needs: lint-check
+    steps:
+      - uses: actions/checkout@v4
+      - name: Setup node
+        uses: actions/setup-node@v4
+        with:
+          node-version: '20.x'
+      - run: (cd QualityControl; npm ci )
+      - run: (cd QualityControl; npm run test )
+  coverage:
+    name: Tests and generate lcov reoprt coverage on ubuntu-latest
     runs-on: ubuntu-latest
+    needs: lint-check
     steps:
       - uses: actions/checkout@v4
       - name: Setup node
         uses: actions/setup-node@v4
         with:
           node-version: '20.x'
       - run: (cd QualityControl; npm ci )
-      - run: (cd QualityControl; npm run coverage )
-      - run: (cd QualityControl; ./node_modules/.bin/nyc report --reporter=text-lcov > coverage.lcov)
+      - run: (cd QualityControl; npm run coverage-lcov )
       - name: Send codecov report for QualityControl
-        uses: codecov/codecov-action@v4
+        uses: codecov/codecov-action@v5
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
           flags: qualitycontrol
           fail_ci_if_error: true
-  #coverage:  Job is currently disabled due to known issue with node-gyp on GH runners
-  #  name: Tests & coverage on macOS-latest
-  #  runs-on: macOS-latest
-  #  steps:
-  #    - uses: actions/checkout@v4
-  #    - name: Setup node
-  #      uses: actions/setup-node@v4
-  #      with:
-  #        node-version: '20.x'
-  #    - run: (cd QualityControl; npm ci )
-  #    - run: (cd QualityControl; npm run test)

.gitignore

@@ -5,5 +5,6 @@ build
 tobject2json.node
 */.nyc*
 */test/integration/test-config*
-.vscode
+.vscode/*
+!.vscode/launch.json
 .idea

.vscode/launch.json

@@ -0,0 +1,23 @@
+{
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "[ilg] run dev",
+            "request": "launch",
+            "runtimeArgs": [
+                "run-script",
+                "dev"
+            ],
+            "localRoot": "${workspaceFolder}/InfoLogger/",
+            "runtimeExecutable": "npm",
+            "skipFiles": [
+                "<node_internals>/**"
+            ],
+            "outputCapture": "std",
+            "type": "node",
+            "windows": {
+                "localRoot": "${workspaceFolder}\\InfoLogger\\"
+            }
+        }
+    ]
+}

Control/lib/adapters/DcsIntegratedEventAdapter.js

@@ -11,8 +11,15 @@
  * or submit itself to any jurisdiction.
  */
 
+const {
+  EcsOperationAndStepStatus: {
+    DONE_ERROR,
+    DONE_TIMEOUT
+  }
+} = require('../common/ecsOperationAndStepStatus.enum.js');
+
 /**
- * DcsIntegratedEventAdapter - Given an AliECS Integrated Service Event for DCS.SOR, build a DCS Integrated Event
+ * @class DcsIntegratedEventAdapter - Given an AliECS Integrated Service Event for DCS.SOR, build a DCS Integrated Event
  * 
  * The DCS SOR event is a special event that comes from either:
  * * the DCS service itself (when containing the payload "dcsEvent") and it is for one detector only
@@ -26,7 +33,77 @@ class DcsIntegratedEventAdapter {
   }
 
   /**
-   * Build a DCS Integrated Event from an AliECS Integrated Service Event. If it is a DCSevent, the detector will replace detectors array
+   * Build a DCS Integrated Event from an AliECS Integrated Service Event - SOR. If it is a DCSevent, the detector will replace detectors array
+   * 
+   * // IntegratedService event, related to SOR but with a failure on ECS side (such as timeout)
+   * @example 
+   * {
+   *  "timestamp": 1733497646607,
+   *  "integratedServiceEvent": {
+   *    "name": "readout-dataflow.dcs.sor",
+   *    "error": "DCS SOR timed out after 1s: rpc error: code = DeadlineExceeded desc = Deadline Exceeded",
+   *    "operationName": "dcs.StartOfRun()",
+   *    "operationStatus": "ONGOING",
+   *    "operationStep": "perform DCS call: StartOfRun",
+   *    "operationStepStatus": "DONE_TIMEOUT",
+   *    "environmentId": "2rRm96N9k7E", 
+   *    "payload": "{\"detectors\":[\"EMC\"],\"detectorsReadiness\":{\"EMC\":\"SOR_AVAILABLE\"},\"runNumber\":1601}"
+   * }
+   * // IntegratedService event with final state DONE_ERROR following the DONE_TIMEOUT from above
+   * @example 
+   * {
+   *  "timestamp": 1734004912438,  
+   *  "integratedServiceEvent": {
+   *    "name": "readout-dataflow.dcs.sor",
+   *    "error": "DCS SOR timed out after 100ms: rpc error: code = DeadlineExceeded desc = context deadline exceeded : SOR failed for EMC, FDD, DCS EOR will run anyway for this run",
+   *    "operationName": "dcs.StartOfRun()",
+   *    "operationStatus": "DONE_ERROR",
+   *    "operationStep": "perform DCS call: StartOfRun",
+   *    "operationStepStatus": "DONE_ERROR",
+   *    "environmentId": "2rYQabnjWy2",
+   *    "payload": "{\"detectors\":[\"EMC\",\"FDD\"],\"detectorsReadiness\":{\"EMC\":\"SOR_AVAILABLE\",\"FDD\":\"SOR_AVAILABLE\"},\"failedDetectors\":[\"EMC\",\"FDD\"],\"runNumber\":1622}"
+   * }
+   * 
+   * // IntegratedService event, related to SOR_PROGRESSING with payload from DCS
+   * @example 
+   * {
+   *  "timestamp": 1734004912360,
+   *  "timestampNano": 1734004912360675322,
+   *  "environmentEvent": null,
+   *  "taskEvent": null,
+   *  "roleEvent": null,
+   *  "callEvent": null,
+   *  "integratedServiceEvent": {
+   *    "name": "readout-dataflow.dcs.sor",
+   *    "error": null,
+   *    "operationName": "dcs.StartOfRun()",
+   *    "operationStatus": "ONGOING",
+   *    "operationStep": "perform DCS call: StartOfRun",
+   *    "operationStepStatus": "ONGOING",
+   *    "environmentId": "2rYQabnjWy2",
+   *    "payload": \"{
+   *      \"dcsEvent\": { 
+   *      \"eventtype\":20,
+   *      \"detector\":2,
+   *      \"state\":5,\"
+   *      extraParameters\":{
+   *        \"run_no\":\"1622\"
+   *      },
+   *      \"timestamp\":\"2024-12-12 13:01:52.358\",
+   *      \"message\":\"run_type\"
+   *    },
+   *    \"detector\":\"EMC\",
+   *    \"detectors\":[\"EMC\",\"FDD\"],
+   *    \"detectorsReadiness\":{
+   *      \"EMC\":\"SOR_AVAILABLE\",
+   *      \"FDD\":\"SOR_AVAILABLE\"
+   *    },
+   *    \"runNumber\":1622,
+   *    \"state\":\"SOR_PROGRESSING\"
+   *  }"
+   * }
+   *
+   * Final OperationStates: DONE_TIMEOUT/DONE_ERROR/DONE_OK
    * @param {object} event - AliECS Integrated Service Event
    * @param {number} timestamp - timestamp of the event (int64 as per proto file definition)
    * @return {object} DCS Integrated Event
@@ -37,7 +114,13 @@ class DcsIntegratedEventAdapter {
 
     const payloadJSON = JSON.parse(payload);
     const { dcsEvent, runNumber, detector = null, state } = payloadJSON;
-    if (!dcsEvent) {
+
+    if (!dcsEvent
+        && operationStatus !== DONE_ERROR && operationStatus !== DONE_TIMEOUT
+        && operationStepStatus !== DONE_ERROR && operationStepStatus !== DONE_TIMEOUT
+    ) {
+      // if there is no DCS event and status is not final error or timeout, we ignore the event as we expect to have `RUN_OK` from DCS as final state
+      // or DONE_TIMEOUT or DONE_ERROR from ECS. We are not interested in DONE_OK from ECS as this means all detectors in RUN_OK which we already look for
       return null;
     }
     let { detectors } = payloadJSON;

Control/lib/api.js

@@ -19,6 +19,8 @@ const config = require('./config/configProvider.js');
 
 // middleware
 const {minimumRoleMiddleware} = require('./middleware/minimumRole.middleware.js');
+const {addDetectorIdMiddleware} = require('./middleware/addDetectorId.middleware.js');
+const {DetectorId} = require('./common/detectorId.enum.js');
 const {lockOwnershipMiddleware} = require('./middleware/lockOwnership.middleware.js');
 
 // controllers
@@ -117,15 +119,20 @@ module.exports.setup = (http, ws) => {
 
   let aliEcsSynchronizer = undefined;
   if (config.kafka && config.kafka?.enable) {
-    const kafkaClient = new Kafka({
-      clientId: 'control-gui',
-      brokers: config.kafka.brokers,
-      retry: { retries: 3 },
-      logLevel: logLevel.NOTHING,
-    });
-
-    aliEcsSynchronizer = new AliEcsSynchronizer(kafkaClient, cacheService);
-    aliEcsSynchronizer.start();
+    try {
+      const kafkaClient = new Kafka({
+        clientId: 'control-gui',
+        brokers: config.kafka.brokers,
+        retry: { retries: 3 },
+        logLevel: logLevel.NOTHING,
+      });
+      aliEcsSynchronizer = new AliEcsSynchronizer(kafkaClient, cacheService);
+      aliEcsSynchronizer.start();
+
+    } catch (error) {
+      logger.errorMessage(`Kafka initialization failed: ${error.message}`);
+    }
+
   }
 
   const statusService = new StatusService(
@@ -184,7 +191,17 @@ module.exports.setup = (http, ws) => {
 
   // Lock Service
   http.get('/locks', lockController.getLocksStateHandler.bind(lockController));
-  http.put('/locks/:action/:detectorId', lockController.actionLockHandler.bind(lockController));
+
+  http.put(`/locks/:action/${DetectorId.ALL}`,
+    minimumRoleMiddleware(Role.GLOBAL),
+    addDetectorIdMiddleware(DetectorId.ALL),
+    lockController.actionLockHandler.bind(lockController)
+  );
+
+  http.put('/locks/:action/:detectorId',
+    minimumRoleMiddleware(Role.DETECTOR),
+    lockController.actionLockHandler.bind(lockController)
+  );
   http.put('/locks/force/:action/:detectorId',
     minimumRoleMiddleware(Role.GLOBAL),
     lockController.actionForceLockHandler.bind(lockController));

Control/lib/common/detectorId.enum.js

@@ -0,0 +1,22 @@
+/**
+ * @license
+ * Copyright 2019-2024 CERN and copyright holders of ALICE O2.
+ * See http://alice-o2.web.cern.ch/copyright for details of the copyright holders.
+ * All rights not expressly granted are reserved.
+ *
+ * This software is distributed under the terms of the GNU General Public
+ * License v3 (GPL Version 3), copied verbatim in the file "COPYING".
+ *
+ * In applying this license CERN does not waive the privileges and immunities
+ * granted to it by virtue of its status as an Intergovernmental Organization
+ * or submit itself to any jurisdiction.
+*/
+
+/**
+ * Enum for detector IDs.
+ */
+const DetectorId = Object.freeze({
+  ALL: 'ALL',
+});
+
+exports.DetectorId = DetectorId;

Control/lib/common/ecsOperationAndStepStatus.enum.js

@@ -0,0 +1,27 @@
+/**
+ * @license
+ * Copyright 2019-2020 CERN and copyright holders of ALICE O2.
+ * See http://alice-o2.web.cern.ch/copyright for details of the copyright holders.
+ * All rights not expressly granted are reserved.
+ *
+ * This software is distributed under the terms of the GNU General Public
+ * License v3 (GPL Version 3), copied verbatim in the file "COPYING".
+ *
+ * In applying this license CERN does not waive the privileges and immunities
+ * granted to it by virtue of its status as an Intergovernmental Organization
+ * or submit itself to any jurisdiction.
+*/
+
+/**
+ * Available ECS Statuses of operations for Kafka Events
+ * These operations can be under the label:
+ * * operationStatus
+ * * operationStepStatus
+ */
+const EcsOperationAndStepStatus = Object.freeze({
+  DONE_OK: 'DONE_OK',
+  DONE_ERROR: 'DONE_ERROR',
+  DONE_TIMEOUT: 'DONE_TIMEOUT',
+});
+
+exports.EcsOperationAndStepStatus = EcsOperationAndStepStatus;

Control/lib/control-core/GrpcProxy.js

@@ -16,7 +16,7 @@
 const protoLoader = require('@grpc/proto-loader');
 const grpcLibrary = require('@grpc/grpc-js');
 const path = require('path');
-const {grpcErrorToNativeError} = require('./../errors/grpcErrorToNativeError.js');
+const {grpcErrorToNativeError} = require('@aliceo2/web-ui');
 const {Status} = require(path.join(__dirname, './../../protobuf/status_pb.js'));
 const {EnvironmentInfo} = require(path.join(__dirname, './../../protobuf/environmentinfo_pb.js'));
 const logger = (require('@aliceo2/web-ui').LogManager)