fix conflicts

Signed-off-by: Saad Khan <[email protected]>

.github/workflows/test-on-pr.yaml

@@ -13,68 +13,8 @@ on:
   workflow_dispatch:
 
 jobs:
-  # This workflow contains two jobs called "build autotune" and "build crc"
-  build_autotune:
-    # The type of runner that the job will run on
-    runs-on: ubuntu-20.04
-
-    steps:
-      # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
-      - uses: actions/checkout@v3
-      - name: Setup Minikube
-        uses: manusa/[email protected]
-        with:
-          minikube version: 'v1.16.0'
-          kubernetes version: 'v1.19.2'
-      - name: Build autotune
-        run: |
-          echo Build autotune
-          pr_number=${{ github.event.pull_request.number }}
-          echo "pr_number=${pr_number}" >> "$GITHUB_ENV"
-          ./build.sh -i autotune_operator:pr_${pr_number}
-          docker images | grep autotune     
-      - name: Check cluster info on minikube
-        run: |
-          kubectl cluster-info
-          kubectl get pods -n kube-system
-      - name: Install Prometheus on minikube
-        run: |
-          echo Install Prometheus on minikube
-          cd scripts
-          ./prometheus_on_minikube.sh -as
-      - name: Deploy kruize in experiment mode
-        run: |
-          echo Deploy kruize in experiment mode
-          cp ./manifests/autotune/autotune-operator-deployment.yaml_template ./manifests/autotune/autotune-operator-deployment.yaml_template.old
-          sed -e "s/imagePullPolicy: Always/imagePullPolicy: IfNotPresent/g" ./manifests/autotune/autotune-operator-deployment.yaml_template.old > ./manifests/autotune/autotune-operator-deployment.yaml_template
-          echo "***************************************************************"
-          cat ./manifests/autotune/autotune-operator-deployment.yaml_template
-          echo "***************************************************************"
-          
-          echo "PR_NUMBER = ${{ env.pr_number }}"
-          ./deploy.sh -c minikube -i autotune_operator:pr_${{ env.pr_number }}
-
-          sleep 20
-      - name: Capture ffdc logs
-        if: always()
-        run: |
-          echo "Capturing ffdc logs"
-          ./scripts/ffdc.sh -d ${GITHUB_WORKSPACE}
-      - name: Archive results
-        if: always()
-        run: |
-          cd ${GITHUB_WORKSPACE}
-          tar cvf autotune_results.tar kruize_*log.txt
-
-      - name: Upload results
-        if: always()
-        uses: actions/upload-artifact@v3
-        with:
-          name: autotune-results
-          path: ./autotune_results.tar
-          retention-days: 2
-
 
+  # This workflow builds the kruize image and runs an end-to-end test to validate the remote monitoring workflow
   build_crc:
     # The type of runner that the job will run on
     runs-on: ubuntu-20.04

Dockerfile.autotune

@@ -16,7 +16,7 @@
 ##########################################################
 #            Build Docker Image
 ##########################################################
-FROM registry.access.redhat.com/ubi9/ubi-minimal:9.4 as mvnbuild-jdk21
+FROM registry.access.redhat.com/ubi9/ubi-minimal:9.5 as mvnbuild-jdk21
 ARG USER=autotune
 ARG AUTOTUNE_HOME=/home/$USER
 
@@ -48,7 +48,7 @@ RUN jlink --strip-debug --compress 2 --no-header-files --no-man-pages --module-p
 #            Runtime Docker Image
 ##########################################################
 # Use ubi-minimal as the base image
-FROM registry.access.redhat.com/ubi9/ubi-minimal:9.4
+FROM registry.access.redhat.com/ubi9/ubi-minimal:9.5
 
 ARG AUTOTUNE_VERSION
 ARG USER=autotune

design/BulkAPI.md

@@ -109,79 +109,84 @@ GET /bulk?job_id=123e4567-e89b-12d3-a456-426614174000&verbose=true
 **Body (JSON):**
 When verbose=true, additional detailed information about the job is provided.
 
+example 1:
+
 ```json
 {
   "status": "IN_PROGRESS",
   "total_experiments": 23,
   "processed_experiments": 22,
-  "data": {
-    "experiments": {
-      "new": [
-        "prometheus-1|default|monitoring|node-exporter(daemonset)|node-exporter",
-        "prometheus-1|default|cadvisor|cadvisor(daemonset)|cadvisor",
-        "prometheus-1|default|monitoring|alertmanager-main(statefulset)|config-reloader",
-        "prometheus-1|default|monitoring|alertmanager-main(statefulset)|alertmanager",
-        "prometheus-1|default|monitoring|prometheus-operator(deployment)|kube-rbac-proxy",
-        "prometheus-1|default|kube-system|coredns(deployment)|coredns",
-        "prometheus-1|default|monitoring|prometheus-k8s(statefulset)|config-reloader",
-        "prometheus-1|default|monitoring|blackbox-exporter(deployment)|kube-rbac-proxy",
-        "prometheus-1|default|monitoring|prometheus-operator(deployment)|prometheus-operator",
-        "prometheus-1|default|monitoring|node-exporter(daemonset)|kube-rbac-proxy",
-        "prometheus-1|default|monitoring|kube-state-metrics(deployment)|kube-rbac-proxy-self",
-        "prometheus-1|default|monitoring|kube-state-metrics(deployment)|kube-state-metrics",
-        "prometheus-1|default|monitoring|kruize(deployment)|kruize",
-        "prometheus-1|default|monitoring|blackbox-exporter(deployment)|module-configmap-reloader",
-        "prometheus-1|default|monitoring|prometheus-k8s(statefulset)|prometheus",
-        "prometheus-1|default|monitoring|kube-state-metrics(deployment)|kube-rbac-proxy-main",
-        "prometheus-1|default|kube-system|kube-proxy(daemonset)|kube-proxy",
-        "prometheus-1|default|monitoring|prometheus-adapter(deployment)|prometheus-adapter",
-        "prometheus-1|default|monitoring|grafana(deployment)|grafana",
-        "prometheus-1|default|kube-system|kindnet(daemonset)|kindnet-cni",
-        "prometheus-1|default|monitoring|kruize-db-deployment(deployment)|kruize-db",
-        "prometheus-1|default|monitoring|blackbox-exporter(deployment)|blackbox-exporter"
-      ],
-      "updated": [],
-      "failed": null
+  "job_id": "5798a2df-6c67-467b-a3c2-befe634a0e3a",
+  "job_start_time": "2024-10-09T18:09:31.549Z",
+  "job_end_time": null,
+  "experiments": [
+    {
+      "name": "prometheus-1|default|kube-system|coredns(deployment)|coredns",
+      "recommendations": {
+        "status": "unprocessed"
+      }
     },
-    "recommendations": {
-      "data": {
-        "processed": [
-          "prometheus-1|default|monitoring|alertmanager-main(statefulset)|config-reloader",
-          "prometheus-1|default|monitoring|node-exporter(daemonset)|node-exporter",
-          "prometheus-1|default|local-path-storage|local-path-provisioner(deployment)|local-path-provisioner",
-          "prometheus-1|default|monitoring|alertmanager-main(statefulset)|alertmanager",
-          "prometheus-1|default|monitoring|prometheus-operator(deployment)|kube-rbac-proxy",
-          "prometheus-1|default|kube-system|coredns(deployment)|coredns",
-          "prometheus-1|default|monitoring|blackbox-exporter(deployment)|kube-rbac-proxy",
-          "prometheus-1|default|monitoring|prometheus-k8s(statefulset)|config-reloader",
-          "prometheus-1|default|monitoring|prometheus-operator(deployment)|prometheus-operator",
-          "prometheus-1|default|monitoring|node-exporter(daemonset)|kube-rbac-proxy",
-          "prometheus-1|default|monitoring|kube-state-metrics(deployment)|kube-rbac-proxy-self",
-          "prometheus-1|default|monitoring|kube-state-metrics(deployment)|kube-state-metrics",
-          "prometheus-1|default|monitoring|kruize(deployment)|kruize",
-          "prometheus-1|default|monitoring|blackbox-exporter(deployment)|module-configmap-reloader",
-          "prometheus-1|default|monitoring|prometheus-k8s(statefulset)|prometheus",
-          "prometheus-1|default|monitoring|kube-state-metrics(deployment)|kube-rbac-proxy-main",
-          "prometheus-1|default|kube-system|kube-proxy(daemonset)|kube-proxy",
-          "prometheus-1|default|monitoring|prometheus-adapter(deployment)|prometheus-adapter",
-          "prometheus-1|default|monitoring|grafana(deployment)|grafana",
-          "prometheus-1|default|kube-system|kindnet(daemonset)|kindnet-cni",
-          "prometheus-1|default|monitoring|kruize-db-deployment(deployment)|kruize-db",
-          "prometheus-1|default|monitoring|blackbox-exporter(deployment)|blackbox-exporter"
-        ],
-        "processing": [
-          "prometheus-1|default|cadvisor|cadvisor(daemonset)|cadvisor"
-        ],
-        "unprocessed": [
-        ],
-        "failed": []
+    {
+      "name": "prometheus-1|default|kube-system|kindnet(deployment)|kindnet-cni",
+      "recommendations": {
+        "status": "processed"
+      }
+    },
+    {
+      "name": "prometheus-1|default|monitoring|kruize(deployment)|kruize",
+      "recommendations": {
+        "status": "processing"
+      }
+    },
+    {
+      "name": "prometheus-1|default|monitoring|kruize(deployment)|kruize",
+      "recommendations": {
+        "status": "failed",
+        "notifications": {
+          "400": {
+            "type": "error",
+            "message": "Not able to fetch metrics",
+            "code": 400
+          }
+        }
+      }
+    },
+    {
+      "name": "prometheus-1|default|monitoring|kruize(deployment)|kruize",
+      "recommendations": {
+        "status": "failed",
+        "notifications": {
+          "400": {
+            "type": "error",
+            "message": "Not able to fetch metrics",
+            "code": 400
+          }
+        }
       }
     }
+  ]
+}
+```
+
+example 2:
+
+```json
+{
+  "status": "FAILED",
+  "total_experiments": 0,
+  "processed_experiments": 0,
+  "notifications": {
+    "503": {
+      "type": "ERROR",
+      "message": "HttpHostConnectException: Unable to connect to the data source. Please try again later. (receive series from Addr: 10.96.192.138:10901 LabelSets: {prometheus=\"monitoring/k8stage\", prometheus_replica=\"prometheus-k8stage-0\"},{prometheus=\"monitoring/k8stage\", prometheus_replica=\"prometheus-k8stage-1\"},{replica=\"thanos-ruler-0\", ruler_cluster=\"\"} MinTime: 1730222825216 MaxTime: 1731412800000: rpc error: code = Unknown desc = receive series from 01JBV2JN5SVN84D3HD5MVSGN3A: load chunks: get range reader: Please reduce your request rate)",
+      "code": 503
+    }
   },
-  "job_id": "5798a2df-6c67-467b-a3c2-befe634a0e3a",
-  "job_start_time": "2024-10-09T18:09:31.549Z",
-  "job_end_time": null
+  "job_id": "270fa4d9-2701-4ca0-b056-74229cc28498",
+  "job_start_time": "2024-11-12T15:05:46.362Z",
+  "job_end_time": "2024-11-12T15:06:05.301Z"
 }
+
 ```
 
 ### Response Parameters
@@ -205,40 +210,37 @@ resource optimization in Kubernetes environments. Below is a breakdown of the JS
     - **Type**: `Integer`
     - **Description**: Number of experiments that have been processed so far.
 
-- **data**:
-    - **Type**: `Object`
-    - **Description**: Contains detailed information about the experiments and recommendations being processed.
+- **experiments**:
+    - **Type**: `Array `
+    - **Description**: Array of experiment objects, each containing details about individual experiments.
+
+    - Each object in the `experiments` array has the following structure:
 
-    - **experiments**:
-        - **new**:
-            - **Type**: `Array of Strings`
-            - **Description**: List of new experiments that have been identified but not yet processed.
+  | Field                   | Type         | Description                                                              |
+              |-------------------------|--------------|--------------------------------------------------------------------------|
+  | `name`                  | `string`     | Name of the experiment, typically indicating a service name and deployment context. |
+  | `notification`          | `object`     | Notifications specific to this experiment (if any).                      |
+  | `recommendation`        | `object`     | Recommendation status and notifications specific to this experiment.     |
 
-        - **updated**:
-            - **Type**: `Array of Strings`
-            - **Description**: List of experiments that were previously processed but have now been updated.
+  #### Recommendation Object
 
-        - **failed**:
-            - **Type**: `null or Array`
-            - **Description**: List of experiments that failed during processing. If no failures, the value is `null`.
+  The `recommendation` field within each experiment provides information about recommendation processing status and
+  errors (if any).
 
-    - **recommendations**:
-        - **data**:
-            - **processed**:
-                - **Type**: `Array of Strings`
-                - **Description**: List of experiments for which recommendations have already been processed.
+  | Field                   | Type         | Description                                                              |
+              |-------------------------|--------------|--------------------------------------------------------------------------|
+  | `status`                | `string`     | Status of the recommendation (e.g., `"unprocessed"`, `"processed"`, `"processing"`, `"failed"`). |
+  | `notification`          | `object`     | Notifications related to recommendation processing.                      |
 
-            - **processing**:
-                - **Type**: `Array of Strings`
-                - **Description**: List of experiments that are currently being processed for recommendations.
+  #### Notification Object
 
-            - **unprocessed**:
-                - **Type**: `Array of Strings`
-                - **Description**: List of experiments that have not yet been processed for recommendations.
+  Both the `notification` and `recommendation.notification` fields may contain error messages or warnings as follows:
 
-            - **failed**:
-                - **Type**: `Array of Strings`
-                - **Description**: List of experiments for which the recommendation process failed.
+  | Field                   | Type         | Description                                                                |
+              |-------------------------|--------------|----------------------------------------------------------------------------|
+  | `type`                  | `string`     | Type of notification (e.g., `"info"`,`"error"`, `"warning"`).              |
+  | `message`               | `string`     | Description of the notification message.                                   |
+  | `code`                  | `integer`    | HTTP-like code indicating the type of error (e.g., `400` for bad request). |
 
 - **job_id**:
     - **Type**: `String`

pom.xml

@@ -10,7 +10,7 @@
     <properties>
         <fabric8-version>4.13.2</fabric8-version>
         <org-json-version>20240303</org-json-version>
-        <jetty-version>9.4.55.v20240627</jetty-version>
+        <jetty-version>10.0.24</jetty-version>
         <slf4j-version>2.17.1</slf4j-version>
         <java-version>17</java-version>
         <prometheus-simpleclient>0.14.1</prometheus-simpleclient>

src/main/java/com/autotune/Autotune.java

@@ -24,14 +24,20 @@
 import com.autotune.analyzer.utils.AnalyzerConstants;
 import com.autotune.common.datasource.DataSourceCollection;
 import com.autotune.common.datasource.DataSourceInfo;
+import com.autotune.common.exceptions.datasource.DataSourceAlreadyExist;
+import com.autotune.common.exceptions.datasource.DataSourceNotServiceable;
+import com.autotune.common.exceptions.datasource.UnsupportedDataSourceProvider;
 import com.autotune.database.helper.DBConstants;
 import com.autotune.database.init.KruizeHibernateUtil;
 import com.autotune.experimentManager.core.ExperimentManager;
 import com.autotune.operator.InitializeDeployment;
 import com.autotune.operator.KruizeDeploymentInfo;
 import com.autotune.service.HealthService;
 import com.autotune.service.InitiateListener;
-import com.autotune.utils.*;
+import com.autotune.utils.CloudWatchAppender;
+import com.autotune.utils.KruizeConstants;
+import com.autotune.utils.MetricsConfig;
+import com.autotune.utils.ServerContext;
 import com.autotune.utils.filter.KruizeCORSFilter;
 import io.prometheus.client.exporter.MetricsServlet;
 import io.prometheus.client.hotspot.DefaultExports;
@@ -50,12 +56,17 @@
 
 import javax.servlet.DispatcherType;
 import java.io.File;
+import java.io.IOException;
 import java.nio.file.Path;
 import java.nio.file.Paths;
+import java.security.KeyManagementException;
+import java.security.KeyStoreException;
+import java.security.NoSuchAlgorithmException;
 import java.util.EnumSet;
 import java.util.HashMap;
 import java.util.Scanner;
 
+import static com.autotune.utils.KruizeConstants.DataSourceConstants.DataSourceErrorMsgs.DATASOURCE_CONNECTION_FAILED;
 import static com.autotune.utils.ServerContext.*;
 
 public class Autotune {
@@ -112,7 +123,11 @@ public static void main(String[] args) {
                 // load available datasources from db
                 loadDataSourcesFromDB();
                 // setting up DataSources
-                setUpDataSources();
+                try {
+                    setUpDataSources();
+                } catch (Exception e) {
+                    LOGGER.error(DATASOURCE_CONNECTION_FAILED, e.getMessage());
+                }
                 // checking available DataSources
                 checkAvailableDataSources();
                 // load available metric profiles from db
@@ -124,7 +139,7 @@ public static void main(String[] args) {
             //Regenerate a Hibernate session following the creation of new tables
             KruizeHibernateUtil.buildSessionFactory();
         } catch (Exception | K8sTypeNotSupportedException | MonitoringAgentNotSupportedException |
-                MonitoringAgentNotFoundException e) {
+                 MonitoringAgentNotFoundException e) {
             e.printStackTrace();
             System.exit(1);
         }
@@ -170,7 +185,7 @@ public static void main(String[] args) {
     /**
      * Set up the data sources available at installation time from config file
      */
-    private static void setUpDataSources() {
+    private static void setUpDataSources() throws UnsupportedDataSourceProvider, DataSourceNotServiceable, DataSourceAlreadyExist, IOException, NoSuchAlgorithmException, KeyStoreException, KeyManagementException {
         DataSourceCollection dataSourceCollection = DataSourceCollection.getInstance();
         dataSourceCollection.addDataSourcesFromConfigFile(KruizeConstants.CONFIG_FILE);
     }
@@ -190,7 +205,7 @@ private static void checkAvailableDataSources() {
         DataSourceCollection dataSourceCollection = DataSourceCollection.getInstance();
         LOGGER.info(KruizeConstants.DataSourceConstants.DataSourceInfoMsgs.CHECKING_AVAILABLE_DATASOURCE);
         HashMap<String, DataSourceInfo> dataSources = dataSourceCollection.getDataSourcesCollection();
-        for (String name: dataSources.keySet()) {
+        for (String name : dataSources.keySet()) {
             DataSourceInfo dataSource = dataSources.get(name);
             String dataSourceName = dataSource.getName();
             String url = dataSource.getUrl().toString();