Address comments of the PR #325

This commit addresses the comments of PR #325.

Signed-off-by: Ashish Ranjan <[email protected]>

tests/pipelines/eks/awscli-cl2-load-with-addons.yaml

@@ -17,6 +17,7 @@ spec:
   - name: slack-hook
   - name: slack-message
   - name: amp-workspace-id
+    default: ""
   tasks:
   - name: slack-notification
     params:

tests/pipelines/eks/awscli-eks-cl2-load.yaml

@@ -23,6 +23,7 @@ spec:
   - name: kubernetes-version
     default: "1.23"
   - name: amp-workspace-id
+    default: ""
   tasks:
   - name: slack-notification
     params:

tests/pipelines/eks/upstream-load.yaml

@@ -48,7 +48,8 @@ spec:
   - name: results-bucket
     description: "Results bucket with path of s3 to upload results"
   - name: amp-workspace-id
-    description: The remote amp workspace id where remote needs to happen.
+    description: The AMP workspace ID where remote write needs to happen.
+    default: ""
   tasks:
   - name: create-eks-cluster
     taskRef:

tests/tasks/generators/clusterloader/load.yaml

@@ -36,7 +36,8 @@ spec:
   - name: cluster-name
     description: The name of the EKS cluster you want to spin.
   - name: amp-workspace-id
-    description: The remote amp workspace id where remote needs to happen.
+    description: The AMP workspace ID where remote write needs to happen.
+    default: ""
   results:
     - name: datapoint
       description: Stores the CL2 result that can be consumed by other tasks (e.g. cloudwatch) 
@@ -76,7 +77,9 @@ spec:
       EOL
       cat $(workspaces.source.path)/overrides.yaml
       cp $(workspaces.source.path)/overrides.yaml $(workspaces.results.path)/overrides.yaml
-
+      
+      # Enable Prometheus if the remote workspace id is provided
+      if [ -n "$(params.amp-workspace-id)" ]; then
       # TODO: Currently pathing the prometheus manifests for remote write. Move this to upsteam going forward.
       echo "volumeBindingMode: WaitForFirstConsumer" >> $(workspaces.source.path)/perf-tests/clusterloader2/pkg/prometheus/manifests/0ssd-storage-class.yaml
       cat $(workspaces.source.path)/perf-tests/clusterloader2/pkg/prometheus/manifests/0ssd-storage-class.yaml
@@ -100,6 +103,7 @@ spec:
           - url: http://localhost:8005/workspaces/$(params.amp-workspace-id)/api/v1/remote_write
       EOF
       cat $(workspaces.source.path)/perf-tests/clusterloader2/pkg/prometheus/manifests/prometheus-prometheus.yaml
+      fi
   - name: run-loadtest
     image: public.ecr.aws/kit/clusterloader2:0213bea
     onError: continue
@@ -109,9 +113,12 @@ spec:
       if [ -n "$(params.endpoint)" ]; then
         ENDPOINT_FLAG="--endpoint $(params.endpoint)"
       fi
+      if [ -n "$(params.amp-workspace-id)" ]; then
+        CL2_PROMETHEUS_FLAGS="--enable-prometheus-server=true --prometheus-storage-class-provisioner kubernetes.io/aws-ebs --prometheus-storage-class-volume-type gp2 --prometheus-manifest-path=$(workspaces.source.path)/perf-tests/clusterloader2/pkg/prometheus/manifests/"
+      fi
       aws eks $ENDPOINT_FLAG update-kubeconfig --name $(params.cluster-name) --region $(params.region)
       cat $(workspaces.source.path)/perf-tests/clusterloader2/testing/load/config.yaml
-      ENABLE_EXEC_SERVICE=false /clusterloader --kubeconfig=/root/.kube/config --testconfig=$(workspaces.source.path)/perf-tests/clusterloader2/testing/load/config.yaml --testoverrides=$(workspaces.source.path)/overrides.yaml --nodes=$(params.nodes) --provider=eks --report-dir=$(workspaces.results.path) --alsologtostderr --v=2
+      ENABLE_EXEC_SERVICE=false /clusterloader --kubeconfig=/root/.kube/config --testconfig=$(workspaces.source.path)/perf-tests/clusterloader2/testing/load/config.yaml --testoverrides=$(workspaces.source.path)/overrides.yaml --nodes=$(params.nodes) --provider=eks --report-dir=$(workspaces.results.path) --alsologtostderr --v=2 $CL2_PROMETHEUS_FLAGS
       if [ $? -eq 0 ]; then
       echo "1" | tee $(results.datapoint.path)
       else

tests/tasks/setup/eks/awscli-mng.yaml

@@ -49,21 +49,27 @@ spec:
       --query cluster.resourcesVpcConfig.subnetIds --output text \
       )
 
-      nodes=$(params.desired-nodes)
+      nodes=$(($(params.desired-nodes)-1))
       asgs=$((nodes/1000))
       asg_name=$(params.cluster-name)-nodes
       create_dp()
       {
         CREATED_NODEGROUP=$(aws eks $ENDPOINT_FLAG --region $(params.region) list-nodegroups --cluster-name $(params.cluster-name)  --query 'nodegroups[?@==`'$asg_name-$1'`]' --output text)
-        #ToDo: paramterize instance-types
+        echo $3
+        EC2_INSTANCES=$3
+        echo $EC2_INSTANCES
+        if [ "$EC2_INSTANCES" == "" ]; then
+          # Defaulting to below instances if no other instances has been provided in the parameter.
+          EC2_INSTANCES="c5.large m5.large r5.large t3.large t3a.large c5a.large m5a.large r5a.large"
+        fi
         if [ "$CREATED_NODEGROUP" == "" ]; then
           #create node group
           aws eks $ENDPOINT_FLAG create-nodegroup \
           --cluster-name $(params.cluster-name) \
           --nodegroup-name $asg_name-$1 \
           --node-role $(params.host-cluster-node-role-arn) \
           --region $(params.region) \
-          --instance-types $3 \
+          --instance-types $EC2_INSTANCES \
           --scaling-config minSize=$(params.min-nodes),maxSize=$2,desiredSize=$2 \
           --subnets $NG_SUBNETS
         fi
@@ -77,15 +83,15 @@ spec:
       for i in $(seq 1 $asgs)
       do
         #max number of nodes MNG allows per ASG
-        create_dp $i 1000 c5.large,m5.large,r5.large,t3.large,t3a.large,c5a.large,m5a.large,r5a.large
+        create_dp $i 1000 
       done
-      remaining_nodes=$((nodes%1000))
+      remaining_nodes=$(((nodes)%1000))
       if [[ $remaining_nodes -gt 0 ]]
       then
         echo "The remaining_nodes var is greater than 0."
-        create_dp 0 $remaining_nodes c5.large,m5.large,r5.large,t3.large,t3a.large,c5a.large,m5a.large,r5a.large
+        create_dp 0 $remaining_nodes
       fi
-      # Creating an extra asg with 1 node for prometheus server pod scheduling.
+      # Creating an extra asg with 1 large node to ensure prometheus server has a scheduling space.
       create_dp $(($asgs + 1)) 1 m5.4xlarge
   - name: validate-nodes
     image: alpine/k8s:1.22.6
@@ -104,6 +110,6 @@ spec:
       while true; do
           ready_node=$(kubectl get nodes 2>/dev/null | grep -w Ready | wc -l)
           echo "ready-nodes=$ready_node"
-          if [[ "$ready_node" -eq $(($(params.desired-nodes) + 1)) ]]; then break; fi
+          if [[ "$ready_node" -eq $(params.desired-nodes) ]]; then break; fi
           sleep 5
       done