chore: add benchmark tool

examples/standalone-data-generator/Dockerfile

@@ -0,0 +1,21 @@
+# run below command on M1 mac to build image for linux/amd64
+FROM --platform=linux/amd64 python:3-alpine   
+
+# Set the working directory to /app
+WORKDIR /app
+
+# Copy the current directory contents into the container at /app
+COPY . /app
+
+# Install any needed packages specified in requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Make the entrypoint script executable
+RUN chmod +x /app/performance-entrypoint.sh
+
+RUN ls -la /app
+
+# Set the default command to run when the container starts
+CMD ["python", "create_event_for_performance.py"]
+
+ENTRYPOINT [ "/app/performance-entrypoint.sh" ]   

examples/standalone-data-generator/README.md

@@ -109,4 +109,44 @@ DEFAULT_PRODUCT_COUNT = 2
 
 ```
 
-Please modify the `enums.py` to define the detail logic for device and user information. 
+Please modify the `enums.py` to define the detail logic for device and user information. 
+
+## Clickstream sample data for performance test
+We have developed a tool for performance tests, which utilizes ECS Fargate to continuously send test data to Clickstream. The number of ECS Service tasks can be increased or decreased to adjust the RPS (Requests per Second).
+
+Follow below step to start your Clickstream performance test
+1. Add configuration file:
+
+Please download your `amplifyconfiguration.json` file from your web console of the solution, then copy it to the root
+folder which at the same level as README file. then you can execute the following command to create and send your sample
+data.
+
+In the `amplifyconfiguration.json` file, we will only parse `appId`, `endpoint` and `isCompressEvents` three parameter
+to run the program.
+
+2. Start performance test:
+Run below script to start performance test
+```
+./create-ecs-performance-test.sh <testName> <taskNumber> <region>
+```
+
+<testName>: the suffix of the ECS cluster name, for example: if <testName> is **MyTest**, you ECS cluster name is **clickstream-sample-data-cluster-MyTest**
+<taskNumber>: the number of your ECS service tasks, you can change it from the ECS console after the cluster created.
+<region>: the region where the ECS cluster created.
+For example: 
+```
+./create-ecs-performance-test.sh MyTest 5 us-east-1
+```
+
+According to our testing, if the ECS cluster of performance tool is created in the same region of the Clickstream solution, a task can generate about 200 RPS.
+A request payload size is ~2KB and contains 10 events.
+
+3. Clean up performance test resources.
+run below script to clean up all resources of performance test tool
+```
+./cleanup-ecs-performance-test.sh <testName> <region>
+```
+
+
+
+

examples/standalone-data-generator/cleanup-ecs-performance-test.sh

@@ -0,0 +1,47 @@
+#!/bin/bash
+
+# Variables
+TEST_NAME=$1
+AWS_REGION=$2
+CLUSTER_NAME="clickstream-sample-data-cluster-${TEST_NAME}"
+SERVICE_NAME="clickstream-sample-data-service-${TEST_NAME}"
+TASK_DEFINITION_NAME="clickstream-sample-data-task-${TEST_NAME}"
+ECR_REPO_NAME="clickstream-sample-data-repo-${TEST_NAME}"
+LOG_GROUP_NAME="/ecs/clickstream-sample-data-log-${TEST_NAME}"
+ROLE_NAME="clickstream-sample-data-ecs-task-role-${TEST_NAME}-${AWS_REGION}"
+
+# De-register ECS Service
+echo "Deleting ECS Service..."
+aws ecs update-service --cluster "${CLUSTER_NAME}" --service "${SERVICE_NAME}" --desired-count 0 --region ${AWS_REGION}
+aws ecs delete-service --cluster "${CLUSTER_NAME}" --service "${SERVICE_NAME}" --force --region ${AWS_REGION}
+
+sleep 30
+
+# Deregister ECS Task Definition
+echo "Deregistering Task Definitions..."
+TASK_DEFS=$(aws ecs list-task-definitions --family-prefix "${TASK_DEFINITION_NAME}" --region ${AWS_REGION} --query "taskDefinitionArns[]" --output text)
+for task_def in $TASK_DEFS; do
+  aws ecs deregister-task-definition --task-definition "${task_def}" --region ${AWS_REGION}
+done
+
+# Delete ECS Cluster
+echo "Deleting ECS Cluster..."
+aws ecs delete-cluster --cluster "${CLUSTER_NAME}" --region ${AWS_REGION}
+
+# Delete ECR repository
+echo "Deleting ECR Repository..."
+aws ecr delete-repository --repository-name "${ECR_REPO_NAME}" --region ${AWS_REGION} --force
+
+# Detach IAM policies and delete role
+echo "Detaching IAM Policies and Deleting Role..."
+aws iam detach-role-policy --role-name "${ROLE_NAME}" --policy-arn "arn:aws:iam::aws:policy/CloudWatchLogsFullAccess"
+aws iam detach-role-policy --role-name "${ROLE_NAME}" --policy-arn "arn:aws:iam::aws:policy/service-role/AmazonECSTaskExecutionRolePolicy"
+aws iam delete-role --role-name "${ROLE_NAME}"
+
+# Delete CloudWatch Log Group
+echo "Deleting CloudWatch Log Group..."
+aws logs delete-log-group --log-group-name "${LOG_GROUP_NAME}" --region ${AWS_REGION}
+
+rm -f amplifyconfiguration-${TEST_NAME}.json
+
+echo "Cleanup completed."

examples/standalone-data-generator/configure.py

@@ -37,6 +37,23 @@
 BATCH_EVENT_DURATION_IN_MINUTES = 20
 IS_LOG_FULL_REQUEST_MESSAGE = True
 
+# for performance tool
+ALL_USER_REALTIME_PERFORMANCE = 100000
+RANDOM_DAU_PERFORMANCE = range(10000, 10001)
+THREAD_NUMBER_FOR_USER_PERFORMANCE = 1
+FLUSH_DURATION_PERFORMANCE = 3
+BATCH_EVENT_DURATION_IN_MINUTES_PERFORMANCE = 2
+NEED_SLEEP = True
+# 100 RPS
+# PERFORMANCE_SLEEP_TIME = 0.002
+# 10 RPS
+# PERFORMANCE_SLEEP_TIME = 0.08
+
+PERFORMANCE_SLEEP_TIME = 0.003
+
+# PERFORMANCE_SLEEP_TIME = 0.001
+
+
 # common settings
 SESSION_TIMES = range(1, 4)
 IS_GZIP = True

examples/standalone-data-generator/create-ecs-performance-test.sh

@@ -0,0 +1,169 @@
+#!/bin/bash
+
+# Variables
+TEST_NAME=$1
+DOCKERFILE_PATH="./Dockerfile"
+IMAGE_NAME="clickstream-sample-data"
+TAG=$TEST_NAME
+AWS_REGION=$3
+ECR_REPO_NAME="clickstream-sample-data-repo-${TEST_NAME}"
+NUMBER_OF_TASKS=$2
+CLUSTER_NAME="clickstream-sample-data-cluster-${TEST_NAME}"
+SERVICE_NAME="clickstream-sample-data-service-${TEST_NAME}"
+TASK_DEFINITION_NAME="clickstream-sample-data-task-${TEST_NAME}"
+SUBNET_IDS=""
+SECURITY_GROUP_ID=""
+LOG_GROUP_NAME="/ecs/clickstream-sample-data-log-${TEST_NAME}"
+ROLE_NAME="clickstream-sample-data-ecs-task-role-${TEST_NAME}-${AWS_REGION}"
+
+# backup amplifyconfiguration.json for later checking
+cp -f amplifyconfiguration.json "amplifyconfiguration-${TEST_NAME}.json"
+
+AWS_ACCOUNT_ID=$(aws sts get-caller-identity --query "Account" --output text)
+ROLE="arn:aws:iam::${AWS_ACCOUNT_ID}:role/${ROLE_NAME}"
+
+# Check if the AWS_ACCOUNT_ID variable is set
+if [ -z "$AWS_ACCOUNT_ID" ]; then
+    echo "Failed to retrieve AWS account ID."
+    exit 1
+else
+    echo "AWS Account ID: $AWS_ACCOUNT_ID"
+fi
+
+# Get the default VPC ID
+DEFAULT_VPC_ID=$(aws ec2 describe-vpcs --filters "Name=is-default,Values=true" --region ${AWS_REGION}  --query "Vpcs[0].VpcId" --output text)
+
+if [ -z "$DEFAULT_VPC_ID" ]; then
+    echo "No default VPC found."
+    exit 1
+fi
+
+# Fetch Subnet IDs if SUBNET_IDS is empty
+if [ -z "$SUBNET_IDS" ]; then
+    SUBNET_IDS=$(aws ec2 describe-subnets --filters "Name=vpc-id,Values=$DEFAULT_VPC_ID" --region ${AWS_REGION} --query "Subnets[*].SubnetId" --output text)
+    SUBNET_IDS=$(echo $SUBNET_IDS | sed 's/ /,/g')  # Convert space-separated list to comma-separated
+    if [ -z "$SUBNET_IDS" ]; then
+        echo "No subnets found in the default VPC."
+        exit 1
+    fi
+    echo "SUBNET_IDS=\"$SUBNET_IDS\""
+fi
+
+# Fetch Security Group ID if SECURITY_GROUP_ID is empty
+if [ -z "$SECURITY_GROUP_ID" ]; then
+    SECURITY_GROUP_ID=$(aws ec2 describe-security-groups --filters "Name=vpc-id,Values=$DEFAULT_VPC_ID" --region ${AWS_REGION} --query "SecurityGroups[?GroupName=='default'].GroupId" --output text)
+    if [ -z "$SECURITY_GROUP_ID" ]; then
+        echo "No default security group found in the default VPC."
+        exit 1
+    fi
+    echo "SECURITY_GROUP_ID=\"$SECURITY_GROUP_ID\""
+fi
+
+# Create a CloudWatch log group if it doesn't exist
+LOG_GROUP_EXISTS=$(aws logs describe-log-groups --log-group-name-prefix "${LOG_GROUP_NAME}" --query 'logGroups[?logGroupName==`'${LOG_GROUP_NAME}'`]' --output text --region ${AWS_REGION})
+
+if [ -z "$LOG_GROUP_EXISTS" ]; then
+  echo "start create log group"
+  aws logs create-log-group --log-group-name "${LOG_GROUP_NAME}" --region ${AWS_REGION}
+fi
+
+# Check if the role exists
+ROLE_EXISTS=$(aws iam list-roles --query 'Roles[?RoleName==`'${ROLE_NAME}'`].RoleName' --output text)
+
+if [ -z "$ROLE_EXISTS" ]; then
+  echo "start create role"
+  # Create a trust policy file
+  echo '{
+    "Version": "2012-10-17",
+    "Statement": [
+      {
+        "Effect": "Allow",
+        "Principal": {
+          "Service": "ecs-tasks.amazonaws.com"
+        },
+        "Action": "sts:AssumeRole"
+      }
+    ]
+  }' > TrustPolicy.json
+
+
+  # Create the role with the trust policy
+  aws iam create-role --role-name "${ROLE_NAME}" --assume-role-policy-document file://TrustPolicy.json
+
+  # Attach the permission
+  aws iam attach-role-policy --role-name "${ROLE_NAME}" --policy-arn "arn:aws:iam::aws:policy/CloudWatchLogsFullAccess"
+  aws iam attach-role-policy --role-name "${ROLE_NAME}" --policy-arn "arn:aws:iam::aws:policy/service-role/AmazonECSTaskExecutionRolePolicy"
+fi
+
+# Clean up the trust policy file
+rm -f TrustPolicy.json
+
+# Full image name with AWS account ID and region
+FULL_IMAGE_NAME="${AWS_ACCOUNT_ID}.dkr.ecr.${AWS_REGION}.amazonaws.com/${ECR_REPO_NAME}:${TAG}"
+
+# Get the login command from ECR and execute it directly
+aws ecr get-login-password --region $AWS_REGION | docker login --username AWS --password-stdin $AWS_ACCOUNT_ID.dkr.ecr.$AWS_REGION.amazonaws.com
+
+# Build your Docker image locally
+docker build -t $IMAGE_NAME -f $DOCKERFILE_PATH .
+
+# Check if ECR repository exists
+REPO_EXISTS=$(aws ecr describe-repositories --repository-names "${ECR_REPO_NAME}" --region ${AWS_REGION} 2>&1)
+
+if [ $? -ne 0 ]; then
+  # If the repository does not exist in ECR, create it.
+  aws ecr create-repository --repository-name "${ECR_REPO_NAME}" --region ${AWS_REGION}
+fi
+
+# Tag the Docker image with the full image name
+docker tag $IMAGE_NAME:latest $FULL_IMAGE_NAME
+
+# Push Docker image to ECR
+docker push $FULL_IMAGE_NAME
+
+# Create a task definition file
+cat > task-definition.json << EOF
+{
+  "family": "${TASK_DEFINITION_NAME}",
+  "executionRoleArn": "${ROLE}",
+  "taskRoleArn": "${ROLE}",
+  "containerDefinitions": [
+    {
+      "name": "${IMAGE_NAME}",
+      "image": "${FULL_IMAGE_NAME}",
+      "essential": true,
+      "logConfiguration": {
+        "logDriver": "awslogs",
+        "options": {
+          "awslogs-group": "${LOG_GROUP_NAME}",
+          "awslogs-region": "${AWS_REGION}",
+          "awslogs-stream-prefix": "ClickStream-Test"
+        }
+      }    
+    }
+  ], 
+  "networkMode": "awsvpc",  
+  "requiresCompatibilities": ["FARGATE"],
+  "cpu": "1024",
+  "memory": "2048"
+}
+EOF
+
+
+# Register the task definition with ECS
+aws ecs register-task-definition --region $AWS_REGION  --cli-input-json file://task-definition.json
+
+# Check if the ECS cluster exists
+CLUSTER_EXISTS=$(aws ecs describe-clusters --clusters "${CLUSTER_NAME}" --region ${AWS_REGION} | jq -r .clusters[0].status)
+
+if [ "$CLUSTER_EXISTS" != "ACTIVE" ]; then
+  # If the cluster does not exist, create it
+  aws ecs create-cluster --cluster-name "${CLUSTER_NAME}" --region ${AWS_REGION} --settings name=containerInsights,value=enabled
+fi
+
+aws ecs create-service --service-name "${SERVICE_NAME}" --desired-count ${NUMBER_OF_TASKS} --task-definition "${TASK_DEFINITION_NAME}" --cluster "${CLUSTER_NAME}" --region ${AWS_REGION} --launch-type "FARGATE" --network-configuration "awsvpcConfiguration={subnets=[$SUBNET_IDS],securityGroups=[$SECURITY_GROUP_ID],assignPublicIp=ENABLED}"
+
+# Clean up
+rm -f task-definition.json
+
+