Cloudwatch

# CPU utilization alarm for EC2
aws cloudwatch put-metric-alarm \
  --alarm-name "HighCPU-i-1234567890abcdef0" \
  --metric-name CPUUtilization \
  --namespace AWS/EC2 \
  --statistic Average \
  --period 300 \
  --threshold 80 \
  --comparison-operator GreaterThanThreshold \
  --evaluation-periods 2 \
  --dimensions Name=InstanceId,Value=i-1234567890abcdef0 \
  --alarm-actions arn:aws:sns:us-east-1:123456789012:alerts \
  --ok-actions arn:aws:sns:us-east-1:123456789012:alerts

import boto3

cloudwatch = boto3.client('cloudwatch')

cloudwatch.put_metric_alarm(
    AlarmName='HighCPU-i-1234567890abcdef0',
    MetricName='CPUUtilization',
    Namespace='AWS/EC2',
    Statistic='Average',
    Period=300,
    Threshold=80.0,
    ComparisonOperator='GreaterThanThreshold',
    EvaluationPeriods=2,
    Dimensions=[
        {'Name': 'InstanceId', 'Value': 'i-1234567890abcdef0'}
    ],
    AlarmActions=['arn:aws:sns:us-east-1:123456789012:alerts'],
    OKActions=['arn:aws:sns:us-east-1:123456789012:alerts']
)

aws cloudwatch put-metric-alarm \
  --alarm-name "LambdaErrorRate-MyFunction" \
  --metrics '[
    {
      "Id": "errors",
      "MetricStat": {
        "Metric": {
          "Namespace": "AWS/Lambda",
          "MetricName": "Errors",
          "Dimensions": [{"Name": "FunctionName", "Value": "MyFunction"}]
        },
        "Period": 60,
        "Stat": "Sum"
      },
      "ReturnData": false
    },
    {
      "Id": "invocations",
      "MetricStat": {
        "Metric": {
          "Namespace": "AWS/Lambda",
          "MetricName": "Invocations",
          "Dimensions": [{"Name": "FunctionName", "Value": "MyFunction"}]
        },
        "Period": 60,
        "Stat": "Sum"
      },
      "ReturnData": false
    },
    {
      "Id": "errorRate",
      "Expression": "errors/invocations*100",
      "Label": "Error Rate",
      "ReturnData": true
    }
  ]' \
  --threshold 5 \
  --comparison-operator GreaterThanThreshold \
  --evaluation-periods 3 \
  --alarm-actions arn:aws:sns:us-east-1:123456789012:alerts

# Find errors in Lambda logs
aws logs start-query \
  --log-group-name /aws/lambda/MyFunction \
  --start-time $(date -d '1 hour ago' +%s) \
  --end-time $(date +%s) \
  --query-string '
    fields @timestamp, @message
    | filter @message like /ERROR/
    | sort @timestamp desc
    | limit 50
  '

# Get query results
aws logs get-query-results --query-id <query-id>

import boto3
import time

logs = boto3.client('logs')

# Start query
response = logs.start_query(
    logGroupName='/aws/lambda/MyFunction',
    startTime=int(time.time()) - 3600,
    endTime=int(time.time()),
    queryString='''
        fields @timestamp, @message
        | filter @message like /ERROR/
        | sort @timestamp desc
        | limit 50
    '''
)

query_id = response['queryId']

# Wait for results
while True:
    result = logs.get_query_results(queryId=query_id)
    if result['status'] == 'Complete':
        break
    time.sleep(1)

for row in result['results']:
    print(row)

# Create metric filter for error count
aws logs put-metric-filter \
  --log-group-name /aws/lambda/MyFunction \
  --filter-name ErrorCount \
  --filter-pattern "ERROR" \
  --metric-transformations \
    metricName=ErrorCount,metricNamespace=MyApp,metricValue=1,defaultValue=0

# ALARM when >100 errors in 3 of the last 5 query runs
aws cloudwatch put-log-alarm \
  --alarm-name "HighErrorCount" \
  --comparison-operator GreaterThanThreshold \
  --threshold 100 \
  --query-results-to-evaluate 5 \
  --query-results-to-alarm 3 \
  --treat-missing-data notBreaching \
  --alarm-actions arn:aws:sns:us-east-1:123456789012:alerts \
  --scheduled-query-configuration '{
    "QueryString": "fields @timestamp, @message | filter @message like /ERROR/",
    "LogGroupIdentifiers": ["/aws/lambda/MyFunction"],
    "ScheduledQueryRoleARN": "arn:aws:iam::123456789012:role/ScheduledQueryRole",
    "AggregationExpression": "count(*)",
    "ScheduleConfiguration": {
      "ScheduleExpression": "rate(10 minutes)",
      "StartTimeOffset": 600
    }
  }'

# Log alarms are omitted from describe-alarms unless requested
aws cloudwatch describe-alarms --alarm-types LogAlarm

import boto3

cloudwatch = boto3.client('cloudwatch')

cloudwatch.put_metric_data(
    Namespace='MyApp',
    MetricData=[
        {
            'MetricName': 'OrdersProcessed',
            'Value': 1,
            'Unit': 'Count',
            'Dimensions': [
                {'Name': 'Environment', 'Value': 'Production'},
                {'Name': 'OrderType', 'Value': 'Standard'}
            ]
        }
    ]
)

cat > dashboard.json << 'EOF'
{
  "widgets": [
    {
      "type": "metric",
      "x": 0, "y": 0, "width": 12, "height": 6,
      "properties": {
        "title": "Lambda Invocations",
        "metrics": [
          ["AWS/Lambda", "Invocations", "FunctionName", "MyFunction"]
        ],
        "period": 60,
        "stat": "Sum",
        "region": "us-east-1"
      }
    },
    {
      "type": "log",
      "x": 12, "y": 0, "width": 12, "height": 6,
      "properties": {
        "title": "Recent Errors",
        "query": "SOURCE '/aws/lambda/MyFunction' | filter @message like /ERROR/ | limit 20",
        "region": "us-east-1"
      }
    }
  ]
}
EOF

aws cloudwatch put-dashboard \
  --dashboard-name MyAppDashboard \
  --dashboard-body file://dashboard.json