feat(scheduler): metrics for all schedules (#27544)

Class Schedule now provides static methods for accessing all schedules metrics with default configuration, such as `metricAllErrors` for viewing errors when executing targets.

Advances #23394

----

*By submitting this pull request, I confirm that my contribution is made under the terms of the Apache-2.0 license*

Author: filletofish

packages/@aws-cdk/aws-scheduler-alpha/README.md

@@ -245,7 +245,16 @@ EventBridge Scheduler publishes additional metrics when your schedule exhausts i
 
 ### Metrics for all schedules
 
-TODO: Not yet implemented. See section in [L2 Event Bridge Scheduler RFC](https://github.com/aws/aws-cdk-rfcs/blob/master/text/0474-event-bridge-scheduler-l2.md)
+Class `Schedule` provides static methods for accessing all schedules metrics with default configuration,
+ such as `metricAllErrors` for viewing errors when executing targets.
+
+ ```ts
+new cloudwatch.Alarm(this, 'SchedulesErrorAlarm', {
+    metric: Schedule.metricAllErrors(),
+    threshold: 0,
+    evaluationPeriods: 1,
+});
+ ```
 
 ### Metrics for a Group
 

packages/@aws-cdk/aws-scheduler-alpha/lib/schedule.ts

@@ -1,4 +1,5 @@
 import { IResource, Resource } from 'aws-cdk-lib';
+import * as cloudwatch from 'aws-cdk-lib/aws-cloudwatch';
 import { CfnSchedule } from 'aws-cdk-lib/aws-scheduler';
 import { Construct } from 'constructs';
 import { IGroup } from './group';
@@ -72,6 +73,99 @@ export interface ScheduleProps {
  * An EventBridge Schedule
  */
 export class Schedule extends Resource implements ISchedule {
+  /**
+   * Return the given named metric for all schedules.
+   *
+   * @default - sum over 5 minutes
+   */
+  public static metricAll(metricName: string, props?: cloudwatch.MetricOptions): cloudwatch.Metric {
+    return new cloudwatch.Metric({
+      namespace: 'AWS/Scheduler',
+      metricName,
+      statistic: 'sum',
+      ...props,
+    });
+  }
+
+  /**
+   * Metric for the number of invocations that were throttled across all schedules.
+   *
+   * @see https://docs.aws.amazon.com/scheduler/latest/UserGuide/scheduler-quotas.html
+   *
+   * @default - sum over 5 minutes
+   */
+  public static metricAllThrottled(props?: cloudwatch.MetricOptions): cloudwatch.Metric {
+    return this.metricAll('InvocationThrottleCount', props);
+  }
+
+  /**
+   * Metric for all invocation attempts across all schedules.
+   *
+   * @default - sum over 5 minutes
+   */
+  public static metricAllAttempts(props?: cloudwatch.MetricOptions): cloudwatch.Metric {
+    return this.metricAll('InvocationAttemptCount', props);
+  }
+  /**
+   * Emitted when the target returns an exception after EventBridge Scheduler calls the target API across all schedules.
+   *
+   * @default - sum over 5 minutes
+   */
+  public static metricAllErrors(props?: cloudwatch.MetricOptions): cloudwatch.Metric {
+    return this.metricAll('TargetErrorCount', props);
+  }
+
+  /**
+   * Metric for invocation failures due to API throttling by the target across all schedules.
+   *
+   * @default - sum over 5 minutes
+   */
+  public static metricAllTargetThrottled(props?: cloudwatch.MetricOptions): cloudwatch.Metric {
+    return this.metricAll('TargetErrorThrottledCount', props);
+  }
+
+  /**
+   * Metric for dropped invocations when EventBridge Scheduler stops attempting to invoke the target after a schedule's retry policy has been exhausted.
+   * Metric is calculated for all schedules.
+   *
+   * @default - sum over 5 minutes
+   */
+  public static metricAllDropped(props?: cloudwatch.MetricOptions): cloudwatch.Metric {
+    return this.metricAll('InvocationDroppedCount', props);
+  }
+
+  /**
+   * Metric for invocations delivered to the DLQ across all schedules.
+   *
+   * @default - sum over 5 minutes
+   */
+  public static metricAllSentToDLQ(props?: cloudwatch.MetricOptions): cloudwatch.Metric {
+    return this.metricAll('InvocationsSentToDeadLetterCount', props);
+  }
+
+  /**
+   * Metric for failed invocations that also failed to deliver to DLQ across all schedules.
+   *
+   * @default - sum over 5 minutes
+   */
+  public static metricAllFailedToBeSentToDLQ(errorCode?: string, props?: cloudwatch.MetricOptions): cloudwatch.Metric {
+    if (errorCode) {
+      return this.metricAll(`InvocationsFailedToBeSentToDeadLetterCount_${errorCode}`, props);
+    }
+
+    return this.metricAll('InvocationsFailedToBeSentToDeadLetterCount', props);
+  }
+
+  /**
+   * Metric for delivery of failed invocations to DLQ when the payload of the event sent to the DLQ exceeds the maximum size allowed by Amazon SQS.
+   * Metric is calculated for all schedules.
+   *
+   * @default - sum over 5 minutes
+   */
+  public static metricAllSentToDLQTrunacted(props?: cloudwatch.MetricOptions): cloudwatch.Metric {
+    return this.metricAll('InvocationsSentToDeadLetterCount_Truncated_MessageSizeExceeded', props);
+  }
+
   /**
    * The schedule group associated with this schedule.
    */

packages/@aws-cdk/aws-scheduler-alpha/test/integ.schedule.js.snapshot/aws-cdk-scheduler-schedule.assets.json

@@ -116,6 +116,18 @@
      }
     }
    }
+  },
+  "AllSchedulerErrorsAlarmA3246F8C": {
+   "Type": "AWS::CloudWatch::Alarm",
+   "Properties": {
+    "ComparisonOperator": "GreaterThanOrEqualToThreshold",
+    "EvaluationPeriods": 1,
+    "MetricName": "TargetErrorCount",
+    "Namespace": "AWS/Scheduler",
+    "Period": 300,
+    "Statistic": "Sum",
+    "Threshold": 1
+   }
   }
  },
  "Parameters": {

packages/@aws-cdk/aws-scheduler-alpha/test/integ.schedule.js.snapshot/aws-cdk-scheduler-schedule.template.json

@@ -1,5 +1,6 @@
 import { IntegTest } from '@aws-cdk/integ-tests-alpha';
 import * as cdk from 'aws-cdk-lib';
+import * as cloudwatch from 'aws-cdk-lib/aws-cloudwatch';
 import * as iam from 'aws-cdk-lib/aws-iam';
 import * as lambda from 'aws-cdk-lib/aws-lambda';
 import * as scheduler from '../lib';
@@ -42,6 +43,12 @@ new scheduler.Schedule(stack, 'DisabledSchedule', {
   enabled: false,
 });
 
+new cloudwatch.Alarm(stack, 'AllSchedulerErrorsAlarm', {
+  metric: scheduler.Schedule.metricAllErrors(),
+  threshold: 1,
+  evaluationPeriods: 1,
+});
+
 new IntegTest(app, 'integtest-schedule', {
   testCases: [stack],
 });

packages/@aws-cdk/aws-scheduler-alpha/test/integ.schedule.js.snapshot/manifest.json

@@ -1,4 +1,4 @@
-import { App, Stack } from 'aws-cdk-lib';
+import { App, Stack, Duration } from 'aws-cdk-lib';
 
 import { Template } from 'aws-cdk-lib/assertions';
 import * as iam from 'aws-cdk-lib/aws-iam';
@@ -62,4 +62,43 @@ describe('Schedule', () => {
       State: 'DISABLED',
     });
   });
+
+  test('returns metric for delivery of failed invocations to DLQ', () => {
+    // WHEN
+    const metric = Schedule.metricAllFailedToBeSentToDLQ();
+
+    // THEN
+    expect(metric.namespace).toEqual('AWS/Scheduler');
+    expect(metric.metricName).toEqual('InvocationsFailedToBeSentToDeadLetterCount');
+    expect(metric.dimensions).toBeUndefined();
+    expect(metric.statistic).toEqual('Sum');
+    expect(metric.period).toEqual(Duration.minutes(5));
+  });
+
+  test('returns metric for delivery of failed invocations to DLQ for specific error code', () => {
+    // WHEN
+    const metric = Schedule.metricAllFailedToBeSentToDLQ('test_error_code');
+
+    // THEN
+    expect(metric.namespace).toEqual('AWS/Scheduler');
+    expect(metric.metricName).toEqual('InvocationsFailedToBeSentToDeadLetterCount_test_error_code');
+    expect(metric.dimensions).toBeUndefined();
+    expect(metric.statistic).toEqual('Sum');
+    expect(metric.period).toEqual(Duration.minutes(5));
+  });
+
+  test('returns metric for all errors with provided statistic and period', () => {
+    // WHEN
+    const metric = Schedule.metricAllErrors({
+      statistic: 'Maximum',
+      period: Duration.minutes(1),
+    });
+
+    // THEN
+    expect(metric.namespace).toEqual('AWS/Scheduler');
+    expect(metric.metricName).toEqual('TargetErrorCount');
+    expect(metric.dimensions).toBeUndefined();
+    expect(metric.statistic).toEqual('Maximum');
+    expect(metric.period).toEqual(Duration.minutes(1));
+  });
 });