[APM] Add cloud attributes to data telemetry

x-pack/plugins/apm/common/apm_telemetry.ts

@@ -91,6 +91,13 @@ export function getApmTelemetryMapping() {
           {}
         ),
       },
+      cloud: {
+        properties: {
+          availability_zone: keyword,
+          provider: keyword,
+          region: keyword,
+        },
+      },
       counts: {
         properties: {
           agent_configuration: allProperties,

x-pack/plugins/apm/common/elasticsearch_fieldnames.test.ts

@@ -23,6 +23,11 @@ describe('Transaction', () => {
       name: 'java',
       version: 'agent version',
     },
+    cloud: {
+      availability_zone: 'europe-west1-c',
+      provider: 'gcp',
+      region: 'europe-west1',
+    },
     http: {
       request: { method: 'GET' },
       response: { status_code: 200 },
@@ -74,6 +79,11 @@ describe('Span', () => {
       name: 'java',
       version: 'agent version',
     },
+    cloud: {
+      availability_zone: 'europe-west1-c',
+      provider: 'gcp',
+      region: 'europe-west1',
+    },
     processor: {
       name: 'transaction',
       event: 'span',
@@ -121,6 +131,11 @@ describe('Error', () => {
       name: 'java',
       version: 'agent version',
     },
+    cloud: {
+      availability_zone: 'europe-west1-c',
+      provider: 'gcp',
+      region: 'europe-west1',
+    },
     error: {
       exception: [
         {

x-pack/plugins/apm/common/elasticsearch_fieldnames.ts

@@ -4,6 +4,10 @@
  * you may not use this file except in compliance with the Elastic License.
  */
 
+export const CLOUD_AVAILABILITY_ZONE = 'cloud.availability_zone';
+export const CLOUD_PROVIDER = 'cloud.provider';
+export const CLOUD_REGION = 'cloud.region';
+
 export const SERVICE_NAME = 'service.name';
 export const SERVICE_ENVIRONMENT = 'service.environment';
 export const SERVICE_FRAMEWORK_NAME = 'service.framework.name';

x-pack/plugins/apm/dev_docs/telemetry.md

@@ -40,6 +40,9 @@ and/or config/kibana.dev.yml files.
 
 Running the script with `--clear` will delete the index first.
 
+If you're using an Elasticsearch instance without TLS verification (if you have `elasticsearch.ssl.verificationMode: none` set in your kibana.yml)
+you can run the script with `env NODE_TLS_REJECT_UNAUTHORIZED=0` to avoid TLS connection errors.
+
 After running the script you should see sample telemetry data in the "xpack-phone-home" index.
 
 ### Updating Data Telemetry Mappings
@@ -62,6 +65,10 @@ node ./scripts/merge-telemetry-mapping.js ../../../../telemetry/config/templates
 
 this will replace the contents of the mapping in the repository checkout with the updated mapping. You can then [follow the telemetry team's instructions](https://github.com/elastic/telemetry#mappings) for opening a pull request with the mapping changes.
 
+The queries for the stats are in the [collect data telemetry tasks](../server/lib/apm_telemetry/collect_data_telemetry/tasks.ts).
+
+The collection tasks also use the [`APMDataTelemetry` type](../server/lib/apm_telemetry/types.ts) which also needs to be updated with any changes to the fields.
+
 ## Behavioral Telemetry
 
 Behavioral telemetry is recorded with the ui_metrics and application_usage methods from the Usage Collection plugin.

x-pack/plugins/apm/server/lib/apm_telemetry/collect_data_telemetry/tasks.test.ts

@@ -0,0 +1,68 @@
+/*
+ * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
+ * or more contributor license agreements. Licensed under the Elastic License;
+ * you may not use this file except in compliance with the Elastic License.
+ */
+
+import { tasks } from './tasks';
+import { ApmIndicesConfig } from '../../settings/apm_indices/get_apm_indices';
+
+describe('data telemetry collection tasks', () => {
+  const indices = {
+    'apm_oss.errorIndices': 'apm-8.0.0-error',
+    'apm_oss.metricsIndices': 'apm-8.0.0-metric',
+    'apm_oss.spanIndices': 'apm-8.0.0-span',
+    'apm_oss.transactionIndices': 'apm-8.0.0-transaction',
+  } as ApmIndicesConfig;
+
+  describe('cloud', () => {
+    const cloudTask = tasks.find((task) => task.name === 'cloud');
+
+    it('returns a map of cloud provider data', async () => {
+      const search = jest.fn().mockResolvedValueOnce({
+        aggregations: {
+          availability_zone: {
+            buckets: [
+              { doc_count: 1, key: 'us-west-1' },
+              { doc_count: 1, key: 'europe-west1-c' },
+            ],
+          },
+          provider: {
+            buckets: [
+              { doc_count: 1, key: 'aws' },
+              { doc_count: 1, key: 'gcp' },
+            ],
+          },
+          region: {
+            buckets: [
+              { doc_count: 1, key: 'us-west' },
+              { doc_count: 1, key: 'europe-west1' },
+            ],
+          },
+        },
+      });
+
+      expect(await cloudTask?.executor({ indices, search } as any)).toEqual({
+        cloud: {
+          availability_zone: ['us-west-1', 'europe-west1-c'],
+          provider: ['aws', 'gcp'],
+          region: ['us-west', 'europe-west1'],
+        },
+      });
+    });
+
+    describe('with no results', () => {
+      it('returns an empty map', async () => {
+        const search = jest.fn().mockResolvedValueOnce({});
+
+        expect(await cloudTask?.executor({ indices, search } as any)).toEqual({
+          cloud: {
+            availability_zone: [],
+            provider: [],
+            region: [],
+          },
+        });
+      });
+    });
+  });
+});

x-pack/plugins/apm/server/lib/apm_telemetry/collect_data_telemetry/tasks.ts

@@ -22,6 +22,9 @@ import {
   SERVICE_RUNTIME_NAME,
   SERVICE_RUNTIME_VERSION,
   USER_AGENT_ORIGINAL,
+  CLOUD_AVAILABILITY_ZONE,
+  CLOUD_PROVIDER,
+  CLOUD_REGION,
 } from '../../../../common/elasticsearch_fieldnames';
 import { Span } from '../../../../typings/es_schemas/ui/span';
 import { APMError } from '../../../../typings/es_schemas/ui/apm_error';
@@ -32,6 +35,66 @@ const TIME_RANGES = ['1d', 'all'] as const;
 type TimeRange = typeof TIME_RANGES[number];
 
 export const tasks: TelemetryTask[] = [
+  {
+    name: 'cloud',
+    executor: async ({ indices, search }) => {
+      function getBucketKeys({
+        buckets,
+      }: {
+        buckets: Array<{
+          doc_count: number;
+          key: string | number;
+        }>;
+      }) {
+        return buckets.map((bucket) => bucket.key as string);
+      }
+
+      const az = 'availability_zone';
+      const region = 'region';
+      const provider = 'provider';
+
+      const response = await search({
+        index: [
+          indices['apm_oss.errorIndices'],
+          indices['apm_oss.metricsIndices'],
+          indices['apm_oss.spanIndices'],
+          indices['apm_oss.transactionIndices'],
+        ],
+        body: {
+          size: 0,
+          aggs: {
+            [az]: {
+              terms: {
+                field: CLOUD_AVAILABILITY_ZONE,
+              },
+            },
+            [provider]: {
+              terms: {
+                field: CLOUD_PROVIDER,
+              },
+            },
+            [region]: {
+              terms: {
+                field: CLOUD_REGION,
+              },
+            },
+          },
+        },
+      });
+
+      const { aggregations } = response;
+
+      if (!aggregations) {
+        return { cloud: { [az]: [], [provider]: [], [region]: [] } };
+      }
+      const cloud = {
+        [az]: getBucketKeys(aggregations[az]),
+        [provider]: getBucketKeys(aggregations[provider]),
+        [region]: getBucketKeys(aggregations[region]),
+      };
+      return { cloud };
+    },
+  },
   {
     name: 'processor_events',
     executor: async ({ indices, search }) => {

x-pack/plugins/apm/server/lib/apm_telemetry/types.ts

@@ -25,6 +25,11 @@ export type APMDataTelemetry = DeepPartial<{
       patch: number;
     };
   };
+  cloud: {
+    availability_zone: string[];
+    provider: string[];
+    region: string[];
+  };
   counts: {
     transaction: TimeframeMap;
     span: TimeframeMap;
@@ -102,6 +107,7 @@ export type APMDataTelemetry = DeepPartial<{
     };
   };
   tasks: Record<
+    | 'cloud'
     | 'processor_events'
     | 'agent_configuration'
     | 'services'