Test for a failed clone during split migration (elastic#158998)

## Summary

Adds a test for elastic#158733. This is based on the un-merged elastic#158940, so see
the last commit
[#6eafe910424414b5670e5f325accc59d87dd6dc4](elastic@6eafe91)
for the actual changes proposed by this PR

### Checklist

Delete any items that are not applicable to this PR.

- [ ] Any text added follows [EUI's writing
guidelines](https://elastic.github.io/eui/#/guidelines/writing), uses
sentence case text and includes [i18n
support](https://github.com/elastic/kibana/blob/main/packages/kbn-i18n/README.md)
- [ ]
[Documentation](https://www.elastic.co/guide/en/kibana/master/development-documentation.html)
was added for features that require explanation or tutorials
- [ ] [Unit or functional
tests](https://www.elastic.co/guide/en/kibana/master/development-tests.html)
were updated or added to match the most common scenarios
- [ ] Any UI touched in this PR is usable by keyboard only (learn more
about [keyboard accessibility](https://webaim.org/techniques/keyboard/))
- [ ] Any UI touched in this PR does not create any new axe failures
(run axe in browser:
[FF](https://addons.mozilla.org/en-US/firefox/addon/axe-devtools/),
[Chrome](https://chrome.google.com/webstore/detail/axe-web-accessibility-tes/lhdoppojpmngadmnindnejefpokejbdd?hl=en-US))
- [ ] If a plugin configuration key changed, check if it needs to be
allowlisted in the cloud and added to the [docker
list](https://github.com/elastic/kibana/blob/main/src/dev/build/tasks/os_packages/docker_generator/resources/base/bin/kibana-docker)
- [ ] This renders correctly on smaller devices using a responsive
layout. (You can test this [in your
browser](https://www.browserstack.com/guide/responsive-testing-on-local-server))
- [ ] This was checked for [cross-browser
compatibility](https://www.elastic.co/support/matrix#matrix_browsers)

### Risk Matrix

Delete this section if it is not applicable to this PR.

Before closing this PR, invite QA, stakeholders, and other developers to
identify risks that should be tested prior to the change/feature
release.

When forming the risk matrix, consider some of the following examples
and how they may potentially impact the change:

| Risk | Probability | Severity | Mitigation/Notes |

|---------------------------|-------------|----------|-------------------------|
| Multiple Spaces—unexpected behavior in non-default Kibana Space.
| Low | High | Integration tests will verify that all features are still
supported in non-default Kibana Space and when user switches between
spaces. |
| Multiple nodes—Elasticsearch polling might have race conditions
when multiple Kibana nodes are polling for the same tasks. | High | Low
| Tasks are idempotent, so executing them multiple times will not result
in logical error, but will degrade performance. To test for this case we
add plenty of unit tests around this logic and document manual testing
procedure. |
| Code should gracefully handle cases when feature X or plugin Y are
disabled. | Medium | High | Unit tests will verify that any feature flag
or plugin combination still results in our service operational. |
| [See more potential risk
examples](https://github.com/elastic/kibana/blob/main/RISK_MATRIX.mdx) |

### For maintainers

- [ ] This was checked for breaking API changes and was [labeled
appropriately](https://www.elastic.co/guide/en/kibana/master/contributing.html#kibana-release-notes-process)

---------

Co-authored-by: Gerard Soldevila <gerard.soldevila@elastic.co>
(cherry picked from commit 75ec1ec)

src/core/server/integration_tests/saved_objects/migrations/group3/split_failed_to_clone.test.ts

@@ -0,0 +1,188 @@
+/*
+ * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
+ * or more contributor license agreements. Licensed under the Elastic License
+ * 2.0 and the Server Side Public License, v 1; you may not use this file except
+ * in compliance with, at your election, the Elastic License 2.0 or the Server
+ * Side Public License, v 1.
+ */
+
+import Path from 'path';
+import type { TestElasticsearchUtils } from '@kbn/core-test-helpers-kbn-server';
+import {
+  type ISavedObjectTypeRegistry,
+  type SavedObjectsType,
+  MAIN_SAVED_OBJECT_INDEX,
+} from '@kbn/core-saved-objects-server';
+import { DEFAULT_INDEX_TYPES_MAP } from '@kbn/core-saved-objects-base-server-internal';
+import {
+  clearLog,
+  startElasticsearch,
+  getKibanaMigratorTestKit,
+  getCurrentVersionTypeRegistry,
+  overrideTypeRegistry,
+  getAggregatedTypesCount,
+  type KibanaMigratorTestKit,
+} from '../kibana_migrator_test_kit';
+import { delay } from '../test_utils';
+import '../jest_matchers';
+import { CloneIndexParams } from '@kbn/core-saved-objects-migration-server-internal/src/actions';
+
+// mock clone_index from packages/core
+jest.mock('@kbn/core-saved-objects-migration-server-internal/src/actions/clone_index', () => {
+  const realModule = jest.requireActual(
+    '@kbn/core-saved-objects-migration-server-internal/src/actions/clone_index'
+  );
+  return {
+    ...realModule,
+    cloneIndex: (params: CloneIndexParams) => async () => {
+      // we need to slow down the clone operation for indices other than
+      // .kibana so that .kibana can completely finish the migration before we
+      // fail
+      if (params.target.includes('slow_clone'))
+        await new Promise((resolve) => setTimeout(resolve, 1000));
+      return realModule.cloneIndex(params)();
+    },
+  };
+});
+
+// define a type => index distribution
+const RELOCATE_TYPES: Record<string, string> = {
+  dashboard: '.kibana_slow_clone_1',
+  visualization: '.kibana_slow_clone_1',
+  'canvas-workpad': '.kibana_slow_clone_1',
+  search: '.kibana_slow_clone_2',
+  task: '.kibana_task_manager',
+  'epm-packages-assets': '.kibana_slow_clone_1',
+  // the remaining types will be forced to go to '.kibana',
+  // overriding `indexPattern: foo` defined in the registry
+};
+
+export const logFilePath = Path.join(__dirname, 'split_failed_to_clone.test.log');
+
+describe('when splitting .kibana into multiple indices and one clone fails', () => {
+  let esServer: TestElasticsearchUtils['es'];
+  let typeRegistry: ISavedObjectTypeRegistry;
+  let migratorTestKitFactory: () => Promise<KibanaMigratorTestKit>;
+
+  beforeAll(async () => {
+    typeRegistry = await getCurrentVersionTypeRegistry({ oss: false });
+    await clearLog(logFilePath);
+    esServer = await startElasticsearch({
+      dataArchive: Path.join(__dirname, '..', 'archives', '7.14.0_xpack_sample_saved_objects.zip'),
+      timeout: 60000,
+    });
+  });
+
+  afterAll(async () => {
+    await esServer?.stop();
+    await delay(2);
+  });
+
+  it('after resolving the problem and retrying the migration completes successfully', async () => {
+    const updatedTypeRegistry = overrideTypeRegistry(
+      typeRegistry,
+      (type: SavedObjectsType<any>) => {
+        return {
+          ...type,
+          indexPattern: RELOCATE_TYPES[type.name] ?? MAIN_SAVED_OBJECT_INDEX,
+        };
+      }
+    );
+
+    migratorTestKitFactory = () =>
+      getKibanaMigratorTestKit({
+        types: updatedTypeRegistry.getAllTypes(),
+        kibanaIndex: '.kibana',
+        logFilePath,
+        defaultIndexTypesMap: DEFAULT_INDEX_TYPES_MAP,
+      });
+
+    const { runMigrations: runMigrationsWhichFailsWhenCloning, client } =
+      await migratorTestKitFactory();
+
+    // count of types in the legacy index
+    expect(await getAggregatedTypesCount(client, '.kibana')).toEqual({
+      'apm-telemetry': 1,
+      application_usage_daily: 4,
+      'canvas-workpad': 3,
+      'canvas-workpad-template': 5,
+      config: 1,
+      'core-usage-stats': 1,
+      dashboard: 19,
+      'epm-packages': 3,
+      'epm-packages-assets': 293,
+      event_loop_delays_daily: 1,
+      'graph-workspace': 3,
+      'index-pattern': 5,
+      'ingest-agent-policies': 2,
+      'ingest-outputs': 1,
+      'ingest-package-policies': 2,
+      ingest_manager_settings: 1,
+      map: 3,
+      'osquery-usage-metric': 1,
+      'sample-data-telemetry': 3,
+      search: 14,
+      space: 1,
+      'spaces-usage-stats': 1,
+      telemetry: 1,
+      'ui-metric': 5,
+      'usage-counters': 4,
+      visualization: 173,
+    });
+
+    // cause a failure when cloning .kibana_slow_clone_* indices
+    client.cluster.putSettings({ persistent: { 'cluster.max_shards_per_node': 15 } });
+
+    await expect(runMigrationsWhichFailsWhenCloning()).rejects.toThrowError(
+      /cluster_shard_limit_exceeded/
+    );
+
+    // remove the failure
+    client.cluster.putSettings({ persistent: { 'cluster.max_shards_per_node': 20 } });
+
+    const { runMigrations: runMigrations2ndTime } = await migratorTestKitFactory();
+    await runMigrations2ndTime();
+
+    expect(await getAggregatedTypesCount(client, '.kibana')).toMatchInlineSnapshot(`
+      Object {
+        "apm-telemetry": 1,
+        "application_usage_daily": 4,
+        "canvas-workpad-template": 5,
+        "config": 1,
+        "core-usage-stats": 1,
+        "epm-packages": 3,
+        "event_loop_delays_daily": 1,
+        "graph-workspace": 3,
+        "index-pattern": 5,
+        "ingest-agent-policies": 2,
+        "ingest-outputs": 1,
+        "ingest-package-policies": 2,
+        "ingest_manager_settings": 1,
+        "map": 3,
+        "sample-data-telemetry": 3,
+        "space": 1,
+        "spaces-usage-stats": 1,
+        "telemetry": 1,
+        "ui-metric": 5,
+        "usage-counters": 4,
+      }
+    `);
+    expect(await getAggregatedTypesCount(client, '.kibana_slow_clone_1')).toMatchInlineSnapshot(`
+      Object {
+        "canvas-workpad": 3,
+        "dashboard": 19,
+        "epm-packages-assets": 293,
+        "visualization": 173,
+      }
+    `);
+    expect(await getAggregatedTypesCount(client, '.kibana_slow_clone_2')).toMatchInlineSnapshot(`
+      Object {
+        "search": 14,
+      }
+    `);
+
+    // If we run a third time, we should not get any errors
+    const { runMigrations: runMigrations3rdTime } = await migratorTestKitFactory();
+    await runMigrations3rdTime();
+  });
+});