Merge branch 'rake-task-for-reindexing' into 'master'

Add rake task for reindexing

See merge request gitlab-org/gitlab!27772

doc/integration/elasticsearch.md

@@ -426,6 +426,15 @@ There are several rake tasks available to you via the command line:
   - Performs an Elasticsearch import that indexes the snippets data.
 - [`sudo gitlab-rake gitlab:elastic:projects_not_indexed`](https://gitlab.com/gitlab-org/gitlab/blob/master/ee/lib/tasks/gitlab/elastic.rake)
   - Displays which projects are not indexed.
+- [`sudo gitlab-rake gitlab:elastic:reindex_to_another_cluster[<SOURCE_CLUSTER_URL>,<DESTINATION_CLUSTER_URL>]`](https://gitlab.com/gitlab-org/gitlab/blob/master/ee/lib/tasks/gitlab/elastic.rake)
+  - Creates a new index in the destination cluster and triggers a [reindex from
+   remote](https://www.elastic.co/guide/en/elasticsearch/reference/current/docs-reindex.html#reindex-from-remote)
+   such that the index is fully copied from the source index. This can be
+   useful when you wish to perform a migration to a new cluster as this
+   reindexing should be quicker than reindexing via GitLab. Note that remote
+   reindex requires your source cluster to be whitelisted in your destination
+   cluster in Elasticsearch settings as per [the
+   documentation](https://www.elastic.co/guide/en/elasticsearch/reference/current/docs-reindex.html#reindex-from-remote).
 
 ### Environment Variables
 

ee/changelogs/unreleased/rake-task-for-reindexing.yml

+---
+title: Add rake task for reindexing Elasticsearch
+merge_request: 27772
+author:
+type: added

ee/lib/gitlab/elastic/helper.rb

@@ -4,7 +4,7 @@ module Gitlab
   module Elastic
     class Helper
       # rubocop: disable CodeReuse/ActiveRecord
-      def self.create_empty_index(version = ::Elastic::MultiVersionUtil::TARGET_VERSION)
+      def self.create_empty_index(version = ::Elastic::MultiVersionUtil::TARGET_VERSION, client = nil)
         settings = {}
         mappings = {}
 
@@ -23,7 +23,7 @@ module Gitlab
         end
 
         proxy = Project.__elasticsearch__.version(version)
-        client = proxy.client
+        client ||= proxy.client
         index_name = proxy.index_name
 
         create_index_options = {
@@ -52,6 +52,36 @@ module Gitlab
       end
       # rubocop: enable CodeReuse/ActiveRecord
 
+      def self.reindex_to_another_cluster(source_cluster_url, destination_cluster_url, version = ::Elastic::MultiVersionUtil::TARGET_VERSION)
+        proxy = Project.__elasticsearch__.version(version)
+        index_name = proxy.index_name
+
+        destination_client = Gitlab::Elastic::Client.build(url: destination_cluster_url)
+
+        create_empty_index(version, destination_client)
+
+        optimize_for_write_settings = { index: { number_of_replicas: 0, refresh_interval: "-1" } }
+        destination_client.indices.put_settings(index: index_name, body: optimize_for_write_settings)
+
+        source_addressable = Addressable::URI.parse(source_cluster_url)
+
+        response = destination_client.reindex(body: {
+          source: {
+            remote: {
+              host: source_addressable.omit(:user, :password).to_s,
+              username: source_addressable.user,
+              password: source_addressable.password
+            },
+            index: index_name
+          },
+          dest: {
+            index: index_name
+          }
+        }, wait_for_completion: false)
+
+        response['task']
+      end
+
       def self.delete_index(version = ::Elastic::MultiVersionUtil::TARGET_VERSION)
         Project.__elasticsearch__.version(version).delete_index!
       end

ee/lib/tasks/gitlab/elastic.rake

@@ -90,6 +90,12 @@ namespace :gitlab do
       end
     end
 
+    desc "GitLab | Elasticsearch | Reindex to another cluster"
+    task :reindex_to_another_cluster, [:source_cluster_url, :dest_cluster_url] => :environment do |_, args|
+      task_id = Gitlab::Elastic::Helper.reindex_to_another_cluster(args.source_cluster_url, args.dest_cluster_url)
+      puts "Reindexing to another cluster started with task id: #{task_id}".color(:green)
+    end
+
     def project_id_batches(&blk)
       relation = Project
 

ee/spec/lib/ee/gitlab/elastic/helper_spec.rb

 # frozen_string_literal: true
 
 require 'fast_spec_helper'
+require 'webmock/rspec'
 
 describe Gitlab::Elastic::Helper do
   describe '.index_exists' do
@@ -14,4 +15,49 @@ describe Gitlab::Elastic::Helper do
       expect(described_class.index_exists?).to eq(false)
     end
   end
+
+  describe 'reindex_to_another_cluster' do
+    it 'creates an empty index and triggers a reindex' do
+      _version_check_request = stub_request(:get, 'http://newcluster.example.com:9200/')
+        .to_return(status: 200, body: { version: { number: '7.5.1' } }.to_json)
+
+      _index_exists_check = stub_request(:head, 'http://newcluster.example.com:9200/gitlab-test')
+        .to_return(status: 404, body: +'')
+
+      create_cluster_request = stub_request(:put, 'http://newcluster.example.com:9200/gitlab-test')
+        .to_return(status: 200, body: +'')
+
+      optimize_settings_for_write_request = stub_request(:put, 'http://newcluster.example.com:9200/gitlab-test/_settings')
+        .with(body: { index: { number_of_replicas: 0, refresh_interval: "-1" } })
+        .to_return(status: 200, body: +'')
+
+      reindex_request = stub_request(:post, 'http://newcluster.example.com:9200/_reindex?wait_for_completion=false')
+        .with(
+          body: {
+            source: {
+              remote: {
+                host: 'http://oldcluster.example.com:9200/',
+                username: 'olduser',
+                password: 'oldpass'
+              },
+              index: 'gitlab-test'
+            },
+            dest: {
+              index: 'gitlab-test'
+            }
+          }).to_return(status: 200,
+                       headers: { "Content-Type" => "application/json" },
+                       body: { task: 'abc123' }.to_json)
+
+      source_url = 'http://olduser:oldpass@oldcluster.example.com:9200/'
+      dest_url = 'http://newcluster.example.com:9200/'
+
+      task = Gitlab::Elastic::Helper.reindex_to_another_cluster(source_url, dest_url)
+      expect(task).to eq('abc123')
+
+      assert_requested create_cluster_request
+      assert_requested optimize_settings_for_write_request
+      assert_requested reindex_request
+    end
+  end
 end

ee/spec/tasks/gitlab/elastic_rake_spec.rb

@@ -72,4 +72,12 @@ describe 'gitlab:elastic namespace rake tasks', :elastic do
       run_rake_task 'gitlab:elastic:index_snippets'
     end
   end
+
+  describe 'reindex_to_another_cluster' do
+    it 'calls reindex_to_another_cluster' do
+      expect(Gitlab::Elastic::Helper).to receive(:reindex_to_another_cluster).with('http://oldcluster.example.com:9300/', 'http://newcluster.example.com:9300/')
+
+      run_rake_task 'gitlab:elastic:reindex_to_another_cluster', 'http://oldcluster.example.com:9300/', 'http://newcluster.example.com:9300/'
+    end
+  end
 end