Add elastic test rake task

db/fixtures/development/04_project.rb

 require './spec/support/sidekiq'
 
+# rubocop:disable Rails/Output
+
 Sidekiq::Testing.inline! do
   Gitlab::Seeder.quiet do
-    project_urls = [
-      'https://gitlab.com/gitlab-org/gitlab-test.git',
-      'https://gitlab.com/gitlab-org/gitlab-shell.git',
-      'https://gitlab.com/gnuwget/wget2.git',
-      'https://gitlab.com/Commit451/LabCoat.git',
-      'https://github.com/jashkenas/underscore.git',
-      'https://github.com/flightjs/flight.git',
-      'https://github.com/twitter/typeahead.js.git',
-      'https://github.com/h5bp/html5-boilerplate.git',
-      'https://github.com/google/material-design-lite.git',
-      'https://github.com/jlevy/the-art-of-command-line.git',
-      'https://github.com/FreeCodeCamp/freecodecamp.git',
-      'https://github.com/google/deepdream.git',
-      'https://github.com/jtleek/datasharing.git',
-      'https://github.com/WebAssembly/design.git',
-      'https://github.com/airbnb/javascript.git',
-      'https://github.com/tessalt/echo-chamber-js.git',
-      'https://github.com/atom/atom.git',
-      'https://github.com/mattermost/mattermost-server.git',
-      'https://github.com/purifycss/purifycss.git',
-      'https://github.com/facebook/nuclide.git',
-      'https://github.com/wbkd/awesome-d3.git',
-      'https://github.com/kilimchoi/engineering-blogs.git',
-      'https://github.com/gilbarbara/logos.git',
-      'https://github.com/reduxjs/redux.git',
-      'https://github.com/awslabs/s2n.git',
-      'https://github.com/arkency/reactjs_koans.git',
-      'https://github.com/twbs/bootstrap.git',
-      'https://github.com/chjj/ttystudio.git',
-      'https://github.com/MostlyAdequate/mostly-adequate-guide.git',
-      'https://github.com/octocat/Spoon-Knife.git',
-      'https://github.com/opencontainers/runc.git',
-      'https://github.com/googlesamples/android-topeka.git'
+    Gitlab::Seeder.without_gitaly_timeout do
+      project_urls = %w[
+        https://gitlab.com/gitlab-org/gitlab-test.git
+        https://gitlab.com/gitlab-org/gitlab-shell.git
+        https://gitlab.com/gnuwget/wget2.git
+        https://gitlab.com/Commit451/LabCoat.git
+        https://github.com/jashkenas/underscore.git
+        https://github.com/flightjs/flight.git
+        https://github.com/twitter/typeahead.js.git
+        https://github.com/h5bp/html5-boilerplate.git
+        https://github.com/google/material-design-lite.git
+        https://github.com/jlevy/the-art-of-command-line.git
+        https://github.com/FreeCodeCamp/freecodecamp.git
+        https://github.com/google/deepdream.git
+        https://github.com/jtleek/datasharing.git
+        https://github.com/WebAssembly/design.git
+        https://github.com/airbnb/javascript.git
+        https://github.com/tessalt/echo-chamber-js.git
+        https://github.com/atom/atom.git
+        https://github.com/mattermost/mattermost-server.git
+        https://github.com/purifycss/purifycss.git
+        https://github.com/facebook/nuclide.git
+        https://github.com/wbkd/awesome-d3.git
+        https://github.com/kilimchoi/engineering-blogs.git
+        https://github.com/gilbarbara/logos.git
+        https://github.com/reduxjs/redux.git
+        https://github.com/awslabs/s2n.git
+        https://github.com/arkency/reactjs_koans.git
+        https://github.com/twbs/bootstrap.git
+        https://github.com/chjj/ttystudio.git
+        https://github.com/MostlyAdequate/mostly-adequate-guide.git
+        https://github.com/octocat/Spoon-Knife.git
+        https://github.com/opencontainers/runc.git
+        https://github.com/googlesamples/android-topeka.git
       ]
 
-    # You can specify how many projects you need during seed execution
-    size = ENV['SIZE'].present? ? ENV['SIZE'].to_i : 8
+      large_project_urls = %w[
+        https://github.com/torvalds/linux.git
+        https://gitlab.gnome.org/GNOME/gimp.git
+        https://gitlab.gnome.org/GNOME/gnome-mud.git
+        https://gitlab.com/fdroid/fdroidclient.git
+        https://gitlab.com/inkscape/inkscape.git
+        https://github.com/gnachman/iTerm2.git
+      ]
 
-    project_urls.first(size).each_with_index do |url, i|
+      def create_project(url, force_latest_storage: false)
         group_path, project_path = url.split('/')[-2..-1]
 
         group = Group.find_by(path: group_path)
@@ -67,7 +76,7 @@ Sidekiq::Testing.inline! do
           skip_disk_validation: true
         }
 
-      if i % 2 == 0
+        if force_latest_storage
           params[:storage_version] = Project::LATEST_STORAGE_VERSION
         end
 
@@ -91,5 +100,38 @@ Sidekiq::Testing.inline! do
           print 'F'
         end
       end
+
+      # You can specify how many projects you need during seed execution
+      size = ENV['SIZE'].present? ? ENV['SIZE'].to_i : 8
+
+      project_urls.first(size).each_with_index do |url, i|
+        create_project(url, force_latest_storage: i.even?)
+      end
+
+      if ENV['LARGE_PROJECTS'].present?
+        large_project_urls.each(&method(:create_project))
+
+        if ENV['FORK'].present?
+          puts "\nGenerating forks"
+
+          project_name = ENV['FORK'] == 'true' ? 'torvalds/linux' : ENV['FORK']
+
+          project = Project.find_by_full_path(project_name)
+
+          User.offset(1).first(5).each do |user|
+            new_project = Projects::ForkService.new(project, user).execute
+
+            if new_project.valid? && (new_project.valid_repo? || new_project.import_state.scheduled?)
+              print '.'
+            else
+              new_project.errors.full_messages.each do |error|
+                puts "#{new_project.full_path}: #{error}"
+              end
+              print 'F'
+            end
+          end
+        end
+      end
+    end
   end
 end

doc/development/elasticsearch.md

@@ -38,6 +38,13 @@ this adds `gitlab-elasticsearch-indexer` to `$GOPATH/bin`, please make sure that
 
 **note:** `make` will not recompile the executable unless you do `make clean` beforehand
 
+## Helpful rake tasks
+
+- `gitlab:elastic:test:index_size`: Tells you how much space the current index is using, as well as how many documents are in the index.
+- `gitlab:elastic:test:index_size_change`: Outputs index size, reindexes, and outputs index size again. Useful when testing improvements to indexing size.
+
+Additionally, if you need large repos or multiple forks for testing, please consider [following these instructions](https://docs.gitlab.com/ee/development/rake_tasks.html#extra-project-seed-options)
+
 ## How does it work?
 
 The ElasticSearch integration depends on an external indexer. We ship a [ruby indexer](https://gitlab.com/gitlab-org/gitlab-ee/blob/master/bin/elastic_repo_indexer) by default but are also working on an [indexer written in Go](https://gitlab.com/gitlab-org/gitlab-elasticsearch-indexer). The user must trigger the initial indexing via a rake task, but after this is done GitLab itself will trigger reindexing when required via `after_` callbacks on create, update, and destroy that are inherited from [/ee/app/models/concerns/elastic/application_search.rb](https://gitlab.com/gitlab-org/gitlab-ee/blob/master/ee/app/models/concerns/elastic/application_search.rb).

doc/development/rake_tasks.md

@@ -38,6 +38,14 @@ Note that since you can't see the questions from stdout, you might just want
 to `echo 'yes'` to keep it running. It would still print the errors on stderr
 so no worries about missing errors.
 
+### Extra Project seed options
+
+There are a few environment flags you can pass to change how projects are seeded
+
+- `SIZE`: defaults to `8`, max: `32`. Amount of projects to create.
+- `LARGE_PROJECTS`: defaults to false. If set will clone 6 large projects to help with testing.
+- `FORK`: defaults to false. If set to `true` will fork `torvalds/linux` five times. Can also be set to an existing project full_path and it will fork that instead.
+
 ### Notes for MySQL
 
 Since the seeds would contain various UTF-8 characters, such as emojis or so,

ee/lib/gitlab/elastic/helper.rb

@@ -49,6 +49,10 @@ module Gitlab
       def self.refresh_index
         Project.__elasticsearch__.refresh_index!
       end
+
+      def self.index_size
+        Project.__elasticsearch__.client.indices.stats['indices'][Project.__elasticsearch__.index_name]['total']
+      end
     end
   end
 end

ee/lib/tasks/gitlab/elastic/test.rake

+namespace :gitlab do
+  namespace :elastic do
+    namespace :test do
+      desc 'GitLab | Elasticsearch | Test | Measure space taken by ES indices'
+      task index_size: :environment do
+        puts "===== Size stats for index: #{Project.__elasticsearch__.index_name} ====="
+        pp Gitlab::Elastic::Helper.index_size.slice(*%w(docs store))
+      end
+
+      desc 'GitLab | Elasticsearch | Test | Measure space taken by ES indices, reindex, and measure space taken again'
+      task :index_size_change do
+        Rake::Task["gitlab:elastic:test:index_size"].invoke
+
+        puts '===== Reindexing, please wait ====='
+
+        silence_stdout do
+          Rake::Task["gitlab:elastic:index"].invoke
+        end
+
+        # `#invoke` will only ever invoke a rake task once unless it gets reenabled and
+        # we can't use `#execute` because the `index_size` task depends on loading the environment
+        Rake::Task["gitlab:elastic:test:index_size"].reenable
+        Rake::Task["gitlab:elastic:test:index_size"].invoke
+
+        puts 'Done! Please ensure document count is the expected value, otherwise please check indexing is working properly.'
+      end
+    end
+  end
+end
+
+def silence_stdout(&_block)
+  old_stdout = $stdout.dup
+  $stdout.reopen(File::NULL)
+  $stdout.sync = true
+
+  yield
+ensure
+  $stdout.reopen(old_stdout)
+  old_stdout.close
+end

lib/gitlab/seeder.rb

@@ -26,6 +26,19 @@ module Gitlab
       puts "\nOK".color(:green)
     end
 
+    def self.without_gitaly_timeout
+      # Remove Gitaly timeout
+      old_timeout = Gitlab::CurrentSettings.current_application_settings.gitaly_timeout_default
+      Gitlab::CurrentSettings.current_application_settings.update_columns(gitaly_timeout_default: 0)
+      # Otherwise we still see the default value when running seed_fu
+      ApplicationSetting.expire
+
+      yield
+    ensure
+      Gitlab::CurrentSettings.current_application_settings.update_columns(gitaly_timeout_default: old_timeout)
+      ApplicationSetting.expire
+    end
+
     def self.mute_notifications
       NotificationService.prepend(MuteNotifications)
     end