Commit d1825985 authored by Douwe Maan's avatar Douwe Maan Committed by Winnie Hellmann
Browse files

Merge branch 'github-importer-refactor' into 'master' 

Rewrite the GitHub importer to perform work in parallel and greatly improve performance

Closes #33135, #38621, and #39361

See merge request gitlab-org/gitlab-ce!14731
(cherry picked from commit 92249f1a)
parent 0946b638

app/controllers/import/github_controller.rb

+2 −2
Original line number Diff line number Diff line
@@ -43,7 +43,7 @@ def create 
    @target_namespace = find_or_create_namespace(namespace_path, current_user.namespace_path)



    if can?(current_user, :create_projects, @target_namespace)

      @project = Gitlab::GithubImport::ProjectCreator.new(repo, @project_name, @target_namespace, current_user, access_params, type: provider).execute

      @project = Gitlab::LegacyGithubImport::ProjectCreator.new(repo, @project_name, @target_namespace, current_user, access_params, type: provider).execute

    else

      render 'unauthorized'

    end
@@ -52,7 +52,7 @@ def create 
  private



  def client

    @client ||= Gitlab::GithubImport::Client.new(session[access_token_key], client_options)

    @client ||= Gitlab::LegacyGithubImport::Client.new(session[access_token_key], client_options)

  end



  def verify_import_enabled

app/models/project.rb

+41 −0
Original line number Diff line number Diff line
@@ -365,6 +365,7 @@ def self.with_feature_available_for_user(feature, user) 
  scope :abandoned, -> { where('projects.last_activity_at < ?', 6.months.ago) }



  scope :excluding_project, ->(project) { where.not(id: project) }

  scope :import_started, -> { where(import_status: 'started') }



  state_machine :import_status, initial: :none do

    event :import_schedule do
@@ -1190,6 +1191,10 @@ def repository_exists? 
    !!repository.exists?

  end



  def wiki_repository_exists?

    wiki.repository_exists?

  end



  # update visibility_level of forks

  def update_forks_visibility_level

    return unless visibility_level < visibility_level_was
@@ -1433,6 +1438,31 @@ def rename_repo_notify! 
    reload_repository!

  end



  def after_import

    repository.after_import

    import_finish

    remove_import_jid

    update_project_counter_caches

  end



  def update_project_counter_caches

    classes = [

      Projects::OpenIssuesCountService,

      Projects::OpenMergeRequestsCountService

    ]



    classes.each do |klass|

      klass.new(self).refresh_cache

    end

  end



  def remove_import_jid

    return unless import_jid



    Gitlab::SidekiqStatus.unset(import_jid)

    update_column(:import_jid, nil)

  end



  def running_or_pending_build_count(force: false)

    Rails.cache.fetch(['projects', id, 'running_or_pending_build_count'], force: force) do

      builds.running_or_pending.count(:all)
@@ -1690,6 +1720,17 @@ def reference_counter(wiki: false) 
    Gitlab::ReferenceCounter.new(gl_repository(is_wiki: wiki))

  end



  # Refreshes the expiration time of the associated import job ID.

  #

  # This method can be used by asynchronous importers to refresh the status,

  # preventing the StuckImportJobsWorker from marking the import as failed.

  def refresh_import_jid_expiration

    return unless import_jid



    Gitlab::SidekiqStatus

      .set(import_jid, StuckImportJobsWorker::IMPORT_JOBS_EXPIRATION)

  end



  private



  def storage

app/models/repository.rb

+4 −0
Original line number Diff line number Diff line
@@ -973,6 +973,10 @@ def fetch_source_branch!(source_repository, source_branch, local_ref) 
    raw_repository.fetch_source_branch!(source_repository.raw_repository, source_branch, local_ref)

  end



  def remote_exists?(name)

    raw_repository.remote_exists?(name)

  end



  def compare_source_branch(target_branch_name, source_repository, source_branch_name, straight:)

    raw_repository.compare_source_branch(target_branch_name, source_repository.raw_repository, source_branch_name, straight: straight)

  end

app/models/user.rb

+14 −9
Original line number Diff line number Diff line
@@ -267,18 +267,23 @@ def sort(method) 
      end

    end



    def for_github_id(id)

      joins(:identities)

        .where(identities: { provider: :github, extern_uid: id.to_s })

    end



    # Find a User by their primary email or any associated secondary email

    def find_by_any_email(email)

      sql = 'SELECT *

      FROM users

      WHERE id IN (

        SELECT id FROM users WHERE email = :email

        UNION

        SELECT emails.user_id FROM emails WHERE email = :email

      )

      LIMIT 1;'

      by_any_email(email).take

    end



    # Returns a relation containing all the users for the given Email address

    def by_any_email(email)

      users = where(email: email)

      emails = joins(:emails).where(emails: { email: email })

      union = Gitlab::SQL::Union.new([users, emails])



      User.find_by_sql([sql, { email: email }]).first

      from("(#{union.to_sql}) #{table_name}")

    end



    def filter(filter_name)

app/services/projects/import_service.rb

+17 −1
Original line number Diff line number Diff line
@@ -4,6 +4,18 @@ class ImportService < BaseService 


    Error = Class.new(StandardError)



    # Returns true if this importer is supposed to perform its work in the

    # background.

    #

    # This method will only return `true` if async importing is explicitly

    # supported by an importer class (`Gitlab::GithubImport::ParallelImporter`

    # for example).

    def async?

      return false unless has_importer?



      !!importer_class.try(:async?)

    end



    def execute

      add_repository_to_project unless project.gitlab_project_import?
@@ -75,12 +87,16 @@ def import_data 
      end

    end



    def importer_class

      Gitlab::ImportSources.importer(project.import_type)

    end



    def has_importer?

      Gitlab::ImportSources.importer_names.include?(project.import_type)

    end



    def importer

      Gitlab::ImportSources.importer(project.import_type).new(project)

      importer_class.new(project)

    end



    def unknown_url?