Module: Gitlab::GithubImport::ParallelScheduling

Included in:
Importer::DiffNotesImporter, Importer::IssuesImporter, Importer::LfsObjectsImporter, Importer::NotesImporter, Importer::PullRequestsImporter
Defined in:
lib/gitlab/github_import/parallel_scheduling.rb

Constant Summary collapse

ALREADY_IMPORTED_CACHE_KEY =

The base cache key to use for tracking already imported objects.

'github-importer/already-imported/%{project}/%{collection}'

Instance Attribute Summary collapse

Instance Method Summary collapse

Instance Attribute Details

#already_imported_cache_key ⇒ Object (readonly)

Returns the value of attribute already_imported_cache_key


6
7
8
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 6

def already_imported_cache_key
  @already_imported_cache_key
end

#client ⇒ Object (readonly)

Returns the value of attribute client


6
7
8
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 6

def client
  @client
end

#page_counter ⇒ Object (readonly)

Returns the value of attribute page_counter


6
7
8
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 6

def page_counter
  @page_counter
end

#project ⇒ Object (readonly)

Returns the value of attribute project


6
7
8
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 6

def project
  @project
end

Instance Method Details

#already_imported?(object) ⇒ Boolean

Returns true if the given object has already been imported, false otherwise.

object - The object to check.

Returns:

  • (Boolean) 

112
113
114
115
116
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 112

def already_imported?(object)
  id = id_for_already_imported_cache(object)

  Gitlab::Cache::Import::Caching.set_includes?(already_imported_cache_key, id)
end

#collection_method ⇒ Object

The name of the method to call to retrieve the data to import.

Raises:

  • (NotImplementedError) 

151
152
153
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 151

def collection_method
  raise NotImplementedError
end

#collection_options ⇒ Object

Any options to be passed to the method used for retrieving the data to import.


157
158
159
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 157

def collection_options
  {}
end

#each_object_to_import ⇒ Object

The method that will be called for traversing through all the objects to import, yielding them to the supplied block.


78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 78

def each_object_to_import
  repo = project.import_source

  # We inject the page number here to make sure that all importers always
  # start where they left off. Simply starting over wouldn't work for
  # repositories with a lot of data (e.g. tens of thousands of comments).
  options = collection_options.merge(page: page_counter.current)

  client.each_page(collection_method, repo, options) do |page|
    # Technically it's possible that the same work is performed multiple
    # times, as Sidekiq doesn't guarantee there will ever only be one
    # instance of a job. In such a scenario it's possible for one job to
    # have a lower page number (e.g. 5) compared to another (e.g. 10). In
    # this case we skip over all the objects until we have caught up,
    # reducing the number of duplicate jobs scheduled by the provided
    # block.
    next unless page_counter.set(page.number)

    page.objects.each do |object|
      next if already_imported?(object)

      yield object

      # We mark the object as imported immediately so we don't end up
      # scheduling it multiple times.
      mark_as_imported(object)
    end
  end
end

#execute ⇒ Object 


28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 28

def execute
  retval =
    if parallel?
      parallel_import
    else
      sequential_import
    end

  # Once we have completed all work we can remove our "already exists"
  # cache so we don't put too much pressure on Redis.
  #
  # We don't immediately remove it since it's technically possible for
  # other instances of this job to still run, instead we set the
  # expiration time to a lower value. This prevents the other jobs from
  # still scheduling duplicates while. Since all work has already been
  # completed those jobs will just cycle through any remaining pages while
  # not scheduling anything.
  Gitlab::Cache::Import::Caching.expire(already_imported_cache_key, 15.minutes.to_i)

  retval
end

#id_for_already_imported_cache(object) ⇒ Object

Returns the ID to use for the cache used for checking if an object has already been imported or not.

object - The object we may want to import.

Raises:

  • (NotImplementedError) 

129
130
131
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 129

def id_for_already_imported_cache(object)
  raise NotImplementedError
end

#importer_class ⇒ Object

The class to use for importing objects when importing them sequentially.

Raises:

  • (NotImplementedError) 

140
141
142
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 140

def importer_class
  raise NotImplementedError
end

#initialize(project, client, parallel: true) ⇒ Object

project - An instance of `Project`. client - An instance of `Gitlab::GithubImport::Client`. parallel - When set to true the objects will be imported in parallel.


15
16
17
18
19
20
21
22
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 15

def initialize(project, client, parallel: true)
  @project = project
  @client = client
  @parallel = parallel
  @page_counter = PageCounter.new(project, collection_method)
  @already_imported_cache_key = ALREADY_IMPORTED_CACHE_KEY %
    { project: project.id, collection: collection_method }
end

#mark_as_imported(object) ⇒ Object

Marks the given object as “already imported”.


119
120
121
122
123
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 119

def mark_as_imported(object)
  id = id_for_already_imported_cache(object)

  Gitlab::Cache::Import::Caching.set_add(already_imported_cache_key, id)
end

#parallel? ⇒ Boolean

Returns:

  • (Boolean) 

24
25
26
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 24

def parallel?
  @parallel
end

#parallel_import ⇒ Object

Imports all objects in parallel by scheduling a Sidekiq job for every individual object.


61
62
63
64
65
66
67
68
69
70
71
72
73
74
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 61

def parallel_import
  waiter = JobWaiter.new

  each_object_to_import do |object|
    repr = representation_class.from_api_response(object)

    sidekiq_worker_class
      .perform_async(project.id, repr.to_hash, waiter.key)

    waiter.jobs_remaining += 1
  end

  waiter
end

#representation_class ⇒ Object

The class used for converting API responses to Hashes when performing the import.

Raises:

  • (NotImplementedError) 

135
136
137
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 135

def representation_class
  raise NotImplementedError
end

#sequential_import ⇒ Object

Imports all the objects in sequence in the current thread.


51
52
53
54
55
56
57
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 51

def sequential_import
  each_object_to_import do |object|
    repr = representation_class.from_api_response(object)

    importer_class.new(repr, project, client).execute
  end
end

#sidekiq_worker_class ⇒ Object

The Sidekiq worker class used for scheduling the importing of objects in parallel.

Raises:

  • (NotImplementedError) 

146
147
148
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 146

def sidekiq_worker_class
  raise NotImplementedError
end