Module: Gitlab::GithubImport::ParallelScheduling

Includes:
JobDelayCalculator
Included in:
Importer::Attachments::BaseImporter, Importer::CollaboratorsImporter, Importer::DiffNotesImporter, Importer::IssueEventsImporter, Importer::IssuesImporter, Importer::LfsObjectsImporter, Importer::NotesImporter, Importer::ProtectedBranchesImporter, Importer::PullRequests::AllMergedByImporter, Importer::PullRequests::ReviewRequestsImporter, Importer::PullRequests::ReviewsImporter, Importer::PullRequestsImporter, Importer::SingleEndpointDiffNotesImporter, Importer::SingleEndpointIssueEventsImporter, Importer::SingleEndpointIssueNotesImporter, Importer::SingleEndpointMergeRequestNotesImporter
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}'
JOB_WAITER_CACHE_KEY =

The base cache key to use for storing job waiter key

'github-importer/job-waiter/%{project}/%{collection}'
JOB_WAITER_REMAINING_CACHE_KEY =

The base cache key to use for storing job waiter remaining jobs

'github-importer/job-waiter-remaining/%{project}/%{collection}'

Instance Attribute Summary collapse

Instance Method Summary collapse

Methods included from JobDelayCalculator

#parallel_import_batch

Instance Attribute Details

#already_imported_cache_key ⇒ Object (readonly)

Returns the value of attribute already_imported_cache_key.



8
9
10
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 8

def already_imported_cache_key
  @already_imported_cache_key
end

#client ⇒ Object (readonly)

Returns the value of attribute client.



8
9
10
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 8

def client
  @client
end

#job_waiter_cache_key ⇒ Object (readonly)

Returns the value of attribute job_waiter_cache_key.



8
9
10
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 8

def job_waiter_cache_key
  @job_waiter_cache_key
end

#job_waiter_remaining_cache_key ⇒ Object (readonly)

Returns the value of attribute job_waiter_remaining_cache_key.



8
9
10
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 8

def job_waiter_remaining_cache_key
  @job_waiter_remaining_cache_key
end

#page_counter ⇒ Object (readonly)

Returns the value of attribute page_counter.



8
9
10
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 8

def page_counter
  @page_counter
end

#project ⇒ Object (readonly)

Returns the value of attribute project.



8
9
10
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 8

def project
  @project
end

Instance Method Details

#abort_on_failure ⇒ Object 



202
203
204
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 202

def abort_on_failure
  false
end

#already_imported?(object) ⇒ Boolean

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

object - The object to check.

Returns:

  • (Boolean) 


155
156
157
158
159
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 155

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) 


198
199
200
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 198

def collection_method
  raise NotImplementedError
end

#collection_options ⇒ Object

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



208
209
210
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 208

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.



111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 111

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|
      object = object.to_h

      next if already_imported?(object)

      if increment_object_counter?(object)
        Gitlab::GithubImport::ObjectCounter.increment(project, object_type, :fetched)
      end

      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 



41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 41

def execute
  info(project.id, message: "starting importer")

  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, Gitlab::Cache::Import::Caching::SHORTER_TIMEOUT)
  info(project.id, message: "importer finished")

  retval
rescue StandardError => e
  Gitlab::Import::ImportFailureService.track(
    project_id: project.id,
    error_source: self.class.name,
    exception: e,
    fail_import: abort_on_failure,
    metrics: true
  )

  raise(e)
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) 


176
177
178
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 176

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) 


187
188
189
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 187

def importer_class
  raise NotImplementedError
end

#increment_object_counter?(_object) ⇒ Boolean

Returns:

  • (Boolean) 


147
148
149
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 147

def increment_object_counter?(_object)
  true
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.



24
25
26
27
28
29
30
31
32
33
34
35
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 24

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 }
  @job_waiter_cache_key = JOB_WAITER_CACHE_KEY %
    { project: project.id, collection: collection_method }
  @job_waiter_remaining_cache_key = JOB_WAITER_REMAINING_CACHE_KEY %
    { project: project.id, collection: collection_method }
end

#mark_as_imported(object) ⇒ Object

Marks the given object as “already imported”.



162
163
164
165
166
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 162

def mark_as_imported(object)
  id = id_for_already_imported_cache(object)

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

#object_type ⇒ Object

Raises:

  • (NotImplementedError) 


168
169
170
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 168

def object_type
  raise NotImplementedError
end

#parallel? ⇒ Boolean

Returns:

  • (Boolean) 


37
38
39
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 37

def parallel?
  @parallel
end

#parallel_import ⇒ Object

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



87
88
89
90
91
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 87

def parallel_import
  raise 'Batch settings must be defined for parallel import' if parallel_import_batch.blank?

  spread_parallel_import
end

#representation_class ⇒ Object

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

Raises:

  • (NotImplementedError) 


182
183
184
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 182

def representation_class
  raise NotImplementedError
end

#sequential_import ⇒ Object

Imports all the objects in sequence in the current thread.



77
78
79
80
81
82
83
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 77

def sequential_import
  each_object_to_import do |object|
    repr = object_representation(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) 


193
194
195
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 193

def sidekiq_worker_class
  raise NotImplementedError
end

#spread_parallel_import ⇒ Object 



93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
 
# File 'lib/gitlab/github_import/parallel_scheduling.rb', line 93

def spread_parallel_import
  enqueued_job_counter = 0

  each_object_to_import do |object|
    repr = object_representation(object)

    job_delay = calculate_job_delay(enqueued_job_counter)
    sidekiq_worker_class.perform_in(job_delay, project.id, repr.to_hash, job_waiter.key)
    enqueued_job_counter += 1

    job_waiter.jobs_remaining = Gitlab::Cache::Import::Caching.increment(job_waiter_remaining_cache_key)
  end

  job_waiter
end