gitlab-org--gitlab-foss/app/workers/git_garbage_collect_worker.rb

97 lines
2.6 KiB
Ruby
Raw Normal View History

# frozen_string_literal: true
class GitGarbageCollectWorker
include ApplicationWorker
sidekiq_options retry: false
# Timeout set to 24h
LEASE_TIMEOUT = 86400
2016-10-27 08:59:52 -04:00
def perform(project_id, task = :gc, lease_key = nil, lease_uuid = nil)
project = Project.find(project_id)
active_uuid = get_lease_uuid(lease_key)
if active_uuid
return unless active_uuid == lease_uuid
renew_lease(lease_key, active_uuid)
else
lease_uuid = try_obtain_lease(lease_key)
2016-10-27 08:59:52 -04:00
return unless lease_uuid
end
task = task.to_sym
::Projects::GitDeduplicationService.new(project).execute
gitaly_call(task, project.repository.raw_repository)
# Refresh the branch cache in case garbage collection caused a ref lookup to fail
2016-10-27 08:59:52 -04:00
flush_ref_caches(project) if task == :gc
project.repository.expire_statistics_caches if task != :pack_refs
Allow public forks to be deduplicated When a project is forked, the new repository used to be a deep copy of everything stored on disk by leveraging `git clone`. This works well, and makes isolation between repository easy. However, the clone is at the start 100% the same as the origin repository. And in the case of the objects in the object directory, this is almost always going to be a lot of duplication. Object Pools are a way to create a third repository that essentially only exists for its 'objects' subdirectory. This third repository's object directory will be set as alternate location for objects. This means that in the case an object is missing in the local repository, git will look in another location. This other location is the object pool repository. When Git performs garbage collection, it's smart enough to check the alternate location. When objects are duplicated, it will allow git to throw one copy away. This copy is on the local repository, where to pool remains as is. These pools have an origin location, which for now will always be a repository that itself is not a fork. When the root of a fork network is forked by a user, the fork still clones the full repository. Async, the pool repository will be created. Either one of these processes can be done earlier than the other. To handle this race condition, the Join ObjectPool operation is idempotent. Given its idempotent, we can schedule it twice, with the same effect. To accommodate the holding of state two migrations have been added. 1. Added a state column to the pool_repositories column. This column is managed by the state machine, allowing for hooks on transitions. 2. pool_repositories now has a source_project_id. This column in convenient to have for multiple reasons: it has a unique index allowing the database to handle race conditions when creating a new record. Also, it's nice to know who the host is. As that's a short link to the fork networks root. Object pools are only available for public project, which use hashed storage and when forking from the root of the fork network. (That is, the project being forked from itself isn't a fork) In this commit message I use both ObjectPool and Pool repositories, which are alike, but different from each other. ObjectPool refers to whatever is on the disk stored and managed by Gitaly. PoolRepository is the record in the database.
2018-12-03 08:49:58 -05:00
# In case pack files are deleted, release libgit2 cache and open file
# descriptors ASAP instead of waiting for Ruby garbage collection
project.cleanup
2016-10-27 08:59:52 -04:00
ensure
cancel_lease(lease_key, lease_uuid) if lease_key.present? && lease_uuid.present?
2016-10-27 08:59:52 -04:00
end
private
def try_obtain_lease(key)
::Gitlab::ExclusiveLease.new(key, timeout: LEASE_TIMEOUT).try_obtain
end
def renew_lease(key, uuid)
::Gitlab::ExclusiveLease.new(key, uuid: uuid, timeout: LEASE_TIMEOUT).renew
end
def cancel_lease(key, uuid)
::Gitlab::ExclusiveLease.cancel(key, uuid)
end
def get_lease_uuid(key)
::Gitlab::ExclusiveLease.get_uuid(key)
end
## `repository` has to be a Gitlab::Git::Repository
def gitaly_call(task, repository)
client = if task == :pack_refs
Gitlab::GitalyClient::RefService.new(repository)
else
Gitlab::GitalyClient::RepositoryService.new(repository)
end
case task
when :gc
client.garbage_collect(bitmaps_enabled?)
when :full_repack
client.repack_full(bitmaps_enabled?)
when :incremental_repack
client.repack_incremental
when :pack_refs
client.pack_refs
end
rescue GRPC::NotFound => e
Gitlab::GitLogger.error("#{__method__} failed:\nRepository not found")
raise Gitlab::Git::Repository::NoRepository.new(e)
rescue GRPC::BadStatus => e
Gitlab::GitLogger.error("#{__method__} failed:\n#{e}")
raise Gitlab::Git::CommandError.new(e)
2016-10-27 08:59:52 -04:00
end
def flush_ref_caches(project)
project.repository.after_create_branch
project.repository.branch_names
project.repository.has_visible_content?
end
2016-10-27 08:59:52 -04:00
def bitmaps_enabled?
Gitlab::CurrentSettings.housekeeping_bitmaps_enabled
2016-10-27 08:59:52 -04:00
end
end