Welcome to mirror list, hosted at ThFree Co, Russian Federation.

gitlab.com/gitlab-org/gitlab-foss.git - Unnamed repository; edit this file 'description' to name the repository.
summaryrefslogtreecommitdiff
path: root/lib
diff options
context:
space:
mode:
authorYorick Peterse <yorickpeterse@gmail.com>2018-07-11 15:59:43 +0300
committerYorick Peterse <yorickpeterse@gmail.com>2018-07-11 15:59:43 +0300
commitd975a29be91fd8a6156d3d1446056b5f98412e95 (patch)
treea0440ddb62992c1577c2b962860b491dd9b7a606 /lib
parentad604b52f2699c624187fd99d0d68bb3452a7a5c (diff)
parent659aeba43c498b7a45fb1495371ded7436b238c9 (diff)
Merge branch 'add-back-mr-diff-deletion-migration' into 'master'
Add back MR diff deletion migration See merge request gitlab-org/gitlab-ce!20331
Diffstat (limited to 'lib')
-rw-r--r--lib/gitlab/background_migration/delete_diff_files.rb86
-rw-r--r--lib/gitlab/background_migration/schedule_diff_files_deletion.rb44
2 files changed, 105 insertions, 25 deletions
diff --git a/lib/gitlab/background_migration/delete_diff_files.rb b/lib/gitlab/background_migration/delete_diff_files.rb
index 8fb2c334048..664ead1af44 100644
--- a/lib/gitlab/background_migration/delete_diff_files.rb
+++ b/lib/gitlab/background_migration/delete_diff_files.rb
@@ -4,41 +4,77 @@
module Gitlab
module BackgroundMigration
class DeleteDiffFiles
- def perform(merge_request_diff_id)
- merge_request_diff = MergeRequestDiff.find_by(id: merge_request_diff_id)
+ class MergeRequestDiff < ActiveRecord::Base
+ self.table_name = 'merge_request_diffs'
- return unless merge_request_diff
- return unless should_delete_diff_files?(merge_request_diff)
+ belongs_to :merge_request
+ has_many :merge_request_diff_files
+ end
- MergeRequestDiff.transaction do
- merge_request_diff.update_column(:state, 'without_files')
-
- # explain (analyze, buffers) when deleting 453 diff files:
- #
- # Delete on merge_request_diff_files (cost=0.57..8487.35 rows=4846 width=6) (actual time=43.265..43.265 rows=0 loops=1)
- # Buffers: shared hit=2043 read=259 dirtied=254
- # -> Index Scan using index_merge_request_diff_files_on_mr_diff_id_and_order on merge_request_diff_files (cost=0.57..8487.35 rows=4846 width=6) (actu
- # al time=0.466..26.317 rows=453 loops=1)
- # Index Cond: (merge_request_diff_id = 463448)
- # Buffers: shared hit=17 read=84
- # Planning time: 0.107 ms
- # Execution time: 43.287 ms
- #
- MergeRequestDiffFile.where(merge_request_diff_id: merge_request_diff.id).delete_all
+ class MergeRequestDiffFile < ActiveRecord::Base
+ self.table_name = 'merge_request_diff_files'
+ end
+
+ DEAD_TUPLES_THRESHOLD = 50_000
+ VACUUM_WAIT_TIME = 5.minutes
+
+ def perform(ids)
+ @ids = ids
+
+ # We should reschedule until deadtuples get in a desirable
+ # state (e.g. < 50_000). That may take more than one reschedule.
+ #
+ if should_wait_deadtuple_vacuum?
+ reschedule
+ return
end
+
+ prune_diff_files
+ end
+
+ def should_wait_deadtuple_vacuum?
+ return false unless Gitlab::Database.postgresql?
+
+ diff_files_dead_tuples_count >= DEAD_TUPLES_THRESHOLD
end
private
- def should_delete_diff_files?(merge_request_diff)
- return false if merge_request_diff.state == 'without_files'
+ def reschedule
+ BackgroundMigrationWorker.perform_in(VACUUM_WAIT_TIME, self.class.name.demodulize, [@ids])
+ end
+
+ def diffs_collection
+ MergeRequestDiff.where(id: @ids)
+ end
+
+ def diff_files_dead_tuples_count
+ dead_tuple =
+ execute_statement("SELECT n_dead_tup FROM pg_stat_all_tables "\
+ "WHERE relname = 'merge_request_diff_files'")[0]
- merge_request = merge_request_diff.merge_request
+ dead_tuple&.fetch('n_dead_tup', 0).to_i
+ end
+
+ def prune_diff_files
+ removed = 0
+ updated = 0
- return false unless merge_request.state == 'merged'
- return false if merge_request_diff.id == merge_request.latest_merge_request_diff_id
+ MergeRequestDiff.transaction do
+ updated = diffs_collection.update_all(state: 'without_files')
+ removed = MergeRequestDiffFile.where(merge_request_diff_id: @ids).delete_all
+ end
+
+ log_info("Removed #{removed} merge_request_diff_files rows, "\
+ "updated #{updated} merge_request_diffs rows")
+ end
+
+ def execute_statement(sql)
+ ActiveRecord::Base.connection.execute(sql)
+ end
- true
+ def log_info(message)
+ Rails.logger.info("BackgroundMigration::DeleteDiffFiles - #{message}")
end
end
end
diff --git a/lib/gitlab/background_migration/schedule_diff_files_deletion.rb b/lib/gitlab/background_migration/schedule_diff_files_deletion.rb
new file mode 100644
index 00000000000..609cf19187c
--- /dev/null
+++ b/lib/gitlab/background_migration/schedule_diff_files_deletion.rb
@@ -0,0 +1,44 @@
+# frozen_string_literal: true
+# rubocop:disable Style/Documentation
+
+module Gitlab
+ module BackgroundMigration
+ class ScheduleDiffFilesDeletion
+ class MergeRequestDiff < ActiveRecord::Base
+ self.table_name = 'merge_request_diffs'
+
+ belongs_to :merge_request
+
+ include EachBatch
+ end
+
+ DIFF_BATCH_SIZE = 5_000
+ INTERVAL = 5.minutes
+ MIGRATION = 'DeleteDiffFiles'
+
+ def perform
+ diffs = MergeRequestDiff
+ .from("(#{diffs_collection.to_sql}) merge_request_diffs")
+ .where('merge_request_diffs.id != merge_request_diffs.latest_merge_request_diff_id')
+ .select(:id)
+
+ diffs.each_batch(of: DIFF_BATCH_SIZE) do |relation, index|
+ ids = relation.pluck(:id)
+
+ BackgroundMigrationWorker.perform_in(index * INTERVAL, MIGRATION, [ids])
+ end
+ end
+
+ private
+
+ def diffs_collection
+ MergeRequestDiff
+ .joins(:merge_request)
+ .where("merge_requests.state = 'merged'")
+ .where('merge_requests.latest_merge_request_diff_id IS NOT NULL')
+ .where("merge_request_diffs.state NOT IN ('without_files', 'empty')")
+ .select('merge_requests.latest_merge_request_diff_id, merge_request_diffs.id')
+ end
+ end
+ end
+end