Reduce UPDATEs for background column type changesbackground-migration-fix

Prior to this commit we would essentially update all rows in a table,
even those where the source column (e.g. `issues.closed_at`) was NULL.
This in turn could lead to statement timeouts when using the default
batch size of 10 000 rows per job.

To work around this we don't schedule jobs for rows where the source
value is NULL. We also don't update rows where the source column is NULL
(as an extra precaution) or the target column already has a non-NULL
value. Using this approach it should be possible to update 10 000 rows
in the "issues" table in about 7.5 - 8 seconds.

Fixes https://gitlab.com/gitlab-org/gitlab-ce/issues/42158

3 files changed, 6 insertions, 3 deletions

diff --git a/lib/gitlab/background_migration/copy_column.rb b/lib/gitlab/background_migration/copy_column.rb
index a2cb215c230..ef70f37d5eb 100644
--- a/lib/gitlab/background_migration/copy_column.rb
+++ b/lib/gitlab/background_migration/copy_column.rb
@@ -28,6 +28,8 @@ module Gitlab
         UPDATE #{quoted_table}
         SET #{quoted_copy_to} = #{quoted_copy_from}
         WHERE id BETWEEN #{start_id} AND #{end_id}
+        AND #{quoted_copy_from} IS NOT NULL
+        AND #{quoted_copy_to} IS NULL
         SQL
       end
 
diff --git a/lib/gitlab/database/migration_helpers.rb b/lib/gitlab/database/migration_helpers.rb
index 592a1956ceb..dbe6259fce7 100644
--- a/lib/gitlab/database/migration_helpers.rb
+++ b/lib/gitlab/database/migration_helpers.rb
@@ -525,8 +525,9 @@ module Gitlab
         install_rename_triggers(table, column, temp_column)
 
         # Schedule the jobs that will copy the data from the old column to the
-        # new one.
-        relation.each_batch(of: batch_size) do |batch, index|
+        # new one. Rows with NULL values in our source column are skipped since
+        # the target column is already NULL at this point.
+        relation.where.not(column => nil).each_batch(of: batch_size) do |batch, index|
           start_id, end_id = batch.pluck('MIN(id), MAX(id)').first
           max_index = index
 
diff --git a/spec/lib/gitlab/database/migration_helpers_spec.rb b/spec/lib/gitlab/database/migration_helpers_spec.rb
index 43761c2fe0c..1de3a14b809 100644
--- a/spec/lib/gitlab/database/migration_helpers_spec.rb
+++ b/spec/lib/gitlab/database/migration_helpers_spec.rb
@@ -1038,7 +1038,7 @@ describe Gitlab::Database::MigrationHelpers do
   end
 
   describe '#change_column_type_using_background_migration' do
-    let!(:issue) { create(:issue) }
+    let!(:issue) { create(:issue, :closed, closed_at: Time.zone.now) }
 
     let(:issue_model) do
       Class.new(ActiveRecord::Base) do