Module: Gitlab::Database::MigrationHelpers

Includes:
AsyncConstraints::MigrationHelpers, AsyncIndexes::MigrationHelpers, DynamicModelHelpers, WraparoundVacuumHelpers, Gitlab::Database::Migrations::BackgroundMigrationHelpers, Gitlab::Database::Migrations::BatchedBackgroundMigrationHelpers, Gitlab::Database::Migrations::ConstraintsHelpers, Gitlab::Database::Migrations::ExtensionHelpers, Gitlab::Database::Migrations::LockRetriesHelpers, Gitlab::Database::Migrations::RedisHelpers, Gitlab::Database::Migrations::ReestablishedConnectionStack, Gitlab::Database::Migrations::SidekiqHelpers, Gitlab::Database::Migrations::TimeoutHelpers, PartitionHelpers, RenameTableHelpers
Included in:
BackgroundMigration::LegacyUploadsMigrator, CascadingNamespaceSettings, V2, PartitioningMigrationHelpers::IndexHelpers, PartitioningMigrationHelpers::TableManagementHelpers, PartitioningMigrationHelpers::UniquenessHelpers
Defined in:
lib/gitlab/database/migration_helpers.rb,
lib/gitlab/database/migration_helpers/v2.rb,
lib/gitlab/database/migration_helpers/swapping.rb,
lib/gitlab/database/migration_helpers/announce_database.rb,
lib/gitlab/database/migration_helpers/convert_to_bigint.rb,
lib/gitlab/database/migration_helpers/wraparound_autovacuum.rb,
lib/gitlab/database/migration_helpers/restrict_gitlab_schema.rb,
lib/gitlab/database/migration_helpers/loose_foreign_key_helpers.rb,
lib/gitlab/database/migration_helpers/wraparound_vacuum_helpers.rb,
lib/gitlab/database/migration_helpers/cascading_namespace_settings.rb,
lib/gitlab/database/migration_helpers/automatic_lock_writes_on_tables.rb

Defined Under Namespace

Modules: AnnounceDatabase, AutomaticLockWritesOnTables, CascadingNamespaceSettings, ConvertToBigint, LooseForeignKeyHelpers, RestrictGitlabSchema, Swapping, V2, WraparoundAutovacuum, WraparoundVacuumHelpers

Constant Summary collapse

INTEGER_IDS_YET_TO_INITIALIZED_TO_BIGINT_FILE_PATH =
'db/integer_ids_not_yet_initialized_to_bigint.yml'
TABLE_INT_IDS_YAML_FILE_COMMENT =
<<-MESSAGE.strip_heredoc
  # -- DON'T MANUALLY EDIT --
  # Contains the list of integer IDs which were converted to bigint for new installations in
  # https://gitlab.com/gitlab-org/gitlab/-/issues/438124, but they are still integers for existing instances.
  # On initialize_conversion_of_integer_to_bigint those integer IDs will be removed automatically from here.
MESSAGE
PENDING_INT_IDS_ERROR_MSG =
"'%{table}' table still has %{int_ids} integer IDs. "\
"Please include them in the 'columns' param and in your backfill migration. "\
"For more info: https://gitlab.com/gitlab-org/gitlab/-/issues/482470"
ENFORCE_INITIALIZE_ALL_INT_IDS_FROM_MILESTONE =
'17.4'
DEFAULT_TIMESTAMP_COLUMNS =
%i[created_at updated_at].freeze

Constants included from DynamicModelHelpers

DynamicModelHelpers::BATCH_SIZE

Constants included from Gitlab::Database::Migrations::RedisHelpers

Gitlab::Database::Migrations::RedisHelpers::SCAN_START_CURSOR

Constants included from Gitlab::Database::Migrations::SidekiqHelpers

Gitlab::Database::Migrations::SidekiqHelpers::DEFAULT_MAX_ATTEMPTS, Gitlab::Database::Migrations::SidekiqHelpers::DEFAULT_TIMES_IN_A_ROW

Constants included from Gitlab::Database::Migrations::ConstraintsHelpers

Gitlab::Database::Migrations::ConstraintsHelpers::MAX_IDENTIFIER_NAME_LENGTH

Constants included from Gitlab::Database::Migrations::BatchedBackgroundMigrationHelpers

Gitlab::Database::Migrations::BatchedBackgroundMigrationHelpers::BATCH_CLASS_NAME, Gitlab::Database::Migrations::BatchedBackgroundMigrationHelpers::BATCH_MIN_DELAY, Gitlab::Database::Migrations::BatchedBackgroundMigrationHelpers::BATCH_MIN_VALUE, Gitlab::Database::Migrations::BatchedBackgroundMigrationHelpers::BATCH_SIZE, Gitlab::Database::Migrations::BatchedBackgroundMigrationHelpers::EARLY_FINALIZATION_ERROR, Gitlab::Database::Migrations::BatchedBackgroundMigrationHelpers::ENFORCE_EARLY_FINALIZATION_FROM_VERSION, Gitlab::Database::Migrations::BatchedBackgroundMigrationHelpers::NonExistentMigrationError, Gitlab::Database::Migrations::BatchedBackgroundMigrationHelpers::SUB_BATCH_SIZE

Constants included from Gitlab::Database::Migrations::BackgroundMigrationHelpers

Gitlab::Database::Migrations::BackgroundMigrationHelpers::BATCH_SIZE, Gitlab::Database::Migrations::BackgroundMigrationHelpers::JOB_BUFFER_SIZE

Instance Method Summary collapse

Methods included from PartitionHelpers

#partition?, #table_partitioned?

Methods included from WraparoundVacuumHelpers

#check_if_wraparound_in_progress

Methods included from AsyncConstraints::MigrationHelpers

#prepare_async_check_constraint_validation, #prepare_async_foreign_key_validation, #prepare_partitioned_async_check_constraint_validation, #prepare_partitioned_async_foreign_key_validation, #unprepare_async_check_constraint_validation, #unprepare_async_foreign_key_validation, #unprepare_partitioned_async_check_constraint_validation, #unprepare_partitioned_async_foreign_key_validation

Methods included from AsyncIndexes::MigrationHelpers

#async_index_creation_available?, #prepare_async_index, #prepare_async_index_from_sql, #prepare_async_index_removal, #unprepare_async_index, #unprepare_async_index_by_name

Methods included from RenameTableHelpers

#finalize_table_rename, #rename_table_safely, #undo_finalize_table_rename, #undo_rename_table_safely

Methods included from Gitlab::Database::Migrations::RedisHelpers

#queue_redis_migration_job

Methods included from Gitlab::Database::Migrations::SidekiqHelpers

#migrate_across_instance, #migrate_within_instance, #sidekiq_queue_migrate, #sidekiq_remove_jobs

Methods included from Gitlab::Database::Migrations::ExtensionHelpers

#create_extension, #drop_extension

Methods included from Gitlab::Database::Migrations::ConstraintsHelpers

#add_check_constraint, #add_multi_column_not_null_constraint, #add_not_null_constraint, #add_text_limit, #check_constraint_exists?, check_constraint_exists?, #check_constraint_name, #check_not_null_constraint_exists?, #check_text_limit_exists?, #copy_check_constraints, #drop_constraint, #remove_check_constraint, #remove_multi_column_not_null_constraint, #remove_not_null_constraint, #remove_text_limit, #rename_constraint, #switch_constraint_names, #text_limit_name, #validate_check_constraint, #validate_multi_column_not_null_constraint, #validate_not_null_constraint, #validate_text_limit

Methods included from Gitlab::Database::Migrations::TimeoutHelpers

#disable_statement_timeout

Methods included from Gitlab::Database::Migrations::LockRetriesHelpers

#with_lock_retries

Methods included from Gitlab::Database::Migrations::BatchedBackgroundMigrationHelpers

#delete_batched_background_migration, #ensure_batched_background_migration_is_finished, #finalize_batched_background_migration, #gitlab_schema_from_context, #queue_batched_background_migration

Methods included from Gitlab::Database::Migrations::BackgroundMigrationHelpers

#delete_job_tracking, #delete_queued_jobs, #finalize_background_migration, #migrate_in, #queue_background_migration_jobs_by_range_at_intervals, #requeue_background_migration_jobs_by_range_at_intervals

Methods included from Gitlab::Database::Migrations::ReestablishedConnectionStack

#with_restored_connection_stack

Instance Method Details

#add_concurrent_foreign_key(source, target, column:, **options) ⇒ Object

Adds a foreign key with only minimal locking on the tables involved.

This method only requires minimal locking

source - The source table containing the foreign key. target - The target table the key points to. column - The name of the column to create the foreign key on. target_column - The name of the referenced column, defaults to “id”. on_delete - The action to perform when associated data is removed,

defaults to "CASCADE".

on_update - The action to perform when associated data is updated,

defaults to nil. This is useful for multi column FKs if
it's desirable to update one of the columns.

name - The name of the foreign key. validate - Flag that controls whether the new foreign key will be validated after creation.

If the flag is not set, the constraint will only be enforced for new data.

reverse_lock_order - Flag that controls whether we should attempt to acquire locks in the reverse

order of the ALTER TABLE. This can be useful in situations where the foreign
key creation could deadlock with another process.


256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
# File 'lib/gitlab/database/migration_helpers.rb', line 256

def add_concurrent_foreign_key(source, target, column:, **options)
  options.reverse_merge!({
    on_delete: :cascade,
    on_update: nil,
    target_column: :id,
    validate: true,
    reverse_lock_order: false,
    allow_partitioned: false,
    column: column
  })

  # Transactions would result in ALTER TABLE locks being held for the
  # duration of the transaction, defeating the purpose of this method.
  if transaction_open?
    raise 'add_concurrent_foreign_key can not be run inside a transaction'
  end

  if !options.delete(:allow_partitioned) && table_partitioned?(source)
    raise ArgumentError, 'add_concurrent_foreign_key can not be used on a partitioned ' \
      'table. Please use add_concurrent_partitioned_foreign_key on the partitioned table ' \
      'as we need to create foreign keys on each partition and a FK on the parent table'
  end

  options[:name] ||= concurrent_foreign_key_name(source, column)
  options[:primary_key] = options[:target_column]
  check_options = options.slice(:column, :on_delete, :on_update, :name, :primary_key)

  if foreign_key_exists?(source, target, **check_options)
    warning_message = "Foreign key not created because it exists already " \
      "(this may be due to an aborted migration or similar): " \
      "source: #{source}, target: #{target}, column: #{options[:column]}, "\
      "name: #{options[:name]}, on_update: #{options[:on_update]}, "\
      "on_delete: #{options[:on_delete]}"

    Gitlab::AppLogger.warn warning_message
  else
    execute_add_concurrent_foreign_key(source, target, options)
  end

  # Validate the existing constraint. This can potentially take a very
  # long time to complete, but fortunately does not lock the source table
  # while running.
  # Disable this check by passing `validate: false` to the method call
  # The check will be enforced for new data (inserts) coming in,
  # but validating existing data is delayed.
  #
  # Note this is a no-op in case the constraint is VALID already

  if options[:validate]
    begin
      disable_statement_timeout do
        execute("ALTER TABLE #{source} VALIDATE CONSTRAINT #{options[:name]};")
      end
    rescue PG::ForeignKeyViolation => e
      with_lock_retries do
        execute("ALTER TABLE #{source} DROP CONSTRAINT #{options[:name]};")
      end
      raise "Migration failed intentionally due to ForeignKeyViolation: #{e.message}"
    end
  end
end

#add_concurrent_index(table_name, column_name, options = {}) ⇒ Object

Creates a new index, concurrently

Example:

add_concurrent_index :users, :some_column

See Rails’ ‘add_index` for more info on the available arguments.



107
108
109
110
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
# File 'lib/gitlab/database/migration_helpers.rb', line 107

def add_concurrent_index(table_name, column_name, options = {})
  if transaction_open?
    raise 'add_concurrent_index can not be run inside a transaction, ' \
      'you can disable transactions by calling disable_ddl_transaction! ' \
      'in the body of your migration class'
  end

  if !options.delete(:allow_partition) && partition?(table_name)
    raise ArgumentError, 'add_concurrent_index can not be used on a partitioned '  \
      'table. Please use add_concurrent_partitioned_index on the partitioned table ' \
      'as we need to create indexes on each partition and an index on the parent table'
  end

  options = options.merge({ algorithm: :concurrently })

  if index_exists?(table_name, column_name, **options)
    name = options[:name] || index_name(table_name, column_name)
    _, schema = table_name.to_s.split('.').reverse

    if index_invalid?(name, schema: schema)
      say "Index being recreated because the existing version was INVALID: table_name: #{table_name}, column_name: #{column_name}"

      remove_concurrent_index_by_name(table_name, name)
    else
      say "Index not created because it already exists (this may be due to an aborted migration or similar): table_name: #{table_name}, column_name: #{column_name}"

      return
    end
  end

  disable_statement_timeout do
    add_index(table_name, column_name, **options)
  end

  # We created this index. Now let's remove the queuing entry for async creation in case it's still there.
  unprepare_async_index(table_name, column_name, **options)
end

#add_primary_key_using_index(table_name, pk_name, index_to_use) ⇒ Object



1144
1145
1146
1147
1148
# File 'lib/gitlab/database/migration_helpers.rb', line 1144

def add_primary_key_using_index(table_name, pk_name, index_to_use)
  execute <<~SQL
    ALTER TABLE #{quote_table_name(table_name)} ADD CONSTRAINT #{quote_table_name(pk_name)} PRIMARY KEY USING INDEX #{quote_table_name(index_to_use)}
  SQL
end

#add_sequence(table_name, column_name, sequence_name, start_value) ⇒ Object



1165
1166
1167
1168
1169
1170
# File 'lib/gitlab/database/migration_helpers.rb', line 1165

def add_sequence(table_name, column_name, sequence_name, start_value)
  execute <<~SQL
    CREATE SEQUENCE #{quote_table_name(sequence_name)} START #{start_value};
    ALTER TABLE #{quote_table_name(table_name)} ALTER COLUMN #{quote_column_name(column_name)} SET DEFAULT nextval(#{quote(sequence_name)})
  SQL
end

#add_timestamps_with_timezone(table_name, options = {}) ⇒ Object

Adds ‘created_at` and `updated_at` columns with timezone information.

This method is an improved version of Rails’ built-in method ‘add_timestamps`.

By default, adds ‘created_at` and `updated_at` columns, but these can be specified as:

add_timestamps_with_timezone(:my_table, columns: [:created_at, :deleted_at])

This allows you to create just the timestamps you need, saving space.

Available options are:

:default - The default value for the column.
:null - When set to `true` the column will allow NULL values.
      The default is to not allow NULL values.
:columns - the column names to create. Must end with `_at`.
           Default value: `DEFAULT_TIMESTAMP_COLUMNS`

All options are optional.



69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
# File 'lib/gitlab/database/migration_helpers.rb', line 69

def add_timestamps_with_timezone(table_name, options = {})
  columns = options.fetch(:columns, DEFAULT_TIMESTAMP_COLUMNS)

  columns.each do |column_name|
    validate_timestamp_column_name!(column_name)

    add_column(
      table_name,
      column_name,
      :datetime_with_timezone,
      default: options[:default],
      null: options[:null] || false
    )
  end
end

#backfill_conversion_of_integer_to_bigint(table, columns, primary_key: :id, batch_size: 20_000, sub_batch_size: 1000, pause_ms: 100, interval: 2.minutes) ⇒ Object

Backfills the new columns used in an integer-to-bigint conversion using background migrations.

  • This helper should be called from a post-deployment migration.

  • In order for this helper to work properly, the new columns must be first initialized with the ‘initialize_conversion_of_integer_to_bigint` helper.

  • It tracks the scheduled background jobs through Gitlab::Database::BackgroundMigration::BatchedMigration, which allows a more thorough check that all jobs succeeded in the cleanup migration and is way faster for very large tables.

    Note: this helper is intended to be used in a post-deployment migration, to ensure any new code is deployed (including background job changes) before we begin processing the background migration.

    This helper is part 2 of a multi-step migration process:

    1. initialize_conversion_of_integer_to_bigint to create the new columns and database trigger

    2. backfill_conversion_of_integer_to_bigint to copy historic data using background migrations

    3. remaining steps TBD, see #288005

table - The name of the database table containing the column columns - The name, or an array of names, of the column(s) we want to convert to bigint. primary_key - The name of the primary key column (most often :id) batch_size - The number of rows to schedule in a single background migration sub_batch_size - The smaller batches that will be used by each scheduled job

to update the table. Useful to keep each update at ~100ms while executing
more updates per interval (2.minutes)
Note that each execution of a sub-batch adds a constant 100ms sleep
 time in between the updates, which must be taken into account
 while calculating the batch, sub_batch and interval values.

interval - The time interval between every background migration

example: Assume that we have figured out that updating 200 records of the events

table takes ~100ms on average.

We can set the sub_batch_size to 200, leave the interval to the default

and set the batch_size to 50_000 which will require
~50s = (50000 / 200) * (0.1 + 0.1) to complete and leaves breathing space
between the scheduled jobs


884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
# File 'lib/gitlab/database/migration_helpers.rb', line 884

def backfill_conversion_of_integer_to_bigint(
  table,
  columns,
  primary_key: :id,
  batch_size: 20_000,
  sub_batch_size: 1000,
  pause_ms: 100,
  interval: 2.minutes
)

  unless table_exists?(table)
    raise "Table #{table} does not exist"
  end

  unless column_exists?(table, primary_key)
    raise "Column #{primary_key} does not exist on #{table}"
  end

  conversions = Array.wrap(columns).to_h do |column|
    raise ArgumentError, "Column #{column} does not exist on #{table}" unless column_exists?(table, column)

    temporary_name = convert_to_bigint_column(column)
    raise ArgumentError, "Column #{temporary_name} does not exist on #{table}" unless column_exists?(table, temporary_name)

    [column, temporary_name]
  end

  queue_batched_background_migration(
    'CopyColumnUsingBackgroundMigrationJob',
    table,
    primary_key,
    conversions.keys,
    conversions.values,
    job_interval: interval,
    pause_ms: pause_ms,
    batch_size: batch_size,
    sub_batch_size: sub_batch_size)
end

#backfill_iids(table) ⇒ Object

Note this should only be used with very small tables



1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
# File 'lib/gitlab/database/migration_helpers.rb', line 1131

def backfill_iids(table)
  sql = <<-END
    UPDATE #{table}
    SET iid = #{table}_with_calculated_iid.iid_num
    FROM (
      SELECT id, ROW_NUMBER() OVER (PARTITION BY project_id ORDER BY id ASC) AS iid_num FROM #{table}
    ) AS #{table}_with_calculated_iid
    WHERE #{table}.id = #{table}_with_calculated_iid.id
  END

  execute(sql)
end

#change_column_type_concurrently(table, column, new_type, type_cast_function: nil, batch_column_name: :id) ⇒ Object

Changes the type of a column concurrently.

table - The table containing the column. column - The name of the column to change. new_type - The new column type.



594
595
596
597
598
# File 'lib/gitlab/database/migration_helpers.rb', line 594

def change_column_type_concurrently(table, column, new_type, type_cast_function: nil, batch_column_name: :id)
  temp_column = "#{column}_for_type_change"

  rename_column_concurrently(table, column, temp_column, type: new_type, type_cast_function: type_cast_function, batch_column_name: batch_column_name)
end

#check_trigger_permissions!(table) ⇒ Object



1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
# File 'lib/gitlab/database/migration_helpers.rb', line 1066

def check_trigger_permissions!(table)
  unless Grant.create_and_execute_trigger?(table)
    dbname = ApplicationRecord.database.database_name
    user = ApplicationRecord.database.username

    raise <<-EOF
Your database user is not allowed to create, drop, or execute triggers on the
table #{table}.

If you are using PostgreSQL you can solve this by logging in to the GitLab
database (#{dbname}) using a super user and running:

    ALTER #{user} WITH SUPERUSER

This query will grant the user super user permissions, ensuring you don't run
into similar problems in the future (e.g. when new tables are created).
    EOF
  end
end

#cleanup_concurrent_column_rename(table, old, new) ⇒ Object

Cleans up a concurrent column name.

This method takes care of removing previously installed triggers as well as removing the old column.

table - The name of the database table. old - The name of the old column. new - The name of the new column.



696
697
698
699
700
701
702
703
704
# File 'lib/gitlab/database/migration_helpers.rb', line 696

def cleanup_concurrent_column_rename(table, old, new)
  trigger_name = rename_trigger_name(table, old, new)

  check_trigger_permissions!(table)

  remove_rename_triggers(table, trigger_name)

  remove_column(table, old)
end

#cleanup_concurrent_column_type_change(table, column, temp_column: nil) ⇒ Object

Performs cleanup of a concurrent type change.

table - The table containing the column. column - The name of the column to change. new_type - The new column type.



615
616
617
618
619
620
621
622
623
624
# File 'lib/gitlab/database/migration_helpers.rb', line 615

def cleanup_concurrent_column_type_change(table, column, temp_column: nil)
  temp_column ||= "#{column}_for_type_change"

  transaction do
    # This has to be performed in a transaction as otherwise we might have
    # inconsistent data.
    cleanup_concurrent_column_rename(table, column, temp_column)
    rename_column(table, temp_column, column)
  end
end

#column_for(table, name) ⇒ Object

Returns the column for the given table and column name.



1024
1025
1026
1027
1028
1029
1030
1031
# File 'lib/gitlab/database/migration_helpers.rb', line 1024

def column_for(table, name)
  name = name.to_s

  column = columns(table).find { |column| column.name == name }
  raise(missing_schema_object_message(table, "column", name)) if column.nil?

  column
end

#concurrent_foreign_key_name(table, column, prefix: 'fk_') ⇒ Object

Returns the name for a concurrent foreign key.

PostgreSQL constraint names have a limit of 63 bytes. The logic used here is based on Rails’ foreign_key_name() method, which unfortunately is private so we can’t rely on it directly.

prefix:

  • The default prefix is ‘fk_` for backward compatibility with the existing

concurrent foreign key helpers.

  • For standard rails foreign keys the prefix is ‘fk_rails_`



373
374
375
376
377
378
# File 'lib/gitlab/database/migration_helpers.rb', line 373

def concurrent_foreign_key_name(table, column, prefix: 'fk_')
  identifier = "#{table}_#{multiple_columns(column, separator: '_')}_fk"
  hashed_identifier = Digest::SHA256.hexdigest(identifier).first(10)

  "#{prefix}#{hashed_identifier}"
end

#convert_to_bigint_column(column) ⇒ Object



740
741
742
# File 'lib/gitlab/database/migration_helpers.rb', line 740

def convert_to_bigint_column(column)
  "#{column}_convert_to_bigint"
end

#convert_to_type_column(column, from_type, to_type) ⇒ Object



736
737
738
# File 'lib/gitlab/database/migration_helpers.rb', line 736

def convert_to_type_column(column, from_type, to_type)
  "#{column}_convert_#{from_type}_to_#{to_type}"
end

#copy_foreign_keys(table, old, new) ⇒ Object

Copies all foreign keys for the old column to the new column.

table - The table containing the columns and indexes. old - The old column. new - The new column.



1014
1015
1016
1017
1018
1019
1020
1021
# File 'lib/gitlab/database/migration_helpers.rb', line 1014

def copy_foreign_keys(table, old, new)
  foreign_keys_for(table, old).each do |fk|
    add_concurrent_foreign_key(fk.from_table,
      fk.to_table,
      column: new,
      on_delete: fk.on_delete)
  end
end

#copy_indexes(table, old, new) ⇒ Object

Copies all indexes for the old column to a new column.

table - The table containing the columns and indexes. old - The old column. new - The new column.



962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
# File 'lib/gitlab/database/migration_helpers.rb', line 962

def copy_indexes(table, old, new)
  old = old.to_s
  new = new.to_s

  indexes_for(table, old).each do |index|
    new_columns = index.columns.map do |column|
      column == old ? new : column
    end

    # This is necessary as we can't properly rename indexes such as
    # "ci_taggings_idx".
    unless index.name.include?(old)
      raise "The index #{index.name} can not be copied as it does not "\
        "mention the old column. You have to rename this index manually first."
    end

    name = index.name.gsub(old, new)

    if name.length > 63
      digest = Digest::SHA256.hexdigest(name).first(10)
      name = "idx_copy_#{digest}"
    end

    options = {
      unique: index.unique,
      name: name,
      length: index.lengths,
      order: index.orders
    }

    options[:using] = index.using if index.using
    options[:where] = index.where if index.where

    unless index.opclasses.blank?
      opclasses = index.opclasses.dup

      # Copy the operator classes for the old column (if any) to the new
      # column.
      opclasses[new] = opclasses.delete(old) if opclasses[old]

      options[:opclass] = opclasses
    end

    add_concurrent_index(table, new_columns, options)
  end
end

#create_or_update_plan_limit(limit_name, plan_name, limit_value) ⇒ Object



1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
# File 'lib/gitlab/database/migration_helpers.rb', line 1118

def create_or_update_plan_limit(limit_name, plan_name, limit_value)
  limit_name_quoted = quote_column_name(limit_name)
  plan_name_quoted = quote(plan_name)
  limit_value_quoted = quote(limit_value)

  execute <<~SQL
    INSERT INTO plan_limits (plan_id, #{limit_name_quoted})
    SELECT id, #{limit_value_quoted} FROM plans WHERE name = #{plan_name_quoted} LIMIT 1
    ON CONFLICT (plan_id) DO UPDATE SET #{limit_name_quoted} = EXCLUDED.#{limit_name_quoted};
  SQL
end

#create_temporary_columns_and_triggers(table, mappings, primary_key: :id, old_bigint_column_naming: false) ⇒ Object

rubocop:disable Metrics/CyclomaticComplexity,Metrics/PerceivedComplexity

Raises:

  • (ArgumentError)


1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
# File 'lib/gitlab/database/migration_helpers.rb', line 1173

def create_temporary_columns_and_triggers(table, mappings, primary_key: :id, old_bigint_column_naming: false)
  raise ArgumentError, "No mappings for column conversion provided" if mappings.blank?

  unless mappings.values.all? { |values| mapping_has_required_columns?(values) }
    raise ArgumentError, "Some mappings don't have required keys provided"
  end

  neutral_values_for_type = {
    int: 0,
    bigint: 0,
    uuid: '00000000-0000-0000-0000-000000000000'
  }

  unless table_exists?(table)
    raise "Table #{table} does not exist"
  end

  unless column_exists?(table, primary_key)
    raise "Column #{primary_key} does not exist on #{table}"
  end

  columns = mappings.keys
  columns.each do |column|
    next if column_exists?(table, column)

    raise ArgumentError, "Column #{column} does not exist on #{table}"
  end

  check_trigger_permissions!(table)

  if old_bigint_column_naming
    mappings.each do |column, params|
      params.merge!(
        temporary_column_name: convert_to_bigint_column(column)
      )
    end
  else
    mappings.each do |column, params|
      params.merge!(
        temporary_column_name: convert_to_type_column(column, params[:from_type], params[:to_type])
      )
    end
  end

  with_lock_retries do
    mappings.each do |(column_name, params)|
      column = column_for(table, column_name)
      temporary_name = params[:temporary_column_name]
      data_type = params[:to_type]
      default_value = params[:default_value]

      if (column.name.to_s == primary_key.to_s) || !column.null
        # If the column to be converted is either a PK or is defined as NOT NULL,
        # set it to `NOT NULL DEFAULT 0` and we'll copy paste the correct values bellow
        # That way, we skip the expensive validation step required to add
        #  a NOT NULL constraint at the end of the process
        add_column(
          table,
          temporary_name,
          data_type,
          default: column.default || default_value || neutral_values_for_type.fetch(data_type),
          null: false
        )
      else
        add_column(
          table,
          temporary_name,
          data_type,
          default: column.default
        )
      end
    end

    old_column_names = mappings.keys
    temporary_column_names = mappings.values.map { |v| v[:temporary_column_name] }
    install_rename_triggers(table, old_column_names, temporary_column_names)
  end
end

#define_batchable_model(table_name, connection: self.connection, primary_key: nil) ⇒ Object



39
40
41
# File 'lib/gitlab/database/migration_helpers.rb', line 39

def define_batchable_model(table_name, connection: self.connection, primary_key: nil)
  super(table_name, connection: connection, primary_key: primary_key)
end

#drop_sequence(table_name, column_name, sequence_name) ⇒ Object



1158
1159
1160
1161
1162
1163
# File 'lib/gitlab/database/migration_helpers.rb', line 1158

def drop_sequence(table_name, column_name, sequence_name)
  execute <<~SQL
    ALTER TABLE #{quote_table_name(table_name)} ALTER COLUMN #{quote_column_name(column_name)} DROP DEFAULT;
    DROP SEQUENCE IF EXISTS #{quote_table_name(sequence_name)}
  SQL
end

#each_batch(table_name, connection: self.connection, **kwargs) ⇒ Object



43
44
45
# File 'lib/gitlab/database/migration_helpers.rb', line 43

def each_batch(table_name, connection: self.connection, **kwargs)
  super(table_name, connection: connection, **kwargs)
end

#each_batch_range(table_name, connection: self.connection, **kwargs) ⇒ Object



47
48
49
# File 'lib/gitlab/database/migration_helpers.rb', line 47

def each_batch_range(table_name, connection: self.connection, **kwargs)
  super(table_name, connection: connection, **kwargs)
end

#false_valueObject



384
385
386
# File 'lib/gitlab/database/migration_helpers.rb', line 384

def false_value
  Database.false_value
end

#foreign_key_exists?(source, target = nil, **options) ⇒ Boolean

Returns:

  • (Boolean)


330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
# File 'lib/gitlab/database/migration_helpers.rb', line 330

def foreign_key_exists?(source, target = nil, **options)
  # This if block is necessary because foreign_key_exists? is called in down migrations that may execute before
  # the postgres_foreign_keys view had necessary columns added.
  # In that case, we revert to the previous behavior of this method.
  # The behavior in the if block has a bug: it always returns false if the fk being checked has multiple columns.
  # This can be removed after init_schema.rb passes 20221122210711_add_columns_to_postgres_foreign_keys.rb
  # Tracking issue: https://gitlab.com/gitlab-org/gitlab/-/issues/386796
  unless connection.column_exists?('postgres_foreign_keys', 'constrained_table_name')
    return foreign_keys(source).any? do |foreign_key|
      tables_match?(target.to_s, foreign_key.to_table.to_s) &&
          options_match?(foreign_key.options, options)
    end
  end

  # Since we may be migrating in one go from a previous version without
  # `constrained_table_name` then we may see that this column exists
  # (as above) but the schema cache is still outdated for the model.
  unless Gitlab::Database::PostgresForeignKey.column_names.include?('constrained_table_name')
    Gitlab::Database::PostgresForeignKey.reset_column_information
  end

  fks = Gitlab::Database::PostgresForeignKey.by_constrained_table_name_or_identifier(source)

  fks = fks.by_referenced_table_name(target) if target
  fks = fks.by_name(options[:name]) if options[:name]
  fks = fks.by_constrained_columns(options[:column]) if options[:column]
  fks = fks.by_referenced_columns(options[:primary_key]) if options[:primary_key]
  fks = fks.by_on_delete_action(options[:on_delete]) if options[:on_delete]

  fks.exists?
end

#foreign_keys_for(table, column) ⇒ Object

Returns an Array containing the foreign keys for the given column.



951
952
953
954
955
# File 'lib/gitlab/database/migration_helpers.rb', line 951

def foreign_keys_for(table, column)
  column = column.to_s

  foreign_keys(table).select { |fk| fk.column == column }
end

#index_exists_by_name?(table, index) ⇒ Boolean

Fetches indexes on a column by name for postgres.

This will include indexes using an expression on the column, for example: ‘CREATE INDEX CONCURRENTLY index_name ON table (LOWER(column));`

We can remove this when upgrading to Rails 5 with an updated ‘index_exists?`:

Or this can be removed when we no longer support postgres < 9.5, so we can use ‘CREATE INDEX IF NOT EXISTS`.

Returns:

  • (Boolean)


1096
1097
1098
1099
1100
1101
1102
1103
1104
# File 'lib/gitlab/database/migration_helpers.rb', line 1096

def index_exists_by_name?(table, index)
  # We can't fall back to the normal `index_exists?` method because that
  # does not find indexes without passing a column name.
  if indexes(table).map(&:name).include?(index.to_s)
    true
  else
    postgres_exists_by_name?(table, index)
  end
end

#index_invalid?(index_name, schema: nil) ⇒ Boolean

Returns:

  • (Boolean)


145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
# File 'lib/gitlab/database/migration_helpers.rb', line 145

def index_invalid?(index_name, schema: nil)
  index_name = connection.quote(index_name)
  schema = connection.quote(schema) if schema
  schema ||= 'current_schema()'

  connection.select_value(<<~SQL)
    select not i.indisvalid
    from pg_class c
    inner join pg_index i
      on c.oid = i.indexrelid
    inner join pg_namespace n
      on n.oid = c.relnamespace
    where n.nspname = #{schema}
      and c.relname = #{index_name}
  SQL
end

#indexes_for(table, column) ⇒ Object

Returns an Array containing the indexes for the given column



944
945
946
947
948
# File 'lib/gitlab/database/migration_helpers.rb', line 944

def indexes_for(table, column)
  column = column.to_s

  indexes(table).select { |index| index.columns.include?(column) }
end

#initialize_conversion_of_integer_to_bigint(table, columns, primary_key: :id) ⇒ Object

Initializes the conversion of a set of integer columns to bigint

It can be used for converting both a Primary Key and any Foreign Keys that may reference it or any other integer column that we may want to upgrade (e.g. columns that store IDs, but are not set as FKs).

  • For primary keys and Foreign Keys (or other columns) defined as NOT NULL,

    the new bigint column is added with a hardcoded NOT NULL DEFAULT 0
    which allows us to skip a very costly verification step once we
    are ready to switch it.
    

    This is crucial for Primary Key conversions, because setting a column

    as the PK converts even check constraints to NOT NULL constraints
    and forces an inline re-verification of the whole table.
    
  • It sets up a trigger to keep the two columns in sync.

    Note: this helper is intended to be used in a regular (pre-deployment) migration.

    This helper is part 1 of a multi-step migration process:

    1. initialize_conversion_of_integer_to_bigint to create the new columns and database trigger

    2. backfill_conversion_of_integer_to_bigint to copy historic data using background migrations

    3. remaining steps TBD, see #288005

table - The name of the database table containing the column columns - The name, or array of names, of the column(s) that we want to convert to bigint. primary_key - The name of the primary key column (most often :id)



769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
# File 'lib/gitlab/database/migration_helpers.rb', line 769

def initialize_conversion_of_integer_to_bigint(table, columns, primary_key: :id)
  integer_ids = table_integer_ids
  columns = Array(columns)
  pending_int_ids = Array(integer_ids[table.to_s]) - columns.map(&:to_s)

  # This check can be removed once we convert all integer IDs to bigint
  # in https://gitlab.com/gitlab-org/gitlab/-/issues/465805
  if can_enforce_initializing_all_int_ids? && pending_int_ids.present?
    raise format(PENDING_INT_IDS_ERROR_MSG, table: table, int_ids: pending_int_ids)
  end

  mappings = columns.map do |c|
    {
      c => {
        from_type: :int,
        to_type: :bigint,
        default_value: 0
      }
    }
  end.reduce(&:merge)

  create_temporary_columns_and_triggers(
    table,
    mappings,
    primary_key: primary_key,
    old_bigint_column_naming: true
  )

  deleted = integer_ids.delete(table.to_s)
  return unless can_enforce_initializing_all_int_ids? && deleted.present?

  update_table_integer_ids_file(integer_ids)
end

#install_rename_triggers(table, old, new, trigger_name: nil) ⇒ Object

Installs triggers in a table that keep a new column in sync with an old one.

table - The name of the table to install the trigger in. old_column - The name of the old column. new_column - The name of the new column. trigger_name - The name of the trigger to use (optional).



553
554
555
# File 'lib/gitlab/database/migration_helpers.rb', line 553

def install_rename_triggers(table, old, new, trigger_name: nil)
  Gitlab::Database::UnidirectionalCopyTrigger.on_table(table, connection: connection).create(old, new, trigger_name: trigger_name)
end

#install_sharding_key_assignment_trigger(**args) ⇒ Object

Installs a trigger in a table that assigns a sharding key from an associated table.

table: The table to install the trigger in. sharding_key: The column to be assigned on ‘table`. parent_table: The associated table with the sharding key to be copied. parent_sharding_key: The sharding key on the parent table that will be copied to `sharding_key` on `table`. foreign_key: The column used to fetch the relevant record from `parent_table`.



574
575
576
# File 'lib/gitlab/database/migration_helpers.rb', line 574

def install_sharding_key_assignment_trigger(**args)
  Gitlab::Database::Triggers::AssignDesiredShardingKey.new(**args.merge(connection: connection)).create
end

#lock_tables(*tables, mode: :access_exclusive, only: nil, nowait: nil) ⇒ Object



1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
# File 'lib/gitlab/database/migration_helpers.rb', line 1266

def lock_tables(*tables, mode: :access_exclusive, only: nil, nowait: nil)
  only_param = only && 'ONLY'
  nowait_param = nowait && 'NOWAIT'
  tables_param = tables.map { |t| quote_table_name(t) }.join(', ')
  mode_param = mode.to_s.upcase.tr('_', ' ')

  execute(<<~SQL.squish)
    LOCK TABLE #{only_param} #{tables_param} IN #{mode_param} MODE #{nowait_param}
  SQL
end

#postgres_exists_by_name?(table, name) ⇒ Boolean

Returns:

  • (Boolean)


1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
# File 'lib/gitlab/database/migration_helpers.rb', line 1106

def postgres_exists_by_name?(table, name)
  index_sql = <<~SQL
    SELECT COUNT(*)
    FROM pg_catalog.pg_indexes
    WHERE schemaname = #{connection.quote(current_schema)}
      AND tablename = #{connection.quote(table)}
      AND indexname = #{connection.quote(name)}
  SQL

  connection.select_value(index_sql).to_i > 0
end

#remove_column_default(table_name, column_name) ⇒ Object

While it is safe to call ‘change_column_default` on a column without default it would still require access exclusive lock on the table and for tables with high autovacuum(wraparound prevention) it will fail if their executions overlap.



1258
1259
1260
1261
1262
1263
1264
# File 'lib/gitlab/database/migration_helpers.rb', line 1258

def remove_column_default(table_name, column_name)
  column = connection.columns(table_name).find { |col| col.name == column_name.to_s }

  if column.default || column.default_function
    change_column_default(table_name, column_name, to: nil)
  end
end

#remove_concurrent_index(table_name, column_name, options = {}) ⇒ Object

Removes an existed index, concurrently

Example:

remove_concurrent_index :users, :some_column

See Rails’ ‘remove_index` for more info on the available arguments.



169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
# File 'lib/gitlab/database/migration_helpers.rb', line 169

def remove_concurrent_index(table_name, column_name, options = {})
  if transaction_open?
    raise 'remove_concurrent_index can not be run inside a transaction, ' \
      'you can disable transactions by calling disable_ddl_transaction! ' \
      'in the body of your migration class'
  end

  if partition?(table_name)
    raise ArgumentError, 'remove_concurrent_index can not be used on a partitioned '  \
      'table. Please use remove_concurrent_partitioned_index_by_name on the partitioned table ' \
      'as we need to remove the index on the parent table'
  end

  options = options.merge({ algorithm: :concurrently })

  unless index_exists?(table_name, column_name, **options)
    Gitlab::AppLogger.warn "Index not removed because it does not exist (this may be due to an aborted migration or similar): table_name: #{table_name}, column_name: #{column_name}"
    return
  end

  disable_statement_timeout do
    remove_index(table_name, **options.merge({ column: column_name }))
  end

  # We removed this index. Now let's make sure it's not queued for async creation.
  unprepare_async_index(table_name, column_name, **options)
end

#remove_concurrent_index_by_name(table_name, index_name, options = {}) ⇒ Object

Removes an existing index, concurrently

Example:

remove_concurrent_index :users, "index_X_by_Y"

See Rails’ ‘remove_index` for more info on the available arguments.



204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
# File 'lib/gitlab/database/migration_helpers.rb', line 204

def remove_concurrent_index_by_name(table_name, index_name, options = {})
  if transaction_open?
    raise 'remove_concurrent_index_by_name can not be run inside a transaction, ' \
      'you can disable transactions by calling disable_ddl_transaction! ' \
      'in the body of your migration class'
  end

  if partition?(table_name)
    raise ArgumentError, 'remove_concurrent_index_by_name can not be used on a partitioned '  \
      'table. Please use remove_concurrent_partitioned_index_by_name on the partitioned table ' \
      'as we need to remove the index on the parent table'
  end

  index_name = index_name[:name] if index_name.is_a?(Hash)

  raise 'remove_concurrent_index_by_name must get an index name as the second argument' if index_name.blank?

  options = options.merge({ algorithm: :concurrently })

  unless index_exists_by_name?(table_name, index_name)
    Gitlab::AppLogger.warn "Index not removed because it does not exist (this may be due to an aborted migration or similar): table_name: #{table_name}, index_name: #{index_name}"
    return
  end

  disable_statement_timeout do
    remove_index(table_name, **options.merge({ name: index_name }))
  end

  # We removed this index. Now let's make sure it's not queued for async creation.
  unprepare_async_index_by_name(table_name, index_name, **options)
end

#remove_foreign_key_if_exists(source, target = nil, **kwargs) ⇒ Object



1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
# File 'lib/gitlab/database/migration_helpers.rb', line 1046

def remove_foreign_key_if_exists(source, target = nil, **kwargs)
  reverse_lock_order = kwargs.delete(:reverse_lock_order)
  return unless foreign_key_exists?(source, target, **kwargs)

  if target && reverse_lock_order && transaction_open?
    execute("LOCK TABLE #{target}, #{source} IN ACCESS EXCLUSIVE MODE")
  end

  if target
    remove_foreign_key(source, target, **kwargs)
  else
    remove_foreign_key(source, **kwargs)
  end
end

#remove_foreign_key_without_error(*args, **kwargs) ⇒ Object



1061
1062
1063
1064
# File 'lib/gitlab/database/migration_helpers.rb', line 1061

def remove_foreign_key_without_error(*args, **kwargs)
  remove_foreign_key(*args, **kwargs)
rescue ArgumentError
end

#remove_rename_triggers(table, trigger) ⇒ Object

Removes the triggers used for renaming a column concurrently.



558
559
560
# File 'lib/gitlab/database/migration_helpers.rb', line 558

def remove_rename_triggers(table, trigger)
  Gitlab::Database::UnidirectionalCopyTrigger.on_table(table, connection: connection).drop(trigger)
end

#remove_sharding_key_assignment_trigger(**args) ⇒ Object

Removes trigger used for assigning sharding keys.

table: The table to install the trigger in. sharding_key: The column to be assigned on ‘table`. parent_table: The associated table with the sharding key to be copied. parent_sharding_key: The sharding key on the parent table that will be copied to `sharding_key` on `table`. foreign_key: The column used to fetch the relevant record from `parent_table`.



585
586
587
# File 'lib/gitlab/database/migration_helpers.rb', line 585

def remove_sharding_key_assignment_trigger(**args)
  Gitlab::Database::Triggers::AssignDesiredShardingKey.new(**args.merge(connection: connection)).drop
end

#remove_timestamps(table_name, options = {}) ⇒ Object

To be used in the ‘#down` method of migrations that use `#add_timestamps_with_timezone`.

Available options are:

:columns - the column names to remove. Must be one
           Default value: `DEFAULT_TIMESTAMP_COLUMNS`

All options are optional.



93
94
95
96
97
98
# File 'lib/gitlab/database/migration_helpers.rb', line 93

def remove_timestamps(table_name, options = {})
  columns = options.fetch(:columns, DEFAULT_TIMESTAMP_COLUMNS)
  columns.each do |column_name|
    remove_column(table_name, column_name)
  end
end

#rename_column_concurrently(table, old, new, type: nil, type_cast_function: nil, batch_column_name: :id) ⇒ Object

Renames a column without requiring downtime.

Concurrent renames work by using database triggers to ensure both the old and new column are in sync. However, this method will not remove the triggers or the old column automatically; this needs to be done manually in a post-deployment migration. This can be done using the method ‘cleanup_concurrent_column_rename`.

table - The name of the database table containing the column. old - The old column name. new - The new column name. type - The type of the new column. If no type is given the old column’s

type is used.

batch_column_name - option is for tables without primary key, in this

case another unique integer column can be used. Example: :user_id


512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
# File 'lib/gitlab/database/migration_helpers.rb', line 512

def rename_column_concurrently(table, old, new, type: nil, type_cast_function: nil, batch_column_name: :id)
  unless column_exists?(table, batch_column_name)
    raise "Column #{batch_column_name} does not exist on #{table}"
  end

  if transaction_open?
    raise 'rename_column_concurrently can not be run inside a transaction'
  end

  check_trigger_permissions!(table)

  create_column_from(table, old, new, type: type, batch_column_name: batch_column_name, type_cast_function: type_cast_function)

  install_rename_triggers(table, old, new)
end

#rename_trigger_name(table, old, new) ⇒ Object

Returns the (base) name to use for triggers when renaming columns.



563
564
565
# File 'lib/gitlab/database/migration_helpers.rb', line 563

def rename_trigger_name(table, old, new)
  Gitlab::Database::UnidirectionalCopyTrigger.on_table(table, connection: connection).name(old, new)
end

#replace_sql(column, pattern, replacement) ⇒ Object

This will replace the first occurrence of a string in a column with the replacement using ‘regexp_replace`



1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
# File 'lib/gitlab/database/migration_helpers.rb', line 1035

def replace_sql(column, pattern, replacement)
  quoted_pattern = Arel::Nodes::Quoted.new(pattern.to_s)
  quoted_replacement = Arel::Nodes::Quoted.new(replacement.to_s)

  replace = Arel::Nodes::NamedFunction.new(
    "regexp_replace", [column, quoted_pattern, quoted_replacement]
  )

  Arel::Nodes::SqlLiteral.new(replace.to_sql)
end

#restore_conversion_of_integer_to_bigint(table, columns, primary_key: :id) ⇒ Object

Reverts ‘cleanup_conversion_of_integer_to_bigint`

table - The name of the database table containing the columns columns - The name, or array of names, of the column(s) that we have converted to bigint. primary_key - The name of the primary key column (most often :id)



829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
# File 'lib/gitlab/database/migration_helpers.rb', line 829

def restore_conversion_of_integer_to_bigint(table, columns, primary_key: :id)
  mappings = Array(columns).map do |c|
    {
      c => {
        from_type: :bigint,
        to_type: :int,
        default_value: 0
      }
    }
  end.reduce(&:merge)

  create_temporary_columns_and_triggers(
    table,
    mappings,
    primary_key: primary_key,
    old_bigint_column_naming: true
  )
end

#revert_backfill_conversion_of_integer_to_bigint(table, columns, primary_key: :id) ⇒ Object

Reverts ‘backfill_conversion_of_integer_to_bigint`

table - The name of the database table containing the column columns - The name, or an array of names, of the column(s) we want to convert to bigint. primary_key - The name of the primary key column (most often :id)



928
929
930
931
932
933
934
935
936
937
938
939
940
941
# File 'lib/gitlab/database/migration_helpers.rb', line 928

def revert_backfill_conversion_of_integer_to_bigint(table, columns, primary_key: :id)
  columns = Array.wrap(columns)

  conditions = ActiveRecord::Base.sanitize_sql(
    [
      'job_class_name = :job_class_name AND table_name = :table_name AND column_name = :column_name AND job_arguments = :job_arguments',
      { job_class_name: 'CopyColumnUsingBackgroundMigrationJob',
        table_name: table,
        column_name: primary_key,
        job_arguments: [columns, columns.map { |column| convert_to_bigint_column(column) }].to_json }
    ])

  execute("DELETE FROM batched_background_migrations WHERE #{conditions}")
end

#revert_initialize_conversion_of_integer_to_bigint(table, columns) ⇒ Object Also known as: cleanup_conversion_of_integer_to_bigint

Reverts ‘initialize_conversion_of_integer_to_bigint`

table - The name of the database table containing the columns columns - The name, or array of names, of the column(s) that we’re converting to bigint.



807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
# File 'lib/gitlab/database/migration_helpers.rb', line 807

def revert_initialize_conversion_of_integer_to_bigint(table, columns)
  columns = Array.wrap(columns)
  temporary_columns = columns.map { |column| convert_to_bigint_column(column) }

  trigger_name = rename_trigger_name(table, columns, temporary_columns)
  remove_rename_triggers(table, trigger_name)

  temporary_columns.each { |column| remove_column(table, column, if_exists: true) }

  return unless can_enforce_initializing_all_int_ids?

  integer_ids = table_integer_ids
  integer_ids[table.to_s] = columns.map(&:to_s)
  update_table_integer_ids_file(integer_ids)
end

#swap_primary_key(table_name, primary_key_name, index_to_use) ⇒ Object Also known as: unswap_primary_key



1150
1151
1152
1153
1154
1155
# File 'lib/gitlab/database/migration_helpers.rb', line 1150

def swap_primary_key(table_name, primary_key_name, index_to_use)
  with_lock_retries(raise_on_exhaustion: true) do
    drop_constraint(table_name, primary_key_name, cascade: true)
    add_primary_key_using_index(table_name, primary_key_name, index_to_use)
  end
end

#table_integer_idsObject



1277
1278
1279
# File 'lib/gitlab/database/migration_helpers.rb', line 1277

def table_integer_ids
  YAML.safe_load_file(File.join(INTEGER_IDS_YET_TO_INITIALIZED_TO_BIGINT_FILE_PATH))
end

#true_valueObject



380
381
382
# File 'lib/gitlab/database/migration_helpers.rb', line 380

def true_value
  Database.true_value
end

#undo_change_column_type_concurrently(table, column) ⇒ Object

Reverses operations performed by change_column_type_concurrently.

table - The table containing the column. column - The name of the column to change.



604
605
606
607
608
# File 'lib/gitlab/database/migration_helpers.rb', line 604

def undo_change_column_type_concurrently(table, column)
  temp_column = "#{column}_for_type_change"

  undo_rename_column_concurrently(table, column, temp_column)
end

#undo_cleanup_concurrent_column_rename(table, old, new, type: nil, batch_column_name: :id) ⇒ Object

Reverses the operations performed by cleanup_concurrent_column_rename.

This method adds back the old_column removed by cleanup_concurrent_column_rename. It also adds back the (old_column > new_column) trigger that is removed by cleanup_concurrent_column_rename.

table - The name of the database table containing the column. old - The old column name. new - The new column name. type - The type of the old column. If no type is given the new column’s

type is used.

batch_column_name - option is for tables without primary key, in this

case another unique integer column can be used. Example: :user_id


720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
# File 'lib/gitlab/database/migration_helpers.rb', line 720

def undo_cleanup_concurrent_column_rename(table, old, new, type: nil, batch_column_name: :id)
  unless column_exists?(table, batch_column_name)
    raise "Column #{batch_column_name} does not exist on #{table}"
  end

  if transaction_open?
    raise 'undo_cleanup_concurrent_column_rename can not be run inside a transaction'
  end

  check_trigger_permissions!(table)

  create_column_from(table, new, old, type: type, batch_column_name: batch_column_name)

  install_rename_triggers(table, old, new)
end

#undo_cleanup_concurrent_column_type_change(table, column, old_type, type_cast_function: nil, batch_column_name: :id, limit: nil, temp_column: nil) ⇒ Object

Reverses operations performed by cleanup_concurrent_column_type_change.

table - The table containing the column. column - The name of the column to change. old_type - The type of the original column used with change_column_type_concurrently. type_cast_function - Required if the conversion back to the original type is not automatic batch_column_name - option for tables without a primary key, in this case

another unique integer column can be used. Example: :user_id


634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
# File 'lib/gitlab/database/migration_helpers.rb', line 634

def undo_cleanup_concurrent_column_type_change(table, column, old_type, type_cast_function: nil, batch_column_name: :id, limit: nil, temp_column: nil)
  Gitlab::Database::QueryAnalyzers::RestrictAllowedSchemas.require_ddl_mode!

  temp_column ||= "#{column}_for_type_change"

  # Using a descriptive name that includes orinal column's name risks
  # taking us above the 63 character limit, so we use a hash
  identifier = "#{table}_#{column}_for_type_change"
  hashed_identifier = Digest::SHA256.hexdigest(identifier).first(10)
  temp_undo_cleanup_column = "tmp_undo_cleanup_column_#{hashed_identifier}"

  unless column_exists?(table, batch_column_name)
    raise "Column #{batch_column_name} does not exist on #{table}"
  end

  if transaction_open?
    raise 'undo_cleanup_concurrent_column_type_change can not be run inside a transaction'
  end

  check_trigger_permissions!(table)

  begin
    create_column_from(
      table,
      column,
      temp_undo_cleanup_column,
      type: old_type,
      batch_column_name: batch_column_name,
      type_cast_function: type_cast_function,
      limit: limit
    )

    transaction do
      # This has to be performed in a transaction as otherwise we might
      # have inconsistent data.
      rename_column(table, column, temp_column)
      rename_column(table, temp_undo_cleanup_column, column)

      install_rename_triggers(table, column, temp_column)
    end
  rescue StandardError
    # create_column_from can not run inside a transaction, which means
    #  that there is a risk that if any of the operations that follow it
    #  fail, we'll be left with an inconsistent schema
    # For those reasons, we make sure that we drop temp_undo_cleanup_column
    #  if an error is caught
    if column_exists?(table, temp_undo_cleanup_column)
      remove_column(table, temp_undo_cleanup_column)
    end

    raise
  end
end

#undo_rename_column_concurrently(table, old, new) ⇒ Object

Reverses operations performed by rename_column_concurrently.

This method takes care of removing previously installed triggers as well as removing the new column.

table - The name of the database table. old - The name of the old column. new - The name of the new column.



536
537
538
539
540
541
542
543
544
# File 'lib/gitlab/database/migration_helpers.rb', line 536

def undo_rename_column_concurrently(table, old, new)
  trigger_name = rename_trigger_name(table, old, new)

  check_trigger_permissions!(table)

  remove_rename_triggers(table, trigger_name)

  remove_column(table, new)
end

#update_column_in_batches(table_name, column, value, batch_size: nil, batch_column_name: :id, disable_lock_writes: false) ⇒ Object

Updates the value of a column in batches.

This method updates the table in batches of 5% of the total row count. A ‘batch_size` option can also be passed to set this to a fixed number. This method will continue updating rows until no rows remain.

When given a block this method will yield two values to the block:

  1. An instance of ‘Arel::Table` for the table that is being updated.

  2. The query to run as an Arel object.

By supplying a block one can add extra conditions to the queries being executed. Note that the same block is used for all queries.

Example:

update_column_in_batches(:projects, :foo, 10) do |table, query|
  query.where(table[:some_column].eq('hello'))
end

This would result in this method updating only rows where ‘projects.some_column` equals “hello”.

table - The name of the table. column - The name of the column to update. value - The value for the column.

The ‘value` argument is typically a literal. To perform a computed update, an Arel literal can be used instead:

update_value = Arel.sql('bar * baz')

update_column_in_batches(:projects, :foo, update_value) do |table, query|
  query.where(table[:some_column].eq('hello'))
end

Rubocop’s Metrics/AbcSize metric is disabled for this method as Rubocop determines this method to be too complex while there’s no way to make it less “complex” without introducing extra methods (which actually will make things more complex).

‘batch_column_name` option is for tables without primary key, in this case another unique integer column can be used. Example: :user_id

rubocop: disable Metrics/AbcSize



433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
# File 'lib/gitlab/database/migration_helpers.rb', line 433

def update_column_in_batches(table_name, column, value, batch_size: nil, batch_column_name: :id, disable_lock_writes: false)
  if transaction_open?
    raise 'update_column_in_batches can not be run inside a transaction, ' \
      'you can disable transactions by calling disable_ddl_transaction! ' \
      'in the body of your migration class'
  end

  table = Arel::Table.new(table_name)

  count_arel = table.project(Arel.star.count.as('count'))
  count_arel = yield table, count_arel if block_given?

  total = exec_query(count_arel.to_sql).to_a.first['count'].to_i

  return if total == 0

  if batch_size.nil?
    # Update in batches of 5% until we run out of any rows to update.
    batch_size = ((total / 100.0) * 5.0).ceil
    max_size = 1000

    # The upper limit is 1000 to ensure we don't lock too many rows. For
    # example, for "merge_requests" even 1% of the table is around 35 000
    # rows for GitLab.com.
    batch_size = max_size if batch_size > max_size
  end

  start_arel = table.project(table[batch_column_name]).order(table[batch_column_name].asc).take(1)
  start_arel = yield table, start_arel if block_given?
  start_id = exec_query(start_arel.to_sql).to_a.first[batch_column_name.to_s].to_i

  loop do
    stop_arel = table.project(table[batch_column_name])
      .where(table[batch_column_name].gteq(start_id))
      .order(table[batch_column_name].asc)
      .take(1)
      .skip(batch_size)

    stop_arel = yield table, stop_arel if block_given?
    stop_row = exec_query(stop_arel.to_sql).to_a.first

    update_arel = Arel::UpdateManager.new
      .table(table)
      .set([[table[column], value]])
      .where(table[batch_column_name].gteq(start_id))

    if stop_row
      stop_id = stop_row[batch_column_name.to_s].to_i
      start_id = stop_id
      update_arel = update_arel.where(table[batch_column_name].lt(stop_id))
    end

    update_arel = yield table, update_arel if block_given?

    transaction do
      execute("SELECT set_config('lock_writes.#{table_name}', 'false', true)") if disable_lock_writes
      execute(update_arel.to_sql)
    end

    # There are no more rows left to update.
    break unless stop_row
  end
end

#validate_foreign_key(source, column, name: nil) ⇒ Object



318
319
320
321
322
323
324
325
326
327
328
# File 'lib/gitlab/database/migration_helpers.rb', line 318

def validate_foreign_key(source, column, name: nil)
  fk_name = name || concurrent_foreign_key_name(source, column)

  unless foreign_key_exists?(source, name: fk_name)
    raise missing_schema_object_message(source, "foreign key", fk_name)
  end

  disable_statement_timeout do
    execute("ALTER TABLE #{source} VALIDATE CONSTRAINT #{fk_name};")
  end
end