Commit 8966263e authored by Yorick Peterse's avatar Yorick Peterse

Customizing of update_column_in_batches queries

By passing a block to update_column_in_batches() one can now customize
the queries executed. This in turn can be used to only update a specific
set of rows instead of simply all the rows in the table.
parent 8bfbafbb
......@@ -28,63 +28,73 @@ module Gitlab
# Updates the value of a column in batches.
#
# This method updates the table in batches of 5% of the total row count.
# Any data inserted while running this method (or after it has finished
# running) is _not_ updated automatically.
# This method will continue updating rows until no rows remain.
#
# When given a block this method will yield to 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 there
# `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.
def update_column_in_batches(table, column, value)
quoted_table = quote_table_name(table)
quoted_column = quote_column_name(column)
##
# Workaround for #17711
#
# It looks like for MySQL `ActiveRecord::Base.conntection.quote(true)`
# returns correct value (1), but `ActiveRecord::Migration.new.quote`
# returns incorrect value ('true'), which causes migrations to fail.
#
quoted_value = connection.quote(value)
table = Arel::Table.new(table)
processed = 0
total = exec_query("SELECT COUNT(*) AS count FROM #{quoted_table}").
to_hash.
first['count'].
to_i
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_hash.first['count'].to_i
# Update in batches of 5% until we run out of any rows to update.
batch_size = ((total / 100.0) * 5.0).ceil
loop do
start_row = exec_query(%Q{
SELECT id
FROM #{quoted_table}
ORDER BY id ASC
LIMIT 1 OFFSET #{processed}
}).to_hash.first
start_arel = table.project(table[:id]).
order(table[:id].asc).
take(1).
skip(processed)
start_arel = yield table, start_arel if block_given?
start_row = exec_query(start_arel.to_sql).to_hash.first
# There are no more rows to process
break unless start_row
stop_row = exec_query(%Q{
SELECT id
FROM #{quoted_table}
ORDER BY id ASC
LIMIT 1 OFFSET #{processed + batch_size}
}).to_hash.first
stop_arel = table.project(table[:id]).
order(table[:id].asc).
take(1).
skip(processed + batch_size)
query = %Q{
UPDATE #{quoted_table}
SET #{quoted_column} = #{quoted_value}
WHERE id >= #{start_row['id']}
}
stop_arel = yield table, stop_arel if block_given?
stop_row = exec_query(stop_arel.to_sql).to_hash.first
update_manager = Arel::UpdateManager.new(ActiveRecord::Base)
update_arel = update_manager.table(table).
set([[table[column], value]]).
where(table[:id].gteq(start_row['id']))
update_arel = yield table, update_arel if block_given?
if stop_row
query += " AND id < #{stop_row['id']}"
update_arel = update_arel.where(table[:id].lt(stop_row['id']))
end
execute(query)
execute(update_arel.to_sql)
processed += batch_size
end
......@@ -95,9 +105,9 @@ module Gitlab
# This method runs the following steps:
#
# 1. Add the column with a default value of NULL.
# 2. Update all existing rows in batches.
# 3. Change the default value of the column to the specified value.
# 4. Update any remaining rows.
# 2. Change the default value of the column to the specified value.
# 3. Update all existing rows in batches.
# 4. Set a `NOT NULL` constraint on the column if desired (the default).
#
# These steps ensure a column can be added to a large and commonly used
# table without locking the entire table for the duration of the table
......@@ -109,7 +119,10 @@ module Gitlab
# default - The default value for the column.
# allow_null - When set to `true` the column will allow NULL values, the
# default is to not allow NULL values.
def add_column_with_default(table, column, type, default:, allow_null: false)
#
# This method can also take a block which is passed directly to the
# `update_column_in_batches` method.
def add_column_with_default(table, column, type, default:, allow_null: false, &block)
if transaction_open?
raise 'add_column_with_default can not be run inside a transaction, ' \
'you can disable transactions by calling disable_ddl_transaction! ' \
......@@ -126,7 +139,7 @@ module Gitlab
begin
transaction do
update_column_in_batches(table, column, default)
update_column_in_batches(table, column, default, &block)
change_column_null(table, column, false) unless allow_null
end
......
......@@ -71,6 +71,18 @@ describe Gitlab::Database::MigrationHelpers, lib: true do
expect(Project.where(archived: true).count).to eq(5)
end
context 'when a block is supplied' do
it 'yields an Arel table and query object to the supplied block' do
first_id = Project.first.id
model.update_column_in_batches(:projects, :archived, true) do |t, query|
query.where(t[:id].eq(first_id))
end
expect(Project.where(archived: true).count).to eq(1)
end
end
end
describe '#add_column_with_default' do
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment