debian-mirror-gitlab/app/models/namespace/traversal_hierarchy.rb

96 lines
3.3 KiB
Ruby
Raw Normal View History

2020-07-28 23:09:34 +05:30
# frozen_string_literal: true
#
# A Namespace::TraversalHierarchy is the collection of namespaces that descend
# from a root Namespace as defined by the Namespace#traversal_ids attributes.
#
# This class provides operations to be performed on the hierarchy itself,
# rather than individual namespaces.
#
# This includes methods for synchronizing traversal_ids attributes to a correct
# state. We use recursive methods to determine the correct state so we don't
# have to depend on the integrity of the traversal_ids attribute values
# themselves.
#
class Namespace
class TraversalHierarchy
attr_accessor :root
def self.for_namespace(namespace)
new(recursive_root_ancestor(namespace))
end
def initialize(root)
2021-06-08 01:23:25 +05:30
raise StandardError, 'Must specify a root node' if root.parent_id
2020-07-28 23:09:34 +05:30
@root = root
end
# Update all traversal_ids in the current namespace hierarchy.
def sync_traversal_ids!
# An issue in Rails since 2013 prevents this kind of join based update in
# ActiveRecord. https://github.com/rails/rails/issues/13496
# Ideally it would be:
# `incorrect_traversal_ids.update_all('traversal_ids = cte.traversal_ids')`
2022-05-07 20:08:51 +05:30
sql = <<-SQL
UPDATE namespaces
SET traversal_ids = cte.traversal_ids
FROM (#{recursive_traversal_ids}) as cte
WHERE namespaces.id = cte.id
AND namespaces.traversal_ids::bigint[] <> cte.traversal_ids
SQL
2021-06-08 01:23:25 +05:30
Namespace.transaction do
2022-05-07 20:08:51 +05:30
@root.lock!("FOR NO KEY UPDATE")
2021-06-08 01:23:25 +05:30
Namespace.connection.exec_query(sql)
end
2021-04-29 21:17:54 +05:30
rescue ActiveRecord::Deadlocked
db_deadlock_counter.increment(source: 'Namespace#sync_traversal_ids!')
raise
2020-07-28 23:09:34 +05:30
end
# Identify all incorrect traversal_ids in the current namespace hierarchy.
2021-06-08 01:23:25 +05:30
def incorrect_traversal_ids
2020-07-28 23:09:34 +05:30
Namespace
2021-06-08 01:23:25 +05:30
.joins("INNER JOIN (#{recursive_traversal_ids}) as cte ON namespaces.id = cte.id")
2021-09-04 01:27:46 +05:30
.where('namespaces.traversal_ids::bigint[] <> cte.traversal_ids')
2020-07-28 23:09:34 +05:30
end
private
# Determine traversal_ids for the namespace hierarchy using recursive methods.
# Generate a collection of [id, traversal_ids] rows.
#
# Note that the traversal_ids represent a calculated traversal path for the
# namespace and not the value stored within the traversal_ids attribute.
2021-06-08 01:23:25 +05:30
def recursive_traversal_ids
2020-07-28 23:09:34 +05:30
root_id = Integer(@root.id)
2021-06-08 01:23:25 +05:30
<<~SQL
2020-07-28 23:09:34 +05:30
WITH RECURSIVE cte(id, traversal_ids, cycle) AS (
2021-09-04 01:27:46 +05:30
VALUES(#{root_id}::bigint, ARRAY[#{root_id}]::bigint[], false)
2020-07-28 23:09:34 +05:30
UNION ALL
2021-09-04 01:27:46 +05:30
SELECT n.id, cte.traversal_ids || n.id::bigint, n.id = ANY(cte.traversal_ids)
2020-07-28 23:09:34 +05:30
FROM namespaces n, cte
WHERE n.parent_id = cte.id AND NOT cycle
)
SELECT id, traversal_ids FROM cte
2021-04-29 21:17:54 +05:30
SQL
2020-07-28 23:09:34 +05:30
end
# This is essentially Namespace#root_ancestor which will soon be rewritten
# to use traversal_ids. We replicate here as a reliable way to find the
# root using recursive methods.
def self.recursive_root_ancestor(namespace)
Gitlab::ObjectHierarchy
.new(Namespace.where(id: namespace))
.base_and_ancestors
.reorder(nil)
.find_by(parent_id: nil)
end
2021-04-29 21:17:54 +05:30
def db_deadlock_counter
Gitlab::Metrics.counter(:db_deadlock, 'Counts the times we have deadlocked in the database')
end
2020-07-28 23:09:34 +05:30
end
end