forked from MirrorHub/synapse
Analyze user_ips before running deduplication
Due to the table locks taken out by the naive upsert, the table statistics may be out of date. During deduplication it is important that the correct index is used as otherwise a full table scan may be incorrectly used, which can end up thrashing the database badly.
This commit is contained in:
parent
46b8a79b3a
commit
483ba85c7a
2 changed files with 31 additions and 3 deletions
|
@ -65,6 +65,11 @@ class ClientIpStore(background_updates.BackgroundUpdateStore):
|
|||
columns=["last_seen"],
|
||||
)
|
||||
|
||||
self.register_background_update_handler(
|
||||
"user_ips_analyze",
|
||||
self._analyze_user_ip,
|
||||
)
|
||||
|
||||
self.register_background_update_handler(
|
||||
"user_ips_remove_dupes",
|
||||
self._remove_user_ip_dupes,
|
||||
|
@ -108,6 +113,25 @@ class ClientIpStore(background_updates.BackgroundUpdateStore):
|
|||
yield self._end_background_update("user_ips_drop_nonunique_index")
|
||||
defer.returnValue(1)
|
||||
|
||||
@defer.inlineCallbacks
|
||||
def _analyze_user_ip(self, progress, batch_size):
|
||||
# Background update to analyze user_ips table before we run the
|
||||
# deduplication background update. The table may not have been analyzed
|
||||
# for ages due to the table locks.
|
||||
#
|
||||
# This will lock out the naive upserts to user_ips while it happens, but
|
||||
# the analyze should be quick (28GB table takes ~10s)
|
||||
def user_ips_analyze(txn):
|
||||
txn.execute("ANALYZE user_ips")
|
||||
|
||||
end_last_seen = yield self.runInteraction(
|
||||
"user_ips_analyze", user_ips_analyze
|
||||
)
|
||||
|
||||
yield self._end_background_update("user_ips_analyze")
|
||||
|
||||
defer.returnValue(1)
|
||||
|
||||
@defer.inlineCallbacks
|
||||
def _remove_user_ip_dupes(self, progress, batch_size):
|
||||
# This works function works by scanning the user_ips table in batches
|
||||
|
|
|
@ -13,9 +13,13 @@
|
|||
* limitations under the License.
|
||||
*/
|
||||
|
||||
-- delete duplicates
|
||||
-- analyze user_ips, to help ensure the correct indices are used
|
||||
INSERT INTO background_updates (update_name, progress_json) VALUES
|
||||
('user_ips_remove_dupes', '{}');
|
||||
('user_ips_analyze', '{}');
|
||||
|
||||
-- delete duplicates
|
||||
INSERT INTO background_updates (update_name, progress_json, depends_on) VALUES
|
||||
('user_ips_remove_dupes', '{}', 'user_ips_analyze');
|
||||
|
||||
-- add a new unique index to user_ips table
|
||||
INSERT INTO background_updates (update_name, progress_json, depends_on) VALUES
|
||||
|
@ -23,4 +27,4 @@ INSERT INTO background_updates (update_name, progress_json, depends_on) VALUES
|
|||
|
||||
-- drop the old original index
|
||||
INSERT INTO background_updates (update_name, progress_json, depends_on) VALUES
|
||||
('user_ips_drop_nonunique_index', '{}', 'user_ips_device_unique_index');
|
||||
('user_ips_drop_nonunique_index', '{}', 'user_ips_device_unique_index');
|
||||
|
|
Loading…
Reference in a new issue