Matrix/synapse
Matrix/synapse
1
0
Fork 0
mirror of https://github.com/element-hq/synapse synced 2024-06-28 06:53:37 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge c01300710e into 3aae60f17b

Browse source
This commit is contained in:
Christoph Settgast 2024-06-14 15:37:19 +03:00 committed by GitHub
parent 3aae60f17b c01300710e
commit 15a126c677
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 97 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
changelog.d/17154.bugfix Normal file
View file

@ -0,0 +1 @@
Fixed SQL performance regression introduced in #17044.

99
synapse/storage/databases/main/event_federation.py
View file

@ -280,16 +280,64 @@ class EventFederationWorkerStore(SignatureWorkerStore, EventsWorkerStore, SQLBas
# Now we look up all links for the chains we have, adding chains that
# are reachable from any event.
#
# This query is structured to first get all chain IDs reachable, and
# then pull out all links from those chains. This does pull out more
# rows than is strictly necessary, however there isn't a way of
# structuring the recursive part of query to pull out the links without
# also returning large quantities of redundant data (which can make it a
# lot slower).
sql = """
WITH RECURSIVE links(chain_id) AS (
SELECT
DISTINCT origin_chain_id
FROM event_auth_chain_links WHERE %s
UNION
SELECT
target_chain_id
FROM event_auth_chain_links
INNER JOIN links ON (chain_id = origin_chain_id)
)
SELECT
origin_chain_id, origin_sequence_number,
target_chain_id, target_sequence_number
FROM links
INNER JOIN event_auth_chain_links ON (chain_id = origin_chain_id)
"""
# A map from chain ID to max sequence number *reachable* from any event ID.
chains: Dict[int, int] = {}
for links in self._get_chain_links(txn, set(event_chains.keys())):
# Add all linked chains reachable from initial set of chains.
chains_to_fetch = set(event_chains.keys())
while chains_to_fetch:
batch2 = tuple(itertools.islice(chains_to_fetch, 1000))
chains_to_fetch.difference_update(batch2)
clause, args = make_in_list_sql_clause(
txn.database_engine, "origin_chain_id", batch2
)
txn.execute(sql % (clause,), args)
links: Dict[int, List[Tuple[int, int, int]]] = {}
for (
origin_chain_id,
origin_sequence_number,
target_chain_id,
target_sequence_number,
) in txn:
links.setdefault(origin_chain_id, []).append(
(origin_sequence_number, target_chain_id, target_sequence_number)
)
for chain_id in links:
if chain_id not in event_chains:
continue
_materialize(chain_id, event_chains[chain_id], links, chains)
chains_to_fetch.difference_update(chains)
# Add the initial set of chains, excluding the sequence corresponding to
# initial event.
for chain_id, seq_no in event_chains.items():
@ -579,9 +627,53 @@ class EventFederationWorkerStore(SignatureWorkerStore, EventsWorkerStore, SQLBas
# Now we look up all links for the chains we have, adding chains that
# are reachable from any event.
#
# This query is structured to first get all chain IDs reachable, and
# then pull out all links from those chains. This does pull out more
# rows than is strictly necessary, however there isn't a way of
# structuring the recursive part of query to pull out the links without
# also returning large quantities of redundant data (which can make it a
# lot slower).
sql = """
WITH RECURSIVE links(chain_id) AS (
SELECT
DISTINCT origin_chain_id
FROM event_auth_chain_links WHERE %s
UNION
SELECT
target_chain_id
FROM event_auth_chain_links
INNER JOIN links ON (chain_id = origin_chain_id)
)
SELECT
origin_chain_id, origin_sequence_number,
target_chain_id, target_sequence_number
FROM links
INNER JOIN event_auth_chain_links ON (chain_id = origin_chain_id)
"""
# (We need to take a copy of `seen_chains` as we want to mutate it in
# the loop)
chains_to_fetch = set(seen_chains)
while chains_to_fetch:
batch2 = tuple(itertools.islice(chains_to_fetch, 1000))
clause, args = make_in_list_sql_clause(
txn.database_engine, "origin_chain_id", batch2
)
txn.execute(sql % (clause,), args)
links: Dict[int, List[Tuple[int, int, int]]] = {}
for (
origin_chain_id,
origin_sequence_number,
target_chain_id,
target_sequence_number,
) in txn:
links.setdefault(origin_chain_id, []).append(
(origin_sequence_number, target_chain_id, target_sequence_number)
)
# (We need to take a copy of `seen_chains` as the function mutates it)
for links in self._get_chain_links(txn, set(seen_chains)):
for chains in set_to_chain:
for chain_id in links:
if chain_id not in chains:
@ -589,6 +681,7 @@ class EventFederationWorkerStore(SignatureWorkerStore, EventsWorkerStore, SQLBas
_materialize(chain_id, chains[chain_id], links, chains)
chains_to_fetch.difference_update(chains)
seen_chains.update(chains)
# Now for each chain we figure out the maximum sequence number reachable