diff --git a/synapse/storage/databases/main/events_bg_updates.py b/synapse/storage/databases/main/events_bg_updates.py
index cbe4be1437..29f33bac55 100644
--- a/synapse/storage/databases/main/events_bg_updates.py
+++ b/synapse/storage/databases/main/events_bg_updates.py
@@ -29,6 +29,34 @@ from synapse.types import JsonDict
logger = logging.getLogger(__name__)
+_REPLACE_STREAM_ORDERING_SQL_COMMANDS = (
+ # there should be no leftover rows without a stream_ordering2, but just in case...
+ "UPDATE events SET stream_ordering2 = stream_ordering WHERE stream_ordering2 IS NULL",
+ # now we can drop the rule and switch the columns
+ "DROP RULE populate_stream_ordering2 ON events",
+ "ALTER TABLE events DROP COLUMN stream_ordering",
+ "ALTER TABLE events RENAME COLUMN stream_ordering2 TO stream_ordering",
+ # ... and finally, rename the indexes into place for consistency with sqlite
+ "ALTER INDEX event_contains_url_index2 RENAME TO event_contains_url_index",
+ "ALTER INDEX events_order_room2 RENAME TO events_order_room",
+ "ALTER INDEX events_room_stream2 RENAME TO events_room_stream",
+ "ALTER INDEX events_ts2 RENAME TO events_ts",
+)
+
+
+class _BackgroundUpdates:
+ EVENT_ORIGIN_SERVER_TS_NAME = "event_origin_server_ts"
+ EVENT_FIELDS_SENDER_URL_UPDATE_NAME = "event_fields_sender_url"
+ DELETE_SOFT_FAILED_EXTREMITIES = "delete_soft_failed_extremities"
+ POPULATE_STREAM_ORDERING2 = "populate_stream_ordering2"
+ INDEX_STREAM_ORDERING2 = "index_stream_ordering2"
+ INDEX_STREAM_ORDERING2_CONTAINS_URL = "index_stream_ordering2_contains_url"
+ INDEX_STREAM_ORDERING2_ROOM_ORDER = "index_stream_ordering2_room_order"
+ INDEX_STREAM_ORDERING2_ROOM_STREAM = "index_stream_ordering2_room_stream"
+ INDEX_STREAM_ORDERING2_TS = "index_stream_ordering2_ts"
+ REPLACE_STREAM_ORDERING_COLUMN = "replace_stream_ordering_column"
+
+
@attr.s(slots=True, frozen=True)
class _CalculateChainCover:
"""Return value for _calculate_chain_cover_txn."""
@@ -48,19 +76,15 @@ class _CalculateChainCover:
class EventsBackgroundUpdatesStore(SQLBaseStore):
-
- EVENT_ORIGIN_SERVER_TS_NAME = "event_origin_server_ts"
- EVENT_FIELDS_SENDER_URL_UPDATE_NAME = "event_fields_sender_url"
- DELETE_SOFT_FAILED_EXTREMITIES = "delete_soft_failed_extremities"
-
def __init__(self, database: DatabasePool, db_conn, hs):
super().__init__(database, db_conn, hs)
self.db_pool.updates.register_background_update_handler(
- self.EVENT_ORIGIN_SERVER_TS_NAME, self._background_reindex_origin_server_ts
+ _BackgroundUpdates.EVENT_ORIGIN_SERVER_TS_NAME,
+ self._background_reindex_origin_server_ts,
)
self.db_pool.updates.register_background_update_handler(
- self.EVENT_FIELDS_SENDER_URL_UPDATE_NAME,
+ _BackgroundUpdates.EVENT_FIELDS_SENDER_URL_UPDATE_NAME,
self._background_reindex_fields_sender,
)
@@ -85,7 +109,8 @@ class EventsBackgroundUpdatesStore(SQLBaseStore):
)
self.db_pool.updates.register_background_update_handler(
- self.DELETE_SOFT_FAILED_EXTREMITIES, self._cleanup_extremities_bg_update
+ _BackgroundUpdates.DELETE_SOFT_FAILED_EXTREMITIES,
+ self._cleanup_extremities_bg_update,
)
self.db_pool.updates.register_background_update_handler(
@@ -139,6 +164,59 @@ class EventsBackgroundUpdatesStore(SQLBaseStore):
self._purged_chain_cover_index,
)
+ ################################################################################
+
+ # bg updates for replacing stream_ordering with a BIGINT
+ # (these only run on postgres.)
+
+ self.db_pool.updates.register_background_update_handler(
+ _BackgroundUpdates.POPULATE_STREAM_ORDERING2,
+ self._background_populate_stream_ordering2,
+ )
+ # CREATE UNIQUE INDEX events_stream_ordering ON events(stream_ordering2);
+ self.db_pool.updates.register_background_index_update(
+ _BackgroundUpdates.INDEX_STREAM_ORDERING2,
+ index_name="events_stream_ordering",
+ table="events",
+ columns=["stream_ordering2"],
+ unique=True,
+ )
+ # CREATE INDEX event_contains_url_index ON events(room_id, topological_ordering, stream_ordering) WHERE contains_url = true AND outlier = false;
+ self.db_pool.updates.register_background_index_update(
+ _BackgroundUpdates.INDEX_STREAM_ORDERING2_CONTAINS_URL,
+ index_name="event_contains_url_index2",
+ table="events",
+ columns=["room_id", "topological_ordering", "stream_ordering2"],
+ where_clause="contains_url = true AND outlier = false",
+ )
+ # CREATE INDEX events_order_room ON events(room_id, topological_ordering, stream_ordering);
+ self.db_pool.updates.register_background_index_update(
+ _BackgroundUpdates.INDEX_STREAM_ORDERING2_ROOM_ORDER,
+ index_name="events_order_room2",
+ table="events",
+ columns=["room_id", "topological_ordering", "stream_ordering2"],
+ )
+ # CREATE INDEX events_room_stream ON events(room_id, stream_ordering);
+ self.db_pool.updates.register_background_index_update(
+ _BackgroundUpdates.INDEX_STREAM_ORDERING2_ROOM_STREAM,
+ index_name="events_room_stream2",
+ table="events",
+ columns=["room_id", "stream_ordering2"],
+ )
+ # CREATE INDEX events_ts ON events(origin_server_ts, stream_ordering);
+ self.db_pool.updates.register_background_index_update(
+ _BackgroundUpdates.INDEX_STREAM_ORDERING2_TS,
+ index_name="events_ts2",
+ table="events",
+ columns=["origin_server_ts", "stream_ordering2"],
+ )
+ self.db_pool.updates.register_background_update_handler(
+ _BackgroundUpdates.REPLACE_STREAM_ORDERING_COLUMN,
+ self._background_replace_stream_ordering_column,
+ )
+
+ ################################################################################
+
async def _background_reindex_fields_sender(self, progress, batch_size):
target_min_stream_id = progress["target_min_stream_id_inclusive"]
max_stream_id = progress["max_stream_id_exclusive"]
@@ -190,18 +268,18 @@ class EventsBackgroundUpdatesStore(SQLBaseStore):
}
self.db_pool.updates._background_update_progress_txn(
- txn, self.EVENT_FIELDS_SENDER_URL_UPDATE_NAME, progress
+ txn, _BackgroundUpdates.EVENT_FIELDS_SENDER_URL_UPDATE_NAME, progress
)
return len(rows)
result = await self.db_pool.runInteraction(
- self.EVENT_FIELDS_SENDER_URL_UPDATE_NAME, reindex_txn
+ _BackgroundUpdates.EVENT_FIELDS_SENDER_URL_UPDATE_NAME, reindex_txn
)
if not result:
await self.db_pool.updates._end_background_update(
- self.EVENT_FIELDS_SENDER_URL_UPDATE_NAME
+ _BackgroundUpdates.EVENT_FIELDS_SENDER_URL_UPDATE_NAME
)
return result
@@ -264,18 +342,18 @@ class EventsBackgroundUpdatesStore(SQLBaseStore):
}
self.db_pool.updates._background_update_progress_txn(
- txn, self.EVENT_ORIGIN_SERVER_TS_NAME, progress
+ txn, _BackgroundUpdates.EVENT_ORIGIN_SERVER_TS_NAME, progress
)
return len(rows_to_update)
result = await self.db_pool.runInteraction(
- self.EVENT_ORIGIN_SERVER_TS_NAME, reindex_search_txn
+ _BackgroundUpdates.EVENT_ORIGIN_SERVER_TS_NAME, reindex_search_txn
)
if not result:
await self.db_pool.updates._end_background_update(
- self.EVENT_ORIGIN_SERVER_TS_NAME
+ _BackgroundUpdates.EVENT_ORIGIN_SERVER_TS_NAME
)
return result
@@ -454,7 +532,7 @@ class EventsBackgroundUpdatesStore(SQLBaseStore):
if not num_handled:
await self.db_pool.updates._end_background_update(
- self.DELETE_SOFT_FAILED_EXTREMITIES
+ _BackgroundUpdates.DELETE_SOFT_FAILED_EXTREMITIES
)
def _drop_table_txn(txn):
@@ -1009,3 +1087,81 @@ class EventsBackgroundUpdatesStore(SQLBaseStore):
await self.db_pool.updates._end_background_update("purged_chain_cover")
return result
+
+ async def _background_populate_stream_ordering2(
+ self, progress: JsonDict, batch_size: int
+ ) -> int:
+ """Populate events.stream_ordering2, then replace stream_ordering
+
+ This is to deal with the fact that stream_ordering was initially created as a
+ 32-bit integer field.
+ """
+ batch_size = max(batch_size, 1)
+
+ def process(txn: Cursor) -> int:
+ last_stream = progress.get("last_stream", -(1 << 31))
+ txn.execute(
+ """
+ UPDATE events SET stream_ordering2=stream_ordering
+ WHERE stream_ordering IN (
+ SELECT stream_ordering FROM events WHERE stream_ordering > ?
+ ORDER BY stream_ordering LIMIT ?
+ )
+ RETURNING stream_ordering;
+ """,
+ (last_stream, batch_size),
+ )
+ row_count = txn.rowcount
+ if row_count == 0:
+ return 0
+ last_stream = max(row[0] for row in txn)
+ logger.info("populated stream_ordering2 up to %i", last_stream)
+
+ self.db_pool.updates._background_update_progress_txn(
+ txn,
+ _BackgroundUpdates.POPULATE_STREAM_ORDERING2,
+ {"last_stream": last_stream},
+ )
+ return row_count
+
+ result = await self.db_pool.runInteraction(
+ "_background_populate_stream_ordering2", process
+ )
+
+ if result != 0:
+ return result
+
+ await self.db_pool.updates._end_background_update(
+ _BackgroundUpdates.POPULATE_STREAM_ORDERING2
+ )
+ return 0
+
+ async def _background_replace_stream_ordering_column(
+ self, progress: JsonDict, batch_size: int
+ ) -> int:
+ """Drop the old 'stream_ordering' column and rename 'stream_ordering2' into its place."""
+
+ def process(txn: Cursor) -> None:
+ for sql in _REPLACE_STREAM_ORDERING_SQL_COMMANDS:
+ logger.info("completing stream_ordering migration: %s", sql)
+ txn.execute(sql)
+
+ # ANALYZE the new column to build stats on it, to encourage PostgreSQL to use the
+ # indexes on it.
+ # We need to pass execute a dummy function to handle the txn's result otherwise
+ # it tries to call fetchall() on it and fails because there's no result to fetch.
+ await self.db_pool.execute(
+ "background_analyze_new_stream_ordering_column",
+ lambda txn: None,
+ "ANALYZE events(stream_ordering2)",
+ )
+
+ await self.db_pool.runInteraction(
+ "_background_replace_stream_ordering_column", process
+ )
+
+ await self.db_pool.updates._end_background_update(
+ _BackgroundUpdates.REPLACE_STREAM_ORDERING_COLUMN
+ )
+
+ return 0
|
