Add a /replication API for extracting the updates that happened on

synapse

This is necessary for replicating the data in synapse to be visible to a
separate service because presence and typing notifications aren't stored
in a database so won't be visible to another process.

This API can be used to either get the raw data by requesting the tables
themselves or to just receive notifications for updates by following the
streams meta-stream.

Returns updates for each table requested a JSON array of arrays with a
row for each row in the table.

Each table is prefixed by a header row with the: name of the table,
current stream_id position for the table, number of rows, number of
columns and the names of the columns.
This is followed by the rows that have been added to the server since
the requester last asked.

The API has a timeout and is hooked up to the notifier so that a slave
can long poll for updates.
This commit is contained in:
Mark Haines 2016-03-01 14:49:41 +00:00
parent 742ec37ca3
commit 60a0f81c7a
15 changed files with 846 additions and 4 deletions

View file

@ -159,6 +159,8 @@ class Notifier(object):
self.remove_expired_streams, self.UNUSED_STREAM_EXPIRY_MS
)
self.replication_deferred = ObservableDeferred(defer.Deferred())
# This is not a very cheap test to perform, but it's only executed
# when rendering the metrics page, which is likely once per minute at
# most when scraping it.
@ -207,6 +209,8 @@ class Notifier(object):
))
self._notify_pending_new_room_events(max_room_stream_id)
self.notify_replication()
def _notify_pending_new_room_events(self, max_room_stream_id):
"""Notify for the room events that were queued waiting for a previous
event to be persisted.
@ -276,6 +280,8 @@ class Notifier(object):
except:
logger.exception("Failed to notify listener")
self.notify_replication()
@defer.inlineCallbacks
def wait_for_events(self, user_id, timeout, callback, room_ids=None,
from_token=StreamToken("s0", "0", "0", "0", "0")):
@ -479,3 +485,45 @@ class Notifier(object):
room_streams = self.room_to_user_streams.setdefault(room_id, set())
room_streams.add(new_user_stream)
new_user_stream.rooms.add(room_id)
def notify_replication(self):
"""Notify the any replication listeners that there's a new event"""
with PreserveLoggingContext():
deferred = self.replication_deferred
self.replication_deferred = ObservableDeferred(defer.Deferred())
deferred.callback(None)
@defer.inlineCallbacks
def wait_for_replication(self, callback, timeout):
"""Wait for an event to happen.
:param callback:
Gets called whenever an event happens. If this returns a truthy
value then ``wait_for_replication`` returns, otherwise it waits
for another event.
:param int timeout:
How many milliseconds to wait for callback return a truthy value.
:returns:
A deferred that resolves with the value returned by the callback.
"""
listener = _NotificationListener(None)
def timed_out():
listener.deferred.cancel()
timer = self.clock.call_later(timeout / 1000., timed_out)
while True:
listener.deferred = self.replication_deferred.observe()
result = yield callback()
if result:
break
try:
with PreserveLoggingContext():
yield listener.deferred
except defer.CancelledError:
break
self.clock.cancel_call_later(timer, ignore_errs=True)
defer.returnValue(result)