Roomserver/federation input refactor (#2104)

* Put federation client functions into their own file

* Look for missing auth events in RS input

* Remove retrieveMissingAuthEvents from federation API

* Logging

* Sorta transplanted the code over

* Use event origin failing all else

* Don't get stuck on mutexes:

* Add verifier

* Don't mark state events with zero snapshot NID as not existing

* Check missing state if not an outlier before storing the event

* Reject instead of soft-fail, don't copy roominfo so much

* Use synchronous contexts, limit time to fetch missing events

* Clean up some commented out bits

* Simplify `/send` endpoint significantly

* Submit async

* Report errors on sending to RS input

* Set max payload in NATS to 16MB

* Tweak metrics

* Add `workerForRoom` for tidiness

* Try skipping unmarshalling errors for RespMissingEvents

* Track missing prev events separately to avoid calculating state when not possible

* Tweak logic around checking missing state

* Care about state when checking missing prev events

* Don't check missing state for create events

* Try that again

* Handle create events better

* Send create room events as new

* Use given event kind when sending auth/state events

* Revert "Use given event kind when sending auth/state events"

This reverts commit 089d64d271.

* Only search for missing prev events or state for new events

* Tweaks

* We only have missing prev if we don't supply state

* Room version tweaks

* Allow async inputs again

* Apply backpressure to consumers/synchronous requests to hopefully stop things being overwhelmed

* Set timeouts on roomserver input tasks (need to decide what timeout makes sense)

* Use work queue policy, deliver all on restart

* Reduce chance of duplicates being sent by NATS

* Limit the number of servers we attempt to reduce backpressure

* Some review comment fixes

* Tidy up a couple things

* Don't limit servers, randomise order using map

* Some context refactoring

* Update gmsl

* Don't resend create events

* Set stateIDs length correctly or else the roomserver thinks there are missing events when there aren't

* Exclude our own servername

* Try backing off servers

* Make excluding self behaviour optional

* Exclude self from g_m_e

* Update sytest-whitelist

* Update consumers for the roomserver output stream

* Remember to send outliers for state returned from /gme

* Make full HTTP tests less upsetti

* Remove 'If a device list update goes missing, the server resyncs on the next one' from the sytest blacklist

* Remove debugging test

* Fix blacklist again, remove unnecessary duplicate context

* Clearer contexts, don't use background in case there's something happening there

* Don't queue up events more than once in memory

* Correctly identify create events when checking for state

* Fill in gaps again in /gme code

* Remove `AuthEventIDs` from `InputRoomEvent`

* Remove stray field

Co-authored-by: Kegan Dougal <kegan@matrix.org>
This commit is contained in:
Neil Alexander 2022-01-27 14:29:14 +00:00 committed by GitHub
parent 5b4999afa9
commit a763cbb0e1
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
46 changed files with 1549 additions and 1285 deletions

View file

@ -56,7 +56,7 @@ func CheckForSoftFail(
// Then get the state entries for the current state snapshot.
// We'll use this to check if the event is allowed right now.
roomState := state.NewStateResolution(db, *roomInfo)
roomState := state.NewStateResolution(db, roomInfo)
authStateEntries, err = roomState.LoadStateAtSnapshot(ctx, roomInfo.StateSnapshotNID)
if err != nil {
return true, fmt.Errorf("roomState.LoadStateAtSnapshot: %w", err)

View file

@ -179,7 +179,7 @@ func GetMembershipsAtState(
return events, nil
}
func StateBeforeEvent(ctx context.Context, db storage.Database, info types.RoomInfo, eventNID types.EventNID) ([]types.StateEntry, error) {
func StateBeforeEvent(ctx context.Context, db storage.Database, info *types.RoomInfo, eventNID types.EventNID) ([]types.StateEntry, error) {
roomState := state.NewStateResolution(db, info)
// Lookup the event NID
eIDs, err := db.EventIDs(ctx, []types.EventNID{eventNID})
@ -223,7 +223,7 @@ func LoadStateEvents(
}
func CheckServerAllowedToSeeEvent(
ctx context.Context, db storage.Database, info types.RoomInfo, eventID string, serverName gomatrixserverlib.ServerName, isServerInRoom bool,
ctx context.Context, db storage.Database, info *types.RoomInfo, eventID string, serverName gomatrixserverlib.ServerName, isServerInRoom bool,
) (bool, error) {
roomState := state.NewStateResolution(db, info)
stateEntries, err := roomState.LoadStateAtEvent(ctx, eventID)
@ -279,7 +279,7 @@ func CheckServerAllowedToSeeEvent(
// TODO: Remove this when we have tests to assert correctness of this function
func ScanEventTree(
ctx context.Context, db storage.Database, info types.RoomInfo, front []string, visited map[string]bool, limit int,
ctx context.Context, db storage.Database, info *types.RoomInfo, front []string, visited map[string]bool, limit int,
serverName gomatrixserverlib.ServerName,
) ([]types.EventNID, error) {
var resultNIDs []types.EventNID
@ -387,7 +387,7 @@ func QueryLatestEventsAndState(
return nil
}
roomState := state.NewStateResolution(db, *roomInfo)
roomState := state.NewStateResolution(db, roomInfo)
response.RoomExists = true
response.RoomVersion = roomInfo.RoomVersion