dendrite/federationapi/api/api.go

212 lines
7.7 KiB
Go
Raw Normal View History

package api
import (
"context"
"fmt"
"time"
"github.com/matrix-org/dendrite/federationapi/types"
"github.com/matrix-org/gomatrix"
"github.com/matrix-org/gomatrixserverlib"
)
// FederationClient is a subset of gomatrixserverlib.FederationClient functions which the fedsender
// implements as proxy calls, with built-in backoff/retries/etc. Errors returned from functions in
// this interface are of type FederationClientError
type FederationClient interface {
gomatrixserverlib.BackfillClient
gomatrixserverlib.FederatedStateClient
GetUserDevices(ctx context.Context, s gomatrixserverlib.ServerName, userID string) (res gomatrixserverlib.RespUserDevices, err error)
ClaimKeys(ctx context.Context, s gomatrixserverlib.ServerName, oneTimeKeys map[string]map[string]string) (res gomatrixserverlib.RespClaimKeys, err error)
QueryKeys(ctx context.Context, s gomatrixserverlib.ServerName, keys map[string][]string) (res gomatrixserverlib.RespQueryKeys, err error)
GetEvent(ctx context.Context, s gomatrixserverlib.ServerName, eventID string) (res gomatrixserverlib.Transaction, err error)
MSC2836EventRelationships(ctx context.Context, dst gomatrixserverlib.ServerName, r gomatrixserverlib.MSC2836EventRelationshipsRequest, roomVersion gomatrixserverlib.RoomVersion) (res gomatrixserverlib.MSC2836EventRelationshipsResponse, err error)
MSC2946Spaces(ctx context.Context, dst gomatrixserverlib.ServerName, roomID string, suggestedOnly bool) (res gomatrixserverlib.MSC2946SpacesResponse, err error)
LookupServerKeys(ctx context.Context, s gomatrixserverlib.ServerName, keyRequests map[gomatrixserverlib.PublicKeyLookupRequest]gomatrixserverlib.Timestamp) ([]gomatrixserverlib.ServerKeys, error)
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 089d64d271b5fca8c104e1554711187420dbebca. * 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>
2022-01-27 14:29:14 +00:00
GetEventAuth(ctx context.Context, s gomatrixserverlib.ServerName, roomVersion gomatrixserverlib.RoomVersion, roomID, eventID string) (res gomatrixserverlib.RespEventAuth, err error)
LookupMissingEvents(ctx context.Context, s gomatrixserverlib.ServerName, roomID string, missing gomatrixserverlib.MissingEvents, roomVersion gomatrixserverlib.RoomVersion) (res gomatrixserverlib.RespMissingEvents, err error)
}
// FederationClientError is returned from FederationClient methods in the event of a problem.
type FederationClientError struct {
Err string
RetryAfter time.Duration
Blacklisted bool
}
func (e *FederationClientError) Error() string {
return fmt.Sprintf("%s - (retry_after=%s, blacklisted=%v)", e.Err, e.RetryAfter.String(), e.Blacklisted)
}
// FederationInternalAPI is used to query information from the federation sender.
type FederationInternalAPI interface {
FederationClient
gomatrixserverlib.KeyDatabase
KeyRing() *gomatrixserverlib.KeyRing
QueryServerKeys(ctx context.Context, request *QueryServerKeysRequest, response *QueryServerKeysResponse) error
// PerformDirectoryLookup looks up a remote room ID from a room alias.
PerformDirectoryLookup(
ctx context.Context,
request *PerformDirectoryLookupRequest,
response *PerformDirectoryLookupResponse,
) error
// Query the server names of the joined hosts in a room.
// Unlike QueryJoinedHostsInRoom, this function returns a de-duplicated slice
// containing only the server names (without information for membership events).
// The response will include this server if they are joined to the room.
QueryJoinedHostServerNamesInRoom(
ctx context.Context,
request *QueryJoinedHostServerNamesInRoomRequest,
response *QueryJoinedHostServerNamesInRoomResponse,
) error
// Handle an instruction to make_join & send_join with a remote server.
PerformJoin(
ctx context.Context,
request *PerformJoinRequest,
response *PerformJoinResponse,
)
Peeking over federation via MSC2444 (#1391) * a very very WIP first cut of peeking via MSC2753. doesn't yet compile or work. needs to actually add the peeking block into the sync response. checking in now before it gets any bigger, and to gather any initial feedback on the vague shape of it. * make PeekingDeviceSet private * add server_name param * blind stab at adding a `peek` section to /sync * make it build * make it launch * add peeking to getResponseWithPDUsForCompleteSync * cancel any peeks when we join a room * spell out how to runoutside of docker if you want speed * fix SQL * remove unnecessary txn for SelectPeeks * fix s/join/peek/ cargocult fail * HACK: Track goroutine IDs to determine when we write by the wrong thread To use: set `DENDRITE_TRACE_SQL=1` then grep for `unsafe` * Track partition offsets and only log unsafe for non-selects * Put redactions in the writer goroutine * Update filters on writer goroutine * wrap peek storage in goid hack * use exclusive writer, and MarkPeeksAsOld more efficiently * don't log ascii in binary at sql trace... * strip out empty roomd deltas * re-add txn to SelectPeeks * re-add accidentally deleted field * reject peeks for non-worldreadable rooms * move perform_peek * fix package * correctly refactor perform_peek * WIP of implementing MSC2444 * typo * Revert "Merge branch 'kegan/HACK-goid-sqlite-db-is-locked' into matthew/peeking" This reverts commit 3cebd8dbfbccdf82b7930b7b6eda92095ca6ef41, reversing changes made to ed4b3a58a7855acc43530693cc855b439edf9c7c. * (almost) make it build * clean up bad merge * support SendEventWithState with optional event * fix build & lint * fix build & lint * reinstate federated peeks in the roomserver (doh) * fix sql thinko * todo for authenticating state returned by /peek * support returning current state from QueryStateAndAuthChain * handle SS /peek * reimplement SS /peek to prod the RS to tell the FS about the peek * rename RemotePeeks as OutboundPeeks * rename remote_peeks_table as outbound_peeks_table * add perform_handle_remote_peek.go * flesh out federation doc * add inbound peeks table and hook it up * rename ambiguous RemotePeek as InboundPeek * rename FSAPI's PerformPeek as PerformOutboundPeek * setup inbound peeks db correctly * fix api.SendEventWithState with no event * track latestevent on /peek * go fmt * document the peek send stream race better * fix SendEventWithRewrite not to bail if handed a non-state event * add fixme * switch SS /peek to use SendEventWithRewrite * fix comment * use reverse topo ordering to find latest extrem * support postgres for federated peeking * go fmt * back out bogus go.mod change * Fix performOutboundPeekUsingServer * Fix getAuthChain -> GetAuthChain * Fix build issues * Fix build again * Fix getAuthChain -> GetAuthChain * Don't repeat outbound peeks for the same room ID to the same servers * Fix lint * Don't omitempty to appease sytest Co-authored-by: Kegan Dougal <kegan@matrix.org> Co-authored-by: Neil Alexander <neilalexander@users.noreply.github.com>
2021-01-22 14:55:08 +00:00
// Handle an instruction to peek a room on a remote server.
PerformOutboundPeek(
ctx context.Context,
request *PerformOutboundPeekRequest,
response *PerformOutboundPeekResponse,
) error
// Handle an instruction to make_leave & send_leave with a remote server.
PerformLeave(
ctx context.Context,
request *PerformLeaveRequest,
response *PerformLeaveResponse,
) error
// Handle sending an invite to a remote server.
PerformInvite(
ctx context.Context,
request *PerformInviteRequest,
response *PerformInviteResponse,
) error
// Notifies the federation sender that these servers may be online and to retry sending messages.
PerformServersAlive(
ctx context.Context,
request *PerformServersAliveRequest,
response *PerformServersAliveResponse,
) error
// Broadcasts an EDU to all servers in rooms we are joined to.
PerformBroadcastEDU(
ctx context.Context,
request *PerformBroadcastEDURequest,
response *PerformBroadcastEDUResponse,
) error
}
type QueryServerKeysRequest struct {
ServerName gomatrixserverlib.ServerName
KeyIDToCriteria map[gomatrixserverlib.KeyID]gomatrixserverlib.PublicKeyNotaryQueryCriteria
}
func (q *QueryServerKeysRequest) KeyIDs() []gomatrixserverlib.KeyID {
kids := make([]gomatrixserverlib.KeyID, len(q.KeyIDToCriteria))
i := 0
for keyID := range q.KeyIDToCriteria {
kids[i] = keyID
i++
}
return kids
}
type QueryServerKeysResponse struct {
ServerKeys []gomatrixserverlib.ServerKeys
}
type QueryPublicKeysRequest struct {
Requests map[gomatrixserverlib.PublicKeyLookupRequest]gomatrixserverlib.Timestamp `json:"requests"`
}
type QueryPublicKeysResponse struct {
Results map[gomatrixserverlib.PublicKeyLookupRequest]gomatrixserverlib.PublicKeyLookupResult `json:"results"`
}
type PerformDirectoryLookupRequest struct {
RoomAlias string `json:"room_alias"`
ServerName gomatrixserverlib.ServerName `json:"server_name"`
}
type PerformDirectoryLookupResponse struct {
RoomID string `json:"room_id"`
ServerNames []gomatrixserverlib.ServerName `json:"server_names"`
}
type PerformJoinRequest struct {
RoomID string `json:"room_id"`
UserID string `json:"user_id"`
// The sorted list of servers to try. Servers will be tried sequentially, after de-duplication.
ServerNames types.ServerNames `json:"server_names"`
Content map[string]interface{} `json:"content"`
}
type PerformJoinResponse struct {
JoinedVia gomatrixserverlib.ServerName
LastError *gomatrix.HTTPError
}
Peeking over federation via MSC2444 (#1391) * a very very WIP first cut of peeking via MSC2753. doesn't yet compile or work. needs to actually add the peeking block into the sync response. checking in now before it gets any bigger, and to gather any initial feedback on the vague shape of it. * make PeekingDeviceSet private * add server_name param * blind stab at adding a `peek` section to /sync * make it build * make it launch * add peeking to getResponseWithPDUsForCompleteSync * cancel any peeks when we join a room * spell out how to runoutside of docker if you want speed * fix SQL * remove unnecessary txn for SelectPeeks * fix s/join/peek/ cargocult fail * HACK: Track goroutine IDs to determine when we write by the wrong thread To use: set `DENDRITE_TRACE_SQL=1` then grep for `unsafe` * Track partition offsets and only log unsafe for non-selects * Put redactions in the writer goroutine * Update filters on writer goroutine * wrap peek storage in goid hack * use exclusive writer, and MarkPeeksAsOld more efficiently * don't log ascii in binary at sql trace... * strip out empty roomd deltas * re-add txn to SelectPeeks * re-add accidentally deleted field * reject peeks for non-worldreadable rooms * move perform_peek * fix package * correctly refactor perform_peek * WIP of implementing MSC2444 * typo * Revert "Merge branch 'kegan/HACK-goid-sqlite-db-is-locked' into matthew/peeking" This reverts commit 3cebd8dbfbccdf82b7930b7b6eda92095ca6ef41, reversing changes made to ed4b3a58a7855acc43530693cc855b439edf9c7c. * (almost) make it build * clean up bad merge * support SendEventWithState with optional event * fix build & lint * fix build & lint * reinstate federated peeks in the roomserver (doh) * fix sql thinko * todo for authenticating state returned by /peek * support returning current state from QueryStateAndAuthChain * handle SS /peek * reimplement SS /peek to prod the RS to tell the FS about the peek * rename RemotePeeks as OutboundPeeks * rename remote_peeks_table as outbound_peeks_table * add perform_handle_remote_peek.go * flesh out federation doc * add inbound peeks table and hook it up * rename ambiguous RemotePeek as InboundPeek * rename FSAPI's PerformPeek as PerformOutboundPeek * setup inbound peeks db correctly * fix api.SendEventWithState with no event * track latestevent on /peek * go fmt * document the peek send stream race better * fix SendEventWithRewrite not to bail if handed a non-state event * add fixme * switch SS /peek to use SendEventWithRewrite * fix comment * use reverse topo ordering to find latest extrem * support postgres for federated peeking * go fmt * back out bogus go.mod change * Fix performOutboundPeekUsingServer * Fix getAuthChain -> GetAuthChain * Fix build issues * Fix build again * Fix getAuthChain -> GetAuthChain * Don't repeat outbound peeks for the same room ID to the same servers * Fix lint * Don't omitempty to appease sytest Co-authored-by: Kegan Dougal <kegan@matrix.org> Co-authored-by: Neil Alexander <neilalexander@users.noreply.github.com>
2021-01-22 14:55:08 +00:00
type PerformOutboundPeekRequest struct {
RoomID string `json:"room_id"`
// The sorted list of servers to try. Servers will be tried sequentially, after de-duplication.
ServerNames types.ServerNames `json:"server_names"`
}
type PerformOutboundPeekResponse struct {
LastError *gomatrix.HTTPError
}
type PerformLeaveRequest struct {
RoomID string `json:"room_id"`
UserID string `json:"user_id"`
ServerNames types.ServerNames `json:"server_names"`
}
type PerformLeaveResponse struct {
}
type PerformInviteRequest struct {
RoomVersion gomatrixserverlib.RoomVersion `json:"room_version"`
Event *gomatrixserverlib.HeaderedEvent `json:"event"`
InviteRoomState []gomatrixserverlib.InviteV2StrippedState `json:"invite_room_state"`
}
type PerformInviteResponse struct {
Event *gomatrixserverlib.HeaderedEvent `json:"event"`
}
type PerformServersAliveRequest struct {
Servers []gomatrixserverlib.ServerName
}
type PerformServersAliveResponse struct {
}
2020-06-11 15:07:16 +01:00
// QueryJoinedHostServerNamesInRoomRequest is a request to QueryJoinedHostServerNames
type QueryJoinedHostServerNamesInRoomRequest struct {
RoomID string `json:"room_id"`
ExcludeSelf bool `json:"exclude_self"`
}
2020-06-11 15:07:16 +01:00
// QueryJoinedHostServerNamesInRoomResponse is a response to QueryJoinedHostServerNames
type QueryJoinedHostServerNamesInRoomResponse struct {
ServerNames []gomatrixserverlib.ServerName `json:"server_names"`
}
type PerformBroadcastEDURequest struct {
}
type PerformBroadcastEDUResponse struct {
}
type InputPublicKeysRequest struct {
Keys map[gomatrixserverlib.PublicKeyLookupRequest]gomatrixserverlib.PublicKeyLookupResult `json:"keys"`
}
type InputPublicKeysResponse struct {
}