168 lines
4.6 KiB
Go
Raw Normal View History

add extensions for typing and receipts; bugfixes and additional perf improvements Features: - Add `typing` extension. - Add `receipts` extension. - Add comprehensive prometheus `/metrics` activated via `SYNCV3_PROM`. - Add `SYNCV3_PPROF` support. - Add `by_notification_level` sort order. - Add `include_old_rooms` support. - Add support for `$ME` and `$LAZY`. - Add correct filtering when `*,*` is used as `required_state`. - Add `num_live` to each room response to indicate how many timeline entries are live. Bug fixes: - Use a stricter comparison function on ranges: fixes an issue whereby UTs fail on go1.19 due to change in sorting algorithm. - Send back an `errcode` on HTTP errors (e.g expired sessions). - Remove `unsigned.txn_id` on insertion into the DB. Otherwise other users would see other users txn IDs :( - Improve range delta algorithm: previously it didn't handle cases like `[0,20] -> [20,30]` and would panic. - Send HTTP 400 for invalid range requests. - Don't publish no-op unread counts which just adds extra noise. - Fix leaking DB connections which could eventually consume all available connections. - Ensure we always unblock WaitUntilInitialSync even on invalid access tokens. Other code relies on WaitUntilInitialSync() actually returning at _some_ point e.g on startup we have N workers which bound the number of concurrent pollers made at any one time, we need to not just hog a worker forever. Improvements: - Greatly improve startup times of sync3 handlers by improving `JoinedRoomsTracker`: a modest amount of data would take ~28s to create the handler, now it takes 4s. - Massively improve initial initial v3 sync times, by refactoring `JoinedRoomsTracker`, from ~47s to <1s. - Add `SlidingSyncUntil...` in tests to reduce races. - Tweak the API shape of JoinedUsersForRoom to reduce state block processing time for large rooms from 63s to 39s. - Add trace task for initial syncs. - Include the proxy version in UA strings. - HTTP errors now wait 1s before returning to stop clients tight-looping on error. - Pending event buffer is now 2000. - Index the room ID first to cull the most events when returning timeline entries. Speeds up `SelectLatestEventsBetween` by a factor of 8. - Remove cancelled `m.room_key_requests` from the to-device inbox. Cuts down the amount of events in the inbox by ~94% for very large (20k+) inboxes, ~50% for moderate sized (200 events) inboxes. Adds book-keeping to remember the unacked to-device position for each client.
2022-12-14 18:53:55 +00:00
package syncv3
import (
"io/ioutil"
"net/http"
"net/http/httptest"
"strings"
"testing"
"time"
slidingsync "github.com/matrix-org/sliding-sync"
"github.com/matrix-org/sliding-sync/sync2"
"github.com/matrix-org/sliding-sync/sync3"
"github.com/matrix-org/sliding-sync/testutils"
add extensions for typing and receipts; bugfixes and additional perf improvements Features: - Add `typing` extension. - Add `receipts` extension. - Add comprehensive prometheus `/metrics` activated via `SYNCV3_PROM`. - Add `SYNCV3_PPROF` support. - Add `by_notification_level` sort order. - Add `include_old_rooms` support. - Add support for `$ME` and `$LAZY`. - Add correct filtering when `*,*` is used as `required_state`. - Add `num_live` to each room response to indicate how many timeline entries are live. Bug fixes: - Use a stricter comparison function on ranges: fixes an issue whereby UTs fail on go1.19 due to change in sorting algorithm. - Send back an `errcode` on HTTP errors (e.g expired sessions). - Remove `unsigned.txn_id` on insertion into the DB. Otherwise other users would see other users txn IDs :( - Improve range delta algorithm: previously it didn't handle cases like `[0,20] -> [20,30]` and would panic. - Send HTTP 400 for invalid range requests. - Don't publish no-op unread counts which just adds extra noise. - Fix leaking DB connections which could eventually consume all available connections. - Ensure we always unblock WaitUntilInitialSync even on invalid access tokens. Other code relies on WaitUntilInitialSync() actually returning at _some_ point e.g on startup we have N workers which bound the number of concurrent pollers made at any one time, we need to not just hog a worker forever. Improvements: - Greatly improve startup times of sync3 handlers by improving `JoinedRoomsTracker`: a modest amount of data would take ~28s to create the handler, now it takes 4s. - Massively improve initial initial v3 sync times, by refactoring `JoinedRoomsTracker`, from ~47s to <1s. - Add `SlidingSyncUntil...` in tests to reduce races. - Tweak the API shape of JoinedUsersForRoom to reduce state block processing time for large rooms from 63s to 39s. - Add trace task for initial syncs. - Include the proxy version in UA strings. - HTTP errors now wait 1s before returning to stop clients tight-looping on error. - Pending event buffer is now 2000. - Index the room ID first to cull the most events when returning timeline entries. Speeds up `SelectLatestEventsBetween` by a factor of 8. - Remove cancelled `m.room_key_requests` from the to-device inbox. Cuts down the amount of events in the inbox by ~94% for very large (20k+) inboxes, ~50% for moderate sized (200 events) inboxes. Adds book-keeping to remember the unacked to-device position for each client.
2022-12-14 18:53:55 +00:00
"github.com/prometheus/client_golang/prometheus/promhttp"
)
func runMetricsServer(t *testing.T) *httptest.Server {
return httptest.NewServer(promhttp.Handler())
}
func getMetrics(t *testing.T, srv *httptest.Server) []string {
t.Helper()
req, err := http.NewRequest("GET", srv.URL+"/metrics", nil)
if err != nil {
t.Fatalf("failed to make metrics request: %s", err)
}
res, err := srv.Client().Do(req)
if err != nil {
t.Fatalf("failed to perform metrics request: %s", err)
}
if res.StatusCode != 200 {
t.Fatalf("/metrics returned HTTP %d", res.StatusCode)
}
defer res.Body.Close()
blob, err := ioutil.ReadAll(res.Body)
if err != nil {
t.Fatalf("/metrics failed to read response body: %s", err)
}
return strings.Split(string(blob), "\n")
}
func assertMetric(t *testing.T, lines []string, key string, val string) {
t.Helper()
for _, line := range lines {
if !strings.HasPrefix(line, key+" ") {
continue
}
segments := strings.Split(line, " ")
if val != segments[1] {
t.Errorf("want '%v %v' got '%v'", key, val, line)
}
return
}
t.Errorf("did not find key '%v' in %d lines", key, len(lines))
}
func TestMetricsNumPollers(t *testing.T) {
metricKey := "sliding_sync_poller_num_pollers"
pqString := testutils.PrepareDBConnectionString()
// setup code
v2 := runTestV2Server(t)
v3 := runTestServer(t, v2, pqString, slidingsync.Opts{
AddPrometheusMetrics: true,
})
add extensions for typing and receipts; bugfixes and additional perf improvements Features: - Add `typing` extension. - Add `receipts` extension. - Add comprehensive prometheus `/metrics` activated via `SYNCV3_PROM`. - Add `SYNCV3_PPROF` support. - Add `by_notification_level` sort order. - Add `include_old_rooms` support. - Add support for `$ME` and `$LAZY`. - Add correct filtering when `*,*` is used as `required_state`. - Add `num_live` to each room response to indicate how many timeline entries are live. Bug fixes: - Use a stricter comparison function on ranges: fixes an issue whereby UTs fail on go1.19 due to change in sorting algorithm. - Send back an `errcode` on HTTP errors (e.g expired sessions). - Remove `unsigned.txn_id` on insertion into the DB. Otherwise other users would see other users txn IDs :( - Improve range delta algorithm: previously it didn't handle cases like `[0,20] -> [20,30]` and would panic. - Send HTTP 400 for invalid range requests. - Don't publish no-op unread counts which just adds extra noise. - Fix leaking DB connections which could eventually consume all available connections. - Ensure we always unblock WaitUntilInitialSync even on invalid access tokens. Other code relies on WaitUntilInitialSync() actually returning at _some_ point e.g on startup we have N workers which bound the number of concurrent pollers made at any one time, we need to not just hog a worker forever. Improvements: - Greatly improve startup times of sync3 handlers by improving `JoinedRoomsTracker`: a modest amount of data would take ~28s to create the handler, now it takes 4s. - Massively improve initial initial v3 sync times, by refactoring `JoinedRoomsTracker`, from ~47s to <1s. - Add `SlidingSyncUntil...` in tests to reduce races. - Tweak the API shape of JoinedUsersForRoom to reduce state block processing time for large rooms from 63s to 39s. - Add trace task for initial syncs. - Include the proxy version in UA strings. - HTTP errors now wait 1s before returning to stop clients tight-looping on error. - Pending event buffer is now 2000. - Index the room ID first to cull the most events when returning timeline entries. Speeds up `SelectLatestEventsBetween` by a factor of 8. - Remove cancelled `m.room_key_requests` from the to-device inbox. Cuts down the amount of events in the inbox by ~94% for very large (20k+) inboxes, ~50% for moderate sized (200 events) inboxes. Adds book-keeping to remember the unacked to-device position for each client.
2022-12-14 18:53:55 +00:00
defer v2.close()
defer v3.close()
metricsServer := runMetricsServer(t)
defer metricsServer.Close()
metrics := getMetrics(t, metricsServer)
assertMetric(t, metrics, metricKey, "0")
// start a poller
v2.addAccount(t, alice, aliceToken)
add extensions for typing and receipts; bugfixes and additional perf improvements Features: - Add `typing` extension. - Add `receipts` extension. - Add comprehensive prometheus `/metrics` activated via `SYNCV3_PROM`. - Add `SYNCV3_PPROF` support. - Add `by_notification_level` sort order. - Add `include_old_rooms` support. - Add support for `$ME` and `$LAZY`. - Add correct filtering when `*,*` is used as `required_state`. - Add `num_live` to each room response to indicate how many timeline entries are live. Bug fixes: - Use a stricter comparison function on ranges: fixes an issue whereby UTs fail on go1.19 due to change in sorting algorithm. - Send back an `errcode` on HTTP errors (e.g expired sessions). - Remove `unsigned.txn_id` on insertion into the DB. Otherwise other users would see other users txn IDs :( - Improve range delta algorithm: previously it didn't handle cases like `[0,20] -> [20,30]` and would panic. - Send HTTP 400 for invalid range requests. - Don't publish no-op unread counts which just adds extra noise. - Fix leaking DB connections which could eventually consume all available connections. - Ensure we always unblock WaitUntilInitialSync even on invalid access tokens. Other code relies on WaitUntilInitialSync() actually returning at _some_ point e.g on startup we have N workers which bound the number of concurrent pollers made at any one time, we need to not just hog a worker forever. Improvements: - Greatly improve startup times of sync3 handlers by improving `JoinedRoomsTracker`: a modest amount of data would take ~28s to create the handler, now it takes 4s. - Massively improve initial initial v3 sync times, by refactoring `JoinedRoomsTracker`, from ~47s to <1s. - Add `SlidingSyncUntil...` in tests to reduce races. - Tweak the API shape of JoinedUsersForRoom to reduce state block processing time for large rooms from 63s to 39s. - Add trace task for initial syncs. - Include the proxy version in UA strings. - HTTP errors now wait 1s before returning to stop clients tight-looping on error. - Pending event buffer is now 2000. - Index the room ID first to cull the most events when returning timeline entries. Speeds up `SelectLatestEventsBetween` by a factor of 8. - Remove cancelled `m.room_key_requests` from the to-device inbox. Cuts down the amount of events in the inbox by ~94% for very large (20k+) inboxes, ~50% for moderate sized (200 events) inboxes. Adds book-keeping to remember the unacked to-device position for each client.
2022-12-14 18:53:55 +00:00
v2.queueResponse(alice, sync2.SyncResponse{
Rooms: sync2.SyncRoomsResponse{
Join: v2JoinTimeline(roomEvents{
roomID: "!unimportant",
events: createRoomState(t, alice, time.Now()),
}),
},
})
v3.mustDoV3Request(t, aliceToken, sync3.Request{})
// verify increase
metrics = getMetrics(t, metricsServer)
assertMetric(t, metrics, metricKey, "1")
// start another poller
v2.addAccount(t, bob, bobToken)
add extensions for typing and receipts; bugfixes and additional perf improvements Features: - Add `typing` extension. - Add `receipts` extension. - Add comprehensive prometheus `/metrics` activated via `SYNCV3_PROM`. - Add `SYNCV3_PPROF` support. - Add `by_notification_level` sort order. - Add `include_old_rooms` support. - Add support for `$ME` and `$LAZY`. - Add correct filtering when `*,*` is used as `required_state`. - Add `num_live` to each room response to indicate how many timeline entries are live. Bug fixes: - Use a stricter comparison function on ranges: fixes an issue whereby UTs fail on go1.19 due to change in sorting algorithm. - Send back an `errcode` on HTTP errors (e.g expired sessions). - Remove `unsigned.txn_id` on insertion into the DB. Otherwise other users would see other users txn IDs :( - Improve range delta algorithm: previously it didn't handle cases like `[0,20] -> [20,30]` and would panic. - Send HTTP 400 for invalid range requests. - Don't publish no-op unread counts which just adds extra noise. - Fix leaking DB connections which could eventually consume all available connections. - Ensure we always unblock WaitUntilInitialSync even on invalid access tokens. Other code relies on WaitUntilInitialSync() actually returning at _some_ point e.g on startup we have N workers which bound the number of concurrent pollers made at any one time, we need to not just hog a worker forever. Improvements: - Greatly improve startup times of sync3 handlers by improving `JoinedRoomsTracker`: a modest amount of data would take ~28s to create the handler, now it takes 4s. - Massively improve initial initial v3 sync times, by refactoring `JoinedRoomsTracker`, from ~47s to <1s. - Add `SlidingSyncUntil...` in tests to reduce races. - Tweak the API shape of JoinedUsersForRoom to reduce state block processing time for large rooms from 63s to 39s. - Add trace task for initial syncs. - Include the proxy version in UA strings. - HTTP errors now wait 1s before returning to stop clients tight-looping on error. - Pending event buffer is now 2000. - Index the room ID first to cull the most events when returning timeline entries. Speeds up `SelectLatestEventsBetween` by a factor of 8. - Remove cancelled `m.room_key_requests` from the to-device inbox. Cuts down the amount of events in the inbox by ~94% for very large (20k+) inboxes, ~50% for moderate sized (200 events) inboxes. Adds book-keeping to remember the unacked to-device position for each client.
2022-12-14 18:53:55 +00:00
v2.queueResponse(bob, sync2.SyncResponse{
Rooms: sync2.SyncRoomsResponse{
Join: v2JoinTimeline(roomEvents{
roomID: "!unimportant",
events: createRoomState(t, bob, time.Now()),
}),
},
})
v3.mustDoV3Request(t, bobToken, sync3.Request{})
// verify increase
metrics = getMetrics(t, metricsServer)
assertMetric(t, metrics, metricKey, "2")
// now invalidate a poller
v2.invalidateToken(aliceToken)
// verify decrease
metrics = getMetrics(t, metricsServer)
assertMetric(t, metrics, metricKey, "1")
}
func TestMetricsNumConns(t *testing.T) {
metricKey := "sliding_sync_api_num_active_conns"
pqString := testutils.PrepareDBConnectionString()
// setup code
v2 := runTestV2Server(t)
v3 := runTestServer(t, v2, pqString, slidingsync.Opts{
AddPrometheusMetrics: true,
})
add extensions for typing and receipts; bugfixes and additional perf improvements Features: - Add `typing` extension. - Add `receipts` extension. - Add comprehensive prometheus `/metrics` activated via `SYNCV3_PROM`. - Add `SYNCV3_PPROF` support. - Add `by_notification_level` sort order. - Add `include_old_rooms` support. - Add support for `$ME` and `$LAZY`. - Add correct filtering when `*,*` is used as `required_state`. - Add `num_live` to each room response to indicate how many timeline entries are live. Bug fixes: - Use a stricter comparison function on ranges: fixes an issue whereby UTs fail on go1.19 due to change in sorting algorithm. - Send back an `errcode` on HTTP errors (e.g expired sessions). - Remove `unsigned.txn_id` on insertion into the DB. Otherwise other users would see other users txn IDs :( - Improve range delta algorithm: previously it didn't handle cases like `[0,20] -> [20,30]` and would panic. - Send HTTP 400 for invalid range requests. - Don't publish no-op unread counts which just adds extra noise. - Fix leaking DB connections which could eventually consume all available connections. - Ensure we always unblock WaitUntilInitialSync even on invalid access tokens. Other code relies on WaitUntilInitialSync() actually returning at _some_ point e.g on startup we have N workers which bound the number of concurrent pollers made at any one time, we need to not just hog a worker forever. Improvements: - Greatly improve startup times of sync3 handlers by improving `JoinedRoomsTracker`: a modest amount of data would take ~28s to create the handler, now it takes 4s. - Massively improve initial initial v3 sync times, by refactoring `JoinedRoomsTracker`, from ~47s to <1s. - Add `SlidingSyncUntil...` in tests to reduce races. - Tweak the API shape of JoinedUsersForRoom to reduce state block processing time for large rooms from 63s to 39s. - Add trace task for initial syncs. - Include the proxy version in UA strings. - HTTP errors now wait 1s before returning to stop clients tight-looping on error. - Pending event buffer is now 2000. - Index the room ID first to cull the most events when returning timeline entries. Speeds up `SelectLatestEventsBetween` by a factor of 8. - Remove cancelled `m.room_key_requests` from the to-device inbox. Cuts down the amount of events in the inbox by ~94% for very large (20k+) inboxes, ~50% for moderate sized (200 events) inboxes. Adds book-keeping to remember the unacked to-device position for each client.
2022-12-14 18:53:55 +00:00
defer v2.close()
defer v3.close()
metricsServer := runMetricsServer(t)
defer metricsServer.Close()
metrics := getMetrics(t, metricsServer)
assertMetric(t, metrics, metricKey, "0")
// start a poller
v2.addAccount(t, alice, aliceToken)
add extensions for typing and receipts; bugfixes and additional perf improvements Features: - Add `typing` extension. - Add `receipts` extension. - Add comprehensive prometheus `/metrics` activated via `SYNCV3_PROM`. - Add `SYNCV3_PPROF` support. - Add `by_notification_level` sort order. - Add `include_old_rooms` support. - Add support for `$ME` and `$LAZY`. - Add correct filtering when `*,*` is used as `required_state`. - Add `num_live` to each room response to indicate how many timeline entries are live. Bug fixes: - Use a stricter comparison function on ranges: fixes an issue whereby UTs fail on go1.19 due to change in sorting algorithm. - Send back an `errcode` on HTTP errors (e.g expired sessions). - Remove `unsigned.txn_id` on insertion into the DB. Otherwise other users would see other users txn IDs :( - Improve range delta algorithm: previously it didn't handle cases like `[0,20] -> [20,30]` and would panic. - Send HTTP 400 for invalid range requests. - Don't publish no-op unread counts which just adds extra noise. - Fix leaking DB connections which could eventually consume all available connections. - Ensure we always unblock WaitUntilInitialSync even on invalid access tokens. Other code relies on WaitUntilInitialSync() actually returning at _some_ point e.g on startup we have N workers which bound the number of concurrent pollers made at any one time, we need to not just hog a worker forever. Improvements: - Greatly improve startup times of sync3 handlers by improving `JoinedRoomsTracker`: a modest amount of data would take ~28s to create the handler, now it takes 4s. - Massively improve initial initial v3 sync times, by refactoring `JoinedRoomsTracker`, from ~47s to <1s. - Add `SlidingSyncUntil...` in tests to reduce races. - Tweak the API shape of JoinedUsersForRoom to reduce state block processing time for large rooms from 63s to 39s. - Add trace task for initial syncs. - Include the proxy version in UA strings. - HTTP errors now wait 1s before returning to stop clients tight-looping on error. - Pending event buffer is now 2000. - Index the room ID first to cull the most events when returning timeline entries. Speeds up `SelectLatestEventsBetween` by a factor of 8. - Remove cancelled `m.room_key_requests` from the to-device inbox. Cuts down the amount of events in the inbox by ~94% for very large (20k+) inboxes, ~50% for moderate sized (200 events) inboxes. Adds book-keeping to remember the unacked to-device position for each client.
2022-12-14 18:53:55 +00:00
v2.queueResponse(alice, sync2.SyncResponse{
Rooms: sync2.SyncRoomsResponse{
Join: v2JoinTimeline(roomEvents{
roomID: "!unimportant",
events: createRoomState(t, alice, time.Now()),
}),
},
})
v3.mustDoV3Request(t, aliceToken, sync3.Request{})
// verify increase
metrics = getMetrics(t, metricsServer)
assertMetric(t, metrics, metricKey, "1")
// start another poller
v2.addAccount(t, bob, bobToken)
add extensions for typing and receipts; bugfixes and additional perf improvements Features: - Add `typing` extension. - Add `receipts` extension. - Add comprehensive prometheus `/metrics` activated via `SYNCV3_PROM`. - Add `SYNCV3_PPROF` support. - Add `by_notification_level` sort order. - Add `include_old_rooms` support. - Add support for `$ME` and `$LAZY`. - Add correct filtering when `*,*` is used as `required_state`. - Add `num_live` to each room response to indicate how many timeline entries are live. Bug fixes: - Use a stricter comparison function on ranges: fixes an issue whereby UTs fail on go1.19 due to change in sorting algorithm. - Send back an `errcode` on HTTP errors (e.g expired sessions). - Remove `unsigned.txn_id` on insertion into the DB. Otherwise other users would see other users txn IDs :( - Improve range delta algorithm: previously it didn't handle cases like `[0,20] -> [20,30]` and would panic. - Send HTTP 400 for invalid range requests. - Don't publish no-op unread counts which just adds extra noise. - Fix leaking DB connections which could eventually consume all available connections. - Ensure we always unblock WaitUntilInitialSync even on invalid access tokens. Other code relies on WaitUntilInitialSync() actually returning at _some_ point e.g on startup we have N workers which bound the number of concurrent pollers made at any one time, we need to not just hog a worker forever. Improvements: - Greatly improve startup times of sync3 handlers by improving `JoinedRoomsTracker`: a modest amount of data would take ~28s to create the handler, now it takes 4s. - Massively improve initial initial v3 sync times, by refactoring `JoinedRoomsTracker`, from ~47s to <1s. - Add `SlidingSyncUntil...` in tests to reduce races. - Tweak the API shape of JoinedUsersForRoom to reduce state block processing time for large rooms from 63s to 39s. - Add trace task for initial syncs. - Include the proxy version in UA strings. - HTTP errors now wait 1s before returning to stop clients tight-looping on error. - Pending event buffer is now 2000. - Index the room ID first to cull the most events when returning timeline entries. Speeds up `SelectLatestEventsBetween` by a factor of 8. - Remove cancelled `m.room_key_requests` from the to-device inbox. Cuts down the amount of events in the inbox by ~94% for very large (20k+) inboxes, ~50% for moderate sized (200 events) inboxes. Adds book-keeping to remember the unacked to-device position for each client.
2022-12-14 18:53:55 +00:00
v2.queueResponse(bob, sync2.SyncResponse{
Rooms: sync2.SyncRoomsResponse{
Join: v2JoinTimeline(roomEvents{
roomID: "!unimportant",
events: createRoomState(t, bob, time.Now()),
}),
},
})
res := v3.mustDoV3Request(t, bobToken, sync3.Request{})
// verify increase
metrics = getMetrics(t, metricsServer)
assertMetric(t, metrics, metricKey, "2")
// now live poll -> no increase
res = v3.mustDoV3RequestWithPos(t, bobToken, res.Pos, sync3.Request{
RoomSubscriptions: map[string]sync3.RoomSubscription{
"!foo": { // doesn't matter, just so long as we return quickly
TimelineLimit: 1,
},
},
})
metrics = getMetrics(t, metricsServer)
assertMetric(t, metrics, metricKey, "2")
// now replace conn -> no increase
v3.mustDoV3Request(t, aliceToken, sync3.Request{})
metrics = getMetrics(t, metricsServer)
assertMetric(t, metrics, metricKey, "2")
// TODO: now expire conn -> decrease
}