Files
Warp/server/internal/storage/sqlstore/push.go
T
tajniak81andClaude Opus 5.5 487e0f410b
CI / Test (ubuntu-latest) (push) Canceled after 0s
CI / Test (windows-latest) (push) Canceled after 0s
CI / Storage tests on PostgreSQL (push) Canceled after 0s
CI / Complement (federation off) (push) Canceled after 0s
CI / golangci-lint (push) Canceled after 0s
CI / Smoke test the binary (push) Canceled after 0s
Phase 10: hardening and ops
Implements PLAN.md Phase 10.

Simplified Sliding Sync (MSC4186) is served at the unstable
org.matrix.simplified_msc3575 endpoint and advertised in /versions. Lists
are sorted by activity and filtered by DM, invite, encryption, room type,
space and tag; room subscriptions, required_state with wildcards, $ME and
$LAZY, and the to_device, e2ee, account_data, receipts and typing
extensions are supported. Per-connection state is kept in memory and an
unknown pos answers M_UNKNOWN_POS.

Threads and relations: m.relates_to is indexed on roomserver_events
(migration 0012), /relations (with recursion) and /threads are served, and
every event a timeline read returns carries its m.thread, m.replace and
m.reference summaries in unsigned.m.relations. Notifications carry a
thread ID (migration 0013): threaded receipts clear only their thread, and
sync reports unread_thread_notifications when the filter asks.

Spaces: /hierarchy walks a space breadth first, asking other servers about
rooms this one is not in through the new federation hierarchy endpoint;
room_summary describes one room. /search runs on FTS5 (sqlite, pocketbase)
or tsvector (postgres), bounded to what each user may see, with context,
profiles, state, grouping and paging.

The PocketBase driver is real: the sqlite schema and store on an embedded
PocketBase app's database, with media in its filesystem, local or S3
(database.pocketbase.s3). It runs the full storage test suite.

Ops: OpenTelemetry tracing over OTLP/HTTP (tracing.*), with server spans
per route, component spans, and trace propagation on federation, push and
application service calls. New metrics for persisted events, waiting
syncs, sliding sync connections and the database pool, with a Grafana
dashboard. deploy/ adds a Compose setup (PostgreSQL, Prometheus, Grafana,
Jaeger) and a Helm chart; cmd/warp-loadtest loads a server and reports
request and delivery latencies.

The load tester found a long-standing bug, fixed here: on a server where
no account data had been written, every incremental /sync re-sent the push
rules and returned at once, and an all-zero token was taken for an initial
sync, so long polls became busy loops.

The PostgreSQL migrations and search dialect compile but were not run
against a live PostgreSQL in this change.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-17 20:21:31 +02:00

429 lines
15 KiB
Go

package sqlstore
import (
"context"
"database/sql"
"fmt"
"github.com/dariuszjaniak/warp/server/internal/storage"
)
// The push store's sequence table and its one counter.
const (
pushSequences = "push_sequences"
seqNotification = "notification"
)
// Push is the shared implementation of storage.PushStore.
type Push struct {
db *sql.DB
rebind func(string) string
}
// NewPush builds a push store.
func NewPush(db *sql.DB, rebind func(string) string) *Push {
if rebind == nil {
rebind = func(query string) string { return query }
}
return &Push{db: db, rebind: rebind}
}
func (s *Push) q(query string) string { return s.rebind(query) }
// tx runs fn in a transaction, rolling back on any error.
func (s *Push) tx(ctx context.Context, fn func(*sql.Tx) error) error {
tx, err := s.db.BeginTx(ctx, nil)
if err != nil {
return fmt.Errorf("begin transaction: %w", err)
}
defer func() { _ = tx.Rollback() }()
if err := fn(tx); err != nil {
return err
}
if err := tx.Commit(); err != nil {
return fmt.Errorf("commit transaction: %w", err)
}
return nil
}
const (
pusherColumns = `localpart, app_id, pushkey, device_id, kind, app_display_name,
device_display_name, profile_tag, lang, data_json, pushkey_ts_ms`
selectPushersSQL = `SELECT ` + pusherColumns + ` FROM push_pushers
WHERE localpart = ? ORDER BY app_id, pushkey`
upsertPusherSQL = `INSERT INTO push_pushers (` + pusherColumns + `)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
ON CONFLICT (localpart, app_id, pushkey) DO UPDATE SET
device_id = excluded.device_id,
kind = excluded.kind,
app_display_name = excluded.app_display_name,
device_display_name = excluded.device_display_name,
profile_tag = excluded.profile_tag,
lang = excluded.lang,
data_json = excluded.data_json,
pushkey_ts_ms = excluded.pushkey_ts_ms`
deleteOtherUsersPushersSQL = `DELETE FROM push_pushers
WHERE app_id = ? AND pushkey = ? AND localpart <> ?`
deletePusherSQL = `DELETE FROM push_pushers
WHERE localpart = ? AND app_id = ? AND pushkey = ?`
deleteAllPushersSQL = `DELETE FROM push_pushers WHERE localpart = ?`
)
// Pushers implements storage.PushStore.
func (s *Push) Pushers(ctx context.Context, localpart string) ([]storage.Pusher, error) {
rows, err := s.db.QueryContext(ctx, s.q(selectPushersSQL), localpart)
if err != nil {
return nil, fmt.Errorf("read the pushers of %q: %w", localpart, err)
}
defer func() { _ = rows.Close() }()
var out []storage.Pusher
for rows.Next() {
var p storage.Pusher
var data string
if err := rows.Scan(&p.Localpart, &p.AppID, &p.PushKey, &p.DeviceID, &p.Kind, &p.AppDisplayName,
&p.DeviceDisplayName, &p.ProfileTag, &p.Lang, &data, &p.PushKeyTSMS); err != nil {
return nil, fmt.Errorf("read the pushers of %q: %w", localpart, err)
}
p.Data = []byte(data)
out = append(out, p)
}
if err := rows.Err(); err != nil {
return nil, fmt.Errorf("read the pushers of %q: %w", localpart, err)
}
return out, nil
}
// SetPusher implements storage.PushStore.
func (s *Push) SetPusher(ctx context.Context, p storage.Pusher, appendOthers bool) error {
return s.tx(ctx, func(tx *sql.Tx) error {
if !appendOthers {
if _, err := tx.ExecContext(ctx, s.q(deleteOtherUsersPushersSQL), p.AppID, p.PushKey, p.Localpart); err != nil {
return fmt.Errorf("remove other users' pushers for the key: %w", err)
}
}
if _, err := tx.ExecContext(ctx, s.q(upsertPusherSQL), p.Localpart, p.AppID, p.PushKey, p.DeviceID, p.Kind,
p.AppDisplayName, p.DeviceDisplayName, p.ProfileTag, p.Lang, string(p.Data), p.PushKeyTSMS); err != nil {
return fmt.Errorf("write the pusher of %q: %w", p.Localpart, err)
}
return nil
})
}
// DeletePusher implements storage.PushStore.
func (s *Push) DeletePusher(ctx context.Context, localpart, appID, pushKey string) error {
if _, err := s.db.ExecContext(ctx, s.q(deletePusherSQL), localpart, appID, pushKey); err != nil {
return fmt.Errorf("delete a pusher of %q: %w", localpart, err)
}
return nil
}
// DeletePushersForDevices implements storage.PushStore.
func (s *Push) DeletePushersForDevices(ctx context.Context, localpart string, deviceIDs []string) error {
query, args := deleteAllPushersSQL, []any{localpart}
if len(deviceIDs) > 0 {
query += ` AND device_id IN (` + placeholders(len(deviceIDs)) + `)`
for _, id := range deviceIDs {
args = append(args, id)
}
}
if _, err := s.db.ExecContext(ctx, s.q(query), args...); err != nil {
return fmt.Errorf("delete the pushers of %q's devices: %w", localpart, err)
}
return nil
}
// The sums are cast back to BIGINT because PostgreSQL widens SUM(BIGINT)
// to NUMERIC, which does not scan into an int64.
const (
insertNotificationSQL = `INSERT INTO push_notifications
(id, user_id, room_id, event_id, event_pos, thread_id, ts_ms, highlight, actions, is_read)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)`
bumpRoomCountsSQL = `INSERT INTO push_room_counts
(user_id, room_id, notification_count, highlight_count, stream_pos)
VALUES (?, ?, 1, ?, ?)
ON CONFLICT (user_id, room_id) DO UPDATE SET
notification_count = push_room_counts.notification_count + 1,
highlight_count = push_room_counts.highlight_count + excluded.highlight_count,
stream_pos = excluded.stream_pos`
markReadSQL = `UPDATE push_notifications SET is_read = ?
WHERE user_id = ? AND room_id = ? AND is_read = ? AND event_pos <= ?`
// markThreadReadSQL is markReadSQL for one thread, or for the main
// timeline as thread ''.
markThreadReadSQL = markReadSQL + ` AND thread_id = ?`
countUnreadSQL = `SELECT COUNT(*), CAST(COALESCE(SUM(CASE WHEN highlight THEN 1 ELSE 0 END), 0) AS BIGINT)
FROM push_notifications WHERE user_id = ? AND room_id = ? AND is_read = ?`
setRoomCountsSQL = `INSERT INTO push_room_counts
(user_id, room_id, notification_count, highlight_count, stream_pos)
VALUES (?, ?, ?, ?, ?)
ON CONFLICT (user_id, room_id) DO UPDATE SET
notification_count = excluded.notification_count,
highlight_count = excluded.highlight_count,
stream_pos = excluded.stream_pos`
selectCountChangesSQL = `SELECT room_id FROM push_room_counts
WHERE user_id = ? AND stream_pos > ? AND stream_pos <= ? ORDER BY room_id`
selectUnreadTotalSQL = `SELECT CAST(COALESCE(SUM(notification_count), 0) AS BIGINT)
FROM push_room_counts WHERE user_id = ?`
notificationColumns = `id, user_id, room_id, event_id, event_pos, thread_id, ts_ms, highlight, actions, is_read`
pruneNotificationsSQL = `DELETE FROM push_notifications WHERE is_read = ? AND ts_ms < ?`
)
// AddNotifications implements storage.PushStore.
//
// Every notification takes a position of its own, which is both its ID
// and the stamp on its room's counts: a sync that has seen a position has
// seen every count change at or below it.
func (s *Push) AddNotifications(ctx context.Context, ns []storage.NewNotification) (int64, error) {
if len(ns) == 0 {
return currentSequence(ctx, s.db, s.q, pushSequences, seqNotification)
}
var last int64
err := s.tx(ctx, func(tx *sql.Tx) error {
for _, n := range ns {
pos, err := nextSequence(ctx, tx, s.q, pushSequences, seqNotification)
if err != nil {
return err
}
if _, err := tx.ExecContext(ctx, s.q(insertNotificationSQL), pos, n.UserID, n.RoomID, n.EventID,
n.EventPos, n.ThreadID, n.TimestampMS, n.Highlight, string(n.Actions), false); err != nil {
return fmt.Errorf("write a notification for %q: %w", n.UserID, err)
}
highlight := 0
if n.Highlight {
highlight = 1
}
if _, err := tx.ExecContext(ctx, s.q(bumpRoomCountsSQL), n.UserID, n.RoomID, highlight, pos); err != nil {
return fmt.Errorf("count a notification for %q: %w", n.UserID, err)
}
last = pos
}
return nil
})
return last, err
}
// MarkNotificationsRead implements storage.PushStore.
//
// The counts are recounted from the rows that are still unread rather than
// decremented, so that whatever got them out of step — a crash between
// two writes of an older version, a row pruned by hand — is put right by
// the next receipt. The room's counts stay the room's total across every
// thread whichever thread the receipt read.
func (s *Push) MarkNotificationsRead(ctx context.Context, userID, roomID, thread string, upTo int64) (int64, bool, error) {
var (
pos int64
moved bool
)
err := s.tx(ctx, func(tx *sql.Tx) error {
query, args := markReadSQL, []any{true, userID, roomID, false, upTo}
if thread != storage.AllThreads {
query, args = markThreadReadSQL, append(args, thread)
}
res, err := tx.ExecContext(ctx, s.q(query), args...)
if err != nil {
return fmt.Errorf("mark %q's notifications read: %w", userID, err)
}
n, err := res.RowsAffected()
if err != nil {
return fmt.Errorf("mark %q's notifications read: %w", userID, err)
}
if n == 0 {
pos, err = currentSequence(ctx, tx, s.q, pushSequences, seqNotification)
return err
}
var notifications, highlights int64
if err := tx.QueryRowContext(ctx, s.q(countUnreadSQL), userID, roomID, false).
Scan(&notifications, &highlights); err != nil {
return fmt.Errorf("count %q's unread notifications: %w", userID, err)
}
if pos, err = nextSequence(ctx, tx, s.q, pushSequences, seqNotification); err != nil {
return err
}
if _, err := tx.ExecContext(ctx, s.q(setRoomCountsSQL), userID, roomID, notifications, highlights, pos); err != nil {
return fmt.Errorf("write %q's notification counts: %w", userID, err)
}
moved = true
return nil
})
return pos, moved, err
}
// NotificationCounts implements storage.PushStore.
func (s *Push) NotificationCounts(ctx context.Context, userID string, roomIDs []string) (map[string]storage.NotificationCounts, error) {
out := make(map[string]storage.NotificationCounts, len(roomIDs))
if len(roomIDs) == 0 {
return out, nil
}
for _, id := range roomIDs {
out[id] = storage.NotificationCounts{}
}
query := `SELECT room_id, notification_count, highlight_count FROM push_room_counts
WHERE user_id = ? AND room_id IN (` + placeholders(len(roomIDs)) + `)`
args := make([]any, 0, len(roomIDs)+1)
args = append(args, userID)
for _, id := range roomIDs {
args = append(args, id)
}
rows, err := s.db.QueryContext(ctx, s.q(query), args...)
if err != nil {
return nil, fmt.Errorf("read %q's notification counts: %w", userID, err)
}
defer func() { _ = rows.Close() }()
for rows.Next() {
var roomID string
var c storage.NotificationCounts
if err := rows.Scan(&roomID, &c.Notifications, &c.Highlights); err != nil {
return nil, fmt.Errorf("read %q's notification counts: %w", userID, err)
}
out[roomID] = c
}
if err := rows.Err(); err != nil {
return nil, fmt.Errorf("read %q's notification counts: %w", userID, err)
}
return out, nil
}
// ThreadNotificationCounts implements storage.PushStore.
//
// These are counted from the unread rows rather than kept like the room
// totals: a room has few unread notifications at a time, they are a range
// of an index, and a table of per-thread counts would be one more thing
// every write and every receipt has to keep in step.
func (s *Push) ThreadNotificationCounts(ctx context.Context, userID string, roomIDs []string) (map[string]map[string]storage.NotificationCounts, error) {
out := make(map[string]map[string]storage.NotificationCounts, len(roomIDs))
if len(roomIDs) == 0 {
return out, nil
}
query := `SELECT room_id, thread_id, COUNT(*),
CAST(COALESCE(SUM(CASE WHEN highlight THEN 1 ELSE 0 END), 0) AS BIGINT)
FROM push_notifications
WHERE user_id = ? AND is_read = ? AND room_id IN (` + placeholders(len(roomIDs)) + `)
GROUP BY room_id, thread_id`
args := make([]any, 0, len(roomIDs)+2)
args = append(args, userID, false)
for _, id := range roomIDs {
args = append(args, id)
}
rows, err := s.db.QueryContext(ctx, s.q(query), args...)
if err != nil {
return nil, fmt.Errorf("read %q's thread notification counts: %w", userID, err)
}
defer func() { _ = rows.Close() }()
for rows.Next() {
var roomID, thread string
var notifications, highlights int64
if err := rows.Scan(&roomID, &thread, &notifications, &highlights); err != nil {
return nil, fmt.Errorf("read %q's thread notification counts: %w", userID, err)
}
if out[roomID] == nil {
out[roomID] = map[string]storage.NotificationCounts{}
}
out[roomID][thread] = storage.NotificationCounts{
Notifications: int(notifications),
Highlights: int(highlights),
}
}
if err := rows.Err(); err != nil {
return nil, fmt.Errorf("read %q's thread notification counts: %w", userID, err)
}
return out, nil
}
// NotificationCountChanges implements storage.PushStore.
func (s *Push) NotificationCountChanges(ctx context.Context, userID string, from, to int64) ([]string, error) {
rows, err := s.db.QueryContext(ctx, s.q(selectCountChangesSQL), userID, from, to)
if err != nil {
return nil, fmt.Errorf("read %q's notification count changes: %w", userID, err)
}
defer func() { _ = rows.Close() }()
var out []string
for rows.Next() {
var roomID string
if err := rows.Scan(&roomID); err != nil {
return nil, fmt.Errorf("read %q's notification count changes: %w", userID, err)
}
out = append(out, roomID)
}
if err := rows.Err(); err != nil {
return nil, fmt.Errorf("read %q's notification count changes: %w", userID, err)
}
return out, nil
}
// UnreadNotifications implements storage.PushStore.
func (s *Push) UnreadNotifications(ctx context.Context, userID string) (int, error) {
var n int64
if err := s.db.QueryRowContext(ctx, s.q(selectUnreadTotalSQL), userID).Scan(&n); err != nil {
return 0, fmt.Errorf("count %q's unread notifications: %w", userID, err)
}
return int(n), nil
}
// Notifications implements storage.PushStore.
func (s *Push) Notifications(ctx context.Context, userID string, before int64, limit int, onlyHighlight bool) ([]storage.Notification, error) {
query := `SELECT ` + notificationColumns + ` FROM push_notifications WHERE user_id = ?`
args := []any{userID}
if before > 0 {
query += ` AND id < ?`
args = append(args, before)
}
if onlyHighlight {
query += ` AND highlight = ?`
args = append(args, true)
}
query += ` ORDER BY id DESC LIMIT ?`
args = append(args, limit)
rows, err := s.db.QueryContext(ctx, s.q(query), args...)
if err != nil {
return nil, fmt.Errorf("read %q's notifications: %w", userID, err)
}
defer func() { _ = rows.Close() }()
var out []storage.Notification
for rows.Next() {
var n storage.Notification
var actions string
if err := rows.Scan(&n.ID, &n.UserID, &n.RoomID, &n.EventID, &n.EventPos, &n.ThreadID, &n.TimestampMS,
&n.Highlight, &actions, &n.Read); err != nil {
return nil, fmt.Errorf("read %q's notifications: %w", userID, err)
}
n.Actions = []byte(actions)
out = append(out, n)
}
if err := rows.Err(); err != nil {
return nil, fmt.Errorf("read %q's notifications: %w", userID, err)
}
return out, nil
}
// PruneNotifications implements storage.PushStore.
func (s *Push) PruneNotifications(ctx context.Context, beforeMS int64) (int64, error) {
res, err := s.db.ExecContext(ctx, s.q(pruneNotificationsSQL), true, beforeMS)
if err != nil {
return 0, fmt.Errorf("prune read notifications: %w", err)
}
n, err := res.RowsAffected()
if err != nil {
return 0, fmt.Errorf("prune read notifications: %w", err)
}
return n, nil
}