Files
3x-ui/internal/web/service/client_sync_orphan_test.go
T
mrchatam 6f7a305239 fix(node): stop stale expiry sync from undoing client extensions (#6228) (#6231)
* fix(node): stop stale expiry sync from undoing client extensions (#6228)

After an expired client is extended on the master, a lagging node could
overwrite client_traffics with an older absolute expiry and latch
enable=false. Reject older absolute expiries on merge, ignore
expiry-stale disables when the master is not over quota, lift stale
lifecycle fields out of adopted settings, stamp reconcile fingerprints
from the pre-lift node blob, and mark the node dirty so the next tick
re-pushes.

* fix(node): lockstep client_traffics expiry/enable SQL with review fixes (#6228)

Make expiry merge keep any master absolute (node only activates when master
is unset/duration). Include this tick's up/down deltas in the enable
stale-disable quota check so a crossing-tick disable is not dropped.

* fix(node): add settings absolute helper for renew/lift guards (#6228)

Expose settingsClientAbsoluteExpiry so traffic merge can tell a real
node auto-renew (settings+stats later) from lagging ClientStats after a
master shorten. Trim lift godoc to the invariant.

* fix(node): authority-aware lifecycle merge for multi-node sync (#6228)

While config_dirty, accumulate traffic only — do not adopt node
expiry/enable/total/reset (and preserve dipped baselines so a false
renew cannot fire after clear). On clean ticks, master absolute expiry
wins; node auto-renew still goes through nodeClientRenewed when settings
also show the later deadline. Defer settings lifecycle lift until after
traffic deltas land, align SyncInbound via applyMasterClientLifecycle,
and avoid re-MarkNodeDirty when already dirty.

* fix(node): clear config_dirty only after the post-reconcile traffic merge (#6228)

After a successful ReconcileNode, keep the node dirty through the same
tick's SetRemoteTraffic so lagging ClientStats cannot clobber the
just-pushed master lifecycle, then ClearNodeDirty.

* test(node): cover dirty-gate, master-absolute, and renew false-positives (#6228)

Add regressions for extend/shorten while dirty, clean-sibling shorten,
settings vs lagging disable, renew recovery after dirty, renew with
matching settings, and shorten+Reset lagging stats not treated as renew.

* fix(node): address the review findings on the lifecycle merge (#6228)

The automated review on #6231 flagged a blocking regression and six smaller
issues. All of them are fixed here.

Blocking: making the master's absolute expiry always win left nodeClientRenewed
as the only channel for a node-side auto-renew, and that required a counter dip.
A client that used no traffic in the period never dips, so its renewal was
dropped, the master kept the expired deadline and disableInvalidClients removed
it with no way back (master-side autoRenewClients skips node inbounds). The node
bumps reset_count on every renewal, so that counter is now an independent
renewal signal and is persisted with the renewal so it keeps converging.

The deferred ClearNodeDirty made every reconcile-success tick merge in dirty
mode, which suppressed inbound adoption, new client_traffics rows, the orphan
sweeps and the whole SyncInbound record loop -- and left the node dirty forever
whenever SetRemoteTraffic errored. The clear goes back to where it was; a
separate justPushed flag now freezes only the client lifecycle merge for the
tick whose push just landed.

staleNodeDisable only recognised a lagging disable by an older expiry, so a
quota top-up (raise totalGB, leave the expiry alone) was re-latched to disabled
by the next lagging snapshot -- the #6228 symptom on a second axis. The
reviewer's suggestion of dropping the expiry precondition outright fails
TestNodeQuotaDisable_SameExpiryStillLatches, because the master's own counters
legitimately sit below a node's after a seeded-at-zero adoption. nodeDisableIsStale
instead compares the limits the node judged the client against with the master's
own: matching limits mean a genuine verdict that still latches (#4917), differing
limits mean the node has not seen the master's change yet. It also now measures
the master deadline against wall-clock now, so an expired master row no longer
looks "extended" merely because the node's copy is older still.

Also: the settings lift now writes enable in both directions, so a blob fetched
before a master disable cannot carry enable=true back into central settings and
on to the node; the renewal guard parses the inbound settings once per inbound
instead of once per renewing client; the adoption loop only writes settings when
they actually changed; and two comments that described mechanisms the code does
not use were corrected.

The test deadlines are now relative to the run: the merge compares against now,
so fixed timestamps would have rotted into the wrong side of it.

---------

Co-authored-by: mrchatam <287639636+mrchatam@users.noreply.github.com>
Co-authored-by: Sanaei <ho3ein.sanaei@gmail.com>
2026-08-23 23:17:56 +02:00

149 lines
5.0 KiB
Go

package service
import (
"fmt"
"testing"
"time"
"github.com/mhsanaei/3x-ui/v3/internal/database/model"
"github.com/mhsanaei/3x-ui/v3/internal/xray"
"gorm.io/gorm"
)
func readOrphanMark(t *testing.T, db *gorm.DB, email string) int64 {
t.Helper()
var row model.ClientRecord
if err := db.Where("email = ?", email).First(&row).Error; err != nil {
t.Fatalf("read client %q: %v", email, err)
}
return row.SyncOrphanedAt
}
func backdateOrphanMark(t *testing.T, db *gorm.DB, email string) {
t.Helper()
past := time.Now().Add(-2 * syncOrphanReapGrace).UnixMilli()
if err := db.Model(&model.ClientRecord{}).
Where("email = ?", email).
Update("sync_orphaned_at", past).Error; err != nil {
t.Fatalf("backdate orphan mark: %v", err)
}
}
// The merge must soft-orphan, not delete: everything stays recoverable until
// the grace period has elapsed and the reaper confirms nothing reclaimed it.
func TestSyncOrphanSurvivesMergeUntilGraceElapses(t *testing.T) {
db := initTrafficTestDB(t)
svc := &InboundService{}
clientSvc := &ClientService{}
seedNodeRow(t, db, &model.Node{Id: 1, Name: "n1", Address: "127.0.0.1", Port: 2096, ApiToken: "tok", Enable: true})
const email = "gone@x"
createNodeInboundWithClient(t, db, 1, "n1-in", 41001, email)
settings := fmt.Sprintf(`{"clients":[{"email":%q,"enable":true}]}`, email)
syncNodeWithSettings(t, svc, 1, "n1-in", settings,
xray.ClientTraffic{Email: email, Up: 5, Down: 5, Enable: true})
if rec, traf := countClientRows(t, db, email); rec != 1 || traf != 1 {
t.Fatalf("setup: clients=%d client_traffics=%d, want 1/1", rec, traf)
}
if _, err := svc.setRemoteTrafficLocked(1, snapshotWithoutClients(t, "n1-in"), false, false); err != nil {
t.Fatalf("orphaning merge: %v", err)
}
if rec, traf := countClientRows(t, db, email); rec != 1 || traf != 1 {
t.Fatalf("merge hard-deleted the client: clients=%d client_traffics=%d, want 1/1", rec, traf)
}
if readOrphanMark(t, db, email) <= 0 {
t.Fatal("merge did not stamp sync_orphaned_at")
}
reaped, err := clientSvc.ReapSyncOrphans()
if err != nil {
t.Fatalf("reap inside grace: %v", err)
}
if reaped != 0 {
t.Fatalf("reaped %d client(s) inside the grace period, want 0", reaped)
}
if rec, _ := countClientRows(t, db, email); rec != 1 {
t.Fatal("client removed before the grace period elapsed")
}
backdateOrphanMark(t, db, email)
reaped, err = clientSvc.ReapSyncOrphans()
if err != nil {
t.Fatalf("reap after grace: %v", err)
}
if reaped != 1 {
t.Fatalf("reaped %d client(s) after the grace period, want 1", reaped)
}
rec, traf := countClientRows(t, db, email)
if rec != 0 || traf != 0 {
t.Fatalf("after reap: clients=%d client_traffics=%d, want 0/0", rec, traf)
}
}
// A client the node reports again was never gone: clearing the mark is what
// turns a bad merge into a recoverable blip instead of a delayed deletion.
func TestSyncOrphanMarkClearedOnReattach(t *testing.T) {
db := initTrafficTestDB(t)
svc := &InboundService{}
clientSvc := &ClientService{}
seedNodeRow(t, db, &model.Node{Id: 1, Name: "n1", Address: "127.0.0.1", Port: 2096, ApiToken: "tok", Enable: true})
const email = "flaky@x"
createNodeInboundWithClient(t, db, 1, "n1-in", 41001, email)
settings := fmt.Sprintf(`{"clients":[{"email":%q,"enable":true}]}`, email)
syncNodeWithSettings(t, svc, 1, "n1-in", settings,
xray.ClientTraffic{Email: email, Up: 5, Down: 5, Enable: true})
if _, err := svc.setRemoteTrafficLocked(1, snapshotWithoutClients(t, "n1-in"), false, false); err != nil {
t.Fatalf("orphaning merge: %v", err)
}
if readOrphanMark(t, db, email) <= 0 {
t.Fatal("setup: expected the merge to mark the client")
}
syncNodeWithSettings(t, svc, 1, "n1-in", settings,
xray.ClientTraffic{Email: email, Up: 6, Down: 6, Enable: true})
if orphanedAt := readOrphanMark(t, db, email); orphanedAt != 0 {
t.Fatalf("re-attached client kept its orphan mark: sync_orphaned_at=%d", orphanedAt)
}
backdateOrphanMark(t, db, email)
if reaped, err := clientSvc.ReapSyncOrphans(); err != nil || reaped != 0 {
t.Fatalf("reaped %d client(s) (err=%v) that the node still reports, want 0", reaped, err)
}
}
// The reaper is scoped to the node sweep. Orphans from any other cause carry no
// mark and keep their existing manual-cleanup semantics.
func TestReapSyncOrphansIgnoresUnmarkedOrphans(t *testing.T) {
db := initTrafficTestDB(t)
clientSvc := &ClientService{}
const email = "manual@x"
rec := &model.ClientRecord{Email: email, Enable: true, UUID: "44444444-4444-4444-4444-444444444444"}
if err := db.Create(rec).Error; err != nil {
t.Fatalf("create client: %v", err)
}
reaped, err := clientSvc.ReapSyncOrphans()
if err != nil {
t.Fatalf("reap: %v", err)
}
if reaped != 0 {
t.Fatalf("reaped %d unmarked orphan(s), want 0", reaped)
}
var surviving int64
if err := db.Model(&model.ClientRecord{}).Where("email = ?", email).Count(&surviving).Error; err != nil {
t.Fatalf("count clients: %v", err)
}
if surviving != 1 {
t.Fatalf("unmarked orphan was reaped: %d rows survive, want 1", surviving)
}
}