Skip to content

ROX-37314: Release the cluster deletion lock before cleanup #23210

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
vikin91 wants to merge 1 commit into
base: master
Choose a base branch
from
+22 −3
Draft

ROX-37314: Release the cluster deletion lock before cleanup #23210

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 4 additions & 3 deletions central/cluster/lifecycle/gate.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,17 +53,18 @@ func (g *Gate) Enter(clusterID string) (active bool, release func()) {
}
}

// BeginDeletion prevents new active writes and waits for existing writes to finish.
// BeginDeletion prevents new active writes and waits for in-flight writes to finish.
// The returned function must be called once cluster cleanup completes.
func (g *Gate) BeginDeletion(clusterID string) func() {
e := g.retain(clusterID)
concurrency.WithLock(&e.stateMu, func() {
e.deleting = true
})
e.mu.Lock()
// Drain in-flight read locks, then release. Cleanup can exceed the dev
// mutex watchdog (10s), which aborts the process on a long exclusive hold.
concurrency.WithLock(&e.mu, func() {})

return func() {
concurrency.UnsafeUnlock(&e.mu)
concurrency.WithLock(&e.stateMu, func() {
e.deleting = false
})
Expand Down
18 changes: 18 additions & 0 deletions central/cluster/lifecycle/gate_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,3 +45,21 @@ func TestGateBlocksDeletionUntilActiveWriteCompletes(t *testing.T) {
require.True(t, active)
release()
}

// TestBeginDeletionDropsWriteLockBeforeCleanup checks that BeginDeletion only
// holds the write lock long enough to drain in-flight leases. The dev mutex
// watchdog aborts the process if that lock stays held through cleanup.
func TestBeginDeletionDropsWriteLockBeforeCleanup(t *testing.T) {
gate := New()
releaseDeletion := gate.BeginDeletion("cluster-id")
t.Cleanup(releaseDeletion)

e := gate.entries["cluster-id"]
require.NotNil(t, e)
require.True(t, e.mu.TryLock(), "write lock still held after BeginDeletion returned")
e.mu.Unlock()

active, release := gate.Enter("cluster-id")
require.False(t, active)
require.Nil(t, release)
}
Loading