mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-10-29 08:20:42 +01:00
* mount: drain OFD locks when a file description is released The kernel scopes OFD fcntl locks to the open file description but reports no lock_owner for them at RELEASE — it only sends one for flock holders — so an OFD write lock taken on a file handle outlived the holder and blocked every later open of that file (e.g. etcd failing to reopen its WAL after a restart). The mount now records the owner of each granted non-flock lock under its file handle and releases those owners on RELEASE, which also covers any POSIX locks left over when FLUSH could not run. Generated with [Devin](https://devin.ai) Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com> * mount: give every open its own fh value over the shared handle AcquireFileHandle reuses one FileHandle per inode, so every open reported the same fh to the kernel. A RELEASE for one description could then not be told apart from a sibling still holding the inode open — draining lock owners recorded under the shared fh dropped locks belonging to descriptions that stay open. Each open now registers its own fh value in fh2inode, all resolving to the shared FileHandle, and RELEASE removes exactly the id that is closing. This also stops a duplicated RELEASE on one id from double-decrementing the open count. Generated with [Devin](https://devin.ai) Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com> * mount: forget flushed lock owners so a later release cannot re-drop locks POSIX lock owners are process-scoped: Flush releases every lock the process holds on the inode, but the owner stayed recorded under each open's fh for the Release-time drain. If the process took a fresh lock through another open before an old description finished closing, the stale record made that RELEASE drop the new lock too. Flush now drops the released owner from every recorded open of the inode, so the Release drain only ever fires for owners whose locks were never flushed. Generated with [Devin](https://devin.ai) Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com> * mount: keep close-time lock owner records when the release fails A routed POSIX owner release that errors keeps the flush hint for a retry, but Flush also dropped the owner from every open's release records unconditionally — so the final Release skipped the retry and the owner filer's lock was stranded until lease reaping. Only forget the owner once its locks were actually released. --------- Co-authored-by: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
140 lines
4.5 KiB
Go
140 lines
4.5 KiB
Go
package mount
|
|
|
|
import (
|
|
"math"
|
|
"testing"
|
|
"time"
|
|
|
|
"github.com/seaweedfs/go-fuse/v2/fuse"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/util"
|
|
)
|
|
|
|
// A close() frees the file description's flock locks even when the handle
|
|
// flush is stuck — e.g. a filer that stopped answering. If the locks outlive
|
|
// the blocked flush, a restarted process taking the same file's flock sees
|
|
// "file already locked" until the mount restarts.
|
|
func TestReleaseDropsFlockWhileFlushBlocked(t *testing.T) {
|
|
wfs := newInvalidateTestWFS(t)
|
|
wfs.posixLocks = NewPosixLockTable()
|
|
startFakeFiler(t, wfs, &fakeFilerServer{})
|
|
|
|
inode := wfs.inodeToPath.Lookup(util.FullPath("/dir/f"), time.Now().Unix(), false, false, 0, false)
|
|
fh, _, _ := wfs.fhMap.AcquireFileHandle(wfs, inode, &filer_pb.Entry{
|
|
Name: "f",
|
|
Attributes: &filer_pb.FuseAttributes{},
|
|
}, 0, 0)
|
|
fh.dirtyMetadata = true
|
|
|
|
const owner = uint64(42)
|
|
if st := wfs.posixLocks.SetLk(inode, lockRange{Start: 0, End: math.MaxUint64, Typ: f_WRLCK, Owner: owner, IsFlock: true}); st != fuse.OK {
|
|
t.Fatalf("take flock: %v", st)
|
|
}
|
|
|
|
// Stall the release flush at the handle lock flushMetadataToFiler waits on.
|
|
active := wfs.fhLockTable.AcquireLock("test", fh.fh, util.ExclusiveLock)
|
|
released := false
|
|
releaseLock := func() {
|
|
if !released {
|
|
wfs.fhLockTable.ReleaseLock(fh.fh, active)
|
|
released = true
|
|
}
|
|
}
|
|
defer releaseLock()
|
|
|
|
done := make(chan struct{})
|
|
go func() {
|
|
defer close(done)
|
|
wfs.Release(nil, &fuse.ReleaseIn{
|
|
InHeader: fuse.InHeader{NodeId: inode},
|
|
Fh: uint64(fh.fh),
|
|
LockOwner: owner,
|
|
ReleaseFlags: fuse.FUSE_RELEASE_FLOCK_UNLOCK,
|
|
})
|
|
}()
|
|
|
|
// The dead holder's flock must be gone while the flush is still parked.
|
|
deadline := time.Now().Add(10 * time.Second)
|
|
for {
|
|
var out fuse.LkOut
|
|
wfs.posixLocks.GetLk(inode, lockRange{Start: 0, End: math.MaxUint64, Typ: f_WRLCK, Owner: 7, IsFlock: true}, &out)
|
|
if out.Lk.Typ == f_UNLCK {
|
|
break
|
|
}
|
|
if time.Now().After(deadline) {
|
|
t.Fatal("flock still held while the release flush is blocked")
|
|
}
|
|
time.Sleep(5 * time.Millisecond)
|
|
}
|
|
|
|
// Let the parked flush through: the live filer answers the metadata update.
|
|
releaseLock()
|
|
select {
|
|
case <-done:
|
|
case <-time.After(10 * time.Second):
|
|
t.Fatal("release never completed after the flush unblocked")
|
|
}
|
|
}
|
|
|
|
// OFD locks are scoped to the open file description, not the process, and the
|
|
// kernel reports no lock_owner for them at RELEASE — only flock holders carry
|
|
// one. Draining the owners recorded for the released handle frees them, so a
|
|
// restarted process (new owner) no longer sees the dead description's write
|
|
// lock.
|
|
func TestReleaseDropsOfdLocks(t *testing.T) {
|
|
wfs := newInvalidateTestWFS(t)
|
|
wfs.posixLocks = NewPosixLockTable()
|
|
startFakeFiler(t, wfs, &fakeFilerServer{})
|
|
|
|
inode := wfs.inodeToPath.Lookup(util.FullPath("/dir/f"), time.Now().Unix(), false, false, 0, false)
|
|
entry := &filer_pb.Entry{
|
|
Name: "f",
|
|
Attributes: &filer_pb.FuseAttributes{},
|
|
}
|
|
_, openFh, _ := wfs.fhMap.AcquireFileHandle(wfs, inode, entry, 0, 0)
|
|
_, siblingFh, _ := wfs.fhMap.AcquireFileHandle(wfs, inode, entry, 0, 0)
|
|
if siblingFh == openFh {
|
|
t.Fatal("sibling open must get its own fh value")
|
|
}
|
|
|
|
const ofdOwner = uint64(0x0fd0001)
|
|
ofd := &fuse.LkIn{
|
|
InHeader: fuse.InHeader{NodeId: inode},
|
|
Fh: uint64(openFh),
|
|
Owner: ofdOwner,
|
|
Lk: fuse.FileLock{Start: 0, End: math.MaxUint64, Typ: f_RDLCK},
|
|
}
|
|
// A second open file description holds a read lock on the same inode;
|
|
// it must survive the first description's release.
|
|
const siblingOwner = uint64(0x0fd0002)
|
|
sibling := &fuse.LkIn{
|
|
InHeader: fuse.InHeader{NodeId: inode},
|
|
Fh: uint64(siblingFh),
|
|
Owner: siblingOwner,
|
|
Lk: fuse.FileLock{Start: 0, End: math.MaxUint64, Typ: f_RDLCK},
|
|
}
|
|
if st := wfs.SetLk(nil, sibling); st != fuse.OK {
|
|
t.Fatalf("take sibling read lock: %v", st)
|
|
}
|
|
if st := wfs.SetLk(nil, ofd); st != fuse.OK {
|
|
t.Fatalf("take ofd lock: %v", st)
|
|
}
|
|
|
|
wfs.Release(nil, &fuse.ReleaseIn{
|
|
InHeader: fuse.InHeader{NodeId: inode},
|
|
Fh: uint64(openFh),
|
|
})
|
|
|
|
// The dead description's read lock is gone: the sibling can upgrade to a
|
|
// write lock only because nothing else blocks it.
|
|
var out fuse.LkOut
|
|
wfs.posixLocks.GetLk(inode, lockRange{Start: 0, End: math.MaxUint64, Typ: f_WRLCK, Owner: 7}, &out)
|
|
if out.Lk.Typ != f_RDLCK {
|
|
t.Fatalf("sibling lock lost on release: typ=%d", out.Lk.Typ)
|
|
}
|
|
sibling.Lk.Typ = f_WRLCK
|
|
if st := wfs.SetLk(nil, sibling); st != fuse.OK {
|
|
t.Fatalf("ofd lock survived release: upgrade got %v", st)
|
|
}
|
|
}
|