aboutsummaryrefslogtreecommitdiffstats
path: root/fs/dlm
diff options
context:
space:
mode:
authorDavid Teigland <teigland@redhat.com>2007-01-24 11:21:33 -0500
committerSteven Whitehouse <swhiteho@redhat.com>2007-02-05 13:37:50 -0500
commitb790c3b7c38aae28c497bb363a6fe72f7c96568f (patch)
treee4dda1c5c775b4ae164a997f1216147066de31e3 /fs/dlm
parent8fd3a98f2c22982aff4d29e4ee72959d3032c123 (diff)
[DLM] can miss clearing resend flag
A long, complicated sequence of events, beginning with the RESEND flag not being cleared on an lkb, can result in an unlock never completing. - lkb on waiters list for remote lookup - the remote node is both the dir node and the master node, so it optimizes the lookup into a request and sends a request reply back - the request reply is saved on the requestqueue to be processed after recovery - recovery runs dlm_recover_waiters_pre() which sets RESEND flag so the lookup will be resent after recovery - end of recovery: process_requestqueue takes saved request reply which removes the lkb off the waitesr list, _without_ clearing the RESEND flag - end of recovery: dlm_recover_waiters_post() doesn't do anything with the now completed lookup lkb (would usually clear RESEND) - later, the node unmounts, unlocks this lkb that still has RESEND flag set - the lkb is on the waiters list again, now for unlock, when recovery occurs, dlm_recover_waiters_pre() shows the lkb for unlock with RESEND set, doesn't do anything since the master still exists - end of recovery: dlm_recover_waiters_post() takes this lkb off the waiters list because it has the RESEND flag set, then reports an error because unlocks are never supposed to be handled in recover_waiters_post(). - later, the unlock reply is received, doesn't find the lkb on the waiters list because recover_waiters_post() has wrongly removed it. - the unlock operation has been lost, and we're left with a stray granted lock - unmount spins waiting for the unlock to complete The visible evidence of this problem will be a node where gfs umount is spinning, the dlm waiters list will be empty, and the dlm locks list will show a granted lock. The fix is simply to clear the RESEND flag when taking an lkb off the waiters list. Signed-off-by: David Teigland <teigland@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
Diffstat (limited to 'fs/dlm')
-rw-r--r--fs/dlm/lock.c6
1 files changed, 6 insertions, 0 deletions
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index 7c7ac2aaa8b1..c10257f10b90 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -754,6 +754,11 @@ static void add_to_waiters(struct dlm_lkb *lkb, int mstype)
754 mutex_unlock(&ls->ls_waiters_mutex); 754 mutex_unlock(&ls->ls_waiters_mutex);
755} 755}
756 756
757/* We clear the RESEND flag because we might be taking an lkb off the waiters
758 list as part of process_requestqueue (e.g. a lookup that has an optimized
759 request reply on the requestqueue) between dlm_recover_waiters_pre() which
760 set RESEND and dlm_recover_waiters_post() */
761
757static int _remove_from_waiters(struct dlm_lkb *lkb) 762static int _remove_from_waiters(struct dlm_lkb *lkb)
758{ 763{
759 int error = 0; 764 int error = 0;
@@ -764,6 +769,7 @@ static int _remove_from_waiters(struct dlm_lkb *lkb)
764 goto out; 769 goto out;
765 } 770 }
766 lkb->lkb_wait_type = 0; 771 lkb->lkb_wait_type = 0;
772 lkb->lkb_flags &= ~DLM_IFL_RESEND;
767 list_del(&lkb->lkb_wait_reply); 773 list_del(&lkb->lkb_wait_reply);
768 unhold_lkb(lkb); 774 unhold_lkb(lkb);
769 out: 775 out: