summaryrefslogtreecommitdiff
path: root/fs/dlm/lock.c
diff options
context:
space:
mode:
authorDavid Teigland <teigland@redhat.com>2008-01-07 16:15:05 -0600
committerDavid Teigland <teigland@redhat.com>2008-01-30 11:04:42 -0600
commit601342ce022b964f756b67f2eb99b605c1afa3ed (patch)
tree78b8c873dbc41bca33ed23dcf61fbea1572a007c /fs/dlm/lock.c
parent8a358ca8e738b6226b004efea462ac28c0a2bbb1 (diff)
downloadlinux-3.10-601342ce022b964f756b67f2eb99b605c1afa3ed.tar.gz
linux-3.10-601342ce022b964f756b67f2eb99b605c1afa3ed.tar.bz2
linux-3.10-601342ce022b964f756b67f2eb99b605c1afa3ed.zip
dlm: recover locks waiting for overlap replies
When recovery looks at locks waiting for replies, it fails to consider locks that have already received a reply for their first remote operation, but not received a reply for secondary, overlapping unlock/cancel. The appropriate stub reply needs to be called for these waiters. Appears when we start doing recovery in the presence of a many overlapping unlock/cancel ops. Signed-off-by: David Teigland <teigland@redhat.com>
Diffstat (limited to 'fs/dlm/lock.c')
-rw-r--r--fs/dlm/lock.c37
1 files changed, 32 insertions, 5 deletions
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index 43ca2a30c41..a758f1b80e3 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -3846,6 +3846,7 @@ static int waiter_needs_recovery(struct dlm_ls *ls, struct dlm_lkb *lkb)
void dlm_recover_waiters_pre(struct dlm_ls *ls)
{
struct dlm_lkb *lkb, *safe;
+ int wait_type, stub_unlock_result, stub_cancel_result;
mutex_lock(&ls->ls_waiters_mutex);
@@ -3864,7 +3865,33 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls)
if (!waiter_needs_recovery(ls, lkb))
continue;
- switch (lkb->lkb_wait_type) {
+ wait_type = lkb->lkb_wait_type;
+ stub_unlock_result = -DLM_EUNLOCK;
+ stub_cancel_result = -DLM_ECANCEL;
+
+ /* Main reply may have been received leaving a zero wait_type,
+ but a reply for the overlapping op may not have been
+ received. In that case we need to fake the appropriate
+ reply for the overlap op. */
+
+ if (!wait_type) {
+ if (is_overlap_cancel(lkb)) {
+ wait_type = DLM_MSG_CANCEL;
+ if (lkb->lkb_grmode == DLM_LOCK_IV)
+ stub_cancel_result = 0;
+ }
+ if (is_overlap_unlock(lkb)) {
+ wait_type = DLM_MSG_UNLOCK;
+ if (lkb->lkb_grmode == DLM_LOCK_IV)
+ stub_unlock_result = -ENOENT;
+ }
+
+ log_debug(ls, "rwpre overlap %x %x %d %d %d",
+ lkb->lkb_id, lkb->lkb_flags, wait_type,
+ stub_cancel_result, stub_unlock_result);
+ }
+
+ switch (wait_type) {
case DLM_MSG_REQUEST:
lkb->lkb_flags |= DLM_IFL_RESEND;
@@ -3877,7 +3904,7 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls)
case DLM_MSG_UNLOCK:
hold_lkb(lkb);
ls->ls_stub_ms.m_type = DLM_MSG_UNLOCK_REPLY;
- ls->ls_stub_ms.m_result = -DLM_EUNLOCK;
+ ls->ls_stub_ms.m_result = stub_unlock_result;
ls->ls_stub_ms.m_flags = lkb->lkb_flags;
_receive_unlock_reply(lkb, &ls->ls_stub_ms);
dlm_put_lkb(lkb);
@@ -3886,15 +3913,15 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls)
case DLM_MSG_CANCEL:
hold_lkb(lkb);
ls->ls_stub_ms.m_type = DLM_MSG_CANCEL_REPLY;
- ls->ls_stub_ms.m_result = -DLM_ECANCEL;
+ ls->ls_stub_ms.m_result = stub_cancel_result;
ls->ls_stub_ms.m_flags = lkb->lkb_flags;
_receive_cancel_reply(lkb, &ls->ls_stub_ms);
dlm_put_lkb(lkb);
break;
default:
- log_error(ls, "invalid lkb wait_type %d",
- lkb->lkb_wait_type);
+ log_error(ls, "invalid lkb wait_type %d %d",
+ lkb->lkb_wait_type, wait_type);
}
schedule();
}