summaryrefslogtreecommitdiff
path: root/fs/gfs2
diff options
context:
space:
mode:
authorAndreas Gruenbacher <agruenba@redhat.com>2022-02-02 11:00:48 +0100
committerAndreas Gruenbacher <agruenba@redhat.com>2022-02-15 15:01:40 +0100
commita892b12393afb74c397dc752eaba1e96e2702303 (patch)
tree56e538b35896a1348e111906bacac182eda51e54 /fs/gfs2
parent7336905a89f19173bf9301cd50a24421162f417c (diff)
gfs2: Expect -EBUSY after canceling dlm locking requests
Due to the asynchronous nature of the dlm api, when we request a pending locking request to be canceled with dlm_unlock(DLM_LKF_CANCEL), the locking request will either complete before it could be canceled, or the cancellation will succeed. In either case, gdlm_ast will be called once and the status will indicate the outcome of the locking request, with -DLM_ECANCEL indicating a canceled request. Inside dlm, when a locking request completes before its cancel request could be processed, gdlm_ast will be called, but the lock will still be considered busy until a DLM_MSG_CANCEL_REPLY message completes the cancel request. During that time, successive dlm_lock() or dlm_unlock() requests for that lock will return -EBUSY. In other words, waiting for the gdlm_ast call before issuing the next locking request is not enough. There is no way of waiting for a cancel request to actually complete, either. We rarely cancel locking requests, but when we do, we don't know when the next locking request for that lock will occur. This means that any dlm_lock() or dlm_unlock() call can potentially return -EBUSY. When that happens, this patch simply repeats the request after a short pause. This workaround could be improved upon by tracking for which dlm locks cancel requests have been issued, but that isn't strictly necessary and it would complicate the code. We haven't seen -EBUSY errors from dlm without cancel requests. Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Diffstat (limited to 'fs/gfs2')
-rw-r--r--fs/gfs2/lock_dlm.c15
1 files changed, 14 insertions, 1 deletions
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 50578f881e6d..2559a79cf14b 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -261,6 +261,7 @@ static int gdlm_lock(struct gfs2_glock *gl, unsigned int req_state,
int req;
u32 lkf;
char strname[GDLM_STRNAME_BYTES] = "";
+ int error;
req = make_mode(gl->gl_name.ln_sbd, req_state);
lkf = make_flags(gl, flags, req);
@@ -279,8 +280,14 @@ static int gdlm_lock(struct gfs2_glock *gl, unsigned int req_state,
* Submit the actual lock request.
*/
- return dlm_lock(ls->ls_dlm, req, &gl->gl_lksb, lkf, strname,
+again:
+ error = dlm_lock(ls->ls_dlm, req, &gl->gl_lksb, lkf, strname,
GDLM_STRNAME_BYTES - 1, 0, gdlm_ast, gl, gdlm_bast);
+ if (error == -EBUSY) {
+ msleep(20);
+ goto again;
+ }
+ return error;
}
static void gdlm_put_lock(struct gfs2_glock *gl)
@@ -312,8 +319,14 @@ static void gdlm_put_lock(struct gfs2_glock *gl)
return;
}
+again:
error = dlm_unlock(ls->ls_dlm, gl->gl_lksb.sb_lkid, DLM_LKF_VALBLK,
NULL, gl);
+ if (error == -EBUSY) {
+ msleep(20);
+ goto again;
+ }
+
if (error) {
fs_err(sdp, "gdlm_unlock %x,%llx err=%d\n",
gl->gl_name.ln_type,