From: "Yan, Zheng" <zheng.z.yan@xxxxxxxxx>
Aborted requests usually get cleared when the reply is received.
If MDS crashes, no reply will be received. So we need to cleanup
aborted requests when re-sending requests.
Signed-off-by: Yan, Zheng <zheng.z.yan@xxxxxxxxx>
Reviewed-by: Greg Farnum <greg@xxxxxxxxxxx>
Signed-off-by: Sage Weil <sage@xxxxxxxxxxx>
(cherry picked from commit eb1b8af33c2e42a9a57fc0a7588f4a7b255d2e79)
---
fs/ceph/mds_client.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index b7bda5d..91214b2 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1875,8 +1875,11 @@ static int __do_request(struct ceph_mds_client *mdsc,
int mds = -1;
int err = -EAGAIN;
- if (req->r_err || req->r_got_result)
+ if (req->r_err || req->r_got_result) {
+ if (req->r_aborted)
+ __unregister_request(mdsc, req);
goto out;
+ }
if (req->r_timeout &&
time_after_eq(jiffies, req->r_started + req->r_timeout)) {
--
1.8.5.1
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html