Messages in this thread Patch in this message | | | From | Luis Henriques <> | Subject | [PATCH 3.11 020/208] ceph: cleanup aborted requests when re-sending requests. | Date | Mon, 13 Jan 2014 15:57:41 +0000 |
| |
3.11.10.3 -stable review patch. If anyone has any objections, please let me know.
------------------
From: "Yan, Zheng" <zheng.z.yan@intel.com>
commit eb1b8af33c2e42a9a57fc0a7588f4a7b255d2e79 upstream.
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@intel.com> Reviewed-by: Greg Farnum <greg@inktank.com> Signed-off-by: Sage Weil <sage@inktank.com> Signed-off-by: Luis Henriques <luis.henriques@canonical.com> --- 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 187bf21..c9c69cd 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1841,8 +1841,11 @@ 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)) { -- 1.8.3.2
| |