diff options
| author | Sage Weil <sage@newdream.net> | 2010-05-24 11:15:51 -0700 |
|---|---|---|
| committer | Sage Weil <sage@newdream.net> | 2010-05-29 09:12:35 -0700 |
| commit | aa91647c898d62e869fcf35e977ab3c533be8fc1 (patch) | |
| tree | 6a5ff908ecb2732d891baa4bac52b5690130e887 | |
| parent | 0aa12fb439838a85802ab8b7fbb9bcfc3e6e05cb (diff) | |
ceph: make mds requests killable, not interruptible
The underlying problem is that many mds requests can't be restarted. For
example, a restarted create() would return -EEXIST if the original request
succeeds. However, we do not want a hung MDS to hang the client too. So,
use the _killable wait_for_completion variants to abort on SIGKILL but
nothing else.
Signed-off-by: Sage Weil <sage@newdream.net>
| -rw-r--r-- | fs/ceph/mds_client.c | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 885aa5710cfd..08413c8a85b2 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1768,12 +1768,12 @@ int ceph_mdsc_do_request(struct ceph_mds_client *mdsc, mutex_unlock(&mdsc->mutex); dout("do_request waiting\n"); if (req->r_timeout) { - err = (long)wait_for_completion_interruptible_timeout( + err = (long)wait_for_completion_killable_timeout( &req->r_completion, req->r_timeout); if (err == 0) err = -EIO; } else { - err = wait_for_completion_interruptible(&req->r_completion); + err = wait_for_completion_killable(&req->r_completion); } dout("do_request waited, got %d\n", err); mutex_lock(&mdsc->mutex); |