diff options
| author | Sage Weil <sage@newdream.net> | 2010-02-17 07:01:03 +0100 |
|---|---|---|
| committer | Sage Weil <sage@newdream.net> | 2010-02-17 07:01:03 +0100 |
| commit | e2663ab60de59d20fa33da3528f6d5359f8eb003 (patch) | |
| tree | f167aba83280b6767e1f9bdf2e67e4ac48a85c68 /fs | |
| parent | ceph: reset osd connections after fault (diff) | |
| download | linux-e2663ab60de59d20fa33da3528f6d5359f8eb003.tar.xz linux-e2663ab60de59d20fa33da3528f6d5359f8eb003.zip | |
ceph: allow connection to be reopened by fault callback
Fix the messenger to allow a ceph_con_open() during the fault callback.
Previously the work wasn't getting queued on the connection because the
fault path avoids requeued work (normally spurious). Loop on reopening by
checking for the OPENING state bit.
This fixes OSD reconnects when a TCP connection drops.
Signed-off-by: Sage Weil <sage@newdream.net>
Diffstat (limited to 'fs')
| -rw-r--r-- | fs/ceph/messenger.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/fs/ceph/messenger.c b/fs/ceph/messenger.c index 44bdaf439924..acf383f6a9cd 100644 --- a/fs/ceph/messenger.c +++ b/fs/ceph/messenger.c @@ -1808,7 +1808,7 @@ done: clear_bit(BUSY, &con->state); dout("con->state=%lu\n", con->state); if (test_bit(QUEUED, &con->state)) { - if (!backoff) { + if (!backoff || test_bit(OPENING, &con->state)) { dout("con_work %p QUEUED reset, looping\n", con); goto more; } |