RepoMirrors/ceph
1
0
Fork 0
mirror of https://github.com/ceph/ceph synced 2025-02-21 01:47:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

msg/Pipe: avoid creating empty out_q entry

Browse Source 
We need to maintain the invariant that all sub queues in out_q are never
empty.  Fix discard_requeued_up_to() to avoid creating an entry unless we
know it is already present.

This bug leads to an incorrect reconnect attempt when

 - we accept a pipe (lossless peer)
 - they send some stuff, maybe
 - fault
 - we initiate reconnect, even tho we have nothing queued

In particular, we shouldn't reconnect because we aren't checking for
resets, and the fact that our out_seq is 0 while the peer's might be
something else entirely will trigger asserts later.

This fixes at least one source of #5626, and possibly #5517.

Backport: cuttlefish
Signed-off-by: Sage Weil <sage@inktank.com>
This commit is contained in:
Sage Weil 2013-07-16 10:09:02 -07:00
parent 579d858aab
commit 9f1c272618
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/msg/Pipe.cc
View File

@ -1124,6 +1124,8 @@ void Pipe::requeue_sent()
void Pipe::discard_requeued_up_to(uint64_t seq)
{
ldout(msgr->cct, 10) << "discard_requeued_up_to " << seq << dendl;
if (out_q.count(CEPH_MSG_PRIO_HIGHEST) == 0)
return;
list<Message*>& rq = out_q[CEPH_MSG_PRIO_HIGHEST];
while (!rq.empty()) {
Message *m = rq.front();
@ -1135,6 +1137,8 @@ void Pipe::discard_requeued_up_to(uint64_t seq)
rq.pop_front();
out_seq++;
}
if (rq.empty())
out_q.erase(CEPH_MSG_PRIO_HIGHEST);
}
/*