* ibv_poll_cq misbehaving with RoCE 40Gbps
@ 2013-09-13 13:23 xrg.dev-8HG2SOrYmURWk0Htik3J/w
0 siblings, 0 replies; only message in thread
From: xrg.dev-8HG2SOrYmURWk0Htik3J/w @ 2013-09-13 13:23 UTC (permalink / raw)
To: linux-rdma-u79uwXL29TY76Z2rM5mHXA
Hello list,
I am experiencing a strange behavior with ibv_poll_cq on RoCE 40
Gb. When calling the following:
int N = ibv_poll_cq (CQ, DEPTH, WC);
N sometimes becomes equal to DEPTH, although the number of
outstanding WR is well below DEPTH. In our current example, DEPTH =
128 and the # of outstanding requests is 4. With N >> # of valid
WC, scanning the WC array produces, of course, errors.
I am using RHEL 6.4 with the OFED distribution provided by RH. Any
clue were this error may be coming from ?
Thanks,
Xavier
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2013-09-13 13:23 UTC | newest]
Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2013-09-13 13:23 ibv_poll_cq misbehaving with RoCE 40Gbps xrg.dev-8HG2SOrYmURWk0Htik3J/w
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).