<html><body>
<p><tt>"Roland Dreier" <roland.list@gmail.com> wrote on 06/12/2008 05:47:07 PM:<br>
<br>
> > Anybody saw mlx4_core CQ overrun before? The test is based on OFED-1.3. FW<br>
> > version is 2.3.0. Please let me know any more info is needed.<br>
> <br>
> Yes, I've seen CQ overrun -- when a CQ is overrun...<br>
</tt><br>
<tt>Thanks for your prompt response. So it is not possible a driver or FW bug? We will recheck our test.</tt><br>
<tt> <br>
> > c955mgrs1:~ # dsh -av "grep 'CQ overrun' /var/log/messages" | sort<br>
> > dsh: c955c2s1.ppd.pok.ibm.com Host is not responding. No command will be<br>
> > issued to this host<br>
> > c955c1s11.ppd.pok.ibm.com: Jun 10 07:18:15 c955c1s11 kernel: mlx4_core<br>
> > 0003:01:00.0: CQ overrun on CQN 000098<br>
> <br>
> What test are you running to get this error? My first guess would be<br>
> a bug in the<br>
> test that overruns a CQ.<br>
> <br>
> - R.<br>
</tt><br>
<tt>Some vendor specific MPI stress test.</tt><br>
<br>
<tt>Thanks</tt><br>
<tt>Shirley</tt></body></html>