[openib-general] RHEL4ASU3 question

[Bob Woodruff]

Don wrote,
>Looking at the viacheck.c file,  it seems that this error is generated when
a bad status is found >in the status of a completion queue entry.   From the
"code=1" ,  it may be some sort of "length 
>error".    This could be coming from the driver or the card, I suppose?
That's as far as I have >gotten so far. 

>Does this sound like any of the "issues" you referred to above relative to
RHEL4 U3 and the DDR 
>cards?   If so, is there a fix? 

>-Don Albert- 
>Bull HN Info Systems 

Most likely it is the same problem I had with the DDR cards and the stock 
RedHat EL4.0 - U3 release. I reported the problem to RedHat, but they added
a bugzila
comment that they did not have any DDR hardware. Perhaps Mellanox could
provide
them with some. 

Michael ?

My guess is that the version of code that they have in the release is too
old
and does not completely support the DDR card. I tried them with newer SVN
code
and it worked OK.

You might try my backport patches and/or test RPMs that are based on RedHat
EL4 - U3
kernel, but with a newer version of the SVN code or replace your RedHat
kernel with
a newer kernel.org kernel. Not sure if that is feasible or not in your
environment,
but I am pretty sure that newer SVN code will fix the problem. 

https://openib.org/svn/gen2/branches/backport-to-2.6.9/RPMS/

You may also need newer usermode libraries to go with the newer kernel,
either 
kernel.org or my backport to 2.6.9-34EL. You will need to uninstall the
redhat
usermode RPMS and install either my usermode RPM or the ones from the
release 1.0
RC2 should probably work as well.

woody


woody