[ofa-general] ***SPAM*** Re: IB Bonding errors with recent kernel

[Moni Shoua]

Dennis Portello wrote:
> Hello,
> 
> I seem to be experiencing the exact issue discussed below (back in
> December). I'm using the 2.6.27 kernel and the bonding drivers available
> in that kernel. Was there ever a solution or patch to solve this? I have
Not really, a patch was sent a long time ago but it wasn't accepted. The claim was that it takes
care of a phenomena that exists only with Redhat 4 (I tend to agree).
You can read the discussion here http://kerneltrap.org/mailarchive/linux-netdev/2008/4/10/1391984

> been using the ib-bond scripts as well, but using other approaches like
> standard OS tools or adding the bond through sysfs all seem to have the
> same results.
> 
As I recall, this shouldn't happen when working with ib-bond. However, ib-bond is a deprecated tool
so I wouldn't tell you to use it as a solution but I do wonder why do you still see the -22 status in d,esg
> Regular TCP/IP unicast works, though dmesg is full of warning about
> multicast failing. Multicast does not work at all.
Multicast that is not working is not related to the issue you describe. I suggest that
you open a  bug  here https://bugs.openfabrics.org/ and describe what you do and what you get 
in details.

thanks
 MoniS