[openib-general] heads-up - ipoib NAPI

[harish]

Hi Eli,

How did the CPU utilizations compare for the NAPI vs. no NAPI case? What are
your thoughts on what bottleneck you are hitting?

Sorry to bother you ;)
thanks
harish

On 9/21/06, eli at dev.mellanox.co.il <eli at dev.mellanox.co.il> wrote:
>
> > Hi Eli,
> >
> > Thanks for sharing the results with us. It is great to see the reduction
> > in
> > Interrupts. Could you please specify the netperf test specifications
> > [message size; socket size]. Wondering what the numbers would be if we
> use
> > large socket and message sizes [128K & 64K respectively]. The reason for
> > the
> > request is to make sure we are not hitting any TCP related bottleneck
> > while
> > comparing NAPI vs. no NAPI cases. Please let me know what you think.
>
> I used large socket buffer sizes. Here is the command line I used. The
> reult for the bandwidth is the some of all the connections.
>
> netperf -H 11.4.3.144 -l 600 -f M -p $port -- -s 200000,200000 -S
> 200000,200000
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.openfabrics.org/pipermail/general/attachments/20060921/e5ebceab/attachment.html>