[Beowulf] Performance tuning for Jumbo Frames

Rahul Nabar rpnabar at gmail.com
Mon Dec 14 11:54:11 PST 2009

On Sat, Dec 12, 2009 at 10:40 AM, Patrick Geoffray <patrick at myri.com> wrote:

> It is most likely due to the switch. Try back-to-back to measure without it.
> I don't know what hardware you are using, but you can get close to 10us
> latency over TCP with a standard 10GE NIC and interrupt coalescing disabled.
> With a NIC supporting OS-bypass (RDMA only make sense for bandwidth), you
> should get at least half that, ideally below 3us.

What was your tool to measure this latency? Just curious.


More information about the Beowulf mailing list