On Mon, 6 Oct 2014 02:13:44 -0700
Matthew Hall wrote:
> Hi Guys,
>
> I'm doing my development on kind of a cheap machine with no NUMA support...
> but several years ago I used DPDK to build a NUMA box that could do 40 gbits
> bidirectional L4-L7 stateful traffic replay.
>
> So given the past
On Fri, Oct 24, 2014 at 06:36:29PM +0530, Stephen Hemminger wrote:
> The code is fairly consistent in returning -1 for cases of not a NUMA socket,
> bogus port value. It is interpreted as SOCKET_ID_ANY in several places.
> The examples mostly check for -1 and use socket 0 as a fallback.
> Probably
Hi guys,
Could anybody comment on my observations about the PCI scan process and how to
improve the NUMA compatibility, etc.?
The original bug contains a bogus commit history (fake source for commit, fake
timestamp, no detail about what was done in the commit). I also don't have a
list of subs
Hi,
Did anybody get a chance to look what might be going on in this weird NUMA
bug? I could use some help to understand how you're supposed to make code that
will work right on both NUMA and non-NUMA. Otherwise it's hard to make a
bulletproof DPDK based app that will be able to reliably init on
Hi Guys,
I'm doing my development on kind of a cheap machine with no NUMA support...
but several years ago I used DPDK to build a NUMA box that could do 40 gbits
bidirectional L4-L7 stateful traffic replay.
So given the past experiences I had before, I wanted to clean the code up so
it'd work
5 matches
Mail list logo
