On Jan 10, 2013, at 2:18 PM, Ben Pfaff wrote:
> On Thu, Jan 10, 2013 at 01:59:06PM -0800, Justin Pettit wrote:
>> Can you take a look at the incremental and let me know what you think?
>
> Looks good, thanks.
Thanks for the reviews. I pushed it.
--Justin
On Thu, Jan 10, 2013 at 01:59:06PM -0800, Justin Pettit wrote:
> Can you take a look at the incremental and let me know what you think?
Looks good, thanks.
___
dev mailing list
dev@openvswitch.org
http://openvswitch.org/mailman/listinfo/dev
On Jan 10, 2013, at 11:24 AM, Ben Pfaff wrote:
> On Thu, Jan 10, 2013 at 09:30:31AM -0800, Justin Pettit wrote:
>> -for (ch = dpif->channels; ch < &dpif->channels[dpif->n_channels]; ch++)
>> {
>> +for (ch = dpif->channels; ch < &dpif->channels[dpif->uc_array_size];
>> ch++)
>
> A { g
On Thu, Jan 10, 2013 at 09:30:31AM -0800, Justin Pettit wrote:
> -for (ch = dpif->channels; ch < &dpif->channels[dpif->n_channels]; ch++) {
> +for (ch = dpif->channels; ch < &dpif->channels[dpif->uc_array_size];
> ch++)
A { got lost here somehow.
Also, I noticed that in the commit messa
On Jan 9, 2013, at 11:48 AM, Ben Pfaff wrote:
> Previously I commented on this but I didn't see a response in your
> follow-up. The first time, I said that I think that's going to prompt
> more questions than it's going to answer. How about:
>
>- With the Linux datapath, packets for new fl
Thanks for the revision. I have some further comments.
On Mon, Jan 07, 2013 at 05:32:29PM -0800, Justin Pettit wrote:
> +- The Linux datapath implementation creates a different kernel-
> + userspace channel for each port instead of sharing a static 16
> + channels to provide better
Userspace-kernel communication is a possible bottleneck when OVS is
receiving a large number of flow set up requests. To help prevent a bad
actor from consuming too much of this resource, we introduced channels
to segegrate traffic. Previously, we created 17 channels and
round-robin assigned port
