st, 2016 02:59
> *To:* Jan Scheurich
> *Cc:* dev@openvswitch.org; antonio.fische...@intel.com
> *Subject:* Re: [ovs-dev] [PATCH v4] dpif-netdev: dpcls per in_port with
> sorted subtables
>
>
>
> Hi Jan,
>
> thanks for the patch!
>
> I tried benchmarking with flow
-netdev: dpcls per in_port with sorted
subtables
Hi Jan,
thanks for the patch!
I tried benchmarking with flow tables from utilities/ovs-pipegen.py and the
results look very good.
[Jan] Do you have any numbers? Setting up pipelines is one thing. Is there are
standard test setup for measuring DPDK
Hi Jan,
thanks for the patch!
I tried benchmarking with flow tables from utilities/ovs-pipegen.py and the
results look very good.
I had to manually edit the patch to apply: some whitespaces are trimmed,
some lines are truncated and the form feeds('^L') are two separate
characters. Would you min
gt;> Scheurich
>> Sent: Wednesday, August 10, 2016 3:17 PM
>> To: dev@openvswitch.org
>> Cc: jan.scheur...@web.de
>> Subject: [ovs-dev] [PATCH v4] dpif-netdev: dpcls per in_port with
>> sorted subtables
>>
>> This replaces PATCH v3 (http://patchwo
Jan
> Scheurich
> Sent: Wednesday, August 10, 2016 3:17 PM
> To: dev@openvswitch.org
> Cc: jan.scheur...@web.de
> Subject: [ovs-dev] [PATCH v4] dpif-netdev: dpcls per in_port with
> sorted subtables
>
> This replaces PATCH v3 (http://patchwork.ozlabs.org/patch/657277).
> I
This replaces PATCH v3 (http://patchwork.ozlabs.org/patch/657277).
It should apply once Jarno's patch to revert the cpvector introduction
(http://patchwork.ozlabs.org/patch/657508) has been merged.
The user-space datapath (dpif-netdev) consists of a first level "exact match
cache" (EMC) matching
