On Fri, 2016-08-19 at 18:09 -0700, David Miller wrote:
> From: Eric Dumazet
> Date: Fri, 19 Aug 2016 12:56:56 -0700
>
> > On Fri, 2016-08-19 at 16:47 -0300, Thadeu Lima de Souza Cascardo wrote:
> >> Instead of using flow stats per NUMA node, use it per CPU. When using
> >> megaflows, the stats lo
From: Eric Dumazet
Date: Fri, 19 Aug 2016 12:56:56 -0700
> On Fri, 2016-08-19 at 16:47 -0300, Thadeu Lima de Souza Cascardo wrote:
>> Instead of using flow stats per NUMA node, use it per CPU. When using
>> megaflows, the stats lock can be a bottleneck in scalability.
>
> ...
>
>>
>> flo
On Fri, 2016-08-19 at 16:47 -0300, Thadeu Lima de Souza Cascardo wrote:
> Instead of using flow stats per NUMA node, use it per CPU. When using
> megaflows, the stats lock can be a bottleneck in scalability.
...
>
> flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow)
> -
Instead of using flow stats per NUMA node, use it per CPU. When using
megaflows, the stats lock can be a bottleneck in scalability.
On a E5-2690 12-core system, usual throughput went from ~4Mpps to ~15Mpps
when forwarding between two 40GbE ports with a single flow configured on
the datapath.
---