[dpdk-dev] [PATCH v8 1/3] eal/x86: run-time dispatch over memcpy

[Yao, Lei A]

Hi, Thomas

> -----Original Message-----
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Thomas Monjalon
> Sent: Thursday, November 2, 2017 6:45 PM
> To: Wang, Zhihong <zhihong.wang at intel.com>; Li, Xiaoyun
> <xiaoyun.li at intel.com>
> Cc: dev at dpdk.org; Richardson, Bruce <bruce.richardson at intel.com>;
> Ananyev, Konstantin <konstantin.ananyev at intel.com>; Lu, Wenzhuo
> <wenzhuo.lu at intel.com>; Zhang, Helin <helin.zhang at intel.com>;
> ophirmu at mellanox.com
> Subject: Re: [dpdk-dev] [PATCH v8 1/3] eal/x86: run-time dispatch over
> memcpy
> 
> 02/11/2017 11:22, Wang, Zhihong:
> > > I don't know what is creating this drop exactly.
> > > When doing different tests on different environments, we do not see
> this
> > > drop.
> > > If nobody else can see such issue, I guess we can ignore it.
> >
> > Hi Thomas, Xiaoyun,
> >
> > With this patch (commit 84cc318424d49372dd2a5fbf3cf84426bf95acce) I see
> > more than 20% performance drop in vhost loopback test with testpmd
> > macswap for 256 bytes packets, which means it impacts actual vSwitching
> > performance.
> >
> > Suggest we fix it or revert it for this release.
> 
> I think we need more numbers to take a decision.
> What is the benefit of this patch? In which use-cases?
> What are the drawbacks? In which use-cases?
> 
> Please, it is a call to test performance with and without this patch
> in more environments (CPU, packet size, applications).

Following is the performance drop we observe in vhost/virtio loopback performance
with and without this patch
Test application: testpmd
CPU info: Intel(R) Xeon(R) CPU E5-2699 v4 @ 2.20GHz
OS: Ubuntu 16.04

Mergebale Path	
packet size	Performance Drop
64	-1.30%
128	0.81%
158	-19.17%
188	-19.18%
218	-16.29%
230	-16.57%
256	-16.77%
280	-3.07%
300	-3.22%
380	-2.44%
420	-1.65%
512	-0.99%
1024	0.00%
1518	-0.68%
	
Vector Path	
packet size	Performance Drop
64	3.30%
128	7.18%
256	-12.77%
512	-0.98%
1024	0.27%
1518	0.68%