[dpdk-dev] [PATCH v2] examples/l3fwd: pass flow arguments when start app

Wu, Jingjing jingjing.wu at intel.com
Tue Oct 10 09:57:00 CEST 2017



> -----Original Message-----
> From: Wu, Jingjing
> Sent: Thursday, October 5, 2017 4:36 PM
> To: Stephen Hemminger <stephen at networkplumber.org>; Li, Xiaoyun
> <xiaoyun.li at intel.com>
> Cc: dev at dpdk.org
> Subject: RE: [dpdk-dev] [PATCH v2] examples/l3fwd: pass flow arguments when
> start app
> 
> 
> 
> > -----Original Message-----
> > From: Stephen Hemminger [mailto:stephen at networkplumber.org]
> > Sent: Monday, October 2, 2017 1:24 AM
> > To: Li, Xiaoyun <xiaoyun.li at intel.com>
> > Cc: Wu, Jingjing <jingjing.wu at intel.com>; dev at dpdk.org
> > Subject: Re: [dpdk-dev] [PATCH v2] examples/l3fwd: pass flow arguments
> > when start app
> >
> > On Sat, 30 Sep 2017 09:59:08 +0800
> > Xiaoyun Li <xiaoyun.li at intel.com> wrote:
> >
> > > To make the performance can be tuning on different NICs or
> > > platforms. We need to make the number of descriptors and Rx/TX
> > > threshold as arguments when starting l3fwd application.
> > >
> > > Signed-off-by: Xiaoyun Li <xiaoyun.li at intel.com>
> >
> > Not sure about this. The point of l3fwd is to make it as simple an
> > application as possible to help users.
> >
> > Given that drivers can now supply default values for thresholds, I
> > think the l3fwd sample should get rid of all the special descriptor
> > values it is setting. Then if the values are not right for best
> > performance that should be pushed back to the driver writer to fix.
> 
> But now what the driver using are the arguments passed from l3fwd
> application, such as RTE_TEST_RX_DESC_DEFAULT. About the threshold, I guess
> it is already done by driver to use default value. For number of descriptors, any
> ideas? Diver to provide a suggestion one?
> 

And additionally, even driver provides a suggestion value for descriptors or threshold,
on different platform, the performance result also varies. So I think xiaoyun's change to
pass those are arguments makes sense.


Thanks
Jingjing


More information about the dev mailing list