[dpdk-dev] [PATCH v2 1/3] packet_ordering: add statistics for each worker thread

Phil Yang (Arm Technology China) Phil.Yang at arm.com
Sat Mar 30 17:55:22 CET 2019


> -----Original Message-----
> From: Pattan, Reshma <reshma.pattan at intel.com>
> Sent: Saturday, March 30, 2019 12:40 AM
> To: Phil Yang (Arm Technology China) <Phil.Yang at arm.com>; dev at dpdk.org;
> thomas at monjalon.net
> Cc: Hunt, David <david.hunt at intel.com>; Gavin Hu (Arm Technology China)
> <Gavin.Hu at arm.com>; Honnappa Nagarahalli
> <Honnappa.Nagarahalli at arm.com>; nd <nd at arm.com>
> Subject: RE: [PATCH v2 1/3] packet_ordering: add statistics for each worker
> thread
> 
> 
> 
> > -----Original Message-----
> > From: Phil Yang [mailto:phil.yang at arm.com]
> >
> > The current implementation using '__sync' built-ins to synchronize
> > statistics within worker threads. '__sync' built-ins functions are
> > full barriers which will affect the performance, so add a per worker packets
> statistics.
> >
> > Enable by option --insight-worker.
> >
> 
> I don't feel the need of this new option to print per core stats.  Any reason
> for this?

Hi Reshma,

Thanks for your comment. 
The per core stats aims at removing the '__sync' builtin full barrier in the worker thread. 
It records the workload of each core (It shows the bottleneck core as well).  Since the maximum core number may be more than 128, so disable the print in default and add this new option for debugging use. 

Anyway, if you insist there is no need to print that info out, I can remove the option. But I think using per core stats will benefit performance.

Thanks,
Phil

> 
> Thanks,
> Reshma


More information about the dev mailing list