All of lore.kernel.org
 help / color / mirror / Atom feed
From: David Daney <ddaney@caviumnetworks.com>
To: Aaro Koskinen <aaro.koskinen@iki.fi>
Cc: driverdev-devel <devel@driverdev.osuosl.org>,
	linux-mips <linux-mips@linux-mips.org>,
	netdev <netdev@vger.kernel.org>,
	David Daney <ddaney@caviumnetworks.com>,
	Aaro Koskinen <aaro.koskinen@nokia.com>
Subject: Re: Improving OCTEON II 10G Ethernet performance
Date: Thu, 25 Aug 2016 13:11:45 -0700	[thread overview]
Message-ID: <57BF5101.6080909@caviumnetworks.com> (raw)
In-Reply-To: <20160825182210.GE12169@raspberrypi.musicnaut.iki.fi>

On 08/25/2016 11:22 AM, Aaro Koskinen wrote:
> Hi,
>
> On Thu, Aug 25, 2016 at 09:50:15AM -0700, David Daney wrote:
>> Ideally we would configure the packet classifiers on the RX side to create
>> multiple RX queues based on a hash of the TCP 5-tuple, and handle each queue
>> with a single NAPI instance.  That should result in better performance while
>> maintaining packet ordering.
>
> Would this need anything else than reprogramming CVMX_PIP_PRT_TAGX, and
> eliminating the global pow_receive_group and creating multiple NAPI instances
> and registering IRQ handlers?
>

That is essentially how it works.  Set the tag generation parameters, 
and use the low order bits of the tag to select which POW/SSO group is 
assigned.  The SSO group corresponds to an "rx queue"


> In the Yocto tree, the CVMX_PIP_PRT_TAGX register values are actually
> documented:
>
> http://git.yoctoproject.org/cgit/cgit.cgi/linux-yocto-contrib/tree/arch/mips/include/asm/octeon/cvmx-pip-defs.h?h=apaliwal/octeon#n3737

Wow, I didn't realize that documentation was made public.


>
> A.
>

WARNING: multiple messages have this Message-ID (diff)
From: David Daney <ddaney@caviumnetworks.com>
To: Aaro Koskinen <aaro.koskinen@iki.fi>
Cc: David Daney <ddaney@caviumnetworks.com>,
	Ed Swierk <eswierk@skyportsystems.com>,
	linux-mips <linux-mips@linux-mips.org>,
	driverdev-devel <devel@driverdev.osuosl.org>,
	netdev <netdev@vger.kernel.org>,
	Aaro Koskinen <aaro.koskinen@nokia.com>
Subject: Re: Improving OCTEON II 10G Ethernet performance
Date: Thu, 25 Aug 2016 13:11:45 -0700	[thread overview]
Message-ID: <57BF5101.6080909@caviumnetworks.com> (raw)
In-Reply-To: <20160825182210.GE12169@raspberrypi.musicnaut.iki.fi>

On 08/25/2016 11:22 AM, Aaro Koskinen wrote:
> Hi,
>
> On Thu, Aug 25, 2016 at 09:50:15AM -0700, David Daney wrote:
>> Ideally we would configure the packet classifiers on the RX side to create
>> multiple RX queues based on a hash of the TCP 5-tuple, and handle each queue
>> with a single NAPI instance.  That should result in better performance while
>> maintaining packet ordering.
>
> Would this need anything else than reprogramming CVMX_PIP_PRT_TAGX, and
> eliminating the global pow_receive_group and creating multiple NAPI instances
> and registering IRQ handlers?
>

That is essentially how it works.  Set the tag generation parameters, 
and use the low order bits of the tag to select which POW/SSO group is 
assigned.  The SSO group corresponds to an "rx queue"


> In the Yocto tree, the CVMX_PIP_PRT_TAGX register values are actually
> documented:
>
> http://git.yoctoproject.org/cgit/cgit.cgi/linux-yocto-contrib/tree/arch/mips/include/asm/octeon/cvmx-pip-defs.h?h=apaliwal/octeon#n3737

Wow, I didn't realize that documentation was made public.


>
> A.
>

  reply	other threads:[~2016-08-25 20:11 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-08-25  1:29 Improving OCTEON II 10G Ethernet performance Ed Swierk
2016-08-25 16:50 ` David Daney
2016-08-25 18:22   ` Aaro Koskinen
2016-08-25 18:22     ` Aaro Koskinen
2016-08-25 20:11     ` David Daney [this message]
2016-08-25 20:11       ` David Daney
2016-08-25 21:18       ` Aaro Koskinen
2016-08-25 21:18         ` Aaro Koskinen
2016-08-25 22:26         ` David Daney
2016-08-25 22:26           ` David Daney
2016-08-25 17:32 ` Aaro Koskinen
2016-08-25 17:32   ` Aaro Koskinen

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=57BF5101.6080909@caviumnetworks.com \
    --to=ddaney@caviumnetworks.com \
    --cc=aaro.koskinen@iki.fi \
    --cc=aaro.koskinen@nokia.com \
    --cc=devel@driverdev.osuosl.org \
    --cc=linux-mips@linux-mips.org \
    --cc=netdev@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.