All of lore.kernel.org
 help / color / mirror / Atom feed
From: Saeed Mahameed <saeedm@dev.mellanox.co.il>
To: Tom Herbert <tom@herbertland.com>
Cc: Saeed Mahameed <saeedm@mellanox.com>,
	"David S. Miller" <davem@davemloft.net>,
	Linux Kernel Network Developers <netdev@vger.kernel.org>,
	Kernel Team <kernel-team@fb.com>
Subject: Re: [PATCH net-next 00/12] Mellanox mlx5e XDP performance optimization
Date: Sun, 26 Mar 2017 11:16:38 +0200	[thread overview]
Message-ID: <CALzJLG80OErFDz=6x3q4p3-tCNXV5RZeAK6E4dvYeCYpKQHCgQ@mail.gmail.com> (raw)
In-Reply-To: <CALx6S35AMWNeGDOx7d+M5Dqd-B60HGzwhmbLtcoPS2PfpA2m9Q@mail.gmail.com>

On Sat, Mar 25, 2017 at 6:54 PM, Tom Herbert <tom@herbertland.com> wrote:
> On Fri, Mar 24, 2017 at 2:52 PM, Saeed Mahameed <saeedm@mellanox.com> wrote:
>> Hi Dave,
>>
>> This series provides some preformancee optimizations for mlx5e
>> driver, especially for XDP TX flows.
>>
>> 1st patch is a simple change of rmb to dma_rmb in CQE fetch routine
>> which shows a huge gain for both RX and TX packet rates.
>>
>> 2nd patch removes write combining logic from the driver TX handler
>> and simplifies the TX logic while improving TX CPU utilization.
>>
>> All other patches combined provide some refactoring to the driver TX
>> flows to allow some significant XDP TX improvements.
>>
>> More details and performance numbers per patch can be found in each patch
>> commit message compared to the preceding patch.
>>
>> Overall performance improvemnets
>>   System: Intel(R) Xeon(R) CPU E5-2620 v3 @ 2.40GHz
>>
>> Test case                   Baseline      Now      improvement
>> ---------------------------------------------------------------
>> TX packets (24 threads)     45Mpps        54Mpps      20%
>> TC stack Drop (1 core)      3.45Mpps      3.6Mpps     5%
>> XDP Drop      (1 core)      14Mpps        16.9Mpps    20%
>> XDP TX        (1 core)      10.4Mpps      13.7Mpps    31%
>>
> Awesome, and good timing. I'll be presenting XDP at IETF next and
> would like to include these numbers in the presentation if you don't
> mind...
>

Not at all, please go ahead.

But as you see, the system i tested on is not that powerful. We can
get even better results with a modern system.
If you want i can provide you those numbers by mid-week.

      reply	other threads:[~2017-03-26  9:17 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-03-24 21:52 [PATCH net-next 00/12] Mellanox mlx5e XDP performance optimization Saeed Mahameed
2017-03-24 21:52 ` [PATCH net-next 01/12] net/mlx5e: Use dma_rmb rather than rmb in CQE fetch routine Saeed Mahameed
2017-03-24 21:52 ` [PATCH net-next 02/12] net/mlx5e: Xmit, no write combining Saeed Mahameed
2017-03-24 21:52 ` [PATCH net-next 03/12] net/mlx5e: Single bfreg (UAR) for all mlx5e SQs and netdevs Saeed Mahameed
2017-03-24 21:52 ` [PATCH net-next 04/12] net/mlx5e: Move XDP completion functions to rx file Saeed Mahameed
2017-03-24 21:52 ` [PATCH net-next 05/12] net/mlx5e: Move mlx5e_rq struct declaration Saeed Mahameed
2017-03-24 21:52 ` [PATCH net-next 06/12] net/mlx5e: Move XDP SQ instance into RQ Saeed Mahameed
2017-03-24 21:52 ` [PATCH net-next 07/12] net/mlx5e: Poll XDP TX CQ before RX CQ Saeed Mahameed
2017-03-24 21:52 ` [PATCH net-next 08/12] net/mlx5e: Optimize XDP frame xmit Saeed Mahameed
2017-03-24 21:52 ` [PATCH net-next 09/12] net/mlx5e: Generalize tx helper functions for different SQ types Saeed Mahameed
2017-03-24 21:52 ` [PATCH net-next 10/12] net/mlx5e: Proper names for SQ/RQ/CQ functions Saeed Mahameed
2017-03-24 21:52 ` [PATCH net-next 11/12] net/mlx5e: Generalize SQ create/modify/destroy functions Saeed Mahameed
2017-03-24 21:52 ` [PATCH net-next 12/12] net/mlx5e: Different SQ types Saeed Mahameed
2017-03-24 23:26 ` [PATCH net-next 00/12] Mellanox mlx5e XDP performance optimization Alexei Starovoitov
2017-03-25 12:30   ` Saeed Mahameed
2017-03-25  2:12 ` David Miller
2017-03-25 16:54 ` Tom Herbert
2017-03-26  9:16   ` Saeed Mahameed [this message]

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='CALzJLG80OErFDz=6x3q4p3-tCNXV5RZeAK6E4dvYeCYpKQHCgQ@mail.gmail.com' \
    --to=saeedm@dev.mellanox.co.il \
    --cc=davem@davemloft.net \
    --cc=kernel-team@fb.com \
    --cc=netdev@vger.kernel.org \
    --cc=saeedm@mellanox.com \
    --cc=tom@herbertland.com \
    /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.