DPDK patches and discussions
 help / color / mirror / Atom feed
From: Maxime Coquelin <maxime.coquelin@redhat.com>
To: dev@dpdk.org, tiwei.bie@intel.com, zhihong.wang@intel.com
Subject: Re: [dpdk-dev] [PATCH v2 0/2] Vhost: unitfy receive paths
Date: Fri, 8 Jun 2018 15:58:04 +0200	[thread overview]
Message-ID: <407773c9-8653-a35b-d531-475b2491bff4@redhat.com> (raw)
In-Reply-To: <20180529094514.23835-1-maxime.coquelin@redhat.com>



On 05/29/2018 11:45 AM, Maxime Coquelin wrote:
> Hi,
> 
> This second version fixes the feature bit check in
> rxvq_is_mergeable(), and remove "mergeable" from rx funcs
> names. No difference is seen in the benchmarks
> 
> This series is preliminary work to ease the integration of
> packed ring layout support. But even without packed ring
> layout, the result is positive.
> 
> First patch unify both paths, and second one is a small
> optimization to avoid copying batch_copy_nb_elems VQ field
> to/from the stack.
> 
> With the series applied, I get modest performance gain for
> both mergeable and non-mergeable casesi (, and the gain of
> about 300 LoC is non negligible maintenance-wise.
> 
> Rx-mrg=off benchmarks:
> 
> +------------+-------+-------------+-------------+----------+
> |    Run     |  PVP  | Guest->Host | Host->Guest | Loopback |
> +------------+-------+-------------+-------------+----------+
> | v18.05-rc5 | 14.47 |       16.64 |       17.57 |    13.15 |
> | + series   | 14.87 |       16.86 |       17.70 |    13.30 |
> +------------+-------+-------------+-------------+----------+
> 
> Rx-mrg=on benchmarks:
> 
> +------------+------+-------------+-------------+----------+
> |    Run     | PVP  | Guest->Host | Host->Guest | Loopback |
> +------------+------+-------------+-------------+----------+
> | v18.05-rc5 | 9.38 |       13.78 |       16.70 |    12.79 |
> | + series   | 9.38 |       13.80 |       17.49 |    13.36 |
> +------------+------+-------------+-------------+----------+
> 
> Note: Even without my series, the guest->host benchmark with
> mergeable buffers enabled looks suspicious as it should in
> theory be alsmost identical as when Rx mergeable buffers are
> disabled. To be investigated...
> 
> Maxime Coquelin (2):
>    vhost: unify Rx mergeable and non-mergeable paths
>    vhost: improve batched copies performance
> 
>   lib/librte_vhost/virtio_net.c | 376 +++++-------------------------------------
>   1 file changed, 37 insertions(+), 339 deletions(-)
> 

Applied to dpdk-next-virtio.

Maxime

      parent reply	other threads:[~2018-06-08 13:58 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-05-29  9:45 Maxime Coquelin
2018-05-29  9:45 ` [dpdk-dev] [PATCH v2 1/2] vhost: unify Rx mergeable and non-mergeable paths Maxime Coquelin
2018-05-29  9:45 ` [dpdk-dev] [PATCH v2 2/2] vhost: improve batched copies performance Maxime Coquelin
2018-05-31  9:55 ` [dpdk-dev] [PATCH v2 0/2] Vhost: unitfy receive paths Wang, Zhihong
2018-05-31 12:52   ` Maxime Coquelin
2018-06-08 13:58 ` Maxime Coquelin [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=407773c9-8653-a35b-d531-475b2491bff4@redhat.com \
    --to=maxime.coquelin@redhat.com \
    --cc=dev@dpdk.org \
    --cc=tiwei.bie@intel.com \
    --cc=zhihong.wang@intel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).