From: Yuanhan Liu <yuanhan.liu@linux.intel.com>
To: Rich Lane <rich.lane@bigswitch.com>
Cc: dev@dpdk.org, "huawei.xie" <huawei.xie@intel.com>
Subject: Re: [PATCH 0/3] [RFC] vhost: micro vhost optimization
Date: Tue, 10 May 2016 15:08:45 -0700 [thread overview]
Message-ID: <20160510220845.GW5641@yliu-dev.sh.intel.com> (raw)
In-Reply-To: <CAGSMBPM3NCaw+Q1U2zkcAJBkv2DZP=z_GPLodfB=9eur7hrcag@mail.gmail.com>
On Tue, May 10, 2016 at 02:49:43PM -0700, Rich Lane wrote:
> I see a significant performance improvement with these patches, around 5% at 64
> bytes.
Thanks for testing.
>
> The one patch that didn't give any performance boost for me was "vhost: arrange
> virtio_net fields for better cache sharing".
Yeah, same here from my test. I mean, in theory, it should give us a
tiny boost, it doesn't in real life though. And since it (should) do
no harm, I would still include this patch in this set. Maybe I should
have noted at first that no real perf gain from the 3rd patch.
--yliu
>
> Tested-by: Rich Lane <rich.lane@bigswitch.com>
>
> On Mon, May 2, 2016 at 5:46 PM, Yuanhan Liu <yuanhan.liu@linux.intel.com>
> wrote:
>
> Here is a small patch set does the micro optimization, which brings about
> 10% performance boost in my 64B packet testing, with the following topo:
>
> pkt generator <----> NIC <-----> Virtio NIC
>
> Patch 1 pre updates the used ring and update them in batch. It should be
> feasible from my understanding: there will be no issue, guest driver will
> not start processing them as far as we haven't updated the "used->idx"
> yet. I could miss something though.
>
> Patch 2 saves one check for small packets (that can be hold in one desc
> buf and mbuf).
>
> Patch 3 moves several frequently used fields into one cache line, for
> better cache sharing.
>
> Note that this patch set is based on my latest vhost ABI refactoring
> patchset.
>
>
> ---
> Yuanhan Liu (3):
> vhost: pre update used ring for Tx and Rx
> vhost: optimize dequeue for small packets
> vhost: arrange virtio_net fields for better cache sharing
>
> lib/librte_vhost/vhost-net.h | 8 +--
> lib/librte_vhost/vhost_rxtx.c | 110
> ++++++++++++++++++++++++------------------
> 2 files changed, 68 insertions(+), 50 deletions(-)
>
> --
> 1.9.0
>
>
>
next prev parent reply other threads:[~2016-05-10 22:04 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-05-03 0:46 [PATCH 0/3] [RFC] vhost: micro vhost optimization Yuanhan Liu
2016-05-03 0:46 ` [PATCH 1/3] vhost: pre update used ring for Tx and Rx Yuanhan Liu
2016-06-01 6:40 ` Xie, Huawei
2016-06-01 6:55 ` Yuanhan Liu
2016-06-03 8:18 ` Xie, Huawei
2016-06-01 13:05 ` Michael S. Tsirkin
2016-05-03 0:46 ` [PATCH 2/3] vhost: optimize dequeue for small packets Yuanhan Liu
2016-06-01 6:24 ` Xie, Huawei
2016-06-01 6:44 ` Yuanhan Liu
2016-06-03 7:42 ` Xie, Huawei
2016-06-03 7:43 ` Xie, Huawei
2016-05-03 0:46 ` [PATCH 3/3] vhost: arrange virtio_net fields for better cache sharing Yuanhan Liu
2016-06-01 6:42 ` Xie, Huawei
2016-05-10 21:49 ` [PATCH 0/3] [RFC] vhost: micro vhost optimization Rich Lane
2016-05-10 22:08 ` Yuanhan Liu [this message]
2016-06-14 12:42 ` Yuanhan Liu
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=20160510220845.GW5641@yliu-dev.sh.intel.com \
--to=yuanhan.liu@linux.intel.com \
--cc=dev@dpdk.org \
--cc=huawei.xie@intel.com \
--cc=rich.lane@bigswitch.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.