From: Rich Lane <rich.lane@bigswitch.com>
To: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Cc: dev@dpdk.org, Huawei Xie <huawei.xie@intel.com>,
"Wang, Zhihong" <zhihong.wang@intel.com>
Subject: Re: [dpdk-dev] [PATCH] vhost: add back support for concurrent enqueue
Date: Tue, 23 Aug 2016 15:42:30 -0700 [thread overview]
Message-ID: <CAGSMBPPqNDZjVFWCGCjsvTo95J9b-Vx-1WZzzOBQ7korknbXHg@mail.gmail.com> (raw)
In-Reply-To: <20160822141636.GC30752@yliu-dev.sh.intel.com>
On Mon, Aug 22, 2016 at 7:16 AM, Yuanhan Liu <yuanhan.liu@linux.intel.com>
wrote:
> On Thu, Aug 18, 2016 at 11:27:06AM -0700, Rich Lane wrote:
> > On Mon, Aug 15, 2016 at 7:37 PM, Yuanhan Liu <
> yuanhan.liu@linux.intel.com>
> > wrote:
> >
> > On Mon, Aug 15, 2016 at 01:00:24PM -0700, Rich Lane wrote:
> > > Concurrent enqueue is an important performance optimization when
> the
> > number
> > > of cores used for switching is different than the number of vhost
> queues.
> > > I've observed a 20% performance improvement compared to a strategy
> that
> > > binds queues to cores.
> > >
> > > The atomic cmpset is only executed when the application calls
> > > rte_vhost_enqueue_burst_mp. Benchmarks show no performance impact
> > > when not using concurrent enqueue.
> > >
> > > Mergeable RX buffers aren't supported by concurrent enqueue to
> minimize
> > > code complexity.
> >
> > I think that would break things when Mergeable rx is enabled (which
> is
> > actually enabled by default).
> >
> >
> > Would it be reasonable to return -ENOTSUP in this case, and restrict
> concurrent
> > enqueue
> > to devices where VIRTIO_NET_F_MRG_RXBUF is disabled?
> >
> > I could also add back concurrent enqueue support for mergeable RX, but I
> was
> > hoping to avoid
> > that since the mergeable codepath is already complex and wouldn't be
> used in
> > high performance
> > deployments.
>
> Another note is that, you might also have noticed, Zhihong made a patch
> set [0] to optimize the enqueue code path (mainly on mergeable path). It
> basically does a rewrite from scatch, which removes the desc buf
> reservation,
> meaning it would be harder to do concurrent enqueue support based on that.
>
> [0]: Aug 19 Zhihong Wang ( 68) ├─>[PATCH v3 0/5] vhost: optimize
> enqueue
>
Yes, I'd noticed that these patches would conflict. Once the vhost-cuse
removal and
Zhihong's patches have merged I'll send a new version.
next prev parent reply other threads:[~2016-08-23 22:42 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-08-15 20:00 Rich Lane
2016-08-16 2:37 ` Yuanhan Liu
2016-08-18 18:27 ` Rich Lane
2016-08-22 14:16 ` Yuanhan Liu
2016-08-23 22:42 ` Rich Lane [this message]
2017-03-09 13:46 ` Thomas Monjalon
2017-03-14 5:59 ` Yuanhan Liu
2016-09-11 12:18 ` 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=CAGSMBPPqNDZjVFWCGCjsvTo95J9b-Vx-1WZzzOBQ7korknbXHg@mail.gmail.com \
--to=rich.lane@bigswitch.com \
--cc=dev@dpdk.org \
--cc=huawei.xie@intel.com \
--cc=yuanhan.liu@linux.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).