linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Jesper Dangaard Brouer <brouer@redhat.com>
To: lsf@lists.linux-foundation.org, linux-mm <linux-mm@kvack.org>
Cc: brouer@redhat.com,
	James Bottomley <James.Bottomley@HansenPartnership.com>,
	"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
	Tom Herbert <tom@herbertland.com>,
	Alexei Starovoitov <alexei.starovoitov@gmail.com>,
	Brenden Blanco <bblanco@plumgrid.com>,
	lsf-pc@lists.linux-foundation.org
Subject: [LSF/MM TOPIC] Generic page-pool recycle facility?
Date: Thu, 7 Apr 2016 16:17:15 +0200	[thread overview]
Message-ID: <20160407161715.52635cac@redhat.com> (raw)
In-Reply-To: <1460034425.20949.7.camel@HansenPartnership.com>

(Topic proposal for MM-summit)

Network Interface Cards (NIC) drivers, and increasing speeds stress
the page-allocator (and DMA APIs).  A number of driver specific
open-coded approaches exists that work-around these bottlenecks in the
page allocator and DMA APIs. E.g. open-coded recycle mechanisms, and
allocating larger pages and handing-out page "fragments".

I'm proposing a generic page-pool recycle facility, that can cover the
driver use-cases, increase performance and open up for zero-copy RX.


The basic performance problem is that pages (containing packets at RX)
are cycled through the page allocator (freed at TX DMA completion
time).  While a system in a steady state, could avoid calling the page
allocator, when having a pool of pages equal to the size of the RX
ring plus the number of outstanding frames in the TX ring (waiting for
DMA completion).

The motivation for quick page recycling came primarily for performance
reasons.  But returning pages to the same pool also benefit other
use-cases.  If a NIC HW RX ring is strictly bound (e.g. to a process
or guest/KVM) then pages can be shared/mmap'ed (RX zero-copy) as
information leaking does not occur.  (Obviously for this use-case,
when adding pages into the pool these need to zero'ed out).


The motivation behind implemeting this (extremely fast page-pool) is
because we need it as a building block in the network stack, but
hopefully other areas could also benefit from this.


[Resources/Links]: It is specifically related to:

What Facebook calls XDP (eXpress Data Path)
 * https://github.com/iovisor/bpf-docs/blob/master/Express_Data_Path.pdf
 * RFC patchset thread: http://thread.gmane.org/gmane.linux.network/406288

And what I call the "packet-page" level:
 * BoF on kernel network performance: http://lwn.net/Articles/676806/
 * http://people.netfilter.org/hawk/presentations/NetDev1.1_2016/links.html


See you soon at LFS/MM-summit :-)
-- 
Best regards,
  Jesper Dangaard Brouer
  MSc.CS, Principal Kernel Engineer at Red Hat
  Author of http://www.iptv-analyzer.org
  LinkedIn: http://www.linkedin.com/in/brouer

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

       reply	other threads:[~2016-04-07 14:17 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <1460034425.20949.7.camel@HansenPartnership.com>
2016-04-07 14:17 ` Jesper Dangaard Brouer [this message]
2016-04-07 14:38   ` [Lsf-pc] [LSF/MM TOPIC] Generic page-pool recycle facility? Christoph Hellwig
2016-04-07 15:11     ` [Lsf] " Bart Van Assche
2016-04-10 18:45       ` Sagi Grimberg
2016-04-11 21:41         ` Jesper Dangaard Brouer
2016-04-11 22:02           ` Alexander Duyck
2016-04-12  6:28             ` Jesper Dangaard Brouer
2016-04-12 15:37               ` Alexander Duyck
2016-04-11 22:21           ` Alexei Starovoitov
2016-04-12  6:16             ` Jesper Dangaard Brouer
2016-04-12 17:20               ` Alexei Starovoitov
2016-04-07 15:48     ` Chuck Lever
2016-04-07 16:14       ` [Lsf-pc] [Lsf] " Rik van Riel
2016-04-07 19:43         ` [Lsf] [Lsf-pc] " Jesper Dangaard Brouer
2016-04-07 15:18   ` Eric Dumazet
2016-04-09  9:11     ` [Lsf] " Jesper Dangaard Brouer
2016-04-09 12:34       ` Eric Dumazet
2016-04-11 20:23         ` Jesper Dangaard Brouer
2016-04-11 21:27           ` Eric Dumazet
2016-04-07 19:48   ` Waskiewicz, PJ
2016-04-07 20:38     ` Jesper Dangaard Brouer
2016-04-08 16:12       ` Alexander Duyck
2016-04-11  8:58   ` [Lsf-pc] " Mel Gorman
2016-04-11 12:26     ` Jesper Dangaard Brouer
2016-04-11 13:08       ` Mel Gorman
2016-04-11 16:19         ` [Lsf] " Jesper Dangaard Brouer
2016-04-11 16:53           ` Eric Dumazet
2016-04-11 19:47             ` Jesper Dangaard Brouer
2016-04-11 21:14               ` Eric Dumazet
2016-04-11 18:07           ` Mel Gorman
2016-04-11 19:26             ` Jesper Dangaard Brouer
2016-04-11 16:20         ` Matthew Wilcox
2016-04-11 17:46           ` Thadeu Lima de Souza Cascardo
2016-04-11 18:37             ` Jesper Dangaard Brouer
2016-04-11 18:53               ` Bart Van Assche

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=20160407161715.52635cac@redhat.com \
    --to=brouer@redhat.com \
    --cc=James.Bottomley@HansenPartnership.com \
    --cc=alexei.starovoitov@gmail.com \
    --cc=bblanco@plumgrid.com \
    --cc=linux-mm@kvack.org \
    --cc=lsf-pc@lists.linux-foundation.org \
    --cc=lsf@lists.linux-foundation.org \
    --cc=netdev@vger.kernel.org \
    --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 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).