Netdev List
 help / color / mirror / Atom feed
From: Eric Dumazet <eric.dumazet@gmail.com>
To: Alexander Duyck <alexander.h.duyck@intel.com>
Cc: netdev@vger.kernel.org, davem@davemloft.net, jeffrey.t.kirsher@intel.com
Subject: Re: [PATCH] net: Update netdev_alloc_frag to work more efficiently with TCP and GRO
Date: Wed, 20 Jun 2012 10:17:03 +0200	[thread overview]
Message-ID: <1340180223.4604.828.camel@edumazet-glaptop> (raw)
In-Reply-To: <1340170590.4604.784.camel@edumazet-glaptop>

On Wed, 2012-06-20 at 07:36 +0200, Eric Dumazet wrote:

> I tested this idea one month ago and got not convincing results, because
> the branch was taken half of the time.
> 
> The cases where page can be reused is probably specific to ixgbe because
> it uses a different allocator for the frags themselves.
> netdev_alloc_frag() is only used to allocate the skb head.
> 
> For typical nics, we allocate frags to populate the RX ring _way_ before
> packet is received by the NIC.
> 
> Then, I played with using order-2 pages instead of order-0 ones if
> PAGE_SIZE < 8192.
> 
> No clear win either, but you might try this too.

By the way, big cost in netdev_alloc_frag() is the irq masking/restore
We probably could have a version for softirq users...

Another idea would also use a pool of pages, instead of a single one,
if we want to play with the "clear the offset if page count is one"
idea.

Strange, I did again benchs with order-2 allocations and got good
results this time, but with latest net-next, maybe things have changed
since last time I did this.

(netdev_alloc_frag(), get_page_from_freelist() and put_page() less
prevalent in perf results)

  reply	other threads:[~2012-06-20  8:17 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-06-20  0:43 [PATCH] net: Update netdev_alloc_frag to work more efficiently with TCP and GRO Alexander Duyck
2012-06-20  1:49 ` Alexander Duyck
2012-06-20  5:36 ` Eric Dumazet
2012-06-20  8:17   ` Eric Dumazet [this message]
2012-06-20  8:44     ` Eric Dumazet
2012-06-20  9:04       ` David Miller
2012-06-20  9:14         ` Eric Dumazet
2012-06-20 13:21     ` Eric Dumazet
2012-06-21  4:07       ` Alexander Duyck
2012-06-21  5:07         ` Eric Dumazet
2012-06-22 12:33           ` Eric Dumazet
2012-06-23  0:17             ` Alexander Duyck
2012-06-29 23:04             ` Alexander Duyck
2012-06-30  8:39               ` Eric Dumazet
2012-06-21  5:56     ` David Miller
2012-06-20 16:30   ` Alexander Duyck
2012-06-20 17:14     ` Alexander Duyck
2012-06-20 18:41       ` Eric Dumazet
2012-06-20 20:10         ` Alexander Duyck

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=1340180223.4604.828.camel@edumazet-glaptop \
    --to=eric.dumazet@gmail.com \
    --cc=alexander.h.duyck@intel.com \
    --cc=davem@davemloft.net \
    --cc=jeffrey.t.kirsher@intel.com \
    --cc=netdev@vger.kernel.org \
    /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