netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Ben Hutchings <bhutchings@solarflare.com>
To: Anton Blanchard <anton@samba.org>
Cc: leitao@linux.vnet.ibm.com, michael@ellerman.id.au,
	jesse@kernel.org, netdev@vger.kernel.org
Subject: Re: [PATCH 07/15] ehea: Allocate large enough skbs to avoid partial cacheline DMA writes
Date: Thu, 12 May 2011 03:52:48 +0100	[thread overview]
Message-ID: <1305168768.4065.382.camel@localhost> (raw)
In-Reply-To: <20110512005623.100278010@samba.org>

On Thu, 2011-05-12 at 10:52 +1000, Anton Blanchard wrote:
> plain text document attachment (ehea_8.patch)
> The ehea adapter has a mode where it will avoid partial cacheline DMA
> writes on receive by always padding packets to fall on a cacheline
> boundary.
> 
> Unfortunately we currently aren't allocating enough space for a full
> ethernet MTU packet to be rounded up, so this optimisation doesn't hit.
> 
> It's unfortunate that the next largest packet size exposed by the
> hypervisor interface is 2kB, meaning our skb allocation comes out of a
> 4kB SLAB. However the performance increase due to this optimisation is
> quite large and my TCP stream numbers increase from 900MB to 1000MB/sec.

You can allocate page buffers and then split them into exactly 2K
segments.  If you switch from inet_lro to GRO then GRO will handle the
eventual skb allocation for you (even for non-mergeable packets).

Ben.

-- 
Ben Hutchings, Senior Software Engineer, Solarflare
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.


  reply	other threads:[~2011-05-12  2:52 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-05-12  0:52 [PATCH 00/15] ehea updates v2 Anton Blanchard
2011-05-12  0:52 ` [PATCH 01/15] ehea: Remove NETIF_F_LLTX Anton Blanchard
2011-05-12  0:52 ` [PATCH 02/15] ehea: Update multiqueue support Anton Blanchard
2011-05-12  2:31   ` Joe Perches
2011-05-12  2:57   ` Ben Hutchings
2011-05-12  0:52 ` [PATCH 03/15] ehea: Remove force_irq logic in napi poll routine Anton Blanchard
2011-05-12  2:31   ` Joe Perches
2011-05-12  3:06     ` David Miller
2011-05-12  2:47   ` Ben Hutchings
2011-05-24  3:32   ` Benjamin Herrenschmidt
2011-05-12  0:52 ` [PATCH 04/15] ehea: Remove num_tx_qps module option Anton Blanchard
2011-05-12  0:52 ` [PATCH 05/15] ehea: Dont check NETIF_F_TSO in TX path Anton Blanchard
2011-05-12  0:52 ` [PATCH 06/15] ehea: Add vlan_features Anton Blanchard
2011-05-12  0:52 ` [PATCH 07/15] ehea: Allocate large enough skbs to avoid partial cacheline DMA writes Anton Blanchard
2011-05-12  2:52   ` Ben Hutchings [this message]
2011-05-12  0:52 ` [PATCH 08/15] ehea: Simplify ehea_xmit2 and ehea_xmit3 Anton Blanchard
2011-05-12  0:52 ` [PATCH 09/15] ehea: Merge swqe2 TSO and non TSO paths Anton Blanchard
2011-05-12  0:52 ` [PATCH 10/15] ehea: Simplify type 3 transmit routine Anton Blanchard
2011-05-12  0:52 ` [PATCH 11/15] ehea: Remove some unused definitions Anton Blanchard
2011-05-12  0:52 ` [PATCH 12/15] ehea: Add 64bit statistics Anton Blanchard
2011-05-12  0:52 ` [PATCH 13/15] ehea: Remove LRO support Anton Blanchard
2011-05-12  0:52 ` [PATCH 14/15] ehea: Add GRO support Anton Blanchard
2011-05-12  6:03   ` Michał Mirosław
2011-05-12  0:52 ` [PATCH 15/15] ehea: Remove unused tcp_end field in send WQ Anton Blanchard
2011-05-12  2:31   ` Joe Perches
2011-05-12  3:06     ` David Miller
2011-05-12  3:12       ` Joe Perches
2011-05-31  1:16         ` Benjamin Herrenschmidt
  -- strict thread matches above, loose matches on Subject: below --
2011-10-14 15:30 EHEA updates Thadeu Lima de Souza Cascardo
2011-10-14 15:31 ` [PATCH 07/15] ehea: Allocate large enough skbs to avoid partial cacheline DMA writes Thadeu Lima de Souza Cascardo

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=1305168768.4065.382.camel@localhost \
    --to=bhutchings@solarflare.com \
    --cc=anton@samba.org \
    --cc=jesse@kernel.org \
    --cc=leitao@linux.vnet.ibm.com \
    --cc=michael@ellerman.id.au \
    --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;
as well as URLs for NNTP newsgroup(s).