Netdev List
 help / color / mirror / Atom feed
From: Ben Hutchings <bhutchings@solarflare.com>
To: Eric Dumazet <eric.dumazet@gmail.com>
Cc: David Miller <davem@davemloft.net>,
	netdev <netdev@vger.kernel.org>, Andi Kleen <ak@linux.intel.com>
Subject: Re: [PATCH net-next] net: more accurate skb truesize
Date: Thu, 13 Oct 2011 17:05:01 +0100	[thread overview]
Message-ID: <1318521901.2745.18.camel@bwh-desktop> (raw)
In-Reply-To: <1318519581.2393.18.camel@edumazet-HP-Compaq-6005-Pro-SFF-PC>

On Thu, 2011-10-13 at 17:26 +0200, Eric Dumazet wrote:
> skb truesize currently accounts for sk_buff struct and part of skb head.
> 
> Considering that skb_shared_info is larger than sk_buff, its time to
> take it into account for better memory accounting.
> 
> This patch introduces SKB_TRUESIZE(X) macro to centralize various
> assumptions into a single place.
> 
> At skb alloc phase, we put skb_shared_info struct at the exact end of
> skb head, to allow a better use of memory (lowering number of
> reallocations), since kmalloc() gives us power-of-two memory blocks.
[...]
> index 5b2c5f1..be66154 100644
> --- a/net/core/skbuff.c
> +++ b/net/core/skbuff.c
> @@ -184,11 +184,15 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
>  		goto out;
>  	prefetchw(skb);
>  
> -	size = SKB_DATA_ALIGN(size);
> -	data = kmalloc_node_track_caller(size + sizeof(struct skb_shared_info),
> -			gfp_mask, node);
> +	size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
[...]

If we want to put the data and skb_shared_info on separate cache-lines
then we should use:
	size = SKB_DATA_ALIGN(size) + sizeof(struct skb_shared_info);
(which is effectively what we're doing now).

If that's not important, and we just want to be sure that the allocation
occupies at least a whole cache line, then it should be:
	size = SKB_DATA_ALIGN(size + sizeof(struct skb_shared_info));

But I don't think it makes sense to use SKB_DATA_ALIGN(sizeof(struct
skb_shared_info)).

Ben.

-- 
Ben Hutchings, Staff 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:[~2011-10-13 16:05 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-10-13 15:26 [PATCH net-next] net: more accurate skb truesize Eric Dumazet
2011-10-13 16:05 ` Ben Hutchings [this message]
2011-10-13 16:24   ` Eric Dumazet
2011-10-13 16:32     ` Ben Hutchings
2011-10-13 17:11       ` Eric Dumazet
2011-10-13 17:13         ` Ben Hutchings
2011-10-13 17:28           ` Eric Dumazet
2011-10-13 20:05             ` David Miller
2011-10-13 20:33 ` Andi Kleen
2011-10-13 20:51   ` Eric Dumazet

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=1318521901.2745.18.camel@bwh-desktop \
    --to=bhutchings@solarflare.com \
    --cc=ak@linux.intel.com \
    --cc=davem@davemloft.net \
    --cc=eric.dumazet@gmail.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