netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Cong Wang <amwang@redhat.com>
To: David Miller <davem@davemloft.net>
Cc: eric.dumazet@gmail.com, netdev@vger.kernel.org,
	edumazet@google.com, ycheng@google.com, ncardwell@google.com
Subject: Re: [Patch net-next] tcp_metrics: rearrange fields to avoid holes
Date: Thu, 01 Aug 2013 10:48:31 +0800	[thread overview]
Message-ID: <1375325311.7780.9.camel@cr0> (raw)
In-Reply-To: <20130730.232639.178259761581407616.davem@davemloft.net>

On Tue, 2013-07-30 at 23:26 -0700, David Miller wrote:
> From: Cong Wang <amwang@redhat.com>
> Date: Wed, 31 Jul 2013 11:13:22 +0800
> 
> > I know saving 8 bytes is not interesting for you, but it is for me,
> > since I need some room in struct tcp_metrics_block for union inet_addr.
> > With this patch, I don't have to make struct tcp_metrics_block expand to
> > 3 cachelines. :)
> 
> Cong, please.
> 
> Instead of making code accomodate an unnecessarily large "union
> inet_addr", make a small version of it that accomodates this use case
> and doesn't have the extra fields.

Please teach me how to do that?

The fields not used by inetpeer are sin_port and scope_id etc., and
sin_port is in the middle of sockaddr* structs.

Hmm, maybe just define a new struct by kicking the last field from
struct sockaddr_{in,in6}, so that we can at least shrink 4 bytes.

Except this, I have no idea how to do that.

Thanks!

  reply	other threads:[~2013-08-01  2:48 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-07-31  2:48 [Patch net-next] tcp_metrics: rearrange fields to avoid holes Cong Wang
2013-07-31  3:08 ` Eric Dumazet
2013-07-31  3:13   ` Cong Wang
2013-07-31  3:24     ` Eric Dumazet
2013-07-31  3:35       ` Joe Perches
2013-07-31  3:40         ` Cong Wang
2013-07-31  3:37       ` Cong Wang
2013-07-31  3:57         ` Eric Dumazet
2013-07-31  6:26     ` David Miller
2013-08-01  2:48       ` Cong Wang [this message]
2013-08-01  7:15         ` David Miller
2013-08-01  8:13           ` Cong Wang

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=1375325311.7780.9.camel@cr0 \
    --to=amwang@redhat.com \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=eric.dumazet@gmail.com \
    --cc=ncardwell@google.com \
    --cc=netdev@vger.kernel.org \
    --cc=ycheng@google.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).