netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: David Miller <davem@davemloft.net>
To: yi.zhu@intel.com
Cc: netdev@vger.kernel.org
Subject: Re: [RFC PATCH] accounting for socket backlog
Date: Thu, 25 Feb 2010 00:31:24 -0800 (PST)	[thread overview]
Message-ID: <20100225.003124.183011848.davem@davemloft.net> (raw)
In-Reply-To: <1267067593.16986.1583.camel@debian>

From: Zhu Yi <yi.zhu@intel.com>
Date: Thu, 25 Feb 2010 11:13:13 +0800

> @@ -1372,8 +1372,13 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
>  	bh_lock_sock(sk);
>  	if (!sock_owned_by_user(sk))
>  		rc = __udp_queue_rcv_skb(sk, skb);
> -	else
> +	else {
> +		if (atomic_read(&sk->sk_backlog.len) >= sk->sk_rcvbuf) {
> +			bh_unlock_sock(sk);
> +			goto drop;
> +		}
>  		sk_add_backlog(sk, skb);
> +	}

We have to address this issue, of course, but I bet this method of
handling it negatively impacts performance in normal cases.

Right now we can queue up a lot and still get it to the application
if it is slow getting scheduled onto a cpu, but if you put this
limit here it could result in lots of drops.

  reply	other threads:[~2010-02-25  8:31 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-02-25  3:13 [RFC PATCH] accounting for socket backlog Zhu Yi
2010-02-25  8:31 ` David Miller [this message]
2010-02-26  2:44   ` Zhu Yi
2010-02-26  5:52     ` David Miller
2010-02-25 11:24 ` Eric Dumazet
2010-02-26  2:34   ` Zhu Yi
2010-02-26 13:12     ` Eric Dumazet
2010-03-01  2:17       ` Zhu Yi
2010-03-01  2:29         ` Eric Dumazet
2010-03-01  3:03           ` Zhu Yi
2010-03-01  3:12             ` 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=20100225.003124.183011848.davem@davemloft.net \
    --to=davem@davemloft.net \
    --cc=netdev@vger.kernel.org \
    --cc=yi.zhu@intel.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).