netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
To: Per Hurtig <per.hurtig@kau.se>, netdev@vger.kernel.org
Cc: eric.dumazet@gmail.com, anna.brunstrom@kau.se,
	mohammad.rajiullah@kau.se, ncardwell@google.com,
	nanditad@google.com
Subject: Re: [PATCH] tcp: fixing TLP's FIN recovery
Date: Sat, 07 Jun 2014 17:56:06 +0400	[thread overview]
Message-ID: <539319F6.2090907@cogentembedded.com> (raw)
In-Reply-To: <1402139419-9118-1-git-send-email-per.hurtig@kau.se>

Hello.

On 07-06-2014 15:10, Per Hurtig wrote:

> Fix to a problem observed when losing a FIN segment that does not
> contain data.  In such situations, TLP is unable to recover from
> *any* tail loss and instead adds at least PTO ms to the
> retransmission process, i.e., RTO = RTO + PTO.

     You should provide your signoff.

[...]

> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
> index d463c35..6573765 100644
> --- a/net/ipv4/tcp_output.c
> +++ b/net/ipv4/tcp_output.c
> @@ -2130,8 +2130,10 @@ void tcp_send_loss_probe(struct sock *sk)
>   	if (WARN_ON(!skb || !tcp_skb_pcount(skb)))
>   		goto rearm_timer;
>
> -	/* Probe with zero data doesn't trigger fast recovery. */
> -	if (skb->len > 0)
> +	/* Probe with zero data doesn't trigger fast recovery, if not

    s/not/no/?
    Or rather "if FIN flag is not set"?

> +	 * FIN flag is set.
> +	 */
> +	if ((skb->len > 0) || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN))
>   		err = __tcp_retransmit_skb(sk, skb);

WBR, Sergei

  reply	other threads:[~2014-06-07 13:56 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-06-06 18:46 tcp: fixing TLP's FIN recovery Per Hurtig
2014-06-06 19:07 ` Eric Dumazet
2014-06-07 11:10   ` [PATCH] " Per Hurtig
2014-06-07 13:56     ` Sergei Shtylyov [this message]
2014-06-07 14:34       ` Per Hurtig
2014-06-08  2:58         ` Eric Dumazet
2014-06-08  7:41           ` Per Hurtig
2014-06-08 16:35             ` Eric Dumazet
2014-06-09  7:04               ` Nandita Dukkipati
2014-06-09  7:02             ` Nandita Dukkipati
2014-06-09 13:13               ` Per Hurtig
2014-06-09 14:33                 ` Eric Dumazet
2014-06-09 14:39                   ` Eric Dumazet
2014-06-09 14:42                   ` Per Hurtig
2014-06-09 15:04                     ` Eric Dumazet
2014-06-09 15:56                       ` Per Hurtig
2014-06-09 16:15                         ` Eric Dumazet
2014-06-09 16:24                           ` Eric Dumazet
2014-06-09 18:33                             ` Eric Dumazet
2014-06-12 14:21               ` Weiping Pan
2014-06-12 14:32                 ` Eric Dumazet
2014-06-12 15:08                   ` [PATCH v2 1/1] " Per Hurtig
2014-06-12 15:28                     ` Eric Dumazet
2014-06-12 17:36                       ` Nandita Dukkipati
2014-06-12 17:46                         ` Neal Cardwell
2014-06-12 18:06                     ` David Miller
2014-10-07 15:03                       ` Josh Hunt
2014-10-07 20:17                         ` David Miller

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=539319F6.2090907@cogentembedded.com \
    --to=sergei.shtylyov@cogentembedded.com \
    --cc=anna.brunstrom@kau.se \
    --cc=eric.dumazet@gmail.com \
    --cc=mohammad.rajiullah@kau.se \
    --cc=nanditad@google.com \
    --cc=ncardwell@google.com \
    --cc=netdev@vger.kernel.org \
    --cc=per.hurtig@kau.se \
    /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).