All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Ilpo Järvinen" <ilpo.jarvinen@helsinki.fi>
To: netdev@vger.kernel.org
Cc: David Miller <davem@davemloft.net>,
	Pasi Sarolahti <pasi.sarolahti@nokia.com>
Subject: [PATCH 10/18] [TCP]: Don't enter to fast recovery while using FRTO
Date: Mon, 19 Feb 2007 13:38:04 +0200	[thread overview]
Message-ID: <11718850922734-git-send-email-ilpo.jarvinen@helsinki.fi> (raw)
In-Reply-To: <11718850923324-git-send-email-ilpo.jarvinen@helsinki.fi>

Because TCP is not in Loss state during FRTO recovery, fast
recovery could be triggered by accident. Non-SACK FRTO is more
robust than not yet included SACK-enhanced version (that can
receiver high number of duplicate ACKs with SACK blocks during
FRTO), at least with unidirectional transfers, but under
extraordinary patterns fast recovery can be incorrectly
triggered, e.g., Data loss+ACK losses => cumulative ACK with
enough SACK blocks to meet sacked_out >= dupthresh condition).

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
---
 net/ipv4/tcp_input.c |    4 ++++
 1 files changed, 4 insertions(+), 0 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 9637abd..309da3e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1547,6 +1547,10 @@ static int tcp_time_to_recover(struct so
 {
 	__u32 packets_out;
 
+	/* Do not perform any recovery during FRTO algorithm */
+	if (tp->frto_counter)
+		return 0;
+
 	/* Trick#1: The loss is proven. */
 	if (tp->lost_out)
 		return 1;
-- 
1.4.2


  reply	other threads:[~2007-02-19 11:38 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-02-19 11:37 [PATCHSET 0/18] FRTO: fixes and small changes + SACK enhanced version Ilpo Järvinen
2007-02-19 11:37 ` [PATCH 1/18] [TCP] FRTO: Incorrectly clears TCPCB_EVER_RETRANS bit Ilpo Järvinen
2007-02-19 11:37   ` [PATCH 2/18] [TCP] FRTO: Separated response from FRTO detection algorithm Ilpo Järvinen
2007-02-19 11:37     ` [PATCH 3/18] [TCP] FRTO: Moved tcp_use_frto from tcp.h to tcp_input.c Ilpo Järvinen
2007-02-19 11:37       ` [PATCH 4/18] [TCP] FRTO: Comment cleanup & improvement Ilpo Järvinen
2007-02-19 11:37         ` [PATCH 5/18] [TCP] FRTO: Consecutive RTOs keep prior_ssthresh and ssthresh Ilpo Järvinen
2007-02-19 11:38           ` [PATCH 6/18] [TCP] FRTO: Use Disorder state during operation instead of Open Ilpo Järvinen
2007-02-19 11:38             ` [PATCH 7/18] [TCP] FRTO: Ignore some uninteresting ACKs Ilpo Järvinen
2007-02-19 11:38               ` [PATCH 8/18] [TCP] FRTO: fixes fallback to conventional recovery Ilpo Järvinen
2007-02-19 11:38                 ` [PATCH 9/18] [TCP] FRTO: Response should reset also snd_cwnd_cnt Ilpo Järvinen
2007-02-19 11:38                   ` Ilpo Järvinen [this message]
2007-02-19 11:38                     ` [PATCH 11/18] [TCP] FRTO: frto_counter modulo-op converted to two assignments Ilpo Järvinen
2007-02-19 11:38                       ` [PATCH 12/18] [TCP]: Prevent unrelated cwnd adjustment while using FRTO Ilpo Järvinen
2007-02-19 11:38                         ` [PATCH 13/18] [TCP] FRTO: Entry is allowed only during (New)Reno like recovery Ilpo Järvinen
2007-02-19 11:38                           ` [PATCH 14/18] [TCP] FRTO: Reverse RETRANS bit clearing logic Ilpo Järvinen
     [not found]                             ` <1171885092244-git- send-email-ilpo.jarvinen@helsinki.fi>
2007-02-19 11:38                             ` [PATCH 15/18] [TCP] FRTO: Fake cwnd for ssthresh callback Ilpo Järvinen
2007-02-19 11:38                               ` [PATCH 16/18] [TCP]: Prevent reordering adjustments during FRTO Ilpo Järvinen
2007-02-19 11:38                                 ` [PATCH 17/18] [TCP]: SACK enhanced FRTO Ilpo Järvinen
2007-02-19 11:38                                   ` [PATCH 18/18] [TCP] FRTO: Sysctl documentation for SACK enhanced version Ilpo Järvinen

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=11718850922734-git-send-email-ilpo.jarvinen@helsinki.fi \
    --to=ilpo.jarvinen@helsinki.fi \
    --cc=davem@davemloft.net \
    --cc=netdev@vger.kernel.org \
    --cc=pasi.sarolahti@nokia.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.