netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Fan Du <fan.du@intel.com>
To: johnwheffner@gmail.com
Cc: davem@davemloft.net, netdev@vger.kernel.org, fengyuleidian0615@gmail.com
Subject: [PATCH net-next 3/4] ipv4: Use probe_size to check write queue data length
Date: Tue, 10 Mar 2015 17:16:25 +0800	[thread overview]
Message-ID: <1425978986-8512-4-git-send-email-fan.du@intel.com> (raw)
In-Reply-To: <1425978986-8512-1-git-send-email-fan.du@intel.com>

When building a probe segment, only 'probe_size' of bytes
is needed, so check write queue data length with probe_size
instead of size_needed.

Signed-off-by: Fan Du <fan.du@intel.com>
---
 net/ipv4/tcp_output.c |    8 +++-----
 1 files changed, 3 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 79977d1..89d3f84 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1872,7 +1872,6 @@ static int tcp_mtu_probe(struct sock *sk)
 	struct net *net = sock_net(sk);
 	int len;
 	int probe_size;
-	int size_needed;
 	int copy;
 	int mss_now;
 	int interval;
@@ -1895,7 +1894,6 @@ static int tcp_mtu_probe(struct sock *sk)
 	mss_now = tcp_current_mss(sk);
 	probe_size = tcp_mtu_to_mss(sk, (icsk->icsk_mtup.search_high +
 				    icsk->icsk_mtup.search_low) >> 1);
-	size_needed = probe_size + (tp->reordering + 1) * tp->mss_cache;
 	interval = icsk->icsk_mtup.search_high - icsk->icsk_mtup.search_low;
 	/* When misfortune happens, we are reprobing actively,
 	 * and then reprobe timer has expired. We stick with current
@@ -1911,12 +1909,12 @@ static int tcp_mtu_probe(struct sock *sk)
 	}
 
 	/* Have enough data in the send queue to probe? */
-	if (tp->write_seq - tp->snd_nxt < size_needed)
+	if (tp->write_seq - tp->snd_nxt < probe_size)
 		return -1;
 
-	if (tp->snd_wnd < size_needed)
+	if (tp->snd_wnd < probe_size)
 		return -1;
-	if (after(tp->snd_nxt + size_needed, tcp_wnd_end(tp)))
+	if (after(tp->snd_nxt + probe_size, tcp_wnd_end(tp)))
 		return 0;
 
 	/* Do we need to wait to drain cwnd? With none in flight, don't stall */
-- 
1.7.1

  parent reply	other threads:[~2015-03-10  9:21 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-03-10  9:16 [PATCH net-next 0/4] Fix for TCP PMTU Fan Du
2015-03-10  9:16 ` [PATCH net-next 1/4] ipv4: Rename tcp_mtu_probing to tcp_blackhole_probe Fan Du
2015-03-10  9:16 ` [PATCH net-next 2/4] ipv4: Correct two conditions checking when buildig nskb Fan Du
2015-03-18 12:44   ` John Heffner
2015-03-10  9:16 ` Fan Du [this message]
2015-03-10 12:26   ` [PATCH net-next 3/4] ipv4: Use probe_size to check write queue data length John Heffner
2015-03-18  1:37     ` Fan Du
2015-03-18 12:41       ` John Heffner
2015-03-10  9:16 ` [PATCH net-next 4/4] ipv4: clamp sysctl_tcp_probe_threshold Fan Du

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=1425978986-8512-4-git-send-email-fan.du@intel.com \
    --to=fan.du@intel.com \
    --cc=davem@davemloft.net \
    --cc=fengyuleidian0615@gmail.com \
    --cc=johnwheffner@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;
as well as URLs for NNTP newsgroup(s).