Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1741731

Re: [PATCH v5 4/4] ipv4: Namespaceify tcp_fastopen_blackhole_timeout knob

From David Miller <davem@davemloft.net>
Newsgroups linux.kernel
Subject Re: [PATCH v5 4/4] ipv4: Namespaceify tcp_fastopen_blackhole_timeout knob
Date 2017-09-28 19:50 +0200
Message-ID <uuL6F-3wn-7@gated-at.bofh.it> (permalink)
References <uubmx-5iR-3@gated-at.bofh.it> <uubmx-5iR-1@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw


From: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Date: Wed, 27 Sep 2017 11:35:43 +0800

> Different namespace application might require different time period in
> second to disable Fastopen on active TCP sockets.
> 
> Tested:
> Simulate following similar situation that the server's data gets dropped
> after 3WHS.
> C ---- syn-data ---> S
> C <--- syn/ack ----- S
> C ---- ack --------> S
> S (accept & write)
> C?  X <- data ------ S
> 	[retry and timeout]
> 
> And then print netstat of TCPFastOpenBlackhole, the counter increased as
> expected when the firewall blackhole issue is detected and active TFO is
> disabled.
> # cat /proc/net/netstat | awk '{print $91}'
> TCPFastOpenBlackhole
> 1
> 
> Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>

Applied.

Back to linux.kernel | Previous | NextPrevious in thread | Find similar | Unroll thread


Thread

[PATCH v5 4/4] ipv4: Namespaceify tcp_fastopen_blackhole_timeout knob Haishuang Yan <yanhaishuang@cmss.chinamobile.com> - 2017-09-27 05:40 +0200
  Re: [PATCH v5 4/4] ipv4: Namespaceify  tcp_fastopen_blackhole_timeout knob David Miller <davem@davemloft.net> - 2017-09-28 19:50 +0200

csiph-web