netdev - puzzled of the congestion control window of Scalable TCP

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [day] [month] [year] [list]

Message-ID: <28850421.post@talk.nabble.com>
Date:	Thu, 10 Jun 2010 18:15:35 -0700 (PDT)
From:	jellyaaa <wgdaaa@....com>
To:	netdev@...r.kernel.org
Subject: puzzled of the congestion control window of Scalable TCP


I am now doing something related to the STCP (Scalable TCP). By pringking the
dynamic snd_cwnd in linux (kernel 2.6.18) ,the result puzzled me . Theoryly,
if any congestion occurs, the snd_cwnd = snd_cwnd * 0.875,but I haven't got
the result I expected. The snd_cwnd changes like this :

snd_cwnd = 1 , snd_ssthresh = 2147483647
snd_cwnd = 2 , snd_ssthresh = 2147483647
snd_cwnd = 3, snd_ssthresh = 2147483647
......
snd_cwnd = 19022, snd_ssthresh = 2147483647      // keeping this value for
several ms 
snd_cwnd = 1769, snd_ssthresh = 16645        // congestion occurs 
snd_cwnd = 1770, snd_ssthresh = 16645                  
......


>From the above data. when congestion occurs , snd_ssthresh = 16645 ~=~
19022*0.875=16626 corresponds  to the theory calculated result. no problems. 
but what is the mean of snd_cwnd = 1770? how this value is calculated .who
(where )calculated it ?


-- 
View this message in context: http://old.nabble.com/puzzled-of-the-congestion-control-window-of-Scalable-TCP-tp28850421p28850421.html
Sent from the netdev mailing list archive at Nabble.com.

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html