RE: Does tcptrace measure RTT for every ACK?

From: ronny.tittoto@exgate.tek.com
Date: 11/19/02

  • Next message: Avinash Lakhiani: "tcptrace Re. jPlot v1.0.2 released"

    Message-Id: <200211190816.gAJ8Gf217919@masaka.cs.ohiou.edu>
    From: ronny.tittoto@exgate.tek.com
    Subject: RE: Does tcptrace measure RTT for every ACK?
    Date: Tue, 19 Nov 2002 09:08:07 +0100
    
    

    a good article could be found here
    http://citeseer.nj.nec.com/jiang02passive.html

    Ronny

    > -----Original Message-----
    > From: uaca@alumni.uv.es [mailto:uaca@alumni.uv.es]
    > Sent: lunedì 18 novembre 2002 20.34
    > To: TCPTRACE Mailing List
    > Cc: Rogelio Montañana; StasK@narus.com
    > Subject: Re: Does tcptrace measure RTT for every ACK?
    >
    >
    > On Sat, Nov 16, 2002 at 09:10:09PM -0800, Stas Khirman wrote:
    > > Gentlemen,
    > >
    > > Did you considered to use three-way handshake as a good
    > estimation for RTT?
    >
    > Yes:
    >
    > What do you think about the following?
    >
    >
    > suposse the following scenario:
    >
    > Monitor
    > [Host A]------------------------------------[Host B]
    >
    > SYN
    > t0 ····················t1···················t2
    >
    > SYN+ACK
    > t5 ····················t4···················t3
    >
    > ACK
    > t6 ····················t7···················t8
    >
    >
    > then
    >
    > t4-t1= two way delay from monitor to Host B
    > t7-t4= two way delay from monitor to Host A
    >
    > so when we have the following situation
    >
    > Monitor
    > [Host A]------------------------------------[Host B]
    >
    > A sends packet i
    > ))))))))))))))))))))))))>>>>>>>>>>>>>>>>>>>>>>>>>>>>
    >
    > B acks packet i
    > ((((((((((((((((((((((((<<<<<<<<<<<<<<<<<<<<<<<<<<<<
    >
    >
    > tcptrace actualy meassures rtt as
    >
    > sum('>') +sum('<')
    >
    > in this case making the above calculations we do instead
    >
    > sum('>') +sum('<') +(t7 -t4)
    >
    >
    > Note: this makes tha asumtion that t3-t2 and t6-t5 is near zero
    >
    > The same can be done in the other way
    >
    > This is based on a white paper I read from packeteer.com
    >
    > I have just made a patch for tcptrace that does this wich is at
    >
    > http://despistao.cjb.net:8000/tcptrace/symetric_rtt.diff
    >
    > Please note that the code is very untested
    >
    > any comment will be greatly apprecited
    >
    > regards
    >
    > Ulisses
    >
    > Debian GNU/Linux: a dream come true
    > --------------------------------------------------------------
    > ---------------
    > "Computers are useless. They can only give answers."
    > Pablo Picasso
    >
    > ---> Visita http://www.valux.org/ para saber acerca de la <---
    > ---> Asociación Valenciana de Usuarios de Linux <---
    >
    > --------------------------------------------------------------
    > --------------
    > To unsubscribe, send a message with body containing
    > "unsubscribe tcptrace" to
    > majordomo@tcptrace.org.
    >

    ----------------------------------------------------------------------------
    To unsubscribe, send a message with body containing "unsubscribe tcptrace" to
    majordomo@tcptrace.org.



    This archive was generated by hypermail 2b30 : 11/19/02 EST