SORT BY:

LIST ORDER
THREAD
AUTHOR
SUBJECT


SEARCH

IPS HOME


    [Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

    Re: another issue with error recovery...



    
    
    As far as I know that is a recognized issue in the TCP world.  Let's hope
    it will we fixed.
    
    Julo
    
    Matt Wakeley <matt_wakeley@agilent.com> on 26/06/2000 21:03:43
    
    Please respond to Matt Wakeley <matt_wakeley@agilent.com>
    
    To:   SCSI-TCP <scsi-tcp@external.cisco.com>
    cc:    (bcc: Julian Satran/Haifa/IBM)
    Subject:  another issue with error recovery...
    
    
    
    
    Here is another issue that may affect error recovery... Any comments on
    this?
    
    -Matt
    
    IMAP://cassin.rose.hp.com?fetch>UID>/INBOX>44400&part=1.2
    
    
    Path:
    news.cup.hp.com!fc.hp.com!col.hp.com!agilent.com!sdd.hp.com!enews.sgi.com!nntp.primenet.com!nntp.gctr.net!newsfeed.direct.ca!news.he.net!newsfeed.concentric.net!global-news-master
    
    From: "Eric A. Hall" <ehall@ehsco.com>
    Newsgroups: comp.protocols.tcp-ip
    Subject: Re: Sequence number of TCP.
    Date: 14 Jun 2000 14:27:11 EDT
    Organization: EHS Company
    Message-ID: <3947CE7D.E3949D43@ehsco.com>
    References: <0eb98234.3d28ff1a@usw-ex0102-016.remarq.com>
    <8i7gs0$17f$1@s2.feed.news.oleane.net> <8i8fq0$ppi$1@web1.cup.hp.com>
    NNTP-Posting-Host: 209.31.7.42
    Mime-Version: 1.0
    Content-Type: text/plain; charset=us-ascii
    Content-Transfer-Encoding: 7bit
    X-Mailer: Mozilla 4.7 [en] (WinNT; I)
    X-Accept-Language: en
    Xref: news.cup.hp.com comp.protocols.tcp-ip:11799
    
    
    
    > How well that happens today when one uses a gigabit interface without
    > enabling the large window extensions I'm not really sure... sending
    > data at roughly 900mbit/s is about 88 MB/s into a 4096 MB sequence
    > space, or wrap in ~46 seconds if I've done my math correctly.
    
    The theoretical wrap-time with Gigabit Ethernet is ~17 seconds. I
    haven't done this math in a long time so don't ask to see my work :)
    It's also a theoretical boundary and not a practical one. Yet. Terrabit
    and Petabit networks will change this again. Giving a fast enough frame
    rate it's probably going to get so that window wrap-around happens in
    the millisecond range. This is only a few years away at best.
    
    --
    Eric A. Hall                                      http://www.ehsco.com/
    Internet Core Protocols        http://www.oreilly.com/catalog/coreprot/
    
    
    
    
    


Home

Last updated: Tue Sep 04 01:08:13 2001
6315 messages in chronological order