Return to BSD News archive
Path: euryale.cc.adfa.oz.au!newshost.anu.edu.au!harbinger.cc.monash.edu.au!nntp.coast.net!zombie.ncsc.mil!news.mathworks.com!newsfeed.internetmci.com!zdc!zdc-e!szdc-e!news From: "John S. Dyson" <toor@dyson.iquest.net> Newsgroups: comp.os.linux.networking,comp.unix.bsd.netbsd.misc,comp.unix.bsd.freebsd.misc Subject: Re: TCP latency Date: Sun, 14 Jul 1996 15:06:55 -0500 Organization: John S. Dyson's home machine Lines: 22 Message-ID: <31E9535F.167EB0E7@dyson.iquest.net> References: <4paedl$4bm@engnews2.eng.sun.com> <4rlf6i$c5f@linux.cs.helsinki.fi> <31DEA3A3.41C67EA6@dyson.iquest.net> <Du681x.2Gy@kroete2.freinet.de> <31DFEB02.41C67EA6@dyson.iquest.net> <4rpdtn$30b@symiserver2.symantec.com> <x7ohlq78wt.fsf@oberon.di.fc.ul.pt> <Pine.LNX.3.91.960709020017.19115I-100000@reflections.mindspring.com> <4s12la$pm8@enomem.lkg.dec.com> <m24tnf9f69.fsf@frob.mlm.extern.lrz-muenchen.de> <4sbhrq$msh@enomem.lkg.dec.com> NNTP-Posting-Host: dyson.iquest.net Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-Mailer: Mozilla 3.0b5a (X11; I; FreeBSD 2.2-CURRENT i386) Xref: euryale.cc.adfa.oz.au comp.os.linux.networking:45188 comp.unix.bsd.netbsd.misc:4040 comp.unix.bsd.freebsd.misc:23547 Matt Thomas wrote: > > In article <m24tnf9f69.fsf@frob.mlm.extern.lrz-muenchen.de>, > Andi Kleen <andi@mlm.extern.lrz-muenchen.de> writes: > > >I think a mmap() interface to sockets would be more elegant (and you could > >do exactly the same thing) > > I can't see how mmap() would map to a socket. Unlike a file, you can't > directly address portions of a communication stream. What would lseek > do? Sockets have semantics that are very sequential in nature. mmap > is not a good fit. > > How would you use mmap on a pipe? > Can't resist: It means that you can't read memory backwards? :-). It would require some kind of bound on both the size of the transfer and/or perhaps bound the search backwards. It sure does not initially appear to be practical. John