Return to BSD News archive
Path: euryale.cc.adfa.oz.au!newshost.carno.net.au!harbinger.cc.monash.edu.au!news.rmit.EDU.AU!news.unimelb.EDU.AU!munnari.OZ.AU!news.ecn.uoknor.edu!news.wildstar.net!news.ececs.uc.edu!newsxfer.itd.umich.edu!newsxfer3.itd.umich.edu!su-news-hub1.bbnplanet.com!news.bbnplanet.com!www.nntp.primenet.com!nntp.primenet.com!news1.best.com!nntp1.ba.best.com!usenet From: Bryan O'Sullivan <bos@serpentine.com> Newsgroups: comp.programming.threads,comp.unix.bsd.freebsd.misc Subject: Re: [??] pure kernel vs. dual concurrency implementations Date: 21 Feb 1997 18:23:01 -0800 Organization: Polymorphous Thaumaturgy Lines: 24 Sender: bos@organon Message-ID: <87d8ttinp6.fsf@serpentine.com> References: <330CE6A4.63B0@cet.co.jp> <874tf7lbxc.fsf@serpentine.com> <Pine.BSF.3.95.970221180902.15657A-100000@hydra.parkplace.ne.jp> NNTP-Posting-Host: organon.serpentine.com X-Newsreader: Gnus v5.3/Emacs 19.34 Xref: euryale.cc.adfa.oz.au comp.programming.threads:3273 comp.unix.bsd.freebsd.misc:35922 m> Ok. Just to confirm, there are dual concurrency implementations m> that do the non-blocking thing, right? Not that I am aware of; after all, there is no reason to jump through hoops to lay non-blocking behaviour underneath blocking calls in a two-level implementation. m> Are there certain applications better handled by pure kernel m> threads and others better handled by a dual concurrency m> implementation? Truly pathological applications - that is, programs that start hundreds or thousands of threads, all of which spend most of their time blocking in system calls - might run marginally more efficiently under a pure kernel implementation. I would expect pretty much anything else to do better under a two-level implementation. <b -- Let us pray: What a Great System. bos@eng.sun.com Please Do Not Crash. bos@serpentine.com ^G^IP@P6 http://www.serpentine.com/~bos