From owner-freebsd-hackers Wed Feb 25 14:08:52 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id OAA07497 for freebsd-hackers-outgoing; Wed, 25 Feb 1998 14:08:52 -0800 (PST) (envelope-from owner-freebsd-hackers@FreeBSD.ORG) Received: from smtp03.primenet.com (smtp03.primenet.com [206.165.6.133]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id OAA07472 for ; Wed, 25 Feb 1998 14:08:42 -0800 (PST) (envelope-from tlambert@usr01.primenet.com) Received: (from daemon@localhost) by smtp03.primenet.com (8.8.8/8.8.8) id OAA14706; Wed, 25 Feb 1998 14:34:01 -0700 (MST) Received: from usr01.primenet.com(206.165.6.201) via SMTP by smtp03.primenet.com, id smtpd014669; Wed Feb 25 14:33:55 1998 Received: (from tlambert@localhost) by usr01.primenet.com (8.8.5/8.8.5) id OAA28267; Wed, 25 Feb 1998 14:33:52 -0700 (MST) From: Terry Lambert Message-Id: <199802252133.OAA28267@usr01.primenet.com> Subject: Re: so how goes java? To: perlsta@cs.sunyit.edu (Alfred Perlstein) Date: Wed, 25 Feb 1998 21:33:52 +0000 (GMT) Cc: nate@mt.sri.com, hackers@FreeBSD.ORG In-Reply-To: <029201bd421c$cd2ae5a0$0600a8c0@win95.local.sunyit.edu> from "Alfred Perlstein" at Feb 25, 98 01:40:09 pm X-Mailer: ELM [version 2.4 PL25] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG > >They are not pre-emptive. > > (figures since until recently the SUN version was also co-operative) > one of my first things (besides fixing this problem) is to look into native > threads, co-operative multitasking is an oxymoron. > i also plan on having several snapshots of 3.0 compiled versions of the > port. i'll inform the porting team when my NDA is all set and good. Do not confuse call conversion threading with Yield-based threading. Though call conversion threading is non-preemptive, one thread will not be blocked simply because another thread has made a blocking call. This is the point of call conversion. Kernel threading buys you SMP scalability (assuming there is ever code changes checked in to ensure thread-CPU affinity), and a much higher context switch overhead. Terry Lambert terry@lambert.org --- Any opinions in this posting are my own and not those of my present or previous employers. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message