From owner-freebsd-current@FreeBSD.ORG Fri Mar 14 02:40:07 2008 Return-Path: Delivered-To: current@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id AE6D9106566C for ; Fri, 14 Mar 2008 02:40:07 +0000 (UTC) (envelope-from das@FreeBSD.ORG) Received: from zim.MIT.EDU (ZIM.MIT.EDU [18.95.3.101]) by mx1.freebsd.org (Postfix) with ESMTP id 6EDC18FC17 for ; Fri, 14 Mar 2008 02:40:07 +0000 (UTC) (envelope-from das@FreeBSD.ORG) Received: from zim.MIT.EDU (localhost [127.0.0.1]) by zim.MIT.EDU (8.14.2/8.14.2) with ESMTP id m2E26shS035704; Thu, 13 Mar 2008 22:06:54 -0400 (EDT) (envelope-from das@FreeBSD.ORG) Received: (from das@localhost) by zim.MIT.EDU (8.14.2/8.14.2/Submit) id m2E26shu035703; Thu, 13 Mar 2008 22:06:54 -0400 (EDT) (envelope-from das@FreeBSD.ORG) Date: Thu, 13 Mar 2008 22:06:54 -0400 From: David Schultz To: Julian Elischer Message-ID: <20080314020654.GA35542@zim.MIT.EDU> Mail-Followup-To: Julian Elischer , FreeBSD Current , Daniel Eischen References: <47D82E6F.6010302@elischer.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <47D82E6F.6010302@elischer.org> Cc: Daniel Eischen , FreeBSD Current Subject: Re: KSE X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 14 Mar 2008 02:40:07 -0000 On Wed, Mar 12, 2008, Julian Elischer wrote: > In the last few years several things have happened that have > changed the threading landscape, in particular the fact is, that > with it's commanding position, Linux has forced most developers to > abandon threading their applications in a way that is not suitable for > 1:1. Because of this, even if all of you had done the world's best SA implementation in the world, it might not have improved performance for any of the "killer applications" at all. That's because the designers of these apps have put a lot of effort into making them run well on many platforms, including ones where threads are expensive; hence, M:N threads are just extra baggage. Solaris had a pretty mature M:N threading implementation that they essentially abandoned several years ago, probably for similar reasons. It's a shame things worked out this way, because it pushes more complexity into the apps, but that's life. Thanks for all the work you guys put into it.