From owner-freebsd-hackers Tue Apr 4 19:33:46 2000 Delivered-To: freebsd-hackers@freebsd.org Received: from apollo.backplane.com (apollo.backplane.com [216.240.41.2]) by hub.freebsd.org (Postfix) with ESMTP id B4C3B37B732 for ; Tue, 4 Apr 2000 19:33:44 -0700 (PDT) (envelope-from dillon@apollo.backplane.com) Received: (from dillon@localhost) by apollo.backplane.com (8.9.3/8.9.1) id TAA72623; Tue, 4 Apr 2000 19:33:43 -0700 (PDT) (envelope-from dillon) Date: Tue, 4 Apr 2000 19:33:43 -0700 (PDT) From: Matthew Dillon Message-Id: <200004050233.TAA72623@apollo.backplane.com> To: Alfred Perlstein Cc: Andrew Gallatin , freebsd-hackers@FreeBSD.ORG Subject: Re: reducing the number of NFSv3 commit ops References: <14570.10864.359054.10598@grasshopper.cs.duke.edu> <20000404141641.P20770@fw.wintelcom.net> <14570.22237.61025.935384@grasshopper.cs.duke.edu> <20000404143243.S20770@fw.wintelcom.net> Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG :> :> I'll look at that tonight. But before I do -- why is it broken? :> (the name sorta implies that it us ;) : :I'm not sure, i did it a while back and ran out of time to get it :working, it functions in the strategy layer and tries to grab adjacent :commit blocks to the already clustered IO. : :I think I may have some math errors or something, I haven't had time :to give it a retry in a while. : :-- :-Alfred Perlstein - [bright@wintelcom.net|alfred@freebsd.org] :"I have the heart of a child; I keep it in a jar on my desk." If I remember the right patch, I think my comment on it was that the buffers should use non-blocking locks rather then blocking locks in order to avoid deadlocks, which it looks like you did. This may still patch into -stable but it probably isn't safe to patch into -current. It still looks a little rough but the general concept is sound. -Matt Matthew Dillon To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message