From owner-cvs-all Tue Oct 16 9:48:55 2001 Delivered-To: cvs-all@freebsd.org Received: from apollo.backplane.com (apollo.backplane.com [216.240.41.2]) by hub.freebsd.org (Postfix) with ESMTP id BA09837B40C; Tue, 16 Oct 2001 09:48:48 -0700 (PDT) Received: (from dillon@localhost) by apollo.backplane.com (8.11.6/8.9.1) id f9GGmjm31651; Tue, 16 Oct 2001 09:48:45 -0700 (PDT) (envelope-from dillon) Date: Tue, 16 Oct 2001 09:48:45 -0700 (PDT) From: Matthew Dillon Message-Id: <200110161648.f9GGmjm31651@apollo.backplane.com> To: Dag-Erling Smorgrav Cc: Bruce Evans , , Subject: Re: cvs commit: src/sys/vm vnode_pager.c References: <200110161629.f9GGTju31481@apollo.backplane.com> Sender: owner-cvs-all@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG : :Matthew Dillon writes: :> ffs_sync() in -current is doing a lot of mutex operations :> in the loop. If you have various -current mutex debugging :> options turned on, even the default ones I think, this could :> be responsible for the latency you are experiencing. Each :> scan loop is doing four mutex ops. : :So, what changed in the witness code to make it so slow (or in the FFS :code to make it perform so many mutex operations) around late June / :early July? : :DES :-- :Dag-Erling Smorgrav - des@ofug.org You'll have to inquire. I don't know. Even a small change could have a large effect considering that each sync is doing several hundred thousand mutex calls. If you think about it, a mutex call taking a mere 1uS could result in very noticeable delays. -Matt Matthew Dillon To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe cvs-all" in the body of the message