Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758393AbXIMORt (ORCPT ); Thu, 13 Sep 2007 10:17:49 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754238AbXIMORl (ORCPT ); Thu, 13 Sep 2007 10:17:41 -0400 Received: from viefep18-int.chello.at ([213.46.255.22]:43300 "EHLO viefep12-int.chello.at" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1754183AbXIMORk (ORCPT ); Thu, 13 Sep 2007 10:17:40 -0400 Subject: Re: Understanding I/O behaviour - next try From: Peter Zijlstra To: spamtrap@knobisoft.de Cc: Fengguang Wu , linux-kernel@vger.kernel.org, mingo@redhat.com In-Reply-To: <353439.71100.qm@web32603.mail.mud.yahoo.com> References: <353439.71100.qm@web32603.mail.mud.yahoo.com> Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="=-z8V6K1Yk2RT7/irSCJcq" Date: Thu, 13 Sep 2007 16:17:37 +0200 Message-Id: <1189693057.21778.234.camel@twins> Mime-Version: 1.0 X-Mailer: Evolution 2.10.1 Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1655 Lines: 51 --=-z8V6K1Yk2RT7/irSCJcq Content-Type: text/plain Content-Transfer-Encoding: quoted-printable On Wed, 2007-08-29 at 01:15 -0700, Martin Knoblauch wrote: > > > Another thing I saw during my tests is that when writing to NFS, the > > > "dirty" or "nr_dirty" numbers are always 0. Is this a conceptual thin= g, > > > or a bug? > >=20 > > What are the nr_unstable numbers? NFS has the concept of unstable storage, that is a state where it is agreed the page has been transferred to the remote server, but has not yet been written to disk. > Ahh. Yes, they go up to 80-90k pages. Comparable to the nr_dirty > numbers for the disk case. Good to know. >=20 > For NFS, the nr_writeback numbers seem surprisingly high. They also go > to 80-90k (pages ?). In the disk case they rarely go over 12k. see: /proc/sys/fs/nfs/nfs_congestion_kb That is the limit for when the nfs BDI is marked congested, so nfs_writeout + nfs_unstable <=3D nfs_congestion_kb The nfs_dirty always being 0 just means that pages very quickly start their writeout cycle. --=-z8V6K1Yk2RT7/irSCJcq Content-Type: application/pgp-signature; name=signature.asc Content-Description: This is a digitally signed message part -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.6 (GNU/Linux) iD8DBQBG6UaBXA2jU0ANEf4RAko7AJ9PrM/lMbDczfBO/1JqB3BHKWU66ACfZwNH N8XKZ9IP8xQwpJ1mCs7O3bc= =wxnk -----END PGP SIGNATURE----- --=-z8V6K1Yk2RT7/irSCJcq-- - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/