From: Bernd Schubert Subject: Re: ext4_clear_journal_err: Filesystem error recorded from previous mount: IO failure Date: Sun, 24 Oct 2010 17:39:04 +0200 Message-ID: <4CC45318.3080002@ddn.com> References: <201010221533.29194.bs_lists@aakef.fastmail.fm> <20101022172536.GP3127@thunk.org> <20101023221714.GB24650@thunk.org> <4CC43AC9.8000409@redhat.com> <4CC44304.1050409@ddn.com> <4CC44EAF.3090507@redhat.com> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enig7BCB6103584EDD6E9DDA0784" Cc: Ted Ts'o , Amir Goldstein , Bernd Schubert , "linux-ext4@vger.kernel.org" , Andreas Dilger To: Ric Wheeler Return-path: Received: from mail.datadirectnet.com ([74.62.46.229]:5777 "EHLO mail.datadirectnet.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932885Ab0JXPjK (ORCPT ); Sun, 24 Oct 2010 11:39:10 -0400 In-Reply-To: <4CC44EAF.3090507@redhat.com> Sender: linux-ext4-owner@vger.kernel.org List-ID: --------------enig7BCB6103584EDD6E9DDA0784 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable On 10/24/2010 05:20 PM, Ric Wheeler wrote: >=20 > This still sounds more like a Lustre issue than an ext4 one, Andreas ca= n fill in=20 > the technical details. The underlying device handling is unrelated to Lustre. In that sense it is just a local filesystem. >=20 > What ever shared storage sits under ext4 is irrelevant to the fail over= case. >=20 > Unless Lustre does other magic, they still need to obey the basic clust= er rules=20 > - one mount per cluster. Yes, one mount per cluster. >=20 > If Lustre is doing the same trick you would do with active/passive fail= ure over=20 > clusters that export ext4 via NFS, you would still need to clean up the= file=20 > system before being able to re-export it from a fail over node. What exactly is your question here? We use pacemaker/stonith to do the fencing job. What exactly do you want to clean up? The device is recovered by journals, Lustre goes into recovery mode, clients reconnect, locks are updated and incomplete transactions resend. Cheers, Bernd --------------enig7BCB6103584EDD6E9DDA0784 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.10 (GNU/Linux) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/ iEYEARECAAYFAkzEUxgACgkQqh74FqyuOzTCmgCguV95gbLXfJdeX27aYoOh/qFA aR8An06nb4fqZ5QfR0nRTA6PZaTH3SNs =daBJ -----END PGP SIGNATURE----- --------------enig7BCB6103584EDD6E9DDA0784--