From: Aaron Straus Subject: Re: [NFS] blocks of zeros (NULLs) in NFS files in kernels >= 2.6.20 Date: Fri, 5 Sep 2008 15:14:35 -0700 Message-ID: <20080905221435.GA12911@merfinllc.com> References: <20080905191939.GG22796@merfinllc.com> <0A24B45A-9761-4310-B1DB-B4738964E862@oracle.com> <20080905200455.GH22796@merfinllc.com> <04854041-E23D-48B5-B9FF-0B7ECEB2C371@oracle.com> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="17pEHd4RhPHOinZp" Cc: Neil Brown , Linux NFS Mailing List , Trond Myklebust , LKML Kernel To: Chuck Lever Return-path: Received: from quackingmoose.com ([63.73.180.143]:60382 "EHLO penguin.merfinllc.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751646AbYIEWOg (ORCPT ); Fri, 5 Sep 2008 18:14:36 -0400 In-Reply-To: <04854041-E23D-48B5-B9FF-0B7ECEB2C371@oracle.com> Sender: linux-nfs-owner@vger.kernel.org List-ID: --17pEHd4RhPHOinZp Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable Hi, On Sep 05 04:36 PM, Chuck Lever wrote: > I have the latest Fedora 9 kernels on two clients, mounting via NFSv3 =20 > using "actimeo=3D600" (for other reasons). The server is OpenSolaris =20 > 2008.5. >=20 > reader.py reported zeroes in the test file after about 5 minutes. Awesome. Thanks for testing! Our actime is much shorter which is probably why it happens sooner for us. > Looking at the file a little later, I don't see any problems with it. >=20 > Since your scripts are not using any kind of serialization (ie file =20 > locking) between the clients, I wonder if non-determinant behavior is =20 > to be expected. Hmm... yep. I don't know what guarantees we want to make. The behavior doesn't seem to be consistent with older kernels though... so I'm thinking it might be a bug. We hit this particular issue because we have scripts which essentially 'tail -f' log files looking for errors. They miss log messages (and see corrupted ones) b/c of the NULLs. That's also why there is no serialization.... we don't need it when grep'ing through log messages. I'm bisecting now. I see a block of intricate-looking NFS patches, I'll try to narrow it down to a particular commit. =20 I'll also get the wireshark data at that point. Thanks, =3Da=3D --=20 =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D Aaron Straus aaron-bYFJunmd+ZV8UrSeD/g0lQ@public.gmane.org --17pEHd4RhPHOinZp Content-Type: application/pgp-signature; name="signature.asc" Content-Description: Digital signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.2.2 (GNU/Linux) iD8DBQFIwa9Lr/o4YuvB+jgRAmvKAKDUdRcC4+2SENjQ7ZG5zDktvwmtfwCg38Cv G/k0kYMgXmnCnQFFINZ0oP8= =N7mJ -----END PGP SIGNATURE----- --17pEHd4RhPHOinZp--