From mboxrd@z Thu Jan 1 00:00:00 1970 From: Bernd Schubert Subject: Re: large files Date: Tue, 18 May 2004 15:42:06 +0200 Sender: Bernd Schubert Message-ID: <200405181544.36152.bernd-schubert@web.de> References: <200405172148.33162.bernd-schubert@web.de> <1084824741.20437.368.camel@watt.suse.com> Mime-Version: 1.0 Content-Type: multipart/signed; protocol="application/pgp-signature"; micalg=pgp-sha1; boundary="Boundary-02=_ENhqAjf9LzcQKzL"; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Return-path: list-help: list-unsubscribe: list-post: Errors-To: flx@namesys.com In-Reply-To: <1084824741.20437.368.camel@watt.suse.com> List-Id: To: Chris Mason Cc: Reiserfs mail-list --Boundary-02=_ENhqAjf9LzcQKzL Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Content-Description: signed data Content-Disposition: inline Hello Chris, > > As a comparison data point, could you please try 2.6.6-mm3? I realize > you don't want to run this kernel in production, but it would tell us if > I understand the problems at hand. the results in 2.6.6-mm3 are below, we almost consider to run this kernel=20 version. Here are two other interesting facts: 1.) During the filecreation in 2.4.26 the load on the system was around 3-4= ,=20 whereas in 2.6.6-mm3 the load was at about 8-9. 2.) When the dd file creation process finished (2.4.26 was running) the sys= tem=20 became so unresponsible, that the drdb connection timed out and a resync=20 process automatically started when the system became responsible again. I=20 don't have any comparism to 2.6.6-mm3 since we would need another drbd=20 version. Also, I don't know if this happend when dd finished or when=20 rm-started, since both were running from a script. Here are the measured times for file creation and file deleting =3D=3D=3D=3D=3D> 2.4.26: taylor:~# cat test.out-2.4.26 time dd if=3D/dev/zero of=3D/worka/testfile.dd bs=3D1M count=3D300000 300000+0 records in 300000+0 records out 314572800000 bytes transferred in 5746.266841 seconds (54743855 bytes/sec) real 95m46.275s user 0m0.760s sys 29m57.800s time rm -fr /worka/testfile.dd real 11m20.589s user 0m0.000s sys 4m59.850s =3D=3D=3D=3D=3D> 2.6.6-mm3 taylor:~# cat test.out-2.6.6-mm3 time dd if=3D/dev/zero of=3D/worka/testfile.dd bs=3D1M count=3D300000 300000+0 records in 300000+0 records out 314572800000 bytes transferred in 4902.873869 seconds (64160900 bytes/sec) real 81m46.211s user 0m1.172s sys 22m26.010s time rm -fr /worka/testfile.dd real 1m38.000s user 0m0.000s sys 1m5.872s Do you have any ideas how we could improve 2.4.x?=20 Thanks, Bernd =2D-=20 Bernd Schubert Physikalisch Chemisches Institut / Theoretische Chemie Universit=E4t Heidelberg INF 229 69120 Heidelberg e-mail: bernd.schubert@pci.uni-heidelberg.de --Boundary-02=_ENhqAjf9LzcQKzL Content-Type: application/pgp-signature Content-Description: signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.2.4 (GNU/Linux) iD8DBQBAqhNEC8BUnAF+ydYRAsMDAJ9syvt+82PwoQr410+pAMgaGt6cGACfWxvh +/H3quWGsazEigAk44G3JYk= =jUkJ -----END PGP SIGNATURE----- --Boundary-02=_ENhqAjf9LzcQKzL--