Date: Wed, 17 Oct 2007 13:14:00 +0300 From: Kostik Belousov <kostikbel@gmail.com> To: Peter Jeremy <peterjeremy@optushome.com.au> Cc: freebsd-hackers@freebsd.org Subject: Re: Filesystem snapshots dog slow Message-ID: <20071017101400.GH6511@deviant.kiev.zoral.com.ua> In-Reply-To: <20071017100003.GK1191@turion.vk2pj.dyndns.org> References: <20071016113046.GA35318@eos.sc1.parodius.com> <4714A663.5010800@freebsd.org> <20071017100003.GK1191@turion.vk2pj.dyndns.org>
next in thread | previous in thread | raw e-mail | index | archive | help
--uAgJxtfIS94j9H4T Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Wed, Oct 17, 2007 at 08:00:03PM +1000, Peter Jeremy wrote: > On 2007-Oct-16 06:54:11 -0500, Eric Anderson <anderson@freebsd.org> wrote: > >will give you a good understanding of what the issue is. Essentially, yo= ur=20 > >disk is hammered making copies of all the cylinder groups, skipping thos= e=20 > >that are 'busy', and coming back to them later. On a 200Gb disk, you cou= ld=20 > >have 1000 cylinder groups, each having to be locked, copied, unlocked, a= nd=20 > >then checked again for any subsequent changes. The stalls you see are w= hen=20 > >there are lock contentions, or disk IO issues. On a single disk (like y= our=20 > >setup above), your snapshots will take forever since there is very littl= e=20 > >random IO performance available to you. >=20 > That said, there is a fair amount of scope available for improving > both the creation and deletion performance. >=20 > Firstly, it's not clear to me that having more than a few hundred CGs > has any real benefits. There was a massive gain in moving from > (effectively) a single CG in pre-FFS to a few dozen CGs in FFS as it > was first introduced. Modern disks are roughly 5 orders of magnitude > larger and voice-coil actuators mean that seek times are almost > independent of distance. CG sizes are currently limited by the > requirement that the cylinder group (including cylinder group maps) > must fit into a single FS block. Removing this restriction would > allow CGs to be much larger. >=20 > Secondly, all the I/O during both snapshot creation and deletion is > in FS-block size chunks. Increasing the I/O size would significantly > increase the I/O performance. Whilst it doesn't make sense to read > more than you need, there still appears to be plenty of scope to > combine writes. >=20 > Between these two items, I would expect potential performance gains > of at least 20:1. >=20 > Note that I'm not suggesting that either of these items is trivial. This is, unfortunately, quite true. Allowing non-atomic updates of the cg block means a lot of complications in the softupdate code, IMHO. --uAgJxtfIS94j9H4T Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.4 (FreeBSD) iD8DBQFHFeBnC3+MBN1Mb4gRAtSOAKDuOFuqcDEHtsPa2r4oYii2aZeYgwCgoYZC fMAT7d/+eHzEZSeLe72yyzM= =zclz -----END PGP SIGNATURE----- --uAgJxtfIS94j9H4T--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20071017101400.GH6511>