Date: Wed, 22 Nov 2006 21:37:33 -0500 From: Kris Kennaway <kris@obsecurity.org> To: Dieter <freebsd@sopwith.solgatos.com> Cc: freebsd-questions@freebsd.org Subject: Re: processes not getting fair share of available disk I/O (was: Re: TCP parameters and interpreting tcpdump output ) Message-ID: <20061123023733.GA46545@xor.obsecurity.org> In-Reply-To: <200611230212.CAA03777@sopwith.solgatos.com> References: <20061123011751.GA45406@xor.obsecurity.org> <200611230212.CAA03777@sopwith.solgatos.com>
next in thread | previous in thread | raw e-mail | index | archive | help
--5vNYLRcllDrimb99 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Wed, Nov 22, 2006 at 06:12:06PM +0000, Dieter wrote: > > > > > time ls on a small directory on disk2 > > > > >=3D3D20 > > > > > real 4m51.911s > > > > > user 0m0.000s > > > > > sys 0m0.002s > > > > >=3D3D20 > > > > > I expect access to a busy disk to take longer, but 5 minutes is > > > > > a bit much. And that's the root directory of the filesystem, > > > > > it didn't have to follow a long chain of directories to get there. > > > > >=3D3D20 > > > > > Sometimes I see long delays when accessing disk3, but it is > > > > > behaving at the moment. > > > >=3D20 > > > > ls still has to acquire a number of locks in order to be sure that = the > > > > contents of the directory aren't changing. If there are lots of ot= her > > > > processes all competing for these locks, it will be slow. It looks > > > > like that's the case on your system, although details of your workl= oad > > > > have been trimmed from your email. > > >=3D20 > > > In telnet window 1: > > >=3D20 > > > cd /disk1/ > > > cp -ip very_big_file /disk2/bar/ (the workload) > > >=3D20 > > > In telnet window 2: > > >=3D20 > > > time ls /disk3/foo1/ (make sure time and ls are cached in memory) > > > time ls /disk3/foo2/ (see timing numbers above) > > > time ls /disk2/ (see timing numbers above) > > >=3D20 > > > The /disk2/ directory is small, only contains 3 directories and .snap > > >=3D20 > > > Would the cp into /disk2/bar/ lock the /disk2/ directory? > >=20 > > It shouldn't do. > >=20 > > What scheduler are you using? >=20 > kern.sched.name: 4BSD > kern.sched.quantum: 100000 > kern.sched.preemption: 1 OK, that's correct. Can you also provide details of your disk hardware (e.g. dmesg) and kernel configuration? Kris --5vNYLRcllDrimb99 Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.5 (FreeBSD) iD8DBQFFZQlsWry0BWjoQKURAuWDAKDesSahKkM6WQQtZba4gCnt98GypACg0fZC RhaVgBrzJ/kVucwygUIzeec= =kfK5 -----END PGP SIGNATURE----- --5vNYLRcllDrimb99--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20061123023733.GA46545>