Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 28 Jul 2005 10:28:44 +0200
From:      Pawel Jakub Dawidek <pjd@FreeBSD.org>
To:        Julian Elischer <julian@elischer.org>
Cc:        FreeBSD Current <freebsd-current@freebsd.org>
Subject:   Re: Apparent strange disk behaviour in 6.0
Message-ID:  <20050728082844.GW46538@darkness.comp.waw.pl>
In-Reply-To: <42E88F2B.5000108@elischer.org>
References:  <42E88135.30603@elischer.org> <42E88F2B.5000108@elischer.org>

next in thread | previous in thread | raw e-mail | index | archive | help

--3sbgfNE+TCfp+/cI
Content-Type: text/plain; charset=iso-8859-2
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable

On Thu, Jul 28, 2005 at 12:54:19AM -0700, Julian Elischer wrote:
+> it APPEARS that teh system is swapping out running programs in order to=
=20
+> store more write data!
+>=20
+> experiment:
+> boot to single user mode.
+> type:
+> mount {big partition}
+> dd if=3D/dev/zero bs=3D128K of=3D/$bigpartition}/bigfile count=3D1000000
+>=20
+> notice that after a short while your dd is killed because the system is=
=20
+> out of swapspace.
+> (it doesn't have any)
+> Why the F*ck does it need swapspace.? there are exactly 2 proceses=20
+> running in userspace
+> and one of them s in wait4(). dd shows a resident size of about 170KB
+> leaving about a GIGABYTE of unused RAM.
+>=20
+> The system should make dd wait rather than trying to swap its pages out..
+>=20
+>=20
+> if you then do
+> swapon (your swap device)
+> and repeat teh command in the background,
+> vmstat 1 will show you pages being faulted in and out...
+> no WONDER IO goes to hell in a handbasket..
+>=20
+> Outgoing IO should never be able to force running programs out!
+> It should start re-using old pages from the same file!
+>=20
+> 4.11 gives a consinstent 65MB/sec with this array, for as long as I run =
it..
+> 6.0 gives me 65MB for 15 seconds and then it drops to 20MB/sec and then=
=20
+> 10MB/sec
+> and the swap disk bursts into life.
+>=20
+> the array goes from all the lights solidly on, to bursts of activity=20
+> with large gaps in between them.

It looks I observed the same behaviour!

I was testing GELI GEOM class and I was getting ENOMEM errors from malloc(9=
).
Then, I was sure I've a memory leak, but this was only 'vmstat -m' issue so
there was no memory leak and I shouldn't get ENOMEM in the first place while
copying /usr/src/sys directory.

I'm also able to reproduce your dd(1) test easly.

Not sure when it was introduced...

--=20
Pawel Jakub Dawidek                       http://www.wheel.pl
pjd@FreeBSD.org                           http://www.FreeBSD.org
FreeBSD committer                         Am I Evil? Yes, I Am!

--3sbgfNE+TCfp+/cI
Content-Type: application/pgp-signature
Content-Disposition: inline

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.2.4 (FreeBSD)

iD8DBQFC6Jc8ForvXbEpPzQRAtDOAKCEs64AZynA6fhL0pgbYPgf43SqpACfe9sR
HGMmNKG1ZvplxRYrOa5bf7A=
=oELY
-----END PGP SIGNATURE-----

--3sbgfNE+TCfp+/cI--



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20050728082844.GW46538>