Date: Mon, 2 Oct 2006 15:02:28 +0300 From: Vasil Dimov <vd@FreeBSD.org> To: Kris Kennaway <kris@obsecurity.org> Cc: ports@freebsd.org, Michel Talon <talon@lpthe.jussieu.fr> Subject: Re: Yet another INDEX builder. Message-ID: <20061002120228.GA15712@qlovarnika.bg.datamax> In-Reply-To: <20060930184636.GA76783@xor.obsecurity.org> References: <20060930134951.GA89865@lpthe.jussieu.fr> <20060930184636.GA76783@xor.obsecurity.org>
next in thread | previous in thread | raw e-mail | index | archive | help
--C7zPtVaVf+AK4Oqc
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable
On Sat, Sep 30, 2006 at 02:46:36PM -0400, Kris Kennaway wrote:
[...]
>=20
> The only situation where you might reasonably expect to see something
> approaching a factor of 2 speed improvement is if your ports tree is
> on a striped or mirrored device on separate controllers, so 2 reads
> can be completely decoupled from each other in hardware. I've not
> tried this though.
>=20
Here are some timings from my machine:
/usr/ports# diskinfo -t /dev/stripe/gs0
/dev/stripe/gs0
512 # sectorsize
12582649856 # mediasize in bytes (12G)
24575488 # mediasize in sectors
Seek times:
Full stroke: 250 iter in 1.341719 sec =3D 5.367 msec
Half stroke: 250 iter in 1.648136 sec =3D 6.593 msec
Quarter stroke: 500 iter in 2.668755 sec =3D 5.338 msec
Short forward: 400 iter in 2.317754 sec =3D 5.794 msec
Short backward: 400 iter in 1.124325 sec =3D 2.811 msec
Seq outer: 2048 iter in 0.310119 sec =3D 0.151 msec
Seq inner: 2048 iter in 0.337578 sec =3D 0.165 msec
Transfer rates:
outside: 102400 kbytes in 0.989050 sec =3D 103534 kbytes/sec
middle: 102400 kbytes in 0.996347 sec =3D 102775 kbytes/sec
inside: 102400 kbytes in 1.029199 sec =3D 99495 kbytes/sec
/usr/ports# dmesg |grep ^CPU
CPU: AMD Athlon(tm) 64 Processor 3500+ (2210.07-MHz K8-class CPU)
During all tests gstat(8) showed that the stripe was quite idling:
L(q) ops/s r/s kBps ms/r w/s kBps ms/w %busy Name
0 22 22 44 7.6 0 0 0.0 16.6| stripe/gs0
L(q) ops/s r/s kBps ms/r w/s kBps ms/w %busy Name
0 24 24 48 1.8 0 0 0.0 4.3| stripe/gs0
L(q) ops/s r/s kBps ms/r w/s kBps ms/w %busy Name
0 30 28 56 1.4 2 255 0.8 4.0| stripe/gs0
L(q) ops/s r/s kBps ms/r w/s kBps ms/w %busy Name
0 2 2 4 5.9 0 0 0.0 1.2| stripe/gs0
/usr/ports# time make index INDEX_JOBS=3D1
real 19m29.649s
user 12m9.367s
sys 5m13.881s
/usr/ports# time make index INDEX_JOBS=3D2
real 18m38.334s
user 12m54.316s
sys 5m4.062s
/usr/ports# time make index INDEX_JOBS=3D3
real 18m0.804s
user 12m29.657s
sys 5m16.442s
/usr/ports# time make index INDEX_JOBS=3D4
real 18m33.941s
user 12m56.167s
sys 5m12.183s
/usr/ports# time make index INDEX_JOBS=3D10
real 20m30.924s
user 13m56.722s
sys 5m29.590s
/tmp$ time ./build_index.py
=2E.....archivers......
The port archivers/fileroller is obsolete
The port archivers/gshar+gunshar is obsolete
[... a lot more obsolete ports ...]
The port x11-wm/wmx is obsolete
The port x11-wm/xwmm is obsolete
=2E.....dns......
=2E.....polish......
=2E.....arabic......
=2E.....accessibility......
=2E.....net-mgmt......
=2E.....x11-themes......
=2E.....net-im......
=2E.....net-p2p......
The tree (15813ports) takes 1606.92809916 seconds to explore.
Now computing the recursively extended dependencies.
Took 1.09403419495 seconds.
Now converting to packages and sorting.
Last phase takes 1.55835795403 seconds.=20
Total time spent: 1611.23766518 seconds.
real 26m51.585s
user 15m14.370s
sys 10m49.645s
--=20
Vasil Dimov
gro.DSBeerF@dv
%
Peace cannot be kept by force; it
can only be achieved by understanding.
-- A. Einstein
--C7zPtVaVf+AK4Oqc
Content-Type: application/pgp-signature
Content-Disposition: inline
-----BEGIN PGP SIGNATURE-----
iD8DBQFFIP/UFw6SP/bBpCARAoosAJ97rYeLAN6vFXjml97UuGkQUj4lwgCgktVh
yfFc7HJvJmlTpEaBXgWEncg=
=SAc2
-----END PGP SIGNATURE-----
--C7zPtVaVf+AK4Oqc--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20061002120228.GA15712>