Date: Thu, 1 Feb 2007 15:06:27 -0500 From: Kris Kennaway <kris@obsecurity.org> To: Julian Elischer <julian@elischer.org> Cc: FreeBSD Current <current@freebsd.org> Subject: Re: lock contention etc. Message-ID: <20070201200627.GA73677@xor.obsecurity.org> In-Reply-To: <45C24113.7000608@elischer.org> References: <45C24113.7000608@elischer.org>
next in thread | previous in thread | raw e-mail | index | archive | help
--T4sUOijqQbZv57TR Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Thu, Feb 01, 2007 at 11:35:47AM -0800, Julian Elischer wrote: > here's an intersting set of numbers.. >=20 > notice the increase in 'system time' for the same work done when there > is more parallelism. >=20 > make buildworld > 3762.94 real 2627.66 user 1275.78 sys > 3763.32 real 2632.04 user 1271.80 sys > 3763.34 real 2627.99 user 1276.39 sys > 3763.03 real 2632.50 user 1270.91 sys >=20 > make -j 2 buildworld > 2465.10 real 2958.94 user 1918.64 sys > 2463.97 real 2968.43 user 1910.65 sys > 2472.13 real 2978.64 user 1912.80 sys > 2582.83 real 2965.51 user 2047.19 sys >=20 > make -j 4 buildworld > 2262.88 real 4322.31 user 3333.58 sys > 2255.88 real 4330.32 user 3319.48 sys > 2256.09 real 4318.84 user 3336.57 sys > 2257.63 real 4338.34 user 3313.07 sys >=20 > (2 processors with HTT) (looks like 4 processors) > -current, sched_4bsd >=20 > I'm guessing that the extra system time represents a lot of > contention somewhere. >=20 > What is the best way to get actual numbers on this? LOCK_PROFILING. Kris --T4sUOijqQbZv57TR Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.6 (FreeBSD) iD8DBQFFwkhDWry0BWjoQKURArpaAJ976RGJbWEhtIBPTaX2IfElxRMqQwCg5RDY SG1C6+Fe/gMBhcJEXDCWaSY= =75p7 -----END PGP SIGNATURE----- --T4sUOijqQbZv57TR--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20070201200627.GA73677>