Date: Fri, 16 May 2003 11:48:36 +0200 From: Pawel Jakub Dawidek <nick@garage.freebsd.pl> To: Peter Jeremy <peterjeremy@optushome.com.au> Cc: freebsd-hackers@freebsd.org Subject: Re: Optimizations. Message-ID: <20030516094836.GW45118@garage.freebsd.pl> In-Reply-To: <20030516084749.GA22269@cirb503493.alcatel.com.au> References: <20030515123033.GP45118@garage.freebsd.pl> <FHEMJMOKKMJDGKFOHHEPEEILGLAA.mooneer@translator.cx> <20030515151945.GQ45118@garage.freebsd.pl> <200305151407.28717.wes@softweyr.com> <3EC481D3.124F61B8@mindspring.com> <20030516070732.GT45118@garage.freebsd.pl> <20030516084749.GA22269@cirb503493.alcatel.com.au>
next in thread | previous in thread | raw e-mail | index | archive | help
--0in9KoZ32yGPAlXZ
Content-Type: text/plain; charset=iso-8859-2
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable
On Fri, May 16, 2003 at 06:47:49PM +1000, Peter Jeremy wrote:
+> >Look at functions in /sys/kern/kern_tc.c. There are so many little
+> >functions. How about put __inline here and there?
+>=20
+> How about you try this and post some results showing what effect this
+> has - both at the micro-benchmark level and for a real-world
+> application (like a proxy or load balancer).
Ehh, this is just an example to show that there are places that could be
optimized without loosing clean code.
Ok, this is going to nowhere.
+> >And second thing. Does anybody think about representing time in BCD cod=
e?
[...]
+> At the end, it's not clear what you gain. You still need the ability
+> to perform arithmetic to convert between UTC and local time. All you've
+> saved is the binary-to-decimal conversion - which is trivial compared
+> to all the other overheads.
I don't have experience in this topic, but there was some time ago long
discussion about new time representation. And I think one of the biggest
problem is to increase second when we got 999999 microseconds.
In current implementation there are some hacks (_I_think_) to speedup
this and in BCD arithmetic this is natural.
Of course I may be wrong, but this is only suggestion/idea.
PS. May intetion wasn't to start war. IMHO microoptimizations could
increase performance - that's all. Let's stop this thread here,
because as I see and as I said it's going to nowhere.
--=20
Pawel Jakub Dawidek pawel@dawidek.net
UNIX Systems Programmer/Administrator http://garage.freebsd.pl
Am I Evil? Yes, I Am! http://cerber.sourceforge.net
--0in9KoZ32yGPAlXZ
Content-Type: application/pgp-signature
Content-Disposition: inline
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.0.7 (FreeBSD)
iQCVAwUBPsSz9D/PhmMH/Mf1AQGfDwP/cMjRS9XxxH5mXZ/md1EIgCmoTwjFKOyv
iEcFuXOz399FdyZqSLqyd4eEG3dUW14z2hVmfKhJAqmiqYTbK+WKcZW11ZFtP5/r
fvM0UlBtGdxyimg/0CuG1Le91gBcSL20Bo4ydILfwhkTtxlYSW5Pmi3n8G3kgIPL
QLgROvyfOgA=
=xe49
-----END PGP SIGNATURE-----
--0in9KoZ32yGPAlXZ--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20030516094836.GW45118>