Date: Wed, 16 May 2001 01:29:09 -0700 From: Terry Lambert <tlambert2@mindspring.com> To: Matt Dillon <dillon@earth.backplane.com> Cc: dave <dleimbac@earthlink.net>, freebsd-questions@FreeBSD.ORG, arch@FreeBSD.ORG Subject: Re: Gettimeofday Again... Message-ID: <3B023A55.D8E21C03@mindspring.com> References: <200105150337.UAA19677@gull.mail.pas.earthlink.net> <200105150346.f4F3kLE45720@earth.backplane.com> <3B00EF40.A1232B75@mindspring.com> <200105151737.f4FHbBL55271@earth.backplane.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Matt Dillon wrote: > :The gettimeofday() calls were _the_ major useless overhead, > :until I eliminated them by creating a zero system call version > > Terry, to be blunt... if you need performance you don't go > making superfluous system calls for every transaction. If > you want marketing eye candy, all you need to do is a > statistical measurement... do fine measurement of 10% of > the transactions rather then fine measurement of 100% of > the transaction, and you are done. > > Also, using gettimeofday() is a ridiculous way to measure > fine grained time billions of times in production code. I > mean, sure, it works... but getitimer() is about 5 times > faster. I didn't need it for elapsed time measurements, I needed it for log timestamps, so getitimer() would be useless. BTW... to be blunt, gettimeofday() wouldn't be _the_ major useless overhead, if I were making superfluous system calls. ;^). -- Terry To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-questions" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?3B023A55.D8E21C03>