Return to BSD News archive
Path: sserve!manuel!munnari.oz.au!network.ucsd.edu!dog.ee.lbl.gov!horse.ee.lbl.gov!torek From: torek@horse.ee.lbl.gov (Chris Torek) Newsgroups: comp.unix.bsd Subject: Re: High Resolution getrusage Date: 3 Aug 1992 19:54:22 GMT Organization: Lawrence Berkeley Laboratory, Berkeley Lines: 17 Message-ID: <25172@dog.ee.lbl.gov> References: <1992Aug02.202928.20590@watson.ibm.com> <1992Aug3.055929.23488@Unibase.SK.CA> Reply-To: torek@horse.ee.lbl.gov (Chris Torek) NNTP-Posting-Host: 128.3.112.15 >w2chase@watson.ibm.com (Craig Chase) writes: >>... I need resolution better than 10 microseconds ... In article <1992Aug3.055929.23488@Unibase.SK.CA> roe@Unibase.SK.CA (Roe Peterson) writes: >Good luck finding a BSD machine of any kind out there with the necessary >resolution in the clock itself to provide this kind of resolution. Both the SPARCstation and the HP 9000/300 series machines have fairly high precision clocks. (The SPARC clock reads in us; the HP clock reads in units of 4 us.) When running 4.4BSD-alpha, both machines will give results accurate to a few microseconds for both gettimeofday() and getrusage(). Other BSD-derived systems may be hopelessly inaccurate, however. -- In-Real-Life: Chris Torek, Lawrence Berkeley Lab CSE/EE (+1 510 486 5427) Berkeley, CA Domain: torek@ee.lbl.gov