Return to BSD News archive
Path: euryale.cc.adfa.oz.au!newshost.carno.net.au!harbinger.cc.monash.edu.au!news.rmit.EDU.AU!news.unimelb.EDU.AU!munnari.OZ.AU!spool.mu.edu!howland.erols.net!news.sprintlink.net!news-peer.sprintlink.net!newsfeed.internetmci.com!newsfeed.direct.ca!nntp.portal.ca!van-bc!n1van.istar!van.istar!west.istar!ott.istar!istar.net!gateway.qnx.com!not-for-mail From: doug@qnx.com (Doug Santry) Newsgroups: comp.unix.bsd.freebsd.misc Subject: Re: Embedded FreeBSD Date: 22 Jan 1997 15:38:45 -0500 Organization: QNX Software Systems Lines: 27 Message-ID: <5c5tsl$116@qnx.com> References: <32B744C0.2DA9@wdc.net> <5c08m3$dvk@qnx.com> <5c14ih$7nn@uriah.heep.sax.de> <32e4a295.4103196@news.zippo.com> NNTP-Posting-Host: qnx.com Xref: euryale.cc.adfa.oz.au comp.unix.bsd.freebsd.misc:34392 In article <32e4a295.4103196@news.zippo.com>, Enoch Wexler <wexler@inter.net.il> wrote: >On 21 Jan 1997 01:02:09 GMT, j@uriah.heep.sax.de (J Wunsch) wrote: > >>doug@qnx.com (Doug Santry) wrote: >> >>> The kernel is riddled with splhigh() calls. I wouldn't trust a device >>> that needs attention in under 2 microseconds on a Unix system. QNX >>> can guarantee it on a 200 MHz pentium. That is the worst case interrupt >>> latency. >> >>Sure, 2 µs is certainly out of the question with a Unix kernel. 20 µs >>probably not. Hey!, my old CP/M BIOS had to pick up one byte after >>each 16 µs from the FDC -- without DMA. :-) >> >>The biggest problem is to keep the splhigh() times short. > >Ask the hardware engineer to do a better job and relax that 2 µs >constraint... Enoch. Nothing to do with the hardware engineer. Sometimes that is the rate that events occur. The ABS in a car needs performance and can't wait around for servicing. There are tons of hard deadline scheduling problems that are simply the nature of the world around us and not the hardware. We aren't talking about sound cards here. DJS