Return to BSD News archive
Path: sserve!newshost.anu.edu.au!munnari.oz.au!bunyip.cc.uq.oz.au!harbinger.cc.monash.edu.au!yeshua.marcam.com!news.kei.com!bloom-beacon.mit.edu!grapevine.lcs.mit.edu!grapevine!jtw From: jtw@lcs.mit.edu (John Wroclawski) Newsgroups: comp.os.386bsd.development Subject: Re: [FreeBSD 1.0R] DMA Problems? Date: 04 Jan 1994 04:43:17 GMT Organization: MIT Home for Wayward Triumphs Lines: 36 Message-ID: <JTW.94Jan3234318@pmws.lcs.mit.edu> References: <jmonroyCIHJA2.oy@netcom.com> <2fl24q$jn2@u.cc.utah.edu> <jmonroyCIo4yD.1G5@netcom.com> <2fnapb$6eb@u.cc.utah.edu> <jmonroyCIvwpv.8F3@netcom.com> NNTP-Posting-Host: pmws.lcs.mit.edu In-reply-to: jmonroy@netcom.com's message of Fri, 31 Dec 1993 05:32:19 GMT In article <jmonroyCIvwpv.8F3@netcom.com> jmonroy@netcom.com (Jesus Monroy Jr) writes: To clarify the issue: DMA DRAM refresh skipping would be a bad term to use. What happens is the timer for channel 0, the DRAM refresh timer, is reprogrammed so that there are less refreshes per second (ie. 2000 new vs. 3000 old refreshes per second)... It is possible, via software, to reprogram the refresh cycle. My example program does this. The results are had when the system crashes. That is, to make this a software *probe* the program would (if it existed for *BSD) slowly turn down the timer till the system crashed. At this point, some test could readily determine the *consistency* of ths system. This won't work very well. It is impossible to -probe- for a minimum DRAM refresh rate because the answer is not binary. If you avoid refresh for long enough, yes, the data will flat-out be lost. But long before that the DRAM will simply become much more sensitive to power supply noise, cosmic rays, lightning, and all of the other things that occasionally cause DRAMS to lose data. Unless you can duplicate all of these external events during your probe operation, you cannot even begin to predict when the RAM will fail. For what it's worth most DRAMS operating at room temperature will hold bits fairly well for at least ten times longer than the specified refresh interval. This value falls rapidly at higher temperatures. At the specified maximum operating temperature, the longest time you can wait safely is fairly close to the listed refresh interval. John Wroclawski jtw@lcs.mit.edu