home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!munnari.oz.au!bruce.cs.monash.edu.au!monu6!vaxc.cc.monash.edu.au!johnhm
- From: johnhm@vaxc.cc.monash.edu.au
- Newsgroups: comp.os.linux
- Subject: Re: AMD386 vs. Intel386 & external cache problems
- Message-ID: <1992Aug13.175743.89748@vaxc.cc.monash.edu.au>
- Date: 13 Aug 92 17:57:43 +1000
- References: <1992Aug12.153149.29972@news.th-darmstadt.de>
- Organization: Computer Centre, Monash University, Australia
- Lines: 52
-
- In article <1992Aug12.153149.29972@news.th-darmstadt.de>, herr@hp11.iti.informatik.th-darmstadt.de (Gabor Herr) writes:
- > Hello Linuxers,
- >
- > two weeks ago I posted to this newsgroup, that I had problems with my new 386
- > motherboard (AMD386, 40MHz, ETEQ Cougar chipset, 64KB cache, 8MB memory).
- > Running Linux on it, from time to time some processes or even
- > the kernel died with a signal SIGSEGV, which was caused by a `general protection
- > error'. After turning off the onboard external cache everything worked
- > fine.
- >
- lines deleted
- > I also want to know what was the reason for this kind of errors.
- > Therefore some questions:
- >
- > - Is there anybody out in the net using Linux on a configuration
- > similar to my old one? Please try to run the above tests and tell me
- > if it worked...
- >
- > - Are there differences between AMD 386 and Intel 386? Has the AMD
- > probably some bugs?
- >
- > Thanx...
- >
- > Gabor
- >
- >
- I have had similar problems although not in quite the the same degree.
- I have a 25Mhz Intel 386 chip on a motherboard with 64k cache, ETEQ chipset
- and 8Meg of memory (8 x 1Meg SIMMS). Io cards include ET4000 video, io card,
- mfm HD controler, and AHA1542B SCSI controler (all exept for SCSI are noname).
- I would get segmentation or general protection faults occasionaly when
- memory was pretty full such as during compiles, compiling under X windows
- was'nt practical. I found that disabling memory interleaving with BIOS setup
- would make the machine much more reliable but still not good enough for
- compiling under X windows, X windows would sometimes hang the machine
- (only rarely though). The change in behaviour made me suspect memory faults
- were occuring sometimes when addressing one memory bank then the other.
- Yesterday I tried removing one bank of memory and found that memory faults
- still occured. Susspecting a bad SIMM now I tried swapping the second bank
- and was able to compile the kernel without errors. 0.97p1 is far more prone
- to generating these errors, presumably because execution is more widely
- spread over memory. Up to 0.96cp3 I could reliable compile without using
- Xwindows. The problem is NOT resolved yet though since I have yet to get
- down to SIMM which I can say I faulty, it may be a wild goose chase anyway.
-
- --
-
- John H. Morris E-mail: johnHM@vaxc.cc.monash.edu.au
- Monash University Computer Centre Phone: +61 3 5654763
- Wellington Road, FAX: +61 3 5654746
- Clayton 3168,
- Australia.
-