Re: memory & filesystem corruption under heavy load?

garth zenie (gzenie@espresso.hampshire.edu)
Fri, 05 Apr 1996 17:09:18 -0500


On Fri, 5 Apr 1996 10:18:48 -0500 Robert L Krawitz wrote:

> What does the corruption look like?

from pgtable.h:

***************

"lock\n\t" \
"btsl $0, "SYMBOL_NAME_STR(kernel_flag)"\n\t" \
"jnc 3f\n\t" \
"cmpb "SYMBOL_NAME_STR(activeries per page directory level: the i386 is two-level, so
* we don't really have any PMD directory physically.
*/
#define PTRS_PER_PTE 1024
#define PTRS_PER_PMD 1
#define PTRS_PER_PGD 1024

***************

sometimes it is much more profound than this. it just look like
complete garbage has been dumped into the file.

i failed to mention in my first message (i should fall out of the
habit of making posts when i am on the verge of unconsciousness), that
there is a strong possiblity that there is a SCSI factor to all of
this:

**Tagged Queuing** **Kernel Version** ** Corruption **
off 1.2.13 never
off 1.3.77 never
on 1.2.13 never
on 1.3.77 always

this seems to imply that it isn't a hardware problem. it does however
seem to point a finger at the SCSI code. however, it could be some
bug which is brought out by the (much) increased disk performance when
tagged queuing is turned on.

> Is there anything in common here? Does everyone who's seeing problems
> have, say, a Pentium, or do people with 486 and other systems see this

well, here's the breakdown on my system just in case it is of any use
to anybody:

P166 (brand new)
32MB EDO RAM
256k pipelined cache
Micronics M54Hi Motherboard
PCI 3c590 ethernet (vortex)
PCI Buslogic BT-948
PCI Triton IDE
PCI Diamond Stealth Video VRAM
ISA Soundblaster 16
Conner CFP2107S SCSI drive

i don't have this problem on any of the (slower) linux boxes that i
take care of. unforunately, none of them are PCI so i can't try the
buslogic card in one of them.

-- garth