Memory Health

[Nobody's Hero]

Is there a utility in RedHat9 that will allow me to check for single bit memory errors. Or just check the overall health of memory. Like cstm in HPUX world? I know to check messages in /var/messages.

When I run a dmesg I get this warning:

Uhhuh. NMI received. Dazed and confused, but trying to continue
You probably have a hardware problem with your RAM chips

Any idea?

[Gopi Sekar]

use memtest86 program which is a standalone memory checking program.

it is available as part of installation CD1 of SUSE and Fedora core 4

Hope this helps,
Gopi

[Steven E. Protter · Accepted solution]

There is no cstm for Linux. I would be extremely concerned about that message. To the point that I'd bring the server down and keep swapping out RAM chips until I was able to boot the box without the dmesg output.

http://insight.zdnet.co.uk/hardware/servers/0,39020445,2132568,00.htm

http://people.redhat.com/dledford/memtest.html

http://www-106.ibm.com/developerworks/linux/library/l-rel/

http://slashdot.org/

Those links have some information or programs that you would like to use to diagnose the issue.

SEP
http://www.isnamerica.com/contactsep.shtml

[xyko_1]

Hi Robert,

You may get memtest86 here.

http://www.linux.org/apps/AppId_7360.html

Regards,
xyko