Hi.
We have been running a new AlphaServer 533au2 running DU4.0D. The
system has been crashing with the panic string "System Uncorrectable
Machine Check" intermittently while running heavy load. The system has
crashed with a uptime of 20 minutes to 14 days. This has happened
intermittently leading us to believe that this is a hardware problem. We
have had a memory board and cpu board replaced and the problems keep
coming back, tomorrow we are having the motherboard replaced. No one we
have talked too seem to have much experience running unix, I haven't
found the panic string listed in any documentation so far. What does
this error mean? This error message is similar (in spelling) to the "CPU
Machine Check" posted by Bart, however Our system has crashed and the
only errors in the syslog are:
>malloc failed: bucket size = 262144, #of failures = 1, ra 0xfffffc00004e81ac
>malloc failed: bucket size = 524288, #of failures = 1, ra 0xfffffc00004e81ac
>malloc failed: bucket size = 65536, #of failures = 1, ra 0xfffffc00004e81ac
>malloc failed: bucket size = 131072, #of failures = 1, ra 0xfffffc00004e81ac
Thanks Anthony
Received on Tue Mar 09 1999 - 23:08:43 NZDT