RHEL 4 U5 - Server immediate shutdown

Dear all,

My server has shutdown frequently.
It is AMD64, OS is RHEL 4 U5.
I've seen the system log, before the shutdown occured:

Jul 29 04:28:56 localhost kernel: EDAC k8 MC0: general bus error: participating processor(local node response), time-out(no timeout) memory transaction type(generic read), mem or i/o(mem access), cache level(generic)
Jul 29 04:28:56 localhost kernel: MC0: CE page 0x2c3ea7, offset 0x570, grain 8, syndrome 0x1cc8, row 5, channel 0, label "": k8_edac
Jul 29 04:28:56 localhost kernel: MC0: CE - no information available: k8_edac Error Overflow set
Jul 29 04:28:56 localhost kernel: EDAC k8 MC0: extended error code: ECC chipkill x4 error

So I googled & found out the tool memtest86+ that checks the memory errors. I run the memtest86+ for 26 hours. Its 1st test was finished, but no more errors.

What should I do now?

Please help

EDAC is set of drivers in the Linux kernel that handle detection of ECC errors from memory controllers, so even though "memtest86+" haven't noticed errors, the memory may be corrupted in some undetectable way. Depending on the RAM modules you have, and server's importance, you can :
a) remove RAM modules one by one, thus eventually detect the faulty one.
b) ask the vendor of the machine for possible solutions.
c) replace all the RAM modules you have.

Thank you very much. I will try them now.