Re: New Motherboards ECC memory and PCI-E issues

On Tue, 23 Jan 2007 12:57:20 GMT, anton@xxxxxxxxxxxxxxxxxxxxxxxxxx
(Anton Ertl) wrote:

sndive@xxxxxxxxx writes:
jimomuraNOSPAM@xxxxxxxxxxx wrote:

.. . .

I think gamers care only about latency and the rest of the consumers
are way too stupid to demand ECC.

.. . .

OTOH, I never had any data errors (that I know of) until I bought the
ASUS K8V Deluxe in 2003 with ECC memory; this worked mostly, but for
some things (in particular, having to do with USB, but also often when
unpacking a Linux kernel) I got wrong data (without error messages or
anything).

Was that running Linux or another OS? The errors are not always
correctable, but a signal should also be sent to the OS. Then
again, the problems might not have been due to memory, as you
mention below.

I returned the motherboard, and got a K8V SE Deluxe
instead, which does not have this problem (it still has a problem
booting 64-bit Linux, but I know a workaround for that).

Oh? Which Linux?

So, while ECC may reduce the probability of data corruption, it does
not eliminate it, and the other sources of data corruption may be more
significant than RAM errors. Still, for our servers, we require ECC.

I have had occasion to check other peoples computers, (and my own)
with Memtest86 or other memory checking software, and over the
years I have come to the conclusion that bad memory systems (not
necessarly defective RAM) are the most common faults. Even
Windows is not necessarily as bad as some people think it is.
It is often a good place to start looking for low frequency
"elusive" problems. On one computer I found a problem that I
still do not really understand. With 1 stick of DDR, it would
give 1 pass of Memtest86 without errors, but the 2nd pass would
eventually show up errors. After finding that I make certain
that I run Memtest86 at least 3 full passes before marking it
off as a good memory system. I have never found an error on the
3rd pass if the 2nd pass was OK, but then again, I never really
expected to find an error on the 2nd pass (unless overheating
was at issue).

----== Posted via Newsfeeds.Com - Unlimited-Unrestricted-Secure Usenet News==----
http://www.newsfeeds.com The #1 Newsgroup Service in the World! 120,000+ Newsgroups
----= East and West-Coast Server Farms - Total Privacy via Encryption =----
.

Relevant Pages

  • Re: What happens to Linux on a parity check?
    ... Linux has either never failed or handles the problem quietly. ... I don't believe I ever had a memory hardware problem on a Linux ... Do you have ECC on that system? ... There might be parity on the caches in which case a parity ...
    (comp.os.linux.hardware)
  • Re: 2 Gigabyte ddr2 memory modules for P5K WS
    ... P5K because it has a serial port and I need one for an old Wacom ... and it appears to be pretty stable with 8 gigs of memory. ... It is possible to get ECC protection for memory products, ... x38 chipset, but am I really future proofing a computer, or will I ...
    (alt.comp.periphs.mainboard.asus)
  • Re: 2 Gigabyte ddr2 memory modules for P5K WS
    ... x38 chipset, but am I really future proofing a computer, or will I ... Things like CSI and integrating the memory controller on the processor, ... Crush all chipset maker opposition (VIA is already out of the picture, ... I might consider four sticks with ECC. ...
    (alt.comp.periphs.mainboard.asus)
  • Re: ECC and DMA to/from disk controllers
    ... that a disk controller correctly reads data from disk and ... has correct data in the controller memory and buffers. ... ECC bits would be calculated in server memory based on incorrect data from ... One example is "bus mastering" DMA itself. ...
    (Linux-Kernel)
  • Re: Any comparisons of Opteron F and Woodcrest yet?
    ... memory capacity. ... What do L, SMP and ECC mean? ... Socket F and AM2 are very similar, as are Conroe and Woodcrest. ... Each Woodcrest/Conroe and Socket F/AM2 processor contains 2 cores. ...
    (comp.arch)