>>>>> "rl" == Rob Logan <r...@logan.com> writes:
rl> that's why this X58 MB claims ECC support:
the claim is worth something. People always say ``AMD supports ECC
because the memory controller is in the CPU so they all support it, it
cannot be taken away from you by lying idiot motherboard manufacturers
or greedy marketers trying to segment users into different demand
groups'' but you still need some motherboard BIOS to flip the ECC
switch to ``wings stay on'' mode before you start down the runway.
Here is a rather outdated and Linux-specific workaround for cheapo AMD
desktop boards that don't have an ECC option in their BIOS:
http://newsgroups.derkeiler.com/Archive/Alt/alt.comp.periphs.mainboard.asus/2005-10/msg00365.html
http://hyvatti.iki.fi/~jaakko/sw/
The discussion about ECC-only vs scrub-and-fix, about how to read from
PCI if ECC errors are happening (though not necessarily which stick),
and his 10-ohm testing method, is also interesting. I still don't
understand what chip-kill means.
I remember something about a memory scrubbing kernel thread in
Solaris. This sounds like the AMD chips have a hardware scrubber?
Also how are ECC errors reported in Solaris? I guess this is getting
OT though.
Anyway ECC is not just a feature bullet to gather up and feel good.
You have to finish the job and actually interact with it.
pgpYuGZlK9cDn.pgp
Description: PGP signature
_______________________________________________ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
