Re: memtest86, built into kernel

Matthias Urlichs (smurf@smurf.noris.de)
Tue, 23 Apr 1996 08:31:59 +0100

In linux.dev.kernel, article <199604221629.RAA00579@elbereth.sophos.com=
>,
Matthew J Brown <mjb@sophos.com> writes:
>=20
> Basically they say there that with modern SIMMs the MTBF for a soft
> error (ie. alpha particle corruption) is between 12-30 years of
> continual system use.
>=20
There are other problems (for instance, marginal memory timing) which
parity can catch.

> Given that it happens so rarely, that parity is only 50% likely to
> catch the error anyway,

Parity catches _all_ errors, assuming(!) they affect only a single bit.

> it doesn't seem worth it to me. ECC is more useful, since it will
> correct single-bit errors rather than just hanging.
>=20
That's right, but even more expensive. :-(

Is there any Linux-capable machine that offers ECC?
If so, can Linux be patched to (a) detect that, (b) interrogate the ECC
hardware which bank has the faulty bit? The answer, currently, is No,
unfortunately.

--=20
Having children is like having a bowling alley installed in your brain.
-- Martin Mull
--=20
Matthias Urlichs \ Noris Network GmbH i.Gr/ Xlink-POP N=FCrnberg=
=20
Schleiermacherstra=DFe 12 \ Linux+Internet / EMail: urlichs@nor=
is.de
90491 N=FCrnberg (Germany) \ Consulting+Programming+Networking+etc'i=
ng
PGP: 1B 89 E2 1C 43 EA 80 44 15 D2 29 CF C6 C7 E0 DE=20
Click <A HREF=3D"http://smurf.noris.de/~smurf/finger">here</A>. =
42