Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 7 Sep 2001 20:40:22 +0200 (CEST)
From:      Oliver Fromme <olli@secnetix.de>
To:        freebsd-stable@FreeBSD.ORG
Subject:   Re: 4.4-rc instability
Message-ID:  <200109071840.UAA29351@lurza.secnetix.de>
In-Reply-To: <5.1.0.14.2.20010828100929.03f6c0c0@netmail.home.com>

next in thread | previous in thread | raw e-mail | index | archive | help
Carroll Kong <damascus@home.com> wrote:
 > At 12:11 PM 8/28/01 +0200, Oliver Fromme wrote:
 > [...]
 > > Frankly, I expected the machine to halt or freeze with
 > > something like an NMI or "parity check error", like the old
 > > PCs with parity SIMMs did.  Would have been better than
 > > just randomly dying.
 > 
 > But it cannot detect triple bit errors,

Nope, it can detect _most_ triple-bit errors, too, but just
not all of them.  It is _guaranteed_ that it'll detect all
two-bit errors, though.

 > which is probably what you had, and 

I think it would be a very strange thing if all of those
errors were exactly triple-bit errors, and even that kind
of triple-bit errors that slipped through the ECC detection.
In fact, when the RAM had grown so many defects that I
couldn't even boot single-user anymore, I guess that whole
bitlines of the chips were failing.

 > NEITHER could the parity simms which would fail if you got double bit 
 > errors.  It would just silently say "yahoo we are ok!" since a double bit 
 > error would "undo" any real error.  Quite primitive.

Not quite.  Typically, defective RAM doesn't "flip" bits
from 0 to 1 and vice versa, but grounds certain bits to 0
(or to 1), no matter what you write to it.  Another thing
that can happen typically is that the bits become "weak"
and lose their value between two refresh cycles.

So, if you have two defective bits in a memory unit (8,
32 or 64 bits, depending on the type of SIMM or DIMM),
this will usually be detected sooner or later, when
different values are written to it, even when using
ordinary parity.

Regards
   Oliver

-- 
Oliver Fromme, secnetix GmbH & Co KG, Oettingenstr. 2, 80538 München
Any opinions expressed in this message may be personal to the author
and may not necessarily reflect the opinions of secnetix in any way.

"All that we see or seem is just a dream within a dream" (E. A. Poe)

To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-stable" in the body of the message




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200109071840.UAA29351>