Date: Thu, 30 Dec 1999 08:25:28 +1100 From: Peter Jeremy <peter.jeremy@alcatel.com.au> To: "Kenneth D. Merry" <ken@kdm.org> Cc: freebsd-hardware@FreeBSD.ORG Subject: Re: ECC RAM useless with FreeBSD? Message-ID: <99Dec30.081608est.40322@border.alcanet.com.au> In-Reply-To: <19991228215756.A94267@panzer.kdm.org>; from ken@kdm.org on Wed, Dec 29, 1999 at 03:57:56PM %2B1100 References: <8070C3A4E99ED211A63200105A19B99B317471@mail.edifecs.com> <19991228215756.A94267@panzer.kdm.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On 1999-Dec-29 15:57:56 +1100, "Kenneth D. Merry" <ken@kdm.org> wrote: > As it stands, though, you won't know about a 1-bit memory >problem if you turn ECC on. The i440LX (and presumably later and better controllers) records details of the latest ECC correction - at least to the extent of which DIMM it was. It can also be configured to detect, but not correct, single bit errors (which prevents a 3-bit error being silently converted into 4 invalid bits). I'm not sure whether it can trigger an interrupt on correction. It would be fairly easy to write a scrubber daemon that woke up (or was run from cron) regularly and read all of physical RAM (via /dev/mem). It could report any ECC corrections it caused (or that were present when it started). Peter To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hardware" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?99Dec30.081608est.40322>