Re: [PROPOSAL] Coping with random bit errors

H. Peter Anvin (hpa@transmeta.com)
11 Oct 1997 01:30:32 GMT

Messages sorted by: [ date ][ thread ][ subject ][ author ]
Next message: Herbert Xu: "fireport 40 not supported (fwd)"
Previous message: Richard Gooch: "Re: [PROPOSAL] Coping with random bit errors"
Maybe in reply to: Richard Gooch: "[PROPOSAL] Coping with random bit errors"

Followup to: <Pine.LNX.3.95dg3.971010180732.21333A-100000@twinlark.arctic.org>
By author: Dean Gaudet <dgaudet-list-linux-kernel@arctic.org>
In newsgroup: linux.dev.kernel
>
> Even when you have ECC it's worthwhile for an idle thread to go through
> ram doing a read and writeback of every byte. This allows single-bit
> errors to be corrected before they become two-bit errors.
>

I like this idea...

-hpa

-- 
    PGP: 2047/2A960705 BA 03 D3 2C 14 A8 A8 BD  1E DF FE 69 EE 35 BD 74
    See http://www.zytor.com/~hpa/ for web page and full PGP public key
        I am Bahá'í -- ask me about it or see http://www.bahai.org/
   "To love another person is to see the face of God." -- Les Misérables

Next message: Herbert Xu: "fireport 40 not supported (fwd)"
Previous message: Richard Gooch: "Re: [PROPOSAL] Coping with random bit errors"
Maybe in reply to: Richard Gooch: "[PROPOSAL] Coping with random bit errors"