lkml.org 
[lkml]   [2000]   [Jul]   [5]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: BK performance tip (22x faster)
On Wed, Jul 05, 2000 at 11:28:08PM +0100, Alex Buell wrote:
> On Wed, 5 Jul 2000, Richard Gooch wrote:
>
> > > 2.3/4 kernels use a SLAB cache for inodes, instead of an ad hoc
> > > cache. the old limit was used to determine when to reap inodes.
> > > the new system reaps them automatically when system memory is short.
> >
> > Good. That's what I was hoping for.
>
> Does this means buffer cache corruption causing Linux 2.2.x to lose its
> lunch are a thing of the past? 'Cause I've just had my machine die twice
> in the last two days due to this thing!
>
> I'd love to see self-correcting software ECC for caches.

Hmm. BK has a sort of lame checksum that it uses for integrity and we
used to see checksum failures frequently until I stopped buying memory
without ECC. This same lame checksum was what found the cache aliasing
bug in SPARC/Linux.

At any rate, I have been using 2.2.15-pre9 for months without any errors
so are you sure that it is buffer cache corruption and not bad memory
dimms? If you are sure, I want to know.
--
---
Larry McVoy lm@bitmover.com http://www.bitmover.com/lm

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2005-03-22 13:57    [W:0.070 / U:0.812 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site