[OpenAFS] clarification on client caches

[Dexter 'Kim' Kimball]

At one site I consulted for we converged on 3 GB years ago  -- cache
filled with lots of tiny files ( < 15K) so lots of used chunks.  We
found that the cache algorithms did not deal well with 12 GB cache --
everything fine until time to purge, and then catatonia.  3GB was a good
number for us, it worked fine (no catatonia) and I haven't revisited
larger caches since.

Kim 

> -----Original Message-----
> From: openafs-info-admin@openafs.org 
> [mailto:openafs-info-admin@openafs.org] On Behalf Of Derek Atkins
> Sent: Tuesday, September 07, 2004 6:55 AM
> To: openafs-info@openafs.org
> Subject: Re: [OpenAFS] clarification on client caches
> 
> 
> Derrick J Brashear <shadow@dementia.org> writes:
> 
> >> Is it not typical to have cache sizes of this size?
> >
> > sadly no. most of my test hosts don't have that much free 
> disk, and a 
> > few don't have that much disk period.
> 
> Indeed, the cache algorithms probably don't deal well with 
> 5GB, let alone 20-30.
> 
> -derek
> -- 
>        Derek Atkins, SB '93 MIT EE, SM '95 MIT Media Laboratory
>        Member, MIT Student Information Processing Board  (SIPB)
>        URL: http://web.mit.edu/warlord/    PP-ASEL-IA     N1NWH
>        warlord@MIT.EDU                        PGP key available
> _______________________________________________
> OpenAFS-info mailing list
> OpenAFS-info@openafs.org 
> https://lists.openafs.org/mailman/listinfo/ope> nafs-info
>