[OpenAFS] humungous disk caches
Derek Atkins
warlord@MIT.EDU
12 Mar 2003 20:04:36 -0500
Gee, and just a couple years ago I thought a 1G cache was too big..
It used to be that even a 1G cache would take HOURS to create, let
alone anything bigger. That was fixed, but there are other limits
to the caching, as you're seeing.
Honestly, I think you'll run into a bunch of other hashtable
limitations when you get that big. I also think you'll find that the
cache (as it's currently implemented) works better if it's smaller.
How big are these files that you're dealing with?
-derek
Bryan Bayerdorffer <bryan.bayerdorffer@analog.com> writes:
> Derrick J Brashear wrote:
> >>How about ext3? Does the journaling get in the way at all? Is ext2 the only
> >>safe option?
> > ext3 is fine.
> > reiserfs will blow up now, or later.
>
> Ok, ext3 it is. So what's the practical upper limit on the size of the disk
> cache? Switching to ext3 didn't affect the apparent 16GB limit, beyond which
> the first access to /afs will hang. Nothing in the kernel log. I haven't yet
> straced, but I will if there isn't an easy answer to this.
>
> Our apps are characterized by very large files that are read often and modified
> only rarely, so I'd like to see if a large disk cache (128GB) will improve
> performance.
>
> --
> .. ..-. ..- -.-. .- -. .-. . .- -.. - .... .. ... --. . - .- .-.. .. ..-. .
> Bryan Bayerdorffer bryan@meatspace.net bryan@spd.analog.com
> (Wit's End Computation Center) (Analog Devices)
>
> "Sing, O goddess, the anger of Achilles son of Peleus, that brought countless
> ills upon the Achaeans." -- Homer
>
> "Donuts---is there anything they can't do?" -- Homer
>
>
>
> _______________________________________________
> OpenAFS-info mailing list
> OpenAFS-info@openafs.org
> https://lists.openafs.org/mailman/listinfo/openafs-info
--
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