Re: [Ext2-devel] disk throughput

[Andrew Morton]

Andreas Dilger wrote:
> 
> On Nov 05, 2001  14:22 -0800, Andrew Morton wrote:
> > But I don't know.  This is just all bullshit handwaving speculation.
> > We need tests.  Numbers.  Does anyone have source to a filesystem
> > aging simulation?  The Smith/Seltzer code seems to be off the air.
> 
> There is a guy doing fragmentation testing for reiserfs.  It turns
> out that (in his tests) reiserfs can get 10x slower as the filesystem
> fills up because of intra-file fragmentation.  I don't know enough
> about reiserfs block/file allocation policy to know how this compares
> to ext2 at all.
> 
> See http://www.informatik.uni-frankfurt.de/~loizides/reiserfs/agetest.html
> 

Wow.  That looks nice.  Unfortunately the tarballs are
missing several files.  read.cxx, agesystem.cxx, etc.  Plus
a number of dud links.

Constantin, could you please check that the agesystem3 tarball
builds OK, maybe put up a new one?   Thanks.

-