Re: [Benchmark] AIM9 results

[Andrew Morton]

Hans Reiser wrote:
> 
> Andrew and Chris, are these changes in performance definitely due to VM
> changes (and not some difference I am not thinking of between 2.5 and
> 2.4 reiserfs code)?
> 

aim9 is just doing

	for (lots)
		close(creat(filename))

ie: deleting a zero-length file.

So I changed inode_setattr() to not call into the filesystem
at all if i_size was not being altered.  Not a very interesting
optimisation, but it was simple to do.

It seems that reiserfs_truncate() has a lot of setup overhead.