On 3/20/07, Malcolm Rowe <malcolm-svn-dev@farside.org.uk> wrote:
>
>
> I created a 2GB file on my local (ext3) partition and created a variety
> of filesystems on it via a loopback mount. I then mounted the new
> filesystem and created 2^20 empty files on it, measuring amortised
> open() time at various points. I tested using the current scheme (all
> files in one directory) and the sharding-by-1000 scheme.
>
> I tested ext2, ext3 (with and without dirindexing), reiserfs, vfat, and
> hfsplus. I wasn't able to test NTFS, unfortunately.
I wrote a VBScript script this morning that basically, I think, duplicates
what you did except on NTFS on Windows XP Pro on a laptop with a 7200rpm IDE
hard disk. It creates 2^20 files and measure the performance of opening the
file for reading every 1,000 files. (Rename attachment to have .vbs
extension to run on Windows.)
Most of the time, the duration was so small it didn't register with the
VBScript Timer function. I did get several opens that output 0.0078125 sec
or similar very small value.
Does that change the conclusion at all?
---------------------------------------------------------------------
To unsubscribe, e-mail: dev-unsubscribe@subversion.tigris.org
For additional commands, e-mail: dev-help@subversion.tigris.org
Received on Wed Mar 21 18:42:30 2007