| 1 |
On Tuesday 25 November 2008, Jorge Peixoto de Morais Neto wrote: |
| 2 |
> > Now, since I usually compile software in a tmpfs, I guess the |
| 3 |
> > filesystem makes nearly zero difference. Video encoding is obviously |
| 4 |
> > bound by CPU, cache and RAM speed, not filesystem. Web rendering is |
| 5 |
> > also hardly affected by filesystem . And launching programs means |
| 6 |
> > mostly reading files, and would reiserfs be significantly faster than |
| 7 |
> > ext3 for this, specially considering that my system is minimalist and |
| 8 |
> > the root partition is only 7% used? |
| 9 |
> > |
| 10 |
> > So it seems I should not have chosen reiserfs, which has a fame of |
| 11 |
> > being less safe than ext3, and certainly has less software support |
| 12 |
> > than ext3. The next time I format my root partition, I will choose |
| 13 |
> > ext3 (then move to ext4 when it is stable). |
| 14 |
> |
| 15 |
> Oh, and according to this benchmark |
| 16 |
> http://linuxgazette.net/122/piszcz.html |
| 17 |
> reiserfs does not deserve its speed fame. |
| 18 |
|
| 19 |
they tested crap. |
| 20 |
|
| 21 |
As I wrote in the other mail. XFS and reiserfs turn on barriers by default, |
| 22 |
ext3 turns them off. |
| 23 |
With barriers on for ext3 it looses 30%(!). reiserfs and xfs don't suffer as |
| 24 |
much, but suffer they do. So if the test did not turn on or off barriers for |
| 25 |
all fs who support them, ext3 had an unfair advantage. |
| 26 |
|
| 27 |
And you want barriers. |
Archives