XFS is pretty tuneable - so you could play with inode size, log size
number of allocation groups etc to best suit your usage.
Such tuning doesn't seem possible with ReiserFS ...
The mongo benchmarks use relatively small files. XFS scales very well to
large files/directories, but that benchmark sticks to small scale stuff.
It *seems* to show ReiserFS in the best possible light and the XFS results
don't seem to reflect anything like real world experience (except that it
correctly highlights the relatively slow delete performance of XFS!)
I gave an XFS talk to the local Linux users group a couple of weeks ago
and in response to a discussion about performance and the Mongo benchmarks
(after the talk), I have been running some comprehensive benchmarks and
simulations (in my own time). I'll post my results in a week or two. when
the whole suite is finished.
All I'll say at this point is "interesting..."
Mike
-----------------------------------------------------------------------
Michael Gigante R&D Software Engineer mg@xxxxxxxxxxxxxxxxx
SGI Performance Tools Group, +61 3 9834 8233
Melbourne Australia V-Net: 524-8233
On Fri, 13 Jul 2001, Simon Matter wrote:
> "P.Dixon" schrieb:
> >
> > Hello,
> >
> > Any idea why xfs appears to be very much slower than reiserfs with these
> > benchmarks:
> >
> > http://www.namesys.com/benchmarks/mongo/2.4.5-xfs-ext2_vs_reiserfs.html
> >
> > Admittedly, the benchmarks were done by namesys...
>
> Maybe we have to ask Mindcraft for serious benchmarks :-)
>
> ReiserFS is good in handling large amount of small files, specially
> deleting them goes fast. That's all about it. The overall performance
> in real life is allmost the same with both filesystems. Its only
> one spcific situation where ReiserFS is really faster, but compare
> recovery time of both filesystems after a crash, XFS shows some 100%
> better perfomance than ReiserFS!
>
> Forget about benchmarks, run your on real life test and
> compare and cpu usage.
>
> Simon
>
> >
> > --
> >
> > Paul
> >
> > -------------------------------------------------------------------------------
> > Paul Dixon Email: P.Dixon@xxxxxxxxx
> > Department of Physics Phone: (020) 7882 5054
> > Queen Mary, University of London Fax : (020) 7882 5054
> > Mile End Road, London E1 4NS URL : http://hepwww.ph.qmw.ac.uk/~pd
> > -------------------------------------------------------------------------------
>
> --
> Simon Matter Tel: +41 61 695 57 35
> Fr.Sauter AG / CIT Fax: +41 61 695 53 30
> Im Surinam 55
> CH-4016 Basel [mailto:simon.matter@xxxxxxxxxxxxxxxx]
>
>
>
|