Re: [Moosefs-users] Questions and comparison

[WK <wk...@bn...>]

On 6/29/2011 11:35 AM, Sébastien Morand wrote:
>
> 1/ Why moosefs instead of glusterfs or xtreemfs?

I played with GlusterFS for the past two years and lurked on their 
mailing lists. We saw lots of little issues and when we did get it 
figured out, an upgrade would create a new set of problems. Note we were 
trying to accomplish replication in addition to storage, so we had more 
translators involved, than a simple layout.

The GlusterFS devs and community are really nice and talented, but I 
think they have created a situation where they are trying to accomplish 
too many things at once. You should look at the GlusterFS mail list 
archives. The recent introduction of 3.2.0 was yet again a big change 
that broke things and once again many people had to downgrade back.

Eventually, the GlusterFS people will get it right. They seem to have a 
lot of resources and an enthusiastic community.

I don't have any experience with XtreemFS


>
> 2/ glusterfs has been described in a paper I read from a french 
> university as really faster than moosefs, did you benchmark them too?
>

I did some crude benchmarks using dd and they were equivalent.  However, 
in actual practice, for our workload MooseFS is faster. That may simply 
be that it does a better job of caching, but the users are MUCH happier 
and the admin is much easier.

Jeff Darcy works for RedHat and is developing CloudFS which is based on 
GlusterFS. He is a huge Gluster fan and is active in the Gluster 
community.  His experience was that MooseFS was faster.

 From http://cloudfs.org/2011/02/

"A less well-known project is MooseFS. It’s broadly similar to GlusterFS 
in terms of being FUSE-based and having built-in replication, but 
diverges in other ways. Their “metadata logger” approach to surviving 
metadata-server death is not quite as good as true distributed metadata 
IMO, but it’s still far better than some systems’ “one metadata server 
and if it dies or slows to a crawl then SUX2BU” approach. Built-in 
snapshots are a feature that really sets them apart. I ran it through 
some very basic tests on some of my machines, and it fared very well. I 
don’t mind saying that it was significantly better than GlusterFS for 
the workloads I tested, so it’s worth checking out."

So I think it depends upon the workload and the configuration.

> 3/ Why fuse and no kernel mode (should be faster)?
>

Thats for the devs to answer, but I would imagine Fuse is much easier to 
maintain and develop for.

WK