On Fri, Feb 20, 2009 at 03:09:28PM +0100, infernix ([email protected])
wrote:
> It looks to me like both the memory usage issue and the mounttime issue
> is fixed in pohmelfs-server git.
>
> So now I'll patiently await your solution to the find / problem. Once
> that's in I will swap my NFS mounts for POHMELFS :)
Cold cache issues with this test are related to the stat(2) performance
on the server. It takes about 30-35 seconds to stat all objects in the
linux kernel source tree, and this stat is performed for directory
reading to get information about the object.
NFS does not have this basically because its server is in the kernel and
it should not copy a not-that-small chunk of the data from kernel to the
userspace.
Test with the stat will show the same issues for the NFS and POHMELFS,
namely cold cache run will take about 1m8sec for POHMELFS and about
33-35 seconds for NFS, since POHMELFS will do two stats - on the server
and client, while NFS will do it on the client only (its in-kernel
server has access to the data directly). Hot cache run will show the
same 33-35 seconds both for POHMELFS and NFS, since there will be only
single stat on the client.
--
Evgeniy Polyakov
_______________________________________________
Pohmelfs mailing list
[email protected]
http://www.ioremap.net/cgi-bin/mailman/listinfo/pohmelfs
