Skip site navigation (1)Skip section navigation (2)
Date:      Sat, 19 Apr 2014 11:11:40 +0200
From:      Rainer Duffner <rainer@ultra-secure.de>
To:        Berend de Boer <berend@pobox.com>
Cc:        FreeBSD FS <freebsd-fs@freebsd.org>
Subject:   Re: What happened with the GlusterFS port?
Message-ID:  <DFA6851C-86F2-4D8C-8D24-E4A9AD0CAE50@ultra-secure.de>
In-Reply-To: <87zjjhofu3.wl%berend@pobox.com>
References:  <28234312-7982-49F5-83FD-865649AA9CCB@ultra-secure.de> <1397850220.58880.16.camel@powernoodle.corp.yahoo.com> <CAKYr3zybY3hdXLpL-fCvqs%2B=syZ7uBE-FiXj%2BXcRGG1YoUZhOQ@mail.gmail.com> <7FAD7618-593D-4797-9EE9-BA36A87CE79B@ultra-secure.de> <87zjjhofu3.wl%berend@pobox.com>

next in thread | previous in thread | raw e-mail | index | archive | help
=09
Am 19.04.2014 um 10:59 schrieb Berend de Boer <berend@pobox.com>:

>>>>>> "Rainer" =3D=3D Rainer Duffner <rainer@ultra-secure.de> writes:
>=20
>    Rainer> GlusterFS would eliminate this (in situations where the
>    Rainer> customer needs a number of servers anyway).
>=20
> If it works. People who try gluster, usually are pretty disappointed.
>=20
> It's not a swap for your traditional nfs server.
>=20


Well, I was suspecting something like this.
We=92ve yet to make it production with the first GlusterFS customer - =
and then the ramp-up until it=92s running their whole stuff will be very =
long.
But I think their dataset is pretty small anyway.
We don=92t deal with a lot of data, usually.

=46rom what I have read, GlusterFS does not work very well with lots of =
small files (as they would occur in a website-hosting environment, where =
GlusterFS would look like a logical choice).
Is that still the case?








Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?DFA6851C-86F2-4D8C-8D24-E4A9AD0CAE50>