Date: Wed, 07 May 2014 11:03:38 +0100 From: Pete French <petefrench@ingresso.co.uk> To: freebsd-geom@freebsd.org, kpielorz_lst@tdx.co.uk, petefrench@ingresso.co.uk Subject: Re: Anyone using HAST in production / performance? Message-ID: <E1WhyhO-000AYu-8Z@dilbert.ingresso.co.uk> In-Reply-To: <A6BBDA2C655FCD0A7D285AA3@study64.tdx.co.uk>
next in thread | previous in thread | raw e-mail | index | archive | help
> Looks like I'm back to looking at iSCSI -> ZFS then for now. HAST has coped
> with everything I've thrown at it ('failure' wise) but I need more speed
> than that as storage for VM's etc.
I would be interested to know how that works out - I tried iscsi
and ZFS a while ago, but my problem with it was that it didnt
handle failure very well - you took away the remote iscsi drive and
the ZFS layer locked up. Thats why I ended up using ggated + gmirror,
instead of iscsi + zfs. We switched back to ZFS when hast came along, but then
for me it is "fast enough"
My experiences with iscsi were a long time ago though - 2007 or so,
and am sure its rather different now!
cheers,
-pete.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?E1WhyhO-000AYu-8Z>