[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-users] 24TB redundant storage

One word "GlusterFS." Its software, its HA its fast, and you can grow it (i think live) and minimal configuration required.

On Tue, Apr 10, 2012 at 10:02 PM, Todd H. Foster <toddf@xxxxxxxxxxxxxxxxx> wrote:
Well, this is so true!  In my situation, I am big enough to get good support, but as far as a san goes, I can put together something out of, say IBM hardware (with service contract)  for less than 20k, have all the support that I need, and have the performance and storage of a 100k san.  My IBM contract is 24/7 and 1 hour response time, and this means someone waiting at the door.  IBM support is great!!! (when you are talking about enterprise products)

Now when we are talking about high performance hardware, you just can't get all of it a Fry's. (Fry's is 3 miles from my data center)   So the next best thing is to go with name brand server quality equipment...

One way or another you are going to pay for this type of system, either with time or support contracts or both!  What is down time worth?  To me it's a lot.

-----Original Message-----
From: xen-users-bounces@xxxxxxxxxxxxx [mailto:xen-users-bounces@xxxxxxxxxxxxx] On Behalf Of Fajar A. Nugraha
Sent: Tuesday, April 10, 2012 6:34 PM
To: xen-users@xxxxxxxxxxxxx
Subject: Re: [Xen-users] 24TB redundant storage

On Wed, Apr 11, 2012 at 8:10 AM, Luke S. Crawford <lsc@xxxxxxxxx> wrote:
> On Tue, Apr 10, 2012 at 12:39:49PM -0700, Todd H. Foster wrote:
>> Buy Dell, HP, or IBM and get a service contract.  IBM will even sell
>> you a contract on used equipment.

> I don't want (to pay for) support.  I've got a big spare pool, and I
> can get to it a hell of a lot faster than dell, IBM or HP.  Unlike
> those brands, I also am able and willing to diagnose an intermittent problem.

> And this didn't happen once;  over and over. Dell thinks it's
> acceptable that sometimes servers "just reboot"  -  They tell you to re-seat drives
> that have been kicked out of the raid.    They complain when you send
> back too many drives.

One thing that seems to work best for me, is to get a deal which includes:
- financing; you "lease" the server from a partner
- an SLA that says "maximum acceptable downtime"
- a contract that says "if you can't meet the service level, I'll cut your payment"

Of course, it only works if you're "big enough" (from vendor's
perspective) that the hardware vendors (or their partners) are willing to fight for your business :)

> I have had good (but very expensive) experiences with RHEL support;  
> part of that is I am just weaker on software than hardware, but I
> think part of that is that when RHEL says you are talking to a top
> level person, you are really talking to a top level person.

Correct. Getting to the "top level" (or at least the one in charge for regional support) might take some time, but they really know what they're talking about.


Xen-users mailing list

Xen-users mailing list

Xen-users mailing list



Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.