Although I give the various players a hard time; the industry doesn't do everything badly and I try to see the positives as well as the negatives. So I was thinking about the perfect array and what features I would like to see! So a random stream of consciousness produced the following!
- Reliability – DMX-like reliability and robustness
- Scalability – DMX-like scalability for block, IBM SOFS for NAS
- Performance – DMX-like performance for block, BlueArc for NAS
- Flexibility – Support for all protocols in a common consistent manner like OnTap
- Thin Provisioning – 3Par's thin provisioning
- Wide Striping – Genuine wide-stripping across ALL Spindles not just a proportion or across groups of spindles – Think 3Par
- Automated Storage Tiering – Think Compellant on steroids!
- Automated Optimisation – Think 3Par
- Dedupe – Dedupe at block or file level – not seen a truly great dedupe solution yet
- Scalable Heterogeneous Support – IBM SVC or HDS
- Minimal-performance impacting Snapshots – think NetApp or….Sun
- Writeable Thin Clones – think LSI's DPM8400
- Synchronous Replication – think SRDF
- Asynchronous Replication – think of something which works without a huge amount of work
- Provisioning interface – think XIV, think 3Par
- Analytics – think Sun
- Monitoring/reporting – think Onaro
- Cost – think PC World (who are too expensive to but you get the idea!)
So a merger between IBM/EMC/HDS/NetApp/Sun/Compellant/BlueArc/LSI/3Par would be a great start. Let's throw Cisco into the mix as well for a unified data-centre fabric and we're done!
What features do you want to see? I'd love to know!
And vendors, without too much marchitecture, what are your killer features? The things that you are most proud of? I don't want a big bragging list but what's the one problem you think you've solved which you are most proud of?
Dedupe – How about the new Atlas dedupe from Riverbed? The variable byte window dedupe built into the array would be pretty cool.
I’d love to see some decent built in quota functionalltiy. Per directory at any depth. Regex rules to apply the quotas. Exclusions for certain groups. Per file extension limits. Would also love to see the rules stack over each other at different folder depths, like GPO or NTFS inherited permissions.
John
Stobod, I think you have the major points for 3PAR: thin provisioning, wide striping and automated optimization. We don’t talk about it as much, but the same mechanism that we use for thin provisioning also makes our snapshots very small and very fast. Then there is the art of the smackup, which is not necessarily a feature of the machine, but this is blogging after all.
I’d like to nominate an old employer of mine, Dell/EqualLogic for ease of installation. I’ve never seen anything that beats the EqualLogic architecture for getting up and running out of the box.
True, the EqualLogic VSA is extremely easy to get up and running. I imagine the real thing is equally easy.
And of course, 3Par should be proud of their Storage-Rapper..he is of course, unique!
Wide Striping – Genuine wide-stripping across ALL Spindles not just a proportion or across groups of spindles – Think 3Par, Think HP-EVA (been at it 8+ years now across 3-4 generations)
Provisioning interface – think XIV, think 3Par, Think HP-EVA (been at it 8+ years now across 3-4 generations)
I’ll give you the wide-striping but 3Par and XIVs interfaces are much easier than the HP EVA interface IMO. The EVA interface is pretty much on a par with Navisphere.
Also the 3PAR arrays scale much further than EVA.
I do find it amusing that you attribute performance to DMX – but hey…
Barry, never had any real problems with our DMXs from a performance point of view. Can only go on experience for things like that and I’ve not heard of a DMX being thrown out for poor performance. YMMV
Throw in Zero Page Reclaim – I believe only HDS do this at the moment but everyoneelse will follow
Extent based migration – Hopefully DMX-5 will set the ball rolling with this.
Optimized hardware architecture and internal algorythms etc to make best use of SSD/EFD – think DMX-4 and hopefully even better in DMX-5
Faster RAID rebuilt times – as quick as XIV but without the risks.
Inteligent non-blocking flux capacitor!
I suspect you’d end up with something you really didn’t want. Like a car designed with the best of everything, it would probably look — and smell — like a camel.
“Throw in Zero Page Reclaim – I believe only HDS do this at the moment but everyoneelse will follow”
3PAR’s latest ASIC chip has ‘Fat-to-Thin’ conversion capability using zero detection. Pretty sure this is the same thing.
Mike S
Yup, same thing…… potentially even better than the HDS implementation. I wasn’t 100% sure if 3Par was shipping yet, thats all. Either way (its either shipping or about to ship) its a great feature for the 3Par T-series to have up its sleave.
Im hearing more and more great stuff about 3Par…..
Nigel
Nigel, how many times do we have say ‘DMX5, that is not the array you are looking for; there is no such array!’