Symmetrix Virtual Provisioning Space Reclamation reduces capacity requirements and total cost of [...] ]]> I spent some time today looking at the release notes for Enginuity code 5874.207.166, which presumably is the one that brings the much lauded Fully Automated Storage Tiering (FAST) into general release on V-Max.  Just above the FAST paragraph I found the following:

Symmetrix Virtual Provisioning Space Reclamation reduces capacity requirements and total cost of ownership by automatically reclaiming chunks (768 KB track groups) that contain all zeros. This is most effective when used on volumes after thick-to-thin migration or replication.

So, it seems that V-Max now supports features previously only seen on 3Par InServ, HDS USP V and HP XP – that is the ability to reclaim empty “zeros” of data from LUNs – otherwise known as Zero Block Reclaim.

I don’t remember EMC mentioning this little fact as part of their big FAST announcement.  In fact, looking back over Barry B’s posts, here’s a link to a post from July in which Barry indicates (quoting again);

I cannot confirm nor deny that VP will support one or more unused space reclamation approaches in the future.

So do EMC just see ongoing space reclamation as a BAU activity, not worthy of an announcement?  I’m surprised that this would be the case.  Reclamation of “empty” storage is incredibly important when migrating from thick->thin storage environments.  Hitachi quote around 40% savings from using ZPR after a migration to thin provisioning on USP V.

Perhaps EMC don’t want us to know that migrating to V-Max can actually reduce the amount of storage in use.  After all, its not good for hardware sales, is it?

By the way, EMC, please feel free to comment on this new feature and how easy it is to use.  I’d be interested to discover how it is implemented.

So for me the day kicked of with Joe Tucci’s keynote speech.  Check it out here.  It’s the first time I’ve seen Tucci speak and he doesn’t come across [...] ]]> Day 1 at this year’s EMC World is now over.  Did we see any game changing new technology or focus?  I don’t think so.

So for me the day kicked of with Joe Tucci’s keynote speech.  Check it out here.  It’s the first time I’ve seen Tucci speak and he doesn’t come across to me as the most charismatic performer.  My overall impression of his presentation content was one of consolidation and incremental change.  The EMC steamroller is clearly heading towards hardware commoditisation and virtualisation.  That message expressed pretty clearly in Tucci’s “next big thing” slide; there are four areas: The Virtual Datacentre, Cloud Computing, Virtual Clients, Virtual Applications.  For a storage company, the message is less about storage and more about the VMware platform.  Is this a positioning exercise for an acquisition by Cisco?

Paul Maritz then stood up and gave us the future of VMware and vSphere.  I heard someone say that the presentation wasn’t new and had been given at a previous VMware shindig.  Again, the message is incremental change but leveraging the ability to “federate” resources and have them running in your datacentre (internal cloud) or with an external service provider (external cloud).  One thing I find interesting is the idea of a flexible charging model – move processing around and pay for what you use.  However the major issue with this idea is the lack of control over what the user can do; is it really a good thing to give your users unbridled access to computing resources?  Where are the cost controls?

Later in the day I checked out a V-Max architecture session.  There’s lots of new incremental changes to the product; 512 hypers per disk (make 1TB drives more useful), new replication devices (R11/R21/R22) to bring improvements to SRDF/STAR and replication technologies, plus a host of other useful changes too numerous for me to mention.  What comes across well in these presentations is EMC’s engineering quality.  There’s good reasoning and structure to the changes they announce and they are pretty well customer focused (for example, incremental improvements to invalid track processing to speed up SRDF failbacks).  EMC do a good job of getting the message out on these changes (specifically Barry Burke’s blog) and there are precious few others in the industry doing a similar thing with this level of depth (the exception for me being Barry Whyte).  HDS and the rest of IBM could do with finding some decent bloggers to get the message out.  Most of us don’t want to wade through product manuals to find these new features; new media can be used to get this message across and with Twitter and blogging EMC are still taking the lead.  HDS clearly have a lot to learn in this area judging by their poor counter-EMC views posted this week.  

Later in the day I wandered around the Solutions Pavilion.  I’ll post more on that for Day 2, in the meantime, here’s a link to my Flickr pictures of the event so far.

EMC World 2009 Images

So, here’s the thinking. [...] ]]> As I  sit here at the start of EMC World Day 1, I’m pondering over some of the conversations of last night.  The direction EMC are taking with V-Max, the Atmos product and Clariion makes me wonder if DMX could be classed as the last of the (EMC) monolithic storage arrays.

So, here’s the thinking.  DMX arrays started to use the DAE (Disk Array Enclosure), previously deployed on Clariion.  Atmos uses this as well.  So effectively these three devices all use a common disk shelf technology.  With the release of V-Max, EMC have moved away from the monolithic design of DMX and to a more modular, node-based controller architecture using Intel processors.  So other than software, doesn’t that make all three storage arrays effectively the same product?

It’s About The Software Stupid

Perhaps EMC are making good on their promise of being a software company.  Make the hardware a commodity and put all the investment into the software.  After all, there’s no margin in hardware any more, or so we’re told.  

Here’s another thing to ponder.  If V-Max is going to be node-based, do all of those nodes have to be running Enginuity?  How easy would it be to flip some of them into Atmos mode, Clariion mode, or even turn them into a virtual tape library?  Perhaps you wouldn’t do that within a local cluster, but the option is there (and the intention from what EMC are implying) to move to geographically dispersed clusters.

With the V-Max architecture, all of a sudden the opportunities open up.

If you’re going, feel free to drop me a [...] ]]> Yes folks, if you’re an EMC customer and unless you’ve been living under a rock for the last few months, you’ll know that EMC World starts next week.  I’ll be attending for the first time (under the guise of amateur blogger).  

If you’re going, feel free to drop me a mail/voicemail/Twitter DM if you want to chat.  I’d be very interested to talk to anyone (especially customers) with views on where EMC is headed with their major platforms, including V-Max and Atmos.

Naturally, the EMC PR machine is in full flow; blog posts are already up from the usual suspects:

]]> So, the announcements have started; EMC have unveiled their next-generation version of the Symmetrix high-end storage array family and it is called the V-Max.  So I guess previous guesses about DMX-5 or DMX-V weren’t far off!

http://thestorageanarchist.typepad.com/weblog/2009/04/1054-overtake-the-future-with-emc-symmetrix-v-max.html

http://storagezilla.typepad.com/storagezilla/2009/04/countdown-to-overtake-the-future.html

http://chucksblog.emc.com/chucks_blog/2009/04/symmetrix-vmax-a-new-paradigm-for-storage-virtualization.html

I picked up the first comments on ZDNet about 6am UK time this morning.  From the brief marketing blurb I’ve read, the new technology will scale better (more connectivity, more drives, more throughput and a bigger range of devices) and be more tuned to virtual infrastructures.  It does however, still rely on the existing Symmetrix technologies such as the Enginuity operating system.

Have a look at the following graphic I borrowed from the ZDnet post.  It describes a new technology called FAST (Fully Automated Storage Tiering).  The implication is that the technology enables the automated tiering of data across all levels of technology within the array.  *IF* this is as good as it sounds, then this will be a killer feature of the new technology.  As usual, the devil is in the detail; I’d hope FAST offers:

• High granularity of data chunks (e.g. 1GB chunks or less).
• High granularity of sampling period (e.g. data migration in minutes and seconds not days)
• Un-interrupted data movement.
• Policy-based migration (e.g. not technology based but a service level the customer can subscribe t0).

The other concern I have is how much legacy architecture V-Max will retain.  Symmetrix and DMX LUN changes are inflexible and require binfile or symconfigure commands to create and destroy LUNs.  Data is not fully dynamic across an entire array, hence the need for Symmetrix Optimiser.  I’d like to understand if V-Max still retains the legacy configuration constraints of the older products or whether EMC have moved to reduce these dependencies.

As usual, EMC continue to push the boundaries.  It will be interesting to see how the competition responds, in particular, those vendors still cranking out their legacy products, which as time goes on, look more and more antiquated.

More news as I discover it.