I’m headed to Storage Field Day 11!

Storage Field DayWe’re just 1 week away from Storage Field Day 11 and I’m proud to say I’ll be there as a delegate!  For those of you who don’t know, the Tech Field Day series (a GestaltIT production) is a chance for vendors and members of the tech community to come together and discus their latest product innovations.  These sessions are broadcast live and are joined by the greater community on twitter.  Now for those of you familiar with the process, you might be saying “Sean, that was an over simplified explanation” and you’re right, it was.  Delegates are highly technical and won’t pull any punches when asking questions, so presenters need to be on top of their game and knowledgeable about all aspects of the products.  Nothing is really off limits, the only rule is no throwing things.

 

What companies will be presenting?

Traditionally with most Field Day events, 8 companies will present to the delegates.  They range from large established companies down to those coming out of stealth (this is a great type of event for coming out of stealth btw).  So lets look at the list of presenters:

Storage Field Day 11 Companies

As you can see, we have some well established vendors, some new ones, and 2 blank spaces (those would be the stealth companies).  I expect we’ll see some updates on storage mediums (Both spinning disk and Flash) as well as storage systems (Both Hardware and Software).

So what’s next?

I’m not really sure what is next.  While storage field day is not new to me (You’ll see me in the background of the EMC presentation at SFD5), I’ve never been a delegate before.  I’m looking forward to being on the other side of this and learning a lot.  So be sure to tune in next week and join in the conversation on twitter using the #SFD11 hashtag!

Peeling back the layers of XtremIO: What is an X-Brick?

XtremIO_iconMany moons ago, on a stage not too far from where I work, EMC announced the future of flash and the creation of the Xtrem brand / business unit.  Today, EMC announces the latest product in the brand: XtremIO.  This all flash storage monster changes the way we think about storage and for the better.  Gone is the need for tiering and different types of RAID configurations. Rebuilds are measured in minutes, not hours. I present to you, the X-Brick!

 

What’s in the X-Brick?

imageSo the picture above shows the major breakdown of an X-Brick.  Behind the covers you have 2 controllers, 2 battery backup units, and a 25 drive DAE that accepts 2.5” drives (does that look familiar?).

 

image

In  the back you can see there is 2 of everything.  There are 2 power supplies, 2 SAS controllers, 2 iSCSI and Fiber Channel ports, and 2 InfiniBand ports for clustering.  Just like with all other EMC products, there is no single point of failure in this design (and I do like how everything gets a UPS instead of just the DAE).

 

image

 

Inside the hardware of each X-Brick are dual SPs (these are external 1U blades, unlike what you see in a VNX SP), each with dual 8 core CPUs and 256GB of RAM.  They each have a SAS 2.0 connection directly to 25 eMLC SSD drives as well as InfiniBand connectivity to other nodes in the cluster (more on this soon).  On the front end, you have 10gig iSCSI as well as 8gig FiberChannel.   This impressive platform sets the stage for even more impressive software.

 

Lets talk about clusters

At launch, the XtremIO platform can support up to 4 X-Bricks (in theory, I don’t see why more can’t be added, and maybe they will be in the future).  Each X-Brick is of a fixed size of around 10TB of storage with around 7.5TB of useable space (though I expect that total size will be increased in the near future).  In a 50/50 read/write performance test, each X-Brick topped out at about 150,000 IOPS (that number increased to around 250,000 if you are doing 100% reads).  And when you max out your cluster with 4 X-Bricks, both your storage and IOPS scale out giving you 40TB of capacity and around 600,000 real world IOPS (topping out at around 1,000,000 if your doing just reads!!!!!!).

 

image

The key to achieving all of this is in the software layer.  When data comes in, it is broken down in to 4K chunks.  Each chunk is then hashed using an SHA-1 algorithm and assigned a unique metadata fingerprint.  The chunks are then spread out across all the storage processors in the cluster to distribute the data around for faster throughput and the logical block address, fingerprint, and SSD offset are recorded in the metadata.  When new data comes in, the fingerprints are checked against the existing database to see if there is a match.  If there is, the metadata is recorded, but the write is not necessary, thus extending the life of the SSDs as well as performing an inline deduplication.  Now 256GB is not a lot of RAM to store metadata, and when full it will destage this to the SSDs.  This is where the cluster really starts to shine.

image

By utilizing the RDMA fabric between the X-Bricks.  The metadata calculation can be distributed across the entire cluster for an even load balancing.  This allows the decoupling of the user data and the meta data so that they don’t have to be on the same X-Brick and also allows you to recall any of the data in a similar fashion.  The in memory metadata of a controller is also mirrored to another controller in the cluster just in case there is a controller failure.  By being able to utilize multiple X-Bricks at the same time, you can scale out all the processing in an active/active environment and increase the total throughput of the cluster as a whole.

 

So what does it look like?

Well first off, it’s not Unisphere, but it’s own interface (the XMS management system) that is launched from the web server running on a controller as well as a robust CLI.  This video demonstration gives you a great overview.

XtremIO v2.2 GUI Demonstration

Final Thoughts

All in all, for a first round product, I think this is a great offering.  I’d like to see it scaled up higher with more storage and more X-Bricks in a cluster as I don’t think they have hit the limits of the architecture.  Be sure to watch the Launch event.  Here is a sneak peek at the cool X-Brick Coffee table (which will one day end up in my living room if I can help it)!

EMC XtremIO Launch 173

Even MORE goodies coming to VNX

So hopefully most of you read my earlier post about new features coming to VNX.  Well I wanted to write some more about new things coming to VNX.

Flash First!

You may have been reading else where about a change coming to tiering on the the VNX, and I’m here to confirm this rumor.  EMC VNX engineers have reversed the way we do tiering on the VNX.

image

With traditional storage pool with FAST enabled, data would be loaded in and then promoted to the flash storage when it was deemed hot.  Now we are completely reversing that policy.  Since most of your data is only read within the first few days, all new data coming into the VNX will be considered hot.  After a few days of little to no access, the data is demoted down to cheaper & more abundant storage.  This change means that you no longer have to wait to see advantages of FAST as everything will be on your fastest storage right away.  Combining this with the new changes to pools that I talked about before, and you’ve got a 2 pronged approach to getting your data the fastest without breaking the bank.

 

A new approach to Data Protection

This next goodie isn’t as much a direct enhancement to the VNX as it is an overall solution.  EMC is introducing a new solution called AppSync.  AppSync offers a 1 click protection package for certain virtualized applications you already have stored on the VNX.

image

What you have here is the ability to sync with VMware, Microsoft SQL Server, and Microsoft Exchange with SLA driven protection.image

As you can see from the graphic above, you can have 3 protection packages:

  • GOLD: You get synchronous replication with no data loss
  • SILVER: You get asynchronous replication with minimal data loss.  You may only lose the last few minutes
  • BRONZE: Hourly Snapshots.  You may loose up to an hour of data

image

The 2nd half of this application is the ability to share this out to other admins in your infrastructure.  Currently, if you want to restore something, you need to talk to the storage admin to tell them to roll back the lun.  With AppSync, you can give access to the to the application admins and let them handle the restore.  An exchange admin can now go in and restore a single mailbox without effecting the other users or bothering the storage admin.

 

This is just Win-Win in my book and I can’t wait to see this in action.  My sources tell me that this will be available as a separate package in the 2nd half of 2012, but that is still subject to change and you should talk to your EMC Sales rep to get a final date of availability.