Yesterday HDS announced (among other products) a new HUS-VM 100% flash. This is a only “marketing configuration” because you can also buy the HUS-VM with mixed HDDs/Flash configurations but there is something more.
In fact, that’s not an ordinary array filled up with disks and then sold as 100% flash. It has a flash-optimized software and the same (very well engineered) hardware MLC modules that are available for the VSP.
The most important thing to me isn’t the 1 Million IOPS that you can theoretically get from it but the TCO of this solution. In fact:
- it is an upgrade to an already available solution,
- it allows you to use the same management platform,
- it’s hybrid and without constraints, because you can buy Flash and use it with all the available features (like dynamic tiering for example),
- you can use it to virtualize other storage (and perhaps add some more performance to it).
In practice, if you are a HDS customer, it’s much easier to add some (optimized) Flash to the array already in place instead of buying and migrating stuff, isn’t it?
Some flash storage startups can probably do better than the HDS HUS-VM in terms of efficiency and rough performance but then what is the cost of the migration from your “old” enterprise array?
I cite myself from a recent blog: “There are a few primary vendors that are looking to SSD in the right way and HDS is one of them: No platforms proliferation, same user experience, seamless migrations, that’s the way to go if you need to preserve your investments.”
Disclaimer: HDS Italy is a Juku consulting srl client but I am not obliged to blog. Furthermore, the content is not reviewed, approved or published by any other person than the Juku team.