StorPool And The Death of Hardware-Defined Storage

Disclaimer: I recently attended Storage Field Day 18.  My flights, accommodation and other expenses were paid for by Tech Field Day. There is no requirement for me to blog about any of the content presented and I am not compensated in any way for my time at the event.  Some materials presented were discussed under NDA and don’t form part of my blog posts, but could influence future discussions.

StorPool recently presented at Storage Field Day 18. You can see their videos from Storage Field Day 18 here, and download a PDF copy of my rough notes from here.

 

StorPool?

StorPool delivers block storage software. Fundamentally, it “pools the attached storage (hard disks or SSDs) of standard servers to create a single pool of shared block storage. The StorPool software is installed on each server in the cluster and combines the performance and capacity of all drives attached to the servers into one global namespace”. There’s a useful technical overview that you can read here.

[image courtesy of StorPool]

StorPool position themselves as a software company delivering scale-out, block storage software. They say they’ve been doing this before SDS / SDN / SDDC & “marketing-defined storage” were popular terms. The idea is that it is always delivered as a working storage solution on customer’s hardware. There are a few ways that the solution can be used, including:

  1. Fully-Managed software + 24/7/365 support, SLAs, etc
  2. On HCL-compatible hardware; or
  3. As a pre-integrated solution.

Data Integrity

The kind of data management features you’d expect from modern storage systems are present here as well, including:

  • Thin provisioning / reclaim;
  • Copy on Write snapshots, clones; and
  • Changed block tracking, incremental recovery, and transfer.

There’s also support for multi-site deployments:

  • Connect 2 or more StorPool clusters over public Internet; and
  • Send snapshots between clusters for backup and DR.

Developed from Scratch

One of the cool things about StorPool is that whole thing has been developed from scratch. They use their own on-disk format, protocol, quorum, client, etc. They’ve had systems running in production for 6+ years, as well as:

  • Numerous 1PB+ flash systems;
  • 17 major releases; and
  • Global customers.

Who Uses It?

So who uses StorPool? Their target customers are companies building private and public clouds, including:

  • Service Providers and folk operating public clouds; and
  • Enterprises and various private cloud implementations.

That’s obviously a fairly broad spectrum of potential customers, but I think that speaks somewhat to the potential versatility of software-defined solutions.

 

Thoughts and Further Reading

“Software-defined” storage solutions have become more and more popular in the last few years. Customers seem to be getting more comfortable with using and supporting their own hardware (up to a point), and vendors seem to be more willing to position these kinds of solutions as viable, production-ready platforms. It helps tremendously, in my opinion, that a lot of the heavy lifting previously done with dedicated silicon on traditional storage systems can now be done by a core on an x86 or ARM-based CPU. And there seem to be a lot more cores going around, giving vendors the option to do a lot more with these software-defined systems too.

There are a number of benefits to adopting software-defined solutions, including the ability to move from one hardware supplier to another without the need to dramatically change the operation environment. There’s a good story to be had in terms of updates too, and it’s no secret that people like that they aren’t tied to the vendor’s professional services arm to get installations done in quite the same way they perhaps were with dedicated storage arrays. It’s important to remember, though, that software isn’t magic. If you throw cruddy hardware at a solution like StorPool, it’s not going to somehow exceed the limitations of that hardware. You still need to give it some grunt to get some good performance in return. That said, there are plenty of examples where software-defined solutions can be improved dramatically through code optimisations, without changing hardware at all.

The point of all this is that, whilst I don’t really think hardware-defined storage solutions are going anywhere for the moment, companies like StorPool are certainly delivering compelling solutions in code that mean you don’t need to be constrained by what the big box storage vendors are selling you. StorPool have put some careful consideration into the features they offer with their platform, and have also focused heavily on the possible performance that could be achieved with the solution. There’s a good resilience story there, and it seems to be very service provider-friendly. Of course, everyone’s situation is different, and not everyone will get what they need from something like StorPool. But if you’re in the market for a distributed block storage system, and have a particular hankering to run it on your own, preferred, flavour of hardware, something like StorPool is certainly worthy of further investigation. If you want to dig in a little more, I recommend checking out the resources section on the StorPool website – it’s packed with useful information. And have a look at Ray’s article as well.

One Comment

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.