Software-defined storage (SDS) is set to revolutionize the storage industry over the coming years.
But this shouldn't come as a surprise: after all, software-defined computing—in the form of server virtualization—has radically altered the server landscape, and software-defined networking is already beginning to change the way virtual machines are linked together.
Storage is just the final part of the puzzle to get the "software-defined" treatment. "One of the advantages of virtualization is that it enables you to mix and match resources as required. Software-defined storage is the logical extension of this and thus inevitable," believes Mark Peters, a senior analyst at Enterprise Strategy Group.
What Is SDS?
What exactly is software defined storage?
Right now there's no standard definition, but it involves separating storage features from the storage hardware itself. IDC defines software-based storage as "any storage software stack that can be installed on any commodity resources (x86 hardware, hypervisors, or cloud) and/or off-the-shelf computing hardware, and used to offer a full suite of storage services and federation between the underlying persistent data placement resources to enable data mobility of its tenants between these resources."
So SDS enables companies to buy heterogeneous storage hardware—choosing whatever is best value (in terms of price, reliability or any other criterion) at any given time—and then buy and use the storage software that provides the features they need. "SDS means separating the hardware buying decision from the software buying decision," Peters explains.
Likely SDS Vendors
There is no shortage of hardware vendors, but the obvious question is where will the storage software come from? Laura DuBois, a storage expert at IDC, predicts it will come from three key camps:
- Open source development—this includes Hadoop with HDFS, OpenZFS, Openstack Swift and storage-specific solutions like Ceph.
- Storage ISVs - Companies like Inktank, Nexenta, Red Hat or Symantec
- Existing storage vendors that have traditionally delivered storage systems and appliances. "Basically, any storage software stack that could run as independent software on industry standard hardware," says DuBois.
If you look at those three camps, you'll see that they are very similar to the groups that have appeared to provide software-defined networking solutions. There are open source projects like Nox and Floodlight that have produced software-defined networking controllers, and there are commercial vendors like Big Switch Networks and Nicira (now part of VMware.) But perhaps most significantly, the big networking hardware vendors like Cisco and Juniper are all getting involved in the software-defined networking space as well. They have to—if they don't, they may become irrelevant.
What's interesting about the hardware vendors like Cisco and Juniper is that although they are embracing OpenFlow, a software defined networking standard, they are also "propriatizing" their offerings so that their software actually works better if it happens to be used with their own networking hardware.
Something similar is likely to happen in the software-defined storage space, Peters believes. "Hardware vendors will inevitably try and propriatize the technology," he says. "You will still get the 'better together' argument: 'we offer SDS, but integrated together with a system.'"
You can't really blame these storage companies for attempting to preserve their markets, but it's not clear that that route is the one that leads to the biggest benefits to storage purchasers. It's more likely that open source projects or storage ISVs will provide these, says Ashish Nadkarni, a research director in IDC's Storage Systems research practice.
"If you are competing purely on the basis of software, and all the players have access to the same hardware, then you are forced to really innovate with what you can deliver in software. The X86 revolution has been a beautiful thing for innovation because vendors can no longer hide behind proprietary hardware. Innovation has to be done in software," explains Nadkarni.
So what kind of innovations can we expect? There's always the prospect of a new killer storage feature that no one has thought of before—but by definition it's not possible to give an example of what that could be.
More likely will be a push towards efficiency, as software vendors don't have a commercial interest in selling as much physical storage capacity as possible. "I think there will be a lot of focus on reducing the storage capacity we need," says ESG's Mark Peters. "Inline dedupe, compression, and other features that focus on better utilization of existing capacity. Software vendors will be quite happy to sell software that makes storage get used more efficiently."
Of course, companies won't be obliged to chooses a single storage software vendor for all their software needs—it should be possible to choose different software for different needs and apply it to different heterogeneous storage hardware as required.
This may sound like storage paradise but there are a few caveats that need to be considered. For example, do companies really want to buy storage hardware and then choose storage software separately rather than buy something integrated, and thus simpler?
IDC's Laura Dubois has her doubts. "If (companies) go the commercial or open source software route, they need to troubleshoot issues between the software stack and the hardware. The question becomes does the customer have the skill, and inclination, to perform this integration? For the SMB the answer is probably 'no' in the short run. However, for sophisticated enterprise accounts or at scale cloud providers the answer is likely to be different."
Just like software-defined networking, software-defined storage is already happening in a small way, through OpenStack, HP StoreVirtual, Nexenta, Symantec CFS and others. But it's likely that it will be several years yet before it hits the mainstream and existing storage hardware vendors have to really start to worry. That's because storage buyers are understandably conservative when it comes to new technologies and standards are yet to emerge.
There will also need to be a push to ensure interoperability, and software companies will have to figure out how to provide adequate customer service and support and customer service before businesses will commit their data to SDS products.
The big storage hardware vendors have been around for a long time and know a thing or two in this regard, so it's likely that they'll adapt rather than die. But whatever happens to them, SDS is here to stay, and it's going to have a material impact on the industry over time.
The good news is that it's storage users who will be the ones to see the business benefits.