Violin Memory Blog

Hear what the experts at Violin Memory have to say about a variety of topics on all things Flash.

SQL Server and the WFA: Part 3 – Reducing CAPEX and OPEX through Simplicity

by on October 21, 2014


We have previously discussed the Windows Flash Array’s (WFA) performance and the importance of latency, and in this blog, we’ll focus on how the WFA can deliver a simpler solution that helps transform the economics of your data center.

Having high throughput and the low latency are imperative, but they are only part of what’s required to make an enterprise-class solution. Transforming the efficiency and economics of the data center, which ultimately yields reduced OPEX and CAPEX, is just as essential for overall corporate success. One way to improve efficiency, and thus reduce expense, is through elegant simplicity of design. In the ideal world, you want to lower costs for your company, improved SQL application response for users, and make your life easier. The WFA achieves this in a variety of ways.


Application performance is a tangible measure of efficiency. One way to improve performance is to get data into server RAM faster so that it can spend more time being worked over by the application as opposed to being stuck in the seemingly interminable I/O wait purgatory. Our Flash Fabric Architecture™ (FFA) avoids the performance bottlenecks common in any disk drive to reduce latency, which in turn means you can support massive concurrency of users at an unprecedented scale. Higher utilization → higher efficiency → reduced CAPEX.

Next, WFA uses SMB Direct, which dramatically increases throughput and thus decreases the time to load data into RAM by shifting much of the I/O processing away from the application servers’ CPUs to the network interface and the storage solution. With SMB Direct, you can reduce application servers’ CPU overhead by up to 30%. In other words, you now have 30% more processing capacity for your SQL Server workloads, with your existing servers. The combination of our FFA, SMB Direct, and the unique kernel-level optimizations of Windows Storage Server 2012 R2 tuned for the WFA hardware delivers performance that is not available on any other vendor’s all-flash SMB Direct solution. Again, higher utilization → reduced CAPEX.


Given the historic limitations of storage, any serious database deployment was based upon direct attached storage (DAS) or block-based storage area networks (SAN) solutions. The low overhead of block-based storage was able to deliver the performance, at least initially, so best practices dictated the use of DAS or SAN for database implementations. The tradeoff, however, was in the flexibility, simplicity, and ease of storage management. As a result, each application directly or indirectly had to deal with issues of expanding and contracting capacity as needed and a host of other cumbersome storage management tasks.

With the WFA and its support for SMB Direct, you can have simplicity of a file-based environment but without sacrificing the performance to which you are accustomed with block-based solutions. Rather than directly mapping to fixed volumes, you can instead map to shares, whose underlying storage can be easily moved around by admins without changing share names or impacting applications’ or users’ references to the data. As a result, storage moves up into the Windows world, natively accessible through simple and flexible share concepts, and easily managed within Windows Clusters. You can easily scale your storage while maintaining consistent performance to accommodate SQL Server growth, all within a simpler, easier, (and dare we say) user-friendlier environment. Simplified management → less effort → reduced OPEX.

OK, that all sounds fine, but what about data locality, storage performance tuning, managing hot spots, and all of the other issues that keep DBAs busy at work and sleepless at night? With Violin’s FFA, these are quaint vestiges of the past as the architecture renders them irrelevant. Since Violin All Flash Arrays are not based upon disk drives, they are not beholden to the architectural limitations of the past, which makes storage simpler and less risky to setup and manage. There are no disk groupings, data locality issues, performance mapping or tuning required. You can enjoy the simplicity and immediacy of a zero tuning experience. That’s right. All of your workloads will perform at the maximum speed of the array, every time, with no storage tuning or up front architecture planning. Your DBAs can cross at least one item off their daily worry list, and you no longer need to renew that expensive data locality software license. A simpler architecture → less effort → reduced CAPEX and OPEX.

Oh, that FFA also means there is ample performance so that you can undertake routine maintenance such as backup, index maintenance, etc. during production hours without negatively impacting primary operations. Moreover, when your maintenance needs include updates to the WFA operating system, Cluster Aware Updating enables you to patch one node at a time so your databases and related applications remain online throughout the process. No downtime → increased ROI.

The last measure of efficiency we’re going to discuss is integration and manageability. With management based on the Microsoft toolkit, existing Windows admin staff can provision storage resources. You can rapidly deploy new development, test, and Q/A scenarios with the knowledge that roll out and roll up will be quick and simple, and the test beds will match the speed and architecture of your production environment. You can reduce the number of tools and skill sets needed to maintain your SQL Server environment by using the native tools, i.e., System Center, PowerShell, Active Directory, etc. that you have already deployed in your Microsoft environment. In addition, you will be squarely on Microsoft’s technology roadmap for not only your servers and applications, but also your storage and its management. Fewer tools and skillsets → reduced CAPEX and OPEX.

As you can see from this and the previous blogs, we can do a lot in 3U of rackspace to not only boost your SQL Server performance, but transform the economics as well. The combination of a simpler architecture, blazing performance enhanced by SMB Direct, file-based access, Microsoft cluster integration, and administration with the Microsoft toolkit yields a fundamentally different and simpler SQL Server storage solution (pardon the alliteration) that is a true enterprise-class solution. Finally, you can have storage that is so fast that it doesn’t require you to change your behavior; you can run tasks during the day while you’re at work, so why not invest in the storage solution that allows you to do so?

In the quest for maximum SQL Server performance, you have two paths from which to choose:

  1. The path on which you arrived at your present environment, or
  2. A new approach that transforms not only your SQL Server performance, but your data center economics as well

You already know the results of path 1; simply repeating the same choices will not yield a different result. With path 2, you might be pleasantly surprised by how the WFA could not only increase your SQL Server performance with greater flexibility on a simpler architecture, but also transform your data center economics by reducing CAPEX and OPEX through greater efficiency and utilization.


For an in-depth discussion and more details on how all-flash storage can transform your SQL Server environment check out this webinar. It’s long, but you can watch it in slices as time permits.

Learn how Violin and Microsoft collaboratively optimized this solution to leverage WFA’s unique performance profile so you can run your SQL Server environment in a Flash.

For more information on the WFA and SQL Server, go to

Where does Firmware come from?

by on October 17, 2014


What is Firmware?  Think of firmware as software for hardware.  Good firmware allows the full expression of the underlying hardware’s capabilities. Good firmware allows for optimization.  In the case of an all-flash array, good firmware handles low-level data movement, RAID, Garbage Collection, data placement, data recovery, and data integrity.

To dig a little deeper, let’s start with Violin’s hardware which is defined by our Flash Fabric Architecture (FFA).  Because our FFA is vertically integrated and developed 100% in-house, our firmware had to be designed by us to support our architecture.  There is no off-the-shelf way to do firmware for a custom hardware design. SSD-based arrays have their own challenges, because the SSD vendor provides the controller functions in firmware to manage their SSD. Violin wanted more.  We felt the benefits of a custom hardware/firmware design warranted the resources.  We are able to design for optimum performance, resilience, and manageability through our entire hardware, firmware and software stack.  We shipped our first array in 2007, and have been steadily refining the architecture for 7 years.

Violin software stack

The layer above firmware is data services.  At Violin, our Concerto Data Services layer includes synchronous (with zero RPO and RTO) and asynchronous replication, mirroring, continuous data protection, thin provisioning, application consistent snapshots, thin clones, consistency groups, automated DR recovery management, WAN optimized replication, scaling up to 280TB in a single name space, LUNs that span shelves (with LUNs that can expand online), deduplication, compression and backup application integration.

Flash Fabric Architecture

Violin has used some third-party software to arrive at our current capabilities.  For instance, our Violin Memory Operating System 6 (vMOS) includes some data services from Symantec, such as thin provisioning, clones and snapshots.  It was an excellent interim step because it provided functions that customers wanted on our high-performing arrays. But again, we wanted more.  We’ve announced and shipped Concerto data services that are tightly integrated with our FFA to optimize the performance, resilience and manageability of the array.  To provide capabilities that allow us to get a fast start we purchased (not licensed) source code from a data services software company.  We chose a software base that is mature and well deployed in large accounts, then we optimized it for our FFA.  We’ve been able to use certain components such as agent software for application consistent snapshots and backups while developing capabilities that weren’t available such as deduplication for granular inline data reduction.  We’ve invested the last two years integrating and developing the elements where needed to optimize for performance, resilience and manageability on our specific hardware/firmware. Concerto Data Services is Violin code optimized to bring out the most from our Flash Fabric Architecture and deliver the highest value to our customers.  Always-on deduplication may benefit the storage vendor, but granular deduplication benefits the customer.

On top of Concerto data services, we developed Symphony management software. This management layer was developed at Violin and again is closely designed to bring out the best in our FFA.  Our customers wanted flexibility and the ability to manage all their Violin arrays from a single pane of glass, and specify their own dashboards, and set their own alert levels, and have an easy-to-use GUI.

Where does firmware come from in other storage companies?

Common practice in the storage industry:

  • Buy a whole array and brand it yours. (From Engenio/LSI to HP, HDS, IBM, et al.)
  • Buy an array company and brand it yours. (3PAR-HP, TMS-IBM, Sun-Oracle, Data Domain-EMC, Isilon-EMC, et al.)
  • License/Buy software and put it in your array. (ZFS at a bunch of companies), Sepaton, ScaleIO, StoredIQ, et al.)

At Violin we believe that real differentiation has to come from the hardware foundation through the management layer.  If you optimize the layers above the hardware you’ll be able to expose all the capabilities of that architecture for your customer.  If you start on a commodity SSD-based foundation with someone else’s firmware/hardware your results will vary.

It took us longer to start with the basic firmware/hardware foundation and build optimized software and management layers on top.  It is a harder path, with a longer time to market.  We feel the results are well worth the effort.  Our customers agree.

To get more information on our Flash Fabric Architecture go here:

To get more information on Symphony management go here:

To get more information on Concerto data services go here:

Postcard from Oracle OpenWorld 2014: The Oracle FS1 Flash Array

by on October 13, 2014


A couple of weeks ago, along with thousands of other people, I attended Oracle OpenWorld 2014 in San Francisco. There were lots of announcements and lots of opportunities to learn (especially at the excellent OakTable World conference-within-a-conference). My personal favourite session was Jeremiah Wilton’s talk on running Oracle on Amazon Cloud Services – I think a whole essay could be written on Oracle’s Cloud Licensing Policy. And as Steve Karam has already pointed out, the overwhelming message of OOW14 was cloud, cloud cloud. It seems that Larry no longer likes to talk about on-premise.

But I don’t want to talk about cloud. My perspective of OOW comes from that of a storage vendor – and for us vendors there was an interesting announcement tucked away beneath all the cloud hyperbole.

The Oracle FS1 Storage Array

Just to be clear, I’m not here to deliver a technical analysis of the FS1. As a database guy I have many colleagues and contacts in the storage industry who are much better qualified to discuss this product (especially those who are ex-Pillar Data Systems, because the FS1 is after all simply the next-generation Pillar Axiom with SSDs).

But as with my tracking of the History of Exadata, I like to watch Oracle’s marketing strategy around its products – I often find you can read more between the lines than you can get simply from buying into the marketing hype. (And let’s face it, Oracle does like a bit of marketing hype.)

Surprise Announcements

The release of the FS1 caught most people by surprise as it was not advertised prior to OpenWorld commencing. After Larry Ellison mentioned it during his keynote, a new session was announced with the catchy name “Introducing the Oracle FS1 Series: Taking Flash Storage into the Mainstream” delivered in almost evangelical style by none other than Mike Workman (previously the CEO of Pillar and now SVP of Oracle Flash Storage Systems). And I was in the room, eagerly awaiting the news.

Now based on my experience of working for vendors (including Oracle) the first thing I think when I hear of surprise announcements is that they are rushing something forward for the purposes of marketing noise – something that perhaps isn’t quite ready. Could that be the case here?

In my opinion and based on this session, emphatically yes. The session introducing the FS1 was incredibly light on details, but – adopting an age-old Oracle tactic – packed full of attacks on competitors. And nobody got attacked more than EMC’s XtremIO all flash array. Here’s one sample slide:

Can you see the small print at the bottom of this slide? I couldn't - and I was sitting four rows from the front.

Can you see the small print at the bottom of this slide? I couldn’t – and I was sitting four rows from the front.

Ironically, this was the first year I can remember where EMC didn’t have a stand in the exhibition hall (in 2013 their stand was one of the biggest at the show). I noticed that the guy sat next to me was an EMC employee so after the session ended I asked him what he thought. “Thanks Oracle for all the free marketing!”, was the reply.

Only a few high-level details came out of the session. For example, we learnt that the FS1 took three years to develop and can have up to four tiers of storage:

  • Performance Flash (actually 400GB SSDs)
  • Capacity Flash (again via 1.6TB SSDs)
  • Performance HDD (300GB or 900GB disk drives)
  • Capacity Disk (4TB disk drives)

That’s a lot of disk. Keep that in mind for later.

Marketing Claims

I quite enjoyed the FS1 introduction session, although I suspect not necessarily in the way I was supposed to. It certainly made me smile when Mr Workman made this statement:

“The Oracle FS1 is the first mainstream, general purpose flash array”

Mainstream? General purpose? Here at Violin Memory we have numerous customers running multiple, mixed workloads on our award-winning 6000 series all flash arrays:

And so on… I even know of a customer who uses a Violin array as a file server! Sounds pretty general purpose to me. And to be fair, I’d be surprised if some of the other all flash array vendors weren’t puzzled by Oracle’s claim too.

But a more confusing comment from Mr Workman was this:

“It’s NOT a hybrid array”

Remember that bit about four tiers of storage, two SSD and two HDD? In what way is that not a hybrid array? Does Oracle consider the phrase “hybrid array” beneath it? I notice that Oracle’s FS1 home page and the associated press release both steer clear of using the H-word. Sadly the media hasn’t received that memo, so the headlines still call it a hybrid - as will the rest of us, I’m sure.


As the FS1 product nears the point where it’s ready for launch (rather than pre-launch) I’m sure we’ll find out more about it. Maybe some of the storage players will comment – although so far all I’ve seen is varying degrees of apathy. Who knows, maybe it will revolutionise the world of storage. But until then – and while all we have is “9x faster than Y” claims – it feels like another triumph of hype over substance.

No offence Oracle, but until you come up with something more concrete I’m just going to think of it at the BS1 Flash Storage Array…

WFA: High Performance Storage for Hyper-V Clusters on Scale-Out File Servers (SOFS)

by on October 8, 2014


High-performance storage is a prerequisite for any enterprise-class virtualization initiative. After all, consolidating workloads onto fast servers and then slowing them down with spinning rust storage is a pointless, not to mention expensive, endeavor. Given the importance that virtualization plays in the modern data center, it follows that storage not only needs to be high performance, but also easy to manage and scale. Recently, Microsoft undertook an experiment to demonstrate exactly this. Deploying a SOFS across two Violin Windows Flash Array-64s, Microsoft illustrated the simplicity of deploying scalable high-performance storage that delivers remarkable IOPS performance, bandwidth, and extremely-low latency.

Summary of Experimental Performance Results

But don’t take my word for it; read what Microsoft has to say. If you’d like to learn a bit more, I invite you to download this white paper and reference architecture:


This white paper, Building High Performance Storage for Hyper-V Cluster on Scale-Out File Servers using Violin Windows Flash Arrays, demonstrates the capabilities and performance for the Violin Windows Flash Array, a next generation All Flash Array storage platform. With the joint efforts of Microsoft and Violin Memory, the WFA provides built-in high performance, availability and scalability through tight integration of Violin’s All Flash Array and Microsoft Windows Server 2012 R2 Scale-Out File Server Cluster.

The results presented in this white paper show the high throughput and low latency that can be achieved using Microsoft technologies bundled with Violin hardware. With two Violin WFA-64 arrays, the workloads running in Hyper-V VMs can linearly scale to over two million or 1.6 million IOPS for random reads or writes, 8.6 GB/s or 6.2GB/s bandwidth for sequential reads or writes. Even at the maximum throughput of 2 million IOPS, the 99th percentile latency can still be capped at 4.5ms and the latency of simulated OLTP IO traffic at a load of 1.15 million IOPS is capped at 3.7-4ms as well.

Learn how Violin and Microsoft collaboratively optimized this solution to leverage WFA’s unique performance profile so you can run your Hyper-V workloads in a Flash.

For more information on the WFA and Hyper-V, go to

Vote for Us! Violin Memory Selected as Finalist for Two SVC Awards

by on October 6, 2014

2014 SVC Awards Finalist logo

Violin is nominated for two awards: SSD/Flash Storage Product of the Year and Storage Company of the Year.

The Storage, Virtualization, Cloud (SVC) Awards reward the products, projects and services, as well as honor companies and teams operating in the cloud, virtualization and storage sectors. The awards are jointly sponsored by DataCentre Solutions, Virtualization World, and Storage Networking Solutions.

Vote for Violin Memory!

More Posts ...

Featured Posts