Nirvanix had some pretty impressive wins in 2011, and has done a good job getting its customers to go public.  It has been roughly a year since the new management took over, and their diversification strategy seems to be working.  Nirvanix sells both software and storage services.  Notable wins in 2011 include:

• Relativity Media–next gen studio behind hits like “Immortals” and “Limitless”; will leverage NVX public cloud for content collaboration to bring movies to completion faster.
• NBC Universal is deploying 2+ Petabytes (videos, photos, movies; leveraging Nirvanix public cloud for content archival and collaboration).
• Advocate Healthcare has 500TB (healthcare content files; NVX public cloud).
• USC deployed 8.5 Petabytes (Videos, Photos; USC will also resell NVX Private Cloud as the USC Digital Repository).
• Cerner Healthcare for 2+ Petabytes (for PACs, radiology, clinical systems, patient records; Cerner will also resell NVX Private Cloud as Cerner Skybox Public Cloud).
• IBM is deploying a Multi-Petabyte Global Private Cloud; NVX is essentially building a replica of its Cloud Storage Network for IBM to sell as its own public cloud–IBM SmartCloud Enterprise.
• DRFortress is offering an onsite physical node federated with Nirvanix public cloud, providing its customers with a hybrid cloud storage deployment.

The first three are true public cloud users that are leveraging Nirvanix to accelerate business (because, as Steve D. mentioned in his blog last month, doing all the storage stuff yourself stinks, or something to that effect).  But the rest are resellers as well as users.  Now, this is a pretty impressive list – names we know and love.

I’ve actually talked to a few of the resellers and there seems to be strong momentum in the channel.  I don’t think it would be too risky to say that the strategy Nirvanix management laid out a year ago and has been executing against since is paying off for them.  Granted, Nirvanix adoption is only a microcosm in the larger cloud universe – but it is proving that the business model can work and there is money in IaaS.  Rumors of Nirvanix’s demise were swirling a mere 18 months ago, rumors which the new team seems to have silenced.

Looking forward to 2012, it would not be surprising to see Nirvanix gobbled up by a bigger player who can leverage the current cloud delivery network infrastructure, cloud software, and hybrid cloud model to offer both public and virtual private cloud services.  There are a lot of variables – a lot depends on the economy, and it is sure to be a shaky year because of the elections.  But Nirvanix is one I will be keeping an eye on.

You can read Terri’s other blog entries at IT Depends.

It is a really exciting time to be looking at this space. I am a bit embarrassed (a trend in my blogs lately) to admit that I have 5 endpoint devices that I use for assorted tasks that are work related: an android phone, an android tablet, an iPad, a laptop, and a desktop. Someday I will settle on which tablet I like better – but for now this is my reality. The ability to access the latest, consistent version of my work documents from any of these devices is invaluable for me – all of our research data points are at my fingertips wherever I am. All of my notes from all of my meetings – right there, no matter what device is in front of me. Okay – I am probably atypical, but still – how many users have a smartphone and laptop? Or a smartphone, laptop and tablet? That is much more typical – and it is driving changes in IT storage strategies.

I was initially skeptical about enterprise adoption of these solutions – the most well known are well known because of consumer use, not business use. However the “bring your own device” (BYOD) trend along with users having multiple endpoint devices is one driver for IT to look at solutions that support these devices, and of the companies we’ve spoken to that have BYOD policies, many (83% according to our research) allow employees to use their devices for both work and personal use. That explains why perhaps the bigger driver is end-user demand – an awful lot of IT’s customers are deploying these solutions without waiting for permission, and IT is being pulled into looking at and endorsing a corporate-wide solution that will provide the manageability, security, and control they need to protect corporate information assets.

I’ve spoken to a number of companies that have adopted these solutions, from web-based businesses to some well known large companies known for a conservative approach to IT, and I am no longer skeptical. They tell similar stories – the big drivers are end-user demand for these solutions, endpoint device support, unleashing the shackles of using a VPN for shared file access, collaboration, and supporting a mobile workforce. And when I ask whether they are augmenting existing storage solutions or replacing, I consistently hear that they are replacing file servers – either Windows or LINUX-based or dedicated NAS systems. Consumerization is indeed changing storage strategies within some enterprise IT shops and driving adoption of these solutions.

We will be increasing our coverage in this area in the coming year – this report is really to set the baseline for our future work. It is only available to premium subscribers – but contact us if you are not a premium subscriber and interested.

You can read Terri’s other blog entries at IT Depends.

Fast forward to 2011 and who would have guessed that companies overwhelmed by email archives and ever-growing volumes of backup data could benefit from the extreme performance and scalability that’s being used at Pixar?  Scale-out NAS challenges are much more “everyday” than “lunatic fringe,” and HP has made it easy for organizations to harness the power of IBRIX scale-out NAS.

ESG Lab recently evaluated the performance of the HP X9320, a fully integrated scale-out NAS solution that leverages the power of IBRIX technology running on industry standard servers and storage from HP.  An excellent large file throughput rate of 2,257 MB/sec  was achieved with a single HP X9320 couplet and performance scaled in a near-linear fashion as couplets were added to a single file system. Small file performance was outstanding as well – a single X9320 couplet created 5.1 million 4 KB files in an hour.   Learn more in this ESG Lab report.

Background

File data growth has outstripped e-mail- and database-driven growth for some time now.  The reasons are many: richer file formats, ubiquitous photo and video, online communities, collaboration tools, 3-D modeling, and 4-D imaging to name a few. But exotic file types are only part of the challenge.  Organizations dealing with extensive and ever-growing volumes of disk-based backup and archive data struggle with similar problems; they need to accommodate growth efficiently, manage it simply, and access it quickly.

Simultaneously, economic conditions have led businesses to emphasize first CAPEX, and now OPEX, reductions more than ever.  File growth has resulted in higher costs in terms of additional storage, complex management, and data center floor space and energy.  As a result, the ability to scale out—that is, independently scale and tune bandwidth, processing, and storage capacity on the fly while managing a single, global namespace—is extremely popular for increasing efficiency and saving money.

Adoption of scale-out NAS solutions is driven by its ability to address multiple challenges. ESG survey respondents report selecting scale-out NAS to achieve faster storage provisioning, better scalability with easier management, improved performance of both IO and throughput, and higher data availability (see Figure 1).[1]

Introducing HP Storage X9320 IBRIX Network Storage Systems Scale-Out NAS

The X9320 Network Storage Solutions are an integrated appliance series consisting of industry-standard HP servers and storage with the IBRIX Fusion segmented file system. Three models are available: one built to optimize performance or capacity, one focused on low cost and high density, and one gateway front end for use with existing SANs.  X9320 couplets can be combined into a single file system with nearly linear capacity and performance scalability.

The X9320 is designed to enable extreme scaling—up to and beyond the currently supported maximum of 16 petabytes in a single namespace. As a result, large file systems can be accessed, managed, and protected from a single interface. Unlike other clustered file system solutions, the X9320 was designed for multi-tenant environments which often have a wide variety of workloads, including response-time sensitive, small random workloads (such as general purpose file sharing) and bandwidth-intensive, large sequential workloads (such as backup to disk, archiving and big data analytics). Features include:

• Non-disruptive growth. The X9320’s modular structure accommodates multi-petabyte growth without downtime. Built-in policy management and automated file migration capabilities let IT optimize for performance, capacity, or retention.
• Non-disruptive workload re-balancing. Workloads are spread across storage resources to avoid overworking individual drives, reduce hotspots, and enhance performance.
• Online migration between storage tiers. X9320 systems help reduce costs by enabling customers to move the most active data to the highest performance drives and less active data to more cost-efficient drives.
• Automated administration. Managing a single file system with an intuitive graphical interface and rich set of command line interfaces reduces administrative cost and complexity.
• Enterprise-class software features. The X9320 supports valuable enterprise-class storage software capabilities including continuous remote replication, snapshots, and automatic online migration between storage tiers.
• Predictable performance at scale. Fully distributed metadata versus a centralized lock manager file system enables predictable, near-linear performance across the file system namespace.

ESG Lab Validation

ESG Lab evaluated the results of two sets of X9320 performance tests that were run in an HP lab in Fort Collins Colorado.  The first tested large block sequential throughput and the second tested small file  creation performance.  Both used three HP StorageWorks X9320 IBRIX Network Storage System (X9320) couplets.

Background

The file system at the heart of an X9320 series scale-out NAS solution was designed to provide near linear performance scalability for large and small files, regardless of the size of the file system.  The segmented architecture of the file system provides scalable performance for large and small file workloads.  This powerful technology was designed by IBRIX which was acquired by HP in 2009.

The IBRIX file system distributes file data and metadata over multiple servers that work together in a fault tolerant, scalable cluster. Each server in the IBRIX cluster has a map to determine which segment holds a particular file. As a result, regardless of which node accepts the data request, the server can quickly identify the location and deliver the data.  This approach minimizes performance bottlenecks as metadata and file access traffic is distributed evenly over multiple segment servers.

Test Bed

Performance testing began with three X9320 couplets as shown in Figure 3. A “couplet” is a term HP uses to describe a pre-configured, fault tolerant pair of HP servers running the IBRIX file system software attached to two pre-configured HP P2000 disk arrays.  In this example, three couplets used 288 15K RPM disk drives to present a single 120 TB file system to 16 NFS v3 clients.  The clients were attached to an Ethernet LAN using two bonded 10GigE ports. The X9320 couplet was attached to the LAN using a pair of 10 GigE bonded connections.[2]

Performance Methodology

The industry standard IOzone utility was used for the large file sequential tests and the HP SNPT performance utility was used to generate small file workloads. The SNPT utility, which stands for “simple NAS performance toolkit,” was used as an alternative to industry-standard tools including Iometer, bonnie, dd, and countless other file system performance tools. SNPT was originally developed by HP to overcome the limitations of industry-standard file system benchmarking tools. SNPT supports multiple streams running over multiple clients writing over many files with a variety of directory structures. SNPT collects fine grain performance data, down to the millisecond level for each file operation if needed. It collects performance data captured at the OS or network levels as well.

ESG Lab audited the source code of the SNPT utility and verified that it uses standard file system calls to open, write, read, and close files. Scripts used to generate SNPT calls and logs created by the SNPT utility were audited by ESG Lab. Performance data collected independently at the NFS client level to verify the authenticity of performance results reported by SNPT was also examined.

X9320 Large File Throughput Scalability

The first set of tests was designed to measure the performance of X9320 couplets for throughput-intensive write and read workloads. Sequential transfers to large files were used during this phase of testing. The aggregate throughput of the system was recorded as 16 Linux clients accessed a single file system in parallel. Tests were run on a file system deployed over one, two, and three couplets. Each of the three couplets was configured with 96 disk drives each. The results are shown in Figure 4 and Table 1.

What the Numbers Mean

• A single X9320 couplet with two industry-standard HP servers delivered 1,179 MB/sec (1.2 GB/sec) of sustained aggregate throughput for large file writes and 2,257 MB/sec (2.3 GB/sec) for large file reads.
• Based on ESG Lab’s experience testing traditional and scale-out NAS solutions, 2.3 GB/sec of aggregate throughput is an excellent result for a single file system running on a pair of industry-standard servers.
• Performance scaled in a perfect linear fashion as the solution was expanded at a single couplet granularity.  Each additional couplet increased throughput in a near linear fashion up to a peak of 3.455 GB/sec for writes and 6.712 GB/sec with three couplets.

Interpreting Large File Throughput Scalability

Content delivery is a good example of an application that benefits from a storage solution with predictably scalable large file throughput.  Content delivery is used to define a broad category of systems which deliver digital video, image, and audio files over a delivery medium such as a broadcasting network, intranet, or the Internet. The delivery of large files over a content delivery medium requires a storage solution with lots of capacity and aggregate read throughput. To put the aggregate throughput results recorded by ESG Lab into perspective, the maximum aggregate read throughput that was recorded for the three-couplet X9320 system (6.555 GB/sec) was used to calculate the number of streams that could be delivered for a number of well known content types. The results are summarized in Figure 5 and Table 2.

What the Numbers Mean

• The aggregate read throughput of the storage repository used to deliver large file digital media is one of the key factors to consider when architecting and sizing a content delivery system.
• ESG Lab used the maximum aggregate read throughput of a three-node X9320 storage system and the bit rates of well known content types to estimate the maximum number of large files that can be streamed in parallel by the three-node X9320 tested by ESG Lab.
• For example, a bit stream rate of 128 Kbps for MP3 files was used to determine that a three-couplet X9320 has the bandwidth required to support up to 429,568 song downloads running in parallel (6.555 GB/sec divided by 128 Kbps).[3]

Write Throughput for Backup to Disk, Archive, and Big Data Analytic Ingest

The extremely high and scalable throughput of the X9320 is ideally suited for bandwidth intensive applications that write a lot of large files.  Backup to disk, e-mail archiving and the data ingest portion of a big data analytic workflow are good examples.    Using backup to disk as an example, the results that are summarized in Table 4 show how the scalable performance of the X9320 can be used to protect up to 1.58 TB of data in a single 8 hour shift.

What the Numbers Mean

• A single X9320 couplet delivered an excellent sustained aggregate write throughput of 1.15 GB/sec.
• Performance scales linearly up to 3.37 GB/sec of sustained write throughput for three couplets.
• Write throughput of 3.37 GB/sec is an extremely high rate, beyond what most commercial NAS system can deliver from a single file system, yet is often required to meet the demands of backup to disk, deep archives, and big data analytic ingest services.
• Using backup to disk as an example, a sustained throughput of 3.37 GB/sec can be used to write 96.8 TB of data during an eight hour backup window.
• Using a bandwidth limited archive operation as an example, a three couplet X9320 solution with a single name space can be used to archive up to 290.4 TB of data in 24 hours.

X9320 Small File Performance Scalability

General purpose business applications that store data on shared file systems typically create and access lots of small files.  As the number of users sharing a single file system increases, small file performance needs to scale to meet the demands of the business.

Big data, high performance, and rich media applications also often require good small file performance.  Applications that store large files often create small files to keep track of metadata (data about the files).  A website that stores uploaded photos on a file share is a good example: besides the large photo files, the application often creates small thumbnail images and may also use small files to store metadata (e.g., titles, tags).

The file system at the heart of an X9320 scale-out NAS solution is designed to perform well for large and small file workloads.

The test bed used to analyze small file performance is shown in Figure 6.  A single 120 TB file system residing on three X9320 couplets with 288 15K RPM drives was tested with 16 NFS clients.

The HP SNPT performance utility and a script running on each of the 16 NFS clients was used to create as many 4 KB files as possible over the course of an hour. A master script launched synchronized copies of the script on each of the clients and waited for them to finish. The total number of files created was recorded. The results are presented in Figure 7 and Table 4.

What the Numbers Mean

• HP claims that a single NFS stream can create hundreds of files per second and multiple streams can create more than 1,000 files per second on a single X9320 couplet. In this example, multiple NFS streams running in multiple directories on a single X9320 couplet wrote 4 KB files at a sustained rate of 1,495 per second, which is more than adequate for most applications.[4]
• ESG Lab added additional couplets to show that the X9320 scale-out NAS solution meets the small file performance requirements of ANY application. The number of files written tripled, going from one couplet with 5,131,623 files written to three couplets with 15,396,504 files written.
• For applications requiring even higher levels of small file performance, IBRIX clients can be used instead of NFS clients to create more than 10,000 files per second on a single X9320 couplet.

ESG Lab Validation Highlights

• ESG Lab confirmed that the segmented IBRIX  file system running on industry-standard HP hardware performs and scales extremely well when processing large and small files.
• Large file performance scaled in a nearly perfect linear fashion as X9320 series scale-out NAS couplets were added to a single file system.
• A single X9320 couplet processing large files achieved an aggregate throughput rate of 1,179 MB/sec for writes and 2,257 MB/sec for reads.
• A three-couplet X9320 system scaled to deliver 3.374 GB/sec of write throughput and 6.555 GB/sec of read throughput.
• A single X9320 couplet accessing multiple directories with the NFS protocol wrote small 4 KB files at a sustained rate of 1,495 files per second.
• A single X9320 couplet created more than 5.1 million 4 KB files over the course of an hour.

Issues to Consider

• All tests were run using the NFS protocol.  The IBRIX native client is available for customers looking to get even better performance.
• The performance results presented in this report are based on benchmarks deployed in a controlled lab environment. Due to the many variables within each production data center, capacity planning and testing in your own environment is needed to see exactly how the X9320 series scale-out NAS will perform with your applications.

The Bigger Truth

In case you haven’t heard, the ever-expanding volume of unstructured data is expensive to store and retain and hard to manage.  While it is difficult to make this oft-repeated statement sound fresh and interesting, the simple fact is that file data growth drives continuing customer challenges and storage industry innovation. Today, all you have to say is “file growth cost and complexity” and your audience fills in the back-story automatically, conjuring images of staffing, energy, data access, retention, and protection challenges.

Many vendors, over many years, have tried to solve the problems of predictable cost effective scale-out NAS performance. A number of well-funded companies came and went without gaining any real traction and hundreds of millions of dollars have gone up in smoke.  Scaling has turned out to be a very difficult problem to solve. Most solutions work well for large or small files, but not for both—leading many companies to deploy a scale-out NAS solution alongside a commodity, entry-level NAS solution to deal with metadata. The difficulty is further demonstrated by the fact that storage industry behemoths, while making progress, have not been able to get the job done either by acquisition or internal development.

ESG has been following IBRIX for several years, since well before its acquisition by HP. We’ve written about it, spoken with customers, and performed several Lab Validations. IBRIX was born in the high-performance computing arena and early animation successes with Disney and Pixar put it on the map. To its credit, while the file system started out highly specialized, IBRIX expanded the product to benefit not just niche markets like medical imaging, scientific research, and animation, but general purpose file serving and file sharing as well. Its segmented architecture makes it work for both large files and large numbers of small files, expanding its usage and target market.

What impressed ESG Lab was not just the technology and virtually unlimited scalability, but IBRIX’s commitment to effective partnering, go-to-market, and messaging strategies. IBRIX was smart to keep a narrow focus on scale-out NAS and to concentrate on OEM solutions with Dell and HP, which led to interest from EMC and IBM. Over time, the configuration and GUI were dramatically simplified and IBRIX focused on improving serviceability, usability, and manufacturability. All of this hard work resulted in its acquisition by HP in 2009.

In this most recent Lab Validation, ESG Lab confirmed that the IBRIX segmented file system running on industry-standard servers and storage from HP delivers outstanding levels of performance and scalability for small and large files. An excellent large file throughput rate of 2.20 GB/sec can be achieved by a single HP X9320 scaling in a near-linear fashion as couplets are added to a single file system. Small file performance was outstanding as a single X9320 cluster created 5.1 million 4 KB files in an hour.

Who would have guessed that companies overwhelmed by Word and PowerPoint archives and ever-growing volumes of backup to disk data could benefit from the same solution as those burdened by 100-TB annual growth of genome sequencing data? Who knew that a NAS file system developed for high-performance computing could evolve into a graceful, cost-effective scale-out solution with predictable and near-linear performance for small and large files and everyday applications?  The challenges that scale-out NAS solves are much more “everyday” than “lunatic fringe,” and the X9320 makes it consumable by almost anyone. If you are facing file system growth and complexity challenges, you should consider the X9320.  If you’re struggling with the bandwidth intensive challenges associated with backup to disk, deep archives, and big data analytics, start with an X9320 as the foundation for your scale-out storage needs.  It’s affordable, includes commercial features like snapshots and replication, and lets NFS and CIFS work on the same file system. You can buy a scale-out architecture that will grow with you and meet the needs of your business without interruption. The IBRIX segmented file system, combined with HP’s servers and storage (not to mention HP’s buying power and supply-chain advantage), brings what started as a niche solution to the masses.

Appendix

[2] See the Appendix for more configuration details.

[3] The bit rates for each content type are listed in Table 8, which can be found in the Appendix.

[4] 5,131,623 files divided by 3,600 seconds equals 1,495 files per second.

I finally put pen to paper (showing my age – plus, somehow fingers to keyboard does not sound nearly as good) and published a market landscape report called Understanding the NAS Market.  I documented how we segment the NAS market by use cases, how it has evolved over time, what types of architectures fit which use cases, what vendors offer solutions where, and what the typical price points are for each segment.  It sounds like a mouthful because it is–at almost 20 pages, the report is on the long side but hopefully will provide some insight into why we’ve seen the rise of scale-out architectures in NAS and things users should consider when evaluating NAS systems!   At this time it is only available to subscription clients as a part of our premium service.

You can read Terri’s other blog entries at IT Depends.

Why? HDS sells HUGE stuff to HUGE shops. Some of the biggest on the planet. But they really only sell block. BlueArc, running at about $100M in revenue, sells HUGE NAS stuff to big shops who need big things–and need them fast. They are not a bulk provider any more than HDS is–if you have an app that needs outrageous (fill in the blank – performance, throughput, uptime, etc.) and it’s “at scale”–then you need one of these guys.

Thus, the marriage is logical. With HDS’ global girth, and EXISTING huge customer base, this should be a no brainer. Big block shops need file access too.

Why now? Because BlueArc (smartly, If I don’t say so myself) used the current smoking hot storage climate to file an S1 (to go public) which by default opened up the kimono–and thus the bidding. IBM could have used them, as could Dell (as could HP really), but HDS is the right suitor. Sooner or later having nothing in the file world would kill them. Plus, they have had a 5 year relationship so they know what they are getting.

Didn’t HDS effectively already own them? No. A while ago that was true–HDS represented a huge portion of BA’s revenue–but last year it was sub 25% or so. That’s why now makes sense. No need to buy something you already effectively own. That wasn’t the case–and the gap was getting bigger, not smaller.

So, it’s the end of another era. BA started (by the esteemed Geoff Barrall) about 11 years ago–along with ESG. And I shall miss them as they were, but will enjoy watching them have a legit shot to do SOMETHING bigger. Who knows if it works or not, but the bet is sound and I like the chances much more then BA trying to slug it out alone. The NAS world is going to change–just as the block world is going to change–so you are either going to have a dance partner or look dumb playing with yourself (so to speak).

Congrats to all involved.

You can read Steve’s other blog entries at The Bigger Truth.