vForum is a great chance to view the latest release of virtualization products from VMware as well as getting a great strategic insight into the future roadmap of enterprise computing. Hot topics this year include Workforce Mobility, Hybrid Cloud, Cloud Security and Virtual Desktop Infrastructure (VDI). With the recent release of vSphere 5.5 there are bound to be some great sessions on the new features and capabilities.

As always there is an amazing amount of content and activities available for delegates – get a feel for the latest software releases via the Hands-on Labs, attend the general sessions or take your VCP or VCAP certification exams (remember they are 75% off regular price!). Choosing which sessions to attend (or which to miss L) is always a challenge. Here are my picks:

• Software Defined Data Centre meets End User Computing – Mon 21^st Oct from 1:30pm
• What’s new in vSphere 5.5 – Mon 21^st from 3:20pm
• Through the End User Computing looking glass: A vision for tomorrow – Tues 22^nd from 2:20pm
• Tools of the trade for the vSphere architect & administrator – Tues 22^nd from 4:30pm

vForum is also a great opportunity to view the latest technology trends in the industry. At booth #L14, Nimble Storage will highlight our flash-optimised hybrid storage solutions. Watch one of our live demonstrations and witness 18,000 IOPS from just 8 SATA hard drives in a 3U storage appliance!

Live Demos from Nimble Storage during breakouts at booth #L14:

• Mon Oct 21^st Lunch Break with Nimble Storage CEO, Suresh Vasudevan – (1:00pm – 1:10pm)
• Mon Oct 21^st Afternoon Tea Break – (3:10pm – 3:20pm)
• Tues Oct 22^nd Morning Tea Break – (10:40am 10:50am)
• Tues Oct 22^nd Lunch Break – (1:00pm – 1:10pm)
• Tues Oct 22^nd Afternoon Break – (3:30pm – 3:40pm)

Attend any of our live demos during the breakout times listed above, and pick up a NimbleDisruptors t-shirt!

More prizes? Have your chance to win one of three Gaming Headsets valued over $300 by entering into our prize draw!

Join in the conversation on Twitter by following @NimbleStorageAU or by using the hashtag #nimblestorageau.

Want more chances to win? Share our content, post a photo or promote our live demo times via Twitter – to submit double entries into our prize draw!

Storage Networking World

Long Beach Convention Center

The first event is Storage Networking World, taking place Oct 15 – 17 in Long Beach – we’ll be at kiosk #A15. If you’re interested in storage solutions for VDI (virtual desktop infrastructure), be sure to attend the session by one of our customers, Daniel Kwong of Sacramento City College, who will deliver a presentation on “Key Storage Strategies for Getting The Most out of Your VDI Deployments.” Daniel will discuss his path to VDI, covering topics that include business drivers, return on investment, and storage needs. He will also discuss how Nimble Storage enabled his VDI environment, which helps serves the college’s 25,000 students and 5,000 staff. The session will take place Tuesday, Oct. 15 from 5:00 pm – 5:40 pm.

EDUCAUSE

Next week, we’ll also be at EDUCAUSE, which runs from Oct 16 – 17 in Anaheim. EDUCAUSE focuses on the best IT solutions for higher education, and we’ll be there to showcase how Nimble Storage arrays are a great fit for the storage needs of educational institutions – from running critical applications, to desktop and server virtualization workloads. Come visit us there at booth #727 to find out more.

The Nimble Storage stand was in the middle of “Storage Avenue” which was great fun for 3000 delegates to see the old and the new storage architectures. The level of interest throughout the four days was amazing. Even with six people on the Nimble Storage stand, we had delegates joining in on conversations, so they could learn more. With my CS210 array on the stand punching out 16,000 random 4K IOPS, many were impressed and curious how Nimble Storage could deliver this performance.

John Whyte delivered great demos each day, which always drew a crowd. The realisation of how CPU performance advancements compare with mechanical hard disk performance advancements was causing penny’s to drop. It’s something most IT professionals know about, but don’t realise until it’s visually compared. It’s a challenge that Nimble Storage has met, built a storage architecture from the ground up and solved.

What projects were most people talking about?  VDI (Virtual Desktop Infrastructure). Over and over this is what people would be enquiring about, and Nimble Storage fits this solution like a glove. It was great to be able to talk about the challenges some organisations are facing with their VDI infrastructure, like boot storms and AV scanning, and show how with Nimble Storage these concerns are history.

Lots of really cool technologies were on show, including 3D printing systems. To see someone scanned by a XBOX 360 Connect controller, a 3D model of their head and shoulders created and bust of them printed out of plastic, was amazing.

Microsoft organised this fantastic event, which all delegates agreed was delivering the right mix of information, entertainment and education. Thanks go to Microsoft for this great event and I look forward to attending next year.

By the way, Australia’s Gold Coast is always spectacular in September.

Coolangatta Beach on the Gold Coast of Australia

For some it will be a chance to learn new development techniques. For others, it will be a first peek under the covers of new software versions, and to understand the new features available and how to plan to integrate them into the IT environment. From this perspective, here are a few sessions that look quite interesting:

• Microsoft Exchange Server 2013 Sizing – Sept 4, 2013 from 6:30 PM (EXL317)
• Building a Fully Automated Cloud with System Center and Hyper-V – Sept 5, 2013 from 3:30 PM (MDC325B)
• SQL Server 2014 – Features Drilldown – Sept 4, 2013 from 8:15 AM (DBI311)

We are thrilled to be a part of this year’s inaugural Gold Coast Microsoft Tech Ed event. Join us at booth #32 to learn how Nimble Storage delivers outstanding performance with its Flash-Optimised Hybrid Storage solutions. Experience the impactful difference of Nimble Storage Solutions for Microsoft Applications at our live demonstrations scheduled during break times across the duration of the conference.

Live Demos from Nimble Storage during Breakouts at Booth #32:

• Nimble Storage Solutions for Microsoft Exchange – Sept 4, 2013 from 11:15 AM and Sept 5 from 3:15 PM
• Nimble Smartstack™ for Windows Server on Hyper V – Sept 4, 2013 from 12:45 PM; Sept 5 from 11:15 AM and Sept 6 from 12:45 PM
• Nimble Storage Solutions for Microsoft SQL – Sept 4 from 3:15 PM, Sept 5 from 12:45 PM and Sept 6 from 11:15 AM

Attend any of our live demos during the breakout times listed above, and pick up a NimbleDisruptors t-shirt!

More prizes? Have your chance to win one of three Gaming Headsets valued over $300 by entering into our prize draw!

Join in the conversation on Twitter by following @NimbleStorageAU or by using the hashtag #nimblestorageau.

Want more chances to win? Share our content, post a photo or promote our live demo times via Twitter – to submit double entries into our prize draw!

It’s been a busy year around here. Since VMworld last August, Nimble Storage has:

• Reached the 1,500-customer milestone, with accelerating adoption every quarter
• Launched our InfoSight services to help customers manage their arrays more efficiently
• Launched our SmartStack pre-validated reference architectures in collaboration with VMware and Cisco
• Debuted in the Visionaries quadrant of Gartner’s Magic Quadrant for General-Purpose Disk Arrays
• Launched NimbleConnect, our online community for Nimble Storage customers, partners, and other IT professionals

If you’re going to VMworld, come by our booth, #921, and see for yourself what the buzz is about – we’d love to catch up with you on all the latest happenings at Nimble Storage, and hear your thoughts on storage and virtualization as well. If you’re rushed for time, our recurring in-booth presentations will tell you what you need to know in a matter of minutes, on topics that include the breakthrough CASL architecture, our SmartStack solutions, and InfoSight.

Visit booth #921 at VMworld to learn more about Nimble Storage flash-optimized storage solutions. Live demos, a Brainiac Bar, and a chance to win a 2-week fantasy rental of a Maserati convertible!

This year we’ll have specific stations with live demos and experts focused on four topics: end user computing, business critical applications, InfoSight, and a tech preview where we’ll give you an early sneak peek at some of the amazing things our engineers are working on in their labs. And our “Brainiac Bar” will have our top technical experts waiting, whiteboard marker in hand, to answer your most pressing storage questions.

The VMworld conference sessions are one of the key reasons attendees make the trip. Here are a few we’re especially excited about and think you may find valuable:

• STO6572 – Evaluating Storage Advances for the Virtualized Datacenter : Nimble CEO, Suresh Vasudevan, will discuss the latest storage advancements for the virtual datacenter. George Mitsopoulos, CTO at service provider Virtacore, will also present on how his firm leverages elastic compute and hybrid storage to deliver scalable, efficient cloud services.
• STO5559 – The Future of Storage: A Panel Discussion: Nimble Founder and Vice President of Engineering, Varun Mehta, will participate in a panel discussion with executives from IBM, HP, Dell, EMC, NetApp and VMware on trends shaping next-generation datacenter architectures. Topics include software defined storage, solid state storage architecture evolution, granular data management, cloud file systems and cloud storage.
• BCO5431 – Customers and Service Provider’s Perspectives on DR Strategy, Tips and Tricks for Private and Hybrid Cloud Environments: Nimble vExpert Wen Yu will be moderating this panel on DR for private cloud and DRaaS. Panelists include Virtacore Systems, eMeter, City of Hot Springs, Arkansas, and Foster Pepper.
• EUC5610 – Virtualized Inception: Mobility Dream within a VDI Dream; Realized!: Robert Dixon, Director of IT for CU Boulder, and his colleagues will explore the journey to desktop virtualization to support BYOD and mobile users around his campus.
• STP1003 – Nimble Storage SmartStack: Proven Reference Architectures from VMware, Cisco, and Nimble Storage : Nimble technical expert Michael McLaughlin and I will present on how our SmartStack solutions with VMware and Cisco help organizations accelerate deployment and reduce risk.

VMworld promises to be a great event this year, and we really hope to see you there. So don’t forget to come by and visit Nimble Storage at booth #921 – you may even get lucky and get a chance to drive around in a Maserati convertible for a couple of weeks!

See you in San Francisco!

Nimble has partnered with Cisco to bring to market the Nimble Storage SmartStack, an integrated solution including best-of-breed storage, servers, networking, and virtualization technology. Working closely together, Cisco and Nimble have jointly produced reference architectures that have been tested for interoperability, performance, and fast deployment.

Cisco and Nimble pre-validated SmartStack solutions have also been developed in collaboration with Citrix, VMware, and Microsoft to address both desktop virtualization, and server virtualization for private cloud deployments. Storage is not purchased in silos, so we’ve developed reference architectures with the key industry-leading ecosystem partners to provide a complete range of solutions.

Come by booth #225 to learn how SmartStack solutions can help your organization accelerate deployments and reduce risk, improve IT productivity, and flexibly scale as needs change. Nimble Storage hybrid arrays will also be featured in the Cisco Unified Data Center Partner Ecosystem Technology Demonstration, so be sure to visit us there as well.

To learn more and to have a chance at winning a $100 Amazon gift card, check out our special Cisco Live site that’s filled with great content, such as product briefs, details on our reference architectures, and SmartStack customer case studies: http://info.nimblestorage.com/cisco-live-2013-nimble-storage.html

See you in Orlando!

• Overview of Windows Server 2012 Hyper-V – June 5, 2013 from 5:00PM to 6:15PM (MDC-B338)
• Transform the Datacenter with Server and Management Innovations from Microsoft – June 3, 2013 from 11:00AM to 12:00PM (FDN06)
• Windows in the Enterprise – June 3, 2013 from 11:00AM to 12:00PM (FDN07)
• Everything You Ever Wanted to Know about Windows, But Were Afraid to Ask – June 4, 2013 from 8:30AM to 9:45AM (WCA-B201)

For Nimble Storage, this is our first year as an exhibitor at the show and we couldn’t be more excited. Join us in our booth #2523 to experience first-hand the efficiency, performance, and functionality the Nimble Storage CS-Series of hybrid storage systems can deliver for Windows environments. Our booth demos will include SmartStack for Windows Server,  along with solutions for Exchange, SQL Server, and file serving using Microsoft Windows Server 2012 and Nimble Storage.

That’s not all – you’ll have a chance to enter our daily raffle for a $100 Amazon gift card, just for joining the conversation. You can also connect with us and ask questions on Twitter by following @nimblestorage or by using the hash tag #nimblestorage.

See you in The Big Easy!

We’re putting a lot of time and energy into building an exciting presence for attendees of this year’s VMworld conference in San Francisco, CA, featuring great demos of our highly efficient SmartStack family of products with Cisco, VMware, and Microsoft, targeted at VDI, business applications, and private cloud.

We are especially excited about the number of session submissions from customers – including several featuring our own customers – on a range of hot topics. Proposed sessions will focus on best practices for scaling infrastructure for cloud environments, circumventing challenges of VDI deployments, and 10 others that will offer up a wealth of realworld insights on storage considerations for the virtualized datacenter.

Have a look at the list of our submitted VMworld 2013 sessions and vote for the ones that you think will be most valuable to you! If you have any feedback, feel free to join in the discussion.

Looking forward to seeing you in August at VMworld 2013!

Whenever an enterprise or a cloud service provider deploys a Nimble Storage array, one of the first questions they ask is usually: How much cache do I need? Often followed by: And how do I figure out how much cache I need, when different workloads put different requirements on the cache?

Great questions, because it’s true, you really do need to characterize each workload in order to properly size a cache requirement. Our research in this area has revealed some interesting things about how customers use their storage. As Nimble’s chief data scientist, I’ll share with you one of the many insights we’ve gained, but first, a little background.

Nimble Storage’s new InfoSight cloud-based service tells customers, as a percentage of their current cache, how much they really need in order to maintain good performance. For each installed array, a customer can pull up a chart in InfoSight that looks like this:

Nimble Storage InfoSight tells customers how much cache
they need to maintain required performance levels.

The left side of the chart shows that this example array had been running on empty through September and October of 2012 – it already needed a bit more cache, as cache utilization was hovering around the 100% mark, and well into the yellow. To make matters worse, around the end of November, the customer doubled their workload against this array, as seen on the right side of the chart. As a result, their cache was no longer delivering the performance benefits it should.

InfoSight now lets them know what kind of scale-to-fit upgrade would accommodate their new workload, so that they can reclaim the performance they had enjoyed around the beginning of 2012. This example illustrates the importance of dynamic cache resizing: with scale-to-fit, customers can continue to grow workload while maintaining the price-performance benefit of the Nimble solution.

How do we compute this figure? We need to understand the customer’s dynamic environment well enough to put a number to how much more cache is needed, or how much headroom is available.

To accomplish this feat, we have developed a model of how our cache works. We take the set of sensor data we’ve collected from an array – more than 30 million values per array per day, on average – and from this dataset we estimate values for the model parameters. Then we plug these estimates into the model, and compute necessary cache.

How detailed is this model? Well, for starters we recognize that some workload components are pretty much random, such as large working set of blocks being touched over and over again, in no particular order. We model a number of facets of this component.

Then there are the periodic components – workflows, cron and batch jobs, which deterministically touch the same blocks at particular times: at 8:00 a.m. each day, for example, a user logs in; at midnight, a data extract is run, and so on.

As it turns out, when it comes to sizing the cache, these periodic access patterns are as important to understand as random working set size: if your cache age (average amount of time data stays in cache before being evicted in favor of hotter data) is 24 hours, you may get significantly more benefit than you would if your cache age were 23 hours and 59 minutes, when it comes to these workload components.

Our model captures and extracts for us, among other things, how much IO for a given workload is against periodic workload components. For this IO, we can extract the incremental benefit associated with increasing cache age, at each such periodicity. The process looks something like this:

InfoSight captures and extracts how much IO for a given workload is needed against periodic workload components.
For this IO, we can extract the incremental benefit associated with increasing cache age, at each such periodicity.
The process looks something like the illustration above.

On the right side of this figure, you’ll notice a spikey chart with peaks at 24, 48, 72 hours. This figure shows that, when we isolate the periodic components of a typical workload, we generally want a cache age of at least 72 hours.

In fact, the chart you’re looking at is an average incremental benefit by cache age across the periodic components of all our customers’ workloads combined. So, it really is a universal lesson: all other things being equal, it pays to size your cache for an honest day’s workload – or two or three.

• InfoSight transforms the paradigm for how storage systems have been traditionally monitored and supported, by introducing the notion of “cloud managed storage infrastructure”.
• NimbleConnect is our new community site, where storage and IT pros can share InfoSight data and leverage the collective insights of their peers to answer their questions and optimize their storage systems..

The foundation for InfoSight and NimbleConnect was laid very early – from a realization that in addition to our groundbreaking storage architecture, scaling the company to tens of thousands of global customers would also require a disruptive and innovative approach to scaling customer support.

The Cloud Allows Us to Rethink Traditional Ways of Monitoring Infrastructure

The traditional support process starts with a customer being alerted to a problem either because of a service disruption to their internal end-users or because on-site monitoring software points to an error condition.  The customer then calls the vendor’s support center where a level-one support engineer asks basic questions and gathers configuration information. For any serious problem, the customer’s call typically gets escalated to a level-two support engineer who then asks the customer to gather and upload an enormous amount of diagnostic information.  This part of the support process can leave the customer frustrated and anxious that too much time has been has been spent on information gathering rather than on problem solving.

InfoSight challenges this traditional process by applying the following basic beliefs to the process:

1. Connectivity.  In a connected world, there is no reason why we cannot monitor our customer-deployed systems like they do.  Therefore, we should know when our systems face a support incident at the same time as a customer does.
2. Comprehensive database with extensive health information gathered proactively.  In a connected world, instead of reactively asking a customer for information when a problem occurs, we should be gathering a wealth of information proactively from our customer-deployed systems – system health information, meta-data, system logs and so on.  What is critical though is to gather information on a frequent basis, since the industry practice of gathering nightly logs and daily phone-home capabilities is too coarse in time.

Today, InfoSight allows us to monitor heartbeats and gather system health information securely from our customer deployed systems every few minutes, resulting in ~30 million sensor values per system, per day in our database!

Deep Data Analytics Can Help Transform Support into a Predictive Process

Going back to the traditional support process, even after all the diagnostic information has been gathered, it takes support organizations a long time to bring the right expertise to bear on the specific customer problem.  What is altogether too frequent and frustrating to a customer is when they are told that the specific problem they encountered is from a known defect, and are then provided a software patch that they need to apply.  The customer is left wondering why they were not informed ahead of time about the potential problem.

In rethinking this process, InfoSight leverages another core belief:

1. Deep Data Analytics Can Predict Problems.  We have a team of data scientists and support engineers that apply advanced analytics and statistical modeling to the wealth of near-real-time information to predict when things could go wrong.  We look for early warnings that can point to potential problems.  When one customer encounters an issue, we immediately query our database to identify other potentially vulnerable customers.  We look for customer implementations that do not adhere to best practices.  The support database and the algorithms and data models that we use to query the database have become a core operational process within our engineering and support organizations.

The best proof-point of the efficiency of this approach is in the fact over 80% of all our support cases are ones where we call a customer to either address an impending issue or prevent an issue!

Going Beyond Support: Cloud-Based Monitoring with InfoSight

We have been leveraging the capabilities of InfoSight to deliver superior support for the last two years.  The next logical evolution of InfoSight was to put the power of all the information and the analytical capabilities in the hands of our customers.

When we looked at the on-site monitoring applications that most customers deploy from incumbent storage vendors, the approach that such software applications use is to poll storage systems on a frequent basis to create an event database which is then transformed into visual graphs – trending information, capacity forecasts, performance monitors, etc.

Leveraging the deep data that we gather from all our customer-installed systems, the InfoSight Portal is a Cloud-based application that allows customers to monitor their infrastructure without the complexity of on-premise software, licenses and agents.

More than 200 customers have already deployed the InfoSight service to generate real-time alerts, forecast their capacity requirements, size their system upgrade needs, monitor application backups, report on the success of their disaster recovery implementations and more.  Every day we continue to hear from our customers on how the InfoSight portal saved the day for them:

• The service provider customer who kept adding more and more workloads and used InfoSight to gauge exactly how much CPU, cache and capacity they needed to keep their applications running in top condition.
• The enterprise customer who had strict policies tied to data protection, who was able to detect the one time his VMware snapshot failed causing his RPO (recovery point objective) and RTO (recovery time objective) goals to be missed, and was able to immediately rectify it.
• The retail customer with arrays in multiple data centers who regularly uses the capacity usage and change rates to compute how much bandwidth she needs to provision to replicate her snapshots across sites.

The list goes on and on.

NimbleConnect: A Community Centered around Real-World Insights from InfoSight

When we shared the InfoSight vision with the industry’s most prominent analysts and influencers, the feedback was overwhelming.  Why restrict this to just Nimble customers, these experts asked.  Why not share these insights with the broader storage community who can benefit from access to this type of information? And thus was born Nimble Connect – the Nimble storage community.

At Nimble, we believe that our single most important asset is our customer base, and our single most important priority is to foster a satisfied customer community.  NimbleConnect provides a platform for these customers to share their stories, best practices, tips and tricks, scripts, and other valuable technical resources.

Furthermore, it takes the insights gleaned from the installed base through InfoSight and returns them back to our customers, where they can be discussed and enhanced. A customer in a particular vertical market looking to deploy VDI (Virtual Desktop Infrastructure) for the first time can now learn what their peers in other institutions are doing with regards to size of the virtual desktop. Microsoft Exchange admins can learn what the installed base is doing when it came to protecting their Exchange environments with snapshots. The NimbleConnect portal uses the richness of InfoSight to provide these and many other insights.

InfoSight and NimbleConnect are the first steps in a vision around how we can transform a customer’s support experience and a customer’s access to peer insights.  The vision was made possible by leveraging the cloud for unprecedented near-real-time information about how our customers use their systems, and by leveraging deep data analytics to transform that information into predictive actions and insights.  We are merely at the beginning of what we believe is possible.  We welcome you to sign up on NimbleConnect and help us make it better.