Using Machine Learning to Eliminate Data Center War Rooms – Virtual Instruments Briefing Note

According to Dimensional Research, over 60% of enterprises experience two or more significant application performance issues per month. In the modern data center, most users equate poor performance the same as application downtime. Performance issues, though, are usually much harder to diagnose than application downtime. These issues are typically caused by an infrastructure that is out of control. To help diagnose and resolve the problem, the organization assembles its top IT staff into a war room to work out the issues. IT needs to regain control of the data center to end the need for data center war rooms and proactively eliminate performance problems before they can impact users and customers.

Why Are Application Performance Issues On The Rise?

There are many contributing factors to the rise in application performance problems. The number of applications that the organization counts on has increased significantly. Many organizations have dozens of applications that they consider either mission critical or business critical and hundreds of applications that users count on every day. To support these applications, the modern data center is achieving a scale and complexity that is beyond human comprehension. The data center is no longer confined to four walls in a single location either; it often spans multiple physical locations and leverages several major cloud providers.

IT needs insight into the infrastructure it is using to support its mission-critical applications, users and customers. There are plenty of tools available and each component of the infrastructure typically contributes some information. The problem is most data centers have no single point of truth. There are too many siloed tools which are not integrated nor do they even correlate information. Without this single point of truth or an understanding of how applications relate to the infrastructure, it is impossible for IT to proactively identify problems. It can only react.

Organizations create war rooms to manually collect and correlate the information that the infrastructure holds within its silos. Even once all the data is gathered, identifying the problem and creating a solution is a slow, painful process. In the war room solving the problem requires human analysis of the data and group-think of potential solutions. Testing of those solutions is typically a trial and error process and often occurs on production systems – substantially increasing the risk or more problems.

Virtual Instruments 6.0 – Reinventing Infrastructure Management

Virtual Instruments breaks down silos with an end-to-end analysis of the data center. Its VirtualWisdom solution understands where the application lives on the infrastructure, knows the business value and SLA tier of each application and understands how applications are behaving and how they are placing stress on the rest of the infrastructure. The VirtualWisdom solution provides application service assurance, predictive capacity management, workload infrastructure balancing, problem resolution and avoidance. It delivers this insight across cloud environments (public, hybrid, private), hyper-converged architectures, virtual infrastructure, bare metal servers, networks and storage systems.

VirtualWisdom’s expertise in capturing and creating a centralized “truth” is the company’s core value. However, as the data center has scaled in response to massive application and data growth it is more difficult for busy IT teams to diagnose the information that VI collects. In the latest release, VirtualWisdom 6.0 adds the ability to use machine learning and analytics to provide IT with a proactive diagnosis of impending problems.

The 6.0 release has proactive dashboards that provide IT with ongoing recommendations on how to best balance data center workloads across the infrastructure. It also provides a predictive capacity management capability that analyzes short and long term usage trends to forecast when the organization will run out of capacity. The capacity trending feature can also identify opportunities for reclamation and improving performance.

The VI correlation engine, Trend Matcher, is now application and topology aware in addition to storage infrastructure aware. The additional data vectors make the artificial intelligence behind Trend Matcher even more accurate and reduce the mean-time-to-resolution for even the most challenging of issues.

VirtualWisdom also includes Automated Investigations. This capability proactively triages, diagnoses and provides guided recommendations to resolve critical alerts.

StorageSwiss Take

The challenge that any monitoring and management application faces today is the speed at which IT can respond to problems it detects and IT’s ability to decipher the information so it can take the appropriate action – ideally before users are affected. IT teams are just too busy and stretched too thin. Another challenge facing IT operations teams is for the most part they are reactive, something has to go wrong (and someone has to get mad) before alerting IT to a problem.

Virtual Instruments is addressing both of these challenges. First, it is not only alerting IT of current problems but also providing recommendations to resolving them. Second, and more importantly, VirtualWisdom 6.0 can use its analytics combined with machine learning to predict potential problems long before they impact production. This proactive nature enables IT to keep applications running seamlessly and users happy.

Sign up for our Newsletter. Get updates on our latest articles and webinars, plus EXCLUSIVE subscriber only content.

Twelve years ago George Crump founded Storage Switzerland with one simple goal; to educate IT professionals about all aspects of data center storage. He is the primary contributor to Storage Switzerland and is a heavily sought after public speaker. With over 25 years of experience designing storage solutions for data centers across the US, he has seen the birth of such technologies as RAID, NAS and SAN, Virtualization, Cloud and Enterprise Flash. Prior to founding Storage Switzerland he was CTO at one of the nation's largest storage integrators where he was in charge of technology testing, integration and product selection.

Tagged with: , , , , , , , ,
Posted in Briefing Note

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

Enter your email address to follow this blog and receive notifications of new posts by email.

Join 21,950 other followers

Blog Stats
  • 1,323,268 views
%d bloggers like this: