Using Machine Learning Analytics to Deliver Service Levels
September 21, 2016

Jerry Melnick
SIOS Technology

Share this

While the layers of abstraction created in virtualized environments afford numerous advantages, they can also obscure how the virtual resources are best allocated and how physical resources are performing. This can make maintaining optimal application performance a never-ending exercise in trial-and-error.

This post highlights some of the challenges encountered when using traditional monitoring and analytics tools, and describes how machine learning, as a next-generation analytics platform, provides a better way to meet SLAs by finding and fixing issues before they become performance problems. A future post will describe how machine learning analytics can also be used to allocate resources for optimal performance and cost-saving efficiency.

Most IT departments identify performance problems with tools that monitor a variety of discrete events against preset thresholds. For example they set a specific threshold for CPU utilization. Whenever that threshold is exceeded, the tool fires off alerts. But the use of thresholds presents several challenges. They do not account for the interrelated nature of resources in virtualized environments, where a change to or in one can have a significant impact on another. Such interrelationships exist both within and across silos. Without a complete understanding of the environment across silos, users of threshold-based tools frequently discover that their attempts to solve a problem have simply moved it to a different silo.

Thresholds often generate "alert storms" of meaningless data and miss important correlations that might indicate a severe problem exists. They are ineffective in detecting the symptoms of subtle issues that may indicate a significant imminent problem such as "noisy neighbors" or datastore latency issues. These subtle issues may not exceed a threshold related to the root cause or may exceed a threshold in short, random intervals, producing alerts that are frequently lost amid the "noise" of alert storms.

Even the so-called dynamic thresholds cannot accommodate the constant change in dynamic environments and, as a result, require significant ongoing IT intervention. And finally, while they may alert IT to an issue, they rarely provide sufficiently actionable information for resolving it. The exponential growth in the size and complexity of virtual environments has outstripped the ability of IT staff to set, manage, and continuously adjust threshold-based tools effectively. The time for an automated solution has come.

Advanced machine learning-based analytics software overcomes these and other challenges by continuously learning the many complex behaviors and interactions among interrelated objects – CPU, storage, network, applications – across the infrastructure. Unlike threshold-based solutions, this growing knowledge enables machine learning-based IT analytics solutions to provide a highly accurate means of identifying the root cause(s) of performance problems and making specific recommendations for resolving them cost-effectively.

This ability to aggregate, normalize, and then correlate and analyze hundreds of thousands of data points from different monitoring and management systems enable machine learning analytics solutions to transform massive volumes of data into meaningful insights across applications, servers and hosts, and storage and network infrastructures.

As it gathers and analyzes this wealth of data, the MLA system learns what constitutes normal behaviors, and it is this baseline that gives the system the ability to detect anomalies and find root causes automatically.

In addition to identifying root causes, advance machine learning based analytics solutions are able to simulate and predict the impact of making certain changes in resources and their allocations, which can be particularly useful for optimizing resource utilization and planning for expansion. This capability can also be useful for assessing if there is adequate capacity to handle a partial or complete failover. And these are topics worthy of a deeper dive in a future post.

Jerry Melnick is President and CEO of SIOS Technology.

Share this

The Latest

April 19, 2018

In the course of researching, documenting and advising on user experience management needs and directions for more than a decade, I've found myself waging a quiet (and sometimes not so quiet) war with several industry assumptions. Chief among these is the notion that user experience management (UEM) is purely a subset of application performance management (APM). This APM-centricity misses some of UEM's most critical value points, and in a basic sense fails to recognize what UEM is truly about ...

April 18, 2018

We now live in the kind of connected world where established businesses that are not evolving digitally are in jeopardy of becoming extinct. New research shows companies are preparing to make digital transformation a priority in the near future. However most of them have a long way to go before achieving any kind of mastery over the multiple disciples required to effectively innovate ...

April 17, 2018

IT Transformation can result in bottom-line benefits that drive business differentiation, innovation and growth, according to new research conducted by Enterprise Strategy Group (ESG) ...

April 16, 2018

While regulatory compliance is an important activity for medium to large businesses, easy and cost-effective solutions can be difficult to find. Network visibility is an often overlooked, but critically important, activity that can help lower costs and make life easier for IT personnel that are responsible for these regulatory compliance solutions ...

April 12, 2018

This is the third in a series of three blogs directed at recent EMA research on the digital war room. In this blog, we'll look at three areas that have emerged in a spotlight in and of themselves — as signs of changing times — let alone as they may impact digital war room decision making. They are the growing focus on development and agile/DevOps; the impacts of cloud; and the growing need for security and operations (SecOps) to team more effectively ...

April 11, 2018

As we've seen, hardware is at the root of a large proportion of data center outages, and the costs and consequences are often exacerbated when VMs are affected. The best answer, therefore, is for IT pros to get back to basics ...

April 10, 2018

Risk is relative. The Peltzman Effect describes how humans change behavior when risk factors are reduced. They often act more recklessly and drive risk right back up. The phenomenon is recognized by many economists, its effects have been studied in the field of medicine, and I'd argue it is at the root of an interesting trend in IT — namely the increasing cost of downtime despite our more reliable virtualized environments ...

April 09, 2018

How do enterprises prepare for the future that our Cloud Vision 2020 survey forecasts? I see three immediate takeaways to focus on ...

April 06, 2018

When will we be at a point where virtually all enterprise workloads are run in the cloud and how will that change things for IT? To find out, we commissioned a survey, Cloud Vision 2020: The Future of the Cloud. The results were fascinating. I'll share three fundamental lessons we learned in the survey ...

April 05, 2018

The digital war room — physical, virtual or hybrid — is not in retreat but in fact is growing in scope to include greater participation from development and security. It's also becoming more proactive, with on average more than 30% of "major incidents" before they impacted business service performance. In this blog I'm providing a few additional highlights from the insights we got on digital war room organization and processes ...