A Smarter, Data Science-Driven Approach to Operations
December 04, 2015

Amit Sasturkar
OpsClarity

Data science and machine learning algorithms have become pervasive throughout the modern consumer world. There are many successful applications of machine learning in consumer products that we use on a daily basis, including:

■ Movie, music and product recommendations

■ Ad targeting

■ Web search

But, when we look at the Ops world, we find that there is no breakthrough product that incorporates these same machine learning innovations.

A relevant comparison is with page-level and host-level features (for example, page rank for URLs or host rank for hosts) used in search ranking. These features are typically a function of the WebMap (the massive graph where nodes are URLs, and edges are hyperlinks between URLs). The page rank algorithm allows the ranking of URLs in the WebMap based on the hyperlinks between them. It is a very effective way to get a reasonable estimate of the overall importance of a URL.

What if we used similar ideas to rank the hundreds or sometimes thousands of alerts that operations engineers receive, especially when they are managing hundreds of machines? What is the equivalent of the WebMap in the Ops world?

Another relevant example is provided by duplicate web page detection. These algorithms run as MapReduce jobs on massive Hadoop clusters (thousands of machines) and detect duplicate pages across tens of billions of web pages. When the mappers or reducers fail or when there are performance degradations, hundreds of alerts are generated, many of them for the same underlying root cause.

What if we applied the techniques of web page duplicate detection to eliminate the duplicate and unnecessary alerts received by Ops?

A third big challenge is personalization of content. Personalization is a well-studied problem in the consumer space, with user feedback — both implicit (clicks and actions) and explicit (reviews and ratings) — contributing critical inputs to the learning algorithms. Employing this type of machine learning means that the more time a user spends with a product, the better their user experience will be.

What if we incorporated feedback to learn Ops users’ preferences and continuously improve the accuracy of alert generation and alert ranking?

The answers to these questions will become evident as we bring the innovations in data science and machine learning that are commonplace in the consumer world to the Ops world. DevOps teams need, in effect, an “expert assistant” that can learn their application and system environment, detect and correlate failures, and make recommendations that drive increased focus and productivity — even as everything is continuously changing. It’s time for Ops to get smarter.

Amit Sasturkar is Co-Founder and CTO of OpsClarity.

The Latest

October 22, 2018

Embracing DevOps at enterprise scale requires a seismic shift in the way an organization plans, builds, tests, releases, and manages applications. Here are four ways to ensure your enterprise DevOps transformation is a success ...

October 18, 2018

Are applications teams prepared to manage the chaos arising from an ever-growing landscape of heterogeneous deployment types? A recent survey of application and operations professionals sought to better understand how the industry is shifting and what the future of DevOps might look like. Here is what the survey uncovered ...

October 16, 2018

More than half of organizations have a dedicated DevOps team to help them better implement agile strategies, accelerate release cycles and ensure continuous development. However, databases have a habit of holding DevOps back ...

October 15, 2018

Test Environment Management can save organizations close to $10,000 for each release, yet only four percent of large enterprises have fully integrated TEM processes into organizational DNA, according to the 2018 Test Environment Management Survey released by EMA and Plutora ...

October 11, 2018

Agile is indeed expanding across the enterprise and there was a significant jump from last year to this year in the percentage of respondents who indicated that all or almost all of their teams were agile, according to the State of Agile 2018 report from CollabNet ...

October 09, 2018

Adopting a modern application architecture is critical to business success and a significant driver of profit growth in today’s digital economy, according to the results of a global survey of IT and business executives released by CA Technologies and conducted by Frost & Sullivan ...

October 04, 2018

How do you integrate tools to enable shift-left performance? The following tools will simplify maintenance, can be managed in a centralized way, and provide an easy-to-use UI to comprehend results ...

October 03, 2018

Focusing at the API layer of an application can help enable a scalable testing practice that can be efficiently executed as part of an accelerated delivery process, and is a practice that can be adopted and enabled at the earliest possible stages of development — truly shifting left functional testing. But what about performance testing? How do we enable the shift left of nonfunctional testing? Here, we explore what this means and how to enable it in your organization ...

October 01, 2018

As businesses look to capitalize on the benefits offered by the cloud, we've seen the rise of the DevOps practice which, in common with the cloud, offers businesses the advantages of greater agility, speed, quality and efficiency. However, achieving this agility requires end-to-end visibility based on continuous monitoring of the developed applications as part of the software development life cycle ...

September 27, 2018

Imagine that you are tasked with architecting a mission-critical cloud application. Or migrating an on-premise app to the cloud. You may ask yourself, "how do the cloud savvy companies like Airbnb, Adobe, SalesForce, etc. build and manage their modern applications?" ...

Share this