Efficient Coding for Cost-Efficient Cloud Savings: How Polar Signals Aids Businesses

Continuous profiling reared its head in a 2010 Google research paper called: Google-Wide Profiling: A Continuous Profiling Infrastructure for Data Centers. Polar Signals is the main developer behind Parca, a continuous profiling open source project which systematically tracks CPU and memory usage, creating profiles of this data to be queried over time. “Our mission is to make the world’s datacenters ten times as efficient as they are today,” Polar Signals’ founder and CEO Frederic Branczyk told TechCrunch. While cutting costs is one of the main benefits that Polar Signals promises, there are other benefits to the technology too — such as incident response efforts around a DDoS attack, for example, as Polar Signals can provide insights on the attack’s impact and identify which parts of a system are under stress. At the time of writing, Polar Signals claims 11employees with experience at companies including AWS, Meta, Red Hat, and HashiCorp.

A new startup is on a mission to help enterprises minimize their cloud expenses through writing “more efficient” code. Called Polar Signals, the company has just secured a massive $6.8 million in funding from well-known backers like Alphabet’s GV, Spark Capital, and Lightspeed.

Originally starting off its seed round in 2021 with $4 million from GV and Lightspeed, Polar Signals is now concluding the round with a total of $10.8 million.

The challenge that Polar Signals seeks to address is this: applications use up system resources, such as CPU and memory, and the more resources they consume, the more expensive a company’s cloud bill becomes. This is because major platform providers charge based on the amount of resources used. One significant factor that impacts resource consumption is the code itself. The more structurally sound the code is, with fewer lines and redundant operations, the more efficiently it will run. And the more efficient it runs, theoretically, the lower the cloud costs will be.

Continuous profiling

This is where “continuous profiling” comes into play, a concept that is part of a larger software monitoring discipline called “observability.” This discipline revolves around measuring a system’s internal state to optimize its performance. Continuous profiling first surfaced in a 2010 Google research paper entitled “Google-Wide Profiling: A Continuous Profiling Infrastructure for Data Centers.”

At its core, continuous profiling involves monitoring resource consumption, even down to specific line numbers in a given codebase, in order to identify any bottlenecks that may be causing excessive resource usage.

Polar Signals is the main driving force behind Parca, an open source project that continuously profiles CPU and memory usage, creating profiles of this data that can be queried over time. Parca serves as Polar Signals’ heartbeat, on which the company is building commercial services, including its recently launched hosted offering Polar Signals Cloud. This offering streamlines the setup and management process and offers the typical features found in most enterprise SaaS tools, such as single sign-on (SSO), team provisioning, and permission management.

“Our goal is to increase the efficiency of the world’s data centers by tenfold,” said Frederic Branczyk, founder and CEO of Polar Signals, in an interview with TechCrunch.

Along with the funding news, Polar Signals is also introducing AI-powered suggestions to improve code. The user can select a section of code, click “optimize with AI,” and review the suggested changes. This feature is available through an early-access program starting today.

While reducing costs is one of the main benefits that Polar Signals promises, there are other advantages to the technology as well. For example, in the event of a DDoS attack, Polar Signals can offer insights on the attack’s impact and identify which parts of a system are under stress.

“The main problem we solve is helping organizations understand and improve resource bottlenecks. However, what we’ve come to realize is that the strongest motivator is not what we initially thought,” Branczyk explained. “Initially, we thought that cost savings would be the primary driver, but we’ve learned that companies are also using it for incident response (for example, ‘why did this latency or CPU spike happen?’). We can provide answers down to the specific line of code that is causing the issue – this is a much more significant motivator for our customers.”

The journey so far

Polar Signals was founded in 2020 by Branczyk, a former Red Hat engineer and a key player in the Prometheus and Kubernetes ecosystems. This experience puts Polar Signals in a strong position to target the enterprise cloud market.

Since its official commercial launch in October, the company has gained over a dozen paying customers, including Vercel, Materialize, Canonical, and Weaviate. This is something that the additional funding will help them capitalize on as they seek to expand in the coming months and years.

“Our pipeline is so extensive that we can’t close new customers quickly enough, which is why we are planning on significantly growing our team in this area,” Branczyk stated.

At the time of writing, Polar Signals has 11 employees with experience at companies like AWS, Meta, Red Hat, and HashiCorp. Although the company is incorporated in the US, only two of its employees are based there. The majority of its workforce is employed through a subsidiary in Germany, where Branczyk himself is located, and global HR firm Remote.com, with teams in Spain, the UK, Poland, and India.

Aside from lead investor Spark Capital, GV, and Lightspeed, the company’s latest funding also includes contributions from a variety of institutional and angel investors, such as Haystack, Lorimer, and Guillermo Rauch, the CEO of Vercel, one of Polar Signals’ customers.

Avatar photo
Kira Kim

Kira Kim is a science journalist with a background in biology and a passion for environmental issues. She is known for her clear and concise writing, as well as her ability to bring complex scientific concepts to life for a general audience.

Articles: 836

Leave a Reply

Your email address will not be published. Required fields are marked *