RSS

Hydrolix Powers Observability at Scale for Akamai

Learn how Hydrolix powered observability at scale for Akamai during the biggest football event of the year.

Franz Knupfer

Published:

May 29, 2024

2 minute read
,

During the biggest football game of the year, viewers don’t want to miss a single play, and some viewers don’t even want to miss a single ad. Any issues with buffering, lag, outages, or poor video quality can result in frustrating user experiences, ads not displaying properly, and other problems. To handle peak events, media companies and CDN providers often need to optimize and troubleshoot content delivery network (CDN) coverage to provide optimal viewing experiences.

Monitoring peak events is already a challenge, but the game between Kansas City and San Francisco provided the biggest challenge of all. With nearly 124 million average viewers, the game was reportedly the most watched live broadcast event since the Apollo 11 moon landing. For Akamai, that meant streaming and analyzing millions of CDN log lines per second in order to troubleshoot issues and potential incidents in real-time.

To provide real-time observability at scale, Akamai used TrafficPeak, a managed Akamai observability service powered by Hydrolix. TrafficPeak is designed to handle observability at terabyte scale and now serves more than a hundred customers, including some of the biggest enterprises in the world. According to Nathan Hoffman, an enterprise architect at Akamai, “it was a no-brainer to use it for the big game. The service is easy to deploy, even with customization.”

“TrafficPeak gave us real-time visibility into our media customers’ data, which we used to balance traffic across geographies and surpass viewers’ expectations of a smooth, reliable experience,” Hoffman said.

Our latest customer story is in Nathan Hoffman’s own words. Learn about the value of TrafficPeak from the perspective of an enterprise architect with a deep understanding of keeping complex systems running smoothly at scale.

Some highlights:

  • During periods of peak traffic, Hoffman’s team was collecting nearly 11 million rows per second while analyzing the data in real time with sub second query performance.
  • Post-event analysis was also essential and showed areas where Hoffman’s team could improve. They used a data-driven approach to rewrite filters and gain a better understanding of how to achieve even faster mitigation and prevent more issues during future peak events.

For a deep dive into how Hoffman and his team used TrafficPeak for big game observability, read the customer story.

TrafficPeak and Hydrolix Offer Observability at Scale

TrafficPeak, like Hydrolix, allows users to keep their data accessible for query analysis long-term. The default retention period is 15 months for “hot” storage, which means you get get sub second query latency whether you need data from a minute or a year ago. And because both TrafficPeak and Hydrolix use commodity object storage, keeping data is cost-effective even at petabyte scale.

Next Steps

Share this post…

Ready to Start?

Cut data retention costs by 75%

Give Hydrolix a try or get in touch with us to learn more

During the biggest football game of the year, viewers don’t want to miss a single play, and some viewers don’t even want to miss a single ad. Any issues with buffering, lag, outages, or poor video quality can result in frustrating user experiences, ads not displaying properly, and other problems. To handle peak events, media companies and CDN providers often need to optimize and troubleshoot content delivery network (CDN) coverage to provide optimal viewing experiences.

Monitoring peak events is already a challenge, but the game between Kansas City and San Francisco provided the biggest challenge of all. With nearly 124 million average viewers, the game was reportedly the most watched live broadcast event since the Apollo 11 moon landing. For Akamai, that meant streaming and analyzing millions of CDN log lines per second in order to troubleshoot issues and potential incidents in real-time.

To provide real-time observability at scale, Akamai used TrafficPeak, a managed Akamai observability service powered by Hydrolix. TrafficPeak is designed to handle observability at terabyte scale and now serves more than a hundred customers, including some of the biggest enterprises in the world. According to Nathan Hoffman, an enterprise architect at Akamai, “it was a no-brainer to use it for the big game. The service is easy to deploy, even with customization.”

“TrafficPeak gave us real-time visibility into our media customers’ data, which we used to balance traffic across geographies and surpass viewers’ expectations of a smooth, reliable experience,” Hoffman said.

Our latest customer story is in Nathan Hoffman’s own words. Learn about the value of TrafficPeak from the perspective of an enterprise architect with a deep understanding of keeping complex systems running smoothly at scale.

Some highlights:

  • During periods of peak traffic, Hoffman’s team was collecting nearly 11 million rows per second while analyzing the data in real time with sub second query performance.
  • Post-event analysis was also essential and showed areas where Hoffman’s team could improve. They used a data-driven approach to rewrite filters and gain a better understanding of how to achieve even faster mitigation and prevent more issues during future peak events.

For a deep dive into how Hoffman and his team used TrafficPeak for big game observability, read the customer story.

TrafficPeak and Hydrolix Offer Observability at Scale

TrafficPeak, like Hydrolix, allows users to keep their data accessible for query analysis long-term. The default retention period is 15 months for “hot” storage, which means you get get sub second query latency whether you need data from a minute or a year ago. And because both TrafficPeak and Hydrolix use commodity object storage, keeping data is cost-effective even at petabyte scale.

Next Steps