How Fnatic Deploys Their Data Stack with Plural
The data team at Fnatic chose Plural to get their data stack up and running in production in less than a few hours.
Fnatic is a leading global esports performance brand headquartered in London, focused on leveling up gamers. Founded in 2004, Fnatic is one of the most successful esports brands winning more tier-one game tournaments than any other team globally.
At the core of Fnatic’s success is its best-in-class data team. Similar to most large-scale organizations, the Fnatic data team relies on third-party applications to serve different business functions.
Apostol Tegko has been with Fnatic since 2021 and currently leads their data team. He and his team work hand-in-hand with every member of the organization to aid them in utilizing data on a daily basis.
While having access to an abundance of data is great, it opens up a degree of complexity when it comes to answering critical business questions and in-game analytics for gaming members.
To answer these questions, the data team began constructing a data stack to solve these use cases. Since the team at Fnatic are big fans of open-source they elected to build their stack with popular open-source technologies.
- Airbyte: For ingesting data from various sources ensuring it arrives in a timely manner
- Airflow: For the orchestration of data pipelines
- dbt: For the transformation of data before it’s sent off to the BI layer
- Clickhouse / Postgres: For data storage and processing
- MetaBase: For data visualization and allowing end users to answer business questions
- Grafana: For monitoring and observability of crucial infrastructure like Clickhouse and their cluster in general.
Why Fnatic chose Plural
Previously, the data team at Fnatic was deploying their data stack in various ec2 instances that they were managing manually.
“Generally speaking it’s quite fast to install things on ec2 Linux boxes,” said Apostol. “However, the networking and other related setups for applications would take at least half a day to a day per application.”
And, when you add this up for the entire data stack it takes upwards of a week to get a fully functional data stack up and running. On top of that, the general upkeep of those applications was a time-consuming task (i.e. ensuring machines have enough resources, the delivery mechanism of custom connectors, etc.)
However, Apostol and his team learned that relying on ec2 long-term wasn’t best for their growing business. “In order to support the growing business needs, especially around solutions for pro-gaming analytics and other digital products that were on our roadmap our previous setup would not hold up well.”
Simply switching to bigger machines was not an efficient option for Apostol and his team as they were searching for a solution that would horizontally scale and be elastic around data syncs.
“Previously we had to limit and throttle down our collections to ensure we are not exhausting our available commute and ultimately creating a subpar experience for data consumers.”
To deploy their ideal data stack the data team at Fnatic chose Plural to get up and running in production in less than a few hours.
“Plural is open-source, however, the process of getting started and getting things up and running doesn’t feel like that in a good way. Plural is the best of both worlds,” he added.
Since switching over to Plural the data team at Fnatic is able to handle more complicated workflows of data flowing into their system.
How Plural fits into Fnatic’s future
Since switching over to Plural, the Fnatic team has been able to begin to build out two complex use cases for their gaming team on Plural. Currently, they are building a custom data application that uses training data their gaming team uses to create custom analytics to reduce the amount of time their gaming team needs to get up to speed with the meta-game changes every couple of weeks.
“We gotta stay competitive,” said Apostol. ”We gotta reduce the time it takes for us to adapt to these changes.”
The other use case they are solving is figuring out how to introduce intelligence to the gaming process by applying Machine Learning (ML) models on top of events.
“By having the infrastructure all ready to go with Plural we are now able to get all of these datasets working to solve these problems we were unable to solve previously,” he said.
Getting started with Plural
Are you looking to deploy open-source applications on Kubernetes without having to reinvent the wheel?
If you are interested in learning more about how Plural works and how we can help your engineering team deploy open-source applications in a cloud production environment, reach out to me and the rest of the team over at Plural.
Check out our GitHub and follow our documentation to get up and running.
And, join us on our Discord channel for questions, discussions, and to meet the rest of the community.
Be the first to know when we drop something new.