Stanislav Kozlovski(@BdKozlovski) 's Twitter Profileg
Stanislav Kozlovski

@BdKozlovski

Have worked on Apache Kafka for 5+ years, now I also write about it. Low-frequency, highly-technical tweets.

ID:1094145275504009217

linkhttps://2minutestreaming.beehiiv.com/ calendar_today09-02-2019 08:05:36

1,1K Tweets

9,6K Followers

262 Following

Stanislav Kozlovski(@BdKozlovski) 's Twitter Profile Photo

Cruise Control is the best open-source tool for balancing your Apache Kafka cluster.

It’s used in big companies like Slack, Wise, and NewRelic... 🤩

But how does it work?

To begin with - a Kafka cluster can be imbalanced on many dimensions. This means that it’s impossible to…

Cruise Control is the best open-source tool for balancing your Apache Kafka cluster. It’s used in big companies like Slack, Wise, and NewRelic... 🤩 But how does it work? To begin with - a Kafka cluster can be imbalanced on many dimensions. This means that it’s impossible to…
account_circle
Stanislav Kozlovski(@BdKozlovski) 's Twitter Profile Photo

You can have extremely high availability or you can have very low resource usage.

You can't have both.

Replication Factor 101

It is a key configuration for availability, durability, and performance. It’s basically a tradeoff between resource usage and availability…

account_circle
Stanislav Kozlovski(@BdKozlovski) 's Twitter Profile Photo

What do you define as a balanced Kafka cluster?

This is a problem I’ve spent 3+ years working peripherally on.

I still find it pretty hard to define.

Some ideas:…

What do you define as a balanced Kafka cluster? This is a problem I’ve spent 3+ years working peripherally on. I still find it pretty hard to define. Some ideas:…
account_circle
Stanislav Kozlovski(@BdKozlovski) 's Twitter Profile Photo

Our paper won the VLDB award for Best Industry Paper!

Kora: A Cloud-Native Event Streaming Platform For Kafka

Not out yet, but trust me when I say it is 🔥🔥🔥

Kudos and thanks to everyone who worked on both the paper and the platform that lead to it!

vldb.org/2023/?conferen…

account_circle
Stanislav Kozlovski(@BdKozlovski) 's Twitter Profile Photo

• scalability
• simpler deployment
• lower cost
• easier maintenance
• single security model
• more availability in cases where it most matters

All this is coming to Apache Kafka.

Can you guess the feature?

account_circle
Stanislav Kozlovski(@BdKozlovski) 's Twitter Profile Photo

🚨 3AM: wake up by page.
😳 4AM: Realize customer's deployment is deleted.
😥 5AM: Scramble & page teams to find remediation.
😵‍💫 11PM: Contact affected customers.
💀 14 Days Later: Incident fully mitigated.

This should scare you.

Which lesson would have prevented this?

🚨 3AM: wake up by page. 😳 4AM: Realize customer's deployment is deleted. 😥 5AM: Scramble & page teams to find remediation. 😵‍💫 11PM: Contact affected customers. 💀 14 Days Later: Incident fully mitigated. This should scare you. Which lesson would have prevented this?
account_circle