Burrow VS fast-data-dev

Hello! I am trying to set up consumer group lag monitoring via DataDog. I noticed that DataDog has a consumer integration which I am considering, especially since it has a consumer lag in seconds metric. I also see that Burrow is another popular option for monitoring consumer lag via a status. I'm curious to hear if folks have any thoughts on monitoring consumer lag via status versus lag in seconds (for example, via this consumer_lag_seconds DataDog metric). Wondering if the overhead of managing Burrow is worth getting consumer lag statuses, or if we can do something similar within DataDog with the built in integration. Thanks!

Burrow

Some random tips: * Use SSDs, not magnetic disks. Our Kafka brokers used to use magnetic disks for more throughput, but this caused wayyyy more problems, like very slow broker restarts. * You'll want to install something like Burrow so you can get better lag metrics. * You might want to install CMAK. It's a web interface for common ops tasks.

As to which consumer is reading from which topics, ACLs help you with managing this (ok, you wouldn't know if a consumer doesn't read from a topic which it is allowed to read from). For consumer lag tracking check out Burrow, which should help you with that (e.g. also can send out notifications as per its docs, haven't tried this myself though).

I liked https://lenses.io/ Lots of capabilities but it's not free as I know.

Lenses

For Kafka Dev I use https://github.com/lensesio/fast-data-dev

Currently I'm using Lenses:https://lenses.io/ as UI tool, but while turning on kafka-start-server server.properties and launch the UI on localhost, it failed to connect:

Oh thats sad to hear ... lenses.io is so powerful I am not sure how I would have gotten by to this point without it!

In Addition to the more critical replys from others, why Kafka still makes sense imo: - you could organist everything with custom pipeline/services at your scale. The cost of maintaining those and keep the technology up to date is growing exponentially with every new Service. Kafka offers ansinge Plattform with a couple components which need to be kept up to date. - deploying, managing and monitoring those service is also a big task and does not come for free. - unless your using Kubernetes underneath, scaling is not easy with services. - peer to peer communications of microservices should be avoided because your building a „deathstar“-like architecture where everything is linked and effectively you’ll end up with a distributed monolith. A message broker or message queue helps to avoid this, Kafka is a good tool for that. - I heard that those aws Kafka replacements are not 100% Kafka as one might expect, you should be careful there. But confluent or other providers probably offer hosted solutions on aws too. - https://lenses.io/ helped us a lot when we started with Kafka to see how everything works together, create stream processor’s with sql and easily deploy Kafka connect workers. The tool costs money though but is worth it in the end in my opinion. (Disclaimer: I don’t work for confluent or lenses, we’re running open source Kafka with strimzi and lenses)

https://github.com/lensesio/fast-data-dev is a really cool option for a Kafka development environment based on docker and/or kubernetes.

Yes: - https://lenses.io/ (use the Lenses box, it’s free) - https://github.com/lensesio/fast-data-dev - https://github.com/provectus/kafka-ui