[spockz]

Interesting. Internally we made a similar tool for performance testing applications, including fault and latency simulation of dependencies. It also includes analysis of resource consumption and whether performance and/or resource consumption have increased or decreased.

This is now the second time a similar tool has popped up here at HN, maybe we should open source it.

[lazarkap]

There is an open source Im working on, that will be able to achieve all this just without dashboard https://github.com/LazarKap/buzzbench.io. How did you analyze resource consumption with your tool??

[spockz]

Yes that was the “second” one I was referring to.

We just piggyback on the Prometheus metrics provided by cadvisor for the container level metrics. Then for the jvm we collect metrics such as memory allocation etc.

This all goes into a big table and the user can select the right version. Next iteration will be where they can configure whether to aim for latency, throughput, or efficiency, and which weights so we can select the winner automatically.

[lazarkap]

I plan to add ability to deploy additional agent to the env that is being tested, and that one would just grab resource metrics and send back to me while its being tested. :D So you can see your resource usage while tests are running and you can predict how much traffic/usage your platfroms/services can handle