Hi Vijay, I'm not too familiar with the subject, but maybe you could have a look at the flink-faker[1], which generates fake data. I would think you could use it to write to kafka in one Flink job, and then have another Flink job to ingest and run your benchmarks.
There is also this microbenchmark repo[2], perhaps that could be useful to run on different CPUs. Hope those help, Austin [1]: https://github.com/knaufk/flink-faker [2]: https://github.com/apache/flink-benchmarks On Fri, Nov 5, 2021 at 5:14 PM Vijay Balakrishnan <bvija...@gmail.com> wrote: > Hi, > I am a newbie to running a performance benchmark load test of Flink on new > CPUs. > Is there an* existing workload generator* that I can use with Kafka and > then ingest it with Flink KafkaConnector & test the performance against > various new chips on servers ? > > Measuring CPU performance etc, vCPU usage, Latency, throughput etc. > Pls pardon my ignorance in a lot of these performance related topics. > > TIA, > Vijay >
