jojoxhsieh

Hi, this is Jojo, I want to use this project to implement gRPC contract testing in Scala, but it seems that [pact-protobuf-plugin](https://github.com/pactflow/pact-protobuf-plugin#installing-the-plugin) need [pact-jvm](https://github.com/pact-foundation/pact-jvm) v4.4.x and also [pact-plugins](https://github.com/pact-foundation/pact-plugins), so maybe...

I tried, but looks like doesn't help.

> how many CPUS there are on master and replica. Can you provide the htop output of the master during that time? I allocate 64 CPU cores for each, during...

> Maybe also worth trying `serialization_max_chunk_size=1`. The bench does not use big values per say, but it might make the snapshot fiber yield more as it will now flush on...

Also tried with different configs: - Separate admin port: still has issue ` --admin_port=16380 ` - Adjust threads: still has issue ` --proactor_threads=48 --conn_io_threads=16 --conn_use_incoming_cpu=false `

> [@jojoxhsieh](https://github.com/jojoxhsieh) how do you monitor QPS and latency from the memtier output? parse the result from `--json-out-file=/home/memtier_out.json` into csv file and then visualize it as chart.

> Did you run replica on a differrent VM from master? On the same VM, just different container > Did you run memtier on a differrent VM as well? Overall...

I use my original reproduction steps, use `--cpuset-cpus` to separate cpu for master/replica, and run memtier_benchmark in another machine, but result is not good.

Hi, @romange, can you share the memtier_benchmark command you use to test?

I use `debug populate 32000000 key 1024 RAND` to populate data instead, but still got same result. Can you share the commands and steps on how you verify?