Francesco Nigro

@barreiro

In vertx 5 this will be gone, but till that moment, we can still hit this

@Sanne I asked @barreiro to investigate on it

I have to take a look but in theory a json related to the run is saved in: https://github.com/RedHatPerf/superheroes-automation/blob/18cbfad9962276dc384d3d4b9614c167a18dd4fd/drivers/hyperfoil.yaml#L20

> so getting access to the tmp folder of the container is not trivial actually the tmp folder is something you could tune via a sys property: `java.io.tmpdir` - but...

Actually @zakkak https://github.com/Hyperfoil/Hyperfoil/blob/d19876ced330fff1662197f6eaeda9f40719b5da/api/src/main/java/io/hyperfoil/internal/Controller.java#L17 it looks like is possible to tune the `run` folder where everything is saved...

As usual, humans sucks at estimation :P JMH reveal something interesting, when the code is interpreted; will update soon this draft

This has been noted by @diegolovison which reported a weird benchmark run, where the server was slow to respond and Hyperfoil complaining of a single core been maxed out.

@mkouba @vietj

> Could this be replaced by the new memory api? VarHandle should just work: https://foojay.io/today/unsafe-is-finally-going-away-embracing-safer-memory-access-with-jep-471/ but as said by @nitsanw ; it's not just matter of replacing it (although it's...