My experience using loom for a load generator

[Andrew Haley]

On 5/22/20 3:39 PM, Eric Ackermann wrote:
> The Kotlin implementation reached up to 10058 requests per second on average, while the loom-based implementation reached up to 10101 requests per second on average (over 3 runs).

That's really interesting, thanks.

This coincidence is very interesting. I guess it must mean that the
bottleneck restricting the number of requests that the load generator
can send per second is perhaps not in the language or the VM at all,
but in the OS somewhere.

Did you see if the running program saturated the CPU? Was this mostly
in kernel or user space?

-- 
Andrew Haley  (he/him)
Java Platform Lead Engineer
Red Hat UK Ltd. <https://www.redhat.com>
https://keybase.io/andrewhaley
EAC8 43EB D3EF DB98 CC77 2FAD A5CD 6035 332F A671