RFR: Prefer to take AOT method from the SC queue faster

[Vladimir Kozlov]

On Fri, 6 Sep 2024 19:41:12 GMT, Aleksey Shipilev <shade at openjdk.org> wrote:

> Probably WIP. Humor me for a second: why could not / should not we take the AOT task for "compilation" (installation, really) right away like this? I suspect when SC queues are overwhelmed with N elements, we keep walking the entire SC queue for no particular reason?
> 
> This improves javac benchmark considerably (look at both wall time and user time):
> 
> 
> # BEFORE
> Benchmark 1: build/linux-x86_64-server-release/images/jdk/bin/java -XX:CacheDataStore=app.cds -Xmx256m -Xms256m -XX:+UnlockExperimentalVMOptions -XX:+UseEpsilonGC -cp JavacBenchApp.jar JavacBenchApp 50
>   Time (mean ± σ):     348.3 ms ±   2.8 ms    [User: 949.0 ms, System: 101.4 ms]
>   Range (min … max):   344.0 ms … 355.3 ms    100 runs
> 
> # AFTER
> Benchmark 1: build/linux-x86_64-server-release/images/jdk/bin/java -XX:CacheDataStore=app.cds -Xmx256m -Xms256m -XX:+UnlockExperimentalVMOptions -XX:+UseEpsilonGC -cp JavacBenchApp.jar JavacBenchApp 50
>   Time (mean ± σ):     312.2 ms ±   2.6 ms    [User: 577.8 ms, System: 95.4 ms]
>   Range (min … max):   307.1 ms … 318.5 ms    100 runs

Currently we do that in `compare_task`:
https://github.com/openjdk/leyden/blob/premain/src/hotspot/share/compiler/compilationPolicy.cpp#L1185

I was very conservative to immediately selecting SCC task because we put these task on normal compilation queues:
https://github.com/veresov/jdk/commit/76157f6e77346ef0b2c47497231210f1fd84b446

Now we have separate queues for these tasks. I thought I changed code how task is selected for these queues (using FIFO).

-------------

PR Comment: https://git.openjdk.org/leyden/pull/17#issuecomment-2334875489