RFR: 8357473: Compilation spike leaves many CompileTasks in free list

[Aleksey Shipilev]

On Fri, 23 May 2025 16:03:05 GMT, Vladimir Kozlov <kvn at openjdk.org> wrote:

> Did you do performance compare?

Both issues in `CompileTasks` are about footprint. I expect no significant difference on throughput, given how few compile tasks we normally allocate. On my ad-hoc runs it is more or less a wash:


$ taskset -c 0-3 hyperfine -w 30 -r 300 \
  "build/linux-x86_64-server-release/images/jdk/bin/java -XX:TieredStopAtLevel=1 Hello.java"

# Baseline
  Time (mean ± σ):     353.4 ms ±   1.8 ms    [User: 482.3 ms, System: 88.3 ms]
  Range (min … max):   348.0 ms … 358.6 ms    300 runs

# No free list -- this PR
  Time (mean ± σ):     354.5 ms ±   1.6 ms    [User: 482.8 ms, System: 89.4 ms]
  Range (min … max):   350.4 ms … 360.1 ms    300 runs

# Global blocking mutex -- #25364
  Time (mean ± σ):     354.3 ms ±   1.7 ms    [User: 482.1 ms, System: 89.4 ms]
  Range (min … max):   350.0 ms … 359.8 ms    300 runs

# This PR + #25364
  Time (mean ± σ):     354.4 ms ±   1.8 ms    [User: 482.2 ms, System: 88.6 ms]
  Range (min … max):   349.8 ms … 360.8 ms    300 runs

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

PR Comment: https://git.openjdk.org/jdk/pull/25409#issuecomment-2905450866