JDK-8361520 : Stabilize SystemGC benchmarks
  • Type: Enhancement
  • Component: hotspot
  • Sub-Component: gc
  • Affected Version: 25
  • Priority: P4
  • Status: Resolved
  • Resolution: Fixed
  • Submitted: 2025-07-07
  • Updated: 2025-08-21
  • Resolved: 2025-07-09
The Version table provides details related to the release that this issue/RFE will be addressed.

Unresolved : Release in which this issue/RFE will be addressed.
Resolved: Release in which this issue/RFE has been resolved.
Fixed : Release in which this issue/RFE has been fixed. The release containing this fix may be available for download as an Early Access Release or a General Availability Release.

To download the current JDK release, click here.
JDK 26
26 b06Fixed
Related Reports
Causes :  
JDK-8325403 - Add SystemGC JMH benchmarks
Relates :  
JDK-8359960 - Regression ~3% on multiple Micros-SystemGC-ZGC only on Mac aarch64
Relates :  
JDK-8343047 - G1: FullGC marking time of large object array unstable between builds
Description
Noticed this while working on a related bug (JDK-8359960):

First, I see the benchmark executes a single shot per fork. As such, I believe the benchmark really tests the cost of initial GC, that probably drags a lot of (potentially non-benchmark-related) objects through new (possibly awkwardly wired, despite +AlwaysPreTouch) memory. The first iteration is 80 ms/op for me here, and the second one is -- whoosh -- only 3 ms/op! Second, and I think that is related, the benchmark is really, really noisy.
Comments
Changeset: a9bd1ad4 Branch: master Author: Aleksey Shipilev <shade@openjdk.org> Date: 2025-07-09 08:56:44 +0000 URL: https://git.openjdk.org/jdk/commit/a9bd1ad40cb4e275d83b2e8b15e3c4be1551f7fc
09-07-2025
A pull request was submitted for review. Branch: master URL: https://git.openjdk.org/jdk/pull/26182 Date: 2025-07-08 09:02:37 +0000
08-07-2025