JDK-8269040 : Regression ~1.7% in DaCapo-pmd-large after JDK-8264774
  • Type: Bug
  • Component: core-libs
  • Affected Version: 17
  • Priority: P4
  • Status: Closed
  • Resolution: Incomplete
  • Submitted: 2021-06-18
  • Updated: 2021-12-07
  • Resolved: 2021-12-07
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.
Other
tbdResolved
Related Reports
Relates :  
Description
Observed on Mac and Linux.
Comments
Later changes recovered the performance.
07-12-2021

Very odd, given that most of the machinery (if not all) introduced by this patch involves the use of an incubating API, so I doubt that the benchmark is using any of it. The only exception I can think of are the changes to support async IO operations on byte buffers backed by segments - but I don't know off-hand if that might have the impact described here.
21-06-2021

Only two instances of ByteBuffer in two tests in the source code repo for the PMD tool: https://github.com/pmd/pmd/search?q=ByteBuffer In other words, this benchmark is not byte buffer heavy, at least not directly so.
21-06-2021