RFR: 8322484: 22-b26 Regression in J2dBench-bimg_misc-G1 (and more) on Windows-x64 and macOS-x64 [v3]

[Kim Barrett]

On Fri, 26 Jan 2024 14:03:57 GMT, Thomas Schatzl <tschatzl at openjdk.org> wrote:

>> Hi all,
>> 
>>   please review this improvement to managing region pin counts in g1.
>> 
>> Some applications do millions of `Get/ReleasePrimitiveArrayCritical` operations per second, in particular some of the j2dbench benchmarks (e.g. vimg_copyarea 10M/s), on some platforms. Every pin/unpin results in an atomic operation that is the cause for these slowdown. 
>> 
>> Only Windows seems to be significantly affected.
>> 
>> This suggested change implements a per-region thread local cache storing the current pin/unpin refcount difference, writing it back only when a thread pins/unpin an object in a different region.
>> 
>> For these benchmarks this often reduces the amount of atomic operations to none, or a few handful; the worst improvement I have seen is that effective atomic operations were reduced to 1/10th. Overall all the j2dbench benchmark scores improve.
>> 
>> There is a remaining issue with the `vimg_shapes_gradient` J2dbench subbenchmark: comparing the original results (before integration of region pinning) with latest jdk23 results, there is a regression of about 5%; this is caused by the backout of a bad compiler change (https://bugs.openjdk.org/browse/JDK-8322985). This will be fixed by its redo CR https://bugs.openjdk.org/browse/JDK-8323116.
>> 
>> Testing: tier1-3, j2dbench, dacapo, specj*, renaissance benchmarks
>> 
>> Thanks,
>>   Thomas
>
> Thomas Schatzl has updated the pull request incrementally with one additional commit since the last revision:
> 
>   remove whitespace

One minor nit in comment.  Otherwise looks good.

src/hotspot/share/gc/g1/g1RegionPinCache.hpp line 36:

> 34: // Keeping such a cache avoids the expensive atomic operations when updating the
> 35: // pin count for the very common case that the application pins and unpins the
> 36: // same object with any interleaving by a garbage collection or pinning/unpinning

s/with/without/

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

Marked as reviewed by kbarrett (Reviewer).

PR Review: https://git.openjdk.org/jdk/pull/17552#pullrequestreview-1845865112
PR Review Comment: https://git.openjdk.org/jdk/pull/17552#discussion_r1467722389