Align RAM Class Sub4G allocation increment with J9Class #22649
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@mpirvu Could you verify if this change mitigates or resolves the startup regression reported in #22530 (comment)? fyi @tajila |
|
Unfortunately, this change makes the startup time 5x worse. |
tajila
reviewed
Sep 24, 2025
babsingh
force-pushed
the
main8
branch
2 times, most recently
from
03a5e70 to
11536e5
Compare
babsingh
force-pushed
the
main8
branch
2 times, most recently
from
8b6a0d1 to
00c5056
Compare
babsingh
changed the title
|
@tajila This PR is ready to be reviewed; it resolves the perf regression reported in javanext #548. |
tajila
reviewed
Oct 15, 2025
runtime/gc_modron_startup/mminit.cpp
Outdated
|
|
||
| UDATA alignToJ9Class = sizeof(J9Class); | ||
| /* Round to the nearest multiple of sizeof(J9Class). */ | ||
| javaVM->ramClassSub4GAllocationIncrement = ((javaVM->ramClassAllocationIncrement + alignToJ9Class - 1) / alignToJ9Class) * alignToJ9Class; |
There was a problem hiding this comment.
We can’t use the bitmask-version of the ROUND_TO macro currently defined in mminit.cpp, since it only works when the granularity (alignment) is a power of 2. I added a modulo-based variant in mminit.cpp and used it for ramClassSub4GAllocationIncrement, as sizeof(J9Class) is not a power of 2.
Aligning the RAM Class Sub4G allocation increment with J9Class improves both startup performance and memory footprint. Recent performance measurements showed the best results when the increment size was aligned with the default -Xmca value of 32 KB. Signed-off-by: Babneet Singh <[email protected]>
|
jenkins test sanity alinux64 jdk21 |
|
jenkins test sanity.functional win jdk11 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Aligning the RAM Class Sub4G allocation increment with
J9Classimproves both startup performance and memory footprint.
Recent performance measurements showed the best results when the
increment size was aligned with the default
-Xmcavalue of32 KB.