8321137: Reconsider ICStub alignment #17277

shipilev · 2024-01-05T11:32:03Z

This continues from #16911. It initially started as performance optimization to compact ICStubs, but I think the safety arguments for fitting the ICStub per instruction cache line prevails. See bug and previous PR for more gory details. The footprint improvements on some architectures come as side-effect of untying the ICStub size from CodeEntryAlignment to (sometimes lower) cache line size.

Note that the size of ICStub is important, because ICBuffer is small (10K by default), and its depletion causes the ICBufferFull safepoint. I would make a (separate) argument to bump the default ICBuffer size a bit to make it less important.

Current patch affects ICStub size in different ways on different platforms, since current size is effectively 2xCodeEntryAlignment and new size is cache line size:

ARM32: 32 -> 64 bytes :(
AArch64: 128 -> 64 bytes :)
x86_64: 64 -> 64 bytes :|
x86_32: 32 -> 64 bytes :(
PPC64: 512 -> 128 bytes :))
RISC-V: 128 -> 64 bytes :)
S390X: 128 -> 256 bytes :(
Zero: <not applicable, Zero does not use IC stubs>

Additional testing:

Linux x86_64 server fastdebug, tier{1,2,3,4}
Linux AArch64 server fastdebug, tier{1,2,3,4}

Progress

Change must be properly reviewed (1 review required, with at least 1 Reviewer)
Change must not contain extraneous whitespace
Commit message must refer to an issue

Issue

JDK-8321137: Reconsider ICStub alignment (Enhancement - P4)

Reviewers

Dean Long (@dean-long - Reviewer) ⚠️ Review applies to b0875b50
Erik Österlund (@fisk - Reviewer) ⚠️ Review applies to b0875b50
Martin Doerr (@TheRealMDoerr - Reviewer) ⚠️ Review applies to b0875b50
Fei Yang (@RealFYang - Reviewer)
Andrew Haley (@theRealAph - Reviewer)

Reviewing

Using git

Checkout this PR locally:
$ git fetch https://git.openjdk.org/jdk.git pull/17277/head:pull/17277
$ git checkout pull/17277

Update a local copy of the PR:
$ git checkout pull/17277
$ git pull https://git.openjdk.org/jdk.git pull/17277/head

Using Skara CLI tools

Checkout this PR locally:
$ git pr checkout 17277

View PR using the GUI difftool:
$ git pr show -t 17277

Using diff file

Download this PR as a diff file:
https://git.openjdk.org/jdk/pull/17277.diff

Webrev

Link to Webrev Comment

bridgekeeper · 2024-01-05T11:33:39Z

👋 Welcome back shade! A progress list of the required criteria for merging this PR into master will be added to the body of your pull request. There are additional pull request commands available for use with this pull request.

openjdk · 2024-01-05T11:34:28Z

@shipilev The following label will be automatically applied to this pull request:

hotspot

When this pull request is ready to be reviewed, an "RFR" email will be sent to the corresponding mailing list. If you would like to change these labels, use the /label pull request command.

mlbridge · 2024-01-05T11:40:40Z

Webrevs

src/hotspot/share/code/icBuffer.cpp

dean-long

Nice job minimizing the changes.

openjdk · 2024-01-06T01:15:21Z

@shipilev This change now passes all automated pre-integration checks.

ℹ️ This project also has non-automated pre-integration requirements. Please see the file CONTRIBUTING.md for details.

After integration, the commit message for the final commit will be:

8321137: Reconsider ICStub alignment

Reviewed-by: dlong, eosterlund, mdoerr, fyang, aph

You can use pull request commands such as /summary, /contributor and /issue to adjust it as needed.

At the time when this comment was updated there had been 28 new commits pushed to the master branch:

b891721: 8316756: C2 EA fails with "missing memory path" when encountering unsafe_arraycopy stub call
bf666bc: 8322692: ZGC: avoid over-unrolling due to hidden barrier size
de97c0e: 8290965: PPC64: Implement post-call NOPs
f70667e: 8318112: CSS percentage values are capped at 100%
2063bb8: Merge
bf7bd9a: 8317547: Enhance TLS connection support
c1a568c: 8314307: Improve loop handling
1cc6fbd: 8318588: Windows build failure after JDK-8314468 due to ambiguous call
ed238e8: 8314468: Improve Compiler loops
fac49b8: 8317331: Solaris build failed with "declaration can not follow a statement (E_DECLARATION_IN_CODE)"
... and 18 more: https://git.openjdk.org/jdk/compare/8abaf119659e46684d196bf76784c11587039f60...master

As there are no conflicts, your changes will automatically be rebased on top of these commits when integrating. If you prefer to avoid this automatic rebasing, please check the documentation for the /integrate command for further details.

➡️ To integrate this PR with the above commit message to the master branch, type /integrate in a new comment.

shipilev · 2024-01-15T16:29:12Z

Thanks @dean-long! Any other takers?

Notably, I would like opinions of platform maintainers: @theRealAph, @TheRealMDoerr, @RealFYang, @bulasevich.

TheRealMDoerr · 2024-01-15T16:38:35Z

It's probably good, but are you aware of the plans to remove the ICStubs completely? @fisk may have an opinion on it.

shipilev · 2024-01-15T16:43:27Z

It's probably good, but are you aware of the plans to remove the ICStubs completely? @fisk may have an opinion on it.

Yes, I did x86_32 version for Erik. I think we want something we can support in JDK update releases. I think the ICStub removal would not be backportable at all.

TheRealMDoerr · 2024-01-15T16:46:50Z

Ok. I think it's good for backports. I'll put it in our test queue.

fisk

Seems like a reasonable band-aid to backport. Looks good.

TheRealMDoerr

Test results are good. Thumbs up from my side!

src/hotspot/share/code/icBuffer.hpp

RealFYang

LGTM. Also performed tier1-3 test with fastdebug build on linux-riscv64 platform.

shipilev · 2024-01-17T12:47:38Z

OK, thanks! I am going to merge it, and look for follow-ups, if any.

/integrate

openjdk · 2024-01-17T12:48:39Z

Going to push as commit 7be9f1d.
Since your change was applied there have been 31 commits pushed to the master branch:

b8dafa6: 8323612: IOVecWrapper should be changed to be TerminatingThreadLocal
f2a4ed6: 8323779: Serial: Remove Generation::promotion_attempt_is_safe
22642ff: 8319382: com/sun/jdi/JdwpAllowTest.java shows failures on AIX if prefixLen of mask is larger than 32 in IPv6 case
b891721: 8316756: C2 EA fails with "missing memory path" when encountering unsafe_arraycopy stub call
bf666bc: 8322692: ZGC: avoid over-unrolling due to hidden barrier size
de97c0e: 8290965: PPC64: Implement post-call NOPs
f70667e: 8318112: CSS percentage values are capped at 100%
2063bb8: Merge
bf7bd9a: 8317547: Enhance TLS connection support
c1a568c: 8314307: Improve loop handling
... and 21 more: https://git.openjdk.org/jdk/compare/8abaf119659e46684d196bf76784c11587039f60...master

Your commit was automatically rebased without conflicts.

openjdk · 2024-01-17T12:48:45Z

@shipilev Pushed as commit 7be9f1d.

💡 You may see a message that your pull request was closed with unmerged commits. This can be safely ignored.

Work

c5c6398

shipilev mentioned this pull request Jan 5, 2024

8321137: Relax ICStub alignment #16911

Closed

5 tasks

openjdk bot added the rfr Pull request is ready for review label Jan 5, 2024

openjdk bot added the hotspot hotspot-dev@openjdk.org label Jan 5, 2024

dean-long reviewed Jan 6, 2024

View reviewed changes

src/hotspot/share/code/icBuffer.cpp Show resolved Hide resolved

dean-long approved these changes Jan 6, 2024

View reviewed changes

openjdk bot added the ready Pull request is ready to be integrated label Jan 6, 2024

Inline new_ic_stub

b0875b5

dean-long approved these changes Jan 8, 2024

View reviewed changes

fisk approved these changes Jan 15, 2024

View reviewed changes

TheRealMDoerr approved these changes Jan 16, 2024

View reviewed changes

theRealAph reviewed Jan 16, 2024

View reviewed changes

src/hotspot/share/code/icBuffer.hpp Outdated Show resolved Hide resolved

shipilev added 2 commits January 16, 2024 10:48

Merge branch 'master' into JDK-8321137-reconsider-icstub-align

0d6d8fa

Cautious

d799cbb

RealFYang approved these changes Jan 17, 2024

View reviewed changes

theRealAph approved these changes Jan 17, 2024

View reviewed changes

openjdk bot added the integrated Pull request has been integrated label Jan 17, 2024

openjdk bot closed this Jan 17, 2024

openjdk bot removed ready Pull request is ready to be integrated rfr Pull request is ready for review labels Jan 17, 2024

shipilev deleted the JDK-8321137-reconsider-icstub-align branch January 31, 2024 16:13

8321137: Reconsider ICStub alignment #17277

8321137: Reconsider ICStub alignment #17277

Uh oh!

Conversation

shipilev commented Jan 5, 2024 • edited by openjdk bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Progress

Issue

Reviewers

Reviewing

Webrev

Uh oh!

bridgekeeper bot commented Jan 5, 2024

Uh oh!

openjdk bot commented Jan 5, 2024

Uh oh!

mlbridge bot commented Jan 5, 2024 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Webrevs

Uh oh!

Uh oh!

dean-long left a comment

Choose a reason for hiding this comment

Uh oh!

openjdk bot commented Jan 6, 2024 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

shipilev commented Jan 15, 2024

Uh oh!

TheRealMDoerr commented Jan 15, 2024

Uh oh!

shipilev commented Jan 15, 2024

Uh oh!

TheRealMDoerr commented Jan 15, 2024

Uh oh!

fisk left a comment

Choose a reason for hiding this comment

Uh oh!

TheRealMDoerr left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

RealFYang left a comment

Choose a reason for hiding this comment

Uh oh!

shipilev commented Jan 17, 2024

Uh oh!

openjdk bot commented Jan 17, 2024

Uh oh!

openjdk bot commented Jan 17, 2024

Uh oh!

Uh oh!

shipilev commented Jan 5, 2024 •

edited by openjdk bot

Loading

mlbridge bot commented Jan 5, 2024 •

edited

Loading

openjdk bot commented Jan 6, 2024 •

edited

Loading