8372584: [Linux]: Replace reading proc to get thread user CPU time with clock_gettime #28556

JonasNorlinder · 2025-11-28T12:00:28Z

Since kernel v2.6.12 the Linux ABI have had support for encoding the clock types in the last three bits. Setting bit to 001 (CPUCLOCK_VIRT) will result in the kernel returning only user time. POSIX compliant implementations of pthread_getcpuclockid for the Linux kernel defaults to construct a clockid that with 010 (CPUCLOCK_SCHED) set, which return system+user time, which is what the POSIX standard mandates, see POSIX.1-2024/IEEE Std 1003.1-2024 §3.90. This patch joins the family of glibc, musl etc. that utilities this bit pattern.

This PR also results in improved performance and thus a reduced observer effect, especially for the 100th percentile (max).

Before patch:

Benchmark                  Mode      Cnt  Score    Error  Units
CPUTime.execute          sample  7506555  0.008 ±  0.001  ms/op
CPUTime.execute:p0.00    sample           0.008           ms/op
CPUTime.execute:p0.50    sample           0.008           ms/op
CPUTime.execute:p0.90    sample           0.008           ms/op
CPUTime.execute:p0.95    sample           0.008           ms/op
CPUTime.execute:p0.99    sample           0.012           ms/op
CPUTime.execute:p0.999   sample           0.015           ms/op
CPUTime.execute:p0.9999  sample           0.021           ms/op
CPUTime.execute:p1.00    sample           1.030           ms/op

After patch:

Benchmark                  Mode      Cnt   Score    Error  Units
CPUTime.execute          sample  8984189  ≈ 10⁻³           ms/op
CPUTime.execute:p0.00    sample           ≈ 10⁻³           ms/op
CPUTime.execute:p0.50    sample           ≈ 10⁻³           ms/op
CPUTime.execute:p0.90    sample           ≈ 10⁻³           ms/op
CPUTime.execute:p0.95    sample           ≈ 10⁻³           ms/op
CPUTime.execute:p0.99    sample            0.001           ms/op
CPUTime.execute:p0.999   sample            0.001           ms/op
CPUTime.execute:p0.9999  sample            0.006           ms/op
CPUTime.execute:p1.00    sample            0.054           ms/op

Testing: java/lang/management/ThreadMXBean/ThreadUserTime.java and the added microbenchmark.

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-8372584: [Linux]: Replace reading proc to get thread user CPU time with clock_gettime (Enhancement - P4)

Reviewers

Claes Redestad (@cl4es - Reviewer)

Reviewing

Using git

Checkout this PR locally:
$ git fetch https://git.openjdk.org/jdk.git pull/28556/head:pull/28556
$ git checkout pull/28556

Update a local copy of the PR:
$ git checkout pull/28556
$ git pull https://git.openjdk.org/jdk.git pull/28556/head

Using Skara CLI tools

Checkout this PR locally:
$ git pr checkout 28556

View PR using the GUI difftool:
$ git pr show -t 28556

Using diff file

Download this PR as a diff file:
https://git.openjdk.org/jdk/pull/28556.diff

Using Webrev

Link to Webrev Comment

Fixy Remove imports added by IDE Remove imports added by IDE Don't touch bit 3 Fix name

bridgekeeper · 2025-11-28T12:02:14Z

👋 Welcome back jnorlinder! 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 · 2025-11-28T12:03:00Z

@JonasNorlinder 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:

8372584: [Linux]: Replace reading proc to get thread user CPU time with clock_gettime

Reviewed-by: redestad

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 24 new commits pushed to the master branch:

6cb1c8f: 8371864: GaloisCounterMode.implGCMCrypt0 AVX512/AVX2 intrinsics stubs cause AES-GCM encryption failure for certain payload sizes
002fff3: 8220816: (fs) Files.createDirectory should make it more obvious that it fails when the directory already exists
a1cc8f4: 8372444: Genshen: Optimize evacuation function
... and 21 more: https://git.openjdk.org/jdk/compare/08c16c384ac9dac22da960ad718ceb95b41ca660...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.

As you do not have Committer status in this project an existing Committer must agree to sponsor your change. Possible candidates are the reviewers of this PR (@dholmes-ora, @cl4es) but any other Committer may sponsor as well.

➡️ To flag this PR as ready for integration with the above commit message, type /integrate in a new comment. (Afterwards, your sponsor types /sponsor in a new comment to perform the integration).

openjdk · 2025-11-28T12:03:45Z

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

hotspot-runtime

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 · 2025-11-28T12:10:37Z

Webrevs

src/hotspot/os/linux/os_linux.cpp

JonasNorlinder · 2025-11-28T13:08:38Z

/issue add JDK-8210452

openjdk · 2025-11-28T13:09:41Z

@JonasNorlinder
Adding additional issue to issue list: 8210452: getCurrentThreadUserTime is 30x-400x times slower then getCurrentThreadCpuTime.

test/micro/org/openjdk/bench/vm/runtime/CPUTime.java

dholmes-ora · 2025-12-01T04:00:58Z

@JonasNorlinder this PR isn't fixing two issue. I think JDK-8372584 should just be closed as a duplicate of JDK-8210452 (which I had forgotten about and which @larry-cable did not get further with).

dholmes-ora

Overall looks good. I'd forgotten that I found about this in 2018.

A few minor nits.

Can't really comment on the benchmark.

src/hotspot/os/linux/os_linux.cpp

dholmes-ora · 2025-12-01T04:04:19Z

src/hotspot/os/linux/os_linux.cpp

+// set, which return system+user time, which is what the POSIX standard mandates, see
+// POSIX.1-2024/IEEE Std 1003.1-2024 §3.90.
+static clockid_t get_thread_clockid(Thread* thread, bool total, bool* success) {
+  constexpr clockid_t CLOCK_TYPE_MASK = 3;


Shouldn't the mask be covering 3-bits?

No we should not touch bit 3 which encodes if the clock is for a thread of process. See here https://elixir.bootlin.com/linux/v6.17.9/source/include/linux/posix-timers_types.h#L9-L19.

Okay so

encoding the clock types in the last three bits

needs a bit more explanation.

dholmes-ora · 2025-12-01T04:08:23Z

src/hotspot/os/linux/os_linux.cpp

+    // It's possible to encounter a terminated native thread that failed
+    // to detach itself from the VM - which should result in ESRCH.
+    assert_status(rc == ESRCH, rc, "pthread_getcpuclockid failed");
+    *success = false;


The normal way I've seen this pattern used is to set it to true rather than assuming it was true to begin with.

Using a positive outcome like success to encode the outcome make it possible to return like so return success ? os::Linux::thread_cpu_time(clockid) : -1;. I prefer having the -1 at the end as I find this reads easier. If we encode a failure we would need to write return !failure ? os::Linux::thread_cpu_time(clockid) : -1;. Hence, I would prefer keeping this as is as double-negatives may be harder to parse.

Okay but you are setting up a usage requirement without documenting anywhere that that requirement exists.

cl4es

Microbenchmark looks good

JonasNorlinder · 2025-12-01T17:56:26Z

/issue remove JDK-8210452

openjdk · 2025-12-01T17:56:48Z

@JonasNorlinder
Removing additional issue from issue list: 8210452.

dholmes-ora · 2025-12-02T09:24:55Z

src/hotspot/os/linux/os_linux.cpp

+// Since kernel v2.6.12 the Linux ABI has had support for encoding the clock types
+// in the last three bits. Setting bit to 001 (CPUCLOCK_VIRT) will result in the kernel
+// returning only user time. POSIX compliant implementations of pthread_getcpuclockid
+// for the Linux kernel defaults to construct a clockid with 010 (CPUCLOCK_SCHED)
+// set, which return system+user time, which is what the POSIX standard mandates, see
+// POSIX.1-2024/IEEE Std 1003.1-2024 §3.90.


I think the bit encoding could be made somewhat clearer.

// Since kernel v2.6.12 the Linux ABI has had support for encoding the clock types in // the last three bits. Bit 2 indicates whether a cpu clock refers to a thread or a process. // Bits 1 and 0 give the type: PROF=0, VIRT=1, SCHED=2, or FD=3. // The clock CPUCLOCK_VIRT (0b001) reports the thread's consumed user time. // POSIX compliant implementations of pthread_getcpuclockid return the clock CPUCLOCK_SCHED // (0b010) which reports the thread's consumed system+user time (as mandated by the POSIX // standard POSIX.1-2024/IEEE Std 1003.1-2024 §3.90)

dholmes-ora · 2025-12-02T09:26:54Z

src/hotspot/os/linux/os_linux.cpp

+// for the Linux kernel defaults to construct a clockid with 010 (CPUCLOCK_SCHED)
+// set, which return system+user time, which is what the POSIX standard mandates, see
+// POSIX.1-2024/IEEE Std 1003.1-2024 §3.90.
+static clockid_t get_thread_clockid(Thread* thread, bool total, bool* success) {


Suggested change

static clockid_t get_thread_clockid(Thread* thread, bool total, bool* success) {

// The out parameter `success` is required to be initialized to `true`.

static clockid_t get_thread_clockid(Thread* thread, bool total, bool* success) {

assert(success != nullptr && *success, "incorrect initialization");

Replace proc with fast Linux specific solution

b3b74d6

Fixy Remove imports added by IDE Remove imports added by IDE Don't touch bit 3 Fix name

openjdk bot added the hotspot-runtime [email protected] label Nov 28, 2025

JonasNorlinder marked this pull request as ready for review November 28, 2025 12:05

openjdk bot added the rfr Pull request is ready for review label Nov 28, 2025

fandreuz reviewed Nov 28, 2025

View reviewed changes

src/hotspot/os/linux/os_linux.cpp Outdated Show resolved Hide resolved

Add review fixes

52b1c3a

fandreuz reviewed Nov 28, 2025

View reviewed changes

test/micro/org/openjdk/bench/vm/runtime/CPUTime.java Outdated Show resolved Hide resolved

Remove unused imports

c022266

dholmes-ora reviewed Dec 1, 2025

View reviewed changes

JonasNorlinder added 2 commits December 1, 2025 12:48

Fix grammar

a962884

Add fixes from @cl4es review comments

345ba38

cl4es approved these changes Dec 1, 2025

View reviewed changes

openjdk bot added the ready Pull request is ready to be integrated label Dec 1, 2025

dholmes-ora reviewed Dec 2, 2025

View reviewed changes

8372584: [Linux]: Replace reading proc to get thread user CPU time with clock_gettime #28556

Are you sure you want to change the base?

8372584: [Linux]: Replace reading proc to get thread user CPU time with clock_gettime #28556

Conversation

JonasNorlinder commented Nov 28, 2025 • edited by openjdk bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Progress

Issue

Reviewers

Reviewing

Uh oh!

bridgekeeper bot commented Nov 28, 2025

Uh oh!

openjdk bot commented Nov 28, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

openjdk bot commented Nov 28, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

mlbridge bot commented Nov 28, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Webrevs

Uh oh!

Uh oh!

JonasNorlinder commented Nov 28, 2025

Uh oh!

openjdk bot commented Nov 28, 2025

Uh oh!

Uh oh!

dholmes-ora commented Dec 1, 2025

Uh oh!

dholmes-ora left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

cl4es left a comment

Choose a reason for hiding this comment

Uh oh!

JonasNorlinder commented Dec 1, 2025

Uh oh!

openjdk bot commented Dec 1, 2025

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Milestone

Development

Uh oh!

4 participants

JonasNorlinder commented Nov 28, 2025 •

edited by openjdk bot

Loading

openjdk bot commented Nov 28, 2025 •

edited

Loading

openjdk bot commented Nov 28, 2025 •

edited

Loading

mlbridge bot commented Nov 28, 2025 •

edited

Loading