apache/celeborn
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[CELEBORN-2057] Bump ap-loader version from 3.0-9 to 4.0-10

Browse Source 
### What changes were proposed in this pull request?

Bump ap-loader version from 3.0-9 to 4.0-10.

### Why are the changes needed?

`ap-loader` has already released v4.0-10, which release note refers to [Loader for 4.0 (v10): Heatmaps and Native memory profiling](https://github.com/jvm-profiling-tools/ap-loader/releases/tag/4.0-10). It should bump version from 3.0-9 to 4.0-10 for `JVMProfiler`.

Backport https://github.com/apache/spark/pull/51257.

### Does this PR introduce _any_ user-facing change?

No.

### How was this patch tested?

Manual test.

Closes #3359 from SteNicholas/CELEBORN-2057.

Authored-by: SteNicholas <programgeek@163.com>
Signed-off-by: mingji <fengmingxiao.fmx@alibaba-inc.com>
This commit is contained in:
SteNicholas 2025-07-10 16:18:28 +08:00 committed by mingji
parent 532cedbfd2
commit cfb4438ade
4 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
dev/deps/dependencies-server
View File

@ -18,7 +18,7 @@
HikariCP/4.0.3//HikariCP-4.0.3.jar
RoaringBitmap/1.0.6//RoaringBitmap-1.0.6.jar
aopalliance-repackaged/2.6.1//aopalliance-repackaged-2.6.1.jar
ap-loader-all/3.0-9//ap-loader-all-3.0-9.jar
ap-loader-all/4.0-10//ap-loader-all-4.0-10.jar
classgraph/4.8.138//classgraph-4.8.138.jar
commons-cli/1.5.0//commons-cli-1.5.0.jar
commons-crypto/1.0.0//commons-crypto-1.0.0.jar

2
docs/developers/jvmprofiler.md
View File

@ -20,7 +20,7 @@ license: |
Since version 0.5.0, Celeborn supports JVM sampling profiler to capture CPU and memory profiles. This article provides a detailed guide of Celeborn `Worker`'s code profiling.
## Worker Code Profiling
The JVM profiler enables code profiling of workers based on the [async profiler](https://github.com/async-profiler/async-profiler/blob/v2.10/README.md), a low overhead sampling profiler.
The JVM profiler enables code profiling of workers based on the [async profiler](https://github.com/async-profiler/async-profiler/blob/v4.0/README.md), a low overhead sampling profiler.
This allows a `Worker` instance to capture CPU and memory profiles for `Worker` which is later analyzed for performance issues.
The profiler captures [Java Flight Recorder (jfr)](https://access.redhat.com/documentation/es-es/red_hat_build_of_openjdk/17/html/using_jdk_flight_recorder_with_red_hat_build_of_openjdk/openjdk-flight-recorded-overview) files for each worker that can be read by tools like Java Mission Control and Intellij etc.
The profiler writes the jfr files to the `Worker`'s working directory in the `Worker`'s local file system and the files can grow to be large,

2
pom.xml
View File

@ -107,7 +107,7 @@
<rocksdbjni.version>9.10.0</rocksdbjni.version>
<jackson.version>2.15.3</jackson.version>
<snappy.version>1.1.10.5</snappy.version>
<ap.loader.version>3.0-9</ap.loader.version>
<ap.loader.version>4.0-10</ap.loader.version>
<picocli.version>4.7.6</picocli.version>
<jmh.version>1.37</jmh.version>

2
project/CelebornBuild.scala
View File

@ -41,7 +41,7 @@ object Dependencies {
val lz4JavaVersion = sparkClientProjects.map(_.lz4JavaVersion).getOrElse("1.8.0")
// Dependent library versions
val apLoaderVersion = "3.0-9"
val apLoaderVersion = "4.0-10"
val commonsCompressVersion = "1.4.1"
val commonsCryptoVersion = "1.0.0"
val commonsIoVersion = "2.17.0"