Migrate self-hosted workflows from ubuntu-20.04 to ubuntu-24.04 (#38133)

Author: aIbrahiim

.github/ACTIONS.md

@@ -28,7 +28,7 @@ Currently, we have both GitHub-hosted and self-hosted runners for running the Gi
 ### Getting Started with self-hosted runners
 * Refer to [this README](./gh-actions-self-hosted-runners/README.md) for the steps for creating your own self-hosted runners for testing your workflows.
 * Depending on your workflow's needs, it must specify the following `runs-on` tags to run in the specified operating system:
-  * Ubuntu 20.04 self-hosted runner: `[self-hosted, ubuntu-20.04]`
+  * Ubuntu 24.04 self-hosted runner: `[self-hosted, ubuntu-24.04, main]` (also `small`, `highmem`, or `highmem22` pool labels as needed)
   * Windows Server 2019 self-hosted runner: `[self-hosted, windows-server-2019]`
   * MacOS GitHub-hosted runner: `macos-latest`
 * Every workflow that tests the source code, needs to have the workflow trigger `pull_request_target` instead of `pull_request`.
@@ -48,7 +48,7 @@ Currently, we have both GitHub-hosted and self-hosted runners for running the Gi
       node-version: 16
 ```
 * You can find the GitHub-hosted runner installations in the following links:
-  * [Ubuntu-20.04](https://github.com/actions/runner-images/blob/main/images/linux/Ubuntu2004-Readme.md#installed-apt-packages)
+  * [Ubuntu-24.04](https://github.com/actions/runner-images/blob/main/images/ubuntu/Ubuntu2404-Readme.md#installed-apt-packages)
   * [Windows-2019](https://github.com/actions/runner-images/blob/main/images/win/Windows2019-Readme.md)
 
 #### GitHub Actions Example
@@ -60,7 +60,7 @@ on:
 permissions: read-all
 jobs:
   github-actions-example:
-    runs-on: [self-hosted, ubuntu-20.04]
+    runs-on: [self-hosted, ubuntu-24.04, main]
     steps:
       - name: Check out repository code
         uses: actions/checkout@v2

.github/gh-actions-self-hosted-runners/arc/environments/beam.env

@@ -86,7 +86,7 @@ additional_runner_pools = [{
 {
     name = "highmem-runner-22"
     machine_type = "c3-highmem-22"
-    runner_image = "us-central1-docker.pkg.dev/apache-beam-testing/beam-github-actions/beam-arc-runner:d7cd81a1649bc665581951d2330c4b8acd19ed72"
+    runner_image = "us-central1-docker.pkg.dev/apache-beam-testing/beam-github-actions/beam-arc-runner:latest"
     min_node_count = "0"
     max_node_count = "8"
     min_replicas = "0"
@@ -96,7 +96,7 @@ additional_runner_pools = [{
         cpu = "7.5"
         memory = "100Gi"
     }
-    labels = ["self-hosted", "ubuntu-20.04", "highmem22"]
+    labels = ["self-hosted", "ubuntu-24.04", "highmem22"]
     enable_selector = true
     enable_taint = true
 },

.github/workflows/IO_Iceberg_Integration_Tests.yml

@@ -55,7 +55,7 @@ jobs:
       github.event_name == 'workflow_dispatch' ||
       (github.event_name == 'schedule' && github.repository == 'apache/beam') ||
       github.event.comment.body == 'Run IcebergIO Integration Test'
-    runs-on: [self-hosted, ubuntu-20.04, main]
+    runs-on: [self-hosted, ubuntu-24.04, main]
     timeout-minutes: 120
     name: ${{ matrix.job_name }} (${{ matrix.job_phrase }})
     strategy:

.github/workflows/IO_Iceberg_Integration_Tests_Dataflow.yml

@@ -55,7 +55,7 @@ jobs:
       github.event_name == 'workflow_dispatch' ||
       (github.event_name == 'schedule' && github.repository == 'apache/beam') ||
       github.event.comment.body == 'Run IcebergIO Integration Tests on Dataflow'
-    runs-on: [self-hosted, ubuntu-20.04, main]
+    runs-on: [self-hosted, ubuntu-24.04, main]
     timeout-minutes: 120
     name: ${{ matrix.job_name }} (${{ matrix.job_phrase }})
     strategy:

.github/workflows/IO_Iceberg_Managed_Integration_Tests_Dataflow.yml

@@ -55,7 +55,7 @@ jobs:
       github.event_name == 'workflow_dispatch' ||
       (github.event_name == 'schedule' && github.repository == 'apache/beam') ||
       github.event.comment.body == 'Run IcebergIO Managed Integration Tests on Dataflow'
-    runs-on: [self-hosted, ubuntu-20.04, main]
+    runs-on: [self-hosted, ubuntu-24.04, main]
     timeout-minutes: 120
     name: ${{ matrix.job_name }} (${{ matrix.job_phrase }})
     strategy:

.github/workflows/IO_Iceberg_Performance_Tests.yml

@@ -55,7 +55,7 @@ jobs:
       github.event_name == 'workflow_dispatch' ||
       (github.event_name == 'schedule' && github.repository == 'apache/beam') ||
       github.event.comment.body == 'Run IcebergIO Performance Test'
-    runs-on: [self-hosted, ubuntu-20.04, main]
+    runs-on: [self-hosted, ubuntu-24.04, main]
     timeout-minutes: 120
     name: ${{ matrix.job_name }} (${{ matrix.job_phrase }})
     strategy:

.github/workflows/IO_Iceberg_Unit_Tests.yml

@@ -80,7 +80,7 @@ jobs:
       (github.event_name == 'schedule' && github.repository == 'apache/beam') ||
       github.event_name == 'workflow_dispatch' ||
       github.event.comment.body == 'Run IcebergIO Unit Tests'
-    runs-on: [self-hosted, ubuntu-20.04, main]
+    runs-on: [self-hosted, ubuntu-24.04, main]
     steps:
       - uses: actions/checkout@v4
       - name: Setup repository

.github/workflows/README.md

@@ -91,7 +91,7 @@ And in case when the workflow already utilizes matrix do the following:
 jobs:
   beam_job_with_matrix:
     name: ${{ matrix.job_name }} (${{ matrix.job_phrase }} ${{ matrix.python_version }})
-    runs-on: [self-hosted, ubuntu-20.04, main]
+    runs-on: [self-hosted, ubuntu-24.04, main]
     timeout-minutes: 30
     strategy:
       fail-fast: false
@@ -180,9 +180,9 @@ Note: most workflows use [self-hosted runners](https://docs.github.com/en/action
 with the main and ubuntu labels to execute ([example](https://github.com/apache/beam/blob/5a54ee6ddd8cb8444c41802929a364fe2561001e/.github/workflows/beam_PostCommit_Go_Dataflow_ARM.yml#L41)).
 If you are testing on a fork, you likely will not have self-hosted runners set up.
 To work around this, you can start using hosted runners and then switch over when you're ready to create a PR.
-You can do this by changing `runs-on: [self-hosted, ubuntu-20.04, main]` (self-hosted, use in your PR) to `runs-on: ubuntu-20.04` (GitHub hosted, use for local testing).
+You can do this by changing `runs-on: [self-hosted, ubuntu-24.04, main]` (self-hosted, use in your PR) to `runs-on: ubuntu-24.04` (GitHub hosted, use for local testing).
 
-Note when using `ubuntu-20.04` as the host, you might need to choose the Java version since some gradle tasks only work with a certain Java version.
+Note when using `ubuntu-24.04` as the host, you might need to choose the Java version since some gradle tasks only work with a certain Java version.
 One example is below to use Java 11 when testing your workflow:
 ```
     steps:
@@ -211,7 +211,7 @@ If you run into this issue, you can either:
 
 Additionally, as mentioned above your fork likely will not have self-hosted runners set up.
 To work around this, you can start using hosted runners and then switch over when you're ready to create a PR.
-You can do this by changing runs-on: [self-hosted, ubuntu-20.04, main] (self-hosted, use in your PR) to runs-on: ubuntu-20.04 (GitHub hosted, use for local testing).
+You can do this by changing runs-on: [self-hosted, ubuntu-24.04, main] (self-hosted, use in your PR) to runs-on: ubuntu-24.04 (GitHub hosted, use for local testing).
 
 # Workflows
 Please note that jobs with matrix need to have matrix element in the comment. Example:

.github/workflows/beam_CancelStaleDataflowJobs.yml

@@ -51,7 +51,7 @@ permissions:
 jobs:
   beam_CancelStaleDataflowJobs:
     name: ${{ matrix.job_name }} (${{ matrix.job_phrase }})
-    runs-on: [self-hosted, ubuntu-20.04, main]
+    runs-on: [self-hosted, ubuntu-24.04, main]
     timeout-minutes: 120
     strategy:
       matrix: 

.github/workflows/beam_CleanUpDataprocResources.yml

@@ -51,7 +51,7 @@ jobs:
     if: |
       github.event_name == 'workflow_dispatch' ||
       (github.event_name == 'schedule' && github.repository == 'apache/beam')
-    runs-on: [self-hosted, ubuntu-20.04, main]
+    runs-on: [self-hosted, ubuntu-24.04, main]
     timeout-minutes: 100
     name: "beam_CleanUpDataprocResources"
     steps: