From 6dc63ee458cf89c309ea0841b273bb06d7b5a2e7 Mon Sep 17 00:00:00 2001 From: Wei Guo Date: Wed, 19 Feb 2025 10:35:39 +0800 Subject: [PATCH] [SPARK-51239][INFRA] Upgrade Github Action image for `TPCDSQueryBenchmark` from 20.04 to latest ### What changes were proposed in this pull request? This PR aims to upgrade Github Action image for `TPCDSQueryBenchmark` from 20.04 to latest and update the dependency of `databricks/tpcds-kit` to the latest codes. In the past, there were compilation problems in high-version Ubuntu images due to g++ version compatibility issues, but this problem has been solved after this PR: https://github.com/databricks/tpcds-kit/pull/7 ### Why are the changes needed? Refer to: https://github.com/actions/runner-images/issues/11101 > The Ubuntu 20.04 Actions runner image will begin deprecation on 2025-02-01 and will be fully unsupported by 2025-04-01 ![image](https://github.com/user-attachments/assets/db68ec55-f3ca-4a24-aa81-5347c85ec0ed) ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? Manual check on Ubuntu 24.04 and Pass GA. ### Was this patch authored or co-authored using generative AI tooling? No. Closes #49980 from wayneguow/tpcds_inf. Authored-by: Wei Guo Signed-off-by: yangjie01 (cherry picked from commit 0af25b836549dcac530e490681d9090787e35956) Signed-off-by: yangjie01 --- .github/workflows/benchmark.yml | 4 ++-- .github/workflows/build_and_test.yml | 5 ++--- 2 files changed, 4 insertions(+), 5 deletions(-) diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.yml index 161b9140426be..9bfe79cfa2fec 100644 --- a/.github/workflows/benchmark.yml +++ b/.github/workflows/benchmark.yml @@ -68,7 +68,7 @@ jobs: tpcds-1g-gen: name: "Generate an input dataset for TPCDSQueryBenchmark with SF=1" if: contains(inputs.class, 'TPCDSQueryBenchmark') || contains(inputs.class, '*') - runs-on: ubuntu-20.04 + runs-on: ubuntu-latest env: SPARK_LOCAL_IP: localhost steps: @@ -105,7 +105,7 @@ jobs: uses: actions/checkout@v4 with: repository: databricks/tpcds-kit - ref: 2a5078a782192ddb6efbcead8de9973d6ab4f069 + ref: 1b7fb7529edae091684201fab142d956d6afd881 path: ./tpcds-kit - name: Build tpcds-kit if: steps.cache-tpcds-sf-1.outputs.cache-hit != 'true' diff --git a/.github/workflows/build_and_test.yml b/.github/workflows/build_and_test.yml index 8f9d9b459f1aa..47a578c481d11 100644 --- a/.github/workflows/build_and_test.yml +++ b/.github/workflows/build_and_test.yml @@ -1028,8 +1028,7 @@ jobs: needs: precondition if: fromJson(needs.precondition.outputs.required).tpcds-1g == 'true' name: Run TPC-DS queries with SF=1 - # Pin to 'Ubuntu 20.04' due to 'databricks/tpcds-kit' compilation - runs-on: ubuntu-20.04 + runs-on: ubuntu-latest timeout-minutes: 120 env: SPARK_LOCAL_IP: localhost @@ -1079,7 +1078,7 @@ jobs: uses: actions/checkout@v4 with: repository: databricks/tpcds-kit - ref: 2a5078a782192ddb6efbcead8de9973d6ab4f069 + ref: 1b7fb7529edae091684201fab142d956d6afd881 path: ./tpcds-kit - name: Build tpcds-kit if: steps.cache-tpcds-sf-1.outputs.cache-hit != 'true'