From 38d039439e391e2be54f7ad82e31bd3faa5b8895 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Isma=C3=ABl=20Mej=C3=ADa?= <iemejia@gmail.com>
Date: Fri, 12 Jun 2026 20:51:38 +0200
Subject: [PATCH 1/2] [SPARK-57420][INFRA] Only generate TPC-DS data when
 required and check CPU compatibility early in benchmark workflow

Two improvements to the benchmark workflow:

1. Skip TPC-DS data generation for non-TPCDS benchmarks. Change
   contains(inputs.class, '*') to inputs.class == '*' so wildcard
   patterns like '*VectorizedDeltaReaderBenchmark' no longer trigger
   the expensive TPC-DS generation job (~5-10 min saved per run).

2. Add early CPU model check step that runs immediately after checkout,
   before compilation. Prints the CPU as a ::notice:: annotation for
   live visibility, and optionally fails fast if the runner CPU does
   not match the expected-cpu input parameter.

Assisted-by: OpenCode:claude-opus-4.6
---
 .github/workflows/benchmark.yml | 25 +++++++++++++++++++++++--
 1 file changed, 23 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.yml
index 3f20752d4b6a5..088c2d240983b 100644
--- a/.github/workflows/benchmark.yml
+++ b/.github/workflows/benchmark.yml
@@ -56,6 +56,11 @@ on:
         description: 'Commit the benchmark results to the current branch'
         required: true
         default: false
+      expected-cpu:
+        type: string
+        description: 'Expected CPU model (e.g. "AMD EPYC 7763"). If set, the job fails early when the runner CPU does not match.'
+        required: false
+        default: ''
 
 jobs:
   matrix-gen:
@@ -73,7 +78,10 @@ jobs:
   # Any TPC-DS related updates on this job need to be applied to tpcds-1g job of build_and_test.yml as well
   tpcds-1g-gen:
     name: "Generate an TPC-DS dataset with SF=1"
-    if: contains(inputs.class, 'TPCDSQueryBenchmark') || contains(inputs.class, 'LZ4TPCDSDataBenchmark') || contains(inputs.class, 'ZStandardTPCDSDataBenchmark') || contains(inputs.class, '*')
+    # Only generate TPC-DS data when running TPC-DS benchmarks or all benchmarks (class == '*').
+    # Use exact equality instead of contains(inputs.class, '*') to avoid matching wildcard
+    # patterns like '*VectorizedDeltaReaderBenchmark' that don't need TPC-DS data.
+    if: contains(inputs.class, 'TPCDSQueryBenchmark') || contains(inputs.class, 'LZ4TPCDSDataBenchmark') || contains(inputs.class, 'ZStandardTPCDSDataBenchmark') || inputs.class == '*'
     runs-on: ubuntu-latest
     env:
       SPARK_LOCAL_IP: localhost
@@ -156,6 +164,19 @@ jobs:
       # In order to get diff files
       with:
         fetch-depth: 0
+    - name: Check CPU model
+      run: |
+        CPU_MODEL=$(grep "model name" /proc/cpuinfo | head -1 | sed 's/model name\s*:\s*//')
+        echo "Runner CPU: $CPU_MODEL"
+        echo "::notice::Runner CPU: $CPU_MODEL"
+        if [ -n "${{ inputs.expected-cpu }}" ]; then
+          if echo "$CPU_MODEL" | grep -qF "${{ inputs.expected-cpu }}"; then
+            echo "CPU matches expected: ${{ inputs.expected-cpu }}"
+          else
+            echo "::error::CPU mismatch! Expected '${{ inputs.expected-cpu }}' but got '$CPU_MODEL'"
+            exit 1
+          fi
+        fi
     - name: Cache SBT and Maven
       uses: actions/cache@v5
       with:
@@ -179,7 +200,7 @@ jobs:
         distribution: zulu
         java-version: ${{ inputs.jdk }}
     - name: Cache TPC-DS generated data
-      if: contains(inputs.class, 'TPCDSQueryBenchmark') || contains(inputs.class, 'LZ4TPCDSDataBenchmark') || contains(inputs.class, 'ZStandardTPCDSDataBenchmark') || contains(inputs.class, '*')
+      if: contains(inputs.class, 'TPCDSQueryBenchmark') || contains(inputs.class, 'LZ4TPCDSDataBenchmark') || contains(inputs.class, 'ZStandardTPCDSDataBenchmark') || inputs.class == '*'
       id: cache-tpcds-sf-1
       uses: actions/cache@v5
       with:

From 1b52da52967335c103899d7d74ea59531ee62cf9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Isma=C3=ABl=20Mej=C3=ADa?= <iemejia@gmail.com>
Date: Mon, 15 Jun 2026 09:18:43 +0200
Subject: [PATCH 2/2] Route expected-cpu input through env variable for shell
 safety

Address review nit: use step-level env block to pass the
inputs.expected-cpu value as a properly-quoted shell variable
instead of template-expanding it directly into the script.

Assisted-by: OpenCode:claude-opus-4.6
---
 .github/workflows/benchmark.yml | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.yml
index 088c2d240983b..40e021d19c88a 100644
--- a/.github/workflows/benchmark.yml
+++ b/.github/workflows/benchmark.yml
@@ -165,15 +165,17 @@ jobs:
       with:
         fetch-depth: 0
     - name: Check CPU model
+      env:
+        EXPECTED_CPU: ${{ inputs.expected-cpu }}
       run: |
         CPU_MODEL=$(grep "model name" /proc/cpuinfo | head -1 | sed 's/model name\s*:\s*//')
         echo "Runner CPU: $CPU_MODEL"
         echo "::notice::Runner CPU: $CPU_MODEL"
-        if [ -n "${{ inputs.expected-cpu }}" ]; then
-          if echo "$CPU_MODEL" | grep -qF "${{ inputs.expected-cpu }}"; then
-            echo "CPU matches expected: ${{ inputs.expected-cpu }}"
+        if [ -n "$EXPECTED_CPU" ]; then
+          if echo "$CPU_MODEL" | grep -qF "$EXPECTED_CPU"; then
+            echo "CPU matches expected: $EXPECTED_CPU"
           else
-            echo "::error::CPU mismatch! Expected '${{ inputs.expected-cpu }}' but got '$CPU_MODEL'"
+            echo "::error::CPU mismatch! Expected '$EXPECTED_CPU' but got '$CPU_MODEL'"
             exit 1
           fi
         fi