From 99f1ea61a09bfdaafec7cf19b8cd2e8f5096612b Mon Sep 17 00:00:00 2001
From: Marko Grujic <markoog@gmail.com>
Date: Wed, 27 Mar 2024 14:19:09 +0100
Subject: [PATCH 1/2] Run TPC-H SF10 during PR benchmarks

---
 .github/workflows/pr_benchmarks.yml | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/.github/workflows/pr_benchmarks.yml b/.github/workflows/pr_benchmarks.yml
index b7b85c9fcf14b..f1c944a8f450f 100644
--- a/.github/workflows/pr_benchmarks.yml
+++ b/.github/workflows/pr_benchmarks.yml
@@ -28,8 +28,9 @@ jobs:
           cd benchmarks
           mkdir data
           
-          # Setup the TPC-H data set with a scale factor of 10
+          # Setup the TPC-H data sets for scale factors 1 and 10
           ./bench.sh data tpch
+          ./bench.sh data tpch10
           
       - name: Generate unique result names
         run: |
@@ -44,6 +45,7 @@ jobs:
           cd benchmarks
 
           ./bench.sh run tpch
+          ./bench.sh run tpch10
           
           # For some reason this step doesn't seem to propagate the env var down into the script
           if [ -d "results/HEAD" ]; then
@@ -64,6 +66,7 @@ jobs:
           cd benchmarks
 
           ./bench.sh run tpch
+          ./bench.sh run tpch10
           
           echo ${{ github.event.issue.number }} > pr
           

From bc5da258add983861d89dc78db825884702cbb04 Mon Sep 17 00:00:00 2001
From: Marko Grujic <markoog@gmail.com>
Date: Wed, 27 Mar 2024 21:40:51 +0100
Subject: [PATCH 2/2] Add memory benchmarks to the workflow

Also distinguish the output file by the SF used.
---
 .github/workflows/pr_benchmarks.yml | 6 +++++-
 benchmarks/bench.sh                 | 4 ++--
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/.github/workflows/pr_benchmarks.yml b/.github/workflows/pr_benchmarks.yml
index f1c944a8f450f..29d001783b17c 100644
--- a/.github/workflows/pr_benchmarks.yml
+++ b/.github/workflows/pr_benchmarks.yml
@@ -31,7 +31,7 @@ jobs:
           # Setup the TPC-H data sets for scale factors 1 and 10
           ./bench.sh data tpch
           ./bench.sh data tpch10
-          
+
       - name: Generate unique result names
         run: |
           echo "HEAD_LONG_SHA=$(git log -1 --format='%H')" >> "$GITHUB_ENV" 
@@ -45,7 +45,9 @@ jobs:
           cd benchmarks
 
           ./bench.sh run tpch
+          ./bench.sh run tpch_mem
           ./bench.sh run tpch10
+          ./bench.sh run tpch_mem10
           
           # For some reason this step doesn't seem to propagate the env var down into the script
           if [ -d "results/HEAD" ]; then
@@ -66,7 +68,9 @@ jobs:
           cd benchmarks
 
           ./bench.sh run tpch
+          ./bench.sh run tpch_mem
           ./bench.sh run tpch10
+          ./bench.sh run tpch_mem10
           
           echo ${{ github.event.issue.number }} > pr
           
diff --git a/benchmarks/bench.sh b/benchmarks/bench.sh
index 039f4790acb0d..a72400892752e 100755
--- a/benchmarks/bench.sh
+++ b/benchmarks/bench.sh
@@ -314,7 +314,7 @@ run_tpch() {
     fi
     TPCH_DIR="${DATA_DIR}/tpch_sf${SCALE_FACTOR}"
 
-    RESULTS_FILE="${RESULTS_DIR}/tpch.json"
+    RESULTS_FILE="${RESULTS_DIR}/tpch_sf${SCALE_FACTOR}.json"
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running tpch benchmark..."
     $CARGO_COMMAND --bin tpch -- benchmark datafusion --iterations 5 --path "${TPCH_DIR}" --format parquet -o ${RESULTS_FILE}
@@ -329,7 +329,7 @@ run_tpch_mem() {
     fi
     TPCH_DIR="${DATA_DIR}/tpch_sf${SCALE_FACTOR}"
 
-    RESULTS_FILE="${RESULTS_DIR}/tpch_mem.json"
+    RESULTS_FILE="${RESULTS_DIR}/tpch_mem_sf${SCALE_FACTOR}.json"
     echo "RESULTS_FILE: ${RESULTS_FILE}"
     echo "Running tpch_mem benchmark..."
     # -m means in memory