diff --git a/.github/workflows/master.yml b/.github/workflows/master.yml
index 881e11d5ea..009ebe90dd 100644
--- a/.github/workflows/master.yml
+++ b/.github/workflows/master.yml
@@ -164,7 +164,8 @@ jobs:
     - name: Install R packages
       if: contains(matrix.modules, 'sparkr')
       run: |
-        sudo apt-get install -y libcurl4-openssl-dev
+        # qpdf is required to reduce the size of PDFs to make CRAN check pass. See SPARK-32497.
+        sudo apt-get install -y libcurl4-openssl-dev qpdf
         sudo Rscript -e "install.packages(c('knitr', 'rmarkdown', 'testthat', 'devtools', 'e1071', 'survival', 'arrow', 'roxygen2'), repos='https://cloud.r-project.org/')"
         # Show installed packages in R.
         sudo Rscript -e 'pkg_list <- as.data.frame(installed.packages()[, c(1,3:4)]); pkg_list[is.na(pkg_list$Priority), 1:2, drop = FALSE]'
diff --git a/dev/run-tests.py b/dev/run-tests.py
index 5d8b7a0758..6aae3bdaef 100755
--- a/dev/run-tests.py
+++ b/dev/run-tests.py
@@ -610,8 +610,14 @@ def main():
 
     # Install SparkR
     should_only_test_modules = opts.modules is not None
-    if not should_only_test_modules:
+    test_modules = []
+    if should_only_test_modules:
+        str_test_modules = [m.strip() for m in opts.modules.split(",")]
+        test_modules = [m for m in modules.all_modules if m.name in str_test_modules]
+
+    if not should_only_test_modules or modules.sparkr in test_modules:
         # If tests modules are specified, we will not run R linter.
+        # SparkR needs the manual SparkR installation.
         if which("R"):
             run_cmd([os.path.join(SPARK_HOME, "R", "install-dev.sh")])
         else:
@@ -642,15 +648,11 @@ def main():
           "and Hive profile", hive_version, "under environment", test_env)
     extra_profiles = get_hadoop_profiles(hadoop_version) + get_hive_profiles(hive_version)
 
-    changed_modules = None
-    test_modules = None
-    changed_files = None
+    changed_modules = []
+    changed_files = []
     included_tags = []
     excluded_tags = []
     if should_only_test_modules:
-        str_test_modules = [m.strip() for m in opts.modules.split(",")]
-        test_modules = [m for m in modules.all_modules if m.name in str_test_modules]
-
         # If we're running the tests in Github Actions, attempt to detect and test
         # only the affected modules.
         if test_env == "github_actions":