Check for expected benchmark results in integration test (#474)

* lay groundwork for ability to check for expected results in integration test script

* copy expected results from docker container

* fix

* comment out check for now

* update expected results

* comment out changes in verification script

* clippy

benchmarks/run.sh

@@ -15,13 +15,25 @@
 # KIND, either express or implied.  See the License for the
 # specific language governing permissions and limitations
 # under the License.
+
+set -e
 set -x
 
 # This bash script is meant to be run inside the docker-compose environment. Check the README for instructions
 
-#TODO: add queries 15, 16, 19, 20, and 22 once we support them
+# regression checks for queries that return the correct results
+# TODO add all queries once https://github.com/apache/arrow-datafusion/issues/3478 is implemented and once
+# queries return decimal results with the correct precision
+for query in 4 12 13
+do
+  /root/tpch benchmark ballista --host ballista-scheduler --port 50050 --query $query --path /data --format tbl --iterations 1 --debug --expected /data
+done
 
-for query in 1 2 3 4 5 6 7 8 9 10 11 12 13 14 17 18 21
+# at least make sure these queries run, even though we do not check that the results are correct yet
+
+#TODO: add query 16 once we support it
+for query in 1 2 3 5 6 7 8 9 10 11 14 15 17 18 19 20 21 22
 do
   /root/tpch benchmark ballista --host ballista-scheduler --port 50050 --query $query --path /data --format tbl --iterations 1 --debug
 done
+