Review Comments Fixed

qa/L0_metrics/general_metrics_test.py

@@ -62,25 +62,22 @@ def get_model_load_times():
 def load_model_explicit(model_name, server_url="http://localhost:8000"):
     endpoint = f"{server_url}/v2/repository/models/{model_name}/load"
     response = requests.post(endpoint)
-
-    if response.status_code == 200:
+    try:
+        self.assertEqual(response.status_code, 200)
         print(f"Model '{model_name}' loaded successfully.")
-    else:
-        print(
-            f"Failed to load model '{model_name}'. Status code: {response.status_code}"
-        )
+    except AssertionError:
+        print(f"Failed to load model '{model_name}'. Status code: {response.status_code}")
         print("Response:", response.text)
 
-
 def unload_model_explicit(model_name, server_url="http://localhost:8000"):
     endpoint = f"{server_url}/v2/repository/models/{model_name}/unload"
     response = requests.post(endpoint)
-
-    if response.status_code == 200:
+    try:
+        self.assertEqual(response.status_code, 200)
         print(f"Model '{model_name}' unloaded successfully.")
-    else:
+    except AssertionError:
         print(
-            f"Failed to load model '{model_name}'. Status code: {response.status_code}"
+            f"Failed to unload model '{model_name}'. Status code: {response.status_code}"
         )
         print("Response:", response.text)
 

qa/L0_metrics/test.sh

@@ -143,34 +143,32 @@ run_and_check_server
 # Test 1 for default model control mode (all models loaded at startup)
 python3 -m pytest --junitxml="general_metrics_test.test_metrics_load_time.report.xml" $CLIENT_PY::TestGeneralMetrics::test_metrics_load_time >> $CLIENT_LOG 2>&1
 kill_server
+set -e
 
 set +e
-CLIENT_PY="./general_metrics_test.py"
-CLIENT_LOG="general_metrics_test_client.log"
-SERVER_LOG="general_metrics_test_server.log"
 SERVER_ARGS="$BASE_SERVER_ARGS --model-control-mode=explicit --log-verbose=1"
 run_and_check_server
 MODEL_NAME='libtorch_float32_float32_float32'
-code=`curl -s -w %{http_code} -X POST ${TRITONSERVER_IPADDR}:8000/v2/repository/models/${MODEL_NAME}/load`
+curl -s -w %{http_code} -X POST ${TRITONSERVER_IPADDR}:8000/v2/repository/models/${MODEL_NAME}/load
 # Test 2 for explicit mode LOAD
 python3 -m pytest --junitxml="general_metrics_test.test_metrics_load_time_explicit_load.report.xml" $CLIENT_PY::TestGeneralMetrics::test_metrics_load_time_explicit_load >> $CLIENT_LOG 2>&1
 
-code=`curl -s -w %{http_code} -X POST ${TRITONSERVER_IPADDR}:8000/v2/repository/models/${MODEL_NAME}/unload`
+curl -s -w %{http_code} -X POST ${TRITONSERVER_IPADDR}:8000/v2/repository/models/${MODEL_NAME}/unload
 # Test 3 for explicit mode UNLOAD
 python3 -m pytest --junitxml="general_metrics_test.test_metrics_load_time_explicit_unload.report.xml" $CLIENT_PY::TestGeneralMetrics::test_metrics_load_time_explicit_unload >> $CLIENT_LOG 2>&1
 kill_server
+set -e
 
 # Test 4 for explicit mode LOAD and UNLOAD with multiple versions
 set +e
 CLIENT_PY="./general_metrics_test.py"
-CLIENT_LOG="general_metrics_test_client.log"
-SERVER_LOG="general_metrics_test_server.log"
 VERSION_DIR="${PWD}/version_models"
 SERVER_ARGS="$BASE_SERVER_ARGS --model-repository=${VERSION_DIR} --model-control-mode=explicit --log-verbose=1"
 run_and_check_server
 python3 -m pytest --junitxml="general_metrics_test.test_metrics_load_time_multiple_version_reload.report.xml" $CLIENT_PY::TestGeneralMetrics::test_metrics_load_time_multiple_version_reload >> $CLIENT_LOG 2>&1
 
 kill_server
+set -e
 
 ### Pinned memory metrics tests
 set +e