model-analyzer.txt

root@ip-172-31-1-60:/opt/triton-model-analyzer# rm -r output_model_repository/
root@ip-172-31-1-60:/opt/triton-model-analyzer# ls
CONTRIBUTING.md  Dockerfile  LICENSE  README.md  VERSION  analysis_results  build_wheel.sh  docs  examples  helm-chart  model_analyzer  qa  requirements.txt  setup.py  tests  wheels
root@ip-172-31-1-60:/opt/triton-model-analyzer# model-analyzer -m /quick_start_repository -n add_sub --triton-launch-mode=local --export-path=analysis_results
2021-04-30 22:06:10.93 INFO[entrypoint.py:210] Triton Model Analyzer started: config={'model_repository': '/quick_start_repository', 'model_names': [{'model_name': 'add_sub', 'objectives': {'perf_throughput': 10}, 'parameters': {'batch_sizes': [1], 'concurrency': []}}], 'objectives': {'perf_throughput': 10}, 'constraints': {}, 'batch_sizes': [1], 'concurrency': [], 'perf_analyzer_timeout': 600, 'perf_analyzer_cpu_util': 80.0, 'run_config_search_max_concurrency': 1024, 'run_config_search_max_instance_count': 5, 'run_config_search_disable': False, 'run_config_search_max_preferred_batch_size': 16, 'export': True, 'cpu_only': False, 'export_path': 'analysis_results', 'summarize': True, 'num_configs_per_model': 3, 'num_top_model_configs': 0, 'filename_model_inference': 'metrics-model-inference.csv', 'filename_model_gpu': 'metrics-model-gpu.csv', 'filename_server_only': 'metrics-server-only.csv', 'max_retries': 1000, 'duration_seconds': 5, 'monitoring_interval': 0.01, 'client_protocol': 'grpc', 'perf_analyzer_path': 'perf_analyzer', 'perf_measurement_window': 5000, 'perf_output': False, 'perf_analyzer_flags': {}, 'triton_launch_mode': 'local', 'triton_docker_image': 'nvcr.io/nvidia/tritonserver:21.04-py3', 'triton_http_endpoint': 'localhost:8000', 'triton_grpc_endpoint': 'localhost:8001', 'triton_metrics_url': 'http://localhost:8002/metrics', 'triton_server_path': 'tritonserver', 'triton_output_path': None, 'triton_server_flags': {}, 'log_level': 'INFO', 'gpus': ['all'], 'output_model_repository_path': './output_model_repository', 'override_output_model_repository': False, 'config_file': None, 'inference_output_fields': ['model_name', 'batch_size', 'concurrency', 'model_config_path', 'instance_group', 'dynamic_batch_sizes', 'satisfies_constraints', 'perf_throughput', 'perf_latency', 'cpu_used_ram'], 'gpu_output_fields': ['model_name', 'gpu_id', 'batch_size', 'concurrency', 'model_config_path', 'instance_group', 'dynamic_batch_sizes', 'satisfies_constraints', 'gpu_used_memory', 'gpu_utilization', 'gpu_power_usage'], 'server_output_fields': ['model_name', 'gpu_id', 'gpu_used_memory', 'gpu_utilization', 'gpu_power_usage'], 'plots': [{'name': 'throughput_v_latency', 'title': 'Throughput vs. Latency', 'x_axis': 'perf_latency', 'y_axis': 'perf_throughput', 'monotonic': True}, {'name': 'gpu_mem_v_latency', 'title': 'GPU Memory vs. Latency', 'x_axis': 'perf_latency', 'y_axis': 'gpu_used_memory', 'monotonic': False}]}
2021-04-30 22:06:10.96 INFO[entrypoint.py:96] Starting a local Triton Server...
2021-04-30 22:06:10.96 INFO[analyzer_state_manager.py:109] Loaded checkpoint from file analysis_results/checkpoints/0.ckpt
2021-04-30 22:06:18.858 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:27.559 INFO[server_local.py:81] Triton Server stopped.
2021-04-30 22:06:27.559 INFO[analyzer.py:94] Profiling server only metrics...
2021-04-30 22:06:27.565 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:36.263 INFO[gpu_monitor.py:73] Using GPU(s) with UUID(s) = { GPU-910a5fbb-b7b6-9578-2a1d-7214b1bba733,GPU-ce20e534-f74d-002d-cea1-d8d56845c873,GPU-b346812d-eada-49e7-264e-602cad0884ed,GPU-0b8ce32e-71eb-369b-77ea-45ba6213a908,GPU-df14663d-d7e7-e0e3-84e9-14682a9faddc,GPU-568cfee1-9ecd-99ae-bd59-903adaa1aad6,GPU-40435e07-c0cb-fe8a-1597-598e7317c353,GPU-1b626e27-3cd9-a8c2-ba2d-4c3c5bfb9bc1 } for the analysis.
2021-04-30 22:06:37.353 INFO[server_local.py:81] Triton Server stopped.
2021-04-30 22:06:37.353 INFO[run_search.py:143] Will sweep both the concurrency and model config parameters...
2021-04-30 22:06:37.353 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 1, and dynamic batching is disabled.
2021-04-30 22:06:37.361 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.367 INFO[client.py:82] Model add_sub_i0 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.367 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 2, and dynamic batching is disabled.
2021-04-30 22:06:37.373 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.377 INFO[client.py:82] Model add_sub_i1 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.377 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 3, and dynamic batching is disabled.
2021-04-30 22:06:37.384 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.388 INFO[client.py:82] Model add_sub_i2 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.388 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 4, and dynamic batching is disabled.
2021-04-30 22:06:37.395 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.400 INFO[client.py:82] Model add_sub_i3 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.400 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 5, and dynamic batching is disabled.
2021-04-30 22:06:37.409 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.412 INFO[client.py:82] Model add_sub_i4 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.412 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 1, and dynamic batching is enabled.
2021-04-30 22:06:37.421 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.424 INFO[client.py:82] Model add_sub_i5 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.424 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 2, and dynamic batching is enabled.
2021-04-30 22:06:37.431 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.436 INFO[client.py:82] Model add_sub_i6 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.436 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 3, and dynamic batching is enabled.
2021-04-30 22:06:37.445 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.448 INFO[client.py:82] Model add_sub_i7 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.448 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 4, and dynamic batching is enabled.
2021-04-30 22:06:37.457 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.460 INFO[client.py:82] Model add_sub_i8 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.460 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 5, and dynamic batching is enabled.
2021-04-30 22:06:37.467 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.472 INFO[client.py:82] Model add_sub_i9 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.472 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 1, and preferred batch size is set to 1.
2021-04-30 22:06:37.481 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.485 INFO[client.py:82] Model add_sub_i10 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.485 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 2, and preferred batch size is set to 1.
2021-04-30 22:06:37.494 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.499 INFO[client.py:82] Model add_sub_i11 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.499 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 3, and preferred batch size is set to 1.
2021-04-30 22:06:37.508 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.511 INFO[client.py:82] Model add_sub_i12 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.511 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 4, and preferred batch size is set to 1.
2021-04-30 22:06:37.520 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.523 INFO[client.py:82] Model add_sub_i13 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.523 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 5, and preferred batch size is set to 1.
2021-04-30 22:06:37.531 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.535 INFO[client.py:82] Model add_sub_i14 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.535 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 1, and preferred batch size is set to 2.
2021-04-30 22:06:37.542 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.547 INFO[client.py:82] Model add_sub_i15 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.547 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 2, and preferred batch size is set to 2.
2021-04-30 22:06:37.556 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.559 INFO[client.py:82] Model add_sub_i16 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.559 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 3, and preferred batch size is set to 2.
2021-04-30 22:06:37.568 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.571 INFO[client.py:82] Model add_sub_i17 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.571 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 4, and preferred batch size is set to 2.
2021-04-30 22:06:37.580 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.583 INFO[client.py:82] Model add_sub_i18 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.583 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 5, and preferred batch size is set to 2.
2021-04-30 22:06:37.591 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.596 INFO[client.py:82] Model add_sub_i19 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.596 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 1, and preferred batch size is set to 4.
2021-04-30 22:06:37.605 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.609 INFO[client.py:82] Model add_sub_i20 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.609 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 2, and preferred batch size is set to 4.
2021-04-30 22:06:37.618 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.621 INFO[client.py:82] Model add_sub_i21 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.621 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 3, and preferred batch size is set to 4.
2021-04-30 22:06:37.630 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.633 INFO[client.py:82] Model add_sub_i22 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.633 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 4, and preferred batch size is set to 4.
2021-04-30 22:06:37.642 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.645 INFO[client.py:82] Model add_sub_i23 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.645 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 5, and preferred batch size is set to 4.
2021-04-30 22:06:37.653 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.658 INFO[client.py:82] Model add_sub_i24 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.658 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 1, and preferred batch size is set to 8.
2021-04-30 22:06:37.667 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.671 INFO[client.py:82] Model add_sub_i25 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.671 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 2, and preferred batch size is set to 8.
2021-04-30 22:06:37.679 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.684 INFO[client.py:82] Model add_sub_i26 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.684 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 3, and preferred batch size is set to 8.
2021-04-30 22:06:37.693 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.697 INFO[client.py:82] Model add_sub_i27 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.697 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 4, and preferred batch size is set to 8.
2021-04-30 22:06:37.705 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.709 INFO[client.py:82] Model add_sub_i28 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.709 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 5, and preferred batch size is set to 8.
2021-04-30 22:06:37.716 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.721 INFO[client.py:82] Model add_sub_i29 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.721 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 1, and preferred batch size is set to 16.
2021-04-30 22:06:37.730 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.733 INFO[client.py:82] Model add_sub_i30 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.733 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 2, and preferred batch size is set to 16.
2021-04-30 22:06:37.742 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.746 INFO[client.py:82] Model add_sub_i31 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.746 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 3, and preferred batch size is set to 16.
2021-04-30 22:06:37.755 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.759 INFO[client.py:82] Model add_sub_i32 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.759 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 4, and preferred batch size is set to 16.
2021-04-30 22:06:37.768 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.772 INFO[client.py:82] Model add_sub_i33 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.772 INFO[run_search.py:284] Concurrency set to 1. Instance count set to 5, and preferred batch size is set to 16.
2021-04-30 22:06:37.780 INFO[server_local.py:64] Triton Server started.
2021-04-30 22:06:37.785 INFO[client.py:82] Model add_sub_i34 load failed: [StatusCode.UNAVAILABLE] explicit model load / unload is not allowed if polling is enabled
2021-04-30 22:06:37.785 INFO[analyzer_state_manager.py:140] Saved checkpoint to analysis_results/checkpoints/0.ckpt.
2021-04-30 22:06:37.787 INFO[server_local.py:81] Triton Server stopped.
Traceback (most recent call last):
  File "/usr/local/bin/model-analyzer", line 8, in <module>
    sys.exit(main())
  File "/usr/local/lib/python3.8/dist-packages/model_analyzer/entrypoint.py", line 233, in main
    analyzer.run()
  File "/usr/local/lib/python3.8/dist-packages/model_analyzer/analyzer.py", line 116, in run
    self._result_manager.collect_and_sort_results(
  File "/usr/local/lib/python3.8/dist-packages/model_analyzer/result/result_manager.py", line 309, in collect_and_sort_results
    result_dict = results[model_name]
KeyError: 'add_sub'