[DMS-790] Add performance testing for GetByQuery

src/edfi-paging-test/edfi_paging_test/helpers/main_arguments.py

@@ -4,7 +4,7 @@
 # See the LICENSE and NOTICES files in the project root for more information.
 
 from typing import List
-from dataclasses import dataclass
+from dataclasses import dataclass, field
 
 from edfi_paging_test.helpers.output_format import OutputFormat
 from edfi_paging_test.helpers.log_level import LogLevel
@@ -26,4 +26,4 @@ class MainArguments:
     contentType: OutputFormat
     resourceList: List[str]
     pageSize: int = 100
-    log_level: LogLevel = LogLevel.INFO
+    log_level: LogLevel = LogLevel.INFO

src/edfi-paging-test/edfi_paging_test/performance_tester.py

@@ -86,7 +86,7 @@ async def run(args: MainArguments) -> None:
         request_client: RequestClient = RequestClient(args)
 
         executor: ThreadPoolExecutor = ThreadPoolExecutor(
-            max_workers=args.connectionLimit
+            max_workers=1  # args.connectionLimit TODO AXEL revert
         )
         loop: asyncio.AbstractEventLoop = asyncio.get_event_loop()
 

src/edfi-paging-test/pyproject.toml

@@ -10,13 +10,13 @@ python = "^3.9"
 ConfigArgParse = "^1.5.3"
 python-dotenv = "^0.19.2"
 requests-oauthlib = "^1.3.1"
-requests = "^2.27.1"
-urllib3 = "2.2.2"
+requests = "^2.32.4"
+urllib3 = "^2.5.0"
 pandas = "^1.4.1"
 errorhandler = "^2.0.1"
 numpy = "1.24.3"
 
-[tool.poetry.dev-dependencies]
+[tool.poetry.group.dev.dependencies]
 flake8 = "^4.0.1"
 pytest = "^7.0.1"
 mypy = "^0.931"
@@ -29,10 +29,6 @@ types-requests = "^2.27.12"
 data-science-types = "^0.2.23"
 pyfakefs = "^4.5.5"
 pook = "^1.0.2"
-
-
-
-[tool.poetry.group.dev.dependencies]
 black = "^24.4.2"
 
 [build-system]

src/edfi-performance-test/pyproject.toml

@@ -8,7 +8,7 @@ license = "Apache-2.0"
 [tool.poetry.dependencies]
 python = "^3.9"
 ConfigArgParse = "^1.5.3"
-urllib3 = "2.2.2"
+urllib3 = "^2.5.0"
 pandas = "^1.4.1"
 errorhandler = "^2.0.1"
 python-dotenv = "^0.20.0"
@@ -18,7 +18,7 @@ gevent = "^23.9.1"
 jinja2 = "3.1.3"
 numpy = "1.24.3"
 
-[tool.poetry.dev-dependencies]
+[tool.poetry.group.dev.dependencies]
 flake8 = "^4.0.1"
 pytest = "^7.0.1"
 mypy = "^0.931"

src/edfi-query-test/.coveragerc

@@ -0,0 +1,5 @@
+[run]
+branch = True
+source = edfi_query_test
+
+[report]

src/edfi-query-test/.flake8

@@ -0,0 +1,4 @@
+[flake8]
+max-line-length = 110
+extend-ignore = E203, W503, E501
+exclude = .git, __pycache__, .venv

src/edfi-query-test/.gitignore

@@ -0,0 +1,3 @@
+.coverage
+*.xml
+*.json

src/edfi-query-test/.mypy.ini

@@ -0,0 +1,11 @@
+[mypy]
+files=edfi_query_test, tests
+
+[mypy-errorhandler]
+ignore_missing_imports = True
+
+[mypy-configargparse]
+ignore_missing_imports = True
+
+[mypy-pook]
+ignore_missing_imports = True

src/edfi-query-test/README.md

@@ -0,0 +1,68 @@
+TODO AXEL
+# Query Volume Test
+
+Provides data out performance metrics for the ODS / AP aimed at analysis of
+bottlenecks, and providing recommendations for server sizing for representative
+agency simulation sizes.
+
+## Getting Started
+
+1. Requires Python 3.9+ and Poetry.
+1. Install required Python packages:
+
+   ```bash
+   poetry install
+   ```
+
+## Running the Tool
+
+For detailed help, execute `poetry run python edfi_query_test -h`.
+
+Sample call using full integrated security, loading from the sample files
+directory:
+
+```bash
+poetry run python edfi_query_test -b "https://localhost:54746" -k "testkey" -s "testsecret" -r "resource1" "resource2"
+```
+
+### Supported arguments
+
+| Command Line Argument                | Required                             | Description                                                                                   |
+| ------------------------------------ | ------------------------------------ | --------------------------------------------------------------------------------------------- |
+| `-b` or `--baseUrl`                  | yes (no default)                     | ​The base url used to derived api, metadata, oauth, and dependency urls (e.g., http://server)  |
+| `-k` or `--key`                      | yes (no default)                     | The web API OAuth key                                                                         |
+| `-s` or `--secret`                   | yes (no default)                     | The web API OAuth secret                                                                      |
+| `-i` or `--ignoreCertificateErrors`  | no (default: false)                  | Ignore certificate errors                                                                     |
+| `-c` or `--connectionLimit`          | no (default: 5)                      | Maximum concurrent connections to api                                                         |
+| `-o` or `--output`                   | no (default: out)                    | Directory for writing results                                                                 |
+| `-t` or `--contentType`              | no (default: csv)                    | Output file content type: CSV, JSON                                                           |
+| `-r` or `--resourceList`             | no (no default)                      | (Optional) List of resources to test  - if not provided, all resources will be retrieved      |
+| `-p` or `--pageSize`                 | no (default: 100)                    | The page size to request. Max: 500.                                                           |
+| `-l` or `--logLevel`                 | no (default: INFO)                   | Override the console output log level: VERBOSE, DEBUG, INFO, WARN, ERROR                      |
+| `-d` or `--description`              | no (default: Query Volume Test Run) | Description for the test run                                                                  |
+
+Each argument can also be set by environment variable, or by using as `.env`
+file. See [.env.example](edfi_query_test/.env.example). Arguments provided at
+the command line override any arguments provided by environment variable.
+
+### Resource List
+
+When no resource list is provided, the tool will query the OpenAPI (Swagger)
+metadata to find all available resources, and then retrieve all of them.
+
+To limit to testing specific resources, simply pass the list of resource names
+to be retrieved. For example, `Students StudentSectionAssociations` will return
+only those two resources. To retrieve a resource from an extension, prefix that
+resource with the extension name and a slash. For example:
+`Students tpdm/Candidates` will retrieve all records from the `/ed-fi/Students` and the
+`tpdm/Candidates` endpoints. Note that this is not case sensitive. When using a .env file,
+the argument is set off as an array, e.g.
+`PERF_RESOURCE_LIST=["students", "StudentSchoolAssociations", "tpdm/candidates"]`
+
+### Dev Operations
+
+1. Style check: `poetry run flake8`
+2. Static typing check: `poetry run mypy .`
+3. Run unit tests: `poetry run pytest`
+4. Run unit tests with code coverage: `poetry run coverage run -m pytest tests`
+5. View code coverage: `poetry run coverage report`

src/edfi-query-test/edfi_query_test/.env.example

@@ -0,0 +1,16 @@
+PERF_API_BASEURL=https://example.com/WebAPI/api/
+PERF_API_KEY=yourClientKey
+PERF_API_SECRET=yourClientSecret
+PERF_CONNECTION_LIMIT=6
+PERF_OUTPUT_DIR=test_output
+PERF_CONTENT_TYPE=JSON
+PERF_API_PAGE_SIZE=402
+PERF_LOG_LEVEL=INFO
+
+# Comment out the following line if you want to test _all_ resources Note that
+# resource names are case sensitive and must match the name given in the Ed-Fi
+# API's Open API specification (swagger.json).
+PERF_RESOURCE_LIST="["students", "studentEducationOrganizationAssociations"]"
+
+# Set to true when using HTTP instead of HTTPS or when using self-signed certificates
+IGNORE_TLS_CERTIFICATE=false

src/edfi-query-test/edfi_query_test/__init__.py

@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: Apache-2.0
+# Licensed to the Ed-Fi Alliance under one or more agreements.
+# The Ed-Fi Alliance licenses this file to you under the Apache License, Version 2.0.
+# See the LICENSE and NOTICES files in the project root for more information.

src/edfi-query-test/edfi_query_test/__main__.py

@@ -0,0 +1,70 @@
+# SPDX-License-Identifier: Apache-2.0
+# Licensed to the Ed-Fi Alliance under one or more agreements.
+# The Ed-Fi Alliance licenses this file to you under the Apache License, Version 2.0.
+# See the LICENSE and NOTICES files in the project root for more information.
+
+import asyncio
+import sys
+import logging
+
+from dotenv import load_dotenv
+from errorhandler import ErrorHandler
+
+from edfi_query_test.helpers.argparser import parse_main_arguments
+from edfi_query_test.helpers.main_arguments import MainArguments
+from edfi_query_test.performance_tester import run
+from edfi_query_test.helpers.log_level import LogLevel
+
+
+logger = logging.getLogger(__name__)
+
+
+def _redefine_debug_as_verbose(configuration: MainArguments, logger: str) -> None:
+    requests_logger = logging.getLogger(logger)
+    if configuration.log_level == LogLevel.VERBOSE:
+        requests_logger.setLevel(logging.DEBUG)
+    else:
+        requests_logger.setLevel(logging.INFO)
+
+
+def _configure_logging(configuration: MainArguments) -> None:
+
+    # Verbose is not a real Python log level, so convert back to DEBUG. Verbose
+    # is used for quieting other loggers when in DEBUG mode.
+    log_level = str(LogLevel.DEBUG if configuration.log_level == LogLevel.VERBOSE else configuration.log_level)
+
+    logging.basicConfig(
+        handlers=[
+            logging.StreamHandler(sys.stdout),
+        ],
+        format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
+        level=log_level,
+    )
+
+    # These two loggers produce far more than we really want to see in debug
+    # mode. Therefore we'll redefine _their_ debug modes as "verbose" for our
+    # purposes.
+    _redefine_debug_as_verbose(configuration, "requests_oauthlib.oauth2_session")
+    _redefine_debug_as_verbose(configuration, "urllib3.connectionpool")
+
+
+async def main() -> None:
+    load_dotenv()
+    configuration = parse_main_arguments()
+    _configure_logging(configuration)
+
+    # Important that this comes _after_ the logging configuration
+    error_tracker = ErrorHandler()
+
+    await run(configuration)
+
+    if error_tracker.fired:
+        logger.fatal(
+            "A fatal error occurred, please review the log output for more information."
+        )
+        sys.exit(1)
+    sys.exit(0)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

src/edfi-query-test/edfi_query_test/api/__init__.py

@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: Apache-2.0
+# Licensed to the Ed-Fi Alliance under one or more agreements.
+# The Ed-Fi Alliance licenses this file to you under the Apache License, Version 2.0.
+# See the LICENSE and NOTICES files in the project root for more information.

src/edfi-query-test/edfi_query_test/api/api_info.py

@@ -0,0 +1,31 @@
+# SPDX-License-Identifier: Apache-2.0
+# Licensed to the Ed-Fi Alliance under one or more agreements.
+# The Ed-Fi Alliance licenses this file to you under the Apache License, Version 2.0.
+# See the LICENSE and NOTICES files in the project root for more information.
+
+
+from typing import List, Dict
+from dataclasses import dataclass
+
+
+@dataclass
+class APIInfo:
+    """
+    Container for holding details from api version endpoint
+    """
+
+    version: str
+    datamodels: List[Dict[str, str]]
+    urls: Dict[str, str]
+
+    @property
+    def oauth_url(self) -> str:
+        return self.urls["oauth"]
+
+    @property
+    def api_metadata_url(self) -> str:
+        return self.urls["openApiMetadata"]
+
+    @property
+    def data_management_api_url(self) -> str:
+        return self.urls["dataManagementApi"]