-
Notifications
You must be signed in to change notification settings - Fork 12
Open
Labels
benchmark-failureintegration test failedintegration test failed
Description
Benchmark scenario ID: phenology
Benchmark scenario definition: https://github.com/ESA-APEx/apex_algorithms/blob/91426ff33c094b53df24495e4582d2f8937475ce/algorithm_catalog/vito/phenology/benchmark_scenarios/phenology.json
openEO backend: openeofed.dataspace.copernicus.eu
GitHub Actions workflow run: https://github.com/ESA-APEx/apex_algorithms/actions/runs/22905469086
Workflow artifacts: https://github.com/ESA-APEx/apex_algorithms/actions/runs/22905469086#artifacts
Test start: 2026-03-10 13:44:06.476341+00:00
Test duration: 0:08:21.162271
Test outcome: ❌ failed
Last successful test phase: download-reference
Failure in test phase: compare:derived_from-change
Contact Information
| Name | Organization | Contact |
|---|---|---|
| Bram Janssen | VITO | Contact via VITO (VITO Website, GitHub) |
Process Graph
{
"phenology1": {
"arguments": {
"spatial_extent": {
"coordinates": [
[
[
5.179169745059369,
51.24984286550534
],
[
5.170016107999743,
51.25052999567865
],
[
5.171081610725707,
51.24861004739975
],
[
5.178604705735125,
51.246720335821465
],
[
5.179169745059369,
51.24984286550534
]
]
],
"type": "Polygon"
},
"temporal_extent": [
"2022-05-01",
"2022-09-30"
]
},
"namespace": "https://raw.githubusercontent.com/VITObelgium/openeo_algorithm_catalog/refs/heads/main/phenology/openeo_udp/phenology.json",
"process_id": "phenology"
},
"saveresult1": {
"arguments": {
"data": {
"from_node": "phenology1"
},
"format": "GTiff",
"options": {}
},
"process_id": "save_result",
"result": true
}
}Error Logs
scenario = BenchmarkScenario(id='phenology', description='Computes phenology metrics based on the Phenolopy implementation on NDV...home/runner/work/apex_algorithms/apex_algorithms/algorithm_catalog/vito/phenology/benchmark_scenarios/phenology.json'))
connection_factory = <function connection_factory.<locals>.get_connection at 0x7f0374f7dda0>
tmp_path = PosixPath('/home/runner/work/apex_algorithms/apex_algorithms/qa/benchmarks/tmp_path_root/test_run_benchmark_phenology_0')
track_metric = <function track_metric.<locals>.track at 0x7f0374f7dee0>
track_phase = <function track_phase.<locals>.track at 0x7f0374f7e020>
upload_assets_on_fail = <function upload_assets_on_fail.<locals>.collect at 0x7f0374f7e0c0>
request = <FixtureRequest for <Function test_run_benchmark[phenology]>>
@pytest.mark.parametrize(
"scenario",
[
# Use scenario id as parameterization id to give nicer test names.
pytest.param(uc, id=uc.id)
for uc in get_benchmark_scenarios()
],
)
def test_run_benchmark(
scenario: BenchmarkScenario,
connection_factory,
tmp_path: Path,
track_metric,
track_phase,
upload_assets_on_fail,
request,
):
track_metric("scenario_id", scenario.id)
with track_phase(phase="connect"):
# Check if a backend override has been provided via cli options.
override_backend = request.config.getoption("--override-backend")
backend_filter = request.config.getoption("--backend-filter")
if backend_filter and not re.match(backend_filter, scenario.backend):
# TODO apply filter during scenario retrieval, but seems to be hard to retrieve cli param
pytest.skip(
f"skipping scenario {scenario.id} because backend {scenario.backend} does not match filter {backend_filter!r}"
)
backend = scenario.backend
if override_backend:
_log.info(f"Overriding backend URL with {override_backend!r}")
backend = override_backend
connection: openeo.Connection = connection_factory(url=backend)
report_path = None
with track_phase(phase="create-job"):
# TODO #14 scenario option to use synchronous instead of batch job mode?
job = connection.create_job(
process_graph=scenario.process_graph,
title=f"APEx benchmark {scenario.id}",
additional=scenario.job_options,
)
track_metric("job_id", job.job_id)
if request.config.getoption("--upload-benchmark-report"):
report_path = tmp_path / "benchmark_report.json"
report_path.write_text(json.dumps({
"job_id": job.job_id,
"scenario_id": scenario.id,
"scenario_description": scenario.description,
"scenario_backend": scenario.backend,
"scenario_source": str(scenario.source) if scenario.source else None,
"reference_data": scenario.reference_data,
"reference_options": scenario.reference_options,
}, indent=2))
upload_assets_on_fail(report_path)
with track_phase(phase="run-job"):
# TODO: monitor timing and progress
# TODO: separate "job started" and run phases?
max_minutes = request.config.getoption("--maximum-job-time-in-minutes")
if max_minutes:
def _timeout_handler(signum, frame):
raise TimeoutError(
f"Batch job {job.job_id} exceeded maximum allowed time of {max_minutes} minutes"
)
old_handler = signal.signal(signal.SIGALRM, _timeout_handler)
signal.alarm(max_minutes * 60)
try:
job.start_and_wait()
finally:
if max_minutes:
signal.alarm(0)
signal.signal(signal.SIGALRM, old_handler)
with track_phase(phase="collect-metadata"):
collect_metrics_from_job_metadata(job, track_metric=track_metric)
results = job.get_results()
collect_metrics_from_results_metadata(results, track_metric=track_metric)
with track_phase(phase="download-actual"):
# Download actual results
actual_dir = tmp_path / "actual"
paths = results.download_files(target=actual_dir, include_stac_metadata=True)
# Upload assets on failure
upload_assets_on_fail(*paths)
with track_phase(phase="download-reference"):
reference_dir = download_reference_data(
scenario=scenario, reference_dir=tmp_path / "reference"
)
if report_path is not None:
report = json.loads(report_path.read_text())
report["actual_files"] = {
str(p.relative_to(actual_dir)): f"{p.stat().st_size / 1024:.1f} kb"
for p in sorted(actual_dir.rglob("*")) if p.is_file()
}
ref_files = {}
for p in sorted(reference_dir.rglob("*")):
if not p.is_file():
continue
rel = p.relative_to(reference_dir)
size_str = f"{p.stat().st_size / 1024:.1f} kb"
actual_counterpart = actual_dir / rel
if not actual_counterpart.exists():
size_str += " (missing in actual)"
elif actual_counterpart.stat().st_size != p.stat().st_size:
size_str += f" (actual: {actual_counterpart.stat().st_size / 1024:.1f} kb)"
ref_files[str(rel)] = size_str
report["reference_files"] = ref_files
report_path.write_text(json.dumps(report, indent=2))
with track_phase(
phase="compare", describe_exception=analyse_results_comparison_exception
):
# Compare actual results with reference data
> assert_job_results_allclose(
actual=actual_dir,
expected=reference_dir,
tmp_path=tmp_path,
rtol=scenario.reference_options.get("rtol", 1e-3),
atol=scenario.reference_options.get("atol", 1),
pixel_tolerance=scenario.reference_options.get("pixel_tolerance", 1),
)
tests/test_benchmarks.py:146:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
actual = PosixPath('/home/runner/work/apex_algorithms/apex_algorithms/qa/benchmarks/tmp_path_root/test_run_benchmark_phenology_0/actual')
expected = PosixPath('/home/runner/work/apex_algorithms/apex_algorithms/qa/benchmarks/tmp_path_root/test_run_benchmark_phenology_0/reference')
def assert_job_results_allclose(
actual: Union[BatchJob, JobResults, str, Path],
expected: Union[BatchJob, JobResults, str, Path],
*,
rtol: float = _DEFAULT_RTOL,
atol: float = _DEFAULT_ATOL,
pixel_tolerance: float = _DEFAULT_PIXELTOL,
tmp_path: Optional[Path] = None,
):
"""
Assert that two job results sets are equal (with tolerance).
:param actual: actual job results, provided as :py:class:`~openeo.rest.job.BatchJob` object,
:py:meth:`~openeo.rest.job.JobResults` object or path to directory with downloaded assets.
:param expected: expected job results, provided as :py:class:`~openeo.rest.job.BatchJob` object,
:py:meth:`~openeo.rest.job.JobResults` object or path to directory with downloaded assets.
:param rtol: relative tolerance
:param atol: absolute tolerance
:param pixel_tolerance: maximum fraction of pixels (in percent)
that is allowed to be significantly different (considering ``atol`` and ``rtol``)
:param tmp_path: root temp path to download results if needed.
It's recommended to pass pytest's `tmp_path` fixture here
:raises AssertionError: if not equal within the given tolerance
.. versionadded:: 0.31.0
.. warning::
This function is experimental and subject to change.
"""
issues = _compare_job_results(
actual, expected, rtol=rtol, atol=atol, pixel_tolerance=pixel_tolerance, tmp_path=tmp_path
)
if issues:
> raise AssertionError("\n".join(issues))
E AssertionError: File set mismatch: {'job-results.json', 'openEO_2022-05-02Z.tif'} != {'job-results.json', 'openEO.tif'}
E Issues for metadata file 'job-results.json':
E Differing 'derived_from' links (0 common, 61 only in actual, 61 only in expected):
E only in actual: {'S2B_MSIL2A_20220502T103619_N0510_R008_T31UFS_20240609T014539', 'S2B_MSIL2A_20220823T104619_N0510_R051_T31UFS_20240704T163824', 'S2A_MSIL2A_20220626T103641_N0510_R008_T31UFS_20240714T133851', 'S2A_MSIL2A_20220709T105041_N0510_R051_T31UFS_20240708T052543', 'S2A_MSIL2A_20220616T103631_N0510_R008_T31UFS_20240628T163751', 'S2A_MSIL2A_20220808T104631_N0510_R051_T31UFS_20240714T002454', 'S2A_MSIL2A_20220917T104711_N0510_R051_T31UFS_20240726T230442', 'S2A_MSIL2A_20220805T103631_N0510_R008_T31UFS_20240713T000709', 'S2B_MSIL2A_20220731T103629_N0510_R008_T31UFS_20240716T204002', 'S2B_MSIL2A_20220515T104619_N0510_R051_T31UFS_20240610T215024', 'S2A_MSIL2A_20220726T103631_N0510_R008_T31UFS_20240717T031142', 'S2A_MSIL2A_20220510T104621_N0510_R051_T31UFS_20240617T152023', 'S2B_MSIL2A_20220704T104629_N0510_R051_T31UFS_20240702T140539', 'S2B_MSIL2A_20220909T103629_N0510_R008_T31UFS_20240726T161307', 'S2B_MSIL2A_20220912T104629_N0510_R051_T31UFS_20240728T003727', 'S2B_MSIL2A_20220711T103629_N0510_R0...
E only in expected: {'/eodata/Sentinel-2/MSI/L2A_N0500/2022/07/04/S2B_MSIL2A_20220704T104629_N0510_R051_T31UFS_20240702T140539.SAFE', '/eodata/Sentinel-2/MSI/L2A_N0500/2022/06/26/S2A_MSIL2A_20220626T103641_N0510_R008_T31UFS_20240714T133851.SAFE', '/eodata/Sentinel-2/MSI/L2A_N0500/2022/06/09/S2A_MSIL2A_20220609T104631_N0510_R051_T31UFS_20240619T185429.SAFE', '/eodata/Sentinel-2/MSI/L2A_N0500/2022/07/29/S2A_MSIL2A_20220729T104631_N0510_R051_T31UFS_20240718T071744.SAFE', '/eodata/Sentinel-2/MSI/L2A_N0500/2022/08/03/S2B_MSIL2A_20220803T104629_N0510_R051_T31UFS_20240712T060026.SAFE', '/eodata/Sentinel-2/MSI/L2A_N0500/2022/07/01/S2B_MSIL2A_20220701T103629_N0510_R008_T31UFS_20240702T141508.SAFE', '/eodata/Sentinel-2/MSI/L2A_N0500/2022/08/23/S2B_MSIL2A_20220823T104619_N0510_R051_T31UFS_20240704T163824.SAFE', '/eodata/Sentinel-2/MSI/L2A_N0500/2022/05/22/S2B_MSIL2A_20220522T103629_N0510_R008_T31UFS_20240613T093452.SAFE', '/eodata/Sentinel-2/MSI/L2A_N0500/2022/07/14/S2B_MSIL2A_20220714T104629_N0510_R051_T31UFS_20....
/opt/hostedtoolcache/Python/3.12.12/x64/lib/python3.12/site-packages/openeo/testing/results.py:521: AssertionError
----------------------------- Captured stdout call -----------------------------
0:00:00 Job 'cdse-j-2603101344094af0a939841e647a717f': send 'start'
0:00:19 Job 'cdse-j-2603101344094af0a939841e647a717f': created (progress 0%)
0:00:24 Job 'cdse-j-2603101344094af0a939841e647a717f': created (progress 0%)
0:00:32 Job 'cdse-j-2603101344094af0a939841e647a717f': created (progress 0%)
0:00:40 Job 'cdse-j-2603101344094af0a939841e647a717f': created (progress 0%)
0:00:50 Job 'cdse-j-2603101344094af0a939841e647a717f': created (progress 0%)
0:01:02 Job 'cdse-j-2603101344094af0a939841e647a717f': created (progress 0%)
0:01:18 Job 'cdse-j-2603101344094af0a939841e647a717f': queued (progress 0%)
0:01:38 Job 'cdse-j-2603101344094af0a939841e647a717f': queued (progress 0%)
0:02:02 Job 'cdse-j-2603101344094af0a939841e647a717f': queued (progress 0%)
0:02:37 Job 'cdse-j-2603101344094af0a939841e647a717f': queued (progress 0%)
0:03:14 Job 'cdse-j-2603101344094af0a939841e647a717f': running (progress N/A)
0:04:02 Job 'cdse-j-2603101344094af0a939841e647a717f': running (progress N/A)
0:05:01 Job 'cdse-j-2603101344094af0a939841e647a717f': running (progress N/A)
0:06:02 Job 'cdse-j-2603101344094af0a939841e647a717f': running (progress N/A)
0:07:02 Job 'cdse-j-2603101344094af0a939841e647a717f': running (progress N/A)
0:08:06 Job 'cdse-j-2603101344094af0a939841e647a717f': finished (progress 100%)
------------------------------ Captured log call -------------------------------
INFO conftest:conftest.py:145 Connecting to 'openeofed.dataspace.copernicus.eu'
INFO openeo.config:config.py:193 Loaded openEO client config from sources: []
INFO conftest:conftest.py:158 Checking for auth_env_var='OPENEO_AUTH_CLIENT_CREDENTIALS_CDSEFED' to drive auth against url='openeofed.dataspace.copernicus.eu'.
INFO conftest:conftest.py:162 Extracted provider_id='CDSE' client_id='openeo-apex-benchmarks-service-account' from auth_env_var='OPENEO_AUTH_CLIENT_CREDENTIALS_CDSEFED'
INFO openeo.rest.connection:connection.py:302 Found OIDC providers: ['CDSE']
INFO openeo.rest.auth.oidc:oidc.py:404 Doing 'client_credentials' token request 'https://identity.dataspace.copernicus.eu/auth/realms/CDSE/protocol/openid-connect/token' with post data fields ['grant_type', 'client_id', 'client_secret', 'scope'] (client_id 'openeo-apex-benchmarks-service-account')
INFO openeo.rest.connection:connection.py:401 Obtained tokens: ['access_token', 'id_token']
INFO openeo.rest.job:job.py:436 Downloading Job result asset 'openEO_2022-05-02Z.tif' from https://s3.waw3-1.openeo.v1.dataspace.copernicus.eu/openeo-data-prod-waw4-1/batch_jobs/j-2603101344094af0a939841e647a717f/openEO_2022-05-02Z.tif?X-Proxy-Head-As-Get=true&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=306df2895e36493da11fed682eafcc94%2F20260310%2Fwaw4-1%2Fs3%2Faws4_request&X-Amz-Date=20260310T135224Z&X-Amz-Expires=86400&X-Amz-SignedHeaders=host&X-Amz-Security-Token=eyJhbGciOiJSUzI1NiIsInR5cCI6IkpXVCJ9.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.uKcprd9kBk9lYGW4SV5gvUCLiljFXBE0IuH8mD2lzqMVBWRsEBzWdX3n5mBUb2bn-rlQZUpERa69SQhmjI4mcnv_E_djZTFzqvOAhspb7xh_9Wyylu0sW4UcArdubBs7NNDE0YfDmq64rTDGmxvMNGoVQ4eWkjttDj59ePPslIzQbu0_80yZDrVi69CrwHQH8mnFuSHmfROHnk3UqeGV5sAnDPI19Zubo-VH_AKJJ9yMuTZeYTM8R3iEQhc8dLvpeibbAQ5RoQfv9mOCOhJDiJ-S4taEyn5EynJjAnaUs9ZvMMZ2ZSZdt-8MKe-vHpOrMdZTT1uWS67WELeLkBrdRQ&X-Amz-Signature=607698a99c264f33211f7b67667ce81636f26a14fb68efcf2dcbb48fc08d294d to /home/runner/work/apex_algorithms/apex_algorithms/qa/benchmarks/tmp_path_root/test_run_benchmark_phenology_0/actual/openEO_2022-05-02Z.tif
INFO apex_algorithm_qa_tools.scenarios:util.py:345 Downloading reference data for scenario.id='phenology' to reference_dir=PosixPath('/home/runner/work/apex_algorithms/apex_algorithms/qa/benchmarks/tmp_path_root/test_run_benchmark_phenology_0/reference'): start 2026-03-10 13:52:25.976766
INFO apex_algorithm_qa_tools.scenarios:util.py:345 Downloading source='https://s3.waw3-1.cloudferro.com/apex-benchmarks/gh-22018234335!tests_test_benchmarks.py__test_run_benchmark_phenology_!actual/openEO_2022-05-02Z.tif' to path=PosixPath('/home/runner/work/apex_algorithms/apex_algorithms/qa/benchmarks/tmp_path_root/test_run_benchmark_phenology_0/reference/openEO.tif'): start 2026-03-10 13:52:25.977055
INFO apex_algorithm_qa_tools.scenarios:util.py:351 Downloading source='https://s3.waw3-1.cloudferro.com/apex-benchmarks/gh-22018234335!tests_test_benchmarks.py__test_run_benchmark_phenology_!actual/openEO_2022-05-02Z.tif' to path=PosixPath('/home/runner/work/apex_algorithms/apex_algorithms/qa/benchmarks/tmp_path_root/test_run_benchmark_phenology_0/reference/openEO.tif'): end 2026-03-10 13:52:27.009386, elapsed 0:00:01.032331
INFO apex_algorithm_qa_tools.scenarios:util.py:345 Downloading source='https://s3.waw3-1.cloudferro.com/apex-benchmarks/gh-22018234335!tests_test_benchmarks.py__test_run_benchmark_phenology_!actual/job-results.json' to path=PosixPath('/home/runner/work/apex_algorithms/apex_algorithms/qa/benchmarks/tmp_path_root/test_run_benchmark_phenology_0/reference/job-results.json'): start 2026-03-10 13:52:27.009804
INFO apex_algorithm_qa_tools.scenarios:util.py:351 Downloading source='https://s3.waw3-1.cloudferro.com/apex-benchmarks/gh-22018234335!tests_test_benchmarks.py__test_run_benchmark_phenology_!actual/job-results.json' to path=PosixPath('/home/runner/work/apex_algorithms/apex_algorithms/qa/benchmarks/tmp_path_root/test_run_benchmark_phenology_0/reference/job-results.json'): end 2026-03-10 13:52:27.635705, elapsed 0:00:00.625901
INFO apex_algorithm_qa_tools.scenarios:util.py:351 Downloading reference data for scenario.id='phenology' to reference_dir=PosixPath('/home/runner/work/apex_algorithms/apex_algorithms/qa/benchmarks/tmp_path_root/test_run_benchmark_phenology_0/reference'): end 2026-03-10 13:52:27.635886, elapsed 0:00:01.659120
INFO openeo.testing.results:results.py:422 Comparing job results: PosixPath('/home/runner/work/apex_algorithms/apex_algorithms/qa/benchmarks/tmp_path_root/test_run_benchmark_phenology_0/actual') vs PosixPath('/home/runner/work/apex_algorithms/apex_algorithms/qa/benchmarks/tmp_path_root/test_run_benchmark_phenology_0/reference')
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
benchmark-failureintegration test failedintegration test failed