Skip to content

Optimize micro_benchmarks execution by limiting dataset metadata scan #339

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
copybara-service merged 1 commit into from
Jun 30, 2026
Merged

Optimize micro_benchmarks execution by limiting dataset metadata scan #339

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 10 additions & 7 deletions xee/micro_benchmarks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@
import ee


REPEAT = 10
REPEAT = 5
LOOPS = 1
PROFILE = False

Expand All @@ -47,21 +47,25 @@ def init_ee_for_tests():
'shape_2d': (1440, 720),
}

_OPEN_KWARGS = {
'engine': xee.EarthEngineBackendEntrypoint,
'n_images': 64, # Limit metadata scan to 64 images to prevent RPC timeouts.
**_GRID_PARAMS,
}


def open_dataset() -> None:
_ = xarray.open_dataset(
'NASA/GPM_L3/IMERG_V06',
engine=xee.EarthEngineBackendEntrypoint,
**_GRID_PARAMS,
**_OPEN_KWARGS,
)


def open_and_chunk() -> None:
ds = xarray.open_dataset(
'NASA/GPM_L3/IMERG_V06',
chunks={'index': 24, 'width': 512, 'height': 512},
engine=xee.EarthEngineBackendEntrypoint,
**_GRID_PARAMS,
**_OPEN_KWARGS,
)
ds.chunk()

Expand All @@ -71,8 +75,7 @@ def open_and_write() -> None:
ds = xarray.open_dataset(
'NASA/GPM_L3/IMERG_V06',
chunks={'time': 24, 'lon': 1440, 'lat': 720},
engine=xee.EarthEngineBackendEntrypoint,
**_GRID_PARAMS,
**_OPEN_KWARGS,
)
ds = ds.isel(time=slice(0, 24))
ds.to_zarr(os.path.join(tmpdir, 'imerg.zarr'))
Expand Down