-
Notifications
You must be signed in to change notification settings - Fork 901
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.
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
Add runner benchmark #4210
base: main
Are you sure you want to change the base?
Add runner benchmark #4210
Changes from 13 commits
98744d5
216cc7a
a4ab4c4
92c7556
e1c4156
06d178d
783b2e8
033237b
0cb6e4f
1b8a7ab
4341284
bc1ec5c
58a70ff
145af85
7e00882
66ad6c5
985a051
0f5a4f0
ddd6a77
4f905b5
515d91c
fdf0fe2
74d24bf
aaa9a3f
b733534
4c9098b
752440b
8ee7dac
05bcd5e
f1a1235
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
This file was deleted.
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,159 @@ | ||
# Write the benchmarking functions here. | ||
# See "Writing benchmarks" in the asv docs for more information. | ||
|
||
from kedro.pipeline import node | ||
from kedro.pipeline.modular_pipeline import pipeline | ||
from kedro.io.data_catalog import DataCatalog | ||
from kedro.runner import SequentialRunner, ThreadRunner, ParallelRunner | ||
import time | ||
import numpy as np | ||
import yaml | ||
import pandas as pd | ||
from kedro.io.memory_dataset import MemoryDataset | ||
from pathlib import Path | ||
|
||
|
||
# Simulate an I/O-bound task | ||
def io_bound_task(input_data): | ||
time.sleep(2) # Simulate an I/O wait (e.g., reading from a file) | ||
output = input_data | ||
return output | ||
|
||
|
||
# Simulate a compute-bound task (matrix multiplication) | ||
def compute_bound_task(input_data) -> str: | ||
# Simulate heavy compute that are not using multicore (not pandas/numpy etc) | ||
ans = 1 | ||
for i in range(1, 50000): | ||
ans = ans * i | ||
return "dummy" | ||
|
||
|
||
def create_data_catalog(): | ||
""" | ||
Use dataset factory pattern to make sure the benchmark cover the slowest path. | ||
""" | ||
catalog_conf = """ | ||
|
||
'output_{pattern}': | ||
type: pandas.CSVDataset | ||
filepath: benchmarks/data/'{pattern}.csv' | ||
|
||
'numpy_{pattern}': | ||
type: pickle.PickleDataset | ||
filepath: benchmarks/data/'{pattern}.pkl' | ||
|
||
'{catch_all_dataset_pattern}': | ||
type: pandas.CSVDataset | ||
filepath: benchmarks/data/data.csv | ||
""" | ||
catalog_conf = yaml.safe_load(catalog_conf) | ||
catalog = DataCatalog.from_config(catalog_conf) | ||
return catalog | ||
|
||
|
||
def create_io_bound_node(inputs=None, outputs=None, name=None): | ||
io_node = node(io_bound_task, inputs=inputs, outputs=outputs, name=name) | ||
return io_node | ||
|
||
|
||
def create_io_bound_pipeline(): | ||
dummy_pipeline = pipeline( | ||
[ | ||
create_io_bound_node("dummy_1", "output_1"), | ||
create_io_bound_node("dummy_2", "output_2"), | ||
create_io_bound_node("dummy_3", "output_3"), | ||
create_io_bound_node("dummy_4", "output_4"), | ||
create_io_bound_node("dummy_5", "output_5"), | ||
create_io_bound_node("dummy_6", "output_6"), | ||
create_io_bound_node("dummy_7", "output_7"), | ||
create_io_bound_node("dummy_1", "output_8"), | ||
create_io_bound_node("dummy_1", "output_9"), | ||
create_io_bound_node("dummy_1", "output_10"), | ||
] | ||
) | ||
return dummy_pipeline | ||
|
||
|
||
def create_compute_bound_node(inputs=None, outputs=None, name=None): | ||
io_node = node(compute_bound_task, inputs=inputs, outputs=outputs, name=name) | ||
return io_node | ||
|
||
|
||
def create_compute_bound_pipeline(): | ||
dummy_pipeline = pipeline( | ||
[ | ||
create_compute_bound_node("dummy_1", "numpy_1"), | ||
create_compute_bound_node("dummy_2", "numpy_2"), | ||
create_compute_bound_node("dummy_3", "numpy_3"), | ||
create_compute_bound_node("dummy_4", "numpy_4"), | ||
create_compute_bound_node("dummy_5", "numpy_5"), | ||
create_compute_bound_node("dummy_6", "numpy_6"), | ||
create_compute_bound_node("dummy_7", "numpy_7"), | ||
create_compute_bound_node("dummy_1", "numpy_8"), | ||
create_compute_bound_node("dummy_1", "numpy_9"), | ||
create_compute_bound_node("dummy_1", "numpy_10"), | ||
] | ||
) | ||
return dummy_pipeline | ||
|
||
|
||
class RunnerMemorySuite: | ||
params = [SequentialRunner, ThreadRunner, ParallelRunner] | ||
param_names = ["runner"] | ||
|
||
def setup(self, *args, **kwargs): | ||
data_dir = Path("benchmarks/data") | ||
data_dir.mkdir(exist_ok=True, parents=True) | ||
|
||
# Create a dummy csv | ||
with open(data_dir / "data.csv", "w") as f: | ||
f.write("col1,col2\n1,2\n") | ||
|
||
def mem_runners(self, runner): | ||
catalog = create_data_catalog() | ||
test_pipeline = create_compute_bound_pipeline() | ||
runner_obj = runner() | ||
runner_obj.run(test_pipeline, catalog=catalog) | ||
|
||
def peakmem_runners(self, runner): | ||
catalog = create_data_catalog() | ||
test_pipeline = create_compute_bound_pipeline() | ||
runner_obj = runner() | ||
runner_obj.run(test_pipeline, catalog=catalog) | ||
|
||
|
||
class RunnerTimeSuite: | ||
def setup(self, *args, **kwargs): | ||
data_dir = Path("benchmarks/data") | ||
data_dir.mkdir(exist_ok=True, parents=True) | ||
|
||
# Create a dummy csv | ||
with open(data_dir / "data.csv", "w") as f: | ||
f.write("col1,col2\n1,2\n") | ||
|
||
def time_sequential_runner(self): | ||
catalog = create_data_catalog() | ||
test_pipeline = create_compute_bound_pipeline() | ||
runner_obj = SequentialRunner() | ||
runner_obj.run(test_pipeline, catalog=catalog) | ||
|
||
def time_parallel_runner(self): | ||
"""compute bound pipeline""" | ||
catalog = create_data_catalog() | ||
test_pipeline = create_compute_bound_pipeline() | ||
runner_obj = ParallelRunner() | ||
runner_obj.run(test_pipeline, catalog=catalog) | ||
|
||
def time_thread_runner(self): | ||
"""IO bound pipeline""" | ||
catalog = create_data_catalog() | ||
test_pipeline = create_io_bound_pipeline() | ||
runner_obj = ThreadRunner() | ||
runner_obj.run(test_pipeline, catalog=catalog) | ||
|
||
|
||
if __name__ == "__main__": | ||
ankatiyar marked this conversation as resolved.
Show resolved
Hide resolved
|
||
suite = RunnerSuite() | ||
for param in suite.params: | ||
suite.time_runners(param) |
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,15 @@ | ||
[project] | ||
name = "kedro_benchmarks" | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. The reason to do this is To make sure this always in I have tried |
||
version = "0.1.0" | ||
description = "Default template for PDM package" | ||
authors = [ | ||
{name = "Nok Lam Chan", email = "nok.lam.chan@quantumblack.com"}, | ||
] | ||
dependencies = [] | ||
requires-python = ">=3.9.0" | ||
readme = "README.md" | ||
license = {text = "MIT"} | ||
|
||
|
||
[tool.pdm] | ||
distribution = false |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Need to revert before merge.