Created
January 31, 2022 17:46
-
-
Save oscarknagg/2fb03c71a0a2a928d6aed7ffd8a9ac51 to your computer and use it in GitHub Desktop.
Ray object store performance
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import string | |
import argparse | |
import time | |
import ray | |
import pandas as pd | |
import numpy as np | |
import uuid | |
import os | |
WRITE_DIR = "/tmp/ray_object_store_performance_test/" | |
@ray.remote | |
def write_to_object_store(n=1000, cols=3, use_object_store=True, object_type=pd.DataFrame): | |
df = pd.DataFrame([ | |
{char: float(i) for i, char in enumerate(string.ascii_lowercase[:cols])} | |
] * n) | |
if use_object_store: | |
ref_or_file = ray.put(df) | |
else: | |
ref_or_file = os.path.join(WRITE_DIR, str(uuid.uuid4()) + ".parquet") | |
df.to_parquet(ref_or_file, engine="pyarrow", compression=None) | |
return ref_or_file, df.memory_usage(index=True).sum() | |
@ray.remote | |
def read_from_object_store(ref_or_file): | |
if isinstance(ref_or_file, ray.ObjectRef): | |
df = ray.get(ref_or_file) | |
else: | |
df = pd.read_parquet(ref_or_file) | |
if __name__ == '__main__': | |
"""Description from Alec Zorab: | |
Simultaneously put/get large ( > a few GB) pandas dataframes into object store. | |
100s of workers putting and 100s of workers reading | |
""" | |
parser = argparse.ArgumentParser() | |
parser.add_argument("--use-disk", default=False, action="store_true", help="Use disk instead of object store") | |
parser.add_argument("--num-cpus", type=int, default=2) | |
parser.add_argument("--num-tasks", type=int, default=None) | |
parser.add_argument("--rows", type=int, default=20_000_000) # Works out to a few GB | |
parser.add_argument("--cols", type=int, default=16) | |
parser.add_argument("--do-read", default=False, action="store_true") | |
args = parser.parse_args() | |
args.num_tasks = args.num_tasks or args.num_cpus * 4 | |
ray.init(num_cpus=args.num_cpus, include_dashboard=True, dashboard_host="0.0.0.0") | |
os.makedirs(WRITE_DIR, exist_ok=True) | |
num_concurrent_write_tasks = args.num_cpus // 2 | |
num_concurrent_read_tasks = args.num_cpus - num_concurrent_write_tasks | |
bytes_written = 0 | |
write_results = set() | |
to_read = [] | |
t0 = time.time() | |
for i in range(args.num_tasks): | |
# print(f"i={i}") | |
if len(write_results) >= num_concurrent_write_tasks: | |
num_ready = num_concurrent_write_tasks | |
ready, not_ready = ray.wait(list(write_results), num_returns=num_ready) | |
# print(len(ready), len(not_ready), len(to_read)) | |
t = time.time() | |
for ref in ready: | |
write_results.remove(ref) | |
for df_ref, df_bytes in ray.get(ready): | |
if args.do_read: | |
to_read.append(df_ref) | |
bytes_written += df_bytes | |
print("{:3f}GB/s".format(bytes_written / (1e9 * (t - t0)))) | |
write_results.add(write_to_object_store.remote(n=args.rows, cols=args.cols, use_object_store=not args.use_disk)) |
Author
oscarknagg
commented
Jan 31, 2022
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment