When running the following, I periodically get MemorySample errors.
I also see this behavior with both query 1 and query 2 from the coiled-runtime benchmark suite.
dask == 2022.9.1
distributed == 2022.9.1
from pathlib import Path
from uuid import uuid1
import coiled
import dask.dataframe as dd
from dask import config
from dask.distributed import Client, performance_report
from distributed.diagnostics import MemorySampler
import pandas as pd
def main():
cluster = coiled.Cluster(
name=f"h2o-benchmarks-{uuid1().hex}",
n_workers=n_workers,
worker_vm_types=["t3.large"], # 2CPU, 8GiB
scheduler_vm_types=["t3.large"],
software="sept-release-arrow-nightly-3"
)
client = Client(cluster)
if client.amm.running() is False:
client.amm.start()
ddf = dd.read_parquet(
"s3://coiled-datasets/h2o-benchmark/N_1e9_K_1e2_parquet/*.parquet",
engine="pyarrow",
)
ms = MemorySampler()
for i in range(5):
try:
client.restart()
print(f"Run {i}")
with ms.sample():
print("starting sample...")
ddf_q3 = (
ddf.groupby("id3", dropna=False)
.agg({"v1": "sum", "v3": "mean"}, split_out=6)
.compute()
)
except Exception as e:
print(f"run failed with {e}")
if __name__ == "__main__"
main()
When running the following, I periodically get
MemorySampleerrors.I also see this behavior with both
query 1andquery 2from thecoiled-runtimebenchmark suite.dask == 2022.9.1distributed == 2022.9.1