Skip to content

feat(_put_file): dynamically adjust chunksize based on file size #990

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
martindurant merged 3 commits into from
Nov 5, 2025
Merged

feat(_put_file): dynamically adjust chunksize based on file size #990

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
429802e
feat(_put_file): dynamically adjust chunksize based on file size
skshetry Oct 28, 2025
28da31d
extract chunksize calculate logic and add tests
skshetry Nov 5, 2025
b82525b
Merge branch 'main' into dynamic=chunksize
martindurant Nov 5, 2025
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
18 changes: 15 additions & 3 deletions s3fs/core.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,7 @@
import errno
import io
import logging
import math
import mimetypes
import os
import socket
Expand Down Expand Up @@ -69,6 +70,8 @@ def setup_logging(level=None):
ResponseParserError,
)

MAX_UPLOAD_PARTS = 10_000 # maximum number of parts for S3 multipart upload

if ClientPayloadError is not None:
S3_RETRYABLE_ERRORS += (ClientPayloadError,)

Expand Down Expand Up @@ -1230,7 +1233,7 @@ async def _put_file(
lpath,
rpath,
callback=_DEFAULT_CALLBACK,
chunksize=50 * 2**20,
chunksize=None,
max_concurrency=None,
mode="overwrite",
**kwargs,
Expand Down Expand Up @@ -1258,6 +1261,15 @@ async def _put_file(
if content_type is not None:
kwargs["ContentType"] = content_type

if chunksize is None:
chunksize = 50 * 2**20 # default chunksize set to 50 MiB
required_chunks = math.ceil(size / chunksize)
# increase chunksize to fit within the MAX_UPLOAD_PARTS limit
if required_chunks > MAX_UPLOAD_PARTS:
# S3 supports uploading objects up to 5 TiB in size,
# so each chunk can be up to ~524 MiB.
chunksize = math.ceil(size / MAX_UPLOAD_PARTS)

with open(lpath, "rb") as f0:
if size < min(5 * 2**30, 2 * chunksize):
chunk = f0.read()
Expand All @@ -1276,8 +1288,8 @@ async def _put_file(
key,
mpu,
f0,
chunksize,
callback=callback,
chunksize=chunksize,
max_concurrency=max_concurrency,
)
parts = [
Expand Down Expand Up @@ -1305,8 +1317,8 @@ async def _upload_file_part_concurrent(
key,
mpu,
f0,
chunksize,
callback=_DEFAULT_CALLBACK,
chunksize=50 * 2**20,
max_concurrency=None,
):
max_concurrency = max_concurrency or self.max_concurrency
Expand Down
Loading