[GH-ISSUE #2616] Slow file reading when disk space is low #1246

New issue

Open

opened 2026-03-04 01:52:32 +03:00 by kerem · 1 comment

kerem commented

2026-03-04 01:52:32 +03:00

Owner

Originally created by @xqc-xiong on GitHub (Dec 9, 2024).
Original GitHub issue: https://github.com/s3fs-fuse/s3fs-fuse/issues/2616

Additional Information

Version of s3fs being used (`s3fs --version`)

1.91

Kernel information (`uname -r`)

ubuntu20.04

GNU/Linux Distribution, if applicable (`cat /etc/os-release`)

How to run s3fs, if applicable

[] command line
[] /etc/fstab

-ouse_cache=/ramdisk -odel_cache -oparallel_count=32 -omultipart_size=50

Details about issue

I encountered a problem when using s3fs. When I used use_cache to specify the use of cache, when the disk space is insufficient, there will be two concurrent reads of the same file. A situation will occur where the data downloaded by one read request is deleted in another read request, resulting in a circular download of data. Only a small part of the data can be read each time, resulting in slow reading. Is there any good solution for this?

Originally created by @xqc-xiong on GitHub (Dec 9, 2024). Original GitHub issue: https://github.com/s3fs-fuse/s3fs-fuse/issues/2616  ### Additional Information #### Version of s3fs being used (`s3fs --version`)  1.91 #### Kernel information (`uname -r`)  ubuntu20.04 #### GNU/Linux Distribution, if applicable (`cat /etc/os-release`)  #### How to run s3fs, if applicable  [] command line [] /etc/fstab  ``` -ouse_cache=/ramdisk -odel_cache -oparallel_count=32 -omultipart_size=50 ``` ### Details about issue  I encountered a problem when using s3fs. When I used use_cache to specify the use of cache, when the disk space is insufficient, there will be two concurrent reads of the same file. A situation will occur where the data downloaded by one read request is deleted in another read request, resulting in a circular download of data. Only a small part of the data can be read each time, resulting in slow reading. Is there any good solution for this?

kerem commented

2026-03-04 01:52:33 +03:00

Author

Owner

@ggtakec commented on GitHub (Jan 19, 2025):

s3fs keeps downloaded files locally.
However, if you run out of disk space, temporary files will be created, resulting in the same problem you're experiencing.
Unfortunately, the only way to avoid this is to delete unnecessary files in the cache directory (ex. periodically), or to point the cache directory to a location with a large amount of disk space.

@ggtakec commented on GitHub (Jan 19, 2025): s3fs keeps downloaded files locally. However, if you run out of disk space, temporary files will be created, resulting in the same problem you're experiencing. Unfortunately, the only way to avoid this is to delete unnecessary files in the cache directory (ex. periodically), or to point the cache directory to a location with a large amount of disk space.