What happened:
juicefs with redis and minio is very slow in macos
What you expected to happen:
macos performs well
How to reproduce it (as minimally and precisely as possible):
1、juicefs mount --buffer-size 600M --max-uploads 40 redis://:xxx@xx.xx.xx.xx:6379/1 ~/jfs
2、open mount point , there are 40 file in mount point, range from 10MB to 1GB
3、each file operation with 2~5 second delay, like: choose one file, open a file, copy a file
Anything else we need to know?
Environment:
JuiceFS version (use juicefs --version) or Hadoop Java SDK version: juicefs version 1.2.0+2024-06-18.873c47b
Cloud provider or hardware configuration running JuiceFS:
OS (e.g cat /etc/os-release): sonama14.3, M1
Kernel (e.g. uname -a): Darwin Kernel Version 23.3.0: Wed Dec 20 21:30:44 PST 2023
Object storage (cloud provider and region, or self maintained): minio with 4 node, 16 disks
Metadata engine info (version, cloud provider managed or self maintained): redis 5.0.7
Network connectivity (JuiceFS to metadata engine, JuiceFS to object storage): 20Mb
Can you see any slow requests in the logs? The 'stats' and 'profile' commands should help you analyze the specific problem and identify where the issue is occurring.
What happened: juicefs with redis and minio is very slow in macos
What you expected to happen: macos performs well
How to reproduce it (as minimally and precisely as possible): 1、juicefs mount --buffer-size 600M --max-uploads 40 redis://:xxx@xx.xx.xx.xx:6379/1 ~/jfs 2、open mount point , there are 40 file in mount point, range from 10MB to 1GB 3、each file operation with 2~5 second delay, like: choose one file, open a file, copy a file
Anything else we need to know?
Environment:
juicefs --version
) or Hadoop Java SDK version: juicefs version 1.2.0+2024-06-18.873c47bcat /etc/os-release
): sonama14.3, M1uname -a
): Darwin Kernel Version 23.3.0: Wed Dec 20 21:30:44 PST 2023