Comments (3)
Currently, JuiceFS does NOT merge small files together to reduce the PUT calls, because that will slow down future read and make it harder the manage the life cycle of data. We had tried this before, it does not work well, so abandoned.
JuiceFS could cache the small files in your local disk, if you read them frequently. So it can reduce the cost for GET requests.
from juicefs.
Thank you for the quick confirmation.
I understand your comments about making lifecycle management more complicated.
However, S3 supports range-based retrievals. So it should actually be possible to make retrievals across multiple S3 sub-objects faster as you could parallelise the range reads across multiple objects.
from juicefs.
That's true if we disable the compression in JuiceFS. But the caching is still a problem, for example, in order to cache a tiny file, you have to cache all the other files in same 4MB block.
from juicefs.
Related Issues (20)
- clone on a big dir is slow and progress display incorrect.
- debug command can't work with latest mount process
- improve debug command
- count stats error in sync cluster mode.
- Compile v1.1.2 failed on Linux HOT 2
- permission denied in clone
- Allow multiple volume to share a SQL database
- pyxattr test_empty_value failed with meta engine tikv. HOT 2
- fsx test failed on bus error with meta engine tikv HOT 2
- expect .minio.sys has a protection mechanism and cannot be deleted by users
- inode used is incorrect with mysql meta engine. HOT 1
- doc: add info to mount juicefs on boot with cache HOT 3
- If the mount point is abnormal, the debug command cannot obtain the config file HOT 1
- mount process does not exit when mount failed. HOT 1
- do not remove broken cache disk on writeback mode.
- After the cache disk is recovered, write data times out for 5 minutes HOT 1
- S3 Gateway Cannot Be Started by Non-root Users HOT 1
- Make hardcoded fetch 100 each worker user configurable HOT 1
- Size error in fsx test. HOT 2
- fslock test failed. HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from juicefs.