JuiceFS is an open-source POSIX file system built on top of Redis and object storage (e.g. Amazon S3), designed and optimized for cloud native environment. By using the widely adopted Redis and S3 as the persistent storage, JuiceFS serves as a stateless middleware to enable many applications to share data easily.

The highlighted features are:

• Fully POSIX-compatible: JuiceFS is a fully POSIX-compatible file system. Existing applications can work with it without any change. See pjdfstest result below.
• Outstanding Performance: The latency can be as low as a few milliseconds and the throughput can be expanded to nearly unlimited. See benchmark result below.
• Cloud Native: By utilizing cloud object storage, you can scale storage and compute independently, a.k.a. disaggregated storage and compute architecture.
• Sharing: JuiceFS is a shared file storage that can be read and written by many clients.
• Global File Locks: JuiceFS supports both BSD locks (flock) and POSIX record locks (fcntl).
• Data Compression: By default JuiceFS uses LZ4 to compress all your data, you could also use Zstandard instead.

Architecture | Getting Started | POSIX Compatibility | Performance Benchmark | Supported Object Storage | Status | Roadmap | Reporting Issues | Contributing | Community | Usage Tracking | License | Credits | FAQ

Architecture

JuiceFS relies on Redis to store file system metadata. Redis is a fast, open-source, in-memory key-value data store and very suitable for storing the metadata. All the data will store into object storage through JuiceFS client.

The storage format of one file in JuiceFS consists of three levels. The first level called "Chunk". Each chunk has fixed size, currently it is 64MiB and cannot be changed. The second level called "Slice". The slice size is variable. A chunk may have multiple slices. The third level called "Block". Like chunk, its size is fixed. By default one block is 4MiB and you could modify it when formatting a volume (see following section). At last, the block will be compressed and encrypted (optional) store into object storage.

Getting Started

Precompiled binaries

You can download precompiled binaries from releases page.

Building from source

You need install Go first, then run following commands:

$ git clone https://github.com/juicedata/juicefs.git
$ cd juicefs
$ make

Dependency

A Redis server (>= 2.2) is needed for metadata, please follow Redis Quick Start.

macFUSE is also needed for macOS.

The last one you need is object storage. There are many options for object storage, local disk is the easiest one to get started.

Format a volume

Assume you have a Redis server running locally, we can create a volume called test using it to store metadata:

$ ./juicefs format localhost test

It will create a volume with default settings. If there Redis server is not running locally, the address could be specifed using URL, for example, redis://username:password@host:6379/1.

As JuiceFS relies on object storage to store data, you can specify a object storage using --storage, --bucket, --accesskey and --secretkey. By default, it uses a local directory to serve as an object store, for all the options, please see ./juicefs format -h.

Mount a volume

Once a volume is formated, your can mount it to a directory, which is called mount point.

$ ./juicefs mount -d localhost ~/jfs

After that you can access the volume just like a local directory.

To get all options, just run ./juicefs mount -h.

POSIX Compatibility

JuiceFS passed all of the 8813 tests in latest pjdfstest.

All tests successful.

Test Summary Report
-------------------
/root/soft/pjdfstest/tests/chown/00.t          (Wstat: 0 Tests: 1323 Failed: 0)
  TODO passed:   693, 697, 708-709, 714-715, 729, 733
Files=235, Tests=8813, 233 wallclock secs ( 2.77 usr  0.38 sys +  2.57 cusr  3.93 csys =  9.65 CPU)
Result: PASS

Performance Benchmark

Throughput

Performed a sequential read/write benchmark on JuiceFS, EFS and S3FS by fio, here is the result:

It shows JuiceFS can provide 10X more throughput than the other two, read more details.

Metadata IOPS

Performed a simple mdtest benchmark on JuiceFS, EFS and S3FS by mdtest, here is the result:

It shows JuiceFS can provide significantly more metadata IOPS than the other two, read more details.

Supported Object Storage

• Amazon S3
• Google Cloud Storage
• Azure Blob Storage
• Alibaba Cloud Object Storage Service (OSS)
• Tencent Cloud Object Storage (COS)
• QingStor Object Storage
• Ceph RGW
• MinIO
• Local disk
• Redis

For the detailed list, see juicesync.

Status

It's considered as beta quality, the storage format is not stabilized yet. It's not recommended to deploy it into production environment. Please test it with your use cases and give us feedback.

Roadmap

• Kubernetes CSI driver
• Stabilize storage format
• Hadoop SDK
• S3 gateway
• Windows client
• Encryption at rest
• Other databases for metadata

Reporting Issues

We use GitHub Issues to track community reported issues. You can also contact the community for getting answers.

Contributing

Thank you for your contribution! Please refer to the CONTRIBUTING.md for more information.

Community

Welcome to join the Discussion and the Slack channel to connect with JuiceFS team members and other users.

Usage Tracking

JuiceFS by default collects anonymous usage data. It only collects core metrics (e.g. version number), no user or any sensitive data will be collected. You could review related code here.

These data help us understand how the community is using this project. You could disable reporting easily by command line option --no-usage-report:

$ ./juicefs mount --no-usage-report

License

JuiceFS is open-sourced under GNU AGPL v3.0, see LICENSE.

Credits

The design of JuiceFS was inspired by Google File System, HDFS and MooseFS, thanks to their great work.

FAQ

Why doesn't JuiceFS support XXX object storage?

JuiceFS already supported many object storage, please check the list first. If this object storage is compatible with S3, you could treat it as S3. Otherwise, try reporting issue to juicesync.

Can I use Redis cluster?

The simple answer is no. JuiceFS uses transaction to guarantee the atomicity of metadata operations, which is not well supported in cluster mode.