DAOS (Distributed Asynchronous Object Storage) is a distributed storage platform designed for high-performance computing and data-intensive applications. It provides an object storage architecture optimised for low-latency access and high concurrency across large storage clusters.
The system is designed around persistent memory and NVMe technologies, using a distributed key-value and array storage model rather than relying on a conventional filesystem architecture. Applications can access data directly through native interfaces or use higher-level interfaces that expose familiar storage abstractions.
DAOS supports demanding workloads such as scientific simulations, large-scale data analytics and AI processing. Its asynchronous design allows many storage operations to proceed concurrently, helping applications make efficient use of modern networking and storage hardware.
The project also provides mechanisms for maintaining data integrity, recovering from storage failures and managing information throughout its lifecycle.
This is free and open source software.
Key Features
- Provides distributed object storage with key-value and array interfaces.
- Supports asynchronous, non-blocking storage operations.
- Offers transactional access with multi-version concurrency control.
- Provides a parallel filesystem interface through the DAOS File System (DFS).
- Supports POSIX-style file access using FUSE and I/O interception mechanisms.
- Uses fully distributed metadata to avoid dependence on a central metadata server.
- Supports data protection through replication and erasure coding.
- Provides automatic recovery and rebuilding following storage failures.
- Allows storage protection policies to be configured for different datasets.
- Supports end-to-end data integrity checking.
- Provides native integration with MPI-IO and HDF5 applications.
- Offers connectors for Hadoop, Spark and other data processing frameworks.
- Includes Python interfaces for working with storage objects.
- Supports RDMA-capable network fabrics through libfabric and UCX.
- Provides storage pools and containers for organising datasets and managing access.
Website: github.com/daos-stack/daos
Support:
Developer: DAOS community, Linux Foundation
License: BSD 2-Clause Plus Patent License
DAOS is written in C. Learn C with our recommended free books and free tutorials.
Related Software
| File Systems | |
|---|---|
| HDFS | Distributed file system providing high-throughput access |
| SeaweedFS | Simple and highly scalable distributed file system |
| Lustre | File system for computer clusters |
| CephFS | Unified, distributed storage system |
| Alluxio | Virtual distributed file system |
| GlusterFS | Scale-out NAS file system |
| JuiceFS | Distributed POSIX file system |
| XtreemFS | Object-based, distributed file system for wide area networks |
| MooseFS | POSIX-compliant distributed file system |
| Quantcast File System | High-performance, fault-tolerant, distributed file system |
| OrangeFS | Multi-server scalable parallel file system |
| LeilFS | Distributed POSIX file system |
Read our verdict in the software roundup.
 LinuxLinks helps you discover the best free and open source software for Linux. Explore our extensive collection of recommended applications, including alternatives to popular proprietary software.We also publish software reviews, Linux tutorials, hardware reviews, free programming books and articles covering the wider open source community. Browse our Linux resources to discover more. Know a useful free and open source Linux application we haven't covered? Suggest a program for inclusion. Has your software been featured on LinuxLinks? Display one of our Featured on LinuxLinks badges on your website or GitHub README. |
Please read our Comment Policy before commenting.