OrangeFS

What OrangeFS is

OrangeFS is a parallel storage system designed for large workloads in high-performance computing, big data, streaming video, genomics, and bioinformatics. Its user-level servers and clients provide parallel access to disks across multiple servers. Configurable file striping and distributed file and directory metadata support this arrangement. OrangeFS offers interfaces for Linux applications, Java JNI, Hadoop HCFS, and WebDAV, as well as optimized MPI-IO for parallel and distributed applications. The listed access methods also include FUSE, a Linux kernel module, and S3. Linux integration is documented through the upstream kernel module; the Linux kernel client has been in the mainline kernel since version 4.6. Other listed clients include native Windows and FUSE modules for Linux and Mac. Security options include capability-based, default, key-based, and certificate-based modes, with LDAP identity mapping available. OrangeFS is free, open-source software under LGPL, with some recent portions also under Apache 2. CloudyCluster offers configurable deployments through Google Cloud and AWS marketplaces. Community, commercial, and research support are available.

Who it suits

OrangeFS suits teams managing large parallel storage workloads, including HPC, big data, streaming video, genomics, or bioinformatics environments. It may also fit users seeking self-hosted storage with multiple client interfaces.

Limits

The open-source release is free. The documentation describes default security as intended for cases where multi-user security is not a priority; other listed modes include key-based and certificate-based security.

Getting started

1. Download the OrangeFS open-source release from the product website.
2. For Linux integration, follow the documentation's recommendation to use the upstream kernel module.
3. Choose an access route such as the direct Linux interface, FUSE, WebDAV, Hadoop HCFS, or MPI-IO.
4. For cloud deployment, use CloudyCluster through Google Cloud or AWS and configure instance count and type, volumes per instance, and filesystem size.
5. Choose a security mode; the default mode is intended for cases where multi-user security is not a priority.

Verdict

OrangeFS combines parallel multi-server storage with multiple application and client interfaces. Its security modes and cloud deployment options are relevant to teams planning large workloads, while the default mode is intended for cases where multi-user security is not a priority.