Projects

DragonFly BSD

DragonFly is an operating system and environment originally based on FreeBSD. DragonFly is developing a radically different approach to concurrency, SMP, and most other kernel subsystems. DragonFly belongs to the same class of operating system as BSD and Linux and is based on the same UNIX ideals and APIs.

ceph

Ceph is a distributed network file system designed to provide excellent performance, reliability, and scalability. Ceph fills two significant gaps in the array of currently available file systems: 1. Robust, open-source distributed storage — Ceph is released under the terms of the LGPL ... [More] , which means it is free software (as in speech and beer). Ceph will provide a variety of key features that are generally lacking from existing open-source file systems, including seamless scalability (the ability to simply add disks to expand volumes), intelligent load balancing, and efficient, easy to use snapshot functionality. 2. Scalability — Ceph is built from the ground up to seamlessly and gracefully scale from gigabytes to petabytes and beyond. Scalability is considered in terms of ... [Less]

Lustre

Lustre is a scalable, secure, robust, highly-available cluster file system.

GlusterFS

GlusterFS is a clustered file-system capable of scaling to several peta-bytes. It aggregates various storage bricks over Infiniband RDMA or TCP/IP interconnect into one large parallel network file system. Storage bricks can be made of any commodity hardware such as x86-64 server with SATA-II RAID and Infiniband HBA).

Oracle Linux Cluster Filesystem (OLCF)

Oracle Cluster File System (OCFS) presents a consistent file system image across the servers in a cluster. OCFS allows administrators to take advantage of a files system for the Oracle database files (data files, control files, and archive logs) and configuration files. This eases administration of the Oracle Real Application Clusters.

chironfs

Chiron FS is a FUSE based filesystem which implements replication at the FILESYSTEM LEVEL like RAID 1 does at the DEVICE LEVEL. The replicated filesystems may be of any kind you want the only requisite is that you mount it. No need for special configuration files, the setup is as simple as one mount command (or one line in fstab).

shadowfs

Shadow Filesystem is a high performance distributed filesystem which cluster commodity pc to provide high availbility, data replication file service.

yyfs

It is a very very simple cluster filesystem as my graduation project.

finefs

FineFS is a simple replicated filesystem, which aims to create data clusters. It is designed for web applications, but can be used for any other usage which needs data replication between machines. Data consistency. Writings are atomic. You never get files that are in-modification state. ... [More] Robustness. Using failure detection and retry strategies, temporary shutdowns are managed without data loss. The fully decentralized design avoid any single point of failure. Synchron/asynchron process. Files information are synchronously distributed across the cluster, while binary data are asynchronously replicated. High-performance. Data are eventually replicated on local hard disks, for better optimization of basic operations (data read and write). Easy to deploy and maintain. Based on well-known technics, FineFS is easy to set-up and doesn't need some extended maintenance. Featured documentationPresentation Technical information Architecture design Protocol description How FineFS works: Add a new file, Fetch a file Installation instructions How to develop an application that uses the FineFS PHP library Performance benchmark when FineFS is used as a non-relational database Why use FineFS? For example, you have many frontal web servers. You need to share the same data over all machines. You can set up a file server. But it is a single point of failure. If the file server fall down, you loose all data. You may prefer to use a Storage Area Network. They usually provide some fail-safe mechanisms. But they are also very expensive, and you must set a high-speed link between the SAN and your servers because data are always accessed through the network. You can use an external service like Amazon S3. But it may be a shame to have some empty disk space on your servers, and data access may be really slow. It is possible to set up a distributed filesystem, like Coda, Ceph, POHMELFS, GlusterFS, GfarmFS, Tahoe, Moose FS, Chirp, GFS, ... But these systems may have some technical restrictions or different design goals (like computing grid), and they are hard to install and maintain. FineFS is an easy and convenient mean to create a cluster. Data are accessed locally most of the time, or fetched over the network if necessary. [Less]