Hados stores files in a cluster of servers. Its goal is to handle high availability by storing copies of the same file on several nodes. It provides RESTFUL APIs to easily store, check, or retrieve files. Using the cluster APIs, you can retrieve files from whichever node hosts them. To avoid any single point of failure, it is possible to apply a request to any node of the cluster; there is no master node.
Collax V-Cube+ is a HA cluster management suite based on a 64bit Linux system and KVM to provide server virtualization. It offers solutions for single virtualization hosts, as well as high availability management on two or more nodes, allowing embedded HA storage using DRBD and iSCSI. By using live snapshots, automatic live migration, and incremental backups, the availability of virtual machines is increased tremendously in case of hardware and software maintenance or even hardware failures. Virtual network switches and the protocols GVRP, LLDP, and RSTP help to set up a virtual DMZ.
Libfairydust is a small wrapper library intended for use with GPU clusters that 'hijacks' CUDA and OpenCL calls. It can be used to 're-route' calls to a certain GPU, so a process requesting GPU#0 might end up running on GPU#4 without knowing (or caring) about it. This works completely transparently and does not need any sort of 'cooperation' from the application, changes to code, or relinking.
Gossimon is a gossip-based distributed monitoring system for a cluster of Linux nodes. Each node in the cluster periodically send information about itself and others to a randomly selected node. This way, each node constantly receives information about cluster nodes. This information is locally maintained (constantly updated) by each node and can be used by various clients for monitoring and resource allocation. The gossip protocols used by gossimon are very robust to node failure, and the information quality is hardly degraded even when large parts of the cluster are taken down. The package contains: infod (the daemon responsible for collecting and sending information for other nodes); mmon (a curses-based monitoring client displaying information about cluster nodes); and infod-client (a command-line client that retrieves cluster information in XML format).
Makeflow is a workflow engine for executing large complex applications on clusters, clouds, and grids. It can be used to drive several different distributed computing systems, including Condor, SGE, and the included Work Queue system. It does not require a distributed filesystem, so you can use it to harness whatever collection of machines you have available. It is typically used for scaling up data-intensive scientific applications to hundreds or thousands of cores.
wsrep-enabled MySQL (previously MySQL/Galera cluster) can use wsrep replication providers, such as Galera, to form a cluster. wsrep API is an abstract replication interface that supports global transaction ID, true multi-master capability, conflict detection and resolution, and parallel applying and is transparent to triggers, stored procedures, and functions by replicating only final transaction results. Only the InnoDB storage engine and DDL commands are supported by this patch.