The overall objective of the XtreemOS project is the design, implementation, evaluation, and distribution of a grid operating system (called XtreemOS) with native support for virtual organizations (VO). XtreemOS is capable of running on a wide range of underlying platforms, from clusters to mobiles. It is based on Mandriva Linux, with support to come for other distributions later.
ZXTM Load Balancer (ZXTM LB) is a powerful, fault-tolerant and high-performance load balancing solution for providers of clustered network services and resilient applications. With high-performance SSL and content compression, content-aware traffic management rules, and flexible health monitoring, ZXTM LB provides an easy-to-use and cost-effective path to adding load balancing intelligence to your services.
Appctl is a framework for virtually any server software. It provides a central script called "ctl" which allows you to start, stop, restart, maintain, or query the current status of an application. It is meant as a completely generic replacement for application-specific startup/stop scripts. The project also supplies generic monitoring scripts for clusters, which can dramatically decrease clustering costs.
auto nice daemon activates itself in certain intervals, and renices jobs according to their priority, and CPU usage. Jobs owned by root are left alone. Jobs are never increased in their priority. It is very flexible. The renice intervals can be adjusted, as well as the default nice level, and the activation intervals. A priority database stores user/group/job tuples along with their renice values for three CPU usage time ranges. The strategy for searching the priority database can be configured. Linux, OpenBSD, FreeBSD, Digital UNIX, Solaris, and IRIX are supported.
changedfiles is a framework for filesystem replication, security monitoring, and/or automatic file transformations--essentially any application where you'd poll files or directories and either do something to them or send them somewhere else (or both). The difference is that the kernel tells you when they change instead of you having to poll. It's an easy real time FTP push mirror to one or multiple sites. It's also a full fledged MySQL client, so you can do realtime database operations (for example, batch imports). It consists of two parts: a kernel module (works with Linux kernel version 2.4) which reports to a device whenever a file on the filesystem changes, and a daemon which runs in user space and can be configured to do almost any action when a change to a file matching the one of the patterns it looks for is reported. The kernel module is SMP safe and has been tested on Intel, PowerPC, and Alpha.
chpox provides transparent checkpointing and restarting of processes on Linux clusters. It was originally designed for recovering tasks that have a long execution time (i.e. numerical simulations) in case of system crashes, power failures, etc. It may work with openMosix, is SMP safe, does not require program recompiling/relinking, and supports virtual memory, regular open files, pipes, Unix domain sockets, current directory, and child processes.
classh is yet another wrapper around ssh for running commands on a number of hosts concurrently. It is similar to xCAT, pssh, Cluster ssh, and a gaggle of other utilities. The only pre-requisite for classh is Python 2.4 or later, and no formal installation is required; a copy of the classh.py file is sufficient to run commands. The SSHJobMan class from classh can be used to create custom job management scripts. This class lets you either wait until all output has returned from a batch job or process the results as they become available by incrementally polling the running job. The output, error messages, exit code, and start and completion times of each job are stored in the results. It's been tested on jobs of over 25,000 hosts and handles over 10,000 hosts per hour across a WAN and without noticeable impact on the administrator's host.