Open Source Perl Distributed Computing Software

DRBL provides diskless or systemless environment. It uses distributed hardware resources and makes it possible for clients to fully access local hardware. It also includes Clonezilla, a partition and disk cloning utility similar to Ghost.

Ganglia is a scalable distributed monitoring system for high-performance computing systems such as clusters and Grids. It is based on a hierarchical design targeted at federations of clusters. Supports clusters up to 2000 nodes in size.

openQRM is a web-based open source datacenter management and hybrid cloud computing platform that integrates flexibly with existing components in enterprise data centers. Releases available at https://github.com/openQRM/openqrm-community. Please visit http://www.openqrm-enterprise.com for latest 5.3 free Community Release. Includes important security updates, bugfixes and enhancements especially for KVM and Cloud plugin. openQRM abstracts Virtualization and supports the following virtualization technologies: KVM, XEN, Citrix XenServer, VMWare ESX & LXC. The Hybrid Cloud Connector in openQRM supports a range of private or public cloud providers to extend your infrastructure on demand via Amazon AWS, Eucalyptus or OpenStack. openQRM automates provisioning, virtualization, storage and configuration management, and it takes care of high-availability.

The OpenSSI project is a comprehensive clustering solution offering a full, highly available SSI environment for Linux. Goals for OpenSSI Clusters include availability, scalability and manageability, built from standard servers.

The Herdtools are a set of user-level cluster management and control utilities with a consistent command line interface. These include things like parallel file copy, remote execution, sudo execution, job kill, etc. We utilize Rob Brown's "procstatd" d

MLN (Manage Large Networks) is a perl program used to manage a set of User-Mode-Linux instances or Xen instances. From a configuration file, it is possible to specify a large complex network of e.g. Xen instances, which are each configured as specified.

Tool for generate status from the condor queue and cluster usage in a HTML file

The project focuses on developing an environment where one can harness idle CPU cycles of numerous networked systems to work together on a particularly processing-intensive problem. (distributed computing you may call it)

Tools, information, and practices for creating and operating dependable, complex, distributed, software-intensive systems. * Sense - Measure - Analyze - Respond - Optimize * Keywords: Performance Co-Pilot - PCP - PCPMon - Rjobd

A Nagios check that ensures the same service on multiple hosts - in a lazy cluster - can be "verified" if the service must remain active on one host at a time.

NIUS allows reservation of nodes under it's control for exclusive interactive use by a group of users. This system is in use by National Center for Data Mining at University of Illinois in Chicago to reserve workstations for researchers.

PBS Job Seer is a program which analyses the state of a PBS/Maui batch system and automatically generates a batch script for MPI jobs which would then be able to start immediately.

Designed to allow quick setup of powerful NOW-based clusters to run compute-intensive applications. Applications do not have to be designed specially for these clusters to benefit.

NOTE: NEWEST FILES AT http://www.schedmd.com/#repos ---------------------------------------------------------------------------------------------------------------------------- SLURM is an open-source resource manager designed for Linux clusters.

SSS-OSCAR is an integrated release of the SciDAC:Scalable System Software (SSS) suite using the OSCAR cluster installation framework. The SSS project seeks to provide a standard interface for effective management and utilization of terascale systems.

SimParEx executes a program(command) on many computers (farm) in parallel and collects the results (task farming). Major features: minimal requirements (TCP, SSH, Perl), flexible task definition, web interface.

NOTE: UBMoD is no longer actively developed and we encourage you to download Open XDMoD as a replacement for UBMoD. Open XDMoD has been developed to provide detailed information on resource utilization and performance for academic and industrial HPC centers. More information is available at http://xdmod.sourceforge.net/ UBMoD is a data warehouse and web portal for mining statistical data from resource managers in high-performance computing environments. UBMoD presents resource utilization over set time periods and provides detailed interactive charts, graphs, and tables.

WOOP(c) is an Open-Source Software Architecture.

metahelper is a utility which makes creating and maintaining upgradeable, removable, and verifiable configuration "metapackages" easy. A metapackage works with files owned by other packages to customize and configure them specifically for your environmen

N-stage worm propagated via SSH. It executes commands in a given list of hosts and copies files to them with rsync. The paths for its propagation to the cluster are configurable. It offers a scalable/reliable transport API thanks to its adaptive algorithm

The underlayer is a symmetric decentralized parallel computing and load balancing framework, providing c, perl and java APIs for distributed job management.