7 projects tagged "Distributed Computing"
StarCluster is a utility for creating traditional computing clusters used in research labs or for general distributed computing applications on Amazon's Elastic Compute Cloud (EC2). It uses a simple configuration file provided by the user to request cloud resources from Amazon and to automatically configure them with a queuing system, an NFS shared /home directory, passwordless SSH, OpenMPI, and ~140GB scratch disk space. It consists of a Python library and a simple command line interface to the library. For end-users, the command line interface provides simple intuitive options for getting started with distributed computing on EC2 (i.e. starting/stopping clusters, managing AMIs, etc). For developers, the library wraps the EC2 API to provide a simplified interface for launching/terminating nodes, executing commands on the nodes, copying files to/from the nodes, etc.
Livespaces is an operating system for building advanced meeting spaces. It provides a distributed software infrastructure built on the Elvin messaging service (the Livespace Bus) for coordinating software and devices across any number of computers in a meeting space, and user-facing applications for controlling a smart meeting room and collaborating with other participants. It also supports federation with remote Livespaces to facilitate collaboration between distributed teams.
WOSH (Wide Open Smart Home) is a message-oriented middleware for controlling and automating a smart home. It comes with working services and devices. WOSH is an open multi-platform C++ framework. Its architecture is service (bundles) oriented and designed for distributed (cloud) computing. WOSH ships with library source, many services, and some applications (a server, a trayicon remote controller, and a GUI full-controller). Some features provided by its micro-kernel are a multi-user system with access policies, a centralized database manager and system monitor, and automatic network management and masquerading (on TCP). Some of the implemented services are: multimedia audio playback, monitor and control of X10 devices, remote control using instant messaging, and a remote control using SMS and call notification.
The Ex-Crawler Project is divided into three subprojects. The main part is the Ex-Crawler daemon server, a highly configurable and flexible Web crawler written in Java. It comes with its own socket server, with which you can manage the server, users, distributed grid/volunteer computing, and much more. Crawled information is stored in a database (Currently MySQL, PostgreSQL, and MSSQL are supported). The second part is a graphical (Java Swing) distributed grid/volunteer computing client, including user computer state detection, based on JADIF Project. The Web search engine is written in PHP. It comes with a Content Management System, user language detection and multi-language support, and templates using Smarty, including an application framework that is partly forked from Joomla 1.5, so that Joomla components can be adapted quickly.
Parrot and Chirp are user-level tools that make it easy to rapidly deploy wide area filesystems. Parrot is the client component: it transparently attaches to unmodified applications, and redirects their system calls to various remote servers. A variety of controls can be applied to modify the namespace and resources available to the application. Chirp is the server component: it allows an ordinary user to easily export and share storage across the wide area with a single command. A rich access control system allows users to mix and match multiple authentication types. Parrot and Chirp are most useful in the context of large scale distributed systems such as clusters, clouds, and grids where one may have limited permissions to install software.
dispy is a Python framework for parallel execution of computations by distributing them across multiple processors in a single machine (SMP), or among many machines in a cluster or grid. The computations can be standalone programs or Python functions. dispy is well suited for the data parallel (SIMD) paradigm where a computation is evaluated with different (large) datasets independently (similar to Hadoop, MapReduce, Parallel Python). dispy features include automatic distribution of dependencies (files, Python functions, classes, modules), client-side and server-side fault recovery, scheduling of computations to specific nodes, encryption for security, sharing of computation resources if desired, and more.