Open Source Clustering Software

Tools for the Linux Kernel's network block device, allowing you to use remote block devices over a TCP/IP network. Note that we have moved to github: https://github.com/NetworkBlockDevice/nbd

Collectl is a light-weight performance monitoring tool capable of reporting interactively as well as logging to disk. It reports statistics on cpu, disk, infiniband, lustre, memory, network, nfs, process, quadrics, slabs and more in easy to read format.

RELIANOID is an open core (Debian GNU/Linux based) Application Delivery Controller (ADC) with advanced load balancing features such as Network Load Balancer, Application Load Balancer with SSL offloading, Advance Network Configuration including Virtual Interfaces, VLANs, Bonding with link aggregation, IPv4/IPv6, advanced routing, stateless cluster, web GUI, JSON API and much more! Enterprise Edition Load Balancer is available with extra features such as global service load balancing (gslb), application security including web application firewall (WAF), blacklists, Realtime Blackhole Lists (DNSBL), DDoS protection, stateful clustering, SNMP monitoring, email and SNMP notifications, RBAC, VPN support, and the best Support directly from an expert Team.

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.

The aoetools are programs for users of the ATA over Ethernet (AoE) network storage protocol, a simple protocol for using storage over an ethernet LAN. The vblade program (storage target) exports a block device using AoE.

Scripts to configure a Mesos cluster using Mesos and Mesosphere services. Mesos master running the Marathon and Chronos frameworks. Mesos agent with Docker containerizer. Mesos DNS for core service discovery. Marathon load balancer using HAProxy for SSL and proxying to internal applications. To try it out locally use the Vagrant configuration. To use the scripts to build a custom Mesos cluster first install the roles in your project and configure Ansible to load roles from the roles directory provided by this project. Install the chronos-sync ruby script distributed as part of Chronos. Once installed the script can be used for keeping version controlled Chronos job definitions up-to-date with a Chronos instance. Install DCOS CLI and configure for use "inside the cluster" with configured master nodes. The configuration relies on Mesos DNS to provide the Mesos master and Marathon endpoints.

JPPF makes it easy to parallelize computationally intensive tasks and execute them on a Grid.

Generic SCSI target subsystem for Linux SCST allows creation of sophisticated storage devices. It includes generic SCSI target core with SCSI target drivers and backend handlers. There are target drivers for iSCSI, Fibre Channel, SRP, SAS, FCoE, etc.

UNFS3 is a user-space implementation of the NFSv3 server specification. It provides a unified mountd and nfsd program and so far runs under Linux, NetBSD, and Solaris.

The aim of the project is to develop an open source iSCSI target with professional features, works well in enterprise environment under real workload, and is scalable and versatile enough to meet the challenge of future storage needs and developements.

Reliable group communication based on IP multicast and configurable protocol stack

Balance is a simple but powerful generic tcp proxy with round robin load balancing and failover mechanisms. Via shared memory its behaviour can be controlled at runtime using a simple command line syntax.

GGI stands for "General Graphics Interface", and it is a project that aims to develop a reliable, stable and fast graphics system that works everywhere. We want to allow any program using GGI to run on any platform requiring at most a recompile.

rshd is a multithreaded daemon service that listens for connections on port 514 (tcp port for the shell/cmd protocol), runs commands passed by clients and sends back the results.

Generic clustering/load-balancing platform (over a LAN or internet) using java based P2P Aorta workers that execute java "tasklets". Various tasklets can be implemented to solve fractals, process images, render webpages, crack RSA "brute force".

Ballast is a tool for balancing user load across SSH servers that supports user-specific policies as well as traditional policies based on metrics such as CPU load. It includes a simple client, a lightweight data server, and a data collection agent.

Alternative implementation of Spring framework remoting subsystem that supports different schemes of remote communication between client and server (1-1, 1-many, dynamic services discovering).

The VSC is a PHP/MySQL/Apache Interface for Nessus 2.x. It allows users to hierarchically manage hosts, scanning policies, and request automated immediate, future/reccuring scans of a host or group of hosts, view scan reports and generate metrics.

XLB is a high performance HTTP load balancer. connection management, caching, ssl, scripting. 300 mbit/sec / 4000 reqs/sec takes 30% cpu on a 2GhZ Xeon. connection pooling to backend servers reduces memory and cpu usage on backends.

OpenBAM is a Business Activity Monitoring(BAM) application for Operations Managers in service organizations who are constantly trying to figure out what's effecting their business by trying to co-relate data from multiple systems.

See http://www.cubrid.org/cluster. CUBRID Cluster is an open source clustered DBMS for high scalability including global schema, distributed partition and load balancing features. It is a spin-off project from CUBRID project and supported by NHN.

Channel is a C++ framework for distributed message passing and event dispatching, configurable with its components (msg ids,routing algorithms...) as template parameters. As a namespace shared by peer threads, channel supports scope control and filtering

A LDAP based cluster control system that allows the deployment and administration of heterogeneous clusters. An extremely generic framework designed to be extended as required by administrators for each cluster.

This project allow to test network availability on multiple nodes. It is built as a plugin architecture in order to use it on multiples networks. Test is based on three steps : module status, local visibility of network, and interconnection between nodes

The BCR flavor of Cooperative Data Sharing (CDS) is a scalable, portable, flexible C-based API and daemon for initiating and communicating between processes/threads in uniprocessor and multiprocessor (e.g. distributed, SMP, and parallel) platforms.