FreeVPS project is released under the GNU General Public License (GPL).

To ensure complete isolation of virtual servers, each is given a certain portion of the filesystem, a separate root directory where all its processes run restricted from other virtual servers, and own virtual network connections.

FreeVPS is fully integrated with H-Sphere, an automated scalable web hosting software. H-Sphere provides an easy-to-use web interface to manage VPS configuration and hosting facilities.

What’s New in This Release:

· Experimental support for the x86_64 arch was added.
· A kernel panic when starting VPS without Ethernet link was fixed.
· Uptime virtualization for context 1 was fixed.
· Building of the ipt_physdev module was fixed.

RedHat EL Athlon RPM mirror 1

Fusion is a high level IPC API providing mechanisms for master/slave environments.

In client/server environments clients delegate every operation to the server which has sole access to shared resources.

The master/slave approach eliminates this overhead by virtually merging the processes at the lower level of their implementation.

This way of making multiple processes look like multiple threads gave Fusion its name.

Here are some key features of “Linux Fusion”:

· Command encoding and decoding
· Transport of command packets
· Transport of data referenced by commands
· Context switches between client and server processes
· Strict seperation of client and server implementation
· Shared memory for data normally held solely by the server
· High level messaging for virtually local event handlers and callbacks
· Advanced locking techniques for synchronization and access control
· Framework for distributed allocation and cleanup of resources

Sources mirror 1 (tar.gz) (3.2.4)

Sources mirror 2 (tar.gz) (7.0.1)

In a MOSIX based system, there is no need to modify or link applications with any library, copy files, login to remote nodes, or even assign processes to different nodes; it is all done automatically. Just “fork and forget”, like in an SMP.

Here are some key features of “MOSIX Grid and Cluster Management”:

· Provides a Single-System Image (SSI).
· Automatic resource discovery.
· Adaptive workload distribution by process migration:
· Preserves the user’s “login-node” environment.
· No need to open “logins” or copy files to remote clusters.
· No need to link applications with special libraries.
· Automatic process migration:
· For load-balancing.
· From slower to faster nodes.
· When a node run out of free memory.
· Supports virtual organizations:
· Manages disruptive configurations:
· Clusters can join or leave the Grid at any time.
· Guest processes are moved out before a cluster is disconnected.
· Long-running guest processes are not killed.
· Clusters could be shared symmetrically or asymmetrically.
· Each cluster owner can assign different priorities to guest processes from other clusters.
· A flexible use of nodes within and among different groups.
· Local processes force out guest processes.
· A secure run time environment (sandbox) for guest processes.
· Live queuing – queued jobs preserve their full generic Linux environment.
· Support of batch jobs, checkpoint and recovery.
· An on-line monitor for the status of the Grid and each cluster.

What’s New in This Release:

· This release uses version 2.6.22.5 of the Linux kernel.

Sources mirror 1

· Can be turned off at compile and runtime (/proc/sys/net/ipv4/ip_random_id)
· Should work on all architectures.
· Not needed for 2.4.x since it has a better system for ip id randomness.
· I ran this on ftp.habets.pp.se for 180 days straight, after which the UPS failed which caused downtime. So it’s stable.

Requirements:

· Linux kernel 2.2.x

Sources mirror 1 (gz)

Using AoE, a Linux system can use AoE block devices like EtherDrive (R) storage blades.

The block devices appear as local device nodes (e.g. /dev/etherd/e0.0).

What’s New in This Release:

· Dynamic minor numbers for devices expand the range of usable AoE addresses.
· The latest Linux kernels are now supported.
· A bug that manifested when AoE targets were not behaving correctly was fixed.
· Specific devices can now be forgotten on demand.
· A module parameter for GPFS users was added.

Sources mirror 1 (tar.gz)

While the national high-performance network infrastructure has grown tremendously both in bandwidth and accessibility, it is still common for applications, hosts, researchers and other users to be unable to take full advantage of this new and improved infrastructure.

Without expert attention from network engineers, users are unlikely to achieve even 10 Mbps single stream TCP transfers, despite the fact that the underlying network infrastructure can support data rates of 100Mbps or more.

On unloaded networks, this poor performance can be attributed primarily to two factors: host system software (principally TCP) that is optimized for low bandwidth environments, and the lack of effective instrumentation and tools to diagnose performance issues.

The Web100 project was created to address these problems. The first is addressed with automatic TCP buffer tuning. The Web100 work in this area has been merged with main-line Linux kernel, and is contained in recent releases.

To address the other problem, we have created a set of TCP instruments, defined in an IETF internet-draft. These instruments are implemented in Linux with the Web100 kernel patch.

What’s New in This Release:

· Updated to Linux kernel 2.6.23.

Sources mirror 1 (tar.gz)

A real time system is able to guarantee the timing requirements of the processes under its control.

RTAI provides an API and the necessary kernel modifications to accommodate such requirements.

What’s New in 3.5 Stable Release:

· Improvements were made to netrpc.
· Context switching between hard and soft real-time, handling of TSC errors, and POSIX compatibility have been improved.
· There are numerous minor bugfixes.

What’s New in 3.6 Test 3 Development Release:

· Linux 2.6.x MODVERSION is honored.
· There are assorted minor patches.

Sources mirror 1 (tar.bz2) (3.5 Stable)

Sources mirror 2 (tar.bz2) (3.6 Test 3 Development)

Linux is a clone of the operating system Unix, written from scratch by Linus Torvalds with assistance from a loosely-knit team of hackers across the Net. It aims towards POSIX and Single UNIX Specification compliance.

It has all the features you would expect in a modern fully-fledged Unix, including true multitasking, virtual memory, shared libraries, demand loading, shared copy-on-write executables, proper memory management, and multistack networking including IPv4 and IPv6.

Although originally developed first for 32-bit x86-based PCs (386 or higher), today Linux also runs on (at least) the Compaq Alpha AXP, Sun SPARC and UltraSPARC, Motorola 68000, PowerPC, PowerPC64, ARM, Hitachi SuperH, IBM S/390, MIPS, HP PA-RISC, Intel IA-64, DEC VAX, AMD x86-64, AXIS CRIS, and Renesas M32R architectures.

Linux is easily portable to most general-purpose 32- or 64-bit architectures as long as they have a paged memory management unit (PMMU) and a port of the GNU C compiler (gcc) (part of The GNU Compiler Suite, GCC). Linux has also been ported to a number of architectures without a PMMU, although functionality is then obviously somewhat limited. See the µClinux project for more info.

Sources mirror 1 (tar.gz)

Sources mirror 2 (tar.bz2)

At the core of the architecture there is an adaptive resource reservation layer that is capable of dynamically adapting the CPU allocation for QoS aware applications based on their run-time requirements.
Timing guarantees are provided through an in-kernel reservation based process scheduler, whose services are exposed to applications through a well-designed API.

A supervisor performs admission control, so that admitting into the system new applications with timing guarantees does not affect the timing guarantees of already admitted applications. Also, it takes care of guaranteeing appropriate security policies in the assignment of timing guarantees to users and user groups, as configured by the system administrator.

A feedback-based QoS control layer may be optionally used by applications who want to keep their timing guarantees by using a CPU allocation that is continuously adapted according to their actual needs. This leaverages the programmer, within certain limits, to hard-code any particular reservation amount within the application, because the best allocation is found out automatically at run-time. Also, this enhances the possibilities for the system to host additional QoS controlled applications. The available control algorithms are well founded on formal scheduling models and control theoretical results.

What’s New in This Release:

· This release fixes a few configuration issues and minor bugs, and introduces the ability to reserve a certain amount of spare bandwidth in the supervisor configuration (useful for adaptive reservations).

Sources mirror 1 (tar.gz)

Linux is a clone of the operating system Unix, written from scratch by Linus Torvalds with assistance from a loosely-knit team of hackers across the Net. It aims towards POSIX and Single UNIX Specification compliance.

It has all the features you would expect in a modern fully-fledged Unix, including true multitasking, virtual memory, shared libraries, demand loading, shared copy-on-write executables, proper memory management, and multistack networking including IPv4 and IPv6.

Although originally developed first for 32-bit x86-based PCs (386 or higher), today Linux also runs on (at least) the Compaq Alpha AXP, Sun SPARC and UltraSPARC, Motorola 68000, PowerPC, PowerPC64, ARM, Hitachi SuperH, IBM S/390, MIPS, HP PA-RISC, Intel IA-64, DEC VAX, AMD x86-64, AXIS CRIS, and Renesas M32R architectures.

Linux is easily portable to most general-purpose 32- or 64-bit architectures as long as they have a paged memory management unit (PMMU) and a port of the GNU C compiler (gcc) (part of The GNU Compiler Suite, GCC). Linux has also been ported to a number of architectures without a PMMU, although functionality is then obviously somewhat limited. See the µClinux project for more info.

Sources mirror 1 (tar.gz)

Sources mirror 2 (tar.bz2)