Pascal Gallard

OpenMosix, OpenSSI and Kerrighed: a comparative study

This paper presents a comparative study of Kerrighed, openMosix and OpenSSI, three single system image (SSI) operating systems for clusters. This experimental study gives an overview of SSI features offered by these SSI and evaluates performance of such features.

Kerrighed: A Single System Image Cluster Operating System for High Performance Computing

Kerrighed is a single system image operating system for clusters. Kerrighed aims at combining high performance, high availability and ease of use and programming. Kerrighed implements a set of global resource management services that aim at making resource distribution transparent to the applications, at managing resource sharing in and between applications and at taking benefit of the whole cluster resources for demanding applications. Kerrighed is implemented as a set of modules extending the Linux kernel. Legacy multi-threaded applications and message-passing based applications developed for an SMP PC running Linux can be executed without re-compilation on a Kerrighed cluster. The proposed demonstration presents a prototype of Kerrighed running on a cluster of four portable PCs. It shows the main features of Kerrighed in global memory, process and stream management by running multi-threaded and MPI applications on top of Kerrighed.

Kerrighed and data parallelism: cluster computing on single system image operating systems

A working single system image distributed operating system is presented. Dubbed Kerrighed, it provides a unified approach and support to both the MPI and the shared memory programming models. The system is operational in a 16-processor cluster at the Institut de Recherche en Informatique et Systemes Aleatoires in Rennes, France. In this paper, the system is described with emphasis on its main contributing and distinguishing factors, namely its DSM based on memory containers, its flexible handling of scheduling and checkpointing strategies, and its efficient and unified communications layer. Because of the importance and popularity of data parallel applications in these systems, we present a brief discussion of the mapping of two well known and established data parallel algorithms. It is shown that ShearSort is remarkably well suited for the architecture/system pair as is the ever so popular and important two-dimensional fast Fourier transform. (2D FFT).

Towards an efficient single system image cluster operating system

The lack of a single system image operating system (OS) for clusters restricts their use for parallel processing. We propose an approach for building an efficient single system image (SSI) cluster operating system. The proposed system implements distributed services performing global and dynamic resource management to offer high performance, high availability and ease of programming. The programming API of the OS running on each cluster node is kept unmodified but the high level OS services can benefit from all cluster resources. Our approach has been validated by a prototype based on Linux.

Dynamic Resource Management in a Cluster for High-Availability

In order to execute high performance applications on a cluster, it is highly desirable to provide distributed services that globally manage physical resources distributed over the cluster nodes. However, as a distributed service may use resources located on different nodes, it becomes sensitive to changes in the cluster configuration due to node addition, reboot or failure. In this paper,w e propose a generic service performing dynamic resource management in a cluster in order to provide distributed services with high availability. This service has been implemented in the Gobelins cluster operating system. The dynamic resource management service we propose makes node addition and reboot nearly transparent to all distributed services of Gobelins and, as a consequence, fully transparent to applications. In the event of a node failure, applications using resources located on the failed node need to be restarted from a previously saved checkpoint but the availability of the cluster operating system is guaranteed, provided that its distributed services implement reconfiguration features.

Complementarity between Virtualization and Single System Image Technologies

Nowadays, the use of clusters in research centers or industries is undeniable. Since few years, the usage of virtual machines (VM) offers more advanced resource management capabilities, using features such as virtual machine live migration. Because of the latest contributions in the domain, some may argue that single system image (SSI) technologies are now deprecated, without considering some complementarities between VMs and SSI technologies are possible. After evaluating different configurations, we show that combining both approaches allows us to better address cluster challenges such as flexibility for the usage of available resources and simplicity of use. In other terms, the study shows that VMs add a level of management flexibility between the hardware and the application, whereas, SSIs give an abstraction of the distributed resources. The simultaneous usage of both technologies could improve the overall platform resources utilization, the cluster productivity and the efficiency of the running applications.

Dynamic Streams for Efficient Communications between Migrating Processes in a Cluster

This paper presents a communication system designed to allow efficient process migration in a cluster. The proposed system is generic enough to allow the migration of any kind of stream: socket, pipe, char devices. Communicating processes using IP or Unix sockets are transparently migrated with our mechanisms and they can still efficiently communicate after migration. The designed communication system is implemented as part of Kerrighed, a single system image operating system for a cluster based on Linux. Preliminary performance results are presented.