Results 1 - 10
of
15
Load Balancing and Unbalancing for Power and Performance in Cluster-Based Systems
, 2001
"... In this paper we address power conservation for clusters of workstations or PCs. Our approach is to develop systems that dynamically turn cluster nodes on -- to be able to handle the load imposed on the system efficiently -- and off -- to save power under lighter load. The key component of our syst ..."
Abstract
-
Cited by 194 (10 self)
- Add to MetaCart
In this paper we address power conservation for clusters of workstations or PCs. Our approach is to develop systems that dynamically turn cluster nodes on -- to be able to handle the load imposed on the system efficiently -- and off -- to save power under lighter load. The key component of our systems is an algorithm that makes load balancing and unbalancing decisions by considering both the total load imposed on the cluster and the power and performance implications of turning nodes off. The algorithm is implemented in two different ways: (1) at the application level for a cluster-based, localityconscious network server; and (2) at the operating system level for an operating system for clustered cycle servers. Our experimental results are very favorable, showing that our systems conserve both power and energy in comparison to traditional systems.
Dynamic Cluster Reconfiguration For Power And Performance
, 2002
"... In this paper we address power conservation for clusters of workstations or PCs. Our approach is to develop systems that dynamically turn cluster nodes on -- to be able to handle the load imposed on the system efficiently -- and off -- to save power under lighter load. The key component of our syste ..."
Abstract
-
Cited by 91 (9 self)
- Add to MetaCart
In this paper we address power conservation for clusters of workstations or PCs. Our approach is to develop systems that dynamically turn cluster nodes on -- to be able to handle the load imposed on the system efficiently -- and off -- to save power under lighter load. The key component of our systems is an algorithm that makes cluster reconfiguration decisions by considering the total load imposed on the system and the power and performance implications of changing the current configuration. The algorithm is implemented in two common cluster-based systems: a network server and an operating system for clustered cycle servers. Our experimental results are very favorable, showing that our systems conserve both power and energy in comparison to traditional systems.
A New Approach to Configurable Dynamic Scheduling in Clusters based on Single System Image Technologies
- Proc. Int’l Symp. Parallel and Distributed Processing
, 2003
"... Clusters are now considered as an alternative to parallel machines to execute workloads made up of sequential and/or parallel applications. For efficient application execution on clusters, dynamic global process scheduling is of prime importance. Different dynamic scheduling policies that have been ..."
Abstract
-
Cited by 19 (7 self)
- Add to MetaCart
(Show Context)
Clusters are now considered as an alternative to parallel machines to execute workloads made up of sequential and/or parallel applications. For efficient application execution on clusters, dynamic global process scheduling is of prime importance. Different dynamic scheduling policies that have been studied for distributed systems or parallel machines may be used in clusters. The choice of a particular policy depends on the kind of workload to be executed. In a cluster, it is thus highly desirable to implement a configurable global scheduler to be able to adapt the dynamic scheduling policy to the workload characteristics, to take benefit of all cluster resources and to cope with node shutdown and reboot. In this paper, we present the architecture of the global scheduler and the process management mechanisms of Kerrighed, a single system image operating system designed for high performance computing on clusters. Kerrighed provides a development framework allowing to easily implement dynamic scheduling policies without kernel modification. In Kerrighed, the global scheduling policy can be dynamically changed while applications execute on the cluster. Kerrighed process management mechanisms allow to easily deploy parallel applications in the cluster and to efficiently migrate or checkpoint processes, including processes sharing memory. Kerrighed has been implemented as a set of modules extending Linux kernel. Preliminary performance results are presented.
Containers: A sound basis for a true single system image
- In Proceeding of IEEE International Symposium on Cluster Computing and the Grid (CCGrid ’01
, 2001
"... Clusters of SMPs are attractive for executing shared memory parallel applications but reconciling high perfor-mance and ease of programming remains an open issue. A possible approach is to provide an efficient Single System Image (SSI) operating system giving the illusion of an SMP machine. But the ..."
Abstract
-
Cited by 15 (10 self)
- Add to MetaCart
(Show Context)
Clusters of SMPs are attractive for executing shared memory parallel applications but reconciling high perfor-mance and ease of programming remains an open issue. A possible approach is to provide an efficient Single System Image (SSI) operating system giving the illusion of an SMP machine. But the global management of all resources to provide a true SSI remains an open issue. In this paper, we introduce the concept of container as a mechanism to unify global resource management at the lowest operating sys-tem level. Higher level operating system services such as virtual memory system and file cache can be easily imple-mented based on containers and transparently take benefit of the whole memory resource available in the cluster. 1.
MTCP: Transport Layer Support For Highly Available Network Services
, 2001
"... We propose a transport layer protocol designed for building highly available Internet network services. The transport layer protocol would provide a mechanism to transparently migrate the server endpoint of a live connection. The connection migration is dynamic and can happen multiple times during ..."
Abstract
-
Cited by 6 (2 self)
- Add to MetaCart
We propose a transport layer protocol designed for building highly available Internet network services. The transport layer protocol would provide a mechanism to transparently migrate the server endpoint of a live connection. The connection migration is dynamic and can happen multiple times during a client-service session. Our migration mechanism is client-initiated, integrated in a migration architecture that uniformly addresses various types of events that affect the quality of service perceived by the client. In the architecture, the migration mechanism is independent and decoupled from any migration policies. The migration mechanism can be applied for different contexts like server load balancing, to provide fault tolerance across server crashes, to improve the performance as perceived by the client etc. We examine and address a number of challenges posed by the transfer of connection state required for a connection migration to both the OS and the application layer. We describe the details of our design and an implementation, as well as experimental data that suggests the usefulness of this approach.
Comparison of decision-directed and pilot-aided algorithms for complex channel tap estimation in a downlink WCDMA system
- in Proc. IEEE International Symposium on Personal, Indoor and Mobile Radio Communications
, 2000
"... ..."
Architectural Review of Load Balancing Single System Image
, 2008
"... Abstract: Problem statement: With the growing popularity of clustering application combined with apparent usability, the single system image is in the limelight and actively studied as an alternative solution for computational intensive applications as well as the platform for next evolutionary grid ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
Abstract: Problem statement: With the growing popularity of clustering application combined with apparent usability, the single system image is in the limelight and actively studied as an alternative solution for computational intensive applications as well as the platform for next evolutionary grid computing era. Approach: Existing researches in this field concentrated on various features of Single System Images like file system and memory management. However, an important design consideration for this environment is load allocation and balancing that is usually handled by an automatic process migration daemon. Literature shows that the design concepts and factors that affect the load balancing feature in an SSI system are not clear. Result: This study will review some of the most popular architecture and algorithms used in load balancing single system image. Various implementations from the past to present will be presented while focusing on the factors that affect the performance of such system. Conclusion: The study showed that although there are some successful open source systems, the wide range of implemented systems investigated that research activity should concentrate on the systems that have already been proposed and proved effectiveness to achieve a high quality load balancing system.
Energy Conservation for Server Systems
, 2005
"... To date, energy consumption has only been a concern for mobile and embedded devices due to battery lifetime and heat dissipation concerns. In this thesis we make the case for energy conservation for server systems. We describe in details the current mechanisms for power management and the state-of-t ..."
Abstract
- Add to MetaCart
To date, energy consumption has only been a concern for mobile and embedded devices due to battery lifetime and heat dissipation concerns. In this thesis we make the case for energy conservation for server systems. We describe in details the current mechanisms for power management and the state-of-the-art policies for energy conservation for the main components of servers. We propose three novel energy conservation techniques for servers, namely Load Concentration, for entire servers; Popular Data Concentration, for disk arrays; and Diverted Accesses for distributed file servers. Our experiments, physical measurements, simulations, and models show that our techniques can greatly enhance the opportunities for power management and consequently accrue significant energy savings.
: Canada (2011)" Design and Performance Analysis of CAPE based on Discontinuous Incremental Checkpoints
, 2011
"... Abstract—Checkpointing Aided Parallel Execution (CAPE) is a paradigm using checkpointing technique to distribute sequential programs equipped with OpenMP directives in distributed systems. In its first prototype, the use of a complete checkpointer strongly decreased global performance. This paper sh ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—Checkpointing Aided Parallel Execution (CAPE) is a paradigm using checkpointing technique to distribute sequential programs equipped with OpenMP directives in distributed systems. In its first prototype, the use of a complete checkpointer strongly decreased global performance. This paper shows how the performance of the CAPE paradigm have been improved using discontinuous incremental checkpointing and provide an in-depth analysis of this performance. I.
Author manuscript, published in "HPCC-2011- International Conferences on High Performance Computing and Communications, Banff: Canada (2011)" Improving Performance of CAPE using Discontinuous Incremental Checkpointing
, 2011
"... Abstract—Originally, OpenMP was designed to develop parallel applications on shared-memory architectures. One of the advantages that made the success of OpenMP is the simplicity of the associated programming model. Checkpointing Aided Parallel Execution (CAPE) is a paradigm that uses checkpointing t ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—Originally, OpenMP was designed to develop parallel applications on shared-memory architectures. One of the advantages that made the success of OpenMP is the simplicity of the associated programming model. Checkpointing Aided Parallel Execution (CAPE) is a paradigm that uses checkpointing techniques to run parallel programs on distributedmemory architectures. In order to show its effectiveness, it has been used to develop a compiler to run OpenMP programs on distributed-memory architectures. The first prototype we developed proved the feasibility of the paradigm but the use of complete checkpoints led to poor performance. This was mainly due to the large amount of data to transfer and process. This paper presents the new prototype we developed for CAPE based on the discontinuous incremental checkpointing technique and an analysis its performance. I.
