The Experts below are selected from a list of 249 Experts worldwide ranked by ideXlab platform

Yi-hsuan Feng - One of the best experts on this subject based on the ideXlab platform.

  • Efficient and Adaptive Stateful Replication for Stream Processing Engines in High-Availability Cluster
    IEEE Transactions on Parallel and Distributed Systems, 2011
    Co-Authors: Yi-hsuan Feng, Nen-fu Huang, Wu Yen-min
    Abstract:

    Stateful stream process engines in High Availability Clusters (HACs) track a large number of concurrent flow states and replicate them to backups to provide reliable functionality. Under High traffic loads, existing solutions in such HACs are expensive owing to precise stateful replication. This work presents two novel methods to address this issue: randomization on replication representation and a replication scheme designed for when system becomes overloaded. A hashing structure called Multilevel Counting Bloom Filter (MLCBF) is proposed as a low resource-consuming solution of stateful replication. Its performance and tradeoffs are then evaluated based on theoretic analysis and extensive trace-based tests. Trace-based simulation reveals that MLCBF reduces network and memory requirements of replication typically by over 90 percent for URL categorization. Most importantly, MLCBF is quite as simple and practical for implementation and maintenance. Moreover, an adaptive scheme called dynamic lazy insertion is designed to prevent replication from overloading system continuously and optimize the throughput of HAC. Testbed evaluation demonstrates its feasibility and effectiveness in an overloaded HAC.

  • HALR: A TCP Enhancement Scheme Using Local Caching in High-Availability Cluster
    IEICE Transactions on Communications, 2009
    Co-Authors: Yi-hsuan Feng, Nen-fu Huang
    Abstract:

    [[abstract]]©2009 IEICE-In this paper, we study the end-to-end TCP performance over a path deploying a High-Availability Cluster, whose characteristics are Highlighted by the failover procedure to remove single-point failure. This paper proposes an approach, called High-Availability Local Recovery (HALR), to enhance TCP performance in the face of a Cluster failover. To minimize the latency of retransmission, HALR saves TCP packets selectively and resends them locally after the failover is finished. For better understanding, we further develop simple analytic models to predict the TCP performance in the aspect of flow latency under a range of failover times and the effects of HALR. Using simulation results, we validate our models and show that HALR improves the TCP performance significantly over a failover event as compared with the original TCP. Typically, HALR reduces the flow latency from 4.1 sec to less than 1.9 sec when the failover time equals to 500 ms. The simulation by real packet trace further demonstrates that the memory requirement of the proposed solution is not a concern for modern network equipments.[[department]]資訊工程學

  • HALR: A TCP Enhancement Scheme Using Local Caching in High-Availability Cluster
    IEICE Transactions on Communications, 2009
    Co-Authors: Yi-hsuan Feng, Nen-fu Huang
    Abstract:

    In this paper, we study the end-to-end TCP performance over a path deploying a High-Availability Cluster, whose characteristics are Highlighted by the failover procedure to remove single-point failure. This paper proposes an approach, called High-Availability Local Recovery (HALR), to enhance TCP performance in the face of a Cluster failover. To minimize the latency of retransmission, HALR saves TCP packets selectively and resends them locally after the failover is finished. For better understanding, we further develop simple analytic models to predict the TCP performance in the aspect of flow latency under a range of failover times and the effects of HALR. Using simulation results, we validate our models and show that HALR improves the TCP performance significantly over a failover event as compared with the original TCP. Typically, HALR reduces the flow latency from 4.1sec to less than 1.9sec when the failover time equals to 500ms. The simulation by real packet trace further demonstrates that the memory requirement of the proposed solution is not a concern for modern network equipments.

  • ICC - Flow Digest: A State Replication Scheme for Stateful High Availability Cluster
    2007 IEEE International Conference on Communications, 2007
    Co-Authors: Yi-hsuan Feng, Nen-fu Huang, Rong-tai Liu
    Abstract:

    Stateful tracking is a popular technique in firewall filtering and state replication is used to provide reliable connectivity. This paper proposes a new approach for improving existing state replication protocols which ensure state consistency amongst the nodes of a stateful HA Cluster. Our goal is to develop a new scheme which reduces the update overhead in the face of both low and High connection loads in order to maximize the capacity and scalability of a High Availability Cluster. A new representation called flow digest is proposed. Also the ways to use flow digest structures to update state changes, recover the connections after a failover, and solve the state inconsistency are presented. The main advantage of the proposed method is to reduce the bandwidth consumption on state replication. The simulation results show that the proposed scheme reduces the number of update messages and, more importantly, eliminates typically at least 86% of bandwidth consumption compared to current solutions.

Nen-fu Huang - One of the best experts on this subject based on the ideXlab platform.

  • Efficient and Adaptive Stateful Replication for Stream Processing Engines in High-Availability Cluster
    IEEE Transactions on Parallel and Distributed Systems, 2011
    Co-Authors: Yi-hsuan Feng, Nen-fu Huang, Wu Yen-min
    Abstract:

    Stateful stream process engines in High Availability Clusters (HACs) track a large number of concurrent flow states and replicate them to backups to provide reliable functionality. Under High traffic loads, existing solutions in such HACs are expensive owing to precise stateful replication. This work presents two novel methods to address this issue: randomization on replication representation and a replication scheme designed for when system becomes overloaded. A hashing structure called Multilevel Counting Bloom Filter (MLCBF) is proposed as a low resource-consuming solution of stateful replication. Its performance and tradeoffs are then evaluated based on theoretic analysis and extensive trace-based tests. Trace-based simulation reveals that MLCBF reduces network and memory requirements of replication typically by over 90 percent for URL categorization. Most importantly, MLCBF is quite as simple and practical for implementation and maintenance. Moreover, an adaptive scheme called dynamic lazy insertion is designed to prevent replication from overloading system continuously and optimize the throughput of HAC. Testbed evaluation demonstrates its feasibility and effectiveness in an overloaded HAC.

  • HALR: A TCP Enhancement Scheme Using Local Caching in High-Availability Cluster
    IEICE Transactions on Communications, 2009
    Co-Authors: Yi-hsuan Feng, Nen-fu Huang
    Abstract:

    [[abstract]]©2009 IEICE-In this paper, we study the end-to-end TCP performance over a path deploying a High-Availability Cluster, whose characteristics are Highlighted by the failover procedure to remove single-point failure. This paper proposes an approach, called High-Availability Local Recovery (HALR), to enhance TCP performance in the face of a Cluster failover. To minimize the latency of retransmission, HALR saves TCP packets selectively and resends them locally after the failover is finished. For better understanding, we further develop simple analytic models to predict the TCP performance in the aspect of flow latency under a range of failover times and the effects of HALR. Using simulation results, we validate our models and show that HALR improves the TCP performance significantly over a failover event as compared with the original TCP. Typically, HALR reduces the flow latency from 4.1 sec to less than 1.9 sec when the failover time equals to 500 ms. The simulation by real packet trace further demonstrates that the memory requirement of the proposed solution is not a concern for modern network equipments.[[department]]資訊工程學

  • HALR: A TCP Enhancement Scheme Using Local Caching in High-Availability Cluster
    IEICE Transactions on Communications, 2009
    Co-Authors: Yi-hsuan Feng, Nen-fu Huang
    Abstract:

    In this paper, we study the end-to-end TCP performance over a path deploying a High-Availability Cluster, whose characteristics are Highlighted by the failover procedure to remove single-point failure. This paper proposes an approach, called High-Availability Local Recovery (HALR), to enhance TCP performance in the face of a Cluster failover. To minimize the latency of retransmission, HALR saves TCP packets selectively and resends them locally after the failover is finished. For better understanding, we further develop simple analytic models to predict the TCP performance in the aspect of flow latency under a range of failover times and the effects of HALR. Using simulation results, we validate our models and show that HALR improves the TCP performance significantly over a failover event as compared with the original TCP. Typically, HALR reduces the flow latency from 4.1sec to less than 1.9sec when the failover time equals to 500ms. The simulation by real packet trace further demonstrates that the memory requirement of the proposed solution is not a concern for modern network equipments.

  • ICC - Flow Digest: A State Replication Scheme for Stateful High Availability Cluster
    2007 IEEE International Conference on Communications, 2007
    Co-Authors: Yi-hsuan Feng, Nen-fu Huang, Rong-tai Liu
    Abstract:

    Stateful tracking is a popular technique in firewall filtering and state replication is used to provide reliable connectivity. This paper proposes a new approach for improving existing state replication protocols which ensure state consistency amongst the nodes of a stateful HA Cluster. Our goal is to develop a new scheme which reduces the update overhead in the face of both low and High connection loads in order to maximize the capacity and scalability of a High Availability Cluster. A new representation called flow digest is proposed. Also the ways to use flow digest structures to update state changes, recover the connections after a failover, and solve the state inconsistency are presented. The main advantage of the proposed method is to reduce the bandwidth consumption on state replication. The simulation results show that the proposed scheme reduces the number of update messages and, more importantly, eliminates typically at least 86% of bandwidth consumption compared to current solutions.

Jianhui Yue - One of the best experts on this subject based on the ideXlab platform.

  • harts High Availability Cluster architecture with redundant tcp stacks
    International Performance Computing and Communications Conference, 2003
    Co-Authors: Zhiyuan Shao, Hai Jin, Bin Chen, Jianhui Yue
    Abstract:

    Improving the Availability of services of is a key issue for survivability of a Cluster system. Lots of schemes are proposed for this purpose. But most of them aim at enhancing only the service-level Availability or application specific. In this paper, we propose a scheme called High Availability with Redundant TCP Stacks (HARTs), providing connection-level Availability by exploring the redundant TCP stacks for TCP connections at the server side. We present our performance experiment results on our HA Cluster prototype. From results, we find the configuration of one primary server with one backup server running on separated 100 Mbps Ethernet has acceptable performance to support the server side applications while delivering High Availability.

  • IPCCC - HARTs: High Availability Cluster architecture with redundant TCP stacks
    Conference Proceedings of the 2003 IEEE International, 1
    Co-Authors: Zhiyuan Shao, Hai Jin, Bin Chen, Jianhui Yue
    Abstract:

    Improving the Availability of services of is a key issue for survivability of a Cluster system. Lots of schemes are proposed for this purpose. But most of them aim at enhancing only the service-level Availability or application specific. In this paper, we propose a scheme called High Availability with Redundant TCP Stacks (HARTs), providing connection-level Availability by exploring the redundant TCP stacks for TCP connections at the server side. We present our performance experiment results on our HA Cluster prototype. From results, we find the configuration of one primary server with one backup server running on separated 100 Mbps Ethernet has acceptable performance to support the server side applications while delivering High Availability.

E. Cortés Ancos - One of the best experts on this subject based on the ideXlab platform.

  • OpenGnSys: A novel system toward centralized deployment and management of computer laboratories
    Computers & Education, 2014
    Co-Authors: T.j. Mateo Sanguino, D. A. Lopez Garcia, I. Fernández De Viana, E. Cortés Ancos
    Abstract:

    Abstract Operation and status of computers in teaching laboratories can significantly influence motivation and expectation of students, thus resulting in a reduction of their academic progress. To address this issue, this paper presents a complete deployment, management, and maintenance tool for operating systems (OS) called OpenGnSys. As part of a larger educational project, OpenGnSys has been tested in a real computer lab with the aim of improving teaching and learning in classroom. OpenGnSys provides an easy and intuitive way to administrate labs from a graphical user console with remote backup functions. Its design comprises a two-node High Availability Cluster for both hardware infrastructure and computer services, thus ensuring the Availability of essential lab equipment. Additionally, this paper proposes a methodology for the installation, maintenance and quality control for computers and laboratory equipment by site acceptance tests (SATs). The main interest of the proposed SATs lies in representing a standardized procedure, which intends to facilitate and determine the degree of compliance with lab specification and operation services. In order to address the research problem, we analyzed OpenGnSys including lab technicians, 94 students and 7 teachers on Computer Science along three academic years. As a result, the OpenGnSys management system has demonstrated the effectiveness of the followed methodology and positively influenced the students' academic progress.

  • OpenGnSys: Centralized management and deployment of operating systems in the classroom
    2013
    Co-Authors: D. Pardo Garrido, T.j. Mateo Sanguino, D. A. Lopez Garcia, E. Cortés Ancos, I. J. Fernandez De Viana Gonzalez
    Abstract:

    This paper presents a complete system for management, maintenance, and deployment of operating systems called OpenGnSys. Such a system has been tested in a real teaching laboratory at the University of Huelva, Spain, which is devoted to practical works on networking. OpenGnSys operations, performed in an easy and intuitive way from a graphical console with remote functions, are managed by a High Availability Cluster. Its implementation provides a dual backup function of both hardware infrastructure and classroom operating services. In addition to lab management, we propose a quality control procedure by site acceptance tests. These tests stand for a standard methodology for determining the compliance degree according to classroom operation and specifications. As a result, this methodology has reduced the effort in classroom administration and operation.

Rong-tai Liu - One of the best experts on this subject based on the ideXlab platform.

  • ICC - Flow Digest: A State Replication Scheme for Stateful High Availability Cluster
    2007 IEEE International Conference on Communications, 2007
    Co-Authors: Yi-hsuan Feng, Nen-fu Huang, Rong-tai Liu
    Abstract:

    Stateful tracking is a popular technique in firewall filtering and state replication is used to provide reliable connectivity. This paper proposes a new approach for improving existing state replication protocols which ensure state consistency amongst the nodes of a stateful HA Cluster. Our goal is to develop a new scheme which reduces the update overhead in the face of both low and High connection loads in order to maximize the capacity and scalability of a High Availability Cluster. A new representation called flow digest is proposed. Also the ways to use flow digest structures to update state changes, recover the connections after a failover, and solve the state inconsistency are presented. The main advantage of the proposed method is to reduce the bandwidth consumption on state replication. The simulation results show that the proposed scheme reduces the number of update messages and, more importantly, eliminates typically at least 86% of bandwidth consumption compared to current solutions.