The Experts below are selected from a list of 16059 Experts worldwide ranked by ideXlab platform
Bei Wang - One of the best experts on this subject based on the ideXlab platform.
-
Analyzing and Modeling the Performance in Xen-Based Virtual Cluster Environment
2010 IEEE 12th International Conference on High Performance Computing and Communications (HPCC), 2010Co-Authors: Kejiang Ye, Xiaohong Jiang, Siding Chen, Dawei Huang, Bei WangAbstract:Virtualization technology is currently widely used due to its benefits on high resource utilization, flexible manageability and powerful system security. However, its use for high performance computing (HPC) is still not popular due to the unclearness of the Virtualization overheads. It's worthy to evaluate the Virtualization cost and to find the performance bottleneck when running HPC applications in Virtual Cluster. We first evaluate the basic performance overheads due to Virtualization. Then we create a 16-node Virtual Cluster and perform a performance evaluation for both para-Virtualization and full Virtualization. After that, we evaluate the MPI (Message Passing Interface) scalability to investigate the impact of MPI and network communication between Virtual machines. In addition to the macro assessment, we use the Oprofile/Xenoprof to investigate the architecture characterization like CPU cycle, L2 cache misses, DTLB misses and ITLB misses which is an auxiliary explanation to the performance bottleneck. Experimental results indicate that performance overheads of Virtualization are acceptable for HPC, para-Virtualization is very suitable for HPC due to the high Virtualization efficiency and efficient inter-domain communication. Finally, we use the non-linear regression modeling technology to present a performance model for network latency and bandwidth to predict the performance in Virtual Cluster environment.
-
HPCC - Analyzing and Modeling the Performance in Xen-Based Virtual Cluster Environment
2010 IEEE 12th International Conference on High Performance Computing and Communications (HPCC), 2010Co-Authors: Xiaohong Jiang, Siding Chen, Dawei Huang, Bei WangAbstract:Virtualization technology is currently widely used due to its benefits on high resource utilization, flexible manageability and powerful system security. However, its use for high performance computing (HPC) is still not popular due to the unclearness of the Virtualization overheads. It's worthy to evaluate the Virtualization cost and to find the performance bottleneck when running HPC applications in Virtual Cluster. We first evaluate the basic performance overheads due to Virtualization. Then we create a 16-node Virtual Cluster and perform a performance evaluation for both para-Virtualization and full Virtualization. After that, we evaluate the MPI (Message Passing Interface) scalability to investigate the impact of MPI and network communication between Virtual machines. In addition to the macro assessment, we use the Oprofile/Xenoprof to investigate the architecture characterization like CPU cycle, L2 cache misses, DTLB misses and ITLB misses which is an auxiliary explanation to the performance bottleneck. Experimental results indicate that performance overheads of Virtualization are acceptable for HPC, para-Virtualization is very suitable for HPC due to the high Virtualization efficiency and efficient inter-domain communication. Finally, we use the non-linear regression modeling technology to present a performance model for network latency and bandwidth to predict the performance in Virtual Cluster environment.
Xiaohong Jiang - One of the best experts on this subject based on the ideXlab platform.
-
vc migration live migration of Virtual Clusters in the cloud
Grid Computing, 2012Co-Authors: Kejiang Ye, Xiaohong JiangAbstract:Live migration of Virtual machines (VM) has recently become a key ingredient behind the management activities of cloud computing system to achieve the goals of load balancing, energy saving, failure recovery, and system maintenance. However, to our knowledge, most of the previous live VM migration techniques concentrated on the migration of a single VM which means these techniques are insufficient when the whole Virtual Cluster or multiple Virtual Clusters need to be migrated. This paper investigates various live migration strategies for Virtual Clusters (VC). We first describe a framework VC-Migration to control the migration of Virtual Clusters. Then we perform a series of experiments to study the performance and overheads of different migration strategies for Virtual Clusters, including concurrent migration, mutual migration, homogeneous VC migration, and heterogeneous VC migration. After that, we present several optimization principles to improve the migration performance of Virtual Clusters. The HPCC benchmark is selected to represent the Virtual Cluster workloads, and the metrics such as downtime, total migration time, and workload performance are measured. Experimental results reveal some new discoveries which are useful to the future development of new migration mechanisms and algorithms to optimize the migration of Virtual Clusters.
-
GRID - VC-Migration: Live Migration of Virtual Clusters in the Cloud
2012 ACM IEEE 13th International Conference on Grid Computing, 2012Co-Authors: Xiaohong Jiang, Fengxi YanAbstract:Live migration of Virtual machines (VM) has recently become a key ingredient behind the management activities of cloud computing system to achieve the goals of load balancing, energy saving, failure recovery, and system maintenance. However, to our knowledge, most of the previous live VM migration techniques concentrated on the migration of a single VM which means these techniques are insufficient when the whole Virtual Cluster or multiple Virtual Clusters need to be migrated. This paper investigates various live migration strategies for Virtual Clusters (VC). We first describe a framework VC-Migration to control the migration of Virtual Clusters. Then we perform a series of experiments to study the performance and overheads of different migration strategies for Virtual Clusters, including concurrent migration, mutual migration, homogeneous VC migration, and heterogeneous VC migration. After that, we present several optimization principles to improve the migration performance of Virtual Clusters. The HPCC benchmark is selected to represent the Virtual Cluster workloads, and the metrics such as downtime, total migration time, and workload performance are measured. Experimental results reveal some new discoveries which are useful to the future development of new migration mechanisms and algorithms to optimize the migration of Virtual Clusters.
-
Analyzing and Modeling the Performance in Xen-Based Virtual Cluster Environment
2010 IEEE 12th International Conference on High Performance Computing and Communications (HPCC), 2010Co-Authors: Kejiang Ye, Xiaohong Jiang, Siding Chen, Dawei Huang, Bei WangAbstract:Virtualization technology is currently widely used due to its benefits on high resource utilization, flexible manageability and powerful system security. However, its use for high performance computing (HPC) is still not popular due to the unclearness of the Virtualization overheads. It's worthy to evaluate the Virtualization cost and to find the performance bottleneck when running HPC applications in Virtual Cluster. We first evaluate the basic performance overheads due to Virtualization. Then we create a 16-node Virtual Cluster and perform a performance evaluation for both para-Virtualization and full Virtualization. After that, we evaluate the MPI (Message Passing Interface) scalability to investigate the impact of MPI and network communication between Virtual machines. In addition to the macro assessment, we use the Oprofile/Xenoprof to investigate the architecture characterization like CPU cycle, L2 cache misses, DTLB misses and ITLB misses which is an auxiliary explanation to the performance bottleneck. Experimental results indicate that performance overheads of Virtualization are acceptable for HPC, para-Virtualization is very suitable for HPC due to the high Virtualization efficiency and efficient inter-domain communication. Finally, we use the non-linear regression modeling technology to present a performance model for network latency and bandwidth to predict the performance in Virtual Cluster environment.
-
HPCC - Analyzing and Modeling the Performance in Xen-Based Virtual Cluster Environment
2010 IEEE 12th International Conference on High Performance Computing and Communications (HPCC), 2010Co-Authors: Xiaohong Jiang, Siding Chen, Dawei Huang, Bei WangAbstract:Virtualization technology is currently widely used due to its benefits on high resource utilization, flexible manageability and powerful system security. However, its use for high performance computing (HPC) is still not popular due to the unclearness of the Virtualization overheads. It's worthy to evaluate the Virtualization cost and to find the performance bottleneck when running HPC applications in Virtual Cluster. We first evaluate the basic performance overheads due to Virtualization. Then we create a 16-node Virtual Cluster and perform a performance evaluation for both para-Virtualization and full Virtualization. After that, we evaluate the MPI (Message Passing Interface) scalability to investigate the impact of MPI and network communication between Virtual machines. In addition to the macro assessment, we use the Oprofile/Xenoprof to investigate the architecture characterization like CPU cycle, L2 cache misses, DTLB misses and ITLB misses which is an auxiliary explanation to the performance bottleneck. Experimental results indicate that performance overheads of Virtualization are acceptable for HPC, para-Virtualization is very suitable for HPC due to the high Virtualization efficiency and efficient inter-domain communication. Finally, we use the non-linear regression modeling technology to present a performance model for network latency and bandwidth to predict the performance in Virtual Cluster environment.
Siding Chen - One of the best experts on this subject based on the ideXlab platform.
-
Analyzing and Modeling the Performance in Xen-Based Virtual Cluster Environment
2010 IEEE 12th International Conference on High Performance Computing and Communications (HPCC), 2010Co-Authors: Kejiang Ye, Xiaohong Jiang, Siding Chen, Dawei Huang, Bei WangAbstract:Virtualization technology is currently widely used due to its benefits on high resource utilization, flexible manageability and powerful system security. However, its use for high performance computing (HPC) is still not popular due to the unclearness of the Virtualization overheads. It's worthy to evaluate the Virtualization cost and to find the performance bottleneck when running HPC applications in Virtual Cluster. We first evaluate the basic performance overheads due to Virtualization. Then we create a 16-node Virtual Cluster and perform a performance evaluation for both para-Virtualization and full Virtualization. After that, we evaluate the MPI (Message Passing Interface) scalability to investigate the impact of MPI and network communication between Virtual machines. In addition to the macro assessment, we use the Oprofile/Xenoprof to investigate the architecture characterization like CPU cycle, L2 cache misses, DTLB misses and ITLB misses which is an auxiliary explanation to the performance bottleneck. Experimental results indicate that performance overheads of Virtualization are acceptable for HPC, para-Virtualization is very suitable for HPC due to the high Virtualization efficiency and efficient inter-domain communication. Finally, we use the non-linear regression modeling technology to present a performance model for network latency and bandwidth to predict the performance in Virtual Cluster environment.
-
HPCC - Analyzing and Modeling the Performance in Xen-Based Virtual Cluster Environment
2010 IEEE 12th International Conference on High Performance Computing and Communications (HPCC), 2010Co-Authors: Xiaohong Jiang, Siding Chen, Dawei Huang, Bei WangAbstract:Virtualization technology is currently widely used due to its benefits on high resource utilization, flexible manageability and powerful system security. However, its use for high performance computing (HPC) is still not popular due to the unclearness of the Virtualization overheads. It's worthy to evaluate the Virtualization cost and to find the performance bottleneck when running HPC applications in Virtual Cluster. We first evaluate the basic performance overheads due to Virtualization. Then we create a 16-node Virtual Cluster and perform a performance evaluation for both para-Virtualization and full Virtualization. After that, we evaluate the MPI (Message Passing Interface) scalability to investigate the impact of MPI and network communication between Virtual machines. In addition to the macro assessment, we use the Oprofile/Xenoprof to investigate the architecture characterization like CPU cycle, L2 cache misses, DTLB misses and ITLB misses which is an auxiliary explanation to the performance bottleneck. Experimental results indicate that performance overheads of Virtualization are acceptable for HPC, para-Virtualization is very suitable for HPC due to the high Virtualization efficiency and efficient inter-domain communication. Finally, we use the non-linear regression modeling technology to present a performance model for network latency and bandwidth to predict the performance in Virtual Cluster environment.
Dawei Huang - One of the best experts on this subject based on the ideXlab platform.
-
Analyzing and Modeling the Performance in Xen-Based Virtual Cluster Environment
2010 IEEE 12th International Conference on High Performance Computing and Communications (HPCC), 2010Co-Authors: Kejiang Ye, Xiaohong Jiang, Siding Chen, Dawei Huang, Bei WangAbstract:Virtualization technology is currently widely used due to its benefits on high resource utilization, flexible manageability and powerful system security. However, its use for high performance computing (HPC) is still not popular due to the unclearness of the Virtualization overheads. It's worthy to evaluate the Virtualization cost and to find the performance bottleneck when running HPC applications in Virtual Cluster. We first evaluate the basic performance overheads due to Virtualization. Then we create a 16-node Virtual Cluster and perform a performance evaluation for both para-Virtualization and full Virtualization. After that, we evaluate the MPI (Message Passing Interface) scalability to investigate the impact of MPI and network communication between Virtual machines. In addition to the macro assessment, we use the Oprofile/Xenoprof to investigate the architecture characterization like CPU cycle, L2 cache misses, DTLB misses and ITLB misses which is an auxiliary explanation to the performance bottleneck. Experimental results indicate that performance overheads of Virtualization are acceptable for HPC, para-Virtualization is very suitable for HPC due to the high Virtualization efficiency and efficient inter-domain communication. Finally, we use the non-linear regression modeling technology to present a performance model for network latency and bandwidth to predict the performance in Virtual Cluster environment.
-
HPCC - Analyzing and Modeling the Performance in Xen-Based Virtual Cluster Environment
2010 IEEE 12th International Conference on High Performance Computing and Communications (HPCC), 2010Co-Authors: Xiaohong Jiang, Siding Chen, Dawei Huang, Bei WangAbstract:Virtualization technology is currently widely used due to its benefits on high resource utilization, flexible manageability and powerful system security. However, its use for high performance computing (HPC) is still not popular due to the unclearness of the Virtualization overheads. It's worthy to evaluate the Virtualization cost and to find the performance bottleneck when running HPC applications in Virtual Cluster. We first evaluate the basic performance overheads due to Virtualization. Then we create a 16-node Virtual Cluster and perform a performance evaluation for both para-Virtualization and full Virtualization. After that, we evaluate the MPI (Message Passing Interface) scalability to investigate the impact of MPI and network communication between Virtual machines. In addition to the macro assessment, we use the Oprofile/Xenoprof to investigate the architecture characterization like CPU cycle, L2 cache misses, DTLB misses and ITLB misses which is an auxiliary explanation to the performance bottleneck. Experimental results indicate that performance overheads of Virtualization are acceptable for HPC, para-Virtualization is very suitable for HPC due to the high Virtualization efficiency and efficient inter-domain communication. Finally, we use the non-linear regression modeling technology to present a performance model for network latency and bandwidth to predict the performance in Virtual Cluster environment.
Yunmook Nah - One of the best experts on this subject based on the ideXlab platform.
-
DASFAA (1) - Performance Comparison of Distributed Processing of Large Volume of Data on Top of Xen and Docker-Based Virtual Clusters
Database Systems for Advanced Applications, 2017Co-Authors: Haejin Chung, Yunmook NahAbstract:Recently, with the advent of cloud computing, it becomes essential to run distributed computing tasks, such as Hadoop MapReduce tasks, on top of Virtual computing nodes instead of physical computing nodes. But, distributed big data processing on top of Virtual machines usually causes unbalanced use of physical resources, such as memory, disk I/O and network resources, thus resulting in severe performance problems. In this paper, we show how Virtualization methods affect distributed processing of very large volume of data, by comparing Hadoop MapReduce processing performance on top of Xen-based Virtual Clusters versus Docker-based Virtual Clusters. In our experiments, we compare the performance of two different Virtual Clusters by changing Virtualization methods, block sizes and node numbers. Our results show that, in terms of the distributed big data processing performance, Docker-based Virtual Cluster is usually faster than Xen-based Virtual Cluster, but there exist some cases where Xen is faster than Docker according to the parameters, such as block size and Virtual node numbers.
