Filters








161 Hits in 3.6 sec

PVFS over InfiniBand: design and performance evaluation

J. Wu, P. Wyckoff, Dhabaleswar Panda
2003 2003 International Conference on Parallel Processing, 2003. Proceedings.  
To the best of our knowledge, this is the first design, implementation and evaluation of PVFS over InfiniBand.  ...  In this paper, we design and implement a PVFS version on InfiniBand by taking advantage of InfiniBand features and resolving many challenging issues.  ...  Acknowledgments: We would like to thank the PVFS team at Argonne National Laboratory and Clemson University for giving us the access to the latest version of PVFS implementation and for providing us with  ... 
doi:10.1109/icpp.2003.1240573 dblp:conf/icpp/WuWP03 fatcat:cdy2wvjzargfjeiuzln32vv37q

Supporting efficient noncontiguous access in PVFS over Infiniband

Jiseheng Wu, Wyckoff, Panda
2003 Proceedings IEEE International Conference on Cluster Computing CLUSTR-03  
We have designed and incorporated this approach in a version of PVFS over InfiniBand.  ...  In this paper, we address noncontiguous data transmission between the client and the I/O server in cluster file systems over a high performance network.  ...  Acknowledgments We would like to thank the PVFS team at Argonne National Laboratory and Clemson University for giving us access to the latest versions of PVFS and for providing us with crucial insights  ... 
doi:10.1109/clustr.2003.1253333 dblp:conf/cluster/WuWP03 fatcat:zesr2ucmyban7e3fmo6jegahqy

Design and evaluation of a high performance parallel file system

Li Ou, Xubin He, S.L. Scott, Zhiyong Xu, Yung-chin Fang
2005 The IEEE Conference on Local Computer Networks 30th Anniversary (LCN'05)l  
Our simulation results show that using same number of total nodes, iPVFS outperforms PVFS for both small requests and large requests under different workloads.  ...  In this paper we propose a high performance parallel file system over iSCSI (iPVFS) for cluster computing. iPVFS provides a cost-effective solution for heterogeneous cluster environment by dividing a set  ...  Powe Junior Faculty Enhancement Award, and the Mathematics, Information and Computational Sciences Office, Office of Advanced Scientific Computing Research, Office of Science, U. S.  ... 
doi:10.1109/lcn.2005.50 dblp:conf/lcn/OuH05 fatcat:bpmexesvuvakrimisemzriyoam

RDMA-Based Job Migration Framework for MPI over InfiniBand

Xiangyong Ouyang, Sonya Marcarelli, Raghunath Rajachandrasekar, Dhabaleswar K. Panda
2010 2010 IEEE International Conference on Cluster Computing  
RDMA-based process image transmission is designed to take advantage of high performance communication in InfiniBand.  ...  To the best of our knowledge, this is the first such job migration design for InfiniBand-based clusters.  ...  SOFTWARE DISTRIBUTION The proposed design will be included in an upcoming MVAPICH2 release.  ... 
doi:10.1109/cluster.2010.20 dblp:conf/cluster/OuyangMRP10 fatcat:ry5mtauklbdmpi7242hshh7rny

High performance RDMA-based design of HDFS over InfiniBand

N. S. Islam, M. W. Rahman, J. Jose, R. Rajachandrasekar, H. Wang, H. Subramoni, C. Murthy, D. K. Panda
2012 2012 International Conference for High Performance Computing, Networking, Storage and Analysis  
For HBase, the Put operation performance is improved by 26% with our design. To the best of our knowledge, this is the first design of HDFS over InfiniBand networks.  ...  Experimental results show that, for 5GB HDFS file writes, the new design reduces the communication time by 87% and 30% over 1Gigabit Ethernet (1GigE) and IP-over-InfiniBand (IPoIB), respectively, on QDR  ...  In HPC field, RDMA has been used to speed up file systems I/O performance. Wu et. al designed the PVFS over InfiniBand to improve PVFS I/O performance [39] .  ... 
doi:10.1109/sc.2012.65 dblp:conf/sc/IslamWJRWSMP12 fatcat:z3qahxdfdjcsrd73uikhlzhcya

Tutorial: Designing High-End Computing Systems with Infiniband and 10-Gigabit Ethernet

Dhabaleswar K. Panda, Matthew J. Koop, Pavan Balaji
2009 2009 17th IEEE Symposium on High Performance Interconnects  
with the associated performance numbers and comparisons.  ...  As InfiniBand Architecture (IB) and 10-Gigabit Ethernet (10GE) technologies mature in their support for next generation high-end Computing (HEC) systems, more and more scientists, engineers and researchers  ...  Designing High-end Systems with InfiniBand and iWARP: Research Challenges, Case Studies and Performance Evaluation • High-end clusters with MPI-1 and MPI-2 • Storage and File Systems (PVFS, Lustre  ... 
doi:10.1109/hoti.2009.36 dblp:conf/hoti/PandaKB09a fatcat:by7qo3ly4vgzzjy7x652rwhy5y

High Performance Block I/O for Global File System (GFS) with InfiniBand RDMA

Shuang Liang, Weikuan Yu, Dhabaleswar K. Panda
2006 2006 International Conference on Parallel Processing (ICPP'06)  
performance over 10Gbps InfiniBand network.  ...  We evaluate this new scheme in comparison with our copy based scheme and TCP over the same InfiniBand hardware.  ...  Performance Evaluation To evaluate the impact of RDMA transport on GFS, we compare our zero copy based RDMA scheme with TCP over IPoIB, an IP emulation on the same InfiniBand hardware.  ... 
doi:10.1109/icpp.2006.47 dblp:conf/icpp/LiangYP06 fatcat:nyxne57ptbdvfi7jlt4dmhqq4y

High Performance Checksum Computation for Fault-Tolerant MPI over Infiniband [chapter]

Alexandre Denis, Francois Trahay, Yutaka Ishikawa
2012 Lecture Notes in Computer Science  
We study the impact of checksums on network communication performance and we propose a mechanism to amortize their cost on InfiniBand.  ...  Our evaluation shows that our mechanisms to ensure message integrity do not impact noticeably the application performance, which is an improvement over the state of the art MPI implementations.  ...  Experiments presented in this paper were carried out using the Grid'5000 experimental testbed, being developed under the INRIA ALADDIN development action with support from CNRS, RENATER and several Universities  ... 
doi:10.1007/978-3-642-33518-1_23 fatcat:au4ejunbqfbvhnbmivbtdcnss4

Minimizing Network Contention in InfiniBand Clusters with a QoS-Aware Data-Staging Framework

Raghunath Rajachandrasekar, Jai Jaswani, Hari Subramoni, Dhabaleswar K. Panda
2012 2012 IEEE International Conference on Cluster Computing  
We leverage the Quality-of-Service (QoS) capabilities of the widely used InfiniBand interconnect to enhance our data-staging filesystem, making it QoS-aware.  ...  This is a user-level framework that is agnostic of the filesystem and MPI implementation.  ...  EXPERIMENTAL EVALUATION In this section, we present the results of our experiments that evaluate the benefits of the proposed design with some micro-benchmarks and some real-world MPI applications.  ... 
doi:10.1109/cluster.2012.90 dblp:conf/cluster/RajachandrasekarJSP12 fatcat:2dj2z5l7xnbirjka5nmzxkw43y

Unifier: Unifying cache management and communication buffer management for PVFS over intiniband

Jiesheng Wu, P. Wyckoff, D. Pandal, R. Ross
IEEE International Symposium on Cluster Computing and the Grid, 2004. CCGrid 2004.  
This paper presents the design and implementation of Unifier. This component has been deployed and evaluated in a version of PVFS1 implementation over InfiniBand.  ...  Experimental results show performance improvements between 30% and 70% over other approaches. Better scalability is also achieved by the PVFS I/O servers.  ...  Acknowledgments We are grateful to Phil Carns from Clemson University for providing us many insights into PVFS2 and many helps during our design and implementation.  ... 
doi:10.1109/ccgrid.2004.1336646 dblp:conf/ccgrid/WuWPR04 fatcat:nf3oyqlimjhonclepadrvn25oy

Modeling a Leadership-Scale Storage System [chapter]

Ning Liu, Christopher Carothers, Jason Cope, Philip Carns, Robert Ross, Adam Crume, Carlos Maltzahn
2012 Lecture Notes in Computer Science  
In this paper, we present the Co-design of Exascale Storage System (CODES) framework for evaluating exascale storage system design points.  ...  While physical implementations of these systems are currently not available, HPC system designers can develop models of exascale systems to evaluate system design points.  ...  Acknowledgments We thank Kevin Harms (ALCF) for his insight on Intrepid's PVFS storage system and helping us better understand its production configuration.  ... 
doi:10.1007/978-3-642-31464-3_2 fatcat:qk5pwdae3jcwrpmsvpflqgrzti

Sockets direct procotol over infiniband in clusters: Is it beneficial?

P. Balaji, S. Narravula, K. Vaidyanathan, S. Krishnamoorthy, J. Wu, D.K. Panda
IEEE International Symposium on - ISPASS Performance Analysis of Systems and Software, 2004  
Next, we evaluate it on two real application domains: (1) A multi-tier Data-Center environment and (2) A Parallel Virtual File System (PVFS).  ...  Our microbenchmark results show that SDP is able to provide up to 2.7 times better bandwidth as compared to the native sockets implementation over InfiniBand (IPoIB) and significantly better latency for  ...  Lastly, we would like to thank the PVFS team at the Argonne National Laboratory and Clemson University for giving us access to the latest version of the PVFS implementation and for providing us with crucial  ... 
doi:10.1109/ispass.2004.1291353 dblp:conf/ispass/BalajiNVKWP04 fatcat:v3zakbjitnbcdnzetfeoo2gqxa

Head-to-TOE Evaluation of High-Performance Sockets over Protocol Offload Engines

P. Balaji, W. Feng, Q. Gao, R. Noronha, W. Yu, D. K. Panda
2005 Proceedings IEEE International Conference on Cluster Computing  
Therefore, we present performance evaluations across 10GigE, IBA, and Myrinet (with identical cluster-compute nodes) in order to enable a coherent comparison with respect to the sockets interface.  ...  Specifically, we evaluate the network technologies at two levels: (i) a detailed micro-benchmark evaluation and (ii) an application-level evaluation with sample applications from different domains, including  ...  MPI-Tile-IO over PVFS We evaluate both the read and write performance of MPI-Tile-IO over PVFS.  ... 
doi:10.1109/clustr.2005.347068 dblp:conf/cluster/BalajiFGNYP05 fatcat:jxxjo3t42rds3nvtktzrow6fei

Cloud versus in-house cluster

Yan Zhai, Mingliang Liu, Jidong Zhai, Xiaosong Ma, Wenguang Chen
2011 State of the Practice Reports on - SC '11  
In addition, our detailed benchmarking and profiling discloses and analyzes several problems regarding the performance and performance stability on EC2.  ...  and applications with scale and problem size unprecedented in previous cloud HPC studies. 3) We perform detailed performance and scalability analysis to locate the chief limiting factors of the state-of-the-art  ...  ., especially Scott McMillan, Nan Qiao, and Bob Kuhn.  ... 
doi:10.1145/2063348.2063363 dblp:conf/sc/ZhaiLZMC11 fatcat:jzgpvj2wmzcvjlydb63wjyhxqq

Integrating parallel file systems with object-based storage devices

Ananth Devulapalli, Dennis Dalessandro, Pete Wyckoff, Nawab Ali, P. Sadayappan
2007 Proceedings of the 2007 ACM/IEEE conference on Supercomputing - SC '07  
In this work we present an implementation of the Parallel Virtual File System (PVFS) integrated with a software emulator of an OSD and describe an infrastructure for client access.  ...  As storage systems evolve, the block-based design of today's disks is becoming inadequate.  ...  Parallel Applications To evaluate application performance, we use two bench- marks that are designed to mimic full application behavior.  ... 
doi:10.1145/1362622.1362659 dblp:conf/sc/DevulapalliDWAS07 fatcat:tq4ej25vfvckbb5hipje6tcj6m
« Previous Showing results 1 — 15 out of 161 results