International Parallel Data Systems Workshop最新文献

Automatic and transparent I/O optimization with storage integrated application runtime support 具有存储集成应用程序运行时支持的自动透明I/O优化

International Parallel Data Systems Workshop Pub Date : 2015-11-15 DOI: 10.1145/2834976.2834983

Noah Watkins, Zhihao Jia, G. Shipman, C. Maltzahn, A. Aiken, P. McCormick

引用次数: 5

Comparative I/O workload characterization of two leadership class storage clusters 比较两个领导级存储集群的I/O工作负载特性

International Parallel Data Systems Workshop Pub Date : 2015-11-15 DOI: 10.1145/2834976.2834985

Raghul Gunasekaran, S. Oral, Jason Hill, Ross G. Miller, Feiyi Wang, Dustin Leverman

{"title":"Comparative I/O workload characterization of two leadership class storage clusters","authors":"Raghul Gunasekaran, S. Oral, Jason Hill, Ross G. Miller, Feiyi Wang, Dustin Leverman","doi":"10.1145/2834976.2834985","DOIUrl":"https://doi.org/10.1145/2834976.2834985","url":null,"abstract":"The Oak Ridge Leadership Computing Facility (OLCF) is a leader in large-scale parallel file system development, design, deployment and continuous operation. For the last decade, the OLCF has designed and deployed two large center-wide parallel file systems. The first instantiation, Spider 1, served the Jaguar supercomputer and its predecessor, Spider 2, now serves the Titan supercomputer, among many other OLCF computational resources. The OLCF has been rigorously collecting file and storage system statistics from these Spider systems since their transition to production state.\u0000 In this paper we present the collected I/O workload statistics from the Spider 2 system and compare it to the Spider 1 data. Our analysis show that the Spider 2 workload is more more write-heavy I/O compared to Spider 1 (75% vs. 60%, respectively). The data also show the OLCF storage policies such as periodic purges are effectively managing the capacity resource of Spider 2. Furthermore, due to improvements in tdm_multipath and ib_srp software, we are utilizing the Spider 2 system bandwidth and latency resources more effectively. The Spider 2 bandwidth usage statistics shows that our system is working within the design specifications. However, it is also evident that our scientific applications can be more effectively served by a burst buffer storage layer. All the data has been collected by monitoring tools developed for the Spider ecosystem. We believe the observed data set and insights will help us better design the next-generation Spider file and storage system. It will also be helpful to the larger community for building more effective large-scale file and storage systems.","PeriodicalId":218652,"journal":{"name":"International Parallel Data Systems Workshop","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122223403","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 32

Tackling the reproducibility problem in storage systems research with declarative experiment specifications 用声明性实验规范解决存储系统研究中的可重复性问题

International Parallel Data Systems Workshop Pub Date : 2015-11-15 DOI: 10.1145/2834976.2834979

I. Jimenez, C. Maltzahn, J. Lofstead, A. Moody, K. Mohror, Remzi H. Arpaci-Dusseau, A. Arpaci-Dusseau

引用次数: 5

Pattern-driven parallel I/O tuning 模式驱动的并行I/O优化

International Parallel Data Systems Workshop Pub Date : 2015-11-15 DOI: 10.1145/2834976.2834977

Babak Behzad, S. Byna, Prabhat, M. Snir

{"title":"Pattern-driven parallel I/O tuning","authors":"Babak Behzad, S. Byna, Prabhat, M. Snir","doi":"10.1145/2834976.2834977","DOIUrl":"https://doi.org/10.1145/2834976.2834977","url":null,"abstract":"The contemporary parallel I/O software stack is complex due to a large number of configurations for tuning I/O performance. Without a proper configuration, I/O becomes a performance bottleneck. As high performance computing (HPC) is moving towards exascale, poor I/O performance has a significant impact on the runtime of large-scale simulations producing massive amounts of data. In this paper, we focus on developing a framework for tuning parallel I/O configurations automatically. This auto-tuning framework first traces high-level I/O accesses and analyzes data write patterns. Based on these patterns and historically available tuning parameters for similar patterns, the framework selects best performing configurations at runtime. If previous history for a pattern is unavailable, the framework initiates model-based training to acquire efficient set of tuning parameters. Our framework includes a runtime system to apply the selected configurations using dynamic linking, without the need for changing application source code. In this paper, we describe this framework and evaluate it using multiple I/O kernels extracted from real applications and demonstrate substantial I/O performance improvement.","PeriodicalId":218652,"journal":{"name":"International Parallel Data Systems Workshop","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122744411","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 27

Experiences in using os-level virtualization for block I/O 对块I/O使用操作系统级虚拟化的经验

International Parallel Data Systems Workshop Pub Date : 2015-11-15 DOI: 10.1145/2834976.2834982

Dan Huang, Jun Wang, Qing Liu, Jiangling Yin, Xuhong Zhang, Xunchao Chen

{"title":"Experiences in using os-level virtualization for block I/O","authors":"Dan Huang, Jun Wang, Qing Liu, Jiangling Yin, Xuhong Zhang, Xunchao Chen","doi":"10.1145/2834976.2834982","DOIUrl":"https://doi.org/10.1145/2834976.2834982","url":null,"abstract":"Today, HPC clusters commonly use Resource Management Systems such as PBS and TORQUE to share physical resources. These systems enable resources to be shared by assigning nodes to users exclusively in non-overlapping time slots. With virtualization technology, users can run their applications on the same node with low mutual interference. However, the overhead introduced by the virtual machine monitor or hypervisor is too high to be accepted, because efficiency is key to many HPC applications. OS-level virtualization (such as Linux Containers) offers a lightweight virtualization layer, which promises a near-native performance and is adopted by some BigData resource sharing platforms such as Mesos. Nevertheless, OS-level virtualization's overhead and isolation on block devices have not been completely evaluated, especially when applied to a shared distributed/parallel file system (D/PFS) such as HDFS or Lustre. In this paper, we thoroughly evaluate the overhead and isolation involved in sharing block I/O via OS-level virtualization on the local disk and D/PFSs. Meanwhile, to assign D/PFS storage resources to users, a middleware system is proposed and implemented to bridge the configuration gap between virtual clusters and remote D/PFSs.","PeriodicalId":218652,"journal":{"name":"International Parallel Data Systems Workshop","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130152692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Heavy-tailed distribution of parallel I/O system response time 并行I/O系统响应时间的重尾分布

International Parallel Data Systems Workshop Pub Date : 2015-11-15 DOI: 10.1145/2834976.2834978

Bin Dong, S. Byna, Kesheng Wu

{"title":"Heavy-tailed distribution of parallel I/O system response time","authors":"Bin Dong, S. Byna, Kesheng Wu","doi":"10.1145/2834976.2834978","DOIUrl":"https://doi.org/10.1145/2834976.2834978","url":null,"abstract":"Estimating I/O time of applications is critical for computing system research and developments, such as performance tuning and job scheduling. Parallel I/O systems on large-scale HPC systems typically use several I/O servers attached to a number of hard disk drives to read and write data concurrently. As a result, the response time of individual I/O servers affects the overall I/O performance and modeling the response time distribution holds the key to estimate I/O time. Existing studies have generally considered that the response time follows a Uniform or a Normal distribution. However, none of these studies considered supercomputing environments that are actively used by a number of users to verify the existence of Uniform or Normal distributions. In this study, we collected ≈ 2,500,000 measurements on two peta-scale class supercomputers that are actively used by ≈5000 users. These two systems, Hopper and Edison at the National Energy Research Scientific Computing Center (NERSC), typically support hundreds of concurrent jobs. Our performance measurements include the overheads introduced by the entire parallel I/O stack (I/O library, network, parallel file system software, cache and hardware). Our study shows that the response time of parallel I/O system follows a heavy-tailed property, in contrary to the widely accepted Normal or Uniform distributions. In exploring for new models, we identify that a mix of Power Law and Normal distributions is a good fit for the response time of parallel I/O systems that are actively used by hundreds of jobs concurrently.","PeriodicalId":218652,"journal":{"name":"International Parallel Data Systems Workshop","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114787009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

BAD-check: bulk asynchronous distributed checkpointing 坏检查:批量异步分布式检查点

International Parallel Data Systems Workshop Pub Date : 2015-11-15 DOI: 10.1145/2834976.2834981

John Bent, B. Settlemyer, Haiyun Bao, S. Faibish, J. Sauer, Jingwang Zhang

引用次数: 2

Taming the cloud object storage with MOS 用MOS驯服云对象存储

International Parallel Data Systems Workshop Pub Date : 2015-11-15 DOI: 10.1145/2834976.2834980

Ali Anwar, Yue Cheng, Aayush Gupta, A. Butt

引用次数: 24

pNFS/PVFS2 over InfiniBand: early experiences pNFS/PVFS2 over InfiniBand:早期体验

International Parallel Data Systems Workshop Pub Date : 2007-11-11 DOI: 10.1145/1374596.1374599

Lei Chai, Xiangyong Ouyang, R. Noronha, D. Panda

{"title":"pNFS/PVFS2 over InfiniBand: early experiences","authors":"Lei Chai, Xiangyong Ouyang, R. Noronha, D. Panda","doi":"10.1145/1374596.1374599","DOIUrl":"https://doi.org/10.1145/1374596.1374599","url":null,"abstract":"The computing power of clusters has been rapidly growing up towards petascale capability, which requires petascale I/O systems to provide data in a sustained high-throughput manner. Network File System (NFS), a ubiquitous standard used in most existing clusters, has shown performance bottleneck associated with the single server model. pNFS, a parallel version of NFS, has been proposed in this context to eliminate the performance bottleneck while maintain the ease of management and interoperability features of NFS. With InfiniBand being one of the most popular high speed networks for clusters, whether pNFS can pick up the advantages of InfiniBand is an interesting and important question. It is also important to quantify and understand the potential benefits of using pNFS compared with the single server NFS, and the possible overhead associated with pNFS. However, since pNFS is relatively new, few such study has been carried out in an InfiniBand cluster environment. In this paper we have designed and carried out a set of experiments to study the performance and scalability of pNFS, using PVFS2 as the backend file system. The aim is to understand the characteristics of pNFS, and its feasibility as the parallel file system solution for clusters. From our experimental results we observer that pNFS can take advantages of high speed networks such as InfiniBand, and achieve up to 480% improvement in throughput compared with using GigE as the transport. pNFS can eliminate the single server bottleneck associated with NFS. pNFS/PVFS2 shows significantly higher throughput and better scalability compared with NFS/PVFS2. pNFS/PVFS2 achieves peak write throughput about 490MB/s, and read throughput about 2250MB/s, with 4 I/O servers. With 8 I/O servers, the numbers are 754MB/s and 3100MB/s. Further, we find that pNFS adds little overhead and achieves almost the same throughput as the backend file system PVFS2. Our results indicate that pNFS is promising as the parallel file system solution for clusters.","PeriodicalId":218652,"journal":{"name":"International Parallel Data Systems Workshop","volume":"66 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114048517","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 16

Scalable locking and recovery for network file systems 网络文件系统的可伸缩锁定和恢复

International Parallel Data Systems Workshop Pub Date : 2007-11-11 DOI: 10.1145/1374596.1374601

P. Braam

引用次数: 6