权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

SHF: Small: Collaborative Research: Uncovering Vulnerabilities in Parallel File Systems for Reliable High Performance Computing

SHF：小型：协作研究：发现并行文件系统中的漏洞以实现可靠的高性能计算

基本信息

批准号：
1718336
负责人：
Yong Chen
金额：
$ 23.3万
依托单位：
Texas Tech University
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2017
资助国家：
美国
起止时间：
2017-08-15 至 2023-07-31
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1718336&HistoricalAwards=false
关键词：
SHF Small Collaborative Research Uncovering

项目摘要

Many scientific problems (e.g., computational biology, high-energy physics, climate science) rely on high performance computing (HPC) systems to manage and process massive amounts of data. However, with the rapid increase in scale and complexity, even the specially-designed and well-maintained HPC platforms may fail. This research aims to design innovative methodologies that scrutinize parallel file systems, the major storage software which empowers HPC platforms, and uncover the issues in parallel file systems that can lead to data loss under various failure scenarios. Such an effort is a fundamental step towards building highly reliable HPC systems and meet the demand of data-driven scientific discovery. In addition, this project integrates the research activities with education and outreach efforts to train broadly inclusive and globally competitive science workforce.More specifically, this project includes two synergistic research tasks, which enables automatic testing as well as diagnosing the issues in parallel file systems. The first task focuses on testing parallel file systems through a single-fault injection framework, which interrupts the normal workloads of the target parallel file system automatically, and examines if the interruption could lead to any issues that cannot be fixed by the corresponding checker of the parallel file system. Building on the first task, the second task focuses on diagnosing the issues uncovered in the previous task through a two-level provenance-based analysis. The first level analysis builds the coarse-grain, inter-node provenance, which provides a high-level picture of the entire system behavior. The second level analysis creates the fine-grain, intra-node provenance that contains causal paths within each individual node. In addition, multiple provenance traces are aligned and compared automatically to help locate the problematic code region with minimal human efforts.

许多科学问题（例如，计算生物学、高能物理学、气候科学）依赖于高性能计算（HPC）系统来管理和处理大量数据。然而，随着规模和复杂性的快速增加，即使是专门设计且维护良好的HPC平台也可能会失败。这项研究旨在设计创新的方法，审查并行文件系统，主要的存储软件，使HPC平台，并发现并行文件系统中的问题，可能导致数据丢失的各种故障情况下。这样的努力是构建高度可靠的HPC系统和满足数据驱动的科学发现需求的基本步骤。此外，该项目将研究活动与教育和推广工作相结合，以培养具有广泛包容性和全球竞争力的科学人才。更具体地说，该项目包括两个协同研究任务，这使得能够自动测试以及诊断并行文件系统中的问题。第一个任务是通过一个单故障注入框架对并行文件系统进行测试，该框架自动中断目标并行文件系统的正常工作负载，并检查中断是否会导致并行文件系统的相应检查器无法修复的任何问题。在第一项任务的基础上，第二项任务侧重于通过基于出处的两级分析来诊断前一项任务中发现的问题。第一级分析构建粗粒度的节点间起源，它提供了整个系统行为的高级描述。第二级分析创建了细粒度的节点内起源，其中包含每个节点内的因果路径。此外，多个起源跟踪会自动对齐和比较，以帮助以最少的人力定位有问题的代码区域。

项目成果

期刊论文数量（10）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

PRS: A Pattern-Directed Replication Scheme for Heterogeneous Object-Based Storage

DOI：
10.1109/tc.2019.2954089
发表时间：
2020-04
期刊：
IEEE Transactions on Computers
影响因子：
3.7
作者：
Jiang Zhou;Yong Chen;Wei Xie;Dong Dai;Shuibing He;Weiping Wang
通讯作者：
Jiang Zhou;Yong Chen;Wei Xie;Dong Dai;Shuibing He;Weiping Wang

AKIN: A Streaming Graph Partitioning Algorithm for Distributed Graph Storage Systems

DOI：
10.1109/ccgrid.2018.00033
发表时间：
2018-05
期刊：
2018 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID)
影响因子：
0
作者：
Wei Zhang-;Yong Chen;Dong Dai
通讯作者：
Wei Zhang-;Yong Chen;Dong Dai

Data Distribution for Heterogeneous Storage Systems

DOI：
10.1109/tc.2022.3223302
发表时间：
2023-06
期刊：
IEEE Transactions on Computers
影响因子：
3.7
作者：
Jiang Zhou;Yong Chen;Mai Zheng;Weiping Wang
通讯作者：
Jiang Zhou;Yong Chen;Mai Zheng;Weiping Wang

RaiderSTREAM: Adapting the STREAM Benchmark to Modern HPC Systems

RaiderSTREAM：使 STREAM 基准适应现代 HPC 系统

DOI：
10.1109/hpec55821.2022.9926292
发表时间：
2022
期刊：
Proccedings of the 27th IEEE High Performance Extreme Computing Conference (HPEC'22
影响因子：
0
作者：
Beebe, Michael;Williams, Brody;Devaney, Stephen;Leidel, John;Chen, Yong;Poole, Steve
通讯作者：
Poole, Steve

HAM: Hotspot-Aware Manager for Improving Communications With 3D-Stacked Memory

HAM：热点感知管理器，用于改善 3D 堆栈内存的通信