舒继武-尊龙网平台

 舒继武-尊龙网平台
舒继武 ieee fellow、杰青、长江学者、教授;博士生导师

研究方向:非易失性内存存储系统、闪存存储系统、分布式存储系统、数据存储可靠性与安全、近数据智能存算融合系统

所属部门:

电子邮件:

个人尊龙网平台主页:

个人简历:

社会兼职

l 中国计算机学会:第十二届理事会理事 (2020-);

l 中国计算机学会:信息存储技术专业委员会主任、常务委员 (2020-);

l 中国计算机学会:学术工委副主任  (2018-);

l 中国大数据智能计算专家委员会:副主任 (2019-2021);

l 中国通信学会:云计算和大数据应用委员会副主任委员 (2018-2021);

l 灾备技术国家工程实验室:副主任、技术委员会委员 (2008-);

l 信息存储系统教育部重点实验室学术委员会委员 (2017-);

l 清华大学信息科学技术学院学术委员会委员 (2011-);

l 863计划海量存储系统关键技术重大项目:总体专家组副组长 (2008-2010);

l acm transaction on storage》:associate editor (2016-);

l ieee transactions on computers》:associate editor (2019-);

l journal of computer science and technology》:member of the editorial board (the area of computer architecture and systems) (2019-);

l 《计算机学报》:编委 (2010-);

l 《软件学报》:责任编委 (2012-);

l 《计算机研究与发展》:编委 (2010-);

l 《大数据》:编委 (2015-).

研究领域

基于非易失存储器件的新型存储系统与技术

闪存存储系统与技术

网络(//大数据)存储系统与关键技术

数据存储可靠性等。

研究概况

    在基于非易失存储器件的新型存储系统与技术方面,基于“计算与内存分离”和“功能抽象”的设计思想,提出了分布式持久性共享内存框架,并攻克了其数据结构、内存管理、一致性与安全等方面系列难题,形成了内存、对象、事务、复制等灵活高效的统一接口,研制出了持久性内存文件系统与键值存储系统,构建出了新型分布式持久性内存存储系统th-dpms,打破计算存储紧耦合设计,充分发挥了新型硬件优势,在尾延迟、高带宽等方面有明显优势;相关主要学术论文发表在micro’2018/2013asplos’2020usenix atc’2017(2)vldb’2020sc’2020isca’2015eurosys’2019/2016dac’2020/2019/2016/2015dsn’2014msst’2020/2016/2015iccd’2014date’2017(2)等重要国际会议和acm tos 2020/2018/2016ieee tpds 2017ieee tc 2020等权威国际期刊上,并获得msst’2015国际会议的best papers nominated;相关成果获得2020年华为首届“奥林帕斯奖”和百万悬红,并获得2020年“ccf科学技术奖”技术发明一等奖;该方面研究已获得国家863项目、国家重点研发项目等资助外,还获得华为、阿里、快手、中兴等公司资助,部分成果已转化并获得应用。

    闪存存储系统与技术方面,针对flash的特有特性,提出了软件直管的开放通道(open-channel ssd)闪存存储架构与相关技术,研制出了闪存文件系统parafs、键值闪存存储系统flashkv、分布式闪存存储系统ocstore等,构建出了软硬件协同的闪存存储系统th-sss,在性能、可靠性等方面有显著优势;相关主要学术论文发表在fast’2014/2013osdi’2020usenix atc’ 2016sc’2017dac’2020/2019icdcs’2019ipdps’2014iccd’2013date’2014等重要国际会议和acm tos 2019ieee tc 2019/2016/2015ieee tpds 2018等权威国际期刊上,并获得nvmsa’2015国际会议的best papers;相关成果获2019年教育部科学技术发明奖一等奖;该方面研究已获得国家863项目和三星、华为、中兴等公司资助,部分成果已转化并获得应用。

    在网络(//大数据)存储系统与关键技术方面,主要针对网络(//大数据)存储系统中面临的性能、扩展性、兼容性、易用性、安全性、易管理等问题进行研究,在存储虚拟化、存储系统在线扩展方法、元数据管理方法、存储cache策略、分级存储、面向san的并行文件系统、云存储安全等方面的研究取得了一些进展。研制出了具有自主知识产权的国产网络存储系统——“清华海量存储网络系统th-msns”2006年前,th-msns系统已有近100套应用在审计署、公安局、电信、油田、高校等行业或部门;同时,也研制了相关的存储子系统,如:存储管理系统th-msis、分布式虚拟化存储系统th-dvsm、带外虚拟化存储系统th-vsm、备份系统th-backup、快照系统th-snapshot、远程镜像系统th-mirror、面向san的并行文件系统redbud、分级存储系统aip、云存储安全系统corslet,一些系统已分别在电信、教育等部门获得实际应用;这些系统与应用成果分别获得2007年获国家科技进步二等奖、2015年国家科学技术发明二等奖等; 这些系统相关的主要学术论文发表在ieee tc 2016/2014/2010/2007/2005acm tos 2010/2007ieee tpds 2016/2015/2014等权威国际期刊和ipdps’2016codes/isss’2016iwqos’2014/2013icpp’2012cluster’2012msst’2006ccgrid’2004等重要国际会议上。

    在数据存储可靠性方面,针对存储纠删码容错能力(容1个、2个和多个错误)、性能(编码效率)和存储利用率等方面存在的问题进行研究,提出并实现了一些相关的高效实用的存储纠删码技术,提高了存储系统的可靠性,相关主要学术论文发表在dsn’2016/2014srds’2017/2016/2015/2014ipdps’2015icpp’2015/2013/2012iwqos’2016等重要国际会议和ieee tc 2017/2016/2010ieee tpds 2019/2018/2017/2016ieee tdsc 2020acm tos 2012/2009等权威国际期刊上,并获得2010ieee tc期刊的featured articlesrds’2015国际会议的nominated best papers

主要研究项目和课题

l 国家重点研发计划重点专项项目: tb级持久性内存存储技术与系统 (2018-2021);

l 国家重点研发计划重点专项课题:分布式持久性共享内存框架研制及存储系统应用示范 (2018-2021);

l 北京市科委重点项目之课题:异构混合内存系统的大数据处理软件平台架构与优化研究(2015-2016);

l 863项目: 面向大数据的先进存储结构及关键技术(2013-2015);

l 863课题: 基于新型存储器件的存储体系结构与关键技术研究(2013-2015);

l 国家自然科学重点基金: 新型分布式存储系统的高可靠性关键技术研究 (2019-2023);

l 国家自然科学重点基金:网络公用数据存储系统可靠性及其灾备研究(2013-2017);

l 国家工信部子课题: 云计算平台上面向移动通信业务云服务关键技术与系统(2013-2015);

l 国家科技支撑计划子课题: 存储虚拟化软件开发及产业化(2010-2013);

l 国家杰出青年科学基金: 大规模网络存储系统的可靠性关键技术研究 (2010-2013);

l 国家自然科学基金: 大规模网络存储系统的容错技术研究 (2009-2011);

l 973课题: 下一代互联网存储按需部署模型与服务质量研究 (2004-2009);

l 863重大课题子课题: 海量存储系统软件和关键技术 (2009-2010).

奖励与荣誉

l 北京市科学技术进步二等奖——高可扩展海量网络存储系统 (2004);

l 高等学校科学技术进步二等奖——深腾2600网络服务器系统 (2007);

l 国家科技进步二等奖——高性能集群计算机与海量存储系统 (2007);

l 中国电子学会技术发明一等奖——面向社区共享的高可用云存储系统(2014);

l 国家科学技术发明二等奖——面向社区共享的高可用云存储系统(2015);

l 江苏省科学技术奖一等奖——大规模数据服务系统与平台的关键技术及产业应用(2018);

l 中国产学研合作促进会创新成果奖一等奖——基于tb级数据架构的需求设计开发一体化软件工程智能技术研发及行业应用(2018);

l 教育部科学技术技术发明一等奖——软硬件协同的闪存存储系统关键技术及应用(2019);

l 中国计算机学会科学技术奖技术发明一等奖——持久性内存存储系统关键技术与应用(2020).

l 清华大学学术新人奖 (2005);

l 教育部:新世纪优秀人才 (2005);

l 中创软件人才奖(2007);

l 国家自然科学基金委: 国家杰出青年科学基金获得者 (2009);

l 教育部长江学者特聘教授 (2014);

l ieee fellow (2018);

l 中国计算机学会会士 (2018)

l 华为“奥林帕斯奖”(2020).

学术成果

代表性会议论文

[1] xiaojian liao, youyou lu, erci xu, jiwu shu, write dependency disentanglement with horae, the 14th usenix symposium on operating systems design and implementation (osdi), (acceptance rate: 70/398=17.59%)

[2] minhui xie, kai ren, youyou lu, jiazhen lin, guangxu yang, bihai wu, fan yang, wanhong xu, jiwu shu, kraken: memory efficient continual learning for large-scale real-time recommendation, the international conference for high performance computing, networking, storage, and analysis (sc), nov. 16-19,2020, denver, co

[3] youmin chen, youyou lu, bohong zhu, jiwu shu, tree: a persistent b -tree with low tail latency, proceedings of very large data bases (vldb)aug 31, 2020 - sep 4, 2020tokyo, japan

[4] qing wan, youyou lu, zhongjie wu, fan yang, jiwu shu, improving the concurrency performance of persistent memory transactions on multicores, the 56th annual design automation conference (dac), july 19, 2020, san francisco, california, usa (acceptance rate: 228/984=23.17%)

[5] yang zhe, youyou lu, erci xu, jiwu shu, coinpurse: a device-assisted file system with dual interfaces, the 56th annual design automation conference (dac), july 19, 2020, san francisco, california, usa. (acceptance rate: 228/984=23.17%)

[6] youmin chen, youyou lu, fan yang, qing wang, yang wang, jiwu shu, flatstore: an efficient log-structured key-value storage engine for persistent memory, the 25th international conference on architectural support for programming languages and operating systems (asplos), march 16-20, 2020, lausanne, switzerland (acceptance rate: 86/476=18.07%)

[7] fan yang, youyou lu, youmin chen, haiyu mao, jiwu shu, no compromises: secure nvm with crash consistency, write-efficiency and high-performance, the 55th annual design automation conference (dac), june 2-6, 2019, las vegas, nv, usa (acceptance rate: 202/815=24.79%)

[8] fei li, youyou lu, zhongjie wu, jiwu shu, ascache: an approximate ssd cache for error-tolerant applications, the 55th annual design automation conference (dac), june 2-6, 2019, las vegas, nv, usa (acceptance rate: 202/815=24.79%)

[9] youmin chen, youyou lu, jiwu shu, scalable rdma rpc on reliable connection with efficient resource sharing, european conference on computer systems (eurosys), dresden, germany, mar 25, 2019 - mar 28, 2019 (acceptance rate: 45/207=21.74%)

[10] haiyu mao, mingcong song, tao li, yutiing dai, jiwu shu, lergan: a zero-free, low data movement and pim-based gan architecture, the 51st annual ieee/acm international symposium on microarchitecture (micro), fukuoka city, japan, 2018, oct 20 – 24, pp.670-682 (acceptance rate: 74/351=21.06%)

[11] siyang li, youyou lu, jiwu shu, fenlin liu, yang hu, tao li, locofs: a loosely-coupled metadata service for distributed file system, the international conference for high performance computing, networking, storage and analysis (sc), nov. 12-17,2017, denver, co (acceptance rate: 61/327=18.65%)

[12] youyou lu, jiwu shu, youmin chen, tao li , octopus: an rdma-enabled distribute persistent memory file system, 2017 usenix annual technical conference (usenix atc), july 12–14, 2017, santa clara, ca, usa, pp.773-785 (acceptance rate: 60/283=21%)

[13] qingda hu, jinglei ren, anirudh badam, jiwu shu, tomas moscibroda, log-structured non-volatile main memory, 2017 usenix annual technical conference (usenix atc), july 12–14, 2017, santa clara, ca, usa, pp.703-717 (acceptance rate: 60/283=21%)

[14] jiacheng zhang, jiwu shu, youyou lu, parafs: a log-structured file system to exploit the internal parallelism of flash devices, 2016 usenix annual technical conference (usenix atc), june 22–24, 2016, denver, colorado, usa (acceptance rate: 19%)

[15] zhirong shen, jiwu shu, patrick p.c. lee, reconsidering single failure recovery in cluster file systems, the 46th annual ieee/ifip international conference on dependable systems and networks (dsn), 2016, june 28-july 1st, toulouse, france (acceptance rate: 58/259=22.39%)

[16] zewei li, yongpan liu, daming zhang, chun jason xue, zhangyuan wang, xin shi, wenyu sun, jiwu shu, huazhong yang, hw/sw co-design of nonvolatile io system in energy harvesting sensor nodes for optimal data acquisition, design automation conference (dac), 5–9 june 2016, austin, usa (acceptance rate: 152/876=17.4 %)

[17] jiaxin ou, jiwu shu, youyou lu, a high performance file system for non-volatile main memory, the european conference on computer systems (eurosys), 18th-21st, april, 2016, london, uk (acceptance rate: 38/180=21.11%)

[18] zhirong sheng, jiwu shu, patrick lee, seek-efficient i/o optimization in single failure recovery for xor-coded storage systems, the 34th international symposium on reliable distributed systems (srds), september 28-october 1, 2015, quebec canada (nominated best papers).

[19] yongpan liu, zewei li, hehe li, yiqun wang, xueqing li, kaisheng ma, shuangchen li, meng-fan chang, sampson john, yuan xie, jiwu shu, huazhong yang, design automation conference (dac), moscone center, san francisco, ca, june 7-11, 2015, article no.150, pp.1-6

[20] chao zhang, guangyu sun, xian zhang, weiqi zhang, weisheng zhao, tao wang, yun liang, yongpan liu, yu wang, jiwu shu, hi-fi playback: tolerating position errors in shift operations of racetrack memory, the 42nd international symposium on computer architecture (isca), portland, or, usa, june 13-17, 2015, pp. 694-706. (acceptance rate: 58/305=19.02%)

[21] louyou lu, jiwu shu, long sun, blurred persistence in transactional persistent memory, the 31st international conference on massive storage systems and technologies (msst), june 1-5, 2015, santa clara, california, usa (nominated best papers)

[22] fan jie, jiang song, shu jiwu, sun long, hu qingda, wl-reviver: a framework for reviving any wear-leveling techniques in the face of failures on phase change memory, the annual ieee/ifip international conference on dependable systems and networks (dsn), june 23 - 26, 2014, atlanta, georgia usa, pp.228-239. (acceptance rate: 49/181 = 27.07%)

[23] zhirong sheng, jiwu shu, hv code: an mds code to improve efficiency and reliability of raid-6 systems, the annual ieee/ifip international conference on dependable systems and networks (dsn), june 23 - 26, 2014, atlanta, georgia usa, pp.550-56. (acceptance rate: 49/181 = 27.07%)

[24] lu youyou, shu jiwu, wang wei, reconfs: a reconstructable file system on flash storage, the 12th usenix conference on file and storage technologies (fast), february 12-15, 2014, san jose, ca, usa, pp. 75-88. (acceptance rate: 21/133=15.79%)

[25] jie fan, song jiang, jiwu shu, youhui zhang, weimin zheng, partitioning data block for efficient recovery of stuck-at-faults in phase change memory, the 46th annual ieee/acm international symposium on microarchitecture (micro), december 7-11, 2013, davis, california, pp. 433-444. (acceptance rate: 39/239=16.32%)

[26] youyou lu, jiwu shu, weimin zheng, extending the lifetime of flash-based storage through reducing write amplification from file systems, 11th usenix conference on file and storage technologies (fast), february 12-15,2013, san jose, ca, usa, pp. 257-270. (acceptance rate: 20/127=15.75%)

代表性期刊论文

[1] fan yang, youmin chen, haiyu mao, youyou, jiwu shu, shieldnvm: an efficient and fast recoverable system for secure non-volatile memory, acm transactions on storage (tos), vol.16, no.2, article 12, publication date: may 2020.

[2] youyou lu, jiwu shu, jiacheng zhang, mitigating synchronous i/o overhead in file systems on open-channel ssds, acm transactions on storage (tos), 15(3), article 17 :1-25, may 2019

[3] youmin chen, youyou lu, pei chen, jiwu shu, efficient and consistent nvmm cache for ssd-based file system, ieee transactions on computers (tc), 68(8): 1147-1158, august, 2019.

[4] siyang li, fenlin liu, jiwu shu, youyou lu, tao li, yang hu, a flattened metadata service for distributed file systems, ieee transactions on parallel and distributed systems (tpds), 29(12):2641-2657, december 2018.

[5] zhirong shen, patrick p. c. lee, jiwu shu and wenzhong guo, encoding-aware data placement for efficient degraded reads in xor-coded storage systems: algorithms and evaluation, ieee transactions on parallel and distributed systems (tpds), 29(12):2757-2770, december 2018.

[6] youmin chen, jiwu shu, jiaxin ou, youyou lu, hinfs: a persistent memory file system with both buffering and direct-access, acm transactions on storage (tos), vol.14, number 1, april 2018, 4:1-4:30.

[7] zhirong shen, jiwu shu, patrick p.c. lee, and yingxun fu, seek-efficient i/o optimization in single failure recovery for xor-coded storage systems, ieee transactions on parallel and distributed systems (tpds), 28(3):877-890, 2017.

[8] yingxun fu, jiwu shu, xianghong luo, zhirong shen, qingda hu, short code: an efficient raid-6 mds code for optimizing degraded reads and partial stripe writes, ieee transactions on computers (tc), 66(1), pp. 127-137, 2017.

[9] jiacheng zhang, youyou lu, jiwu shu, xiongjun qin, flashkv: accelerating kv performance with open-channel ssds, acm transactions on embedded computing systems (acm tecs), vol. 16, no. 5s, article 139:1-19 (september 2017)

[10] youyou lu, jiwu shu, jia guo, peng zhu, supporting system consistency with differential transactions in flash-based ssds, ieee transactions on computers (tc), 65(2), pp. 627-639, 2016.

[11] louyou lu, jiwu shu, long sun, blurred persistence: efficient transactions in persistent memory, acm transactions on storage (tos), vol.12, no. 1, article 3, pp. 1-29, january 2016.

[12] zhirong shen, jiwu shu and yingxun fu, parity-switched data placement: optimizing partial stripe writes in xor-coded storage systems, ieee transactions on parallel and distributed systems (tpds), 27(11), pp. 3311-3322, 2016.

[13] zhirong shen, jiwu shu, hv code: an all-around mds code for raid-6 storage systems, ieee transactions on parallel and distributed systems (tpds), 27(6), pp.1674-1686, june 2016.

[14] yingxun fu, jiwu shu, zhang guangyan, reconsidering single disk failure recovery for erasure coded storage systems: optimizing the load balancing in stack-level, ieee transactions on parallel and distributed systems (tpds), 27(5):1457-1469, 2016.

[15] guangyan zhang, guiyong wu, shupeng wang, jiwu shu, weimin zheng, keqin li, caco: an efficient cauchy coding approach for cloud storage systems, ieee transactions on computers (tc), 65(2), pp.435-447, 2016.

[16] youyou lu, jiwu shu, jia guo, shuai li, and onur mutlu, high-performance and lightweight transaction support in flash-based ssds, ieee transactions on computers (tc), 64(10), pp.2819-2832, 2015.

[17] zhang guangyan, wang jigang, li keqin, shu jiwu, and zheng weimin, redistribute data to regain load balance during raid-4 scaling, ieee transactions on parallel and distributed systems (tpds), vol.25, no.7, pp.1-11, july 2014.

[18] yi letian, shu jiwu, zhao ying, qian yingjin, lu youyou, zheng weiming, design and implementation of an asymmetric block-based parallel file system, ieee transactions on computers (tc), vol.62, no.7, pp.1723-1735, july 2014.

[19] xianghong luo, jiwu shu, generalized x-code: an efficient raid-6 code for arbitrary size of disk array, acm transactions on storage (tos), vol.8, no.3, article 10, pp.1-19, 2012.

[20] wang yang, shu ji-wu, zhang guang-yan, xue wei, sopa: selecting the optimal policy adaptively for a cache system, acm transactions on storage (tos), vol. 6, no. 2, article 7, pp. 1-18, 2010.

[21] guangyan zhang, weimin zheng, and jiwu shu. , ieee transactions on computers (tc), vol. 59(3), pp. 345-357, 2010.

[22] guangyan zhang, jiwu shu, wei xue, and weimin zheng, slas: an efficient approach to scaling round-robin striped volumes, acm transactions on storage (tos), 2007, 3(1), article3, pp.1-39.

[23] guangyan zhang, jiwu shu, wei xue, and weimin zheng, design and implementation of an out-of-band virtualization system for large sans, ieee transactions on computers (tc), 2007, 56(12), pp.1654-1665.

[24] shu ji-wu, li bigang, zheng wei-min, design and implementation of a san system based on the fiber channel protocol, ieee transactions on computers (tc), 54(4), 2005, pp. 439-448.

[25] jiwu shu, wei xue, weiming zheng, a parallel transient stability simulation for power system, ieee transactions on power systems (tops), 2005, 20(4), pp.1709-1717.

[26] li mingqiang, shu jiwu, preventing silent data corruptions from propagating during data reconstruction, ieee transactions on computers (tc), 59(12), pp.1611-1624, 2010 (featured article).

[27] li mingqiang, shu jiwu, daco: a high performance disk architecture designed specially for large scale erasure coded storage systems, ieee transactions on computers (tc), 59(10), pp.1350-1362, 2010.

[28] li mingqiang, shu jiwu, zheng weimin, grid codes: strip-based erasure codes with high fault tolerance for storage systems, acm transactions on storage (tos), 2009, 4(4), article15, pp.1-22.

网站地图