Quantifying and Improving I/O Predictability in Virtualized Systems

被引：0
|
作者：
Li, Cheng [1 ]
Goiri, Inigo [1 ]
Bhattacharjee, Abhishek [1 ]
Bianchini, Ricardo [1 ]
Nguyen, Thu D. [1 ]
机构：
[1] Rutgers State Univ, Dept Comp Sci, Piscataway, NJ 08854 USA
来源：
2013 IEEE/ACM 21ST INTERNATIONAL SYMPOSIUM ON QUALITY OF SERVICE (IWQOS) | 2013年
关键词：
D O I：
暂无
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
Virtualization enables the consolidation of virtual machines (VMs) to increase the utilization of physical servers in Infrastructure-as-a-Service (IaaS) cloud providers. However, our experience shows that storage I/O performance varies wildly in the face of consolidation. Since many users may desire consistent performance, we argue that IaaS providers should offer a class of predictable-performance service in addition to existing (predictability-oblivious) services. Thus, we propose VirtualFence, a storage system that provides predictable VM performance. VirtualFence uses three main techniques: (1) non-work-conserving time-division I/O scheduling, (2) a small solid-state (SSD) cache in front of a much larger hard disk drive (HDD), and (3) space-partitioning of both the SSD cache and the HDD. Our evaluation shows that VirtualFence improves predictability significantly, while allowing cloud providers to reach any desired compromise between predictability and performance.
引用
收藏
页码：93 / 98
页数：6
相关论文
共 50 条
  • [41] Special issue - Quantifying predictability - Preface
    Toth, Z
    Smith, L
    NONLINEAR PROCESSES IN GEOPHYSICS, 2001, 8 (06)
  • [42] Improving Virtualized Storage Performance with Sky
    Arulraj, Leo
    Arpaci-Dusseau, Andrea C.
    Arpaci-Dusseau, Remzi H.
    ACM SIGPLAN NOTICES, 2017, 52 (07) : 112 - 128
  • [43] Improving I/O performance of clustered storage systems by adaptive request distribution
    Wu, Changxun
    Burns, Randal
    HPDC-15: PROCEEDINGS OF THE 15TH IEEE INTERNATIONAL SYMPOSIUM ON HIGH PERFORMANCE DISTRIBUTED COMPUTING, 2005, : 207 - 217
  • [44] Improving Timing Predictability in UGV Control Systems through FPGA Implementation
    Costas, Lucia
    Colodron, Pablo
    Ojha, Unnati
    Rodriguez-Andina, Juan J.
    Farina, Jose
    Chow, Mo-Yuen
    2011 IEEE INTERNATIONAL SYMPOSIUM ON INDUSTRIAL ELECTRONICS (ISIE), 2011,
  • [45] Quantifying local instability and predictability of chaotic dynamical systems by means of local metric entropy
    Wei, MZ
    INTERNATIONAL JOURNAL OF BIFURCATION AND CHAOS, 2000, 10 (01): : 135 - 154
  • [46] hyperCache: A Hypervisor-Level Virtualized I/O Cache on KVM/QEMU
    Kim, Taehoon
    Choi, Seungho
    No, Jaechun
    Park, Sung-soon
    2018 TENTH INTERNATIONAL CONFERENCE ON UBIQUITOUS AND FUTURE NETWORKS (ICUFN 2018), 2018, : 846 - 850
  • [47] Radio: Reconciling Disk I/O Interference in a Para-virtualized Cloud
    Yang, Guangwen
    Wang, Liana
    Xue, Wei
    2022 IEEE 15TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING (IEEE CLOUD 2022), 2022, : 144 - 156
  • [48] Optimized Resource Allocation on Virtualized Non-Uniform I/O Architectures
    Ngoc, Tu Dinh
    Teabe, Boris
    Hagimont, Daniel
    Da Costa, Georges
    2022 22ND IEEE/ACM INTERNATIONAL SYMPOSIUM ON CLUSTER, CLOUD AND INTERNET COMPUTING (CCGRID 2022), 2022, : 432 - 441
  • [49] CANLay: A Network Virtualized Testbed for Vehicle Systems – Improving System Integration and Verification Efforts
    Jepson, Jake
    Mukherjee, Subhojeet
    Span, Martin
    Daily, Jeremy
    INCOSE International Symposium, 2023, 33 (01): : 1 - 16
  • [50] Burstiness-aware I/O Scheduler for MapReduce Framework on Virtualized Environments
    Kim, Sewoog
    Kang, Dongwoo
    Choi, Jongmoo
    Kim, Junmo
    2014 INTERNATIONAL CONFERENCE ON BIG DATA AND SMART COMPUTING (BIGCOMP), 2014, : 305 - 308
12345