FusionFS: Fusing I/O Operations using CISCops in Firmware File Systems

被引:0
|
作者
Zhang, Jian [1 ]
Ren, Yujie [1 ]
Kannan, Sudarsun [1 ]
机构
[1] Rutgers State Univ, New Brunswick, NJ 08854 USA
关键词
D O I
暂无
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
We present FusionFS, a direct-access firmware-level in-storage filesystem that exploits near-storage computational capability for fast I/O and data processing, consequently reducing I/O bottlenecks. In FusionFS, we introduce a new abstraction, CISCop which combines multiple I/O and data processing operations into one fused operation and offloads them for near-storage processing. By offloading, CISCops significantly reduces dominant I/O overheads such as system calls, data movement, communication, and other software overheads. Further, to enhance the use of CISCop we introduce MicroTx, a fine-grained crash consistency and fast (automatic) recovery mechanism for both I/O and data processing operations. Finally, we explore efficient and fair use of in storage compute resources by proposing a novel Completely Fair Scheduler (CFS) for in-storage compute and memory resources across tenants. Evaluation of FusionFS against the state-of-the-art user-level, kernel-level, and firmware-level file systems using microbenchmarks, macrobenchmarks, and real-world applications shows up to 6.12x, 5.09x, and 2.07x performance gains, and 2.65x faster recovery.
引用
收藏
页码:297 / 312
页数:16
相关论文
共 50 条
  • [21] QoSFM: QoS Support for Metadata I/O In Parallel File Systems
    Xiao, Limin
    Xie, Ke
    Li, Guoying
    Ruan, Li
    Li, Xiuqiao
    2013 IEEE 15TH INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING AND COMMUNICATIONS & 2013 IEEE INTERNATIONAL CONFERENCE ON EMBEDDED AND UBIQUITOUS COMPUTING (HPCC_EUC), 2013, : 29 - 38
  • [22] Block I/O Scheduling on Storage Servers of Distributed File Systems
    Jianwei Liao
    Dong Yin
    Xiaoning Peng
    Journal of Grid Computing, 2018, 16 : 299 - 316
  • [23] SCHEDULING PARALLEL I/O OPERATIONS IN MULTIPLE BUS SYSTEMS
    JAIN, R
    SOMALWAR, K
    WERTH, J
    BROWNE, JC
    JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING, 1992, 16 (04) : 352 - 362
  • [24] Stabilizing and boosting I/O performance for file systems with journaling on NVMe SSD
    Lin Qian
    Bin Tang
    Baoliu Ye
    Jianyu Wu
    Xiaoliang Wang
    Sanglu Lu
    Science China Information Sciences, 2022, 65
  • [25] Streamlining distributed Deep Learning I/O with ad hoc file systems
    Schimmelpfennig, Frederic
    Vef, Marc-Andre
    Salkhordeh, Reza
    Miranda, Alberto
    Nou, Ramon
    Brinkmann, Andre
    2021 IEEE INTERNATIONAL CONFERENCE ON CLUSTER COMPUTING (CLUSTER 2021), 2021, : 169 - 180
  • [26] Stabilizing and boosting I/O performance for file systems with journaling on NVMe SSD
    Qian, Lin
    Tang, Bin
    Ye, Baoliu
    Wu, Jianyu
    Wang, Xiaoliang
    Lu, Sanglu
    SCIENCE CHINA-INFORMATION SCIENCES, 2022, 65 (03)
  • [27] On evaluating decentralized parallel I/O scheduling strategies for parallel file systems
    Isaila, Florin
    Singh, David
    Carretero, Jesus
    Garcia, Felix
    HIGH PERFORMANCE COMPUTING FOR COMPUTATIONAL SCIENCE - VECPAR 2006, 2007, 4395 : 120 - +
  • [28] Fault-Tolerant File-I/O for Portable Checkpointing Systems
    Igor Lyubashevskiy
    Volker Strumpen
    The Journal of Supercomputing, 2000, 16 : 69 - 92
  • [29] Fault-tolerant file-I/O for portable checkpointing systems
    Lyubashevskiy, I
    Strumpen, V
    JOURNAL OF SUPERCOMPUTING, 2000, 16 (1-2): : 69 - 92
  • [30] Using file system counters in modelling parallel I/O architectures
    El Sayed, Salem
    Bolten, Matthias
    Pleiter, Dirk
    OPERATING SYSTEMS REVIEW, 2016, 50 (02) : 37 - 46