On Channel Failures, File Fragmentation Policies, and Heavy-Tailed Completion Times

被引:3
|
作者
Nair, Jayakrishnan [1 ]
Andreasson, Martin [2 ]
Andrew, Lachlan L. H. [3 ]
Low, Steven H. [4 ]
Doyle, John C. [4 ]
机构
[1] Indian Inst Technol, Dept Elect Engn, Bombay 400062, Maharashtra, India
[2] KTH Royal Inst Technol, ACCESS Linnaeus Ctr, S-10044 Stockholm, Sweden
[3] Swinburne Univ Technol, Ctr Adv Internet Architectures, Hawthorn, Vic 3800, Australia
[4] CALTECH, Comp & Math Sci Dept, Pasadena, CA 91125 USA
基金
澳大利亚研究理事会;
关键词
Checkpointing; file fragmentation; heavy tails; optimal packet size; server failure; CHECKPOINT PLACEMENT; SYSTEMS; STRATEGIES; RETRANSMISSIONS; DISTRIBUTIONS; PERFORMANCE; ROLLBACK; DELAYS;
D O I
10.1109/TNET.2014.2375920
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
It has been recently discovered that heavy-tailed completion times can result from protocol interaction even when file sizes are light-tailed. A key to this phenomenon is the use of a restart policy where if the file is interrupted before it is completed, it needs to restart from the beginning. In this paper, we show that fragmenting a file into pieces whose sizes are either bounded or independently chosen after each interruption guarantees light-tailed completion time as long as the file size is light-tailed; i. e., in this case, heavy-tailed completion time can only originate from heavy-tailed file sizes. If the file size is heavy-tailed, then the completion time is necessarily heavy-tailed. For this case, we show that when the file size distribution is regularly varying, then under independent or bounded fragmentation, the completion time tail distribution function is asymptotically bounded above by that of the original file size stretched by a constant factor. We then prove that if the distribution of times between interruptions has nondecreasing failure rate, the expected completion time is minimized by dividing the file into equal-sized fragments; this optimal fragment size is unique but depends on the file size. We also present a simple blind fragmentation policy where the fragment sizes are constant and independent of the file size and prove that it is asymptotically optimal. Both these policies are also shown to have desirable completion time tail behavior. Finally, we bound the error in expected completion time due to error in modeling of the failure process.
引用
收藏
页码:529 / 541
页数:13
相关论文
共 34 条
  • [1] Robust Matrix Completion with Heavy-Tailed Noise
    Wang, Bingyan
    Fan, Jianqing
    [J]. JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 2024,
  • [2] Renewal reward processes with heavy-tailed inter-renewal times and heavy-tailed rewards
    Levy, JB
    Taqqu, MS
    [J]. BERNOULLI, 2000, 6 (01) : 23 - 44
  • [3] On Scheduling Policies in the Presence of Heavy-Tailed Interference
    Wu, Hang
    Shen, Cong
    Chen, Shengbo
    [J]. 2017 INFORMATION THEORY AND APPLICATIONS WORKSHOP (ITA), 2017,
  • [4] Channel Selection Algorithm for Cognitive Radio Networks with Heavy-Tailed Idle Times
    Sengottuvelan, Senthilmurugan
    Ansari, Junaid
    Maehoenen, Petri
    Venkatesh, T. G.
    Petrova, Marina
    [J]. IEEE TRANSACTIONS ON MOBILE COMPUTING, 2017, 16 (05) : 1258 - 1271
  • [5] Optimal Channel Sensing Strategy for Cognitive Radio Networks With Heavy-Tailed Idle Times
    Senthilmurugan, S.
    Venkatesh, T. G.
    [J]. IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING, 2017, 3 (01) : 26 - 36
  • [6] Superposition of renewal processes with heavy-tailed interarrival times
    Mitov, KV
    Yanev, NM
    [J]. STATISTICS & PROBABILITY LETTERS, 2006, 76 (06) : 555 - 561
  • [7] Effect of heavy-tailed holding times on outage probability
    Kumar, A
    Srinivasan, SH
    [J]. 8TH WORLD MULTI-CONFERENCE ON SYSTEMICS, CYBERNETICS AND INFORMATICS, VOL III, PROCEEDINGS: COMMUNICATION AND NETWORK SYSTEMS, TECHNOLOGIES AND APPLICATIONS, 2004, : 487 - 491
  • [8] Simulation Optimization for Queues with Heavy-Tailed Service Times
    Hong, Gui-Yu
    Chen, Xin-Yun
    [J]. JOURNAL OF THE OPERATIONS RESEARCH SOCIETY OF CHINA, 2024,
  • [9] On Scheduling Policies With Heavy-Tailed Dynamics in Wireless Queueing Systems
    Chen, Shengbo
    Zhang, Lanxue
    Shen, Cong
    Yu, Keping
    Myint, San Hlaing
    Wen, Zheng
    [J]. IEEE ACCESS, 2020, 8 : 32137 - 32149
  • [10] Scheduling Policies for Single-Hop Networks with Heavy-Tailed Traffic
    Markakis, Mihalis G.
    Modiano, Eytan H.
    Tsitsiklis, John N.
    [J]. 2009 47TH ANNUAL ALLERTON CONFERENCE ON COMMUNICATION, CONTROL, AND COMPUTING, VOLS 1 AND 2, 2009, : 112 - 120