Upper bounds for multi-level multi-server paging

Shlomi Dolev; Anat Eyal; Danny Hendler; Philip Derbeko; Marina Kogan-Sadetsky

doi:10.1016/j.ipl.2018.10.012

Upper bounds for multi-level multi-server paging

Shlomi Dolev, Anat Eyal, Danny Hendler, Philip Derbeko, Marina Kogan-Sadetsky

Research output: Contribution to journal › Article › peer-review

Abstract

The distributed multi-level multi-server paging problem (DMLMSP) defined in this paper extends and generalizes the classical distributed paging problem [3] to a distributed concurrent multi-level setting, in which multiple servers share caches at multiple levels. The DMLMSP can be used for modeling algorithms for efficient distributed storage systems, in which multiple servers use caches for accelerating access to a centralized storage, maintaining cache coherency across multiple nodes while minimizing access latency and optimizing cache-hit ratio. The DMLMSP model fits basic principles of Non-Uniform Cache Architectures (NUCAs) and can be used for analyzing multiple-level centralized storage. We present an optimal offline algorithm for the DMLMSP model, with minimum number of page faults and minimum makespan, whose time complexity is polynomial in the length of the servers' page request sequences. The new algorithm generalizes and simplifies the state of the art algorithms [3,1].

Original language	English
Pages (from-to)	72-76
Number of pages	5
Journal	Information Processing Letters
Volume	142
DOIs	https://doi.org/10.1016/j.ipl.2018.10.012
State	Published - Feb 2019
Externally published	Yes

Bibliographical note

Publisher Copyright:
© 2018 Elsevier B.V.

Funding

We thank to the anonymous reviewers for the constructive very detailed deep comments, which improved significantly the results. We also thank EMC and ISF grant number 428/11 for supporting the research.

Funders	Funder number
EMC
Iowa Science Foundation
Israel Science Foundation	428/11

Keywords

Concurrency
Distributed computing
Distributed systems
Multi-level shared cache
Optimal offline polynomial paging algorithm

Access to Document

10.1016/j.ipl.2018.10.012

Cite this

@article{bbad829f1cd14f7c8ed945f72ddccca6,

title = "Upper bounds for multi-level multi-server paging",

abstract = "The distributed multi-level multi-server paging problem (DMLMSP) defined in this paper extends and generalizes the classical distributed paging problem [3] to a distributed concurrent multi-level setting, in which multiple servers share caches at multiple levels. The DMLMSP can be used for modeling algorithms for efficient distributed storage systems, in which multiple servers use caches for accelerating access to a centralized storage, maintaining cache coherency across multiple nodes while minimizing access latency and optimizing cache-hit ratio. The DMLMSP model fits basic principles of Non-Uniform Cache Architectures (NUCAs) and can be used for analyzing multiple-level centralized storage. We present an optimal offline algorithm for the DMLMSP model, with minimum number of page faults and minimum makespan, whose time complexity is polynomial in the length of the servers' page request sequences. The new algorithm generalizes and simplifies the state of the art algorithms [3,1].",

keywords = "Concurrency, Distributed computing, Distributed systems, Multi-level shared cache, Optimal offline polynomial paging algorithm",

author = "Shlomi Dolev and Anat Eyal and Danny Hendler and Philip Derbeko and Marina Kogan-Sadetsky",

note = "Publisher Copyright: {\textcopyright} 2018 Elsevier B.V.",

year = "2019",

month = feb,

doi = "10.1016/j.ipl.2018.10.012",

language = "אנגלית",

volume = "142",

pages = "72--76",

journal = "Information Processing Letters",

issn = "0020-0190",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Upper bounds for multi-level multi-server paging

AU - Dolev, Shlomi

AU - Eyal, Anat

AU - Hendler, Danny

AU - Derbeko, Philip

AU - Kogan-Sadetsky, Marina

PY - 2019/2

Y1 - 2019/2

N2 - The distributed multi-level multi-server paging problem (DMLMSP) defined in this paper extends and generalizes the classical distributed paging problem [3] to a distributed concurrent multi-level setting, in which multiple servers share caches at multiple levels. The DMLMSP can be used for modeling algorithms for efficient distributed storage systems, in which multiple servers use caches for accelerating access to a centralized storage, maintaining cache coherency across multiple nodes while minimizing access latency and optimizing cache-hit ratio. The DMLMSP model fits basic principles of Non-Uniform Cache Architectures (NUCAs) and can be used for analyzing multiple-level centralized storage. We present an optimal offline algorithm for the DMLMSP model, with minimum number of page faults and minimum makespan, whose time complexity is polynomial in the length of the servers' page request sequences. The new algorithm generalizes and simplifies the state of the art algorithms [3,1].

AB - The distributed multi-level multi-server paging problem (DMLMSP) defined in this paper extends and generalizes the classical distributed paging problem [3] to a distributed concurrent multi-level setting, in which multiple servers share caches at multiple levels. The DMLMSP can be used for modeling algorithms for efficient distributed storage systems, in which multiple servers use caches for accelerating access to a centralized storage, maintaining cache coherency across multiple nodes while minimizing access latency and optimizing cache-hit ratio. The DMLMSP model fits basic principles of Non-Uniform Cache Architectures (NUCAs) and can be used for analyzing multiple-level centralized storage. We present an optimal offline algorithm for the DMLMSP model, with minimum number of page faults and minimum makespan, whose time complexity is polynomial in the length of the servers' page request sequences. The new algorithm generalizes and simplifies the state of the art algorithms [3,1].

KW - Concurrency

KW - Distributed computing

KW - Distributed systems

KW - Multi-level shared cache

KW - Optimal offline polynomial paging algorithm

UR - https://www.scopus.com/pages/publications/85055753606

U2 - 10.1016/j.ipl.2018.10.012

DO - 10.1016/j.ipl.2018.10.012

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:85055753606

SN - 0020-0190

VL - 142

SP - 72

EP - 76

JO - Information Processing Letters

JF - Information Processing Letters

ER -

Upper bounds for multi-level multi-server paging

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this