Leveraging queueing theory and os profiling to reduce application latency

Anshul Gandhi; Amoghvarsha Suresh

doi:10.1145/3366625.3368853

Leveraging queueing theory and os profiling to reduce application latency

Anshul Gandhi
, Amoghvarsha Suresh

Computer Science

Stony Brook University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

Request latency is a critical metric in determining the usability of online services, such as web applications and databases. Most existing approaches to improve application latency start by detecting bottlenecks in the application deployment; this typically entails determining stages of processing where the application spends most of its time. Inspired by queueing theory, we present an alternative approach to detect and mitigate bottlenecks âĂŞ using variability of processing time as a guiding principle when designing applications.

Original language	English
Title of host publication	Middleware 2019 - Proceedings of the 2019 20th International Middleware Conference Tutorials, Part of Middleware 2019
Publisher	Association for Computing Machinery
Pages	1-5
Number of pages	5
ISBN (Electronic)	9781450370400
DOIs	https://doi.org/10.1145/3366625.3368853
State	Published - Dec 9 2019
Event	20th International Middleware Conference Tutorials, Middleware 2019 - Part of Middleware 2019 - Davis, United States Duration: Dec 9 2019 → Dec 13 2019

Publication series

Name	Middleware 2019 - Proceedings of the 2019 20th International Middleware Conference Tutorials, Part of Middleware 2019

Conference

Conference	20th International Middleware Conference Tutorials, Middleware 2019 - Part of Middleware 2019
Country/Territory	United States
City	Davis
Period	12/9/19 → 12/13/19

Access to Document

10.1145/3366625.3368853

Cite this

Gandhi, A., & Suresh, A. (2019). Leveraging queueing theory and os profiling to reduce application latency. In Middleware 2019 - Proceedings of the 2019 20th International Middleware Conference Tutorials, Part of Middleware 2019 (pp. 1-5). (Middleware 2019 - Proceedings of the 2019 20th International Middleware Conference Tutorials, Part of Middleware 2019). Association for Computing Machinery. https://doi.org/10.1145/3366625.3368853

Gandhi, Anshul ; Suresh, Amoghvarsha. / Leveraging queueing theory and os profiling to reduce application latency. Middleware 2019 - Proceedings of the 2019 20th International Middleware Conference Tutorials, Part of Middleware 2019. Association for Computing Machinery, 2019. pp. 1-5 (Middleware 2019 - Proceedings of the 2019 20th International Middleware Conference Tutorials, Part of Middleware 2019).

@inproceedings{37151850d1154cd789d875b224156640,

title = "Leveraging queueing theory and os profiling to reduce application latency",

abstract = "Request latency is a critical metric in determining the usability of online services, such as web applications and databases. Most existing approaches to improve application latency start by detecting bottlenecks in the application deployment; this typically entails determining stages of processing where the application spends most of its time. Inspired by queueing theory, we present an alternative approach to detect and mitigate bottlenecks {\^a}{\u A}{\c S} using variability of processing time as a guiding principle when designing applications.",

author = "Anshul Gandhi and Amoghvarsha Suresh",

note = "Publisher Copyright: {\textcopyright} 2019. ACM; 20th International Middleware Conference Tutorials, Middleware 2019 - Part of Middleware 2019 ; Conference date: 09-12-2019 Through 13-12-2019",

year = "2019",

month = dec,

day = "9",

doi = "10.1145/3366625.3368853",

language = "English",

series = "Middleware 2019 - Proceedings of the 2019 20th International Middleware Conference Tutorials, Part of Middleware 2019",

publisher = "Association for Computing Machinery",

pages = "1--5",

booktitle = "Middleware 2019 - Proceedings of the 2019 20th International Middleware Conference Tutorials, Part of Middleware 2019",

}

Gandhi, A & Suresh, A 2019, Leveraging queueing theory and os profiling to reduce application latency. in Middleware 2019 - Proceedings of the 2019 20th International Middleware Conference Tutorials, Part of Middleware 2019. Middleware 2019 - Proceedings of the 2019 20th International Middleware Conference Tutorials, Part of Middleware 2019, Association for Computing Machinery, pp. 1-5, 20th International Middleware Conference Tutorials, Middleware 2019 - Part of Middleware 2019, Davis, United States, 12/9/19. https://doi.org/10.1145/3366625.3368853

Leveraging queueing theory and os profiling to reduce application latency. / Gandhi, Anshul; Suresh, Amoghvarsha.
Middleware 2019 - Proceedings of the 2019 20th International Middleware Conference Tutorials, Part of Middleware 2019. Association for Computing Machinery, 2019. p. 1-5 (Middleware 2019 - Proceedings of the 2019 20th International Middleware Conference Tutorials, Part of Middleware 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Leveraging queueing theory and os profiling to reduce application latency

AU - Gandhi, Anshul

AU - Suresh, Amoghvarsha

PY - 2019/12/9

Y1 - 2019/12/9

N2 - Request latency is a critical metric in determining the usability of online services, such as web applications and databases. Most existing approaches to improve application latency start by detecting bottlenecks in the application deployment; this typically entails determining stages of processing where the application spends most of its time. Inspired by queueing theory, we present an alternative approach to detect and mitigate bottlenecks âĂŞ using variability of processing time as a guiding principle when designing applications.

AB - Request latency is a critical metric in determining the usability of online services, such as web applications and databases. Most existing approaches to improve application latency start by detecting bottlenecks in the application deployment; this typically entails determining stages of processing where the application spends most of its time. Inspired by queueing theory, we present an alternative approach to detect and mitigate bottlenecks âĂŞ using variability of processing time as a guiding principle when designing applications.

UR - https://www.scopus.com/pages/publications/85078876934

U2 - 10.1145/3366625.3368853

DO - 10.1145/3366625.3368853

M3 - Conference contribution

AN - SCOPUS:85078876934

T3 - Middleware 2019 - Proceedings of the 2019 20th International Middleware Conference Tutorials, Part of Middleware 2019

SP - 1

EP - 5

BT - Middleware 2019 - Proceedings of the 2019 20th International Middleware Conference Tutorials, Part of Middleware 2019

PB - Association for Computing Machinery

T2 - 20th International Middleware Conference Tutorials, Middleware 2019 - Part of Middleware 2019

Y2 - 9 December 2019 through 13 December 2019

ER -

Gandhi A, Suresh A. Leveraging queueing theory and os profiling to reduce application latency. In Middleware 2019 - Proceedings of the 2019 20th International Middleware Conference Tutorials, Part of Middleware 2019. Association for Computing Machinery. 2019. p. 1-5. (Middleware 2019 - Proceedings of the 2019 20th International Middleware Conference Tutorials, Part of Middleware 2019). doi: 10.1145/3366625.3368853

Leveraging queueing theory and os profiling to reduce application latency

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this