NitroSketch: Robust and general sketch-based monitoring in software switches

Zaoxing Liu; Ran Ben-Basat; Gil Einziger; Yaron Kassner; Vladimir Braverman; Roy Friedman; Vyas Sekar

doi:https://doi.org/10.1145/3341302.3342076

NitroSketch: Robust and general sketch-based monitoring in software switches

Zaoxing Liu, Ran Ben-Basat, Gil Einziger, Yaron Kassner, Vladimir Braverman, Roy Friedman, Vyas Sekar

Ben-Gurion University of the Negev, Technion - Israel Institute of Technology

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

Abstract

Software switches are emerging as a vital measurement vantage point in many networked systems. Sketching algorithms or sketches, provide high-fidelity approximate measurements, and appear as a promising alternative to traditional approaches such as packet sampling. However, sketches incur significant computation overhead in software switches. Existing efforts in implementing sketches in virtual switches make sacrifices on one or more of the following dimensions: performance (handling 40 Gbps line-rate packet throughput with low CPU footprint), robustness (accuracy guarantees across diverse workloads), and generality (supporting various measurement tasks). In this work, we present the design and implementation of NitroSketch, a sketching framework that systematically addresses the performance bottlenecks of sketches without sacrificing robustness and generality. Our key contribution is the careful synthesis of rigorous, yet practical solutions to reduce the number of per-packet CPU and memory operations. We implement NitroSketch on three popular software platforms (Open vSwitch-DPDK, FD.io-VPP, and BESS) and evaluate the performance. We show that accuracy is comparable to unmodified sketches while attaining up to two orders of magnitude speedup, and up to 45% reduction in CPU usage.

Original language	American English
Title of host publication	SIGCOMM 2019 - Proceedings of the 2019 Conference of the ACM Special Interest Group on Data Communication
Pages	334-350
Number of pages	17
ISBN (Electronic)	9781450359566
DOIs	https://doi.org/10.1145/3341302.3342076
State	Published - 19 Aug 2019
Event	50th Conference of the ACM Special Interest Group on Data Communication, SIGCOMM 2019 - Beijing, China Duration: 19 Aug 2019 → 23 Aug 2019

Publication series

Name	SIGCOMM 2019 - Proceedings of the 2019 Conference of the ACM Special Interest Group on Data Communication

Conference

Conference	50th Conference of the ACM Special Interest Group on Data Communication, SIGCOMM 2019
Country/Territory	China
City	Beijing
Period	19/08/19 → 23/08/19

Keywords

Flow Monitoring
Sketch
Sketching Algorithm
Software Switch
Virtual Switch

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Signal Processing
Electrical and Electronic Engineering
Communication

Access to Document

https://doi.org/10.1145/3341302.3342076

Cite this

Liu, Z., Ben-Basat, R., Einziger, G., Kassner, Y., Braverman, V., Friedman, R., & Sekar, V. (2019). NitroSketch: Robust and general sketch-based monitoring in software switches. In SIGCOMM 2019 - Proceedings of the 2019 Conference of the ACM Special Interest Group on Data Communication (pp. 334-350). (SIGCOMM 2019 - Proceedings of the 2019 Conference of the ACM Special Interest Group on Data Communication). https://doi.org/10.1145/3341302.3342076

@inproceedings{67e65d2a0b1c49d2890b3da5593bf12f,

title = "NitroSketch: Robust and general sketch-based monitoring in software switches",

abstract = "Software switches are emerging as a vital measurement vantage point in many networked systems. Sketching algorithms or sketches, provide high-fidelity approximate measurements, and appear as a promising alternative to traditional approaches such as packet sampling. However, sketches incur significant computation overhead in software switches. Existing efforts in implementing sketches in virtual switches make sacrifices on one or more of the following dimensions: performance (handling 40 Gbps line-rate packet throughput with low CPU footprint), robustness (accuracy guarantees across diverse workloads), and generality (supporting various measurement tasks). In this work, we present the design and implementation of NitroSketch, a sketching framework that systematically addresses the performance bottlenecks of sketches without sacrificing robustness and generality. Our key contribution is the careful synthesis of rigorous, yet practical solutions to reduce the number of per-packet CPU and memory operations. We implement NitroSketch on three popular software platforms (Open vSwitch-DPDK, FD.io-VPP, and BESS) and evaluate the performance. We show that accuracy is comparable to unmodified sketches while attaining up to two orders of magnitude speedup, and up to 45% reduction in CPU usage.",

keywords = "Flow Monitoring, Sketch, Sketching Algorithm, Software Switch, Virtual Switch",

author = "Zaoxing Liu and Ran Ben-Basat and Gil Einziger and Yaron Kassner and Vladimir Braverman and Roy Friedman and Vyas Sekar",

note = "Publisher Copyright: {\textcopyright} 2019 Association for Computing Machinery.; 50th Conference of the ACM Special Interest Group on Data Communication, SIGCOMM 2019 ; Conference date: 19-08-2019 Through 23-08-2019",

year = "2019",

month = aug,

day = "19",

doi = "https://doi.org/10.1145/3341302.3342076",

language = "American English",

series = "SIGCOMM 2019 - Proceedings of the 2019 Conference of the ACM Special Interest Group on Data Communication",

pages = "334--350",

booktitle = "SIGCOMM 2019 - Proceedings of the 2019 Conference of the ACM Special Interest Group on Data Communication",

}

Liu, Z, Ben-Basat, R, Einziger, G, Kassner, Y, Braverman, V, Friedman, R & Sekar, V 2019, NitroSketch: Robust and general sketch-based monitoring in software switches. in SIGCOMM 2019 - Proceedings of the 2019 Conference of the ACM Special Interest Group on Data Communication. SIGCOMM 2019 - Proceedings of the 2019 Conference of the ACM Special Interest Group on Data Communication, pp. 334-350, 50th Conference of the ACM Special Interest Group on Data Communication, SIGCOMM 2019, Beijing, China, 19/08/19. https://doi.org/10.1145/3341302.3342076

NitroSketch: Robust and general sketch-based monitoring in software switches. / Liu, Zaoxing; Ben-Basat, Ran; Einziger, Gil et al.
SIGCOMM 2019 - Proceedings of the 2019 Conference of the ACM Special Interest Group on Data Communication. 2019. p. 334-350 (SIGCOMM 2019 - Proceedings of the 2019 Conference of the ACM Special Interest Group on Data Communication).

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

TY - GEN

T1 - NitroSketch

T2 - 50th Conference of the ACM Special Interest Group on Data Communication, SIGCOMM 2019

AU - Liu, Zaoxing

AU - Ben-Basat, Ran

AU - Einziger, Gil

AU - Kassner, Yaron

AU - Braverman, Vladimir

AU - Friedman, Roy

AU - Sekar, Vyas

PY - 2019/8/19

Y1 - 2019/8/19

N2 - Software switches are emerging as a vital measurement vantage point in many networked systems. Sketching algorithms or sketches, provide high-fidelity approximate measurements, and appear as a promising alternative to traditional approaches such as packet sampling. However, sketches incur significant computation overhead in software switches. Existing efforts in implementing sketches in virtual switches make sacrifices on one or more of the following dimensions: performance (handling 40 Gbps line-rate packet throughput with low CPU footprint), robustness (accuracy guarantees across diverse workloads), and generality (supporting various measurement tasks). In this work, we present the design and implementation of NitroSketch, a sketching framework that systematically addresses the performance bottlenecks of sketches without sacrificing robustness and generality. Our key contribution is the careful synthesis of rigorous, yet practical solutions to reduce the number of per-packet CPU and memory operations. We implement NitroSketch on three popular software platforms (Open vSwitch-DPDK, FD.io-VPP, and BESS) and evaluate the performance. We show that accuracy is comparable to unmodified sketches while attaining up to two orders of magnitude speedup, and up to 45% reduction in CPU usage.

AB - Software switches are emerging as a vital measurement vantage point in many networked systems. Sketching algorithms or sketches, provide high-fidelity approximate measurements, and appear as a promising alternative to traditional approaches such as packet sampling. However, sketches incur significant computation overhead in software switches. Existing efforts in implementing sketches in virtual switches make sacrifices on one or more of the following dimensions: performance (handling 40 Gbps line-rate packet throughput with low CPU footprint), robustness (accuracy guarantees across diverse workloads), and generality (supporting various measurement tasks). In this work, we present the design and implementation of NitroSketch, a sketching framework that systematically addresses the performance bottlenecks of sketches without sacrificing robustness and generality. Our key contribution is the careful synthesis of rigorous, yet practical solutions to reduce the number of per-packet CPU and memory operations. We implement NitroSketch on three popular software platforms (Open vSwitch-DPDK, FD.io-VPP, and BESS) and evaluate the performance. We show that accuracy is comparable to unmodified sketches while attaining up to two orders of magnitude speedup, and up to 45% reduction in CPU usage.

KW - Flow Monitoring

KW - Sketch

KW - Sketching Algorithm

KW - Software Switch

KW - Virtual Switch

UR - http://www.scopus.com/inward/record.url?scp=85071935014&partnerID=8YFLogxK

U2 - https://doi.org/10.1145/3341302.3342076

DO - https://doi.org/10.1145/3341302.3342076

M3 - Conference contribution

T3 - SIGCOMM 2019 - Proceedings of the 2019 Conference of the ACM Special Interest Group on Data Communication

SP - 334

EP - 350

BT - SIGCOMM 2019 - Proceedings of the 2019 Conference of the ACM Special Interest Group on Data Communication

Y2 - 19 August 2019 through 23 August 2019

ER -

Liu Z, Ben-Basat R, Einziger G, Kassner Y, Braverman V, Friedman R et al. NitroSketch: Robust and general sketch-based monitoring in software switches. In SIGCOMM 2019 - Proceedings of the 2019 Conference of the ACM Special Interest Group on Data Communication. 2019. p. 334-350. (SIGCOMM 2019 - Proceedings of the 2019 Conference of the ACM Special Interest Group on Data Communication). doi: https://doi.org/10.1145/3341302.3342076

NitroSketch: Robust and general sketch-based monitoring in software switches

Abstract

Publication series

Conference

Keywords

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this