Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.14279/19430
Title: PerfIso: Performance isolation for commercial latency-sensitive services
Authors: Iorgulescu, Calin 
Azimi, Reza 
Kwon, Youngjin 
Elnikety, Sameh 
Syamala, Manoj 
Tomita, Paulo 
Narasayya, Vivek R. 
Herodotou, Herodotos 
Chen, Alex 
Zhang, Jack 
Wang, Junhua 
Major Field of Science: Natural Sciences
Field Category: Computer and Information Sciences
Keywords: CPU utilization;CPU-intensive;Machine resources;Production environments;Service level objective;Web searches;Search engines
Issue Date: Jul-2018
Source: USENIX Annual Technical Conference, 11-13 July 2018, Boston. United States
Link: https://www.usenix.org/system/files/conference/atc18/atc18-iorgulescu.pdf
Conference: USENIX Annual Technical Conference 
Abstract: Large commercial latency-sensitive services, such as web search, run on dedicated clusters provisioned for peak load to ensure responsiveness and tolerate data center outages. As a result, the average load is far lower than the peak load used for provisioning, leading to resource under-utilization. The idle resources can be used to run batch jobs, completing useful work and reducing overall data center provisioning costs. However, this is challenging in practice due to the complexity and stringent tail-latency requirements of latency-sensitive services. Left unmanaged, the competition for machine resources can lead to severe response-time degradation and unmet service-level objectives (SLOs). This work describes PerfIso, a performance isolation framework which has been used for nearly three years in Microsoft Bing, a major search engine, to colocate batch jobs with production latency-sensitive services on over 90,000 servers. We discuss the design and implementation of PerfIso, and conduct an experimental evaluation in a production environment. We show that colocating CPU-intensive jobs with latency-sensitive services increases average CPU utilization from 21% to 66% for off-peak load without impacting tail latency.
URI: https://hdl.handle.net/20.500.14279/19430
ISBN: 978-193913302-1
Rights: Attribution-NonCommercial-NoDerivatives 4.0 International
Type: Conference Papers
Affiliation : University of Texas at Austin 
EPFL 
Brown University 
Microsoft Research 
Cyprus University of Technology 
Microsoft Bing 
Publication Type: Peer Reviewed
Appears in Collections:Δημοσιεύσεις σε συνέδρια /Conference papers or poster or presentation

Files in This Item:
File Description SizeFormat
atc18-iorgulescu.pdfFulltext962.98 kBAdobe PDFView/Open
CORE Recommender
Show full item record

Page view(s)

294
Last Week
0
Last month
3
checked on Dec 25, 2024

Download(s) 50

54
checked on Dec 25, 2024

Google ScholarTM

Check

Altmetric


This item is licensed under a Creative Commons License Creative Commons