PerfDB: A Data Management System for Fine-Grained Performance Anomaly Detection

被引：1

作者：

Kimball, Joshua ^{[1
]}

Lima, Rodrigo Alves ^{[1
]}

Kanemasa, Yasuhiko ^{[2
]}

Pu, Calton ^{[1
]}

机构：

[1] Georgia Inst Technol, Sch Comp Sci, Atlanta, GA 30332 USA

[2] Fujitsu Labs Ltd, Syst Software Labs, Kawasaki, Kanagawa, Japan

来源：

2020 IEEE 6TH INTERNATIONAL CONFERENCE ON COLLABORATION AND INTERNET COMPUTING (CIC 2020) | 2020年

基金：

美国国家科学基金会;

关键词：

data management; systems performance; anomaly detection; log analysis; data mining; BOTTLENECKS;

D O I：

10.1109/CIC50333.2020.00021

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this work, we present our performance data management system, PerfDB, that we use to study fine-grained performance anomalies like Millibottlenecks. We use it to present the first experimental evidence of a phenomenon we call, "Localized Latency Requests." These are performance bugs that are part of the long-tail of system latency. We also provide a population study of Very Long Response Time (VLRT) requests, a separate performance anomaly belonging to the latency long tail, being inducing by millibottlenecks through queueing effects.

引用

页码：97 / 106

页数：10

共 33 条

[11] Fonseca Rodrigo., 2010, P 2010 INTERNET NETW, P10
[12] Seer: Leveraging Big Data to Navigate the Complexity of Performance Debugging in Cloud Microservices
Gan, Yu
Zhang, Yanqi
Hu, Kelvin
Cheng, Dailun
He, Yuan
Pancholi, Meghna
Delimitrou, Christina
[J]. TWENTY-FOURTH INTERNATIONAL CONFERENCE ON ARCHITECTURAL SUPPORT FOR PROGRAMMING LANGUAGES AND OPERATING SYSTEMS (ASPLOS XXIV), 2019, : 19 - 33
[13] Jonas E., 2019, Cloud programming simplified: A Berkeley view on serverless computing
[14] Canopy: An End-to-End Performance Tracing And Analysis System
Kaldor, Jonathan
Mace, Jonathan
Bejda, Michal
Gao, Edison
Kuropatwa, Wiktor
O'Neill, Joe
Ong, Kian Win
Schaller, Bill
Shan, Pingjia
Viscomi, Brendan
Venkataraman, Vinod
Veeraraghavan, Kaushik
Song, Yee Jiun
[J]. PROCEEDINGS OF THE TWENTY-SIXTH ACM SYMPOSIUM ON OPERATING SYSTEMS PRINCIPLES (SOSP '17), 2017, : 34 - 50
[15] Kimball J., 2019, INT C CLOUD COMPUTIN
[16] Online experiments: Lessons learned
Kohavi, Ron
Longbotham, Roger
[J]. COMPUTER, 2007, 40 (09) : 103 - 105
[17] Kohavi R, 2007, KDD-2007 PROCEEDINGS OF THE THIRTEENTH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, P959
[18] milliScope: a Fine-Grained Monitoring Framework for Performance Debugging of n-Tier Web Services
Lai, Chien-An
Kimball, Josh
Zhu, Tao
Wang, Qingyang
Pu, Calton
[J]. 2017 IEEE 37TH INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS (ICDCS 2017), 2017, : 92 - 102
[19] IO Performance Interference among Consolidated n-Tier Applications: Sharing is Better than Isolation for Disks
Lai, Chien-An
Wang, Qingyang
Kimball, Josh
Li, Jack
Park, Junhee
Pu, Calton
[J]. 2014 IEEE 7TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING (CLOUD), 2014, : 24 - 31
[20] The Impact of Software Resource Allocation on Consolidated n-Tier Applications
Li, Jack
Wang, Qingyang
Lai, Chien-An
Park, Junhee
Yokoyama, Daisaku
Pu, Calton
[J]. 2014 IEEE 7TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING (CLOUD), 2014, : 320 - 327

← 1 2 3 4 →