Hunting for problems with Artemis

Gabriela F. Creţu-Ciocârlie; Mihai Budiu; Moises Goldszmidt

Hunting for problems with Artemis

Gabriela F. Creţu-Ciocârlie
, Mihai Budiu
, Moises Goldszmidt

Department of Computer Science

Microsoft USA

Research output: Contribution to conference › Paper › peer-review

34 Scopus citations

Abstract

Artemis is a modular application designed for analyzing and troubleshooting the performance of large clusters running datacenter services. Artemis is composed of four modules: (1) distributed log collection and data extraction, (2) a database storing the extracted data, (3) an interactive visualization tool for exploring the data, and (4) a plug-in interface (and a set of sample plug-ins) allowing users to implement data analysis tools including (a) the extraction and construction of new features from the basic measurements collected, and (b) the implementation and invocation of statistical and machine learning algorithms and tools. In this paper we describe each of these components and then we illustrate the power of the plug-in architecture by presenting a case-study using Artemis to analyze a Dryad application running on a 240-machine cluster.

Original language	English
State	Published - 2008
Event	1st USENIX Workshop on the Analysis of System Logs, WASL 2008 - San Diego, United States Duration: 7 Dec 2008 → …

Conference

Conference	1st USENIX Workshop on the Analysis of System Logs, WASL 2008
Country/Territory	United States
City	San Diego
Period	7/12/08 → …

Cite this

@conference{29666796b5f949a58840610745a6f2f6,

title = "Hunting for problems with Artemis",

abstract = "Artemis is a modular application designed for analyzing and troubleshooting the performance of large clusters running datacenter services. Artemis is composed of four modules: (1) distributed log collection and data extraction, (2) a database storing the extracted data, (3) an interactive visualization tool for exploring the data, and (4) a plug-in interface (and a set of sample plug-ins) allowing users to implement data analysis tools including (a) the extraction and construction of new features from the basic measurements collected, and (b) the implementation and invocation of statistical and machine learning algorithms and tools. In this paper we describe each of these components and then we illustrate the power of the plug-in architecture by presenting a case-study using Artemis to analyze a Dryad application running on a 240-machine cluster.",

author = "Cre{\c t}u-Cioc{\^a}rlie, \{Gabriela F.\} and Mihai Budiu and Moises Goldszmidt",

note = "Publisher Copyright: {\textcopyright} 1st USENIX Workshop on the Analysis of System Logs, WASL 2008. All rights reserved.; 1st USENIX Workshop on the Analysis of System Logs, WASL 2008 ; Conference date: 07-12-2008",

year = "2008",

language = "English",

}

TY - CONF

T1 - Hunting for problems with Artemis

AU - Creţu-Ciocârlie, Gabriela F.

AU - Budiu, Mihai

AU - Goldszmidt, Moises

PY - 2008

Y1 - 2008

N2 - Artemis is a modular application designed for analyzing and troubleshooting the performance of large clusters running datacenter services. Artemis is composed of four modules: (1) distributed log collection and data extraction, (2) a database storing the extracted data, (3) an interactive visualization tool for exploring the data, and (4) a plug-in interface (and a set of sample plug-ins) allowing users to implement data analysis tools including (a) the extraction and construction of new features from the basic measurements collected, and (b) the implementation and invocation of statistical and machine learning algorithms and tools. In this paper we describe each of these components and then we illustrate the power of the plug-in architecture by presenting a case-study using Artemis to analyze a Dryad application running on a 240-machine cluster.

AB - Artemis is a modular application designed for analyzing and troubleshooting the performance of large clusters running datacenter services. Artemis is composed of four modules: (1) distributed log collection and data extraction, (2) a database storing the extracted data, (3) an interactive visualization tool for exploring the data, and (4) a plug-in interface (and a set of sample plug-ins) allowing users to implement data analysis tools including (a) the extraction and construction of new features from the basic measurements collected, and (b) the implementation and invocation of statistical and machine learning algorithms and tools. In this paper we describe each of these components and then we illustrate the power of the plug-in architecture by presenting a case-study using Artemis to analyze a Dryad application running on a 240-machine cluster.

UR - https://www.scopus.com/pages/publications/85092624038

UR - https://www.scopus.com/pages/publications/85092624038#tab=citedBy

M3 - Paper

AN - SCOPUS:85092624038

T2 - 1st USENIX Workshop on the Analysis of System Logs, WASL 2008

Y2 - 7 December 2008

ER -

Hunting for problems with Artemis

Abstract

Conference

Other files and links

Fingerprint

Cite this