Wide area cluster monitoring with Ganglia
Published 1 January 2003
Sacerdoti, Katz, Massie, Culler
Citations180
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A structure for monitoring a large set of computational clusters comprised of many clusters while keeping processing requirements low is presented and emphasis is placed on scalability, fast query response, fault tolerance, and grid compatibility.
Abstract
In this paper, we present a structure for monitoring a large set of computational clusters. We illustrate methods for scaling a monitor network comprised of many clusters while keeping processing requirements low. A design for presenting high-level Web-based summaries of the monitor network is provided, along with a generalization to a distributed, multiple-resolution monitoring tree. Emphasis is placed on scalability, fast query response, fault tolerance, and grid compatibility. Experimental evidence is presented that demonstrates the performance of our design.
Keywords
Computer Science
Future Generation Computer SystemsThe network weather service: a distributed resource performance forecasting service for metacomputing
1,287 Citations1999Rich Wolski, Neil Spring +1 more
The current implementation of the NWS for Unix and TCP/IP sockets is described and examples of its performance monitoring and forecasting capabilities are provided.
Parallel ComputingThe ganglia distributed monitoring system: design, implementation, and experience
1,267 Citations2004Matthew L Massie, Brent Chun +1 more
The design, implementation, and evaluation of Ganglia are presented along with experience gained through real world deployments on systems of widely varying scale, configurations, and target application domains over the last two and a half years.
A directory service for configuring high-performance distributed computations
415 Citations2002Sharyn M. Fitzgerald, I. Foster +4 more
This work proposes a Metacomputing Directory Service that provides efficient and scalable access to diverse, dynamic, and distributed information about resource structure and state and defines an extensible data model to represent required information and presents a scalable, high-performance, distributed implementation.
Knowledge and common knowledge in a distributed environment
286 Citations1984Joseph Y. Halpern, Yoram Moses
A model, analysis, and protocol framework for soft state-based communication
141 Citations1999Suchitra Raman, Steven McCanne
The design of the "Soft State Transport Protocol" (SSTP) is sketched, which enjoys the robustness of soft state while retaining the performance benefit of hard state protocols like TCP through its judicious use of feedback.
Supermon: a high-speed cluster monitoring system
125 Citations2003Matthew Sottile, Ronald G. Minnich
The Supermon architecture is presented and initial performance measurements on a cluster of heterogeneous Alpha-processor based nodes are discussed to demonstrate its scalability and function in a heterogeneous environment.
Efficient reactive monitoring
83 Citations2002M. Dilman, D. Raz
This paper develops and analyze several monitoring algorithms that achieve significant reduction in the management overhead while maintaining the functionality and indicates the specific statistical factors that affect the saving and shows how to choose the right algorithm for the type of monitored data.
Leveraging standard core technologies to programmatically build Linux cluster appliances
23 Citations2003Mason J. Katz, Philip M. Papadopoulos +1 more
This work has developed a configuration infrastructure with well-defined inheritance properties that leverages and builds on de facto standards including: XML (with standard parsers), RedHat Kickstart, HTTP transport, CGI, SQL databases, and graph constructs to easily define cluster appliances.
Resource-aware stream management with the customizable dproc distributed monitoring mechanisms
23 Citations2004Sandip Agarwala, Christian Poellabauer +3 more
This paper shows that dproc's run-time customizability for resource monitoring can be customized according to a client's resource availabilities (dynamic stream management), and that appropriate balance can be maintained between monitoring overheads and application quality.
IEEE Journal on Selected Areas in CommunicationsToward efficient monitoring
21 Citations2000Jiping Jiao, Syed Husnain Abass Naqvi +2 more
This paper provides a formal description of the problem of monitoring rapidly changing data, and proposes different algorithms for each classes in terms of the integrity constraints that govern the evolution of the environment, and presents heuristics for low-cost low-complexity measuring algorithms.