<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="6.x">Drupal-Biblio</source-app><ref-type>10</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Jerome Boulon</style></author><author><style face="normal" font="default" size="100%">Andy Konwinski</style></author><author><style face="normal" font="default" size="100%">Runping Qi</style></author><author><style face="normal" font="default" size="100%">Ariel Rabkin</style></author><author><style face="normal" font="default" size="100%">Eric Yang</style></author><author><style face="normal" font="default" size="100%">Mac Yang</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Chukwa, a large-scale monitoring system</style></title><secondary-title><style face="normal" font="default" size="100%">In Cloud Computing and its Applications (CCA '08)</style></secondary-title></titles><dates><year><style  face="normal" font="default" size="100%">2008</style></year><pub-dates><date><style  face="normal" font="default" size="100%">10/2008</style></date></pub-dates></dates><urls><web-urls><url><style face="normal" font="default" size="100%">http://www.cca08.org/papers/Paper-13-Ariel-Rabkin.pdf</style></url></web-urls></urls><pub-location><style face="normal" font="default" size="100%">Chicago, IL</style></pub-location><pages><style face="normal" font="default" size="100%">1-5</style></pages><abstract><style face="normal" font="default" size="100%">We describe the design and initial implementation of Chukwa, a data collection, monitoring and analysis system for large clusters. Chukwa is built on top of Hadoop, an open source distributed filesystem and MapReduce implementation. Chukwa trades a few minutes of latency between data collection and availability in order to scale to thousands of nodes and beyond. Chukwa also includes a flexible and powerful toolkit for querying and processing collected data. These tools support a flexible interface for displaying monitoring and analysis results, enabling human decision makers to operate and optimize the clusters being monitored.</style></abstract></record></records></xml>