<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="6.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Nuno Lopes</style></author><author><style face="normal" font="default" size="100%">Carlos Baquero Moreno</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Building Inverted Indexes Using Balanced Trees Over DHT Systems</style></title><secondary-title><style face="normal" font="default" size="100%">EuroSys 2006 Poster</style></secondary-title></titles><dates><year><style  face="normal" font="default" size="100%">2010</style></year></dates><urls><related-urls><url><style face="normal" font="default" size="100%">https://haslab.uminho.pt/sites/default/files/cbm/files/10.1.1.163.9683.pdf</style></url></related-urls></urls><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;Distributed Hash Table (DHT) systems are scalable and efficient data structures for object storage and location using a simple put/get interface. These systems place objects over a very large set of hosts using a multitude of algorithms in order to distribute objects uniformly among hosts using logarithmic (or lower) costs for routing table sizes and message hops [1, 2]. However, these systems assume that object size (storage load) and popularity (communication load) follow an uniform distribution. When unbalanced data is used on a DHT, hotspots are created at some specific (random) hosts. Although one might argue that storage is not a critical resource, due to the current trend on secondary storage capacity, storing such large objects creates network bottlenecks, which in turn may limit data availability.&lt;/p&gt;
</style></abstract></record></records></xml>