A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://repository.lib.ncsu.edu/bitstream/handle/1840.4/8250/TR-2013-4.pdf;jsessionid=1792013BA48B71539A386BAD34A56828?sequence=1">the original URL</a>. The file type is <code>application/pdf</code>.
<i title="ACM Press">
Proceedings of the 22nd international symposium on High-performance parallel and distributed computing - HPDC '13
The popularity of cloud-based interactive computing services (e.g., virtual desktops) brings new management challenges. Each interactive user leaves abundant but fluctuating residual resources while being intolerant to latency, precluding the use of aggressive VM consolidation. In this paper, we present the Resource Harvester for Interactive Clouds (RHIC), an autonomous management framework that harnesses dynamic residual resources aggressively without slowing the harvested interactive<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2493123.2462927">doi:10.1145/2493123.2462927</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/h6kgbrs6c5cwhnjjfkxys4pcxu">fatcat:h6kgbrs6c5cwhnjjfkxys4pcxu</a> </span>
more »... RHIC builds adhoc clusters for running throughput-oriented "background" workloads using a hybrid of residual and dedicated resources. These hybrid clusters offer significant gains over normal dedicated clusters: 20-40% cost and 20-29% energy in our testbed. For a given background job, RHIC intelligently discovers/maintains the ideal cluster size and composition, to meet user-specified goals such as cost/energy minimization or deadlines. RHIC employs black-box workload performance modeling, requiring only system-level metrics and incorporating techniques to improve modeling accuracy under bursty and heterogeneous residual resources. We demonstrate the effectiveness and adaptivity of our RHIC prototype with two parallel data analytics frameworks, Hadoop and HBase. Our results show that RHIC finds near-ideal cluster sizes/compositions across 28 workload/goal combinations, with 5% average error for cost minimization and 3% for energy, relative to exhaustive searches, and runtimes 2% under deadlines. Further, RHIC significantly outperforms alternative approaches, tolerates high instability in the harvested interactive cloud, works with heterogeneous hardware and imposes only 0.5% overhead.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200309104800/https://repository.lib.ncsu.edu/bitstream/handle/1840.4/8250/TR-2013-4.pdf;jsessionid=1792013BA48B71539A386BAD34A56828?sequence=1" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/56/7a/567aa6c6f41f6be20924b7458b3de5f388625d9b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2493123.2462927"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>