{"_id":"NRNv3Az9Do9Dro6vb","bibbaseid":"lee-fox-bigdatabenchmarksonbaremetalcloud-2018","downloads":0,"creationDate":"2018-08-11T20:07:28.361Z","title":"Big Data Benchmarks on Bare Metal Cloud","author_short":["Lee, H.","Fox, G., C."],"year":2018,"bibtype":"techreport","biburl":"https://bibbase.org/service/mendeley/42d295c0-0737-38d6-8b43-508cab6ea85d","bibdata":{"title":"Big Data Benchmarks on Bare Metal Cloud","type":"techreport","year":"2018","pages":"1-5","id":"f1245ec0-41d2-354a-a60b-557a174f28ee","created":"2019-10-01T17:21:00.989Z","file_attached":false,"profile_id":"42d295c0-0737-38d6-8b43-508cab6ea85d","last_modified":"2020-05-11T14:43:31.664Z","read":false,"starred":false,"authored":"true","confirmed":false,"hidden":false,"citation_key":"Lee2018","private_publication":false,"abstract":"High performance computing requires to deal with a large number of applications running on different environments, and bare metal cloud is promising to enable new hardware features but in a easier way than traditional HPC systems. Data that we need to deal with is growing exponentially although many big data software support processing them at scale. We perform big data benchmark on public bare metal clouds to demonstrate computing performance with direct hardware access and block storage using up to 25000 and 32000 IOPS respectively for Oracle and Amazon. The preliminary results indicate that Amazon and Oracle are competitive supporting high throughput and low latency with operations in parallel. We investigate further on storage options available on Oracle bare metal with different data sets and anticipate to evaluate petabyte-scale workloads on cluster configurations in the future.","bibtype":"techreport","author":"Lee, Hyungro and Fox, Geoffrey C","doi":"10.13140/RG.2.2.12204.36486","bibtex":"@techreport{\n title = {Big Data Benchmarks on Bare Metal Cloud},\n type = {techreport},\n year = {2018},\n pages = {1-5},\n id = {f1245ec0-41d2-354a-a60b-557a174f28ee},\n created = {2019-10-01T17:21:00.989Z},\n file_attached = {false},\n profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d},\n last_modified = {2020-05-11T14:43:31.664Z},\n read = {false},\n starred = {false},\n authored = {true},\n confirmed = {false},\n hidden = {false},\n citation_key = {Lee2018},\n private_publication = {false},\n abstract = {High performance computing requires to deal with a large number of applications running on different environments, and bare metal cloud is promising to enable new hardware features but in a easier way than traditional HPC systems. Data that we need to deal with is growing exponentially although many big data software support processing them at scale. We perform big data benchmark on public bare metal clouds to demonstrate computing performance with direct hardware access and block storage using up to 25000 and 32000 IOPS respectively for Oracle and Amazon. The preliminary results indicate that Amazon and Oracle are competitive supporting high throughput and low latency with operations in parallel. We investigate further on storage options available on Oracle bare metal with different data sets and anticipate to evaluate petabyte-scale workloads on cluster configurations in the future.},\n bibtype = {techreport},\n author = {Lee, Hyungro and Fox, Geoffrey C},\n doi = {10.13140/RG.2.2.12204.36486}\n}","author_short":["Lee, H.","Fox, G., C."],"biburl":"https://bibbase.org/service/mendeley/42d295c0-0737-38d6-8b43-508cab6ea85d","bibbaseid":"lee-fox-bigdatabenchmarksonbaremetalcloud-2018","role":"author","urls":{},"metadata":{"authorlinks":{}},"downloads":0},"search_terms":["big","data","benchmarks","bare","metal","cloud","lee","fox"],"keywords":[],"authorIDs":[],"dataSources":["zgahneP4uAjKbudrQ","ya2CyA73rpZseyrZ8","2252seNhipfTmjEBQ"]}