{"title":"Evaluation of Consumer-Grade SSD as a Primary Storage for Small-Scale Desktop Virtualization on VMware Environment","authors":"Marcel","doi":"10.1109/ICOT.2018.8705816","DOIUrl":null,"url":null,"abstract":"Storage performance was main challenging factor of user experience that define the success factor of desktop virtualization initiative. Some solution was introduced to cope with primary storage requirement for performance, but most of it were require significant investment and introduce some complexity. Consumer-grade SATA SSD on the other hand were getting lower in price and more reliable, this paper intended to analyze how consumer-grade SATA SSD can be used as a primary storage solution for desktop virtualization in small-scale environment, with computer laboratory in University ABC as initial case study to deploy the scenario in production environment. To observe how the consumer-grade SATA SSD can perform, this paper conducted 3 categories of scenario: HDD-SAS 7.2k, SSD-SAS and SATA-SSD, using RAID10 and HBA (JBOD) mode configuration. Experimental test conducted within the scope of this paper showed that consumer-grade SSD-SATA can be used as a primary storage for small-scale desktop virtualization solution. While the price of SSD-SATA within the case of this paper was only about 10,4% higher when compared with HDD-SAS 7.2k solution, SSD-SATA (RAID10) also had significant performance improvement when compared with HDD-SAS 7.2k (RAID10), about 19,67 times higher in bandwidth and IO; and only 0,049 times in latency (95,07% lower latency time). While in HBA-mode, SSD-SATA also gave significant improvement compared with HDD-SAS 7.2k (RAID10), about 18,03 times bigger for bandwidth; and about 0,055 times for latency time (94,45% lower latency time).","PeriodicalId":402234,"journal":{"name":"2018 International Conference on Orange Technologies (ICOT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 International Conference on Orange Technologies (ICOT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICOT.2018.8705816","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Storage performance was main challenging factor of user experience that define the success factor of desktop virtualization initiative. Some solution was introduced to cope with primary storage requirement for performance, but most of it were require significant investment and introduce some complexity. Consumer-grade SATA SSD on the other hand were getting lower in price and more reliable, this paper intended to analyze how consumer-grade SATA SSD can be used as a primary storage solution for desktop virtualization in small-scale environment, with computer laboratory in University ABC as initial case study to deploy the scenario in production environment. To observe how the consumer-grade SATA SSD can perform, this paper conducted 3 categories of scenario: HDD-SAS 7.2k, SSD-SAS and SATA-SSD, using RAID10 and HBA (JBOD) mode configuration. Experimental test conducted within the scope of this paper showed that consumer-grade SSD-SATA can be used as a primary storage for small-scale desktop virtualization solution. While the price of SSD-SATA within the case of this paper was only about 10,4% higher when compared with HDD-SAS 7.2k solution, SSD-SATA (RAID10) also had significant performance improvement when compared with HDD-SAS 7.2k (RAID10), about 19,67 times higher in bandwidth and IO; and only 0,049 times in latency (95,07% lower latency time). While in HBA-mode, SSD-SATA also gave significant improvement compared with HDD-SAS 7.2k (RAID10), about 18,03 times bigger for bandwidth; and about 0,055 times for latency time (94,45% lower latency time).