S. Bertram, M. Boniface, M. Surridge, N. Briscombe, M. Hall-May
Industrial adoption of cloud computing for collaborative business processes is limited by their ability to meet inter-enterprise security requirements. Although some clouds offerings comply with security standards, no solution today allows businesses to assess security compliance of applications at the business level and dynamically link to security countermeasures on-demand. In this paper, we present a Platform-as-a-Service infrastructure that combines semantic security risk management tools with dynamic web service policy frameworks to support the mitigation of security threats throughout the lifecycle of a service-oriented application deployed within the cloud. The platform address the need to model security requirements, dynamically provision and configure security services and link operational security events to vulnerabilities and impact assessments at the business level. The Platform has been evaluated using a collaborative engineering design scenario and a proof-of-concept deployed at a multi-tenant cloud as part of the UK CFMS project. The work is being further enhanced in the European Funded SERSCIS project.
{"title":"On-Demand Dynamic Security for Risk-Based Secure Collaboration in Clouds","authors":"S. Bertram, M. Boniface, M. Surridge, N. Briscombe, M. Hall-May","doi":"10.1109/CLOUD.2010.83","DOIUrl":"https://doi.org/10.1109/CLOUD.2010.83","url":null,"abstract":"Industrial adoption of cloud computing for collaborative business processes is limited by their ability to meet inter-enterprise security requirements. Although some clouds offerings comply with security standards, no solution today allows businesses to assess security compliance of applications at the business level and dynamically link to security countermeasures on-demand. In this paper, we present a Platform-as-a-Service infrastructure that combines semantic security risk management tools with dynamic web service policy frameworks to support the mitigation of security threats throughout the lifecycle of a service-oriented application deployed within the cloud. The platform address the need to model security requirements, dynamically provision and configure security services and link operational security events to vulnerabilities and impact assessments at the business level. The Platform has been evaluated using a collaborative engineering design scenario and a proof-of-concept deployed at a multi-tenant cloud as part of the UK CFMS project. The work is being further enhanced in the European Funded SERSCIS project.","PeriodicalId":375404,"journal":{"name":"2010 IEEE 3rd International Conference on Cloud Computing","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127904218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Dynamic provisioning is a useful technique for handling the virtualized multi-tier applications in cloud environment. Understanding the performance of virtualized multi-tier applications is crucial for efficient cloud infrastructure management. In this paper, we present a novel dynamic provisioning technique for a cluster-based virtualized multi-tier application that employ a flexible hybrid queueing model to determine the number of virtual machines at each tier in a virtualized application. We present a cloud data center based on virtual machine to optimize resources provisioning. Using simulation experiments of three-tier application, we adopt an optimization model to minimize the total number of virtual machines while satisfying the customer average response time constraint and the request arrival rate constraint. Our experiments show that cloud data center resources can be allocated accurately with these techniques, and the extra cost can be effectively reduced.
{"title":"Dynamic Provisioning Modeling for Virtualized Multi-tier Applications in Cloud Data Center","authors":"J. Bi, Zhiliang Zhu, Ruixiong Tian, Qingbo Wang","doi":"10.1109/CLOUD.2010.53","DOIUrl":"https://doi.org/10.1109/CLOUD.2010.53","url":null,"abstract":"Dynamic provisioning is a useful technique for handling the virtualized multi-tier applications in cloud environment. Understanding the performance of virtualized multi-tier applications is crucial for efficient cloud infrastructure management. In this paper, we present a novel dynamic provisioning technique for a cluster-based virtualized multi-tier application that employ a flexible hybrid queueing model to determine the number of virtual machines at each tier in a virtualized application. We present a cloud data center based on virtual machine to optimize resources provisioning. Using simulation experiments of three-tier application, we adopt an optimization model to minimize the total number of virtual machines while satisfying the customer average response time constraint and the request arrival rate constraint. Our experiments show that cloud data center resources can be allocated accurately with these techniques, and the extra cost can be effectively reduced.","PeriodicalId":375404,"journal":{"name":"2010 IEEE 3rd International Conference on Cloud Computing","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114504074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Woomin Hwang, Yangwoo Roh, Youngwoo Park, Ki-Woong Park, K. Park
Memory contention among consolidated virtual machines (VMs) creates the need for a memory balancing operation. In an attempt to provide a prompt memory balancing mechanism, we found problems with the retardation of memory transfer by the reclamation delay. The scheduling of the VMs generates the delay, and a conflicts of two reclamation policies between the guest OS and the hypervisor deteriorates it. As a remedy to these problems, we propose HyperDealer, which selects the victim page by applying reference patterns, reclaims the pages with hypervisor-level paging, and transfers those pages with ballooning of the guest OS. Our scheme eliminates the involvement of the victim VM in memory balancing and extends the dwell time of reclaimed pages in the reclaimed state. Consequently, HyperDealer significantly reduces the time taken to transfer memory with a low overhead and enhances the value of additional memory for the recipient VM. The experimental results of our scheme show that the application performance in the recipient VM is 11% more time-efficient and has a penalty which is 50% less than previous approaches.
{"title":"HyperDealer: Reference-Pattern-Aware Instant Memory Balancing for Consolidated Virtual Machines","authors":"Woomin Hwang, Yangwoo Roh, Youngwoo Park, Ki-Woong Park, K. Park","doi":"10.1109/CLOUD.2010.70","DOIUrl":"https://doi.org/10.1109/CLOUD.2010.70","url":null,"abstract":"Memory contention among consolidated virtual machines (VMs) creates the need for a memory balancing operation. In an attempt to provide a prompt memory balancing mechanism, we found problems with the retardation of memory transfer by the reclamation delay. The scheduling of the VMs generates the delay, and a conflicts of two reclamation policies between the guest OS and the hypervisor deteriorates it. As a remedy to these problems, we propose HyperDealer, which selects the victim page by applying reference patterns, reclaims the pages with hypervisor-level paging, and transfers those pages with ballooning of the guest OS. Our scheme eliminates the involvement of the victim VM in memory balancing and extends the dwell time of reclaimed pages in the reclaimed state. Consequently, HyperDealer significantly reduces the time taken to transfer memory with a low overhead and enhances the value of additional memory for the recipient VM. The experimental results of our scheme show that the application performance in the recipient VM is 11% more time-efficient and has a penalty which is 50% less than previous approaches.","PeriodicalId":375404,"journal":{"name":"2010 IEEE 3rd International Conference on Cloud Computing","volume":"197 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121887306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cloud Computing raises numerous questions about the implementation and deployment of Service-Oriented Architecture (SOA) and virtualization. It also raises questions related to services contracts, their management and verification, independently of services migration within the Cloud(s). Issues and solutions related to the verification of contracts compliance are referred as Service Level Checking (SLC). Implementing SLC in the Cloud Computing context requires an innovating and functional architecture, in order to separate monitoring information collection concerns from contracts compliance verification concerns. Such contracts or Service Level Agreements (SLAs) apply to the target systems and services. In order to solve the separation of concerns issue, we have used the mediation approach. Our architecture and prototype have been implemented and validated in the context of the French ANR SemEUsE and European Celtic SERVERY cooperative research projects.
{"title":"Service Level Checking in the Cloud Computing Context","authors":"A. Chazalet","doi":"10.1109/CLOUD.2010.15","DOIUrl":"https://doi.org/10.1109/CLOUD.2010.15","url":null,"abstract":"Cloud Computing raises numerous questions about the implementation and deployment of Service-Oriented Architecture (SOA) and virtualization. It also raises questions related to services contracts, their management and verification, independently of services migration within the Cloud(s). Issues and solutions related to the verification of contracts compliance are referred as Service Level Checking (SLC). Implementing SLC in the Cloud Computing context requires an innovating and functional architecture, in order to separate monitoring information collection concerns from contracts compliance verification concerns. Such contracts or Service Level Agreements (SLAs) apply to the target systems and services. In order to solve the separation of concerns issue, we have used the mediation approach. Our architecture and prototype have been implemented and validated in the context of the French ANR SemEUsE and European Celtic SERVERY cooperative research projects.","PeriodicalId":375404,"journal":{"name":"2010 IEEE 3rd International Conference on Cloud Computing","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124771093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nowadays, it seems like there is nothing that can not be procured online. Closer observations, however, reveal that especially micro businesses do not yet fully benefit from online exposing their products and services. Though micro enterprises play a significant role with respect to our daily shopping, we are still not able to electronically place orders or conduct business with them. In this article, we propose the concept of cloud-based organic product catalogs as an approach towards bringing e-commerce technology closer to micro enterprises.
{"title":"Organic Product Catalogs: Towards an Architecture for Cloud-Based Micro Enterprise E-commerce","authors":"R. Neumann, R. Dumke, A. Schmietendorf","doi":"10.1109/CLOUD.2010.54","DOIUrl":"https://doi.org/10.1109/CLOUD.2010.54","url":null,"abstract":"Nowadays, it seems like there is nothing that can not be procured online. Closer observations, however, reveal that especially micro businesses do not yet fully benefit from online exposing their products and services. Though micro enterprises play a significant role with respect to our daily shopping, we are still not able to electronically place orders or conduct business with them. In this article, we propose the concept of cloud-based organic product catalogs as an approach towards bringing e-commerce technology closer to micro enterprises.","PeriodicalId":375404,"journal":{"name":"2010 IEEE 3rd International Conference on Cloud Computing","volume":"2016 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127463422","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Y. Yazir, Chris Matthews, Roozbeh Farahbod, S. Neville, A. Guitouni, S. Ganti, Y. Coady
In computing clouds, it is desirable to avoid wasting resources as a result of under-utilization and to avoid lengthy response times as a result of over-utilization. In this paper, we propose a new approach for dynamic autonomous resource management in computing clouds. The main contribution of this work is two-fold. First, we adopt a distributed architecture where resource management is decomposed into independent tasks, each of which is performed by Autonomous Node Agents that are tightly coupled with the physical machines in a data center. Second, the Autonomous Node Agents carry out configurations in parallel through Multiple Criteria Decision Analysis using the PROMETHEE method. Simulation results show that the proposed approach is promising in terms of scalability, feasibility and flexibility.
{"title":"Dynamic Resource Allocation in Computing Clouds Using Distributed Multiple Criteria Decision Analysis","authors":"Y. Yazir, Chris Matthews, Roozbeh Farahbod, S. Neville, A. Guitouni, S. Ganti, Y. Coady","doi":"10.1109/CLOUD.2010.66","DOIUrl":"https://doi.org/10.1109/CLOUD.2010.66","url":null,"abstract":"In computing clouds, it is desirable to avoid wasting resources as a result of under-utilization and to avoid lengthy response times as a result of over-utilization. In this paper, we propose a new approach for dynamic autonomous resource management in computing clouds. The main contribution of this work is two-fold. First, we adopt a distributed architecture where resource management is decomposed into independent tasks, each of which is performed by Autonomous Node Agents that are tightly coupled with the physical machines in a data center. Second, the Autonomous Node Agents carry out configurations in parallel through Multiple Criteria Decision Analysis using the PROMETHEE method. Simulation results show that the proposed approach is promising in terms of scalability, feasibility and flexibility.","PeriodicalId":375404,"journal":{"name":"2010 IEEE 3rd International Conference on Cloud Computing","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129842650","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
LH*RE is a new Scalable Distributed Data Structure (SDDS) for hash files stored in a cloud. The client-side symmetric encryption protects the data against the server-side disclosure. The encryption key(s) at the client are backed up in the file. The client may recover/ revoke any keys lost or stolen from its node. A trusted official can also do it on behalf of the client or of an authority, e.g., to imperatively access the data of a client missing or disabled. In contrast, with high assurance, e.g., 99%, the attacker of the cloud should not usually disclose any data, even if the intrusion succeeds over dozens or possibly thousands of servers for a larger file. Storage and primary key-based access performance of LH*RE should be about those of the well-known LH* SDDS. Two messages should typically suffice for a key-based search and four in the worst case, with the application data load factor of 70%, regardless of the file scale up. These features are among most efficient for a hash SDDS. LH*RE should be attractive with respect to the competition.
{"title":"LH*RE: A Scalable Distributed Data Structure with Recoverable Encryption","authors":"S. Jajodia, W. Litwin, T. Schwarz","doi":"10.1109/CLOUD.2010.41","DOIUrl":"https://doi.org/10.1109/CLOUD.2010.41","url":null,"abstract":"LH*RE is a new Scalable Distributed Data Structure (SDDS) for hash files stored in a cloud. The client-side symmetric encryption protects the data against the server-side disclosure. The encryption key(s) at the client are backed up in the file. The client may recover/ revoke any keys lost or stolen from its node. A trusted official can also do it on behalf of the client or of an authority, e.g., to imperatively access the data of a client missing or disabled. In contrast, with high assurance, e.g., 99%, the attacker of the cloud should not usually disclose any data, even if the intrusion succeeds over dozens or possibly thousands of servers for a larger file. Storage and primary key-based access performance of LH*RE should be about those of the well-known LH* SDDS. Two messages should typically suffice for a key-based search and four in the worst case, with the application data load factor of 70%, regardless of the file scale up. These features are among most efficient for a hash SDDS. LH*RE should be attractive with respect to the competition.","PeriodicalId":375404,"journal":{"name":"2010 IEEE 3rd International Conference on Cloud Computing","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122738383","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Christopher Ward, N. Aravamudan, K. Bhattacharya, Karen Cheng, Robert Filepp, Robert D. Kearney, B. Peterson, L. Shwartz, Christopher C. Young
The steady drumbeat of Cloud as a disruptive influence for Infrastructure Service Providers (ISP’s) and the enablement vehicle for Software As A Service (SAAS)providers can be heard loud and clear in the industry today. In fact, Cloud is probably at the peak of the hype curve, and already there are identified challenges associated with effective deployment for business critical applications (so called Production Applications) in mature enterprises. One of these challenges is the smooth migration of workload from the previous environment to the new cloud enabled environment in a cost effective way, with minimal disruption and risk. In this paper we introduce extensions to an integrated automation capability called the Darwin framework that enables workload migration for this scenario and discuss the impact that automated migration has on the cost and risks normally associated with migration to clouds.
{"title":"Workload Migration into Clouds Challenges, Experiences, Opportunities","authors":"Christopher Ward, N. Aravamudan, K. Bhattacharya, Karen Cheng, Robert Filepp, Robert D. Kearney, B. Peterson, L. Shwartz, Christopher C. Young","doi":"10.1109/CLOUD.2010.84","DOIUrl":"https://doi.org/10.1109/CLOUD.2010.84","url":null,"abstract":"The steady drumbeat of Cloud as a disruptive influence for Infrastructure Service Providers (ISP’s) and the enablement vehicle for Software As A Service (SAAS)providers can be heard loud and clear in the industry today. In fact, Cloud is probably at the peak of the hype curve, and already there are identified challenges associated with effective deployment for business critical applications (so called Production Applications) in mature enterprises. One of these challenges is the smooth migration of workload from the previous environment to the new cloud enabled environment in a cost effective way, with minimal disruption and risk. In this paper we introduce extensions to an integrated automation capability called the Darwin framework that enables workload migration for this scenario and discuss the impact that automated migration has on the cost and risks normally associated with migration to clouds.","PeriodicalId":375404,"journal":{"name":"2010 IEEE 3rd International Conference on Cloud Computing","volume":"148 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115296769","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Matthias Farwick, B. Agreiter, R. Breu, M. Haering, Karsten Voges, Inge Hanschke
Enterprise Architecture Management (EAM), and in particular IT--landscape management try to model the IT- and business elements of a company, in order to analyze its efficiency towards supporting business goals, optimize business--IT alignment, and to plan future IT--transformation as well as IT--standardization. A major challenge in this field is the elicitation of infrastructure information from run--time systems, e.g., to answer the question which servers provide services to a specific information system. Capturing this data is a time consuming manual task which leads to quickly outdated information. Similar to traditional hardware, cloud infrastructure needs to be documented in an EA modeling order to gain insight on its relationships with business information systems and ultimately the business goals. The aim of our research in this area is the automatic integration of various runtime information sources into an EAM view. The overall goal is to minimize manual work to keep enterprise architecture information up--to--date. This enables enterprise architects to make timely and precise decisions. In this work we focus on how information on the cloud infrastructure can be seamlessly integrated into an EA view. Making the cloud visible for enterprise architects is especially important to meet legal (privacy) requirements, on the storage and processing location of data. We present a conceptual approach for the information integration problem, and introduce our prototypical implementation with the open--source infrastructure cloud implementation Eucalyptus, and the open--source enterprise architecture management tool iteraplan.
{"title":"Towards Living Landscape Models: Automated Integration of Infrastructure Cloud in Enterprise Architecture Management","authors":"Matthias Farwick, B. Agreiter, R. Breu, M. Haering, Karsten Voges, Inge Hanschke","doi":"10.1109/CLOUD.2010.20","DOIUrl":"https://doi.org/10.1109/CLOUD.2010.20","url":null,"abstract":"Enterprise Architecture Management (EAM), and in particular IT--landscape management try to model the IT- and business elements of a company, in order to analyze its efficiency towards supporting business goals, optimize business--IT alignment, and to plan future IT--transformation as well as IT--standardization. A major challenge in this field is the elicitation of infrastructure information from run--time systems, e.g., to answer the question which servers provide services to a specific information system. Capturing this data is a time consuming manual task which leads to quickly outdated information. Similar to traditional hardware, cloud infrastructure needs to be documented in an EA modeling order to gain insight on its relationships with business information systems and ultimately the business goals. The aim of our research in this area is the automatic integration of various runtime information sources into an EAM view. The overall goal is to minimize manual work to keep enterprise architecture information up--to--date. This enables enterprise architects to make timely and precise decisions. In this work we focus on how information on the cloud infrastructure can be seamlessly integrated into an EA view. Making the cloud visible for enterprise architects is especially important to meet legal (privacy) requirements, on the storage and processing location of data. We present a conceptual approach for the information integration problem, and introduce our prototypical implementation with the open--source infrastructure cloud implementation Eucalyptus, and the open--source enterprise architecture management tool iteraplan.","PeriodicalId":375404,"journal":{"name":"2010 IEEE 3rd International Conference on Cloud Computing","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131141768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With Cloud Computing gaining tremendous importance in the recent past, understanding low-level implications of the cloud infrastructure becomes necessary. One of the key technologies deployed in large Cloud infrastructures namely the Amazon EC2 for providing isolation and separate protection domains for multiple clients is virtualization. Therefore, identifying the performance bottlenecks in a virtualized setup and understanding the implications of workload combinations and resource configurations on the overall I/O performance helps both the cloud providers in managing their infrastructure efficiently and also their customers by means of better performance. In this paper we present the measurement results of detailed experiments conducted on a virtualized setup focusing on the storage I/O performance. We categorize our experimental evaluation into four components, each of which presenting some significant factors that affect storage I/O performance. Our experimental results can be useful for cloud application developers to tune their applications for better I/O performance and for the cloud service providers to make more effective decisions on resource provisioning and workload scheduling.
{"title":"Storage Management in Virtualized Cloud Environment","authors":"Sankaran Sivathanu, Ling Liu, Yiduo Mei, Xing Pu","doi":"10.1109/CLOUD.2010.27","DOIUrl":"https://doi.org/10.1109/CLOUD.2010.27","url":null,"abstract":"With Cloud Computing gaining tremendous importance in the recent past, understanding low-level implications of the cloud infrastructure becomes necessary. One of the key technologies deployed in large Cloud infrastructures namely the Amazon EC2 for providing isolation and separate protection domains for multiple clients is virtualization. Therefore, identifying the performance bottlenecks in a virtualized setup and understanding the implications of workload combinations and resource configurations on the overall I/O performance helps both the cloud providers in managing their infrastructure efficiently and also their customers by means of better performance. In this paper we present the measurement results of detailed experiments conducted on a virtualized setup focusing on the storage I/O performance. We categorize our experimental evaluation into four components, each of which presenting some significant factors that affect storage I/O performance. Our experimental results can be useful for cloud application developers to tune their applications for better I/O performance and for the cloud service providers to make more effective decisions on resource provisioning and workload scheduling.","PeriodicalId":375404,"journal":{"name":"2010 IEEE 3rd International Conference on Cloud Computing","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114171136","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：