Proceedings of the Seventh ACM Symposium on Cloud Computing最新文献_第4页

SNC-Meister: Admitting More Tenants with Tail Latency SLOs SNC-Meister:接纳更多带有尾延迟slo的租户

Proceedings of the Seventh ACM Symposium on Cloud Computing Pub Date : 2016-10-05 DOI: 10.1145/2987550.2987585

T. Zhu, Daniel S. Berger, Mor Harchol-Balter

{"title":"SNC-Meister: Admitting More Tenants with Tail Latency SLOs","authors":"T. Zhu, Daniel S. Berger, Mor Harchol-Balter","doi":"10.1145/2987550.2987585","DOIUrl":"https://doi.org/10.1145/2987550.2987585","url":null,"abstract":"Meeting tail latency Service Level Objectives (SLOs) in shared cloud networks is both important and challenging. One primary challenge is determining limits on the multi-tenancy such that SLOs are met. Doing so involves estimating latency, which is difficult, especially when tenants exhibit bursty behavior as is common in production environments. Nevertheless, recent papers in the past two years (Silo, QJump, and PriorityMeister) show techniques for calculating latency based on a branch of mathematical modeling called Deterministic Network Calculus (DNC). The DNC theory is designed for adversarial worst-case conditions, which is sometimes necessary, but is often overly conservative. Typical tenants do not require strict worst-case guarantees, but are only looking for SLOs at lower percentiles (e.g., 99th, 99.9th). This paper describes SNC-Meister, a new admission control system for tail latency SLOs. SNC-Meister improves upon the state-of-the-art DNC-based systems by using a new theory, Stochastic Network Calculus (SNC), which is designed for tail latency percentiles. Focusing on tail latency percentiles, rather than the adversarial worst-case DNC latency, allows SNC-Meister to pack together many more tenants: in experiments with production traces, SNC-Meister supports 75% more tenants than the state-of-the-art.","PeriodicalId":362207,"journal":{"name":"Proceedings of the Seventh ACM Symposium on Cloud Computing","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132015507","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}

引用次数: 43

Follow the Sun through the Clouds: Application Migration for Geographically Shifting Workloads 跟随太阳到云:地理位置移动工作负载的应用程序迁移

Proceedings of the Seventh ACM Symposium on Cloud Computing Pub Date : 2016-10-05 DOI: 10.1145/2987550.2987561

Zhiming Shen, Qin Jia, Gur-Eyal Sela, Ben Rainero, Weijia Song, R. V. Renesse, Hakim Weatherspoon

{"title":"Follow the Sun through the Clouds: Application Migration for Geographically Shifting Workloads","authors":"Zhiming Shen, Qin Jia, Gur-Eyal Sela, Ben Rainero, Weijia Song, R. V. Renesse, Hakim Weatherspoon","doi":"10.1145/2987550.2987561","DOIUrl":"https://doi.org/10.1145/2987550.2987561","url":null,"abstract":"Global cloud services have to respond to workloads that shift geographically as a function of time-of-day or in response to special events. While many such services have support for adding nodes in one region and removing nodes in another, we demonstrate that such mechanisms can lead to significant performance degradation. Yet other services do not support application-level migration at all. Live VM migration between availability zones or even across cloud providers would be ideal, but cloud providers do not support this flexible mechanism. This paper presents the Supercloud, a uniform cloud service that supports live VM migration between data centers of all major public cloud providers. The Supercloud also provides a scheduler that automatically determines when and where to move VMs for optimal performance. We demonstrate that live VM migration can support shifting workloads effectively, with low downtimes and transparently to both services and their clients. The Supercloud also addresses challenges for supporting cross-cloud storage and networking.","PeriodicalId":362207,"journal":{"name":"Proceedings of the Seventh ACM Symposium on Cloud Computing","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133133448","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}

引用次数: 39

BASS: Improving I/O Performance for Cloud Block Storage via Byte-Addressable Storage Stack BASS:通过字节可寻址存储堆栈提高云块存储的I/O性能

Proceedings of the Seventh ACM Symposium on Cloud Computing Pub Date : 2016-10-05 DOI: 10.1145/2987550.2987557

Hui Lu, Brendan Saltaformaggio, Cong Xu, U. Bellur, Dongyan Xu

{"title":"BASS: Improving I/O Performance for Cloud Block Storage via Byte-Addressable Storage Stack","authors":"Hui Lu, Brendan Saltaformaggio, Cong Xu, U. Bellur, Dongyan Xu","doi":"10.1145/2987550.2987557","DOIUrl":"https://doi.org/10.1145/2987550.2987557","url":null,"abstract":"In an Infrastructure-as-a-Service cloud, cloud block storage offers conventional, block-level storage resources via a storage area network. However, compared to local storage, this multilayered cloud storage model imposes considerable I/O overheads due to much longer I/O path in the virtualized cloud. In this paper, we propose a novel byte-addressable storage stack, BASS, to bridge the addressability gap between the storage and network stacks in cloud, and in return boost I/O performance for cloud block storage. Equipped with byte-addressability, BASS not only avails the benefits of using variable-length I/O requests that avoid unnecessary data transfer, but also enables a highly efficient non-blocking approach that eliminates the blocking of write processes. We have developed a generic prototype of BASS based on Linux storage stack, which is applicable to traditional VMs, lightweight containers and physical machines. Our extensive evaluation with micro-benchmarks, I/O traces and real-world applications demonstrates the effectiveness of BASS, with significantly improved I/O performance and reduced storage network usage.","PeriodicalId":362207,"journal":{"name":"Proceedings of the Seventh ACM Symposium on Cloud Computing","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130941014","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}

引用次数: 5

Proceedings of the Seventh ACM Symposium on Cloud Computing 第七届ACM云计算研讨会论文集

Proceedings of the Seventh ACM Symposium on Cloud Computing Pub Date : 2016-10-05 DOI: 10.1145/2987550

M. Aguilera, Brian F. Cooper, Y. Diao

引用次数: 0

Tutamen: A Next-Generation Secret-Storage Platform Tutamen:下一代秘密存储平台

Proceedings of the Seventh ACM Symposium on Cloud Computing Pub Date : 2016-10-05 DOI: 10.1145/2987550.2987581

Andy Sayler, Taylor Andrews, Matthew Monaco, D. Grunwald

{"title":"Tutamen: A Next-Generation Secret-Storage Platform","authors":"Andy Sayler, Taylor Andrews, Matthew Monaco, D. Grunwald","doi":"10.1145/2987550.2987581","DOIUrl":"https://doi.org/10.1145/2987550.2987581","url":null,"abstract":"The storage and management of secrets (encryption keys, passwords, etc) are significant open problems in the age of ephemeral, cloud-based computing infrastructure. How do we store and control access to the secrets necessary to configure and operate a range of modern technologies without sacrificing security and privacy requirements or significantly curtailing the desirable capabilities of our systems? To answer this question, we propose Tutamen: a next-generation secret-storage service. Tutamen offers a number of desirable properties not present in existing secret-storage solutions. These include the ability to operate across administrative domain boundaries and atop minimally trusted infrastructure. Tutamen also supports access control based on contextual, multi-factor, and alternate-band authentication parameters. These properties have allowed us to leverage Tutamen to support a variety of use cases not easily realizable using existing systems, including supporting full-disk encryption on headless servers and providing fully-featured client-side encryption for cloud-based file-storage services. In this paper, we present an overview of the secret-storage challenge, Tutamen's design and architecture, the implementation of our Tutamen prototype, and several of the applications we have built atop Tutamen. We conclude that Tutamen effectively eases the secret-storage burden and allows developers and systems administrators to achieve previously unattainable security-oriented goals while still supporting a wide range of feature-oriented requirements.","PeriodicalId":362207,"journal":{"name":"Proceedings of the Seventh ACM Symposium on Cloud Computing","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124898684","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}

引用次数: 7