Towards Optimized Self-Management of Distributed Object Storage Systems

نویسندگان

  • Roman Talyansky
  • Ewnetu Bayuh Lakew
  • Cristian Klein
  • Francisco Hernandez-Rodriguez
  • Erik Elmroth
  • Eliezer Levy
چکیده

Cloud storage is increasingly adopted by users due to simplified storage systems compared to on-premise storage. These systems are mostly presented as Object Storage Systems (OSSs), hiding issues, such as redundancy, from users. As new industries are considering adopting clouds for storage, OSSs have to evolve to support new needs. Among the most challenging is assuring guaranteed performance. In this paper, we present Controllable Trade-offs (CTO), an OSS-agnostic solution to add performance guarantees. CTO presents itself as a thin layer that mediates requests between the user and the OSS. For generic support, performance is controlled by tuning the rejection probability, and implemented as a user-side queue. Results show that CTO may reduce penalties 3.23 times on average and up to 68 times when the load is high.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Optimum energy management strategy in smart distribution networks considering the effect of distributed generators and energy storage units

The penetration of distributed generation sources and energy storage units in distribution networks is increasing. Therefore, their impact on the reliability of the network is very necessary. In this study, in order to provide an optimal energy management strategy for smart distribution network, the multi-objective optimization problem of dynamic distribution feeder reconfiguration in the pres...

متن کامل

Green Energy Generation in Buildings: Grid-Tied Distributed Generation Systems (DGS) With Energy Storage Applications to Sustain the Smart Grid Transformation

The challenge of electricity distribution’s upgrade to incorporate new technologies is big, and electric utilities are mandated to work diligently on this agenda, thus making investments to ensure that current networks maintain their electricity supply commitments secure and reliable in face of disruptions and adverse environmental conditions from a variety of sources. The paper presents a new ...

متن کامل

Towards Low-Latency Model-Oriented Distributed Systems Management

Windows and Unix systems have been traditionally very different with regard to configuration storage and management. In this paper we have adapted our CIM-based model-driven management framework, AdCIM, to extract, integrate and modify management and configuration information from both types of OS in a multiplatform and seamless way. We have achieved very low latencies and client footprints wit...

متن کامل

Probabilistically Secure Cooperative Distributed Storage

The trend towards self-organization of systems like peer-to-peer or mobile ad hoc networks generates increasing needs for distributed data management, in particular data backup and distributed storage functions that will themselves be self-organized and cooperative. Unfortunately, in such systems, the data stored are exposed to the selfishness (e.g. data discarded because of lack of resources) ...

متن کامل

Homomorphic Self-repairing Codes for Agile Maintenance of Distributed Storage Systems

Distributed data storage systems are essential to deal with the need to store massive volumes of data. In order to make such a system fault-tolerant, some form of redundancy becomes crucial. There are various overheads that are incurred due to such redundancy most prominent ones being overheads in terms of storage space and maintenance bandwidth requirements. Erasure codes provide a storage eff...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2015