RAIC: Scaling Storage Availability and Performance in On-Demand Data Centers

نویسندگان

  • Kostas Magoutis
  • Murthy Devarakonda
  • Norbert Vogl
  • Kaladhar Voruganti
چکیده

Redundant Arrays of Independent Controllers (RAIC) is a new methodology for increasing the availability and performance of storage resources in on-demand enterprise data centers. Currently, large and dynamically-growing data sets, typical in e-business ondemand workloads, are constrained by the capacity, availability and performance boundaries of individual RAID controllers. Simple approaches to extending such data sets over multiple RAID controllers result in reduced availability guarantees. Some of the challenges in improving performance by distributing data sets over many RAID controllers include the heterogeneity in the underlying storage resources as well as the lack of information about their characteristics. RAIC is a new methodology to compose storage objects according to user-specified performance and availability goals, which may exceed the capabilities of any single individual RAID controller. RAIC policies ensure that the capacity of storage objects can be extended while maintaining performance and availability goals, even in heterogeneous environments including different types of RAID controllers.

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

SELDAC: Software-Defined Storage based Efficient Load Distribution and Auto Scaling in Cloud Data Centers

—Cloud computing allows the users to access the shared pool of configurable resources such as compute, network and storage on-demand basis from the cloud Data Centers. Cloud storage provides the storage resources to the cloud users over the network. The massive growth of cloud data due to the applications such as video streaming, big data processing, social networking, banking and scientific a...

متن کامل

Improving Data Availability Using Combined Replication Strategy in Cloud Environment

As grow as the data-intensive applications in cloud computing day after day, data popularity in this environment becomes critical and important. Hence to improve data availability and efficient accesses to popular data, replication algorithms are now widely used in distributed systems. However, most of them only replicate the static number of replicas on some requested chosen sites and it is ob...

متن کامل

Logistics performance of European Union markets: Towards the development of entrepreneurship in the transport and storage sector

The markets globalization is one of the factors creating conditions for the development of entrepreneurship. Entrepreneurship does not have one generally accepted definition. Most often, entrepreneurship is perceived as the ability to increase the number of enterprises. Entrepreneurship can be understood as the potential to identify and use development opportunities regardless of own resources....

متن کامل

Efficient location by using data envelopment analysis

So far, many types of location models have been developed to find optimal spatial patterns according to different spatial metrics such as cost, coverage and availability.  The initial focus of these models is on the location availability of service providers and demand estimates, and some of these models are within the framework of multi-objective programming models.  After the advent of scienc...

متن کامل

E2DR: Energy Efficient Data Replication in Data Grid

Abstract— Data grids are an important branch of gird computing which provide mechanisms for the management of large volumes of distributed data. Energy efficiency has recently emerged as a hot topic in large distributed systems. The development of computing systems is traditionally focused on performance improvements driven by the demand of client's applications in scientific and business domai...

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 2004