Using Storage Class Memory for Archives with DAWN, a Durable Array of Wimpy Nodes

نویسندگان

  • Ian F. Adams
  • Ethan L. Miller
  • David S.H. Rosenthal
  • David S. H. Rosenthal
چکیده

The long life and low usage of archival data make cost considerations paramount. Today, most archival storage architectures depend on magnetic or optical media such as tape and disk because they have a low initial cost per byte. The high initial cost of storage class memories (SCMs) has been seen as prohibitive for archival use. Nevertheless, SCMs have many advantages for archival use, including physical robustness and low power usage. In this work, we argue that a suitable architecture can exploit these advantages to make SCM competitive with magnetic media for archival use. Inspired by the FAWN and Pergamum systems, we outline the design of DAWN, a Durable Array of Wimpy Nodes. DAWN will make use of low-power system-on-chip technology paired with SCM to provide a simple, reliable, self-managing archival storage system with a low total cost of operation.

برای دانلود رایگان 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

Improving Datacenter Energy Efficiency Using a Fast Array of Wimpy Nodes

Energy has become an increasingly large financial and scaling burden for computing. With the increasing demand for and scale of Data-Intensive Scalable Computing (DISC), the costs of running large data centers are becoming dominated by power and cooling. In this thesis we propose to help reduce the energy consumed by large-scale computing by using a FAWN: A Fast Array of Wimpy Nodes. FAWN is an...

متن کامل

FAWN: A Fast Array of Wimpy Nodes (CMU-PDL-08-108)

This paper introduces the FAWN—Fast Array of Wimpy Nodes—cluster architecture for providing fast, scalable, and power-efficient key-value storage. A FAWN links together a large number of tiny nodes built using embedded processors and small amounts (2–16GB) of flash memory into an ensemble capable of handling 700 queries per second per node, while consuming fewer than 6 watts of power per node. ...

متن کامل

Energy-efficient Data-intensive Computing with a Fast Array of Wimpy Nodes

Large-scale data-intensive computing systems have become a critical foundation for Internet-scale services. eir widespread growth during the past decade has raised datacenter energy demand and created an increasingly large nancial burden and scaling challenge: Peak energy requirements today are a signi cant cost of provisioning and operating datacenters. In this thesis, we propose to reduce th...

متن کامل

A NEW TWO STEP CLASS OF METHODS WITH MEMORY FOR SOLVING NONLINEAR EQUATIONS WITH HIGH EFFICIENCY INDEX

It is attempted to extend a two-step without memory method to it's with memory. Then, a new two-step derivative free class of without memory methods, requiring three function evaluations per step, is suggested by using a convenient weight function for solving nonlinear equations. Eventually, we obtain a new class of methods by employing a self-accelerating parameter calculated in each iterative...

متن کامل

WattDB - A Journey towards Energy E ciency

Due to their narrow power spectrum between idle and full utilization [2], satisfactory energy e ciency of servers can only be reached in the peak-performance range, whereas energy e ciency obtained for lower activity levels is far from being optimal. Hence, this hardware property obviates a desired energy proportionality or minimal energy use for the entire range of system utilization. To appro...

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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2011