Satori: Enlightened Page Sharing

نویسندگان

  • Grzegorz Milos
  • Derek Gordon Murray
  • Steven Hand
  • Michael A. Fetterman
چکیده

We introduce Satori, an efficient and effective system for sharing memory in virtualised systems. Satori uses enlightenments in guest operating systems to detect sharing opportunities and manage the surplus memory that results from sharing. Our approach has three key benefits over existing systems: it is more able to detect short-lived sharing opportunities, it is efficient and incurs negligible overhead, and it maintains better performance isolation between virtual machines. We have implemented and evaluated a prototype of Satori for the Xen virtual machine monitor. In our evaluation, we show that Satori quickly exploits up to 94% of the maximum possible sharing with insignificant performance overhead. Furthermore, we demonstrate workloads where the additional memory improves macrobenchmark performance by a factor of two.

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

USENIX Annual Technical Conference

After thanking the program committee and the USENIX staff, co-chairs Geoffrey M. Voelker and Alec Wolman announced the Best Paper awards: “Satori, Enlightened Page Sharing” by Grzegorz Miłoś, Derek G. Murray, Steven Hand, and Michael A. Fetterman, and “Tolerating File-System Mistakes with EnvyFS,” by Lakshmi N. Bairavasundaram, Swaminathan Sundararaman, Andrea C. Arpaci-Dusseau, and Remzi H. Ar...

متن کامل

SATORI: a system for ontology-guided visual exploration of biomedical data repositories.

Motivation The ever-increasing number of biomedical datasets provides tremendous opportunities for re-use but current data repositories provide limited means of exploration apart from text-based search. Ontological metadata annotations provide context by semantically relating datasets. Visualizing this rich network of relationships can improve the explorability of large data repositories and he...

متن کامل

Turbo-Satori: a neurofeedback and brain-computer interface toolbox for real-time functional near-infrared spectroscopy.

Turbo-Satori is a neurofeedback and brain-computer interface (BCI) toolbox for real-time functional near-infrared spectroscopy (fNIRS). It incorporates multiple pipelines from real-time preprocessing and analysis to neurofeedback and BCI applications. The toolbox is designed with a focus in usability, enabling a fast setup and execution of real-time experiments. Turbo-Satori uses an incremental...

متن کامل

Shared Page Table : Sharing of Virtual Memory Resources ∗

Traditionally, UNIX has been weak in data sharing. By data sharing, we mean that multiple cooperative processes concurrently access and update the same set of data. As the degree of sharing (the number of cooperative processes) increases, the existing UNIX virtual memory systems run into page table thrashing, which causes a major performance bottleneck. Once page table thrashing occurs, UNIX pe...

متن کامل

Introduction to Arabic Speech Recognition Using CMUSphinx System

demonstrate the possible adaptability of this system to Arabic voice recognition.

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 2009