Energy Efficiency and Storage Flexibility in the Blue File System

Slides:



Advertisements
Similar presentations
Self-Tuning Wireless Network Power Management Manish Anand Edmund B. Nightingale Jason Flinn Department of Electrical Engineering and Computer Science.
Advertisements

Mobile Computing
Cobalt: Separating content distribution from authorization in distributed file systems Kaushik Veeraraghavan Andrew Myrick Jason Flinn University of Michigan.
A Pervasive Reminder System for Smart Homes Sylvain GIROUX and Simon GUERTIN Département d’informatique, Université de Sherbrooke 2500 boul. Université,
Flash: An efficient and portable Web server Authors: Vivek S. Pai, Peter Druschel, Willy Zwaenepoel Presented at the Usenix Technical Conference, June.
Ceph: A Scalable, High-Performance Distributed File System Priya Bhat, Yonggang Liu, Jing Qin.
An Adaptable Benchmark for MPFS Performance Testing A Master Thesis Presentation Yubing Wang Advisor: Prof. Mark Claypool.
Reducing the Energy Usage of Office Applications Jason Flinn M. Satyanarayanan Carnegie Mellon University Eyal de Lara Dan S. Wallach Willy Zwaenepoel.
Cooperative Caching Middleware for Cluster-Based Servers Francisco Matias Cuenca-Acuna Thu D. Nguyen Panic Lab Department of Computer Science Rutgers University.
Figure 1.1 Interaction between applications and the operating system.
WhereStore: Location-based Data Storage for Mobile Devices Interacting with the Cloud Patrick Stuedi, Iqbal Mohomed, Doug Terry Microsoft Research.
Introduction Operating Systems’ Concepts and Structure Lecture 1 ~ Spring, 2008 ~ Spring, 2008TUCN. Operating Systems. Lecture 1.
Client-Server Computing in Mobile Environments
RAID-x: A New Distributed Disk Array for I/O-Centric Cluster Computing Kai Hwang, Hai Jin, and Roy Ho.
Slingshot: Deploying Stateful Services in Wireless Hotspots Ya-Yunn Su Jason Flinn University of Michigan.
Energy Efficiency and Storage Flexibility in the Blue File System Edmund B Nightingale Jason Flinn University of Michigan.
Sanjay Ghemawat, Howard Gobioff, and Shun-Tak Leung Google∗
©Kwan Sai Kit, All Rights Reserved Windows Small Business Server 2003 Features.
PARAID: The Gear-Shifting Power-Aware RAID Charles Weddle, Mathew Oldham, An-I Andy Wang – Florida State University Peter Reiher – University of California,
Data Staging on Untrusted Surrogates Jason Flinn Shafeeq Sinnamohideen Niraj Tolia Mahadev Satyanarayanan Intel Research Pittsburgh, University of Michigan,
Slingshot: Deploying Stateful Services in Wireless Hotspots Ya-Yunn Su Jason Flinn University of Michigan Presenter: Youngki, Lee.
WMPI 2006, Austin, Texas © 2006 John C. Koob An Empirical Evaluation of Semiconductor File Memory as a Disk Cache John C. Koob Duncan G. Elliott Bruce.
Sensitivity of Cluster File System Access to I/O Server Selection A. Apon, P. Wolinski, and G. Amerson University of Arkansas.
Network Computing Laboratory Integrating Portable and Distributed Storage Niraj Tolia, Jan Harkes, Michael Kozuch, and M. Satyanarayanan CMU and Intel.
OPERETTA: An Optimal Energy Efficient Bandwidth Aggregation System Karim Habak†, Khaled A. Harras‡, and Moustafa Youssef† †Egypt-Japan University of Sc.
SPECULATIVE EXECUTION IN A DISTRIBUTED FILE SYSTEM E. B. Nightingale P. M. Chen J. Flint University of Michigan.
WMPI 2006, Austin, Texas © 2006 John C. Koob An Empirical Evaluation of Semiconductor File Memory as a Disk Cache John C. Koob Duncan G. Elliott Bruce.
1 Mobile Computing and Wireless Networking CS 851 Seminar 2002 Fall University of Virginia.
CS Spring 2009 CS 414 – Multimedia Systems Design Lecture 30 – Media Server (Part 5) Klara Nahrstedt Spring 2009.
Speculative Execution in a Distributed File System Ed Nightingale Peter Chen Jason Flinn University of Michigan.
Improving Disk Throughput in Data-Intensive Servers Enrique V. Carrera and Ricardo Bianchini Department of Computer Science Rutgers University.
EnsemBlue: Integrating Distributed Storage and Consumer Electronics Daniel Peek and Jason Flinn University of Michigan.
ENERGY-EFFICIENCY AND STORAGE FLEXIBILITY IN THE BLUE FILE SYSTEM E. B. Nightingale and J. Flinn University of Michigan.
Tanenbaum & Van Steen, Distributed Systems: Principles and Paradigms, 2e, (c) 2007 Prentice-Hall, Inc. All rights reserved DISTRIBUTED SYSTEMS.
CSE 451: Operating Systems Section 9: Storage; networks.
Speculative Execution in a Distributed File System Ed Nightingale Peter Chen Jason Flinn University of Michigan Best Paper at SOSP 2005 Modified for CS739.
Course 03 Basic Concepts assist. eng. Jánó Rajmond, PhD
The Google File System Sanjay Ghemawat, Howard Gobioff, and Shun-Tak Leung Presenter: Chao-Han Tsai (Some slides adapted from the Google’s series lectures)
Tanenbaum & Van Steen, Distributed Systems: Principles and Paradigms, 2e, (c) 2007 Prentice-Hall, Inc. All rights reserved DISTRIBUTED SYSTEMS.
Taeho Kgil, Trevor Mudge Advanced Computer Architecture Laboratory The University of Michigan Ann Arbor, USA CASES’06.
A Practical Performance Analysis of Stream Reuse Techniques in Peer-to-Peer VoD Systems Leonardo B. Pinho and Claudio L. Amorim Parallel Computing Laboratory.
21st ACM Symposium on Operating Systems Principles, Oct 2007 DejaView: A Personal Virtual Computer Recorder.
GridOS: Operating System Services for Grid Architectures
Policies in Distributed Data Storage
CSE 486/586 Distributed Systems Distributed File Systems
Presented by Dr. Ramesh K. Karne
University of Maryland College Park
Distributed File Systems
Slingshot: Deploying Stateful Services in Wireless Hotspots
Jiang Zhou, Wei Xie, Dong Dai, and Yong Chen
Database Performance Tuning and Query Optimization
Networking Lexi Becker Chapter is broke in two parts
Outline Every Joule is Previous: The Case for Revisiting Operating System Design for Energy Efficiency 19-Sep-18 Ubiquitous Computing.
The Google File System Sanjay Ghemawat, Howard Gobioff and Shun-Tak Leung Google Presented by Jiamin Huang EECS 582 – W16.
PARAID: A Gear-Shifting Power-Aware RAID
Digital Processing Platform
ECE-752 Zheng Zheng, Anuj Gadiyar
Energy Efficiency and Storage Flexibility in the Blue File System
Going Viral: Flash Crowds in an Open CDN
Outline Announcements Lab2 Distributed File Systems 1/17/2019 COP5611.
NeST: Network Storage Technologies
Chapter 11 Database Performance Tuning and Query Optimization
CSE 486/586 Distributed Systems Distributed File Systems
Outline - Energy Management
Outline Review of Quiz #1 Distributed File Systems 4/20/2019 COP5611.
CSCI {4,6}900: Ubiquitous Computing
Software Overheads of Storage in Ceph
Page Cache and Page Writeback
Network File System (NFS)
Dong Hyun Kang, Changwoo Min, Young Ik Eom
Presentation transcript:

Energy Efficiency and Storage Flexibility in the Blue File System Edmund B Nightingale Jason Flinn University of Michigan

Towards Ubiquitous Data Access Pervasive computing: anywhere anytime any device Ubiquitous WiFi access Mobile storage Barriers to pervasive data access: Varying I/O performance Energy hogs! Stale, inconsistent data BlueFS overcomes these barriers The Blue File System

Change is Constant Access times vary across storage devices Wireless networks are highly variable Power management affects performance BlueFS provides an adaptive cache hierarchy The Blue File System

Power to the People Distributed file systems use power hungry devices Distributed file systems not designed for energy BlueFS “clean sheet design” for energy efficiency The Blue File System

You Can Take it with You Want to leverage the benefits of portable storage Portable storage is not a mobile data panacea Can be lost, stolen, damaged Sharing is hard More replication = higher chances of stale/inconsistent data BlueFS integrates portable storage into file system The Blue File System

Organization Motivation The Blue File System Evaluation Related Work Conclusion The Blue File System

The Blue File System Work Home > /BlueFS/ > /BlueFS/ Local disk BlueFS Server > /BlueFS/ Local disk Local disk The Blue File System

Write to Many Asynchrony improves performance VFS Ops Write 2 Asynchrony improves performance Aggregating writes saves energy To microdrive Write 1 Unlink 2 Unlink 1 Create 1 Create 2 Mkdir 2 Mkdir 1 To BlueFS Server BlueFS The Blue File System

Read From Any BlueFS monitors cost of reading data from each device > cat /BlueFS/foo Blk 1 BlueFS Server Micro drive BlueFS Blk 2 BlueFS monitors cost of reading data from each device Pick device best performance, least energy The Blue File System

Power Management BlueFS integrated with power management strategies Self Tuning Power Management Hints State Transitions BlueFS BlueFS integrated with power management strategies When a device transitions, BlueFS is notified The Blue File System

Hiding device transitions 5) Network transitions to PSM 1) Network accesses Network 2) Ghost hints issued 3) Disk spins up 4) Disk accesses begin Disk The Blue File System

Cache Management Storage devices treated as cache BlueFS decides which files to cache When a device fills up, LRU used to make space Affinity: file always on portable storage The Blue File System

Cache Consistency Work Home > /BlueFS/ > /BlueFS/ Local disk BlueFS Server > /BlueFS/ > /BlueFS/ Local disk Local disk The Blue File System

Evaluation Goals How does performance of BlueFS compare to other DFS? What benefit does an adaptive cache hierarchy provide? How well does BlueFS support portable storage? How much does BlueFS reduce client energy usage? How does BlueFS perform with heterogeneous storage? The Blue File System

Comparing BlueFS to other DFS Andrew benchmark: Untar, configure, make, delete Apache source 6000.0 BlueFS 10x faster than NFS, 16% faster than Coda WD The Blue File System

Benefits of Adaptive Cache Hierarchy Read various files with the disk in standby mode BlueFS reads 4k files up to 60x faster than ext2 The Blue File System

Support for Portable Storage Ran a file system trace as fast as possible using portable storage BlueFS 44% faster than Lookaside, up to 3x faster for high latency The Blue File System

Energy Efficient Data Access Ran first 10,000 ops of Purcell trace with half full cache Reduces interactive delay 76%, 55% less energy than Coda The Blue File System

Heterogeneous Storage Added 16 MB flash to BlueFS, ran Purcell with full local cache First two bars we’ve already seen on previous slide. With flash BlueFS reduces interactive delay 48%, 25% less energy The Blue File System

Related Work AFS [Howard et al] Coda [Kistler et al] & lookaside caching [Tolia et al] PersonalRAID [Sobti et al] Segank [Sobti et al] Cooperative I/O [Weissel et al] LBFS [Muthitacharoen et al] The Blue File System

Conclusions BlueFS enables ubiquitous data access by: Adapting to device characteristics Reducing mobile computer energy usage Seamlessly integrating portable storage Source: http://notrump.eecs.umich.edu/group/group.html The Blue File System

System Architecture The Blue File System Linux Kernel Wolverine Applications BlueFS Kernel Module Wolverine Linux Kernel Linux File Cache USBStick CardFlash Micro-drive Local Disk To BlueFS Server VFS Operations Up-call Mention Read from any write to many semantics The Blue File System

BFS Kernel Intercepts Linux VFS calls Communicates with Wolverine through pseudo-device driver Caches and invalidates data & metadata in Linux file cache Operations redirected to Wolverine Enables support for devices with different consistency semantics The Blue File System