We think you have liked this presentation. If you wish to download it, please recommend it to your friends in any social system. Share buttons are a little bit lower. Thank you!
Presentation is loading. Please wait.
Published byChristina Hoye
Modified over 2 years ago
High-Performance Computing Seminar © Toni Cortes A Case for Heterogeneous Disk Arrays Toni Cortes and Jesús Labarta Departament dArquitectura de Computadors Univeritat Politècnica de Catalunya - Barcelona
© Toni Cortes Disk Arrays (RAIDs) Group several disks Single address space High capacity Improved performance Low cost Heterogeneous RAID Not all disks are equal B0 B1 B2 B3 B4 B5 B6 B7...
© Toni Cortes Motivation Heterogeneous disk arrays are becoming a common configuration Replacing a new disk Adding new disks Current solution All disks are treated as equal No performance gain is obtained No capacity gain is obtained
© Toni Cortes Objective AdaptRaid0 Block-distribution policy Take advantage of the goodies of each disk Target Environment Scientific and general purpose Not multimedia Solutions have already been presented Very dependent on some characteristics Disk arrays level 0 (RAID0) Level 5 is under development
© Toni Cortes Related Work Multimedia Systems Random distribution with replication (Santos98) Policy based on logical disks (Zimmerman98) Use fast disk for hot data (Dan95) Differences: Large blocks, only reads, and sustained bandwidth General purpose HP AutoRaid (Wilkes95) Disc-Cache Disk (Hu98) Differences: Do not adapt to the existent hardware
© Toni Cortes Disk Arrays and Parallelism Parallelism within a request Requests have to large The sub-request of each disk has to be large Seek + search + transfer in all disks Parallelism between requests The number of disks has to be large Compared to the average number of disks used in a requests
© Toni Cortes AdaptRaid0: An Example Basic idea Load each disk depending on its characteristics Example 1 fast disk Size = S Performance = P 1 slow disk Size = S/2 Performance = P/ FastSlow FastSlow Patern
© Toni Cortes AdaptRaid0: The Parameters Utilization factor (UF) One factor per disk Larger disks have more blocks? Faster disks have more blocks? Lines in pattern (LIP) We define a pattern using the UF Large patterns allow more requests with good disks Small patterns allow a better distribution
© Toni Cortes AdaptRaid0: The Algorithm Algorithm Decide LIP and Uf d Compute number of blocks per disk in the pattern Blocks d = int(UF d * LIP) Distribute blocks in a round-robin way Use the available disks A disk becomes unavailable when Blocks d have already been placed in it Repeat step 3 until one disk becomes full
© Toni Cortes Methodology Parameters UF based on the size of the disk Lines in pattern 100 lines for 8-disk arrays 10 lines for 32-disk arrays Simulation Simulator: HRaid (Cortes99) Workload from HP labs (1999) Reference systems Raid0 and OnlyFast
© Toni Cortes Environment Disks Fast disk Seagate Barracuda 4LP (4.339 Gbytes) Slow disk Seagate Cheetah 4LP (2.061 Gbytes) Bus 10us latency 100Mbit/s bandwidth File system 10 requests in parallel
© Toni Cortes Capacity Evaluation Raid0 Constant capacity Small OnlyFast Small capacity with few disks AadaptRaid0 Offers the best size
© Toni Cortes Performance Evaluation (8 disks) Raid0 Does not use Characteristics of good disks OnlyFast Does not use Parallelism between requests
© Toni Cortes Performance Evaluation (32 disks) Raid0 Does not use Characteristics of good disks It uses Parallelism between requests OnlyFast Does not use Parallelism between requests
© Toni Cortes Conclusions AdaptRaid0 Performance It knows how to use the disks Allows parallelism Size It uses all the available capacity
© Toni Cortes Future Work Solve the same problem for Raid5 Problem of parity blocks Less scalable No parallelism among requests
Storage Networks How to Handle Heterogeneity Bálint Miklós January 24th, 2005 ETH Zürich External Memory Algorithms and Data Structures.
1 Copyright © 2013 Elsevier Inc. All rights reserved. Chapter 112.
1 Copyright © 2013 Elsevier Inc. All rights reserved. Chapter 75.
1 Copyright © 2013 Elsevier Inc. All rights reserved. Chapter 44.
1 Copyright © 2013 Elsevier Inc. All rights reserved. Chapter 107.
1 Copyright © 2013 Elsevier Inc. All rights reserved. Chapter 58.
1 Copyright © 2013 Elsevier Inc. All rights reserved. Chapter 40.
1 Copyright © 2013 Elsevier Inc. All rights reserved. Chapter 29.
1 Copyright © 2013 Elsevier Inc. All rights reserved. Chapter 28.
W4118 Operating Systems Instructor: Junfeng Yang.
Raid dr. Patrick De Causmaecker What is RAID Redundant Array of Independent (Inexpensive) Disks A set of disk stations treated as one.
1 Copyright © 2013 Elsevier Inc. All rights reserved. Chapter 38.
Disk Arrays COEN 180. Large Storage Systems Collection of disks to store large amount of data. Performance advantage: Each drive can satisfy only so many.
Redundant Array of Independent Disks (RAID) Striping of data across multiple media for expansion, performance and reliability.
1 Copyright © 2013 Elsevier Inc. All rights reserved. Chapter 116.
Dynamic Thread Assignment on Heterogeneous Multiprocessor Architectures Pree Thiengburanathum Advanced computer architecture Oct 24,
1 Copyright © 2013 Elsevier Inc. All rights reserved. Chapter 101.
Analysis of NUCA Policies for CMPs Using Parsec Benchmark Suite Javier Lira ψ Carlos Molina ф Antonio González λ λ Intel Barcelona Research Center Intel.
Performance Analysis of NUCA Policies for CMPs Using Parsec v2.0 Benchmark Suite Javier Lira ψ Carlos Molina ф Antonio González λ λ Intel Barcelona Research.
THE QUESTIONS THAT NO ONE ASKS Social Entrepreneurship Conference Luis Pareras.
DiskSim – Storage System Simulator Michigan-CMU Sriram Govindan
Last Bank: Dealing with Address Reuse in Non-Uniform Cache Architecture for CMPs Javier Lira ψ Carlos Molina ф Antonio González λ λ Intel Barcelona Research.
THE HP AUTORAID HIERARCHICAL STORAGE SYSTEM J. Wilkes, R. Golding, C. Staelin T. Sullivan HP Laboratories, Palo Alto, CA.
1 Copyright © 2013 Elsevier Inc. All rights reserved. Appendix 01.
Disks. 2 The Memory Hierarchy Each level acts as a cache for the layer below it CPU registers, L1 cache L2 cache primary memory disk storage (secondary.
CS 153 Design of Operating Systems Spring 2015 Lecture 22: File system optimizations.
UPC MICRO35 Istanbul Nov Effective Instruction Scheduling Techniques for an Interleaved Cache Clustered VLIW Processor Enric Gibert 1 Jesús Sánchez.
SE-292 High Performance Computing Memory Hierarchy R. Govindarajan
U P C MICRO36 San Diego December 2003 Flexible Compiler-Managed L0 Buffers for Clustered VLIW Processors Enric Gibert 1 Jesús Sánchez 2 Antonio González.
RAID Redundant Arrays of Independent Disks Courtesy of Satya, Fall 99.
Collective Buffering: Improving Parallel I/O Performance By Bill Nitzberg and Virginia Lo.
HyLog: A High Performance Approach to Managing Disk Layout Wenguang Wang Yanping Zhao Rick Bunt Department of Computer Science University of Saskatchewan.
A CASE FOR REDUNDANT ARRAYS OF INEXPENSIVE DISKS (RAID) D. A. Patterson, G. A. Gibson, R. H. Katz University of California, Berkeley.
© 2004 Hewlett-Packard Development Company, L.P. The information contained herein is subject to change without notice Volume Concepts HP Restricted Module.
Introduction to RAID Rogério Perino de Oliveira Neves Patrick De Causmaecker
1 I/O Management and Disk Scheduling Disk Performance Parameters Disk Scheduling Disk Management RAID.
1 File System Implementation Operating Systems Hebrew University Spring 2010.
U P C CGO’03 San Francisco March 2003 Local Scheduling Techniques for Memory Coherence in a Clustered VLIW Processor with a Distributed Data Cache Enric.
Csci4203/ece43631 Review Quiz. 1)It is less expensive 2)It is usually faster 3)Its average CPI is smaller 4)It allows a faster clock rate 5)It has a simpler.
24 Hour Clock We are learning how to read the 24 hour clock.
I/O Management and Disk Scheduling Chapter 11. I/O Driver OS module which controls an I/O device hides the device specifics from the above layers in the.
Infrastructure for Data Warehouses. Basics Of Data Access Data Store Machine Memory Buffer Memory Cache Data Store Buffer Bus Structure.
Improved Approximation for the Directed Spanner Problem Grigory Yaroslavtsev Penn State + AT&T Labs - Research (intern) Joint work with Berman (PSU), Bhattacharyya.
Copyright, Harris Corporation & Ophir Frieder, Redundant Arrays of Inexpensive Disks (RAID)
© Toni Cortes Improving Application Performance through Swap Compression R. Cervera, T. Cortes, Y. Becerra and S. Lucas.
Lecture 17 I/O Optimization. Disk Organization Tracks: concentric rings around disk surface Sectors: arc of track, minimum unit of transfer Cylinder:
MiddleMan: A Video Caching Proxy Server NOSSDAV 2000 Brian Smith Department of Computer Science Cornell University Ithaca, NY Soam Acharya Inktomi Corporation.
Operating Systems ECE344 Ashvin Goel ECE University of Toronto Disks and RAID.
Copyright © The McGraw-Hill Companies, Inc. Permission required for reproduction or display. Chapter 1 Image Slides.
© 2016 SlidePlayer.com Inc. All rights reserved.