Disk Storage SystemsCSCE430/830 Disk Storage Systems CSCE430/830 Computer Architecture Lecturer: Prof. Hong Jiang Courtesy of Yifeng Zhu (U. Maine) Fall,

Slides:



Advertisements
Similar presentations
Chapter 6 I/O Systems.
Advertisements

CPS216: Data-Intensive Computing Systems Data Access from Disks Shivnath Babu.
IT253: Computer Organization
Overview of Mass Storage Structure
Silberschatz, Galvin and Gagne Operating System Concepts Disk Scheduling Disk IO requests are for blocks, by number Block requests come in an.
I/O Management and Disk Scheduling
Operating Systems Disk Scheduling A. Frank - P. Weisberg.
- Dr. Kalpakis CMSC Dr. Kalpakis 1 Outline In implementing DBMS we need to answer How should the system store and manage very large amounts of data?
13. Secondary Storage (S&G, Ch. 13)
Operating Systems ECE344 Ashvin Goel ECE University of Toronto Disks and RAID.
OPERATING SYSTEMS CS3530 Summer 2014 OPERATING SYSTEMS CS3530 Summer 2014 Input/Output System Chapter 9.
Disk Storage SystemsCSCE430/830 Disk Storage Systems CSCE430/830 Computer Architecture Lecturer: Prof. Hong Jiang Courtesy of Yifeng Zhu (U. Maine) Fall,
Review of Mem. HierarchyCSCE430/830 Review of Memory Hierarchy CSCE430/830 Computer Architecture Lecturer: Prof. Hong Jiang Courtesy of Yifeng Zhu (U.
Lecture 17 I/O Optimization. Disk Organization Tracks: concentric rings around disk surface Sectors: arc of track, minimum unit of transfer Cylinder:
Disk Drivers May 10, 2000 Instructor: Gary Kimura.
1 Storage Hierarchy Cache Main Memory Virtual Memory File System Tertiary Storage Programs DBMS Capacity & Cost Secondary Storage.
CS 342 – Operating Systems Spring 2003 © Ibrahim Korpeoglu Bilkent University1 Input/Output – 5 Disks CS 342 – Operating Systems Ibrahim Korpeoglu Bilkent.
Disks.
12/3/2004EE 42 fall 2004 lecture 391 Lecture #39: Magnetic memory storage Last lecture: –Dynamic Ram –E 2 memory This lecture: –Future memory technologies.
Avishai Wool lecture Introduction to Systems Programming Lecture 9 Input-Output Devices.
04/21/2004CSCI 315 Operating Systems Design1 Disk Scheduling.
CPSC 231 Secondary storage (D.H.)1 Learning Objectives Understanding disk organization. Sectors, clusters and extents. Fragmentation. Disk access time.
Secondary Storage Management Hank Levy. 8/7/20152 Secondary Storage • Secondary Storage is usually: –anything outside of “primary memory” –storage that.
Introduction to Database Systems 1 The Storage Hierarchy and Magnetic Disks Storage Technology: Topic 1.
Disk and I/O Management
MM File Management Karrie Karahlaios and Brian P. Bailey Spring 2007.
Device Management. So far… We have covered CPU and memory management Computing is not interesting without I/Os Device management: the OS component that.
Topic: Disks – file system devices. Rotational Media Sector Track Cylinder Head Platter Arm Access time = seek time + rotational delay + transfer time.
Copyright ©: Nahrstedt, Angrave, Abdelzaher, Caccamo1 Disk & disk scheduling.
IT 344: Operating Systems Winter 2010 Module 13 Secondary Storage Chia-Chi Teng CTB 265.
Disks Chapter 5 Thursday, April 5, Today’s Schedule Input/Output – Disks (Chapter 5.4)  Magnetic vs. Optical Disks  RAID levels and functions.
Lecture 3 Page 1 CS 111 Online Disk Drives An especially important and complex form of I/O device Still the primary method of providing stable storage.
UNIVERSITY of WISCONSIN-MADISON Computer Sciences Department
Disk Storage SystemsCSCE430/830 Disk Storage Systems CSCE430/830 Computer Architecture Lecturer: Prof. Hong Jiang Courtesy of Yifeng Zhu (U. Maine) Fall,
Chapter 12: Mass-Storage Systems
Operating Systems (CS 340 D) Princess Nora University Faculty of Computer & Information Systems Computer science Department.
Section 13.2 – Secondary storage management (Former Student’s Note)
Device Management Mark Stanovich Operating Systems COP 4610.
Disk Average Seek Time. Multi-platter Disk platter Disk read/write arm read/write head.
CPSC 231 Secondary storage (D.H.)1 Learning Objectives Understanding disk organization. Sectors, clusters and extents. Fragmentation. Disk access time.
COSC 6340: Disks 1 Disks and Files DBMS stores information on (“hard”) disks. This has major implications for DBMS design! » READ: transfer data from disk.
Device Management Andy Wang Operating Systems COP 4610 / CGS 5765.
CPS216: Advanced Database Systems Notes 03: Data Access from Disks Shivnath Babu.
CSE 451: Operating Systems Spring 2010 Module 12.5 Secondary Storage John Zahorjan Allen Center 534.
Chapter 10: Mass-Storage Systems
CHAPTER 10: Computer Peripherals
Sarah Diesburg Operating Systems CS 3430
Disks and RAID.
Secondary Storage Secondary storage typically: Characteristics:
IT 344: Operating Systems Winter 2008 Module 13 Secondary Storage
Lecture 45 Syed Mansoor Sarwar
Disks and Files DBMS stores information on (“hard”) disks.
CSE 153 Design of Operating Systems Winter 2018
CSE 451: Operating Systems Winter 2006 Module 13 Secondary Storage
CSE 451: Operating Systems Autumn 2003 Lecture 12 Secondary Storage
CSE 451: Operating Systems Winter 2007 Module 13 Secondary Storage
CSE 451: Operating Systems Spring 2006 Module 13 Secondary Storage
Disks and scheduling algorithms
Secondary Storage Management Brian Bershad
Persistence: hard disk drive
CSE 451: Operating Systems Secondary Storage
Chapter 11 I/O Management and Disk Scheduling
CSE 451: Operating Systems Winter 2003 Lecture 12 Secondary Storage
CSE 451: Operating Systems Spring 2005 Module 13 Secondary Storage
Secondary Storage Management Hank Levy
CSE451 File System Introduction and Disk Drivers Autumn 2002
CSE 451: Operating Systems Autumn 2004 Secondary Storage
CSE 451: Operating Systems Winter 2004 Module 13 Secondary Storage
Lecture 10: Magnetic Disks
Andy Wang Operating Systems COP 4610 / CGS 5765
Presentation transcript:

Disk Storage SystemsCSCE430/830 Disk Storage Systems CSCE430/830 Computer Architecture Lecturer: Prof. Hong Jiang Courtesy of Yifeng Zhu (U. Maine) Fall, 2006 Portions of these slides are derived from: Dave Patterson © UCB

Disk Storage SystemsCSCE430/830 Disk Device Terminology

Disk Storage SystemsCSCE430/830 Disk Overview: Data Layout tract cylinder sector heads platters

Disk Storage SystemsCSCE430/830 Disk Device Performance Platter Arm Actuator HeadSector Inner Track Outer Track Disk Latency = Seek Time + Rotation Time + Transfer Time + Controller Overhead Seek Time? Depends no. tracks the arm moves and seek speed of disk Rotation Time? depends on rotational speed and how far the sector is from the head Transfer Time? depends on data rate (bandwidth) of disk (bit density) and the size of request Controller Spindle

Disk Storage SystemsCSCE430/830 Disk Time Example Disk parameters: –Transfer size is 8K bytes –Advertised average seek time is 12 ms –Disk spins at 7200 RPM –Transfer rate is 4 MB/sec Controller overhead is 2 ms Assume that disk is idle so no queuing delay What is average disk access time for a sector?

Disk Storage SystemsCSCE430/830 Disk Time Example Disk parameters: –Transfer size is 8K bytes –Advertised average seek time is 12 ms –Disk spins at 7200 RPM –Transfer rate is 4 MB/sec Controller overhead is 2 ms Assume that disk is idle so no queuing delay What is average disk access time for a sector? –Avg seek + avg rotational delay + transfer time + controller overhead –12 ms + 0.5/(7200 RPM/60) + 8 KB/4 MB/s + 2 ms – = 20 ms Advertised seek time assumes no locality: typically 1/4 to 1/3 advertised seek time: 12 ms 3-4 ms

Disk Storage SystemsCSCE430/830 The following shows two potential ways of numbering the sectors of data on a disk (only two tracks are shown and each track has eight sectors). Assuming that typical reads are contiguous (e.g., all 16 sectors are read in order), which way of numbering the sectors will be likely to result in higher performance? Why? Cylinder and Head Skew

Disk Storage SystemsCSCE430/830 Disk Scheduling Seek time is a dominant factor of total disk I/O time Let operating system or disk controller choose which request to serve next depending on the head s current position and requested block s position on disk (disk scheduling) Note that disk scheduling CPU scheduling –a mechanical device – hard to determine (accurate) access times –disk accesses can/should not be preempted – run until it finishes –disk I/O often the main performance bottleneck General goals –short response time –high overall throughput –fairness (equal probability for all blocks to be accessed in the same time) Tradeoff: seek and rotational delay vs. maximum response time

Disk Storage SystemsCSCE430/830 Disk Scheduling Several traditional algorithms –First-Come-First-Serve (FCFS) –Shortest Seek Time First (SSTF) –SCAN (and variations) –Look (and variations) –… A LOT of different algorithms exist depending on expected access pattern

Disk Storage SystemsCSCE430/830 First – Come – First – Serve (FCFS) FCFS serves the first arriving request first: Long seeks Short average response time time cylinder number incoming requests (in order of arrival, denoted by cylinder number): scheduling queue

Disk Storage SystemsCSCE430/830 SCAN SCAN (elevator) moves head edge to edge and serves requests on the way: bi-directional compromise between response time and seek time optimizations several optimizations: C-SCAN, LOOK, C-LOOK, … time cylinder number incoming requests (in order of arrival): scheduling queue

Disk Storage SystemsCSCE430/830 SCAN vs. FCFS Disk scheduling makes a difference! In this case, we see that SCAN requires much less head movement compared to FCFS cylinder number time

Disk Storage SystemsCSCE430/830 Modern Disk Scheduling Disk used to be simple devices and disk scheduling used to be performed by OS (file system or device driver) only … … but, new disks are more complex –hide their true layout, e.g., »only logical block numbers »different number of surfaces, cylinders, sectors, etc. OS viewreal view

Disk Storage SystemsCSCE430/830 Modern Disk Scheduling Disk used to be simple devices and disk scheduling used to be performed by OS (file system or device driver) only … … but, new disks are more complex –hide their true layout –transparently move blocks to spare cylinders »e.g., due to bad disk blocks OS viewreal view

Disk Storage SystemsCSCE430/830 Modern Disk Scheduling Disk used to be simple devices and disk scheduling used to be performed by OS (file system or device driver) only … … but, new disks are more complex –hide their true layout –transparently move blocks to spare cylinders –have different zones OS viewreal view NB! illustration of transfer time, not rotation speed Constant angular velocity (CAV) disks –constant rotation speed –equal amount of data in each track thus, constant transfer time Zoned CAV disks –constant rotation speed –zones are ranges of tracks –typical few zones –the different zones have different amount of data, i.e., more better on outer tracks thus, variable transfer time

Disk Storage SystemsCSCE430/830 Zoned Bit Recording To eliminate this wasted space, modern hard disks employ a technique called zoned bit recording (ZBR). tracks are grouped into zones based on their distance from the center of the disk, and each zone is assigned a number of sectors per track.

Disk Storage SystemsCSCE430/830 Modern Disk Scheduling Disk used to be simple devices and disk scheduling used to be performed by OS (file system or device driver) only … … but, new disks are more complex –hide their true layout –transparently move blocks to spare cylinders –have different zones –head accelerates – most algorithms assume linear movement overhead ~ 10x - 20x x 1 N Cylinders Traveled Time

Disk Storage SystemsCSCE430/830 Modern Disk Scheduling Disk used to be simple devices and disk scheduling used to be performed by OS (file system or device driver) only … … but, new disks are more complex –hide their true layout –transparently move blocks to spare cylinders –have different zones –head accelerates – most algorithms assume linear movement overhead –on device buffer caches may use read-ahead prefetching disk buffer disk

Disk Storage SystemsCSCE430/830 Modern Disk Scheduling Disk used to be simple devices and disk scheduling used to be performed by OS (file system or device driver) only … … but, new disks are more complex –hide their true layout –transparently move blocks to spare cylinders –have different zones –head accelerates – most algorithms assume linear movement overhead –on device buffer caches may use read-ahead prefetching are smart with build in low-level scheduler (usually SCAN- derivate) we cannot fully control the device (black box) OS could (should?) focus on high level scheduling only Current research look at on-device programmable processors