WUSTL CSE 362M - Chapter 9: Peripheral Devices: Magnetic Disks

Unformatted text preview:

Chapter 9: Peripheral Devices: Magnetic DisksMagnetic Disk DrivesMulti-Platter Hard Disk DriveMultiple PlattersSimplified View of Disk Track and Sector OrganizationSimplified View of Individual Bits Encoded on a Disk TrackDisk Layout Methods DiagramTypical Hard Disk Sector OrganizationWinchester Disk Format: Seagate ST506Disk FormattingStatic Disk CharacteristicsDynamic Disk CharacteristicsRAIDData Mapping For RAID 0RAID - 1RAID 0, 1, 2RAID – 2RAID - 3RAID: 4RAID 3 & 4RAID: 5 & 6RAID 5 & 6Comp Sys Design & Arch 2nd Ed © 2004 Prentice HallChapter 9: Peripheral Devices: Magnetic Disks Basic Disk Operation Performance Parameters and History of Improvement Example disks RAID (Redundant Arrays of Inexpensive Disks) Improving Reliability Improving PerformanceComp Sys Design & Arch 2nd Ed © 2004 Prentice HallMagnetic Disk Drives High density and non-volatile Densities similar to semiconductor RAM on an inexpensive medium No power required to retain stored information Motion of medium supplies power for sensing More random access than tape: direct access Different platters selected electronically Track on platter selected by head movement Cyclic sequential access to data on a track Structured address of data on disk Drive: Platter: Track (cylinder): Sector: ByteComp Sys Design & Arch 2nd Ed © 2004 Prentice HallMulti-Platter Hard Disk DriveComp Sys Design & Arch 2nd Ed © 2004 Prentice HallMultiple PlattersComp Sys Design & Arch 2nd Ed © 2004 Prentice HallSimplified View of Disk Track and Sector Organization An integral number of sectors are recorded around a track A sector is the unit of data transfer to or from the diskComp Sys Design & Arch 2nd Ed © 2004 Prentice HallSimplified View of Individual Bits Encoded on a Disk Track Inside tracks are shorter & thus have higher densities or fewer words All sectors contain the same number of bytes Inner portions of a platter may have fewer sectors per track; multiple zone recording. Small areas of the disk are magnetized in different directions• Change in magnetization direction is what is detected on readComp Sys Design & Arch 2nd Ed © 2004 Prentice HallDisk Layout Methods DiagramSame number of bits in each zone, but more zones as you go to outer cylinders.Stallings – Computer Organization & ArchitectureComp Sys Design & Arch 2nd Ed © 2004 Prentice HallTypical Hard Disk Sector Organization Serial bit stream has header, data, & error code Header synchronizes sector read and records sector address Data length is usually power of 2 bytes Error detection/correction code needed at endComp Sys Design & Arch 2nd Ed © 2004 Prentice HallWinchester Disk Format: Seagate ST506Stallings – Computer Organization & ArchitectureComp Sys Design & Arch 2nd Ed © 2004 Prentice HallDisk Formatting Disks are pre-formatted with track and sector address written in headers Disk surface defects may cause some sectors to be marked unusable for the softwareComp Sys Design & Arch 2nd Ed © 2004 Prentice HallStatic Disk Characteristics Areal density of bits on surfacedensity = 1/(bit spacing × track spacing) Maximum density: density on innermost track Unformatted capacity: includes header and error control bits Formatted capacity:sector track surface# of surfacescapacity =bytes sectors tracks×××Comp Sys Design & Arch 2nd Ed © 2004 Prentice HallDynamic Disk Characteristics Seek time: time to move heads to cylinder Track-to-track access: time to adjacent track Rotational latency: time for correct sector to come under read/write head Average access time = seek time + rotational latency Burst rate (maximum transfer bandwidth) burst rate =revssecsectorsrevbytessector××Comp Sys Design & Arch 2nd Ed © 2004 Prentice HallRAID Raid LEVEL 0: Speed improvement only, NO reliability improvement Data is "striped" across several disks so they can be accessed in parallel independent of each other.  “Strips” may be physical blocks, sectors, or other units.  If there is a reasonable probability that multiple disk requeststarget different disks, they can be accessed in parallel (i.e., overlap seek and rotational delay) thus lowering average access time. Very good when accessing sequential/contiguous data.Redundant Array of Inexpensive/Independent DisksReliability and Redundancy for Improved PerformanceComp Sys Design & Arch 2nd Ed © 2004 Prentice HallData Mapping For RAID 0Stallings – Computer Organization & ArchitectureComp Sys Design & Arch 2nd Ed © 2004 Prentice HallRAID - 1 RAID Level 1: "Mirroring," writing the exact same data to two different disk drives. Reliability: If one drive fails, the other can be used. Performance:  Can seek on both drives at the same time, accept the data from the first one to obtain the data and abort the other request. Negatives:  Must write data to two disks, slowest one can determine performance. Costly; need twice as many disks for the same amount of data.Comp Sys Design & Arch 2nd Ed © 2004 Prentice HallRAID 0, 1, 2Stallings – Computer Organization & ArchitectureComp Sys Design & Arch 2nd Ed © 2004 Prentice HallRAID – 2RAID 2 & 3 General: All disks in the array are used for every I/O request. Disks are synchronized so each disk head is over the same disk position at every point in time.RAID Level 2: Data is striped at the bit or word level across several disks. Reliability: Additional ECC (Error Correcting Codes) bits to recover data if one drive fails (e.g., Hamming SECDEC) are calculated. The ECC bits are placed on additional drives. The number is proportional to the log of the number of data disks. Performance:  Data bandwidth improves and correponds to the number of data disks.Comp Sys Design & Arch 2nd Ed © 2004 Prentice HallRAID - 3RAID Level 3: Striped as in level 2 at the byte level. Reliability: A simple parity bit is computed for each bit position.  A single disk (improvement over RAID-2) holds the parity bits in the calculated position. If a parity error is detected: The disk holding the error can be replaced & data rewritten. The error can be corrected on the fly by performing the proper calculation. Performance: Overall bandwidth is increased through parallel access of block of data.Comp Sys Design & Arch 2nd Ed © 2004 Prentice HallRAID: 4RAID Level 4: Similar to level 3- Reliability:


View Full Document

WUSTL CSE 362M - Chapter 9: Peripheral Devices: Magnetic Disks

Download Chapter 9: Peripheral Devices: Magnetic Disks
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Chapter 9: Peripheral Devices: Magnetic Disks and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Chapter 9: Peripheral Devices: Magnetic Disks 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?