Unformatted text preview:

inst eecs berkeley edu cs61c CS61C Machine Structures Lecture 39 I O Disks 2005 4 29 TA Casey Ho Microsoft rolled out a 64 bit version of its Windows operating systems on Monday As compared with existing 32 bit versions 64 bit Windows will handle 16 terabytes of virtual memory as compared to 4 GB for 32 bit Windows System cache size jumps from 1 GB to 1 TB and paging file size increases from 16 TB to 512 TB CS61C L40 I O Disks 1 Ho Fall 2004 UCB Protocol Family Concept Message Logical Message Actual Logical H Message T Actual H H Message T T Actual H Message T Actual H H Message T T Physical CS61C L40 I O Disks 2 Ho Fall 2004 UCB Protocol Family Concept Key to protocol families is that communication occurs logically at the same level of the protocol called peer to peer but is implemented via services at the next lower level Encapsulation carry higher level information within lower level envelope Fragmentation break packet into multiple smaller packets and reassemble CS61C L40 I O Disks 3 Ho Fall 2004 UCB Protocol for Network of Networks Transmission Control Protocol Internet Protocol TCP IP This protocol family is the basis of the Internet a WAN protocol IP makes best effort to deliver TCP guarantees delivery TCP IP so popular it is used even when communicating locally even across homogeneous LAN CS61C L40 I O Disks 4 Ho Fall 2004 UCB TCP IP packet Ethernet packet protocols Application sends message TCP breaks into 64KiB segments adds 20B header IP adds 20B header sends to network If Ethernet broken into 1500B packets with headers trailers 24B All Headers trailers have length field destination CS61C L40 I O Disks 5 Ethernet Hdr IP Header TCP Header EHIP Data TCP data Message Ethernet Hdr Ho Fall 2004 UCB Overhead vs Bandwidth Networks are typically advertised using peak bandwidth of network link e g 100 Mbits sec Ethernet 100 base T Software overhead to put message into network or get message out of network often limits useful bandwidth Assume overhead to send and receive 320 microseconds s want to send 1000 Bytes over 100 Mbit s Ethernet Network transmission time 1000Bx8b B 100Mb s 8000b 100b s 80 s Effective bandwidth 8000b 320 80 s 20 Mb s CS61C L40 I O Disks 6 Ho Fall 2004 UCB Magnetic Disks Computer Processor Memory Devices active passive Input Control where brain programs Output Datapath data live brawn when running Keyboard Mouse Disk Network Display Printer Purpose Long term nonvolatile inexpensive storage for files Large inexpensive slow level in the memory hierarchy discuss later CS61C L40 I O Disks 8 Ho Fall 2004 UCB Disk Device Terminology Arm Head Sector Actuator Inner Track Outer Track Platter Several platters with information recorded magnetically on both surfaces usually Bits recorded in tracks which in turn divided into sectors e g 512 Bytes Actuator moves head end of arm over track seek wait for sector rotate under head then read or write CS61C L40 I O Disks 10 Ho Fall 2004 UCB Disk Device Performance Outer Track Platter Inner Sector Head Arm Controller Spindle Track Actuator Disk Latency Seek Time Rotation Time Transfer Time Controller Overhead Seek Time depends no tracks move arm seek speed of disk Rotation Time depends on speed disk rotates how far sector is from head Transfer Time depends on data rate bandwidth of disk bit density size of request CS61C L40 I O Disks 11 Ho Fall 2004 UCB Data Rate Inner vs Outer Tracks To keep things simple originally same of sectors track Since outer track longer lower bits per inch Competition decided to keep bits inch BPI high for all tracks constant bit density More capacity per disk More sectors per track towards edge Since disk spins at constant speed outer tracks have faster data rate Bandwidth outer track 1 7X inner track CS61C L40 I O Disks 12 Ho Fall 2004 UCB Disk Performance Model Trends Capacity 100 year 2X 1 0 yrs Over time grown so fast that of platters has reduced some even use only 1 now Transfer rate BW 40 yr 2X 2 yrs Rotation Seek time 8 yr 1 2 in 10 yrs Areal Density Bits recorded along a track Bits Inch BPI of tracks per surface Tracks Inch TPI We care about bit density per unit area Bits Inch2 Called Areal Density BPI x TPI MB 100 year 2X 1 0 yrs Fewer chips areal density CS61C L40 I O Disks 13 Ho Fall 2004 UCB Historical Perspective Form factor and capacity drives market more than performance 1970s Mainframes 14 diam disks 1980s Minicomputers Servers 8 5 25 diam disks Late 1980s Early 1990s Pizzabox PCs 3 5 inch diameter disks Laptops notebooks 2 5 inch disks Palmtops didn t use disks so 1 8 inch diameter disks didn t make it CS61C L40 I O Disks 16 Ho Fall 2004 UCB Use Arrays of Small Disks Katz and Patterson asked in 1987 Can smaller disks be used to close gap in performance between disks and CPUs Conventional 4 3 5 5 25 disk designs Low End 10 14 High End Disk Array 1 disk design 3 5 CS61C L40 I O Disks 19 Ho Fall 2004 UCB Replace Small Number of Large Disks with Large Number of Small Disks 1988 Disks IBM 3390K IBM 3 5 0061 x70 Capacity 20 GBytes 320 MBytes 23 GBytes 9X 97 cu ft 11 cu ft Volume 0 1 cu ft 3X 3 KW 1 KW Power 11 W 8X 15 MB s 120 MB s Data Rate 1 5 MB s 6X 600 I Os s 3900 IOs s I O Rate 55 I Os s 250 KHrs Hrs MTTF 50 KHrs 250K 150K Cost 2K Disk Arrays potentially high performance high MB per cu ft high MB per KW but what about reliability CS61C L40 I O Disks 20 Ho Fall 2004 UCB Array Reliability Reliability whether or not a component has failed measured as Mean Time To Failure MTTF Reliability of N disks Reliability of 1 Disk N assuming failures independent 50 000 Hours 70 disks 700 hour Disk system MTTF Drops from 6 years to 1 month Disk arrays too unreliable to be useful CS61C L40 I O Disks 21 Ho Fall 2004 UCB Redundant Arrays of Inexpensive Disks Files are striped across multiple disks Redundancy yields high data availability Availability service still provided to user even if some components failed Disks will still fail Contents reconstructed from data redundantly stored in the array Capacity penalty to store redundant info Bandwidth penalty to update redundant info CS61C L40 I O Disks 22 Ho Fall 2004 UCB Berkeley History RAID I RAID I 1989 Consisted of a Sun 4 280 workstation with 128 MB of DRAM four dual string SCSI controllers 28 5 25inch SCSI disks and specialized disk striping software Today RAID is 27 billion dollar industry 80 nonPC disks sold in RAIDs CS61C L40 I O Disks 23 Ho Fall 2004 UCB RAID 0 No redundancy AID Assume have 4 disks of data for this example organized in


View Full Document

Berkeley COMPSCI 61C - Lecture Notes

Documents in this Course
SIMD II

SIMD II

8 pages

Midterm

Midterm

7 pages

Lecture 7

Lecture 7

31 pages

Caches

Caches

7 pages

Lecture 9

Lecture 9

24 pages

Lecture 1

Lecture 1

28 pages

Lecture 2

Lecture 2

25 pages

VM II

VM II

4 pages

Midterm

Midterm

10 pages

Load more
Loading Unlocking...
Login

Join to view Lecture Notes 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 Lecture Notes 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?