inst eecs berkeley edu cs61c su05 CS61C Machine Structures Lecture 27 RAID Performance 2005 08 08 CS 61C L27 RAID and Performance 1 Andy Carle A Carle Summer 2005 UCB Outlin e RAID Performance CS 61C L27 RAID and Performance 2 A Carle Summer 2005 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 CS 61C L27 RAID and Performance 3 A Carle Summer 2005 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 CS 61C L27 RAID and Performance 4 A Carle Summer 2005 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 JBOD too unreliable to be useful CS 61C L27 RAID and Performance 5 A Carle Summer 2005 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 CS 61C L27 RAID and Performance 6 A Carle Summer 2005 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 CS 61C L27 RAID and Performance 7 A Carle Summer 2005 UCB RAID 0 Striping Assume have 4 disks of data for this example organized in blocks Large accesses faster since transfer from several disks at once This and next 5 slides from RAID edu http www acnc com 04 01 00 html CS 61C L27 RAID and Performance 8 A Carle Summer 2005 UCB RAID 1 Mirror Each disk is fully duplicated onto its mirror Very high availability can be achieved Bandwidth reduced on write 1 Logical write 2 physical writes Most expensive solution 100 capacity overhead CS 61C L27 RAID and Performance 9 A Carle Summer 2005 UCB RAID 3 Parity Parity computed across group to protect against hard disk failures stored in P disk Logically a single high capacity high transfer rate disk 25 capacity cost for parity in this example vs 100 for RAID 1 5 disks vs 8 disks CS 61C L27 RAID and Performance 10 A Carle Summer 2005 UCB RAID 4 parity plus small sized accesses RAID 3 relies on parity disk to discover errors on Read But every sector has an error detection field Rely on error detection field to catch errors on read not on the parity disk Allows small independent reads to different disks simultaneously CS 61C L27 RAID and Performance 11 A Carle Summer 2005 UCB Inspiration for RAID 5 Small writes write to one disk Option 1 read other data disks create new sum and write to Parity Disk access all disks Option 2 since P has old sum compare old data to new data add the difference to P 1 logical write 2 physical reads 2 physical writes to 2 disks Parity Disk is bottleneck for Small writes Write to A0 B1 both write to P disk A0 B0 C0 D0 P A1 B1 C1 D1 P CS 61C L27 RAID and Performance 12 A Carle Summer 2005 UCB RAID 5 Rotated Parity faster small writes Independent writes possible because of interleaved parity Example write to A0 B1 uses disks 0 1 4 5 so can proceed in parallel Still 1 small write 4 physical disk accesses CS 61C L27 RAID and Performance 13 A Carle Summer 2005 UCB Outlin e RAID Performance CS 61C L27 RAID and Performance 14 A Carle Summer 2005 UCB Performance Purchasing Perspective given a collection of machines or upgrade options which has the best performance least cost best performance cost Computer Designer Perspective faced with design options which has the best performance improvement least cost best performance cost All require basis for comparison and metric for evaluation Solid metrics lead to solid progress CS 61C L27 RAID and Performance 15 A Carle Summer 2005 UCB Two Notions of Performance Plane Boeing 747 DC to Top Passen Throughput Paris Speed gers pmph 6 5 610 470 286 700 hours mph BAD Sud 3 1350 132 Concorde hours mph Which has higher performance 178 200 Time to deliver 1 passenger Time to deliver 400 passengers In a computer time for 1 job called Response Time or Execution Time In a computer jobs per day called Throughput or Bandwidth CS 61C L27 RAID and Performance 16 A Carle Summer 2005 UCB Definition s Performance is in units of things per sec bigger is better If we are primarily concerned with response time performance x 1 execution time x F ast is n times faster than S low means performance F n execution time S performance S CS 61C L27 RAID and Performance 17 execution time F A Carle Summer 2005 UCB Example of Response Time v Throughput Time of Concorde vs Boeing 747 Concord is 6 5 hours 3 hours 2 2 times faster Throughput of Boeing vs Concorde Boeing 747 286 700 pmph 178 200 pmph 1 6 times faster Boeing is 1 6 times 60 faster in terms of throughput Concord is 2 2 times 120 faster in terms of flying time response time We will focus primarily on execution time for a single job CS 61C L27 RAID and Performance 18 A Carle Summer 2005 UCB Administrivia Final Exam Friday August 12 11 00 2 00 306 Soda Same as Midterm 2 Same rules as Midterms except you can now have a two sided cheat sheet Project 4 Due Friday HW8 Due Friday but It is optional The grade will be dropped if it hurts your overall semester grade You may want to review it before the final CS 61C L27 RAID and Performance 19 A Carle Summer 2005 UCB Upcoming Schedule Tuesday Parallel Computing HKN Evaluations please BE HERE Course Survey in lab Wednesday Intro to Intel Architecture Mini Review session in the remaining time Thursday Official Review Session Friday Final CS 61C L27 RAID and Performance 20 A Carle Summer 2005 UCB …
View Full Document
Unlocking...