DOC PREVIEW
UMD CMSC 411 - Lecture 18 Storage Systems

This preview shows page 1-2-3 out of 8 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 8 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 8 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 8 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 8 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

CMSC 411CMSC 411Computer Systems ArchitectureLecture 18Storage Systems, cont.Storage Systems, cont.Alan Sussmanl@ d [email protected]• Homework #4 due today•Homework #5posted today•Homework #5 posted today• Exam #2 on Thursday, April 23• Cache simulator project questions?CMSC 411 - 18 (some from Patterson, Sussman, others)2How is the I/O bus connected?• Do we connect it to – the memory bus?– or to the cache?• Typical solution from Fig. 7.15 H&P 3ed.gCMSC 411 - 18 (some from Patterson, Sussman, others)3How does CPU get data from I/O bus?g• Two solutions:– Some (mostly older) machines have op-codes that read or it t I/O d iwrite to I/O devices– In memory mapped I/O, certain physical addresses are reserved for I/O devices like disks, so those reads and writes are put on the I/O busp• Usually I/O is interrupt driven, meaning that after the CPU requests a READ or WRITE, it goes on with other work until the I/O unit signals that it iswith other work until the I/O unit signals that it is finishedCMSC 411 - 18 (some from Patterson, Sussman, others)4DMA to make this work• To allow the CPU to proceed, need another controller to shepherd the READ or WRITE. Direct (DMA) h d i d tmemory access(DMA) hardware is used to:– record the address and the number of bytes to be transferred– act as bus master, initiating each data transfer– interrupt the CPU when the transfer is complete• In some cases, these controllers are really separate I/O processorssepa ate /O p ocesso sCMSC 411 - 18 (some from Patterson, Sussman, others)5Reliability, Availability, and RAIDReliability, Availability, and RAIDFailure rate vs. Availability• Failure rate: concerns whether any of the hardware is brokenA il bilihh h i•Availability: concerns whether the system is usable, even if some pieces are broken•Example 1: Your bank can improve theExample 1: Your bank can improve the availability of the ATM system by installing two ATM machines so that one is available even if one breaksbreaks• Example 2: Your bank can reduce the failure rate of the ATM system by installing a machine that does not break as oftendoes not break as often– Also increases the availability• Generally, hope that more complicated hardware CMSC 411 - 18 (some from Patterson, Sussman, others)7improves availability and performance, but it also may increase the failure rateExample: Disk arrays• Suppose a machine has an array of 20 disks– Case 1: If distribute the data across the disks (striping), then ll 20 di k t b ki l i d t thall 20 disks must be working properly in order to access the data - but throughput can be improved– Case 2: If store 20 copies of the data, one copy per disk, have good availability: can access the data even if some disks failgy• But reliability of the 20 disks is less than reliability of a single disk: the probability of one of the 20 disks failing is essentially 20 times theof the 20 disks failing is essentially 20 times the probability that a single disk will failCMSC 411 - 18 (some from Patterson, Sussman, others)8Disk arrays (cont.)y( )• In Case 2, store multiple copies on multiple disks, calledRAID: redundant arrays of inexpensivecalled RAID: redundant arrays of inexpensive disks• RAID is actually not inexpensive (because of the cost of the controllers power supplies and fans)cost of the controllers, power supplies, and fans), so often the “I” is said to stand for “independent” – More than 80% of non-PC disk drive sales are now RAID, a multi-billion dollarindustrymulti-billion dollar industry– Typically store 2 copies, not 20– Used when availability is critical, in applications such as:»airline reservations»airline reservations» medical records» stock marketCMSC 411 - 18 (some from Patterson, Sussman, others)9RAID – from Fig. 6.4• There are various levels of RAID, depending on the relative importance of availability, accuracy, and costRAID level # faults survivedExample data disksCheck disksCompanies0 - Striped 0 8 0 widely used1 - Mirrored 1 8 8 EMC, HP (Tandem), IBM2 - Memory-style ECC 1 8 43 - Bit-interleaved parity 1 8 1 Storage Concepts4 - Block-interleaved parity 1 8 1 Network Appliance5 – Block interleaved w/distributed parity1 8 1 widely used6 – P+Q redundancy 2 8 2 Network ApplianceCMSC 411 - 18 (some from Patterson, Sussman, others)10RAID levels 0 & 1• One copy of data: RAID 0Dtti ddi k–Data stripedacross a disk array• Two full copies of data (mirroring): RAID 1– If one disk fails, go to other– Can also use this to distribute the load of READs– Most expensive RAID option•RAID 0 and 1 can be combinedRAID 0 and 1 can be combined– 1+0 (or 10) – mirror pairs of disks, then stripe across pairs– 0+1 (or 01) – stripe across one set of half the disks, then mirror writes to both setsCMSC 411 - 18 (some from Patterson, Sussman, others)11RAID 3• Bit-interleaved parity: RAID 3– One copy of the data, stored among several disks, and one extra disk to hold a parity bit (checksum) for the others• Example: Suppose have 4 data disks, and one piece of the data looks like this:Disk 1: 0 1 0 1 1 0 0 0Disk 2: 0 1 1 1 0 1 1 0Disk3: 01111000Disk 3: 0 1 1 1 1 0 0 0Disk 4: 0 0 0 1 0 1 0 1– Then the parity bits are set by taking the sums mod 2:Disk5: 01000011Disk 5: 0 1 0 0 0 0 1 1CMSC 411 - 18 (some from Patterson, Sussman, others)12RAID 3 (cont.)• So if the data on one of the disks becomes corrupted, the parity bits on Disk 5 will be wrong, tllth h b filso can tell there has been a failure– and be able to fix it if know which disk failed• Disadvantage: Each data access must read from gall 5 disks in order to retrieve the data and check for corruption–also can’t always tell where the error is (could even be on thealso can t always tell where the error is (could even be on the parity disk)CMSC 411 - 18 (some from Patterson, Sussman, others)13RAID 4• Block-interleaved parity: RAID 4– Same organization of data as RAID 3 but cheaper reads and itwrites– Read: Read one sector at a time, and count on the disk’s own error detection mechanisms for each sector.–Write: In each write note which bits are changing-this is–Write: In each write, note which bits are changing -this is enough information to change the parity bits without reading from the other disksCMSC 411 - 18 (some from Patterson, Sussman, others)14RAID 4 example• If the original contents areDisk1: 01011000Disk 1: 0 1 0 1 1 0 0


View Full Document

UMD CMSC 411 - Lecture 18 Storage Systems

Documents in this Course
Load more
Download Lecture 18 Storage Systems
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 Lecture 18 Storage Systems 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 18 Storage Systems 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?