Scribd
Upload
37 views

Computer Architecture and Organization: Lecture11: RAID

This document discusses RAID (Redundant Array of Inexpensive Disks), which uses multiple disks to provide increased performance, fault tolerance, or both. It outlines several RAID levels including: RAID 0 uses striping to improve performance but has no redundancy. RAID 1 uses mirroring to provide redundancy by writing all data to two disks. RAID 5 distributes parity across disks to avoid bottlenecks and is widely used. RAID 6 provides two sets of parity for greater fault tolerance.

Uploaded by

Matthew R. Pon
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
37 views

Computer Architecture and Organization: Lecture11: RAID

This document discusses RAID (Redundant Array of Inexpensive Disks), which uses multiple disks to provide increased performance, fault tolerance, or both. It outlines several RAID levels including: RAID 0 uses striping to improve performance but has no redundancy. RAID 1 uses mirroring to provide redundancy by writing all data to two disks. RAID 5 distributes parity across disks to avoid bottlenecks and is widely used. RAID 6 provides two sets of parity for greater fault tolerance.

Uploaded by

Matthew R. Pon
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 13

Computer Architecture and Organization

Lecture11: RAID

Majid Khabbazian [email protected]


Electrical and Computer Engineering University of Alberta

April 9, 2013

Outline
RAID

Parallelism and I/O


In parallel revolution, we should not neglect I/O
Example:
Suppose we have a program that executes in 100 sec, of which 90 sec. is CPU time and the rest is I/O. Suppose the number of processors doubles every two years, but the processors remain the same speed. How much faster our program will run at the end of ten years?

Solution
Use an array of small disks instead of a (few) large disk(s)
Advantage?
We can have many more independent accesses Cost, power, floor space
Smaller disks are generally more efficient per gigabyte

Disadvantage?
Could make reliability much worse! Solution use redundancy
4

RAID
Redundant Array of Inexpensive (Independent) Disks
Use multiple smaller disks (as a large disk) Parallelism improves performance Plus extra disk(s) for redundant data storage

Provides fault tolerant storage system


Especially if failed disks can be hot swapped

A number of standard schemes have evolved which are referred to as levels

RAID 0 (No redundancy)


This is Level zero!
Simply spread data over multiple disks (called striping)

No redundancy (AID?)
Just stripe data over multiple disks

But it does improve performance

Data disks

Redundant disks
6

RAID 1 (Mirroring)
RAID 1: Mirroring
N + N disks, replicate data
Write data to both data disk and mirror disk On disk failure, read from mirror

Data disks

Redundant disks
7

RAID 2 (Error Correction)


RAID 2: Error correcting code (ECC)
N + E disks (e.g., 10 + 4) Split data at bit level across N disks Generate E-bit ECC Too complex, not used in practice

Data disks

Redundant disks
8

RAID 3 (Bit-Interleaved Parity)


N + 1 disks
Data striped across N disks at byte level Redundant disk stores parity Read access
Read all disks

Write access
Generate new parity and update all disks

On failure
Use parity to reconstruct missing data

Not widely used


Data disks

Redundant disks
9

RAID 4 (Block-Interleaved Parity)


N + 1 disks
Data striped across N disks at block level Redundant disk stores parity for a group of blocks Read access
Read only the disk holding the required block

Write access
Just read disk containing modified block, and parity disk Calculate new parity, update data disk and parity disk

On failure
Use parity to reconstruct missing data

Not widely used


10

RAID 5 (Distributed Parity)


N + 1 disks
Like RAID 4, but parity blocks distributed across disks
Avoids parity disk being a bottleneck

Widely used

11

Example (RAID 5)
Writing to block 8 and 5 can be done simultaneously!

12

RAID 6 (P + Q Redundancy)
N + 2 disks
Like RAID 5, but two lots of parity Greater fault tolerance through more redundancy

Data disks

Redundant disks
13

You might also like