Data Protection: RAID

Chapter 3

© 2009 EMC Corporation. All rights reserved.

Chapter Objectives
After completing this chapter, you will be able to:
 Describe what is RAID and the needs it addresses
 Describe the concepts upon which RAID is built
 Define and compare RAID levels
 Recommend the use of the common RAID levels based
on performance and availability considerations
 Explain factors impacting disk drive performance

© 2009 EMC Corporation. All rights reserved. Data Protection: RAID - 2

Why RAID
 Performance limitation of a single drive disk drive
– Limited Capacity
– Limited access speed
 An individual drive has a certain life expectancy
– Measured in MTBF
– Example - If the MTBF of a drive is 750,000 hours, and there are
100 drives in the array, then the MTBF of the array becomes
750,000 / 100, or 7,500 hours
 RAID was introduced to mitigate this problem
 RAID provides:
– Increase capacity
– Higher availability
– Increased performance
© 2009 EMC Corporation. All rights reserved. Data Protection: RAID - 3
RAID - Redundant Array of Independent Disks

RAID
Controller

Host

RAID Array

© 2009 EMC Corporation. All rights reserved. RAID Arrays - 4

RAID Array Components

Physical
Array

Logical
Array

RAID
Controller
Hard Disks

Host

RAID Array

© 2009 EMC Corporation. All rights reserved. Data Protection: RAID - 5

RAID Implementations
 Hardware (usually a specialized disk controller card)
– Controls all drives attached to it
– Array(s) appear to host operating system as a regular disk drive
– Provided with administrative software

 Software
– Runs as part of the operating system
– Performance is dependent on CPU workload
– Does not support all RAID levels

© 2009 EMC Corporation. All rights reserved. Data Protection: RAID - 6

RAID Levels
 0 Striped array with no fault tolerance
 1 Disk mirroring
 3 Parallel access array with dedicated parity disk
 4 Striped array with independent disks and a dedicated
parity disk
 5 Striped array with independent disks and distributed
parity
 6 Striped array with independent disks and dual
distributed parity
 Nested RAID (i.e., 1 + 0, 0 + 1, etc.)
© 2009 EMC Corporation. All rights reserved. Data Protection: RAID - 7
RAID Redundancy: Parity

0
4
8

1
5
9

RAID 2
Controller 6
10

3
7
Host
11

0123
4567
8 9 10 11

Parity Disk
© 2008 EMC Corporation. All rights reserved. RAID Arrays - 8
Parity Calculation

5 Data
5 + 3 + 4 + 2 = 14

3 Data

The middle drive fails: 4 Data

5 + 3 + ? + 2 = 14
2 Data
? = 14 – 5 – 3 – 2
?=4 Parity
14

RAID Array
© 2008 EMC Corporation. All rights reserved. RAID Arrays - 9
Data Organization: Striping
Stripes

Stripe 1

Strip 1 Strip 2 Strip 3

Strips

Stripe

Strip 1 Strip 2 Strip 3

Stripe 1
Stripe 2

Strips
© 2009 EMC Corporation. All rights reserved. Data Protection: RAID - 10
RAID 0 – Striped Array with no Fault Tolerance

1
5
9

RAID 2
Controller 6
10

3
Host 7
11

© 2009 EMC Corporation. All rights reserved. Data Protection: RAID - 11

 RAID 1 – Disk Mirroring

RAID
Block 0
1 Block 0
1
Controller

Host

© 2009 EMC Corporation. All rights reserved. Data Protection: RAID - 12

Nested RAID – 0+1 (Striping and Mirroring)

RAID 1

Block 0

Block 2

RAID RAID 0
Block 0
3
2
1
Controller

Block 1

Host Block 3

© 2009 EMC Corporation. All rights reserved. Data Protection: RAID - 13

Nested RAID – 0+1 (Striping and Mirroring)

RAID 1

Block 0 Block 0

Block 2 Block 2

RAID RAID 0
Controller

Block 1 Block 1

Host Block 3 Block 3

© 2009 EMC Corporation. All rights reserved. Data Protection: RAID - 14

Nested RAID – 1+0 (Mirroring and Striping)

RAID 0

Block 1

Block 3

RAID RAID 1
Block 2
0
Controller

Block 1

Host Block 3

© 2009 EMC Corporation. All rights reserved. Data Protection: RAID - 15

Nested RAID – 1+0 (Mirroring and Striping)

RAID 0

Block 0 Block 1

Block 2 Block 3

RAID RAID 1
Controller

Block 0 Block 1

Host Block 2 Block 3

© 2009 EMC Corporation. All rights reserved. Data Protection: RAID - 16

RAID 0+1 vs. RAID 1+0
 Benefits are identical under normal operations
 Rebuild operations are very different
– RAID 1+0 uses a mirrored pair – only 1 disk is rebuilt if a disk fails
– RAID 0+1 if a single drive fails, the entire stripe is faulted
 RAID is 0+1 is a poorer solution and is less common

© 2009 EMC Corporation. All rights reserved. RAID Arrays - 17

RAID Redundancy: Parity

0
4
8

1
5
9

RAID 2
Controller 6
10

3
7
Host
11

0123
4567
8 9 10 11

Parity Disk RAID Arrays - 18

© 2009 EMC Corporation. All rights reserved.
RAID Redundancy: Parity

0 4

1
6 5
9

RAID 1
?
Controller

3
Host 7 7
11
The middle drive fails:
Parity calculation 4 + 6 + 1 + 7 = 18 0123
4 + 6 + ? + 7 = 18 4 518
67

? = 18 – 4 – 6 – 7
?=1 Parity Disk
© 2009 EMC Corporation. All rights reserved. Data Protection: RAID - 19
RAID 3 – Parallel Transfer with Dedicated Parity
Disk

Block 0
3
2
1 RAID0
Block
Controller
Block
Parity1
Generated
Block 2
Host
Block 3
P0123

© 2009 EMC Corporation. All rights reserved. Data Protection: RAID - 20

RAID 4 – Striping with Dedicated Parity Disk

Block 0
Block 4

Block 1
Block 5

Parity
RAID0 Block 2
Block 0 Block
Generated
Controller Block 6
P0123
Block 3
Host Block 7

P0123
P4567

© 2008 EMC Corporation. All rights reserved. RAID Arrays - 21

RAID 5 – Independent Disks with Distributed Parity

Block 0
Block 4

Block 1
Block 5

Parity
RAID4 Block 2
Block 0
4 Block 0
Generated
Controller Block 6
P405
1627 3
Block 3
Host
P4567

P0123
Block 7

© 2009 EMC Corporation. All rights reserved. Data Protection: RAID - 22

RAID 6 – Dual Parity RAID
 Two disk failures in a RAID set leads to data
unavailability and data loss in single-parity schemes,
such as RAID-3, 4, and 5
 Increasing number of drives in an array and increasing
drive capacity leads to a higher probability of two disks
failing in a RAID set
 RAID-6 protects against two disk failures by maintaining
two parities
– Horizontal parity which is the same as RAID-5 parity
– Diagonal parity is calculated by taking diagonal sets of data blocks
from the RAID set members
 Even-Odd, and Reed-Solomon are two commonly used
algorithms for calculating parity in RAID-6
© 2009 EMC Corporation. All rights reserved. Data Protection: RAID - 23
RAID Implementations
 Hardware (usually a specialized disk controller card)
– Controls all drives attached to it
– Performs all RAID-related functions, including volume management
– Array(s) appear to the host operating system as a regular disk drive
– Dedicated cache to improve performance
– Generally provides some type of administrative software

 Software
– Generally runs as part of the operating system
– Volume management performed by the server
– Provides more flexibility for hardware, which can reduce the cost
– Performance is dependent on CPU load
– Has limited functionality

© 2009 EMC Corporation. All rights reserved. RAID Arrays - 24

RAID Comparison
Min Storage
RAID Cost Read Performance Write Performance
Disks Efficiency %

Very good for both

random and sequential Very good
0 2 100 Low
read

Good
Slower than a single
Good disk, as every write must
1 2 50 High Better than a single disk be committed to two
disks

(n-1)*100/n Poor to fair for small

Good for random reads
where n= random writes
and very good for
3 3 number of Moderate Good for large,
sequential reads
disks sequential writes

Fair for random write

(n-1)*100/n Very good for random
Slower due to parity
where n= reads
overhead
5 3 number of Moderate Good for sequential
Fair to good for
disks reads
sequential writes

(n-2)*100/n Very good for random

Moderate Good for small, random
where n= reads
6 4 but more writes
number of Good for sequential
than RAID 5 (has write penalty)
disks reads

1+0
and 4 50 High Very good Good
0+1

© 2009 EMC Corporation. All rights reserved. Data Protection: RAID - 25

RAID Impacts on Performance
RAID Controller

Ep new = Ep old - E4 old + E4 new

2 XOR
Ep new Ep old E4 old E4 new

P0 D1 D2 D3 D4

 Small (less than element size) write on RAID 3 & 5

 Ep = E1 + E2 + E3 + E4 (XOR operations)
 If parity is valid, then: Ep new = Ep old – E4 old + E4 new (XOR operations)
– 2 disk reads and 2 disk writes

 Parity Vs Mirroring
– Reading, calculating and writing parity segment introduces penalty to every write operation
– Parity RAID penalty manifests due to slower cache flushes
– Increased load in writes can cause contention and can cause slower read response times

© 2009 EMC Corporation. All rights reserved. Data Protection: RAID - 26

Hot Spares

RAID
Controller

© 2009 EMC Corporation. All rights reserved. Data Protection: RAID - 28

Check Your Knowledge
 What is a RAID array?
 What benefits do RAID arrays provide?
 What methods can be used to provide higher data
availability in a RAID array?
 What is the primary difference between RAID 3 and
RAID 5?
 What is advantage of using RAID 6?
 What is a hot spare?

© 2009 EMC Corporation. All rights reserved. Data Protection: RAID - 32