Avago Technologies MegaRAID Fast Path Software - Manual (Page 40)

Page 40 LSI Corporation Confidential | July 2011
MegaRAID SAS Software User Guide Chapter 2: Introduction to RAID | RAID Configuration Strategies
RAID 60 can support up to 8 spans and tolerate up to 16 drive failures, though less than
total drive capacity is available. Two drive failures can be tolerated in each RAID 6 level
drive group.
Figure 14 shows a RAID 60 data layout. The second set of parity drives is denoted by Q.
The P drives follow the RAID 5 parity scheme.
Figure 14: RAID 60 Level Virtual Drive
2.6 RAID Configuration
Strategies
The following factors in RAID drive group configuration are most important:
 Virtual drive availability (fault tolerance)
 Virtual drive performance
 Virtual drive capacity
Table 14: RAID 60 Overview
Uses Provides a high level of data protection through the use of a second parity
block in each stripe. Use RAID 60 for data that requires a very high level of
protection from loss.
In the case of a failure of one drive or two drives in a RAID set in a virtual
drive, the RAID controller uses the parity blocks to re-create all of the missing
information. If two drives in a RAID 6 set in a RAID 60 virtual drive fail, two
drive rebuilds are required, one for each drive. These rebuilds can occur at
the same time.
Use for office automation and online customer service that requires fault
tolerance. Use for any application that has high read request rates but low
write request rates.
Strong points Provides data redundancy, high read rates, and good performance in most
environments. Each RAID 6 set can survive the loss of two drives or the loss
of a drive while another drive is being rebuilt. Provides the highest level of
protection against drive failures of all of the RAID levels. Read performance is
similar to that of RAID 50, though random reads in RAID 60 might be slightly
faster because data is spread across at least one more disk in each RAID 6 set.
Weak points Not well suited to tasks requiring lot of writes. A RAID 60 virtual drive has to
generate two sets of parity data for each write operation, which results in a
significant decrease in performance during writes. Drive performance is
reduced during a drive rebuild. Environments with few processes do not
perform as well because the RAID overhead is not offset by the performance
gains in handling simultaneous processes. RAID 6 costs more because of the
extra capacity required by using two parity blocks per stripe.
Drives A minimum of 8.
Segment 1
Segment 8
Segment 2
Segment 7
Segment 10
Segment 5
Parity (P1-P2)
Parity (Q11–Q12)
Note: Parity is distributed across all drives in the drive group.
Parity (Q1-Q2)
Segment 11 Segment 12
Parity (P15-P16) Segment 15 Segment 16 Parity (Q15-Q16)
Segment 3
Segment 6
Segment 4
Parity (P9-P10) Parity (Q9–Q10) Parity (P11-P12) Segment 9
Parity (P13-P14) Segment 14 Segment 13 Parity (Q13-Q14)
RAID
60
RAID 6 RAID 6
RAID 0
Parity (Q3-Q4) Parity (P3-P4)
Parity (Q5-Q6) Parity (P5-P6) Parity (P3-P4) Parity (Q3-Q4)