Maximizing Fault Tolerance; Maximizing Performance - Lenovo ThinkServer RD650 User Manual

12Gb/s MegaRAID SAS Software User Guide
March 2014
2.3.1

Maximizing Fault Tolerance

Fault tolerance is achieved through the ability to perform automatic and transparent rebuilds using hot spare drives
and hot swaps. A hot spare drive is an unused online available drive that the RAID controller instantly plugs into the
system when an active drive fails. After the hot spare is automatically moved into the RAID drive group, the failed drive
is automatically rebuilt on the spare drive. The RAID drive group continues to handle requests while the rebuild
occurs.
A hot swap is the manual substitution of a replacement unit in a disk subsystem for a defective one, where the
substitution can be performed while the subsystem is running hot swap drives. Auto-Rebuild in the WebBIOS
Configuration Utility allows a failed drive to be replaced and automatically rebuilt by "hot-swapping" the drive in the
same drive bay. The RAID drive group continues to handle requests while the rebuild occurs, providing a high degree
of fault tolerance and zero downtime.
Table 15 RAID Levels and Fault Tolerance
RAID
Level
0 Does not provide fault tolerance. All data is lost if any drive fails. Disk striping writes data across multiple drives instead of just one drive.
It involves partitioning each drive storage space into stripes that can vary in size. RAID 0 is ideal for applications that require high
performance but do not require fault tolerance.
1 Provides complete data redundancy. If one drive fails, the contents of the other drive in the drive group can be used to run the system
and reconstruct the failed drive.
The primary advantage of disk mirroring is that it provides 100 percent data redundancy. Because the contents of the drive are
completely written to a second drive, no data is lost if one of the drives fails. Both drives contain the same data at all times. RAID 1 is
ideal for any application that requires fault tolerance and minimal capacity.
5 Combines distributed parity with disk striping. Parity provides redundancy for one drive failure without duplicating the contents of
entire drives. If a drive fails, the RAID controller uses the parity data to reconstruct all missing information. In RAID 5, this method is
applied to entire drives or stripes across all drives in a drive group. Using distributed parity, RAID 5 offers fault tolerance with limited
overhead.
6 Combines distributed parity with disk striping. RAID 6 can sustain two drive failures and still maintain data integrity. Parity provides
redundancy for two drive failures without duplicating the contents of entire drives. If a drive fails, the RAID controller uses the parity
data to reconstruct all missing information. In RAID 6, this method is applied to entire drives or stripes across all of the drives in a drive
group. Using distributed parity, RAID 6 offers fault tolerance with limited overhead.
00 Does not provide fault tolerance. All data in a virtual drive is lost if any drive in that virtual drive fails. Disk striping writes data across
multiple drives instead of just one drive. It involves partitioning each drive storage space into stripes that can vary in size. RAID 00 is
ideal for applications that require high bandwidth but do not require fault tolerance.
10 Provides complete data redundancy using striping across spanned RAID 1 drive groups. RAID 10 works well for any environment that
requires the 100 percent redundancy offered by mirrored drive groups. RAID 10 can sustain a drive failure in each mirrored drive group
and maintain data integrity.
50 Provides data redundancy using distributed parity across spanned RAID 5 drive groups. RAID 50 includes both parity and disk striping
across multiple drives. If a drive fails, the RAID controller uses the parity data to re-create all missing information. RAID 50 can sustain
one drive failure per RAID 5 drive group and still maintain data integrity.
60 Provides data redundancy using distributed parity across spanned RAID 6 drive groups. RAID 60 can sustain two drive failures per
RAID 6 drive group and still maintain data integrity. It provides the highest level of protection against drive failures of all of the
RAID levels. RAID 60 includes both parity and disk striping across multiple drives. If a drive fails, the RAID controller uses the parity data
to re-create all missing information.
2.3.2

Maximizing Performance

A RAID disk subsystem improves I/O performance. The RAID drive group appears to the host computer as a single
storage unit or as multiple virtual units. I/O is faster because drives can be accessed simultaneously. The following
table describes the performance for each RAID level.
Fault Tolerance
LSI Corporation
- 36 -
Chapter 2: Introduction to RAID
RAID Configuration Strategies