Sun Microsystems Fire 880, Руководство пользователя

Страница: 38 / 236

20 Sun Fire 880 Server Owner’s Guide • August 2001
Dual-Loop Enabled FC-AL Mass Storage
Subsystem
The system’s dual-ported FC-AL disk drives and dual-loop enabled backplanes may
be combined with an optional PCI FC-AL host adapter card to provide for fault
tolerance and high availability of data. This dual-loop configuration allows each disk
drive to be accessed through two separate and distinct data paths, providing:
■
Increased bandwidth – Allowing data transfer rates up to 200 Mbytes per second
versus 100 Mbytes per second for single-loop configurations
■
Hardware redundancy – Providing the ability to sustain component failures in one
path by switching all data transfers to an alternate path
The mass storage subsystem is described in greater detail in Chapter 4.
Support for RAID Storage Configurations
Using a software RAID application such as Solstice DiskSuite™ or VERITAS Volume
Manager, you can configure system disk storage in a variety of different RAID levels.
Configuration options include RAID 0 (striping), RAID 1 (mirroring), RAID 0+1
(striping plus mirroring), RAID 1+0 (mirroring plus striping), and RAID 5
configurations (striping with interleaved parity). You choose the appropriate RAID
configuration based on the price, performance, and reliability/availability goals for
your system. You can also configure one or more drives to serve as “hot spares” to
fill in automatically for a defective drive in the event of a disk failure.
For more information, see “About Volume Management Software” on page 152.
Error Correction and Parity Checking
Error-correcting code (ECC) is used on all internal system data paths to ensure high
levels of data integrity. All data that moves between processors, memory, and PCI
bridge chips have end-to-end ECC protection.
The system reports and logs correctable ECC errors. A correctable ECC error is any
single-bit error in a 128-bit field. Such errors are corrected as soon as they are
detected. The ECC implementation can also detect double-bit errors in the same
128-bit field and multiple-bit errors in the same nibble (4 bits).
In addition to providing ECC protection for data, the system offers parity protection
on all system address buses. Parity protection is also used on the PCI and SCSI
buses, and in the UltraSPARC CPU’s internal and external cache.