IBM xSeries 380, Hardware Maintenance Manual

Page: 15 / 324

G eneral infor mation
5
What the xSeries 380 offers
The unique design of the xSeries 380 server combines the following features:
• Multiprocessor performance
The system supports one to four Itanium processors with 2 MB (733MHz) or 4 MB
(800MHz) of level-3 cache.
• Large system memory
Memory resides on two memory boards. Each memory board contains slots for
32 DIMMs. The memory controller supports PC 100-registered Version 1.2
Buffered SDRAM DIMMs. DIMM sizes supported are 256 MB, 512 MB, and 1 GB.
Each memory board can support from 1GB to 32 GB. The xSeries 380 server can
support up to 64 GB of system memory.
• System-management capabilities
Three controllers provide the system-management capabilities of your server: the
Baseboard Management Controller (BMC), Chassis Bridge Controller (CBC), and
the Hot-Swap Controller (HSC).
By using the Firmware Update utility the three controllers are field upgradeable.
The BMC monitors for system platform management events and logs their
occurrence in the System Event Log (SEL). System platform management events
include over-temperature and over-voltage conditions as well as fan failures
The HSC implements the SAF-TE command set, controls the fault lights, and
provides a path for management information from the SCSI interface. It retrieves
drive fault status, backplane temperature, and fan failure information from the
Intelligent Platform Management Bus (IPMB). Then queries the status of the
power distribution board from the BMC, and controls drive power-on and power-
down, to facilitate hot-swapping PCI adapters, fans, and hard disk drives.
The CBC serves as a bridge between the internal Intelligent Platform
Management Bus (IPMB) and the external Intelligent Chassis Management Bus
Controller (ICMBC). The internal IPMB transports management information
within a system, and the external ICMBC transports server management
information between various chassis in a server(s) and peripherals cluster
configuration.
Reliability, availability, and serviceability features
Three of the most important considerations in server design are reliability, availability,
and serviceability (RAS). The RAS features help you to ensure the integrity of the data
that is stored on your server, the availability of the server when you need it, and the
ease with which you can diagnose and repair problems.
The following is an abbreviated list of the RAS features that the server supports:
• Power-on self-test (POST)
• Automatic restart after a power failure
• Brownout protection
• Dual hot-swap LVDS SCSI hard disk drives
• Error checking and correcting (ECC) memory
• Error codes and messages
• Menu driven setup, system configuration and diagnostic programs