Hitachi 1000 - Manual (Page 39)

www.hitachi.com BladeSymphony 1000 Architecture White Paper 39
Chapter 6
Reliability and Serviceability Features
Reliability, availability, and serviceability are key requirements for platforms running business-critical
application services. In today’s globally competitive environment, where users access applications
round-the-clock, downtime is unacceptable and can result in lost customers, revenue, and reputation.
The BladeSymphony 1000 is designed with a number of features intended to increase the uptime of the
system.
Reliability Features
Intended to execute core business operations, the BladeSymphony 1000’s modular design increases
reliability through the high availability of redundant components. Rather than focus on creating individual
highly available components, the BladeSymphony 1000 utilizes multiple industry-standard components
to cost-effectively increase reliability. Redundant components also increase the serviceability of the
system by allowing the system to continue operating while new components are added or failed
components are replaced.
The BladeSymphony 1000 is designed with features to help ensure the system does not crash due to a
failure and to minimize the effects from a failure. These features are listed in Table 11.
Table 11: Reliability features
Function Feature
Quickly detect/diagnose failed part BIOS self-diagnostic function
Memory scrubbing function (Intel Itanium Server Blade)
Failure recovery by retry and correc-
tion ECC function (memory, CPU bus, SMP link (Intel Itanium
Server Blade), CRC retry function (PCIe, SCSI)
Dynamic isolation of failed part Advanced ECC, online spare memory
Redundant configurations HDD Modules, redundant Switch & Management Modules,
Power Modules, and Cooling Fan Modules
Memory mirroring (Intel Xeon Server Blades)
Redundant system configurations Redundant LAN/FC modules
Cluster system configuration, N+1/N+M configurations
Obtain failure information Isolation of failed part using System Event Log, BladeSym-
phony Management Suite, and Storage Manager
Automatic notification of failure by ASSIST via email
Block failed part Isolation of failed part upon system boot
Repair failed part during operation Repair CPI adapter, Switch & Management Module, Power
Module, Cooling Fan Module while system is operating