IBM BladeCenter JS12, Problem Determination And Service Manual

Page: 25 / 318

Chapter 2. Diagnostics
Use the available diagnostic tools to help solve any problems that might occur in
the blade server.
The first and most crucial component of a solid serviceability strategy is the ability
to accurately and effectively detect errors when they occur. While not all errors are
a threat to system availability, those that go undetected are dangerous because the
system does not have the opportunity to evaluate and act if necessary. POWER6
processor-based systems are specifically designed with error-detection mechanisms
that extend from processor cores and memory to power supplies and hard drives.
POWER6 processor-based systems contain specialized hardware detection circuitry
for detecting erroneous hardware operations. Error checking hardware ranges from
parity error detection coupled with processor instruction retry and bus retry, to
ECC correction on caches and system buses.
IBM hardware error checkers have these distinct attributes:
v Continuous monitoring of system operations to detect potential calculation
errors
v
Attempted isolation of physical faults based on runtime detection of each unique
failure
v
Initiation of a wide variety of recovery mechanisms designed to correct a
problem
POWER6 processor-based systems include extensive hardware and firmware
recovery logic.
Machine check handling
Machine checks are handled by firmware. When a machine check occurs, the
firmware analyzes the error to identify the failing device and creates an error log
entry.
If the system degrades to the point that the service processor cannot reach standby
state, the ability to analyze the error does not exist. If the error occurs during
POWER
®
hypervisor (PHYP) activities, the PHYP initiates a system reboot.
In partitioned mode, an error that occurs during partition activity is surfaced to the
operating system in the partition.
© Copyright IBM Corp. 2008, 2009
11