HP Integrity rx2800 i2 Server User Service Guide

Troubleshooting the processor and memory
All of the processor and memory controller functions are integrated into the processor. DIMMs
reside on the memory expansion boards, and PCIe bus controller chips reside on the I/O riser and
the system board. This section discusses the roles of logical processors, and physical memory ranks.
Troubleshooting the server processor
The server supports both dual-core and quad-core processors. Each server supports one or two
processor modules. The dual-core processor modules contain two individual processor cores. When
two processor modules are installed in the server, the server contains four physical processors.
Furthermore, each physical processor core contains logic to support two physical threads. When
two dual-core processor modules are installed and enabled in the server, the server supports up
to eight threads, or the equivalent of eight logical processors.
Processor load order
For a minimally loaded server, one processor module must be installed in processor socket 0 on
the system board, and the threads must be enabled by user actions. Additional processor modules
of the same revision are installed in processor socket 1 for the server.
Processor module behaviors
Local MCA events can cause the physical processor core and one or both of the logical processors
within that processor module to fail while all other physical and their logical processors continue
operating. Double-bit data cache errors in any physical processor core causes a Global MCA
event, which, in turn, causes all logical and physical processors in the server to fail and reboot the
operating system.
Customer messaging policy
• A diagnostic LED only illuminates for physical processor core errors, when isolation is to a
specific IPF processor module. If there is any uncertainty about a specific processor, then the
customer is pointed to the SEL for any action, and the suspect IPF processor module CRU LED
on the System Insight Display does not illuminate.
• For configuration-type errors (for example, when no IPF processor module is installed in
processor slot 0) all of the CRU LEDs on the diagnostic LED panel illuminate for all of the IPF
processors that are missing.
• No diagnostic messages are reported for single-bit errors that are corrected in both instruction
and data caches, during CMC events to any physical processor core. Diagnostic messages
are reported for CMC events when thresholds are exceeded for single-bit errors; fatal processor
errors cause global / local MCA events.
Table 30 Processor events that illuminate SID LEDs
NotesSourceCauseSample IPMI EventsDiagnostic
LEDs
This event
follows other
SFWProcessor
failed and
deconfigured
Type E0h, 39d:04d
BOOT_DECONFIG_CPU
Processors
failed
processors
Threshold
exceeded for
WIN AgentToo many
cache errors
Type E0h, 5823d:26d
PFM_CACHE_ERR_PROC
Processors
cache paritydetected by
processor errors on
processor
Threshold
exceeded for
WIN AgentToo many
corrected
Type E0h, 5824d:26d
PFM_CORR_ERROR_MEM
Processors
88 Troubleshooting