Sun Message ID: SUN4V-8000-L5

SUN4V-8000-L5

Single core DTLB errors exceeded acceptable levels

Type

Fault

Severity

Major

Description

The number of DTLB errors associated with this thread has exceeded acceptable levels.

Automated Response

The fault manager will attempt to remove all threads associated with this resource from service.

Impact

System performance is likely to be affected.

Suggested Action for System Administrator

Schedule a repair procedure to replace the affected resource, the identity of which can be determined using fmdump -v -u <EVENT_ID>.

Details

The Message ID: SUN4V-8000-L5 indicates a diagnosis has determined that one of the cores in the multi-thread processor contains a faulty resource. The faulty resource is shared by all threads in the core and the fault manager arranged an automated attempt to disable all eight threads in the core. It is recommended that the system administrator contact Sun support and arrange for the replacement of the affected component. Use the command fmdump -v -u <EVENT_ID> with the <EVENT_ID> from the console message to locate the faulty component.

For this fault, the fault manager identifies each thread in the core as faulty as shown in the example below.

# fmdump -v -u 305b067d-f256-46da-a172-b158c4c5f294
TIME                 UUID                                 SUNW-MSG-ID
Sep 26 11:55:44.0409 305b067d-f256-46da-a172-b158c4c5f294 SUN4V-8000-L5
  100%  fault.cpu.ultraSPARC-T2.dtlb

        Problem in: cpu:///cpuid=7/serial=FAC006B0E654482
           Affects: cpu:///cpuid=7/serial=FAC006B0E654482
               FRU: hc://:serial=110508:part=501781301/motherboard=0
          Location: MB

  100%  fault.cpu.ultraSPARC-T2.dtlb

        Problem in: cpu:///cpuid=6/serial=FAC006B0E654482
           Affects: cpu:///cpuid=6/serial=FAC006B0E654482
               FRU: hc://:serial=110508:part=501781301/motherboard=0
          Location: MB

                    .
                    .
                    .
   
  100%  fault.cpu.ultraSPARC-T2.dtlb

        Problem in: cpu:///cpuid=0/serial=FAC006B0E654482
           Affects: cpu:///cpuid=0/serial=FAC006B0E654482
               FRU: hc://:serial=110508:part=501781301/motherboard=0
          Location: MB

Note the FRU called out for each faulty thread is the same. In the example above, the FRU is the motherboard. Also note the FRU part number and location is included:

part=501781301

Location: MB

For more information, contact Sun Support.