What are ereport.cpu.generic-sparc.c2c-link@/host messages on SPARC T4 Servers

Asset ID:	1-79-1525980.1
Update Date:	2017-10-19
Keywords:

Solution Type Predictive Self-Healing Sure

Solution 1525980.1 : What are ereport.cpu.generic-sparc.c2c-link@/host messages on SPARC T4 Servers

Applies to:

SPARC T4-4 - Version All Versions and later
SPARC T4-2 - Version All Versions and later
SPARC SuperCluster T4-4 - Version All Versions and later
Netra SPARC T4-2 Server - Version All Versions and later
Information in this document applies to any platform.

Purpose

Why are ereport.cpu.generic-sparc.c2c-link@/host messages being reported on a SPARC T4 Server and how should they be handled.

Details

A C2C-link ereport is reporting a "retry" on the coherency links that connect CPU chips together. These are the links that memory transaction information is exchanged to keep cache and memory data in sync and valid. These links operate at a very high data rate, 9.6Gb/sec on a multi proceesor T4. High speed links like this may experience retries, and these ereports are only indicating that one occurred. FMA counts them all and will produce a fault message should the ereports on any one C2C link exceed established thresholds.

If the established threshold is exceeded a FMA SUN4V-8002-KQ fault similar to the example below will be reported.

The fault can be seen by executing "fmadm faulty".

==========================================================================================

--------------- ------------------------------------ -------------- ---------
TIME EVENT-ID MSG-ID SEVERITY
--------------- ------------------------------------ -------------- ---------
Mar 06 16:17:01 12f78095-7788-e159-dfa9-8da2a22fb197 SUN4V-8002-KQ Major

Host        : ssccn4-m1
Platform    : ORCL,SPARC-T4-4   Chassis_id :
Product_sn :Fault class : fault.cpu.generic-sparc.c2c
Affects     : hc://:product-id=ORCL,SPARC-T4-4:product-sn=1151BDY190:server-id=ssccn4-m1:chassis-id=1151BDY190/chassis=0/cpuboard=1/chip=2
              hc://:product-id=ORCL,SPARC-T4-4:product-sn=1151BDY190:server-id=ssccn4-m1:chassis-id=1151BDY190/chassis=0/cpuboard=0/chip=0
                  faulted but still in service
FRU         : "/SYS/PM1" (hc://:product-id=ORCL,SPARC-T4-4:product-sn=1151BDY190:server-id=ssccn4-m1:chassis-id=1151BDY190:serial=465769T+1149L9010F:part=7019789:revision=05/chassis=0/cpuboard=1) 50%
              "/SYS/PM0" (hc://:product-id=ORCL,SPARC-T4-4:product-sn=1151BDY190:server-id=ssccn4-m1:chassis-id=1151BDY190:serial=465769T+1124L9000G:part=7019789:revision=03/chassis=0/cpuboard=0) 50%   faulty
Description : The number of chip-to-chip recoverable errors has exceeded acceptable levels.Response    : No automated response.Impact      : System performance may be affected.

=========================================================================================================================

 What to do:

If a SUN4V-8002-KQ is reported open a Service Request with Oracle support for assistance. Provide an explorer and snapshot if possible.

As long as the output of fmadm faulty does not include a SUN4V-8002-KQ any ereport.cpu.generic-sparc.c2c-link@/host messages can be ignored. 

  
NOTE:

SPARC T4-4 Current Product Issues (Doc ID 1358305.1)provides additional steps for dealing with SUN4V-8002-KQ fma faults on T4-4 servers

References

<NOTE:1452064.1> - SUN4V-8002-KQ faults reported on T4-4, T4-2 and Netra T4-2 servers

Attachments

This solution has no attachment