Sun SPARC Enterprise T5240 Server
 

PLA-Support>Sun Systems>SPARC>CMT>SN-SPARC: T5xx0
 

FMA MSGID PCIEX-8000-3S seen in CMT server having  XVR-300 card

In this Document

Symptoms

Changes

Cause

Solution

References

Created from <SR 3-9068181346>

Applies to:

Symptoms

FMA MSG-ID PCIEX-8000-3S is detected by the system, the issue only occurred on PCI-E slot on which seated the XVR-300 card as you can see in the path below. In this case the card was located at PCIE4.

fma/fmadm-faulty.out
--------------- ------------------------------------  -------------- ---------
TIME            EVENT-ID                              MSG-ID         SEVERITY
--------------- ------------------------------------  -------------- ---------
May 28 06:56:01 2283918b-6500-e398-fec4-f184bfed2900  PCIEX-8000-3S  Critical

Host        : xxxxxxxxxxxx
Platform    : SUNW,T5240        Chassis_id  :
Product_sn  :

Fault class : fault.io.pciex.device-interr max 40%
              fault.io.pciex.bus-linkerr 20%
Affects     : dev:////pci@500/pci@0/pci@d/SUNW,XVR-300@0
              dev:////pci@500/pci@0/pci@d
                  faulted but still in service
FRU         : "MB/RISER1/PCIE4" (hc://:product-id=SUNW,T5240:server-id=usbljdeapp001:chassis-id=BEL0824NDV/motherboard=0/hostbridge=0/pciexrc=1/pciexbus=2/pciexdev=0/pciexfn=0/pciexbus=3/pciexdev=13/pciexfn=
0/pciexbus=7/pciexdev=0) max 40%
              "MB" (hc://:product-id=SUNW,T5240:server-id=usbljdeapp001:chassis-id=BEL0824NDV:serial=0182SJC-0822TA0329:part=541252806/motherboard=0) 40%
                  faulty

Description : A problem has been detected on one of the specified devices or on
              one of the specified connecting buses.
              Refer to http://sun.com/msg/PCIEX-8000-3S for more information.

Response    : One or more device instances may be disabled

Impact      : Loss of services provided by the device instances associated with
              this fault

Action      : If a plug-in card is involved check for badly-seated cards or
              bent pins. Otherwise schedule a repair procedure to replace the
              affected device(s).  Use fmadm faulty to identify the devices or
              contact Sun for support.

showfaults
  ID Time                           FRU               Class             Fault
   1 May 28 05:56:29                /SYS/MB/RISER1/PCIE4                   Host detected fault MSGID: PCIEX-8000-3S  UUID: 2283918b-6500-e398-fec4-f184bfed2900
   2 May 28 05:56:29                /SYS/MB                             Host detected fault MSGID: PCIEX-8000-3S  UUID: 2283918b-6500-e398-fec4-f184bfed2900
sc>

SP firmware version: 3.0.10.4

etc/release
                       Solaris 10 5/08 s10s_u5wos_10 SPARC
           Copyright 2008 Sun Microsystems, Inc.  All Rights Reserved.
                        Use is subject to license terms.
                             Assembled 24 March 2008

Changes

 The bug 6724333 indicates that the issue could accur when a user logged into the system and were actively using the graphics card, but in this case the customer wans't actively using the graphics card.

The card SUNW,XVR-300 with Sun Part Number 375-3545 [C] showed in prtdiag as:

PCIE4             xvr   SUNW,XVR-300                      SUNW,375-3545  2.5GTx8
                        /pci@500/pci@0/pci@d/SUNW,XVR-300@0

Cause

  PCI express replay timeout events associated with the XVR-300 card

Jul 30 15:10:05.8776 ereport.io.fire.pec.rto
Jul 30 15:10:05.9566 ereport.io.fire.pec.btp
Jul 30 15:10:06.2536 ereport.io.fire.pec.btp
Jul 30 15:10:06.5606 ereport.io.fire.pec.rto
Jul 30 15:10:06.6026 ereport.io.fire.pec.btp
Jul 30 15:10:06.6646 ereport.io.fire.pec.rto
Jul 30 15:10:07.1676 ereport.io.fire.pec.rto
Jul 30 15:10:07.2856 ereport.io.fire.pec.btp
Jul 30 15:10:07.5306 ereport.io.fire.pec.btp
Jul 30 15:10:07.5676 ereport.io.fire.pec.btp
Jul 30 15:10:07.6715 ereport.io.fire.pec.btp
Jul 30 15:10:08.0955 ereport.io.fire.pec.rto
Jul 30 15:10:08.1195 ereport.io.fire.pec.rto
Jul 30 15:10:08.3545 ereport.io.fire.pec.btp
Jul 30 15:10:08.5255 ereport.io.fire.pec.btp
Jul 30 15:10:08.8075 ereport.io.fire.pec.btp
Jul 30 15:10:08.9195 ereport.io.fire.pec.rto
Jul 30 15:10:09.3445 ereport.io.fire.pec.rto
Jul 30 15:10:09.4385 ereport.io.fire.pec.btp
Jul 30 15:10:09.6835 ereport.io.fire.pec.btp
Jul 30 15:10:09.7455 ereport.io.fire.pec.rto
Jul 30 15:10:10.0205 ereport.io.fire.pec.rto
Jul 30 15:10:10.0845 ereport.io.fire.pec.btp
Jul 30 15:10:10.2255 ereport.io.fire.pec.btp
Jul 30 15:10:10.3665 ereport.io.fire.pec.btp
Jul 30 15:10:10.5845 ereport.io.fire.pec.rto
Jul 30 15:10:10.6735 ereport.io.fire.pec.rto
Jul 30 15:10:10.8295 ereport.io.fire.pec.rto
Jul 30 15:10:10.9235 ereport.io.fire.pec.btp
Jul 30 15:10:11.0355 ereport.io.fire.pec.rto
Jul 30 15:10:11.1915 ereport.io.fire.pec.rto
Jul 30 15:10:11.2055 ereport.io.fire.pec.btp
Jul 30 15:10:11.2955 ereport.io.fire.pec.rto
Jul 30 15:10:11.4654 ereport.io.fire.pec.btp

Solution

The current workaround is to add the following to /etc/system to disable soft errors;
   set pcie:pcie_base_err_default = 0xe

Fixed in Product Version SOLARIS_10U9

References

This solution has no attachment