Sun Microsystems, Inc.  Sun System Handbook - ISO 3.4 June 2011 Internal/Partner Edition
   Home | Current Systems | Former STK Products | EOL Systems | Components | General Info | Search | Feedback

Asset ID: 1-77-1000142.1
Update Date:2011-02-09
Keywords:

Solution Type  Sun Alert Sure

Solution  1000142.1 :   Sun Fire 12K/15K/E20K/E25K Systems Equipped With a Quad GigaSwift (QGE-X) Card May Panic  


Related Items
  • Sun Fire E25K Server
  •  
  • Sun Fire E20K Server
  •  
  • Sun Fire 12K Server
  •  
  • Sun Fire 15K Server
  •  
Related Categories
  • GCS>Sun Microsystems>Sun Alert>Criteria Category>Availability
  •  
  • GCS>Sun Microsystems>Sun Alert>Release Phase>Resolved
  •  

PreviouslyPublishedAs
200188


Bug Id
<SUNBUG: 6624392>

Product
Sun Fire 12K Server
Sun Fire E20K Server
Sun Fire 15K Server
Sun Fire E25K Server

Date of Workaround Release
26-SEP-2007

Date of Resolved Release
21-Aug-2008


Impact

Sun Fire 12K/15K/E20K/E25K systems equipped with UltraSPARC IV or UltraSPARC IV+ System Boards that use high traffic across a Quad GigaSwift (QGE-X) card may panic.

Contributing Factors

This issue can occur on the following platforms:

  • Sun Fire 12K/15K/E20K/25K without patch 118777-13

The described issue only occurs under the following conditions:

1. The Sun Fire 12K/15K/E20K/E25K is equipped with an UltraSPARC IV or UltraSPARC IV+ System Board, and the Quad GigaSwift Ethernet PCIX Card (X4445 - 501-6738)

2. One of the network ports is at or near its peak bandwidth.

3. The network card is running at a frequency over 66MHz.

Note: The more CPU's in a domain, the more likely the panic may occur while the network port is at its peak bandwidth. This issue has not been seen on systems equipped with the UltraSPARC III system boards.

To determine if a system is equipped with a Quad GigaSwift Ethernet PCIX Card (X4445 - 501-6738), the following command can be used:

    # prtdiag
    System Configuration: Sun Microsystems Sun Fire 25000
    System clock frequency: 150 MHz
    Memory size: 327680 Megabytes
   ...
   /IO01/C3V0 PCI 60 A 90 90 1,0 ok pci-pci8086,537c.7/network (netw+ pci-bridge
   /IO01/C3V0 PCI 60 A 90 90 0,0 ok network-pci100b,35.30 SUNW,pci-x-qge
   /IO01/C3V0 PCI 60 A 90 90 1,0 ok network-pci100b,35.30 SUNW,pci-x-qge
   /IO01/C3V0 PCI 60 A 90 90 2,0 ok network-pci100b,35.30 SUNW,pci-x-qge
   /IO01/C3V0 PCI 60 A 90 90 3,0 ok network-pci100b,35.30 SUNW,pci-x-qge
   ...

 Symptoms

If the described issue occurs, a panic string of "Fatal PCI bus error(s)" will be seen.

Workaround

To work around the described issue, slow down the QGE-X card to use PCI speeds instead of PCIX. This is done by adding a post directive to the "postrc" file on the system controller. The "postrc" file is different for each domain. If there is not a "postrc" file for a specific domain, the platform "postrc" file is used. The domain "postrc" files are located at:

    /etc/opt/SUNWSMS/config/A/.postrc
    /etc/opt/SUNWSMS/config/B/.postrc
   /etc/opt/SUNWSMS/config/C/.postrc
    ...
    /etc/opt/SUNWSMS/config/R/.postrc

The platform "postrc" file is located at:

    /etc/opt/SUNWSMS/config/platform/.postrc

The postrc directive is a single line that is added to this file. The syntax is:

    iobrd_no_pcix exp [ lport [ bus ]]
    iobrd_no_pcix 1 0 0 # changes IOBoard Slot 0 on IO1.

Use this "postrc" directive for every QGE-X card that is in the platform.

Below is an example of the postrc directive and its syntax for each slot:

    iobrd_no_pcix 3 0 0 # changes IOBoard Slot 0 on IO3.
    iobrd_no_pcix 3 1 0 # changes IOBoard Slot 2 on IO3.
    iobrd_no_pcix 3 1 1 # changes IOBoard Slot 3 on IO3.

Note: Slot 1 is not a PCIX slot and is not impacted by this issue.

Resolution

This issue is adressed in the following release:

  • Sun Fire 12K/15K/E20K/E25K with patch 118777-13 or later

Modification History
04-Oct-2007: Updated the Impact and Contributing Factors sections
29-Oct-2007: Updated Contributing Factors section
21-Aug-2008: Updated BugID field and Resolution section
State: Resolved

References

<SUNPATCH: 118777-13>

Previously Published As
103046
Internal Comments
Related BugID: 6568209
Please send technical questions to the following email:
[email protected]
and CC the following persons:
Internal Contributor/Submitter
Internal Eng Responsible Engineer
Internal Contributor/submitter
[email protected]
Internal Eng Responsible Engineer
[email protected]
Internal Services Knowledge Engineer
[email protected]
Internal Eng Business Unit Group
SSG ES (Enterprise Systems)
Internal Escalation ID
1-22184143, 1-21909003, 1-22098997
Internal Resolution Patches
118777-13
Internal Sun Alert Kasp Legacy ID

References

SUNPATCH:118777-13

Attachments
This solution has no attachment
  Copyright © 2011 Sun Microsystems, Inc.  All rights reserved.
 Feedback