Hardware Issues

This section describes issues related to SPARC T4-2 server components.

Maximizing Memory Bandwidth

To maximize memory bandwidth, Oracle recommends that only fully-populated memory configurations—as opposed to half-populated configurations—be considered for performance-critical applications.

For specific memory installation and upgrade instructions, see the SPARC T4-2 Server Service Manual.

Direct I/O Support

Only certain PCIe cards can be used as direct I/O endpoint devices on an I/O domain. You can still use other cards in your Oracle VM Server for SPARC environment, but they cannot be used with the Direct I/O feature. Instead, they can be used for service domains and for I/O domains that have entire root complexes assigned to them.

For the most up-to-date list of supported PCIe cards, refer to:

https://support.oracle.com/CSP/main/article?cmd=show&type=NOT&doctype=REFERENCE&id=1325454.1

Installing the Sun Storage 8-Port Internal 6 Gb SAS PCIe HBA in a Split Configuration

You can install the Sun Storage 8-Port Internal 6 Gb SAS PCIe HBA in a split configuration, as follows:

• Sun Storage 8-Port Internal 6 Gb SAS PCIe HBA:

  • HDD0

  • HDD1

  • HDD2

  • HDD3

• Onboard RAID controller:

  • HDD4

  • HDD5

  • Internal DVD

To install the Sun Storage 8-Port Internal 6 Gb SAS PCIe HBA in a split configuration, do the following:

1. Install the HBA, either in PCIe slot 0 or PCIe slot 1.

   ---

   Note - If you install the HBA in PCIe slot 1, PCIe slot 0 must remain unpopulated to ensure proper system cooling.

   ---

   

2. Unplug the SAS data cable from the connector marked DISK0-3 on the motherboard.

3. Plug the SAS data cable into the upper connector on the HBA.

   

Use Links Labeled SPARC T3 to Download sas2ircu Software for SPARC T4 Servers

To download sas2ircu firmware and documentation for SPARC T4-1 and T4-2 servers from the current LSI web site, you must use links labeled SPARC T3-1 and T3-2. The software and documentation is the same for both sets of servers.

This is the web site for downloading sas2ircu software from LSI:

http://www.lsi.com/sep/Pages/oracle/index.aspx

This is the web site for downloading sas2ircu documentation from LSI:

http://www.lsi.com/sep/Pages/oracle/sparc_t3_series.aspx

Sun Type 6 Keyboards Are Not Supported by SPARC T4 Series Servers

Sun Type 6 keyboards cannot be used with SPARC T4 series servers.

RAID10 is Not Supported; Use RAID 1E Instead

RAID 10 is not supported on the SPARC T4-2 server. However, you can create a RAID 1E volume using an even number of disk drives to obtain the same functionality as RAID 10. For example:

ok 9 b c d create-raid1e-volume
Target 9 size is 583983104 Blocks, 298 GB
Target b size is 583983104 Blocks, 298 GB
Target c size is 583983104 Blocks, 298 GB
Target d size is 583983104 Blocks, 298 GB
The volume can be any size from 1 MB to 570296 MB
What size do you want?  [570296] 570296
Volume size will be 1167966208 Blocks, 597 GB
Enter a volume name:  [0 to 15 characters] VolumeTest
Volume has been created
ok probe-scsi-all
/pci@400/pci@2/pci@0/pci@e/scsi@0
ok select /pci@400/pci@2/pci@0/pci@e/scsi@0
ok show-volumes
Volume 0 Target 381  Type RAID1E (Mirroring Extended)
 Name VolumeTest  WWID 0576f2dfda831e3b
 Optimal  Enabled  Background Init In Progress
 4 Members                                         1167966208 Blocks, 597 GB
 Disk 0
  Member 0  Optimal
  Target 9      HITACHI  H106030SDSUN300G A2B0   PhyNum 0
 Disk 1
  Member 1  Optimal
  Target b      HITACHI  H106030SDSUN300G A2B0   PhyNum 1
 Disk 2
  Member 2  Optimal
  Target c      SEAGATE  ST930003SSUN300G 0B70   PhyNum 2
 Disk 3
  Member 3  Optimal
  Target d      HITACHI  H106030SDSUN300G A2B0   PhyNum 3

Refer to the SPARC and Netra SPARC T4 Series Servers Administration Guide for more about creating RAID volumes.

Server Panics When Booting From a USB Thumbdrive Attached to the Front USB Ports (Bug ID 15667682)

When attempting to boot a USB thumbdrive inserted in either front USB port (USB2 or USB3), the server might panic.

Workaround: Use the server's rear USB ports (USB0 or USB1) whenever booting from an external USB device.

Booting Solaris 11 from a USB thumbdrive is not supported.

Cannot Plumb Sun Quad GbE x8 PCIe Low Profile Adapter in PCIe Slot 0 When More Than Five Are Installed (Bug ID 15676454)

The Ethernet ports of a Sun Quad GbE x8 PCIe Low Profile adapter installed in PCIe slot 0 cannot be plumbed if there are more than five Sun Quad GbE x8 PCIe Low Profile adapters installed in the server. However, up to nine Sun Quad GbE x8 PCIe Low Profile adapters are supported in the server when one of these adapters is not installed in slot 0.

Workaround: Do not install a Sun Quad GbE x8 PCIe Low Profile adapter in PCIe slot 0.

Front-Panel Video Port Does Not Support Resolutions Greater Than 1024 x 768 (Bug ID 15698604)

The SPARC T4-2 server contains two video HD15 ports, one in the front of the server and one in the rear of the server. The front video port does not support screen resolutions greater than 1024 x 768.

If you require screen resolutions greater than 1024 x 768, connect the monitor to the server's rear video port. The rear video port supports resolutions up to 1280 x 1024. Refer to the SPARC T4 Series Servers Administration Guide and the fbconfig(1M) man page for instructions on using a local graphics monitor.

PSH Might Not Clear a Retired Cache Line on a Replaced Motherboard (Bug ID 15705327, Bug ID 15713018)

If you replace the replacement enclosure to repair faulty cache on the motherboard, PSH might not clear the cache on the replacement. The cache line remains disabled.

Workaround: Manually clear the disabled cache line by running the following commands:

# fmadm repaired fmri | label
# fmadm replaced fmri | label

Restrictions on Placement of HBAs in Slot 4 and Slot 5 (Bug ID 15717157)

Follow these rules for placement of the following cards in the server.

You can place the following FCoE 10Gb/s Converged Network Adapters in either slot 4 or slot 5, but not in both slots:

• SG-XPCIEFCOE2-Q-SR

• SG-PCIEFCOE2-Q-SR

• SG-XPCIEFCOE2-Q-TA

• SG-PCIEFCOE2-Q-TA

You can place the following Fibre Channel I/O Adapters in either slot 4 or slot 5, but not in both slots:

• SG-XPCIE2FC-QF8-N

• SG-PCIE2FC-QF8-Z

• SG-XPCIE2FC-EM8-N

• SG-PCIE2FC-EM8-Z

Workaround: You can populate both slot 4 and slot 5 with HBA cards if you install the cards before doing a fresh reinstallation of the Oracle Solaris OS.

PCIe Correctable Errors Might Be Reported (Bug ID 15720000, Bug ID 15722832)

In rare cases, PCI Express Gen2 devices in the server might report I/O errors that are identified and reported by PSH. For example:

--------------- ------------------------------------  -------------- ---------
TIME            EVENT-ID                              MSG-ID         SEVERITY
--------------- ------------------------------------  -------------- ---------
Aug 10 13:03:23 a7d43aeb-61ca-626a-f47b-c05635f2cf5a  PCIEX-8000-KP  Major
 
Host        : dt214-154
Platform    : ORCL,SPARC-T3-1B  Chassis_id  :
Product_sn  :
 
Fault class : fault.io.pciex.device-interr-corr 67%
              fault.io.pciex.bus-linkerr-corr 33%
Affects     : dev:////pci@400/pci@1/pci@0/pci@c
              dev:////pci@400/pci@1/pci@0/pci@c/pci@0
                  faulted but still in service
FRU         : "/SYS/MB" (hc://:product-id=ORCL,SPARC-T3-1B:product-sn=1052NND107:server-id=dt214-154:chassis-id=0000000-0000000000:serial=1005LCB-1052D9008K:part=541-424304:revision=50/chassis=0/motherboard=0) 67%
              "FEM0" (hc://:product-id=ORCL,SPARC-T3-1B:product-sn=1052NND107:server-id=dt214-154:chassis-id=0000000-0000000000/chassis=0/motherboard=0/hostbridge=0/pciexrc=0/pciexbus=1/pciexdev=0/pciexfn=0/pciexbus=2/pciexdev=12/pciexfn=0/pciexbus=62/pciexdev=0) 33%
                  faulty
 
Description : Too many recovered bus errors have been detected, which indicates
              a problem with the specified bus or with the specified
              transmitting device. This may degrade into an unrecoverable
              fault.
              Refer to http://sun.com/msg/PCIEX-8000-KP 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.  Use fmadm faulty to identify the device or
              contact Sun for support.

These errors might be an indication of a faulty or incorrectly seated device. Or these errors might be erroneous.

Workaround: Ensure that the device is properly seated and functioning. If the errors continue, apply patch 147705-01 or higher.

L2 Cache Uncorrectable Errors Might Lead to an Entire Processor Being Faulted (Bug ID 15727651, Bug ID 15732875, Bug ID 15732876, Bug ID 15733117)

An L2 cache uncorrectable error might lead to an entire processor being faulted when only specific core strands should be faulted.

Workaround: Schedule a service call with your authorized Oracle service provider to replace the processor containing the faulty core. Until the processor is replaced, you can return the strands related to the functioning cores to service using the following procedure. This procedure restores as much system functionalty as the active cores provide.

1. Identify the faulty core:

   # fmdump -eV -c ereport.cpu.generic-sparc.l2tagctl-uc

   The following example shows the detector portion of the fmdump output for a SPARC T4-2 server.

   ---

   Note - Key elements in the example are highlighted for emphasis. They would not be highlighted in the actual output.

   ---

   detector = (embedded nvlist)
       nvlist version: 0
              version = 0x0
              scheme = hc
              hc-root =
              hc-list-sz = 4
              hc-list - (array of embedded nvlists)
             (start hc-list[0])
             nvlist version: 0
                    hc-name = chassis
                   hc-id = 0
             (end hc-list[0])
             (start hc-list[1])
             nvlist version: 0
                    hc-name = motherboard
                   hc-id = 0
             (end hc-list[1])
             (start hc-list[2])
             nvlist version: 0
                    hc-name = chip
                   hc-id = 1
             (end hc-list[2])
             (start hc-list[3])
             nvlist version: 0
                    hc-name = core
                   hc-id = 10
             (end hc-list[3])
    
   (end detector)

   In this example, the faulted chip is indicated by the following FMRI values:

   • Chassis = 0

   • Motherboard = 0

   • Chip = 1

   • Core = 10

   These FMRI values correspond to the NAC name:

   /SYS/MB/CMP1/CORE2

   ---

   Note - The NAC CORE value is rhe FRMI core value modulo 8.

   ---

   The following NAC name equivalents are for all CMP cores in a SPARC T4-2 server.

   FMRI Values for Cores Corresponding NAC Name chassis=0 / motherboard=0 / chip=0 /core=0 /SYS/MP/CMP0/CORE0 chassis=0 / motherboard=0 / chip=0 /core=1 /SYS/MP/CMP0/CORE1 chassis=0 / motherboard=0 / chip=0 /core=2 /SYS/MP/CMP0/CORE2 chassis=0 / motherboard=0 / chip=0 /core=3 /SYS/MP/CMP0/CORE3 chassis=0 / motherboard=0 / chip=0 /core=4 /SYS/MP/CMP0/CORE4 chassis=0 / motherboard=0 / chip=0 /core=5 /SYS/MP/CMP0/CORE5 chassis=0 / motherboard=0 / chip=0 /core=6 /SYS/MP/CMP0/CORE6 chassis=0 / motherboard=0 / chip=0 /core=7 /SYS/MP/CMP0/CORE7 chassis=0 / motherboard=0 / chip=1 /core=8 /SYS/MP/CMP1/CORE0 chassis=0 / motherboard=0 / chip=1 /core=9 /SYS/MP/CMP1/CORE1 chassis=0 / motherboard=0 / chip=1 /core=10 /SYS/MP/CMP1/CORE2 chassis=0 / motherboard=0 / chip=1 /core=11 /SYS/MP/CMP1/CORE3 chassis=0 / motherboard=0 / chip=1 /core=12 /SYS/MP/CMP1/CORE4 chassis=0 / motherboard=0 / chip=1 /core=13 /SYS/MP/CMP1/CORE5 chassis=0 / motherboard=0 / chip=1 /core=14 /SYS/MP/CMP1/CORE6 chassis=0 / motherboard=0 / chip=1 /core=15 /SYS/MP/CMP1/CORE7

2. Save the UUID value provided in the first line of the fmdump output.

   You will use this UUID value in the final step of this procedure.

3. Halt the Oracle Solaris OS, and power off the server.

   Refer to the Administration Guide for information on powering off the server when the OS is running.

4. At the Oracle ILOM prompt, change directory to the faulty core.

   The following example continues from earlier steps in which the faulty core had a FMRI value of core=10.

   -> cd /SYS/MB/CMP1/CORE2
   /SYS/MB/CMP1/CORE2
   -> show /SYS/MB/CMP1/CORE2
   Targets:
   P0
   P1
   P2
   P3
   P4
   P5
   P6
   P7
   L2CACHE
   L1CACHE
    
   Properties:
   type = CPU Core
   component_state = Enabled
    
   Commands:
   cd
   set
   show
    

5. Disable the faulty core.

   ->set component_state = disabled

6. Power on the server, and restart the Oracle Solaris OS.

   Refer to the Administration Guide for information on powering on the server from the Oracle ILOM prompt.

7. Override the FMA diagnosis manually:

   The faulty component's UUID value is provided in the first line of fmdump output.

    # fmadm repair UUID-of-fault

L2 Cache UEs Are Sometimes Reported as Core Faults Without Any Cache Line Retirements (Bug ID 15731176)

When a processor cache line encounters an uncorrectable error (UE), the fault manager is supposed to attempt to retire the cache line involved in the error. Because of this defect, the fault manager might not retire the faulty cache line and instead reports the entire chip as faulted.

Workaround: Schedule a replacement of the FRU containing the faulty component. For additional information about UEs in processor cache lines, search for message ID SUN4V-8002-WY on the Oracle support site: http://support.oracle.com

Upon a Reboot After an Unrecoverable Hardware Error, CPUs Might Not Start (Bug ID 15733431)

In rare cases, if the server or sever module experiences a serious problem that results in a panic, when the server is rebooted, a number of CPUs might not start, even though the CPUs are not faulty.

Example of the type of error displayed:

rebooting...
Resetting...
 
ERROR: 63 CPUs in MD did not start

Workaround: Log in to Oracle ILOM on the SP and power cycle:

-> stop /SYS
Are you sure you want to stop /SYS (y/n)? y
Stopping /SYS
-> start /SYS
Are you sure you want to start /SYS (y/n) ? y
Starting /SYS

Spurious Power Supply Errors Might Be Reported (Bug ID 15800916)

In some cases, the Oracle ILOM firmware identifies and reports spurious power supply errors. For example:

date time ereport.chassis.power.insufficient asserted@/sys/ps2  /SYS/PS2/POWER_MISSING
date time ereport.chassis.power.insufficient-deasserted@/sys/ps2 /SYS/PS2/POWER_MISSING

Workaround: Update the server to System Firmware 8.2.0.f or later. If these errors persist, they indicate a power supply fault. Refer to the SPARC T4-2 Server Service Manual for specific instructions.