Hardware Issues

This section describes the known hardware-related issues.

SPARC T3 and T4 Platforms Might See Dropped or Double Character Input From USB Keyboards (CR 7067025)

On Oracle's SPARC T3 and T4 servers, all USB ports/connectors available to users are connected to an internal USB 2.0 (ehci) controller through an onboard USB 2.0 hub.

When a full/low speed USB 1.0/1.1 keyboard and mouse are connected to a USB port through this USB 2.0 hub, keyboard input might drop characters or might display double characters.

Workaround: Currently, a workaround has been implemented for this issue where an internal USB hub is manually bound to the ohci (USB 1.0/1.1) driver. This binding causes a variable named ehci_forced_port_to_companion to instruct the ehci (USB 2.0) driver to transfer ownership of a specific port on the USB controller to the ohci (1.0/1.1) driver. Once the ohci driver is bound to a particular port on the USB controller, the ohci driver will also be used by the internal USB hub connected to that port and all USB connectors on that hub.

This workaround is available in the following forms:

• Oracle Solaris 11 OS – Oracle Solaris 11 Support Repository Update 3 (SRU3)

• Oracle Solaris 10 8/11 – Patch 147004-03

For earlier supported versions of Oracle Solaris 10, apply the Solaris 10 8/11 SPARC Bundle, followed by patch 147004-03.

Supplementary Notes

On T3-1, T4-1, T3-2, and T4-2, the rear USB connectors as well as the virtual keyboard, virtual mouse, virtual CD-ROM, and virtual USB ethernet connection to the service processor (a.k.a RKVMS) are all beneath a hub connected to port 2 on the USB controller.

The front USB connectors are connected through a hub to port 4 of the USB controller.

Likewise, on the T3-4 and T4-4 platforms, the rear USB connector is beneath a hub that is connected to port 3 of the USB controller and the front USB connector and the virtual mouse, keyboard, CD-ROM and virtual USB ethernet connection to the service processor are beneath a hub that is connected to port 2 of the USB controller.

To use a physical keyboard and mouse with this workaround, apply the fix (either patch 147004-03 or SRU3) and then perform the following recommended steps:

• On SPARC T3-1, T4-1, T3-2, and T4-2 systems:

1. Connect the input devices to a front USB connector.

2. Add the following line to /kernel/drv/ehci.conf:

   ehci-port-forced-to-companion = 4

3. Reboot.

• On SPARC T3-4 and T4-4 systems:

1. Connect the input devices to a rear USB connector.

2. Add the following line to /kernel/drv/ehci.conf:

   ehci-port-forced-to-companion = 3

3. Reboot.

To use a virtual keyboard and mouse with this workaround, first apply the fix (either patch 147004-03 for Oracle Solaris 10 or SRU3 for Oracle Solaris 11) and then add the following line to /kernel/drv/ehci.conf and reboot:

ehci-port-forced-to-companion = 2

All other devices connected to the hub that services the virtual keyboard and mouse will be forced to operate at the lower USB 1.0/1.1 speed. These include:

• The virtual USB ethernet connection to the service processor.

• The physical USB connectors:

  • Rear connectors on the T3-1, T4-1, T3-2, and T4-2 servers.

  • Front connectors on the T3-4 and T4-4 servers.

When these devices do not come up, messages similar to the following will be displayed on the console and written to system logs:

WARNING: /pci@400/pci@2/pci@0/pci@f/pci@0/usb@0,1/hub@1/hub@3 (hubd4): 
Connecting device on port 2 failed

WARNING: /pci@400/pci@2/pci@0/pci@f/pci@0/usb@0,1/hub@1/hub@3 (hubd4):
Connecting device on port 3 failed

For this reason, you should limit use of following USB ports when using virtual keyboard and mouse functionality:

• Rear USB connectors on the T3-1, T4-1, T3-2, and T4-2

• Front USB connectors on the T3-4 and T4-4

All other virtual devices (such as virtual keyboard and virtual mouse) will continue to function, but will be limited to operating at the lower speed.

Oracle VM Server for SPARC Direct I/O Support

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

For an updated list of PCIe cards that support the direct I/O feature, refer to:

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

Not Oracle Certified DIMM Warning Message (CR 7034912)

After installing supported optional component DIMMs shipped from the Oracle Corporation or from a certified Oracle reseller, or after replacing a failed DIMM with a field-replaceable unit (FRU) DIMM, you might see warning messages similar to the following:

[CPU 0:0:0] WARNING: /SYS/MB/CMP0/BOB0/CH0/D0: Not Oracle Certified

The system displays these messages because optional component and FRU DIMMS have not been marked as certified. Oracle certifies only DIMMs that ship installed in a system from the factory. Although Oracle has not certified these DIMMs, they are still supported. You can safely ignore these warning messages.

Workaround: Install the latest system firmware patch. This issue was corrected in system firmware version 8.1.4.d.

Custom nvalias Settings Will Not Change During a System Reconfiguration

If you use the nvalias OBP command to make custom system settings, you must update these settings if the system reconfigures itself after a hardware failure.

For example, if the system experiences a hardware failure such as a failed CMP, the system will reconfigure the I/O device paths during the next reboot. If you set a custom device path to a boot disk using the nvalias command, the system will not reconfigure the custom device path and the server will not boot the operating system. You must rediscover the device path to the boot disk and update the nvalias setting accordingly.

SPARC T3 Series Servers Do Not Support Sun Type 6 Keyboards

Sun Type 6 keyboards cannot be used with SPARC T3 series servers.

Large Third-Party PCIe Cards Are Not Supported in PCIe Slot 8

A capacitor installed on the SPARC T3-2 server motherboard extends into the PCIe slot 8 about 1.60 mm (0.06 in.) higher than PCI Express specifications permit. You cannot install large third-party PCIe cards (for example, certain quad-Ethernet PCIe cards) into slot 8, since the capacitor will interfere with the PCIe card installation.

Workaround: Only install smaller PCIe cards into PCIe slot 8.

Front-Panel Video Port Does Not Support Resolutions Greater Than 1024 x 768 (CR 7021609)

The SPARC T3-2 server contains two video HD-15 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 T3 Series Servers Administration Guide and the fbconfig(1M) man page for instructions on using a local graphics monitor.

Cannot Plumb Sun Quad GbE x8 PCIe Low Profile Adapter in PCIe Slot 0 When More Than Five Are Installed (CR 6993897)

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.

Blue Ready-to-Remove LED Might Not Illuminate After Being Prepared for Removal Using the MegaRAID Storage Manager (CR 6929361)

When using the MegaRAID Storage Manager (MSM) software to prepare a drive for removal, the MSM software will report that the drive is ready to remove, but the drive's blue ready-to-remove LED might only illuminate briefly, or not illuminate at all.

Workaround: Once the MSM software reports that the drive is ready to remove, it is safe to remove the disk. If you need to locate the selected drive, use the MSM locate function, the MegaCLI command-line utility, or the WebBIOS configuration utility.

Refer to the MSM documentation for more information.

MegaRAID Storage Manager Does Not Discover Sun Storage 6 Gb SAS PCIe RAID HBA, Internal (CR 6971789)

The MegaRAID Storage Manager (MSM) software cannot discover, configure, or monitor an installed Sun Storage 6 Gb SAS PCIe RAID HBA, Internal.

Workaround: Use the MegaCLI command-line utility to discover, configure, and monitor the Sun Storage 6 Gb SAS PCIe RAID HBA, Internal.

Installing Sun Storage 6 Gb SAS PCIe RAID HBA, Internal, Disables the DVD Drive

After installing a Sun Storage 6 Gb SAS PCIe RAID HBA into the server, you will no longer be able to use the front-panel DVD drive.

Inside the SPARC T3-2 server, up to six drives and the optional DVD drive connect to the same hard disk drive backplane. Two internal cables connect the hard disk drive backplane to the motherboard assembly.

When installing the Sun Storage 6 Gb SAS PCIe RAID HBA, you must use these same cables to connect the HBA ports to the hard disk drive backplane. (In order to support RAID 5, both cables must be connected.)

• Remove the SAS cable from the motherboard port labeled DISK0-3 and connect it to the top HBA port labeled PORT 0-3.

• Remove the SAS cable from the motherboard port labeled DISK4-7 and connect it to the bottom HBA port labeled PORT 4-7.

  ---

  Note - The HBA does not provide the SATA data signals required by the front-panel DVD drive, so you will no longer be able to use the DVD drive.

  ---

Refer to the Sun Storage 6 Gb SAS PCIe RAID HBA, Internal Installation Guide For HBA Models SGX-SAS6-R-INT-Z and SG-SAS6-R-INT-Z for additional installation instructions:

http://www.oracle.com/pls/topic/lookup?ctx=E19221-01

Workaround:

To access a DVD drive after installing the Sun Storage 6 Gb SAS PCIe RAID HBA:

• Connect an external USB DVD drive to one of the four USB ports on the server.

• Use the Oracle ILOM Remote Console to control a networked DVD drive remotely.

  The Oracle ILOM Remote Console is a Java application that enables you to redirect and control the keyboard, video, mouse, and storage (KVMS) devices of a host server remotely. Refer to the Oracle ILOM documentation for instructions on using the Oracle ILOM Remote Console.

Sun Storage 6 Gb SAS PCIe RAID HBA, Internal, Must Be Installed In PCIe2 Slot 0 (CR 6982358)

If you plan to install the Sun Storage 6 Gb SAS PCIe RAID HBA, Internal, into the server, you must install the card in PCIe2 slot 0 (the slot closest to the power supplies). Installing this card into any other PCIe2 slot is not supported.

TCP Performance Lags When Using Three or More Ports on Multiple Sun Dual 10 GbE SFP+ PCIe Cards (CR 6943558)

Excessive packet loss has been seen when three or more ports are used across multiple Sun Dual 10GbE SFP+ PCIe cards. As a result, the transmit and receive performance was significantly degraded. When only two ports are used, packet loss is minimal and transmit/receive performance is as expected.

Workaround: Use one of the following procedures to enable flow control for the interfaces. Enabling flow control will greatly reduce packet loss and improve performance.

Enable Flow Control (With a System Reboot)

1. Add the following lines in the /kernel/drv/ixgbe.conf file:

   fm_capable = 0;
   flow_control = 3;
   tx_queue_number = 2;
   rx_queue_number = 6;
   intr_throttling = 1000;

2. Reboot the system to make these driver changes take effect.

Enable Flow Control (Without a System Reboot)

1. Add the following lines in the /kernel/drv/ixgbe.conf file:

   fm_capable = 0;
   flow_control = 3;
   tx_queue_number = 2;
   rx_queue_number = 6;
   intr_throttling = 1000;

2. Unplumb all the ixgbe interfaces.
3. Type the update_drv ixgbe command:

   # update_drv ixgbe

4. Plumb all the ixgbe interfaces.

PARALLEL_BOOT/HOST_LAST_POWER_STATE=enabled Failed, Unexpected Power State (Off) After AC Cycle (CR 6994047)

When HOST_LAST_POWER_STATE is set to enabled and then the system goes through an AC power cycle, the host sometimes is shown as OFF when the power up operation completes. This status information might be false.

Recovery: Power cycle the system again to clear the false status information.

Server Panics When Booting From a USB Thumbdrive Attached to the Front USB Ports (CR 6983185)

When attempting to boot a USB thumbdrive (portable USB flash drive) inserted in one of the front USB ports (USB2 or USB3), the server will panic and fail to boot.

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

Copper QSFP Cables Not Supported (CR 6941888)

The SPARC T3-2 Server 10 Gb Network Module does not support copper QSFP cables. The network module supports only optical QSFP transceiver modules and cables.

When Two Or More 10 Gb Network Module Devices Are Plumbed, Memory DR Remove Operations Might Hang (CR 6983286)

Plumbing two or more SPARC T3-2 Server 10 Gb Network Module devices in a domain creates a condition in the Oracle Solaris kernel that can cause a dynamic reconfiguration (DR) operation to hang when memory is being removed from the domain.

Workaround: If you plan on using memory DR remove operations, do not plumb more than one SPARC T3-2 Server 10 Gb Network Module device.

Recovery: If a DR operation hangs, reboot the domain to clear it.

Cannot Initiate Two Consecutive probe-scsi-all Commands in Systems With Sun StorageTek 8 Gb FC PCIe HBAs (CR 6983959)

On systems containing one or more Sun StorageTek 8 Gb FC PCIe HBAs, Emulex, you cannot use the OpenBoot PROM (OBP) probe-scsi-all command more than once. You must reset the system using the OBP reset command before you can use the probe-scsi-all command again.

The first execution of the probe-scsi-all command will run successfully. If the command is issued again before resetting the system using the OBP reset command, the second probe-scsi-all execution will fail, with an error message similar to the following example:

FCode Version 1.00.54, MPT Version 2.00, Firmware Version 5.00.17.00
Target 9
  Unit 0   Disk   HITACHI  H103030SCSUN300G A2A8    585937500 Blocks, 300 GB
  SASDeviceName 5000cca00ab4403c  SASAddress 5000cca00ab4403d  PhyNum 0
Target a
  Unit 0   Disk   HITACHI  H103030SCSUN300G A2A8    585937500 Blocks, 300 GB
  SASDeviceName 5000cca00ab2551c  SASAddress 5000cca00ab2551d  PhyNum 1
[...]
/pci@600/pci@2/pci@0/pci@5/pci@0/pci@3/SUNW,emlxs@0,1
Cannot Init Link.
/pci@600/pci@2/pci@0/pci@5/pci@0/pci@3/SUNW,emlxs@0
Cannot Init Link.
[...]
Cannot initialize port.
READ_LA Failed.

Workaround: Reset the system using the OBP reset command between two probe-scsi-all executions.

Installing Multiple Sun Flash Accelerator F20 PCIe Cards Causes Errors On First Boot (CR 6988352)

After installing multiple Sun Flash Accelerator F20 PCIe cards, the server will display the following error messages when you boot the server for the first time:

date machinename scsi: [ID 243001 kern.info] smp: smp_do_attach: failed to allocate softstate, device unit-address @w508002000000377f
date machinename scsi: [ID 243001 kern.info] smp: smp_attach(), device unit-address @w508002000000377f failed
date machinename scsi: [ID 243001 kern.warning] WARNING: /pci@400/pci@2/pci@0/pci@0/LSILogic,sas@0 (mpt2):
date machinename failed to configure smp w508002000000377f

You can safely ignore these error messages.

Workaround: Reboot the server once more, and you will no longer see these error messages.

Error Messages Not Retained After UE and CE Memory Failures (CR 6990058)

If your server's memory experiences a uncorrectable error (UE) followed by a correctable error (CE), the correct error messages will not be generated and they will not be retained by the service processor. You will not be able to diagnose the memory problem.

Workaround: Reboot the system. If memory problems persist, contact your service representative for assistance.

Replace Faulty DIMMs With Uncorrectable Errors (UEs) As Soon As Possible (CR 6996144)

If a DIMM has an uncorrectable error (UE), the server will generate a fault.memory.bank error that labels a DIMM as faulty. You can view this error using the Oracle ILOM show faulty command or the fmdump -v command.

If a DIMM in your system contains a persistent uncorrectable error (an error that continually occurs even after multiple reboots), replace this DIMM as soon as possible to avoid any server downtime.

Workaround: Instead of scheduling downtime to replace the faulty DIMMs, replace the faulty DIMMs as soon as possible. Contact your service representative for assistance.

create-raid10-volume Command Fails to Create a RAID 10 Volume on a Sun Storage 6 Gb SAS PCIe HBA (CR 6943131)

The Sun Storage 6 Gb SAS PCIe HBA supports RAID types 0, 1, and 10. When attempting to create a RAID 10 volume, the create-raid10-volume OpenBoot PROM (OBP) command will fail. In the OBP environment, there is no command that allows you to create a RAID 10 volume.

However, you can use the create-raid1e-volume OBP command to create a RAID 1E volume, which is an enhanced RAID 1 volume that includes mirroring and striping.

Workaround: Create a RAID 1E volume using the OBP create-raid1e-volume command.

Cannot Use GbE Ports of a Sun Quad GbE x8 PCIe Low Profile Adapter Installed in PCIe Slot 0 (CR 6993897)

When six or more than Sun Quad GbE x8 PCIe Low Profile adapters are installed in the server, you will not be able to use the GbE ports of the Sun Quad GbE x8 PCIe Low Profile adapter installed in PCIe slot 0. For example, if you install six Sun Quad GbE x8 PCIe Low Profile adapters into PCIe slots 0 to 5, you will not be able to plumb the GbE interfaces of the adapter installed in Slot 0.

Workaround: Do not install a Sun Quad GbE x8 PCIe Low Profile adapter into PCIe slot 0. The server supports up to nine Sun Quad GbE x8 PCIe Low Profile adapters installed in PCIe slots 1 to 9.