topic Re: rx7640 showing only one CPU! in Integrity Servers

rx7640 showing only one CPU!

wimaxpole — Tue, 04 Sep 2012 08:27:52 GMT

Hello,

I have two rx7640 running hp-ux. Node 2 is showing only one CPU (two cores) in hp-ux (machinfo) while Node1 is showing TWO CPUs (four cores).

When I checked in MP, I see only cell board #1 intalled and TWO cpus on them. Therefore I should get four CPUs in hp-ux as the other node. Is there any other place to check? Please help...

MACHINFO

Node 1

$ machinfo
CPU info:
  2 Intel(R) Itanium 2 9000 series processors (1.6 GHz, 18 MB)
          533 MT/s bus, CPU version C2
          4 logical processors (2 per socket)

Memory: 8123 MB (7.93 GB)
   Release:   HP-UX B.11.31
   Version:   U (unlimited-user license)
   Machine:   ia64
   
------------------------------------------------------------


Node 2

$ machinfo
CPU info:
  1 Intel(R) Itanium 2 9000 series processor (1.6 GHz, 18 MB)
          533 MT/s bus, CPU version C2
          2 logical processors (2 per socket)

Memory: 8123 MB (7.93 GB)

Firmware info:
   Firmware revision:  9.022
   FP SWA driver revision: 1.18
   IPMI is supported on this system.
   BMC firmware revision: 3.01

Platform info:
   Model:                  "ia64 hp server rx7640"
  
OS info:
   Release:   HP-UX B.11.31

On Node 1

MP login: Admin
MP password:

(c)Copyright 2000-2006 Hewlett-Packard Co., All Rights Reserved.

                             Welcome to
                  rx7640's Management Processor

    MP MAIN MENU:

         CO: Consoles
        VFP: Virtual Front Panel
         CM: Command Menu
         CL: Console Logs
         SL: Show Event Logs
         FW: Firmware Update
         HE: Help
          X: Exit Connection

MP> cm

                Enter HE to get a list of available commands

                      (Use ^B to return to main menu.)

MP:CM> du

The following MP bus devices were found:
+---+----+----+-----+-----+-------+-----+
|   |    |    |     |     |       |     |
|   |    |LAN\| Sys |     | IO   |     |
|Cab| MP |SCSI|Bkpln|Cells|Chassis| BPS |
| # |M S|0 1|     | 0 1 | 0   1 | 0 1 |
+---+----+----+-----+-----+-------+-----+
| 0 |*   |   *| * |   * | *   * | * * |
+---+----+----+-----+-----+-------+-----+

MP:CM> de

Display status of the selected MP entity (for use by trained personnel only)

    B - BPS (Bulk Power Supplies)
    U - CLU (Cabinet Utilities: Fans, Intrusion, Clock's etc.)
    A - PACI (Partition Console Interface)
    G - MP   (Management Processor)
    P - PM   (Power Management)
    H - Cell Board Controller (PDHC)
        Select device: h
    Enter cell number: 1

Cell Controller (PDHC) status. Cell 1
FW Revision     : B.023.003.040 built SUN AUG 05 21:53:18 2007
HW Revision     : Cell: 0x5, PDH Riser: 0x2
Bootloader Rev : 005.003.001
SBS Revision    : Skyline: 01.18, Abajo0: 01.05, Abajo1: 01.05
System FW Flags : Sys Flash Override: disabled (0x14)
                  Sys Flash Write Enable: disabled

PDHC state      : 0x0f (err bib SMG PWR)
Cell Attn Led   : off

Power Status    : 0x7f (12VSTBY RDY EN PWR vflt tflt fanflt)

Voltage Margin : 0x0000 (nominal)

LED State       : 0x0e (BIB SMG FAB heartbeat)

Complex Compatibility    : C (0x43)
Partition Compatibility : Cell: D (0x44), CPU: G (0x47)

IO Connection Status     : 0x01 (Connection OK)
IO Chassis Phys Location : 0x01 (cabinet=0, PCI Backplane=0, PCI Domain=1)
Core Cell Number         : 0x81 (cabinet=0, cell=1, Valid)

Temp Fault Status        : 0x00 (cpu0 cpu1 cpu2 cpu3 mmu cell)
CPU 0 Temp               : 50 deg C
CPU 1 Temp               : n/a
CPU 2 Temp               : 53 deg C
CPU 3 Temp               : n/a
MMU Temp                 : 29 deg C
Cell Board Temp          : 28 deg C

Fan Status               : 0x00cc (No Fault)
Local I2C Bus Status     : 0x00 (OK)

MP:CM>

***********************************************

On Node 2

MP login: Admin
MP password:

(c)Copyright 2000-2006 Hewlett-Packard Co., All Rights Reserved.

                             Welcome to
                  rx7640's Management Processor

    MP MAIN MENU:

         CO: Consoles
        VFP: Virtual Front Panel
         CM: Command Menu
         CL: Console Logs
         SL: Show Event Logs
         FW: Firmware Update
         HE: Help
          X: Exit Connection

MP> du

Please try again.

    MP MAIN MENU:

         CO: Consoles
        VFP: Virtual Front Panel
         CM: Command Menu
         CL: Console Logs
         SL: Show Event Logs
         FW: Firmware Update
         HE: Help
          X: Exit Connection

MP> cm

                Enter HE to get a list of available commands

                      (Use ^B to return to main menu.)

MP:CM> du

The following MP bus devices were found:
+---+----+----+-----+-----+-------+-----+
|   |    |    |     |     |       |     |
|   |    |LAN\| Sys |     | IO   |     |
|Cab| MP |SCSI|Bkpln|Cells|Chassis| BPS |
| # |M S|0 1|     | 0 1 | 0   1 | 0 1 |
+---+----+----+-----+-----+-------+-----+
| 0 |*   |   *| * |   * | *   * | * * |
+---+----+----+-----+-----+-------+-----+

MP:CM> CM

Unknown Command. Type HE for a list of commands.

MP:CM> cm

Unknown Command. Type HE for a list of commands.

MP:CM> de

Display status of the selected MP entity (for use by trained personnel only)

    B - BPS (Bulk Power Supplies)
    U - CLU (Cabinet Utilities: Fans, Intrusion, Clock's etc.)
    A - PACI (Partition Console Interface)
    G - MP   (Management Processor)
    P - PM   (Power Management)
    H - Cell Board Controller (PDHC)
        Select device: h
    Enter cell number: 1

Cell Controller (PDHC) status. Cell 1
FW Revision     : B.023.003.040 built SUN AUG 05 21:53:18 2007
HW Revision     : Cell: 0x5, PDH Riser: 0x2
Bootloader Rev : 005.003.001
SBS Revision    : Skyline: 01.18, Abajo0: 01.05, Abajo1: 01.05
System FW Flags : Sys Flash Override: disabled (0x14)
                  Sys Flash Write Enable: disabled

PDHC state      : 0x0f (err bib SMG PWR)
Cell Attn Led   : off

Power Status    : 0x7f (12VSTBY RDY EN PWR vflt tflt fanflt)

Voltage Margin : 0x0000 (nominal)

LED State       : 0x0f (BIB SMG FAB HEARTBEAT)

Complex Compatibility    : C (0x43)
Partition Compatibility : Cell: D (0x44), CPU: G (0x47)

IO Connection Status     : 0x01 (Connection OK)
IO Chassis Phys Location : 0x01 (cabinet=0, PCI Backplane=0, PCI Domain=1)
Core Cell Number         : 0x81 (cabinet=0, cell=1, Valid)

Temp Fault Status        : 0x00 (cpu0 cpu1 cpu2 cpu3 mmu cell)
CPU 0 Temp               : 47 deg C
CPU 1 Temp               : n/a
CPU 2 Temp               : 39 deg C
CPU 3 Temp               : n/a
MMU Temp                 : 28 deg C
Cell Board Temp          : 27 deg C

Fan Status               : 0x00cc (No Fault)
Local I2C Bus Status     : 0x00 (OK)

MP:CM>

Please help to resolve..

Re: rx7640 showing only one CPU!

S_Logan — Tue, 04 Sep 2012 14:29:43 GMT

Hi ,

According to the DU output , We can see Both Node 1 and 2 has 2 Physical processors, But in Node 2 shows only one Physical processor in Machinfo.

Please paste info cpu output from EFI and see any CPU deconfigured messages in MP Logs(SEL and FPL)

Please update if the system faced any reboot or any hung issue in recent times?

HTH,

Surendar

Was the post useful?

Say Thank you by Clicking the WHITE KUDOS! Star.

For HP Guided Troubleshooting; http://www.hp.com/support/hpgt

Re: rx7640 showing only one CPU!

Torsten. — Tue, 04 Sep 2012 17:09:56 GMT

CPU could be disabled or just not visible for any reason.

Is it a vPar by chance?

# vparstatus

or even icap?

# icapstatus

# parstatus

Try to format the output or just attach.

Re: rx7640 showing only one CPU!

wimaxpole — Wed, 05 Sep 2012 06:49:50 GMT

Thanks, Is it possible to go to EFI shell on running machine? please explain how.

Re: rx7640 showing only one CPU!

Torsten. — Wed, 05 Sep 2012 07:01:54 GMT

No, during reboot only.

Re: rx7640 showing only one CPU!

wimaxpole — Wed, 05 Sep 2012 08:51:00 GMT

Thanks for your help..

Please find the attached output. There are two inactive cores on node2 . How can I get it working in hp-ux?

On both nodes;

#vparstatus
sh: vparstatus: not found.

Re: rx7640 showing only one CPU!

Torsten. — Wed, 05 Sep 2012 08:51:59 GMT

[Cell]
                        CPU     Memory                                Use
                        OK/     (GB)                          Core    On
Hardware   Actual       Deconf/ OK/                           Cell    Next Par
Location   Usage        Max     Deconf    Connected To        Capable Boot Num
========== ============ ======= ========= =================== ======= ==== ===
cab0,cell0 Absent *    -       -         -                   -       -    -
cab0,cell1 Active Core 2/2/8   8.0/0.0   cab0,bay0,chassis1 yes     yes 0

So we know 1 CPU (2 cores) are disabled.

Try to enable hem from EFI and see what happens.

From EFI do

Shell> cpuconfig

PROCESSOR MODULE INFORMATION

           # of               L3      L4      Family/
   CPU     Logical            Cache   Cache   Model         Processor
   Module CPUs     Speed     Size    Size    (hex.)   Rev State
   ------ ------- -------- ------ ------ ------- --- ------------
     0        2      1.6 GHz   12 MB    None   20/00    C2        Active
     1        2      1.6 GHz   12 MB    None   20/00    C2        Active
     2        2      1.6 GHz    None    None   20/00    C2     SW Deconf
     3        2      1.6 GHz   12 MB    None   20/00    C2        Active

CPU threads are turned off.

Shell> help cpuconfig
Deconfigure or reconfigure cpus

Re: rx7640 showing only one CPU!

S_Logan — Wed, 05 Sep 2012 13:47:35 GMT

Hi,

The c

puconfig command displays the config/deconfig state of processors in the system and allows the user to configure or reconfigure processors.

Syntax
cpuconfig <cpu> <on|off>

Parameters
<cpu>: specifies a processor
<on|off>: state to set the processor

To enable or disable Hyper-Threading, use the EFI cpuconfig threads on or cpuconfig threads off command. For more information, enter help cpuconfig at the EFI Shell prompt or see the appropriate hardware documentation.

HTH,

Surendar

Was the post useful?

Say Thank you by Clicking the WHITE KUDOS! Star.

For HP Guided Troubleshooting; http://www.hp.com/support/hpgt

Re: rx7640 showing only one CPU!

S_Logan — Wed, 05 Sep 2012 13:49:42 GMT

Hi ,

For More infromation on HP Integrity Servers - EFI and EFI/POSSE Commands:

http://h20000.www2.hp.com/bizsupport/TechSupport/Document.jsp?lang=en&cc=us&taskId=120&prodSeriesId=447681&prodTypeId=15351&objectID=c00273667

HTH,

Surendar

Was the post useful?

Say Thank you by Clicking the WHITE KUDOS! Star.

For HP Guided Troubleshooting; http://www.hp.com/support/hpgt

Re: rx7640 showing only one CPU!

wimaxpole — Mon, 10 Sep 2012 06:20:48 GMT

Thanks...

I need to get the system reboot to try in EFI shell in the weekend and will update..

Re: rx7640 showing only one CPU!

wimaxpole — Fri, 14 Sep 2012 08:26:00 GMT

One more question before I reboot. In the syslog I am getting an error log like below. Will the command mentioned in the log is usefull?

node2 EMS [9299]: ------ EMS Event Notification ------ Value: "MAJORWARNING (3)" for Resource: "/system/events/ipmi_fpl/ipmi_fpl" (Threshold: >= " 3") Execute the following command to obtain event details: /opt/resmon/bin/resdata -R 609419266 -r /system/events/ipmi_fpl/ipmi_fpl -n 609419265 -a

Re: rx7640 showing only one CPU!

S_Logan — Fri, 14 Sep 2012 09:36:57 GMT

Hi ,

Please check this thread for more infromation:

http://h30499.www3.hp.com/t5/General/If-probelm-is-serious/td-p/4273051#.UFL6No0gfCc

HTH,

Surendar

Was the post useful?

Say Thank you by Clicking the WHITE KUDOS! Star.

For HP Guided Troubleshooting; http://www.hp.com/support/hpgt

Re: rx7640 showing only one CPU!

wimaxpole — Sun, 16 Sep 2012 13:20:37 GMT

Today I had a chance to check MP logs but not able to reboot the server. Is it because of the error the other CPU is not visible to OS?

[node2] MP:VWR (<cr>,<sp>,+,-,?,F,L,J,D,K,R,T,A,C,U,^B) > [node2] -
Log Entry 6241:    05/05/2012 04:22:31
Alert level 2:  Informational
Keyword:  CELL_INTGRT_POLICY
The Cell Integration Policy is being reported
Reporting Entity:  System Firmware located in cabinet 0, slot 1, cpu 0
Actual Data:  0x0000000000000000
0x43800efe10e005b2 0x0000000000000000
0x4b000efe10e005b3 0x010000004fa4ab07

Log Entry 6240:    05/05/2012 04:22:31
Alert level 3:  Warning
Keyword:  CELL_HW_DEGRADED
A dimm or CPU has been deconfigured or failed testing
Reporting Entity:  System Firmware located in cabinet 0, slot 1, cpu 0
0x6b000efd10e005b1 0x010000004fa4ab07

Log Entry 6264:    07/10/2012 13:46:28
Alert level 3:  Warning
Keyword:  INLET_OVERTEMP_LO
Ambient Air Sensor Overtemp Warning
Reporting Entity:  Power Monitor located in cabinet 0
0x6b000b0c00e005d7 0x010000004ffc3234

Re: rx7640 showing only one CPU!

S_Logan — Tue, 18 Sep 2012 09:02:10 GMT

Hi,

I could see the error logged at 5th May..

Log Entry 6240: 05/05/2012 04:22:31 <<<<<
Alert level 3: Warning
Keyword: CELL_HW_DEGRADED
A dimm or CPU has been deconfigured or failed testing
Reporting Entity: System Firmware located in cabinet 0, slot 1, cpu 0
0x6b000efd10e005b1 0x010000004fa4ab07

Is this system showing CPU issue from that day (5th May)?

HTH,

Surendar

Was the post useful?

Say Thank you by Clicking the WHITE KUDOS! Star.

For HP Guided Troubleshooting; http://www.hp.com/support/hpgt

Re: rx7640 showing only one CPU!

wimaxpole — Mon, 24 Sep 2012 05:27:29 GMT

Yes, this node is showing only one CPU (two cores) and this error is still there till last reboot.

Re: rx7640 showing only one CPU!

S_Logan — Mon, 24 Sep 2012 17:55:12 GMT

Hi,

If you get a downtime of this server, reboot the server and go in to the EFI shell and run the following commands to confirm the CPU Deconfiguration:

EFI Shell>info cpu

EFI Shell >cpuconfig

If you see any CPU deconfigured state. Please log a Hardware ticket with HP for further assistance.

HTH,

Surendar

Was the post useful?

Say Thank you by Clicking the WHITE KUDOS! Star.

For HP Guided Troubleshooting; http://www.hp.com/support/hpgt

Re: errors showing only one CPU!

wimaxpole — Sun, 09 Feb 2014 11:02:32 GMT

Thanks for all..

It was due the CPU cooling FAN which failed during the first few minutes of power up. I replaced the FAN after few tries and system is working till now.

Bye..