System Error Question
Padiyath Sreekumaran <[email protected]> Sun, 11 Oct 2009 20:37:53 +0200
| Newsgroups | gmane.os.tru64.managers |
|---|---|
| Message-ID | <[email protected]> |
Hello, Hello, I donto know how many users still have Alpha machines with Tru64 OS. The machine is having 4 CPU's. When I execute the command=20 #psrinfo -v =20 =20 Status of processor 0 as of: 10/10/09 20:32:00 Processor has been on-line since 10/05/2009 14:10:35 The alpha EV6 (21264) processor operates at 500 MHz, has a cache size of 4194304 bytes, and has an alpha internal floating point processor. =20 Status of processor 1 as of: 10/10/09 20:32:00 Processor has been off-line since 10/05/2009 14:10:36 The alpha EV6 (21264) processor operates at 500 MHz, has a cache size of 4194304 bytes, and has an alpha internal floating point processor. =20 Status of processor 3 as of: 10/10/09 20:32:00 Processor has been off-line since 10/05/2009 14:10:36 The alpha EV6 (21264) processor operates at 500 MHz, has a cache size of 4194304 bytes, and has an alpha internal floating point processor.=20 In "messages" file I see the following: Sep 28 08:59:16 alpha vmunix: Machine Check Processor Fatal Abort Sep 28 08:59:16 alpha vmunix: Machine Check Processor Fatal Abort Sep 28 08:59:16 alpha vmunix: Machine check code =3D 0x100000098 Sep 28 08:59:16 alpha vmunix: Machine check code =3D 0x100000098 Sep 28 08:59:16 alpha vmunix: Ibox Status =3D 0000000000000000 Sep 28 08:59:16 alpha vmunix: Ibox Status =3D 0000000000000000 Sep 28 08:59:16 alpha vmunix: Dcache Status =3D 0000000000000008 Sep 28 08:59:16 alpha vmunix: Dcache Status =3D 0000000000000008 Sep 28 08:59:16 alpha vmunix: Cbox Address =3D 0000000035621c00 Sep 28 08:59:16 alpha vmunix: Cbox Address =3D 0000000049a7cd80 Sep 28 08:59:16 alpha vmunix: Fill Syndrome 1 =3D 000000000000000c Sep 28 08:59:16 alpha vmunix: Fill Syndrome 1 =3D 0000000000000029 Sep 28 08:59:16 alpha vmunix: Fill Syndrome 0 =3D 000000000000000c Sep 28 08:59:16 alpha vmunix: Fill Syndrome 0 =3D 0000000000000085 Sep 28 08:59:16 alpha vmunix: Cbox Status =3D 0000000000000013 Sep 28 08:59:16 alpha vmunix: Cbox Status =3D 0000000000000013 Sep 28 08:59:16 alpha vmunix: EV6 captured status of Bcache mode = =3D 0000000000000002 Sep 28 08:59:16 alpha vmunix: EV6 captured status of Bcache mode = =3D 0000000000000002 Sep 28 08:59:16 alpha vmunix: EV6 Exception Address =3D 0000000120320fc4 Sep 28 08:59:16 alpha vmunix: EV6 Exception Address =3D 000000012011fbc4 Sep 28 08:59:17 alpha vmunix: EV6 Interrupt Enablement and Current Processor mode =3D 0000007ee0000008 Sep 28 08:59:17 alpha vmunix: EV6 Interrupt Enablement and Current Processor mode =3D 0000007ee0000008 Sep 28 08:59:17 alpha vmunix: EV6 Interrupt Summary Register = =3D 0000000080000000 Sep 28 08:59:17 alpha vmunix: EV6 Interrupt Summary Register = =3D 0000000080000000 Sep 28 08:59:17 alpha vmunix: EV6 TBmiss or Fault status =3D 0000000000000230 Sep 28 08:59:17 alpha vmunix: EV6 TBmiss or Fault status =3D 0000000000000230 Sep 28 08:59:17 alpha vmunix: EV6 PAL Base Address =3D 0000000000018000 Sep 28 08:59:17 alpha vmunix: EV6 PAL Base Address =3D 0000000000018000 Sep 28 08:59:17 alpha vmunix: EV6 Ibox control =3D fffffe0006304096 Sep 28 08:59:17 alpha vmunix: EV6 Ibox control =3D fffffe0006304096 Sep 28 08:59:17 alpha vmunix: EV6 Ibox Process_context =3D 00000a8000000004 Sep 28 08:59:17 alpha vmunix: EV6 Ibox Process_context =3D 00007e0000000004 Sep 28 08:59:17 alpha vmunix: O/S Summary flag =3D 0000000000000004 Sep 28 08:59:17 alpha vmunix: O/S Summary flag =3D 0000000000000004 Sep 28 08:59:17 alpha vmunix: Cchip Base Address (phys) =3D 00000f01a0000000 Sep 28 08:59:17 alpha vmunix: Cchip Base Address (phys) = =3D 00000f01a0000000 Sep 28 08:59:17 alpha vmunix: Cchip Device Raw Interrupt Request = =3D 0000000000000000 Sep 28 08:59:17 alpha vmunix: Cchip Device Raw Interrupt Request = =3D 0000000000000000 Sep 28 08:59:17 alpha vmunix: DRIR Register Decode: 0000000000000000 Sep 28 08:59:17 alpha vmunix: DRIR Register Decode: 0000000000000000 Sep 28 08:59:17 alpha vmunix: PCI Device Interrupt Mask = =3D 0000000000000000 Sep 28 08:59:17 alpha vmunix: PCI Device Interrupt Mask = =3D 0000000000000000 Sep 28 08:59:17 alpha vmunix: Cchip Miscellaneous Register = =3D 0000000000000000 Sep 28 08:59:17 alpha vmunix: Cchip Miscellaneous Register = =3D 0000000000000000 Sep 28 08:59:17 alpha vmunix: Misc Register Decode: Sep 28 08:59:17 alpha vmunix: Misc Register Decode: Sep 28 08:59:17 alpha vmunix: Cchip Revision: 00 Sep 28 08:59:17 alpha vmunix: Cchip Revision: 00 Sep 28 08:59:17 alpha vmunix: ID of CPU performing read: 00 Sep 28 08:59:17 alpha vmunix: ID of CPU performing read: 00 Sep 28 08:59:17 alpha vmunix: Pchip 0 Base Address (phys) = =3D 00000f0180000000 Sep 28 08:59:17 alpha vmunix: Pchip 0 Base Address (phys) = =3D 00000f0180000000 Sep 28 08:59:17 alpha vmunix: Pchip 0 Error Register = =3D 0000000000000000 Sep 28 08:59:17 alpha vmunix: Pchip 0 Error Register = =3D 0000000000000000 Sep 28 08:59:17 alpha vmunix: Pchip Error Register Decode: Sep 28 08:59:17 alpha vmunix: Pchip Error Register Decode: Sep 28 08:59:17 alpha vmunix: PCI Xaction Start Address =3D 0000000000000000 =20 PCI Xaction Start Address =3D 0000000000000000 Sep 28 08:59:17 alpha vmunix: PCI Command: Sep 28 08:59:17 alpha vmunix: PCI Command: Interrupt Acknowledge Sep 28 08:59:17 alpha vmunix: Interrupt Acknowledge Sep 28 08:59:17 alpha vmunix: Pchip 1 Base Address (phys) = =3D 00000f0380000000 Sep 28 08:59:18 alpha vmunix: Pchip 1 Base Address (phys) = =3D 00000f0380000000 Sep 28 08:59:18 alpha vmunix: Pchip 1 Error Register = =3D 0000000000000000 Sep 28 08:59:18 alpha vmunix: Pchip 1 Error Register = =3D 0000000000000000 Sep 28 08:59:18 alpha vmunix: Pchip Error Register Decode: Sep 28 08:59:18 alpha vmunix: Pchip Error Register Decode: Sep 28 08:59:18 alpha vmunix: PCI Xaction Start Address = =3D 0000000000000000 PCI Xaction Start Address =3D 0000000000000000 Sep 28 08:59:18 alpha vmunix: PCI Command: Sep 28 08:59:18 alpha vmunix: PCI Command: Interrupt Acknowledge Sep 28 08:59:18 alpha vmunix: Interrupt Acknowledge Sep 28 08:59:18 alpha vmunix: CPU 1 is prevented from being rebooted. Sep 28 08:59:18 alpha vmunix: CPU 3 is prevented from being rebooted. Sep 28 08:59:18 alpha vmunix: The system must be reset or power cycled to clear this state. Sep 28 08:59:18 alpha vmunix: The system must be reset or power cycled to clear this state. Sep 28 08:59:18 alpha vmunix: panic (cpu 1): Processor Machine Check Sep 28 08:59:18 alpha vmunix: syncing disks... done Sep 28 08:59:18 alpha vmunix: Memory trolling not supported, cpu Major id 8, Minor id 7 Sep 28 08:59:18 alpha vmunix: Alpha boot: available memory from 0x5c66000 to 0xffff4000 Sep 28 08:59:18 alpha vmunix: Compaq Tru64 UNIX V5.1A (Rev. 1885); Sun Jan 4 16:15:44 MET 2004 Sep 28 08:59:18 alpha vmunix: physical memory =3D 4096.00 megabytes. Sep 28 08:59:18 alpha vmunix: available memory =3D 3998.87 megabytes. Sep 28 08:59:18 alpha vmunix: using 15674 buffers containing 122.45 megabytes of memory Sep 28 08:59:18 alpha vmunix: Master cpu at slot 0 Sep 28 08:59:18 alpha vmunix: The system must be reset or power cycled to clear this state. Sep 28 08:59:18 alpha vmunix: Sep 28 08:59:18 alpha vmunix: Firmware revision: 7.0-2 Sep 28 08:59:18 alpha vmunix: PALcode: UNIX version=20 I donot know whether this is a CPU problem or not. If this is a CPU problem=20 can I do the following? psrinfo -v shows that CPU2 is down because of some HW problems. CPU1 and CPU3 are off-line. The machine has become very slow since it works with only 1 cpu. My question is : Is there any command which I can use to take down CPU2 in boot prompt?=20 Can I run a unix command (like hwmgr -offline -name cpu2) in multiuser mode to take down cpu2?=20 Can I make CPUs 1 and 3 online after executing the above command and without physically removing cpu2?=20 Is it possible to run the machine without removing the problem cpu?=20 I will be very thankful if any one can help me in this problem. Thanks in advance, Kumar