SCSI error : return code = 0x10000

由於儲存光纖交換機重新做了配置，並儲存了配置資訊，導致所有連線此交換機的系統全部報錯：

Linux：

Jun 13 17:51:01 bhcx kernel: SCSI error : <1 0 1 1> return code = 0x10000
Jun 13 17:51:01 bhcx kernel: end_request: I/O error, dev sdg, sector 98990423
Jun 13 17:51:01 bhcx kernel: SCSI error : <1 0 1 1> return code = 0x10000
Jun 13 17:51:01 bhcx kernel: end_request: I/O error, dev sdg, sector 98990431
Jun 13 17:51:39 bhcx kernel: SCSI error : <1 0 1 1> return code = 0x10000
Jun 13 17:51:39 bhcx kernel: end_request: I/O error, dev sdg, sector 40687935
Jun 13 17:51:39 bhcx kernel: SCSI error : <1 0 1 1> return code = 0x10000
Jun 13 17:51:39 bhcx kernel: end_request: I/O error, dev sdg, sector 91079703
Jun 13 17:51:39 bhcx kernel: SCSI error : <1 0 1 1> return code = 0x10000
Jun 13 17:51:39 bhcx kernel: end_request: I/O error, dev sdg, sector 81053039
Jun 13 17:51:39 bhcx kernel: SCSI error : <1 0 1 1> return code = 0x10000
Jun 13 17:51:39 bhcx kernel: end_request: I/O error, dev sdg, sector 142509495
Jun 13 17:51:39 bhcx kernel: SCSI error : <1 0 1 1> return code = 0x10000
Jun 13 17:51:39 bhcx kernel: end_request: I/O error, dev sdg, sector 142513847
Jun 13 17:51:39 bhcx kernel: SCSI error : <1 0 1 1> return code = 0x10000
Jun 13 17:51:39 bhcx kernel: end_request: I/O error, dev sdg, sector 94970431
Jun 13 17:51:39 bhcx kernel: SCSI error : <1 0 1 1> return code = 0x10000
Jun 13 17:51:39 bhcx kernel: end_request: I/O error, dev sdg, sector 80519335
Jun 13 17:51:39 bhcx kernel: qla2xxx 0000:41:00.1: qla2xxx_eh_abort: cmd already done sp=0000000000000000 timeout=0x1e
Jun 13 17:51:39 bhcx last message repeated 4 times
Jun 13 17:51:39 bhcx kernel: qla2xxx 0000:41:00.1: scsi(1:0:1:1): DEVICE_RESET cmd=0000010278fb25c0 jiffies = 0x187f85453, timeout=1e, dpc_flags=0, status=10000 allowed=80 ha=000001022b93c3c8 vis_ha=000001022b93c3c8.
Jun 13 17:52:01 bhcx kernel: qla2xxx 0000:41:00.1: scsi(1:0:1:1): DEVICE RESET SUCCEEDED.

HP-UX：

Jun 13 17:48:43 wandabh1 vmunix:
Jun 13 17:48:43 wandabh1 vmunix: SCSI: Async write error -- dev: b 31 0x040100, errno: 126, resid: 8192,
Jun 13 17:48:43 wandabh1 vmunix: blkno: 70869464, sectno: 141738928, offset: 72570331136, bcount: 8192.
Jun 13 17:48:43 wandabh1 vmunix: blkno: 70869472, sectno: 141738944, offset: 72570339328, bcount: 8192.
Jun 13 17:48:43 wandabh1 vmunix: blkno: 39087680, sectno: 78175360, offset: 40025784320, bcount: 8192.
Jun 13 17:48:43 wandabh1 vmunix: blkno: 28106256, sectno: 56212512, offset: 28780806144, bcount: 8192.
Jun 13 17:48:43 wandabh1 vmunix: blkno: 28106264, sectno: 56212528, offset: 28780814336, bcount: 8192.
Jun 13 17:48:43 wandabh1 vmunix: blkno: 6204168, sectno: 12408336, offset: 6353068032, bcount: 8192.
Jun 13 17:48:43 wandabh1 vmunix: blkno: 6204192, sectno: 12408384, offset: 6353092608, bcount: 8192.
Jun 13 17:48:43 wandabh1 vmunix: blkno: 6204176, sectno: 12408352, offset: 6353076224, bcount: 8192.
Jun 13 17:48:43 wandabh1 vmunix: SCSI: Write error -- dev: b 31 0x040100, errno: 126, resid: 1024,
Jun 13 17:48:43 wandabh1 vmunix: SCSI: Async write error -- dev: b 31 0x040100, errno: 126, resid: 8192,
Jun 13 17:48:43 wandabh1 above message repeats 7 times
Jun 13 17:48:43 wandabh1 vmunix: blkno: 19106, sectno: 38212, offset: 19564544, bcount: 1024.
Jun 13 17:48:43 wandabh1 vmunix: SCSI: Write error -- dev: b 31 0x040100, errno: 126, resid: 8192,
Jun 13 17:48:43 wandabh1 vmunix: blkno: 46888, sectno: 93776, offset: 48013312, bcount: 8192.
Jun 13 17:48:43 wandabh1 vmunix: blkno: 40024, sectno: 80048, offset: 40984576, bcount: 8192.
Jun 13 17:48:43 wandabh1 vmunix: SCSI: Write error -- dev: b 31 0x040100, errno: 126, resid: 1024,
Jun 13 17:48:43 wandabh1 vmunix: SCSI: Write error -- dev: b 31 0x040100, errno: 126, resid: 8192,
Jun 13 17:48:43 wandabh1 vmunix: blkno: 19107, sectno: 38214, offset: 19565568, bcount: 1024.
Jun 13 17:48:43 wandabh1 vmunix: LVM: Performed a switch for Lun ID = 0 (pv = 0xe0000001ccbe4000), from raw device 0x1f040100 (with priority: 0, and current flags: 0x40) to raw device 0x1f0a0100 (with priority: 1, and current flags: 0x0).
Jun 13 17:48:43 wandabh1 vmunix:
Jun 13 17:48:43 wandabh1 above message repeats 11 times
Jun 13 17:48:43 wandabh1 vmunix: LVM: VG 64 0x010000: PVLink 31 0x040100 Failed! The PV is still accessible.
Jun 13 17:48:48 wandabh1 vmunix: LVM: Performed a switch for Lun ID = 0 (pv = 0xe0000001ccbe4000), from raw device 0x1f0a0100 (with priority: 1, and current flags: 0x0) to raw device 0x1f040100 (with priority: 0, and current flags: 0x80).
Jun 13 17:48:48 wandabh1 vmunix: LVM: VG 64 0x010000: PVLink 31 0x040100 Recovered.

甚至，一臺Oracle資料庫例項Crash

Mon Jun 13 17:51:00 2011
Errors in file /data_bi/mars/admin/udump/mars_ora_6085.trc:
ORA-00202: control file: '/data_bi/mars/ctrl/control01.ctl'
ORA-27091: unable to queue I/O
ORA-27072: File I/O error
Linux-x86_64 Error: 5: Input/output error
Additional information: 4
Additional information: 1
Additional information: -1
Mon Jun 13 17:51:01 2011
Errors in file /data_bi/mars/admin/bdump/mars_lgwr_27879.trc:
ORA-00345: redo log write error block 877306 count 3
ORA-00312: online log 1 thread 1: '/data_bi/mars/log/redo01.log'
ORA-27061: waiting for async I/Os failed
Linux-x86_64 Error: 5: Input/output error
Additional information: -1
Additional information: 1536
Mon Jun 13 17:51:01 2011
Errors in file /data_bi/mars/admin/bdump/mars_lgwr_27879.trc:
ORA-00340: IO error processing online log 1 of thread 1
ORA-00345: redo log write error block 877306 count 3
ORA-00312: online log 1 thread 1: '/data_bi/mars/log/redo01.log'
ORA-27061: waiting for async I/Os failed
Linux-x86_64 Error: 5: Input/output error
Additional information: -1
Additional information: 1536
Mon Jun 13 17:51:01 2011
LGWR: terminating instance due to error 340
Termination issued to instance processes. Waiting for the processes to exit
Mon Jun 13 17:51:16 2011
Instance termination failed to kill one or more processes
Mon Jun 13 17:51:17 2011
Instance terminated by LGWR, pid = 27879

查了一下，估計是跟MPIO有關

[@more@]