Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 19 Jul 2013 17:23:05 +0530
From:      "$owmya gowda" <sowmyagowda90@gmail.com>
To:        freebsd-scsi@freebsd.org
Subject:   Data corruption seen on the pool when an active path is pulled from geom_multipath device while running I/O
Message-ID:  <CA+n7iBr1MLCm9n8aysNE3NZsSpYJT2ykkgEzodp1ujwuBkGd9Q@mail.gmail.com>

Next in thread | Raw E-Mail | Index | Archive | Help
Hi ,
   Read/Write errors are recorded when an active path of the geom_multipath
device is pulled while running the i/o on dataset created for the pool.
Running I/o on dataset using dd.

Freebsd version* :* 9.0
Patch imported from stable 9* : *r229303, r234916

zpool status:
*            *
           pool: poola

           state: ONLINE

           scan: none requested

           config:

NAME                    STATE     READ WRITE CKSUM

poola                       ONLINE       0      0         0

          mirror-0                    ONLINE       0     0         0

           multipath/newdisk4   ONLINE       0     0         0

            multipath/newdisk2   ONLINE       0     0        0


              errors: No known data errors

*
*
*                 *

gmultipath status:
*               *
              Name   Status  Components

multipath/newdisk2  OPTIMAL  da7 (ACTIVE)

                                              da2 (PASSIVE)

multipath/newdisk1  OPTIMAL  da6 (ACTIVE)

                                              da1 (PASSIVE)

multipath/newdisk4  OPTIMAL  da3 (ACTIVE)

                                              da4 (PASSIVE)

 multipath/newdisk  OPTIMAL  da0 (ACTIVE)

                                              da5 (PASSIVE)

multipath/newdisk3  OPTIMAL  da8 (ACTIVE)

                                              da9 (PASSIVE)


*              *
scsi messages in the log:

(da0:mpslsi0:0:136:0): READ(10). CDB: 28 0 0 4a bc d6 0 1 0 0 length 131072
SMID 516 terminated ioc 804b scsi 0 state 0 xfer 0
 (da0:mpslsi0:0:136:0): READ(10). CDB: 28 0 0 4a bc d6 0 1 0 0 length
131072 SMID 516 terminated ioc 804b scsi 0 state 0 xfer 0
 (da0:mpslsi0:0:136:0): READ(10). CDB: 28 0 0 4a bd d6 0 1 0 0 length
131072 SMID 538 terminated ioc 804b scsi 0 state 0 xfer 0
 (da0:mpslsi0:0:136:0): READ(10). CDB: 28 0 0 4a bd d6 0 1 0 0 length
131072 SMID 538 terminated ioc 804b scsi 0 state 0 xfer 0



*zpool status after pulling the active path g_multipath device:*

   pool: mypool1

  state: ONLINE

  status: One or more devices has experienced an unrecoverable error.  An
	attempt was made to correct the error.  Applications are unaffected.

  action: Determine if the device needs to be replaced, and clear the errors
	using 'zpool clear' or replace the device with 'zpool replace'.

   see: http://www.sun.com/msg/ZFS-8000-9P

   scan: resilvered 27.2M in 0h0m with 0 errors on Thu Jul  4 19:47:44 2013

   config:

	NAME                    STATE     READ WRITE CKSUM

	mypool1                 ONLINE       0     0     0

	  mirror-0              ONLINE       0    12     0

	    multipath/newdisk4  ONLINE       0    27     0

	    multipath/newdisk2  ONLINE       0    12     0

	spares
	  multipath/newdisk     AVAIL



errors: No known data errors

Are there any dependencies for the patch that is picked from stable 9 as
mentioned above??
will be waiting for your reply.



Want to link to this message? Use this URL: <http://docs.FreeBSD.org/cgi/mid.cgi?CA+n7iBr1MLCm9n8aysNE3NZsSpYJT2ykkgEzodp1ujwuBkGd9Q>