OpenSolaris

new assert while running i/o from 2 initiators - all i/o failed on both initiators and initiator 1 required fsck to fix the problems.

initiator 1 was running GRITSs using this config file
  /mnt/sparse512/512    write/verify    512             500M              21
  /mnt/sparse512/128k    write/verify    128k             500M              01
  /mnt/sparse1k/1k   write/verify    1k             1G              22
  /mnt/sparse1k/128k   write/verify    128k             1G              02
  /mnt/sparse2k    write/verify    128k             2G              03
  /mnt/sparse4k    write/verify    128k             3G              04
  /mnt/sparse8k    write/verify    128k             5G              05
  /mnt/sparse16k    write/verify    128k             3G              06
  /mnt/sparse32k    write/verify    128k             3G              07
  /mnt/sparse64k    write/verify    128k             3G              08
  /mnt/sparse128k    write/verify    128k             4G              09

initiator 2 was running 2 diskomizer jobs to 2 raw luns

Here is the dump info
 ::stack
libc.so.1`_lwp_kill+0xa()
libc.so.1`raise+0x19()
libc.so.1`abort+0xd1()
libc.so.1`_assert+0x74()
t10_cmd_state_machine+0x419()
t10_aio_done+0xd2()
libc.so.1`_thr_setup+0x89()
libc.so.1`_lwp_start()
> ::status
debugging core file of iscsitgtd (64-bit) from cesar
file: /usr/sbin/amd64/iscsitgtd
initial argv: /usr/sbin/iscsitgtd
threading model: native threads
status: process terminated by SIGABRT (Abort)
panic message: Assertion failed: 0, file ../t10_sam.c, line 601
>
corefile is attached.

This was hit on fw_33, which has all the snv_94 iscsi fixes in it.  The complete list of fixes is on the fishwiki.

N/A

N/A