> That explains the timeouts you're seeing. As I stated in a previous  
> note UFS has extremely poor performance when it comes
> to large files.  

Huh? I would have expected that the explanation for the iscsi initiator
timeouts is that iscsitgtd has crashed.

It seems to crash because it has corrupted it's malloc heap:

% mdb - core-iscsitgt
Loading modules: [ libumem.so.1 libavl.so.1 libc.so.1 libnvpair.so.1 
libuutil.so.1 ld.so.1 ]
> $c
libc.so.1`_lwp_kill+0xa()
libc.so.1`raise+0x19()
libumem.so.1`umem_do_abort+0x1c()
libumem.so.1`umem_err_recoverable+0xc9()
libumem.so.1`process_free+0x199()
libumem.so.1`free+0x16()
thick_provo_start+0x215()
libc.so.1`_thr_setup+0x67()
libc.so.1`_lwp_start()
> ::umem_status
Status:         ready and active
Concurrency:    4
Logs:           (inactive)
Message buffer:
free(485bb1): invalid or corrupted buffer
stack trace:
libumem.so.1'_PROCEDURE_LINKAGE_TABLE_+0x867
libumem.so.1'valloc+0x1b9
libumem.so.1'free+0x16
iscsitgtd'thick_provo_start+0x215
libc.so.1'_thr_slot_offset+0x327
libc.so.1'_thr_slot_offset+0x5d0
 
 
This message posted from opensolaris.org
_______________________________________________
storage-discuss mailing list
[email protected]
http://mail.opensolaris.org/mailman/listinfo/storage-discuss

Reply via email to