Here we go.
I'm using Broadcomm network cards (bnx0) on target host and Asus (i think 
Intel-based) cards on initiator side. Don't have exact chipset info at hand now.
Both target and initiator connected to same switch 3com 5500 24 1Gbit ports 
switch.

I've destroyed raidz1 pool and used whole 500Gb disk as backing-store for 
target (/dev/dsk/c0t1d0s0)

Situation slightly better now - mkfs finished with only 9 timeouts.
But problem is still there. Looks like it is backing-store, which can't consume 
high input traffic.
--
This message posted from opensolaris.org
_______________________________________________
storage-discuss mailing list
[email protected]
http://mail.opensolaris.org/mailman/listinfo/storage-discuss

Reply via email to