On Mon, 2007-04-02 at 19:36 -0400, Douglas Gilbert wrote: > > echo 1 > /sys/class/sas_phy/phy-X:3/link_reset > > > > and see if it just produces > > > > aic94xx: scb:0x80 timed out > > Yes it does. > > > Again? > > It is repeatable. > > Also when I connect to phy 0 it works (both direct > connect and expander). However phys 1 and 2 react > like phy 3 shown above. OK, well, I know what it is, I just don't know how to fix it. On certain error conditions, whatever controls the phy SCB processing seems to freeze to a particular phy. With me, it's externally induced (an expander->expander->satapi configuration). I can recover my system by powering off and on the expander setup. Whatever this condition is, it blows away all error recovery, since they're also done via means of ascbs, so any error recovery ascbs also get stuck until they timeout. Someone with the specs needs to look and see if there's a way we can kick the phy queue (or whatever queue it's stuck in)---I'm assuming it's a phy queue because I can get packets out via other phys, just nothing via the stuck one. James - To unsubscribe from this list: send the line "unsubscribe linux-scsi" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html