Re: SCSI access creating lost time

Alan Cox (alan@lxorguk.ukuu.org.uk)
Sun, 7 Mar 1999 23:57:30 +0000 (GMT)

Messages sorted by: [ date ][ thread ][ subject ][ author ]
Next message: Alan Cox: "Re: [PATCH] a.out don't exec over NFS"
Previous message: Andrea Arcangeli: "Re: select()/socket has problems under 2.2.x."

> It's not coincidence. Both of you have polling based SCSI controllers
> where the drivers sit in tight loops waiting for things to happen inside
> of a spin_lock_irqsave(). There's nothing intelligent that can be done
> until the locking in the drivers/mid-level SCSI code is redone except
> switching to a SCSI controller/driver combo that doesn't spin wait for
> things like individual bytes on the SCSI bus.

You drop the lock. In fact a lot drivers already do drop the lock, and
in fact have to drop the lock because of the way they work. If the lock
is unsafe when dropped that way then the entire mid layer scsi code needs
fixing in 2.2, which is going to suck

Alan

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/

Next message: Alan Cox: "Re: [PATCH] a.out don't exec over NFS"
Previous message: Andrea Arcangeli: "Re: select()/socket has problems under 2.2.x."