[PATCH] nvme/pci: Remove watchdog timer

Keith Busch keith.busch at intel.com
Thu Jun 1 06:13:53 PDT 2017


On Thu, Jun 01, 2017 at 02:50:23PM +0200, Christoph Hellwig wrote:
> On Tue, May 30, 2017 at 10:20:57AM -0400, Keith Busch wrote:
> > I am hoping to get this in this round since it would quiet a lot of
> > errors I'm frequently pinged on: a non-posted request during a hotremove
> > downstream a switch creates a lot of problems for hardware if you don't
> > have DPC enabled.
> 
> With this round do you mean 4.12-rc or 4.13?

Was hoping 4.12 simply only the problems from doing this are recently
becomming more clear, but I guess no rush at this point.
 
> > One thing I'm just realizing, though, this will break subsystem reset.
> > We were depending on the watchdog to detect that event, but now we require
> > an IO timeout. It's easy enough to fix that from the host initiating
> > the NSSR, but there's no way to notify other hosts connected to the
> > same subsystem.
> 
> I don't think I've actually seen it trigger for that case due to the
> PCIe link going down earlier.  But I'll need to double check as I
> actually have access to a dual ported drive at the moment, the machine
> setup is a bit quirky, though.

The watchdog timer might see all 1's if it happens to run when the
link is in the detect state after NSSR, but normally the host should see
just CSTS.NSSRO to know to it needs to reset its controller.



More information about the Linux-nvme mailing list