On Mon, 2017-05-01 at 15:16 -0700, Dave Jiang wrote:
On 05/01/2017 03:06 PM, Kani, Toshimitsu wrote:
> On Mon, 2017-05-01 at 14:23 -0700, Dave Jiang wrote:
> :
> > +++ b/Documentation/ndctl-clear-error.txt
> > @@ -0,0 +1,37 @@
> > +ndctl-clear-error(1)
> > +====================
> > +
> > +NAME
> > +----
> > +ndctl-clear-error - clear badblocks for a device
> > +
> > +SYNOPSIS
> > +--------
> > +[verse]
> > +'ndctl clear-error' [<options>]
> > +
> > +EXAMPLES
> > +--------
> > +
> > +Clear poison (bad blocks) for the provided device
> > +[verse]
> > +ndctl clear-error -f /dev/dax0.0 -s 0 -l 8
> > +
> > +Clear poison (bad blocks) at block offset 0 for 8 blocks on
> > device
> > /dev/dax0.0
> > +
> > +OPTIONS
> > +-------
> > +-f::
> > +--file::
> > +The device/file to be cleared of poison (bad blocks).
> > +
> > +-s::
> > +--start::
> > +The offset where the poison (bad block) starts for this
> > device.
> > +Typically this is acquired from the sysfs badblocks file.
> > +
> > +-l::
> > +--len::
> > +The number of badblocks to clear in size of 512 bytes
> > increments.
> > +
>
> When a specified range is larger than a badblock range, the command
> completes with no-op without any message. I think it should either
> fail with an error message or clear an inclusive badblock.
It's suppose to just fail. Looks like I just forgot to insert an
error print out.
Yes, I am fine with the behavior with a proper error message. It'd be
good to clarify it in the document as well.
Thanks,
-Toshi