[PATCH] xfstests: btrfs 308: regression test for btrfs send

[Dave Chinner]

On Mon, May 20, 2013 at 01:20:34PM -0400, Josef Bacik wrote:
> I'm not sure how the numbering is supposed to work now that we've split
> everything out so I'm just going with the next number in the directory.  This is
> a regression test for btrfs send, we had a problem where we'd try to send a file
> that had been deleted in the source snapshot.  This is just to make sure we
> don't have the same problem in the future.  Thanks,

You are holding open an unlinked file? You want to use
src/multi_open_unlink, then.

/*
 * multi_open_unlink path_prefix num_files sleep_time
 * e.g.
 *   $ multi_open_unlink file 100 60
 *   Creates 100 files: file.1, file.2, ..., file.100
 *   unlinks them all but doesn't close them all until after 60 seconds.
 */

If you need to hold open existing files, add support for that into
multi_open_unlink.c (i.e. allow it to ignore EEXIST when trying to
create files).

> +# need this so that tail doesn't error out racing with the rm
> +sleep 1
> +rm -f $SCRATCH_MNT/foo
> +$BTRFS_UTIL_PROG subvol snap -r $SCRATCH_MNT $SCRATCH_MNT/snap1 > /dev/null 2>&1
> +$BTRFS_UTIL_PROG send -f /dev/null -p $SCRATCH_MNT/snap $SCRATCH_MNT/snap1 >/dev/null 2>&1

I'd send this output to $seqres.full, so if the test fails there's
debug output to look at...

Cheers,

Dave.
-- 
Dave Chinner
david at fromorbit.com