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

From: Dave Chinner <david@fromorbit.com>
To: Josef Bacik <jbacik@fusionio.com>
Cc: xfs@oss.sgi.com, linux-btrfs@vger.kernel.org
Subject: Re: [PATCH] xfstests: btrfs 308: regression test for btrfs send
Date: Tue, 21 May 2013 10:33:26 +1000	[thread overview]
Message-ID: <20130521003326.GJ24543@dastard> (raw)
In-Reply-To: <1369070434-20852-1-git-send-email-jbacik@fusionio.com>

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@fromorbit.com