Re: [PATCH v2] btrfs: raid56: do extra dumping for CONFIG_BTRFS_ASSERT

[David Sterba <dsterba@suse.cz>]

On Wed, May 15, 2024 at 01:14:01PM +0930, Qu Wenruo wrote:
> There are several hard-to-hit ASSERT()s hit inside raid56.
> Unfortunately the ASSERT() expression is a little complex, and except
> the ASSERT(), there is nothing to provide any clue.
> 
> Considering if race is involved, it's pretty hard to reproduce.
> Meanwhile sometimes the dump of the rbio structure can provide some
> pretty good clues, it's worthy to do the extra multi-line dump for
> btrfs raid56 related code.
> 
> The dump looks like this:
> 
>  BTRFS critical (device dm-3): bioc logical=4598530048 full_stripe=4598530048 size=0 map_type=0x81 mirror=0 replace_nr_stripes=0 replace_stripe_src=-1 num_stripes=5
>  BTRFS critical (device dm-3):     nr=0 devid=1 physical=1166147584
>  BTRFS critical (device dm-3):     nr=1 devid=2 physical=1145176064
>  BTRFS critical (device dm-3):     nr=2 devid=4 physical=1145176064
>  BTRFS critical (device dm-3):     nr=3 devid=5 physical=1145176064
>  BTRFS critical (device dm-3):     nr=4 devid=3 physical=1145176064
>  BTRFS critical (device dm-3): rbio flags=0x0 nr_sectors=80 nr_data=4 real_stripes=5 stripe_nsectors=16 scrubp=0 dbitmap=0x0
>  BTRFS critical (device dm-3): logical=4598530048
>  assertion failed: orig_logical >= full_stripe_start && orig_logical + orig_len <= full_stripe_start + rbio->nr_data * BTRFS_STRIPE_LEN, in fs/btrfs/raid56.c:1702
>  ------------[ cut here ]------------
> 
> Signed-off-by: Qu Wenruo <wqu@suse.com>

Please add the patch to for-next so we can start getting more info from
the crashes, thanks.