Re: [PATCH 2/2] xfs: inode and free block counters need to use __percpu_counter_compare

[Brian Foster <bfoster@redhat.com>]

On Wed, May 13, 2015 at 09:52:34AM +1000, Dave Chinner wrote:
> From: Dave Chinner <dchinner@redhat.com>
> 
> Because the counters use a custom batch size, the comparison
> functions need to be aware of that batch size otherwise the
> comparison does not work correctly. This leads to ASSERT failures
> on generic/027 like this:
> 
>  XFS: Assertion failed: 0, file: fs/xfs/xfs_mount.c, line: 1099
>  ------------[ cut here ]------------
> ....
>  Call Trace:
>   [<ffffffff81522a39>] xfs_mod_icount+0x99/0xc0
>   [<ffffffff815285cb>] xfs_trans_unreserve_and_mod_sb+0x28b/0x5b0
>   [<ffffffff8152f941>] xfs_log_commit_cil+0x321/0x580
>   [<ffffffff81528e17>] xfs_trans_commit+0xb7/0x260
>   [<ffffffff81503d4d>] xfs_bmap_finish+0xcd/0x1b0
>   [<ffffffff8151da41>] xfs_inactive_ifree+0x1e1/0x250
>   [<ffffffff8151dbe0>] xfs_inactive+0x130/0x200
>   [<ffffffff81523a21>] xfs_fs_evict_inode+0x91/0xf0
>   [<ffffffff811f3958>] evict+0xb8/0x190
>   [<ffffffff811f433b>] iput+0x18b/0x1f0
>   [<ffffffff811e8853>] do_unlinkat+0x1f3/0x320
>   [<ffffffff811d548a>] ? filp_close+0x5a/0x80
>   [<ffffffff811e999b>] SyS_unlinkat+0x1b/0x40
>   [<ffffffff81e0892e>] system_call_fastpath+0x12/0x71
> 
> This is a regression introduced by commit 501ab32 ("xfs: use generic
> percpu counters for inode counter").
> 
> This patch fixes the same problem for both the inode counter and the
> free block counter in the superblocks.
> 
> Signed-off-by: Dave Chinner <dchinner@redhat.com>
> ---

Reviewed-by: Brian Foster <bfoster@redhat.com>

>  fs/xfs/xfs_mount.c | 34 ++++++++++++++++++++--------------
>  1 file changed, 20 insertions(+), 14 deletions(-)
> 
> diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
> index 02f827f..461e791 100644
> --- a/fs/xfs/xfs_mount.c
> +++ b/fs/xfs/xfs_mount.c
> @@ -1100,14 +1100,18 @@ xfs_log_sbcount(xfs_mount_t *mp)
>  	return xfs_sync_sb(mp, true);
>  }
>  
> +/*
> + * Deltas for the inode count are +/-64, hence we use a large batch size
> + * of 128 so we don't need to take the counter lock on every update.
> + */
> +#define XFS_ICOUNT_BATCH	128
>  int
>  xfs_mod_icount(
>  	struct xfs_mount	*mp,
>  	int64_t			delta)
>  {
> -	/* deltas are +/-64, hence the large batch size of 128. */
> -	__percpu_counter_add(&mp->m_icount, delta, 128);
> -	if (percpu_counter_compare(&mp->m_icount, 0) < 0) {
> +	__percpu_counter_add(&mp->m_icount, delta, XFS_ICOUNT_BATCH);
> +	if (__percpu_counter_compare(&mp->m_icount, 0, XFS_ICOUNT_BATCH) < 0) {
>  		ASSERT(0);
>  		percpu_counter_add(&mp->m_icount, -delta);
>  		return -EINVAL;
> @@ -1129,6 +1133,14 @@ xfs_mod_ifree(
>  	return 0;
>  }
>  
> +/*
> + * Deltas for the block count can vary from 1 to very large, but lock contention
> + * only occurs on frequent small block count updates such as in the delayed
> + * allocation path for buffered writes (page a time updates). Hence we set
> + * a large batch count (1024) to minimise global counter updates except when
> + * we get near to ENOSPC and we have to be very accurate with our updates.
> + */
> +#define XFS_FDBLOCKS_BATCH	1024
>  int
>  xfs_mod_fdblocks(
>  	struct xfs_mount	*mp,
> @@ -1167,25 +1179,19 @@ xfs_mod_fdblocks(
>  	 * Taking blocks away, need to be more accurate the closer we
>  	 * are to zero.
>  	 *
> -	 * batch size is set to a maximum of 1024 blocks - if we are
> -	 * allocating of freeing extents larger than this then we aren't
> -	 * going to be hammering the counter lock so a lock per update
> -	 * is not a problem.
> -	 *
>  	 * If the counter has a value of less than 2 * max batch size,
>  	 * then make everything serialise as we are real close to
>  	 * ENOSPC.
>  	 */
> -#define __BATCH	1024
> -	if (percpu_counter_compare(&mp->m_fdblocks, 2 * __BATCH) < 0)
> +	if (__percpu_counter_compare(&mp->m_fdblocks, 2 * XFS_FDBLOCKS_BATCH,
> +				     XFS_FDBLOCKS_BATCH) < 0)
>  		batch = 1;
>  	else
> -		batch = __BATCH;
> -#undef __BATCH
> +		batch = XFS_FDBLOCKS_BATCH;
>  
>  	__percpu_counter_add(&mp->m_fdblocks, delta, batch);
> -	if (percpu_counter_compare(&mp->m_fdblocks,
> -				   XFS_ALLOC_SET_ASIDE(mp)) >= 0) {
> +	if (__percpu_counter_compare(&mp->m_fdblocks, XFS_ALLOC_SET_ASIDE(mp),
> +				     XFS_FDBLOCKS_BATCH) >= 0) {
>  		/* we had space! */
>  		return 0;
>  	}
> -- 
> 2.0.0
> 
> _______________________________________________
> xfs mailing list
> xfs@oss.sgi.com
> http://oss.sgi.com/mailman/listinfo/xfs