[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]

Re: [Cluster-devel] [GFS2 PATCH] GFS2: Speed up gfs2_rbm_from_block



Hi,

On Wed, 2012-10-17 at 11:06 -0400, Bob Peterson wrote:
> Hi,
> 
> This patch is a rewrite of function gfs2_rbm_from_block. Rather than
> looping to find the right bitmap, the code now does a few simple
> math calculations. This speeds up the function significantly.
> 
It would be a good plan to include the timings that you showed me
yesterday in the patch description to show the improvement this gives.

> Regards,
> 
> Bob Peterson
> Red Hat File Systems
> 
> Signed-off-by: Bob Peterson <rpeterso redhat com> 
> ---
> diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
> index 3d469d3..24bb0b8 100644
> --- a/fs/gfs2/incore.h
> +++ b/fs/gfs2/incore.h
> @@ -621,6 +621,7 @@ struct gfs2_sbd {
>  	u32 sd_hash_bsize_shift;
>  	u32 sd_hash_ptrs;	/* Number of pointers in a hash block */
>  	u32 sd_qc_per_block;
> +	u32 sd_blocks_per_bitmap;
>  	u32 sd_max_dirres;	/* Max blocks needed to add a directory entry */
>  	u32 sd_max_height;	/* Max height of a file's metadata tree */
>  	u64 sd_heightsize[GFS2_MAX_META_HEIGHT + 1];
> diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
> index e443966..0e3554e 100644
> --- a/fs/gfs2/ops_fstype.c
> +++ b/fs/gfs2/ops_fstype.c
> @@ -278,6 +278,9 @@ static int gfs2_read_sb(struct gfs2_sbd *sdp, int silent)
>  	sdp->sd_qc_per_block = (sdp->sd_sb.sb_bsize -
>  				sizeof(struct gfs2_meta_header)) /
>  			        sizeof(struct gfs2_quota_change);
> +	sdp->sd_blocks_per_bitmap = (sdp->sd_sb.sb_bsize -
> +				     sizeof(struct gfs2_meta_header))
> +		* GFS2_NBBY; /* not the rgrp bitmap, subsequent bitmaps only */
>  
>  	/* Compute maximum reservation required to add a entry to a directory */
>  
> diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
> index 43d1a20..7635500 100644
> --- a/fs/gfs2/rgrp.c
> +++ b/fs/gfs2/rgrp.c
> @@ -250,23 +250,23 @@ static u32 gfs2_bitfit(const u8 *buf, const unsigned int len,
>  
>  static int gfs2_rbm_from_block(struct gfs2_rbm *rbm, u64 block)
>  {
> -	u64 rblock = block - rbm->rgd->rd_data0;
> -	u32 goal = (u32)rblock;
> -	int x;
> +	u32 x;
>  
> -	if (WARN_ON_ONCE(rblock > UINT_MAX))
> -		return -EINVAL;
This test was intended to check for underflow, i.e. that the block
number was less than rd_data0. I think it would be a good plan to retain
such a test even though we should not see any blocks outside of the
current bitmap.

Otherwise, it looks good,

Steve.


>  	if (block >= rbm->rgd->rd_data0 + rbm->rgd->rd_data)
>  		return -E2BIG;
>  
> -	for (x = 0; x < rbm->rgd->rd_length; x++) {
> -		rbm->bi = rbm->rgd->rd_bits + x;
> -		if (goal < (rbm->bi->bi_start + rbm->bi->bi_len) * GFS2_NBBY) {
> -			rbm->offset = goal - (rbm->bi->bi_start * GFS2_NBBY);
> -			break;
> -		}
> -	}
> +	rbm->bi = rbm->rgd->rd_bits;
> +	rbm->offset = (u32)(block - rbm->rgd->rd_data0);
> +	/* Check if the block is within the first block */
> +	if (rbm->offset < (rbm->bi->bi_start + rbm->bi->bi_len) * GFS2_NBBY)
> +		return 0;
>  
> +	/* Adjust for the size diff between gfs2_meta_header and gfs2_rgrp */
> +	rbm->offset += (sizeof(struct gfs2_rgrp) -
> +			sizeof(struct gfs2_meta_header)) * GFS2_NBBY;
> +	x = rbm->offset / rbm->rgd->rd_sbd->sd_blocks_per_bitmap;
> +	rbm->offset -= x * rbm->rgd->rd_sbd->sd_blocks_per_bitmap;
> +	rbm->bi += x;
>  	return 0;
>  }
>  
> 



[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]