[Cluster-devel] [GFS2 PATCH][TRY #2] GFS2: Speed up gfs2_rbm_from_block

[Steven Whitehouse]

Hi,

That looks good, and good to see that it makes a difference to at least
one workload, as well as the reduction in time. Now in the -nmw git
tree. Thanks,

Steve.

On Fri, 2012-10-19 at 08:32 -0400, Bob Peterson wrote:
> Hi,
> 
> This is my second attempt at this patch, following Steve's suggestions.
> 
> 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.
> 
> I compared the performance of both algorithms side by side and the new
> algorithm is noticeably faster. Sample instrumentation output from a
> "fast" machine:
> 
> 5 million calls: millisec spent: Orig: 166 New: 113
> 5 million calls: millisec spent: Orig: 189 New: 114
> 
> In addition, I ran postmark (on a somewhat slowr CPU) before the after
> the new algorithm was put in place and postmark showed a decent
> improvement:
> 
> Before the new algorithm:
> -------------------------
> Time:
> 	645 seconds total
> 	584 seconds of transactions (171 per second)
> 
> Files:
> 	150087 created (232 per second)
> 		Creation alone: 100000 files (2083 per second)
> 		Mixed with transactions: 50087 files (85 per second)
> 	49995 read (85 per second)
> 	49991 appended (85 per second)
> 	150087 deleted (232 per second)
> 		Deletion alone: 100174 files (7705 per second)
> 		Mixed with transactions: 49913 files (85 per second)
> 
> Data:
> 	273.42 megabytes read (434.08 kilobytes per second)
> 	852.13 megabytes written (1.32 megabytes per second)
> 
> With the new algorithm:
> -----------------------
> Time:
> 	599 seconds total
> 	530 seconds of transactions (188 per second)
> 
> Files:
> 	150087 created (250 per second)
> 		Creation alone: 100000 files (1886 per second)
> 		Mixed with transactions: 50087 files (94 per second)
> 	49995 read (94 per second)
> 	49991 appended (94 per second)
> 	150087 deleted (250 per second)
> 		Deletion alone: 100174 files (6260 per second)
> 		Mixed with transactions: 49913 files (94 per second)
> 
> Data:
> 	273.42 megabytes read (467.42 kilobytes per second)
> 	852.13 megabytes written (1.42 megabytes per second)
> 
> Regards,
> 
> Bob Peterson
> Red Hat File Systems
> 
> Signed-off-by: Bob Peterson <rpeterso at redhat.com> 
> ---
> commit f7abb1edc9e61eb5ff5ae9fa1a3964b10f3aa553
> Author: Bob Peterson <rpeterso at redhat.com>
> Date:   Wed Oct 17 09:59:43 2012 -0500
> 
>     GFS2: Speed up gfs2_rbm_from_block
>     
>     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.
> 
> 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 38fe18f..669b89b 100644
> --- a/fs/gfs2/rgrp.c
> +++ b/fs/gfs2/rgrp.c
> @@ -251,22 +251,25 @@ 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;
>  	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)(rblock);
> +	/* 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;
>  }
>  
>