Re: [PATCH v2 3/3] fat: allocate multiple clusters in fallocate

[OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>]

Matheus Alves de Almeida <matheus.aalmeida@inf.ufrgs.br> writes:

> The fat_fallocate() code currently does many 1-cluster allocations when
> growing a file in the FALLOC_FL_KEEP_SIZE path. Make it allocate
> everything with one call instead.
>
> Benchmarking was done under QEMU/KVM with a virtio-blk device using
> cache=none. Each result is the arithmetic mean of the listed samples.
>
> start = now_ns();
> for (unsigned int i = 0; i < count; i++)
>      fallocate(fds[i], FALLOC_FL_KEEP_SIZE, 0, bytes);
> elapsed = now_ns() - start;
>
> FAT32 with 512-byte clusters using count=16 files:
> length    mounted sync?    before    after    improvement    samples
> 256MiB    no               2.328s    0.175s   13.2x          10
> 16MiB     no               149.659ms 14.036ms 10.7x          10
> 16MiB     yes              747.993s  3.445s   217.1x         3
> 1MiB      yes              46.63s    0.333s   140.1x         10
>
> FAT32 with 512-byte clusters using count=128 files:
> length    mounted sync?    before    after    improvement    samples
> 1MiB      no               90.873ms  4.686ms  19.4x          10
> 16KiB     no               1.287ms   0.241ms  5.3x           10
> 128KiB    yes              47.284s   0.350s   135x           10
> 4KiB      yes              1.98s     0.144s   13.7x          10
>
> FAT32 with 4096-byte clusters using count=16 files:
> length    mounted sync?    before    after    improvement    samples
> 256MiB    no               295.392ms 24.733ms 11.9x          10
> 16MiB     no               20.509ms  1.404ms  14.6x          10
> 16MiB     yes              92.489s   0.348s   265.4x         10
> 1MiB      yes              5.837s    0.048s   121.3x         10
>
> The improvement is especially large on synchronous mounts, where the
> new code can batch FAT updates instead of synchronously handling each
> cluster allocation separately.
>
> Signed-off-by: Matheus Alves de Almeida <matheus.aalmeida@inf.ufrgs.br>

Acked-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>

Looks good. Thanks.

> ---
>  fs/fat/file.c | 10 ++++------
>  1 file changed, 4 insertions(+), 6 deletions(-)
>
> diff --git a/fs/fat/file.c b/fs/fat/file.c
> index 41d49e9de..3aa541c6b 100644
> --- a/fs/fat/file.c
> +++ b/fs/fat/file.c
> @@ -290,12 +290,10 @@ static long fat_fallocate(struct file *file, int mode,
>  		nr_cluster = (mm_bytes + (sbi->cluster_size - 1)) >>
>  			sbi->cluster_bits;
>  
> -		/* Start the allocation.We are not zeroing out the clusters */
> -		while (nr_cluster-- > 0) {
> -			err = fat_add_clusters(inode, 1);
> -			if (err)
> -				goto error;
> -		}
> +		/* Allocate the clusters. We are not zeroing them out */
> +		err = fat_add_clusters(inode, nr_cluster);
> +		if (err)
> +			goto error;
>  	} else {
>  		if ((offset + len) <= i_size_read(inode))
>  			goto error;

-- 
OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>