Re: [PATCH v8 05/11] null_blk: allow non power of 2 zoned devices

[Damien Le Moal]

On 7/28/22 01:22, Pankaj Raghav wrote:
> Convert the power of 2 based calculation with zone size to be generic in
> null_zone_no with optimization for power of 2 based zone sizes.
> 
> The nr_zones calculation in null_init_zoned_dev has been replaced with a
> division without special handling for power of 2 based zone sizes as
> this function is called only during the initialization and will not
> invoked in the hot path.
> 
> Performance Measurement:
> 
> Device:
> zone size = 128M, blocksize=4k
> 
> FIO cmd:
> 
> fio --name=zbc --filename=/dev/nullb0 --direct=1 --zonemode=zbd  --size=23G
> --io_size=<iosize> --ioengine=io_uring --iodepth=<iod> --rw=<mode> --bs=4k
> --loops=4
> 
> The following results are an average of 4 runs on AMD Ryzen 5 5600X with
> 32GB of RAM:
> 
> Sequential Write:
> 
> x-----------------x---------------------------------x---------------------------------x
> |     IOdepth     |            8                    |            16                   |
> x-----------------x---------------------------------x---------------------------------x
> |                 |  KIOPS   |BW(MiB/s) | Lat(usec) |  KIOPS   |BW(MiB/s) | Lat(usec) |
> x-----------------x---------------------------------x---------------------------------x
> | Without patch   |  578     |  2257    |   12.80   |  576     |  2248    |   25.78   |
> x-----------------x---------------------------------x---------------------------------x
> |  With patch     |  581     |  2268    |   12.74   |  576     |  2248    |   25.85   |
> x-----------------x---------------------------------x---------------------------------x
> 
> Sequential read:
> 
> x-----------------x---------------------------------x---------------------------------x
> | IOdepth         |            8                    |            16                   |
> x-----------------x---------------------------------x---------------------------------x
> |                 |  KIOPS   |BW(MiB/s) | Lat(usec) |  KIOPS   |BW(MiB/s) | Lat(usec) |
> x-----------------x---------------------------------x---------------------------------x
> | Without patch   |  667     |  2605    |   11.79   |  675     |  2637    |   23.49   |
> x-----------------x---------------------------------x---------------------------------x
> |  With patch     |  667     |  2605    |   11.79   |  675     |  2638    |   23.48   |
> x-----------------x---------------------------------x---------------------------------x
> 
> Random read:
> 
> x-----------------x---------------------------------x---------------------------------x
> | IOdepth         |            8                    |            16                   |
> x-----------------x---------------------------------x---------------------------------x
> |                 |  KIOPS   |BW(MiB/s) | Lat(usec) |  KIOPS   |BW(MiB/s) | Lat(usec) |
> x-----------------x---------------------------------x---------------------------------x
> | Without patch   |  522     |  2038    |   15.05   |  514     |  2006    |   30.87   |
> x-----------------x---------------------------------x---------------------------------x
> |  With patch     |  522     |  2039    |   15.04   |  523     |  2042    |   30.33   |
> x-----------------x---------------------------------x---------------------------------x
> 
> Minor variations are noticed in Sequential write with io depth 8 and
> in random read with io depth 16. But overall no noticeable differences
> were noticed
> 
> Reviewed-by: Luis Chamberlain <mcgrof@xxxxxxxxxx>
> Reviewed by: Adam Manzanares <a.manzanares@xxxxxxxxxxx>
> Reviewed-by: Hannes Reinecke <hare@xxxxxxx>
> Signed-off-by: Pankaj Raghav <p.raghav@xxxxxxxxxxx>
> ---
>  drivers/block/null_blk/main.c     |  5 ++---
>  drivers/block/null_blk/null_blk.h |  6 ++++++
>  drivers/block/null_blk/zoned.c    | 18 +++++++++++-------
>  3 files changed, 19 insertions(+), 10 deletions(-)
> 
> diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
> index c451c477978f..f1e0605dee94 100644
> --- a/drivers/block/null_blk/main.c
> +++ b/drivers/block/null_blk/main.c
> @@ -1976,9 +1976,8 @@ static int null_validate_conf(struct nullb_device *dev)
>  	if (dev->queue_mode == NULL_Q_BIO)
>  		dev->mbps = 0;
>  
> -	if (dev->zoned &&
> -	    (!dev->zone_size || !is_power_of_2(dev->zone_size))) {
> -		pr_err("zone_size must be power-of-two\n");
> +	if (dev->zoned && !dev->zone_size) {
> +		pr_err("Invalid zero zone size\n");
>  		return -EINVAL;
>  	}
>  
> diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h
> index 94ff68052b1e..ece6dded9508 100644
> --- a/drivers/block/null_blk/null_blk.h
> +++ b/drivers/block/null_blk/null_blk.h
> @@ -83,6 +83,12 @@ struct nullb_device {
>  	unsigned int imp_close_zone_no;
>  	struct nullb_zone *zones;
>  	sector_t zone_size_sects;
> +	/*
> +	 * zone_size_sects_shift is only useful when the zone size is
> +	 * power of 2. This variable is set to zero when zone size is non
> +	 * power of 2.
> +	 */

Simplify:

	/*
	 * zone_size_sects_shift is used only when the zone size is a
	 * power of 2 number of sectors.
	 */

But personally, I would simply drop this comment. The name is obvious and
the code very clear.

> +	unsigned int zone_size_sects_shift;
>  	bool need_zone_res_mgmt;
>  	spinlock_t zone_res_lock;
>  
> diff --git a/drivers/block/null_blk/zoned.c b/drivers/block/null_blk/zoned.c
> index 55a69e48ef8b..015f6823706c 100644
> --- a/drivers/block/null_blk/zoned.c
> +++ b/drivers/block/null_blk/zoned.c
> @@ -16,7 +16,10 @@ static inline sector_t mb_to_sects(unsigned long mb)
>  
>  static inline unsigned int null_zone_no(struct nullb_device *dev, sector_t sect)
>  {
> -	return sect >> ilog2(dev->zone_size_sects);
> +	if (dev->zone_size_sects_shift)
> +		return sect >> dev->zone_size_sects_shift;
> +
> +	return div64_u64(sect, dev->zone_size_sects);
>  }
>  
>  static inline void null_lock_zone_res(struct nullb_device *dev)
> @@ -65,10 +68,6 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
>  	sector_t sector = 0;
>  	unsigned int i;
>  
> -	if (!is_power_of_2(dev->zone_size)) {
> -		pr_err("zone_size must be power-of-two\n");
> -		return -EINVAL;
> -	}
>  	if (dev->zone_size > dev->size) {
>  		pr_err("Zone size larger than device capacity\n");
>  		return -EINVAL;
> @@ -86,9 +85,14 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
>  	zone_capacity_sects = mb_to_sects(dev->zone_capacity);
>  	dev_capacity_sects = mb_to_sects(dev->size);
>  	dev->zone_size_sects = mb_to_sects(dev->zone_size);
> -	dev->nr_zones = round_up(dev_capacity_sects, dev->zone_size_sects)
> -		>> ilog2(dev->zone_size_sects);
>  
> +	if (is_power_of_2(dev->zone_size_sects))
> +		dev->zone_size_sects_shift = ilog2(dev->zone_size_sects);
> +	else
> +		dev->zone_size_sects_shift = 0;
> +
> +	dev->nr_zones =	DIV_ROUND_UP_SECTOR_T(dev_capacity_sects,
> +					      dev->zone_size_sects);
>  	dev->zones = kvmalloc_array(dev->nr_zones, sizeof(struct nullb_zone),
>  				    GFP_KERNEL | __GFP_ZERO);
>  	if (!dev->zones)


-- 
Damien Le Moal
Western Digital Research