Linux-NVME Archive on lore.kernel.org
 help / color / Atom feed
From: Himanshu Madhani <himanshu.madhani@oracle.com>
To: Keith Busch <kbusch@kernel.org>
Cc: axboe@kernel.dk, sagi@grimberg.me,
	"Chaitanya Kulkarni" <chaitanya.kulkarni@wdc.com>,
	"Johannes Thumshirn" <johannes.thumshirn@wdc.com>,
	"Daniel Wagner" <dwagner@suse.de>,
	"Aravind Ramesh" <aravind.ramesh@wdc.com>,
	linux-nvme@lists.infradead.org, linux-block@vger.kernel.org,
	"Hannes Reinecke" <hare@suse.de>,
	"Martin K . Petersen" <martin.petersen@oracle.com>,
	hch@lst.de, "Matias Bjørling" <matias.bjorling@wdc.com>
Subject: Re: [PATCHv4 2/5] null_blk: introduce zone capacity for zoned device
Date: Tue, 30 Jun 2020 10:34:46 -0500
Message-ID: <B5094B73-43A2-491E-9DE9-931EFA3854B3@oracle.com> (raw)
In-Reply-To: <20200629190641.1986462-3-kbusch@kernel.org>



> On Jun 29, 2020, at 2:06 PM, Keith Busch <kbusch@kernel.org> wrote:
> 
> From: Aravind Ramesh <aravind.ramesh@wdc.com>
> 
> Allow emulation of a zoned device with a per zone capacity smaller than
> the zone size as as defined in the Zoned Namespace (ZNS) Command Set
> specification. The zone capacity defaults to the zone size if not
> specified and must be smaller than the zone size otherwise.
> 
> Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
> Reviewed-by: Matias Bjørling <matias.bjorling@wdc.com>
> Reviewed-by: Daniel Wagner <dwagner@suse.de>
> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
> Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
> Reviewed-by: Hannes Reinecke <hare@suse.de>
> Signed-off-by: Aravind Ramesh <aravind.ramesh@wdc.com>
> ---
> drivers/block/null_blk.h       |  1 +
> drivers/block/null_blk_main.c  | 10 +++++++++-
> drivers/block/null_blk_zoned.c | 16 ++++++++++++++--
> 3 files changed, 24 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h
> index 81b311c9d781..daed4a9c3436 100644
> --- a/drivers/block/null_blk.h
> +++ b/drivers/block/null_blk.h
> @@ -49,6 +49,7 @@ struct nullb_device {
> 	unsigned long completion_nsec; /* time in ns to complete a request */
> 	unsigned long cache_size; /* disk cache size in MB */
> 	unsigned long zone_size; /* zone size in MB if device is zoned */
> +	unsigned long zone_capacity; /* zone capacity in MB if device is zoned */
> 	unsigned int zone_nr_conv; /* number of conventional zones */
> 	unsigned int submit_queues; /* number of submission queues */
> 	unsigned int home_node; /* home node for the device */
> diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c
> index 82259242b9b5..96d1adf6b818 100644
> --- a/drivers/block/null_blk_main.c
> +++ b/drivers/block/null_blk_main.c
> @@ -200,6 +200,10 @@ static unsigned long g_zone_size = 256;
> module_param_named(zone_size, g_zone_size, ulong, S_IRUGO);
> MODULE_PARM_DESC(zone_size, "Zone size in MB when block device is zoned. Must be power-of-two: Default: 256");
> 
> +static unsigned long g_zone_capacity;
> +module_param_named(zone_capacity, g_zone_capacity, ulong, 0444);
> +MODULE_PARM_DESC(zone_capacity, "Zone capacity in MB when block device is zoned. Can be less than or equal to zone size. Default: Zone size");
> +
> static unsigned int g_zone_nr_conv;
> module_param_named(zone_nr_conv, g_zone_nr_conv, uint, 0444);
> MODULE_PARM_DESC(zone_nr_conv, "Number of conventional zones when block device is zoned. Default: 0");
> @@ -341,6 +345,7 @@ NULLB_DEVICE_ATTR(mbps, uint, NULL);
> NULLB_DEVICE_ATTR(cache_size, ulong, NULL);
> NULLB_DEVICE_ATTR(zoned, bool, NULL);
> NULLB_DEVICE_ATTR(zone_size, ulong, NULL);
> +NULLB_DEVICE_ATTR(zone_capacity, ulong, NULL);
> NULLB_DEVICE_ATTR(zone_nr_conv, uint, NULL);
> 
> static ssize_t nullb_device_power_show(struct config_item *item, char *page)
> @@ -457,6 +462,7 @@ static struct configfs_attribute *nullb_device_attrs[] = {
> 	&nullb_device_attr_badblocks,
> 	&nullb_device_attr_zoned,
> 	&nullb_device_attr_zone_size,
> +	&nullb_device_attr_zone_capacity,
> 	&nullb_device_attr_zone_nr_conv,
> 	NULL,
> };
> @@ -510,7 +516,8 @@ nullb_group_drop_item(struct config_group *group, struct config_item *item)
> 
> static ssize_t memb_group_features_show(struct config_item *item, char *page)
> {
> -	return snprintf(page, PAGE_SIZE, "memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size,zone_nr_conv\n");
> +	return snprintf(page, PAGE_SIZE,
> +			"memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size,zone_capacity,zone_nr_conv\n");
> }
> 
> CONFIGFS_ATTR_RO(memb_group_, features);
> @@ -571,6 +578,7 @@ static struct nullb_device *null_alloc_dev(void)
> 	dev->use_per_node_hctx = g_use_per_node_hctx;
> 	dev->zoned = g_zoned;
> 	dev->zone_size = g_zone_size;
> +	dev->zone_capacity = g_zone_capacity;
> 	dev->zone_nr_conv = g_zone_nr_conv;
> 	return dev;
> }
> diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c
> index 624aac09b005..3d25c9ad2383 100644
> --- a/drivers/block/null_blk_zoned.c
> +++ b/drivers/block/null_blk_zoned.c
> @@ -28,6 +28,15 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
> 		return -EINVAL;
> 	}
> 
> +	if (!dev->zone_capacity)
> +		dev->zone_capacity = dev->zone_size;
> +
> +	if (dev->zone_capacity > dev->zone_size) {
> +		pr_err("null_blk: zone capacity (%lu MB) larger than zone size (%lu MB)\n",
> +					dev->zone_capacity, dev->zone_size);
> +		return -EINVAL;
> +	}
> +
> 	dev->zone_size_sects = dev->zone_size << ZONE_SIZE_SHIFT;
> 	dev->nr_zones = dev_size >>
> 				(SECTOR_SHIFT + ilog2(dev->zone_size_sects));
> @@ -60,7 +69,7 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
> 
> 		zone->start = zone->wp = sector;
> 		zone->len = dev->zone_size_sects;
> -		zone->capacity = zone->len;
> +		zone->capacity = dev->zone_capacity << ZONE_SIZE_SHIFT;
> 		zone->type = BLK_ZONE_TYPE_SEQWRITE_REQ;
> 		zone->cond = BLK_ZONE_COND_EMPTY;
> 
> @@ -187,6 +196,9 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
> 			return BLK_STS_IOERR;
> 		}
> 
> +		if (zone->wp + nr_sectors > zone->start + zone->capacity)
> +			return BLK_STS_IOERR;
> +
> 		if (zone->cond != BLK_ZONE_COND_EXP_OPEN)
> 			zone->cond = BLK_ZONE_COND_IMP_OPEN;
> 
> @@ -195,7 +207,7 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
> 			return ret;
> 
> 		zone->wp += nr_sectors;
> -		if (zone->wp == zone->start + zone->len)
> +		if (zone->wp == zone->start + zone->capacity)
> 			zone->cond = BLK_ZONE_COND_FULL;
> 		return BLK_STS_OK;
> 	default:
> —
> 2.24.1
> 

Reviewed-by: Himanshu Madhani <himanshu.madhani@oracle.com>

--
Himanshu Madhani	Oracle Linux Engineering






_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

  reply index

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-06-29 19:06 [PATCHv4 0/5] nvme support for zoned namespace command set Keith Busch
2020-06-29 19:06 ` [PATCHv4 1/5] block: add capacity field to zone descriptors Keith Busch
2020-06-30 15:34   ` Himanshu Madhani
2020-06-29 19:06 ` [PATCHv4 2/5] null_blk: introduce zone capacity for zoned device Keith Busch
2020-06-30 15:34   ` Himanshu Madhani [this message]
2020-06-29 19:06 ` [PATCHv4 3/5] nvme: implement I/O Command Sets Command Set support Keith Busch
2020-06-30  6:01   ` Hannes Reinecke
2020-06-30 15:45   ` Himanshu Madhani
2020-06-29 19:06 ` [PATCHv4 4/5] nvme: support for multi-command set effects Keith Busch
2020-06-30 15:51   ` Himanshu Madhani
2020-06-29 19:06 ` [PATCHv4 5/5] nvme: support for zoned namespaces Keith Busch
2020-06-30 16:36   ` Himanshu Madhani
2020-07-01  6:37 ` [PATCHv4 0/5] nvme support for zoned namespace command set Christoph Hellwig

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=B5094B73-43A2-491E-9DE9-931EFA3854B3@oracle.com \
    --to=himanshu.madhani@oracle.com \
    --cc=aravind.ramesh@wdc.com \
    --cc=axboe@kernel.dk \
    --cc=chaitanya.kulkarni@wdc.com \
    --cc=dwagner@suse.de \
    --cc=hare@suse.de \
    --cc=hch@lst.de \
    --cc=johannes.thumshirn@wdc.com \
    --cc=kbusch@kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=martin.petersen@oracle.com \
    --cc=matias.bjorling@wdc.com \
    --cc=sagi@grimberg.me \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-NVME Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-nvme/0 linux-nvme/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-nvme linux-nvme/ https://lore.kernel.org/linux-nvme \
		linux-nvme@lists.infradead.org
	public-inbox-index linux-nvme

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.infradead.lists.linux-nvme


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git