* [PATCH v2 1/1] null_blk: add option for managing virtual boundary
@ 2021-04-12 9:55 Max Gurtovoy
2021-04-12 11:53 ` Damien Le Moal
2021-04-12 12:47 ` Jens Axboe
0 siblings, 2 replies; 4+ messages in thread
From: Max Gurtovoy @ 2021-04-12 9:55 UTC (permalink / raw)
To: linux-block, martin.petersen, axboe
Cc: oren, idanb, yossike, Damien.LeMoal, Chaitanya.Kulkarni, Max Gurtovoy
This will enable changing the virtual boundary of null blk devices. For
now, null blk devices didn't have any restriction on the scatter/gather
elements received from the block layer. Add a module parameter and a
configfs option that will control the virtual boundary. This will
enable testing the efficiency of the block layer bounce buffer in case
a suitable application will send discontiguous IO to the given device.
Initial testing with patched FIO showed the following results (64 jobs,
128 iodepth, 1 nullb device):
IO size READ (virt=false) READ (virt=true) Write (virt=false) Write (virt=true)
---------- ------------------- ----------------- ------------------- -------------------
1k 10.7M 8482k 10.8M 8471k
2k 10.4M 8266k 10.4M 8271k
4k 10.4M 8274k 10.3M 8226k
8k 10.2M 8131k 9800k 7933k
16k 9567k 7764k 8081k 6828k
32k 8865k 7309k 5570k 5153k
64k 7695k 6586k 2682k 2617k
128k 5346k 5489k 1320k 1296k
Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
---
changes from v1:
- added configfs option (Chaitanya and Damien)
- added virt_boundary to feature list
---
drivers/block/null_blk/main.c | 12 +++++++++++-
drivers/block/null_blk/null_blk.h | 1 +
2 files changed, 12 insertions(+), 1 deletion(-)
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index d6c821d48090..c35872cc5f37 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -84,6 +84,10 @@ enum {
NULL_Q_MQ = 2,
};
+static bool g_virt_boundary = false;
+module_param_named(virt_boundary, g_virt_boundary, bool, 0444);
+MODULE_PARM_DESC(virt_boundary, "Require a virtual boundary for the device. Default: False");
+
static int g_no_sched;
module_param_named(no_sched, g_no_sched, int, 0444);
MODULE_PARM_DESC(no_sched, "No io scheduler");
@@ -366,6 +370,7 @@ NULLB_DEVICE_ATTR(zone_capacity, ulong, NULL);
NULLB_DEVICE_ATTR(zone_nr_conv, uint, NULL);
NULLB_DEVICE_ATTR(zone_max_open, uint, NULL);
NULLB_DEVICE_ATTR(zone_max_active, uint, NULL);
+NULLB_DEVICE_ATTR(virt_boundary, bool, NULL);
static ssize_t nullb_device_power_show(struct config_item *item, char *page)
{
@@ -486,6 +491,7 @@ static struct configfs_attribute *nullb_device_attrs[] = {
&nullb_device_attr_zone_nr_conv,
&nullb_device_attr_zone_max_open,
&nullb_device_attr_zone_max_active,
+ &nullb_device_attr_virt_boundary,
NULL,
};
@@ -539,7 +545,7 @@ 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_capacity,zone_nr_conv,zone_max_open,zone_max_active,blocksize,max_sectors\n");
+ "memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size,zone_capacity,zone_nr_conv,zone_max_open,zone_max_active,blocksize,max_sectors,virt_boundary\n");
}
CONFIGFS_ATTR_RO(memb_group_, features);
@@ -605,6 +611,7 @@ static struct nullb_device *null_alloc_dev(void)
dev->zone_nr_conv = g_zone_nr_conv;
dev->zone_max_open = g_zone_max_open;
dev->zone_max_active = g_zone_max_active;
+ dev->virt_boundary = g_virt_boundary;
return dev;
}
@@ -1880,6 +1887,9 @@ static int null_add_dev(struct nullb_device *dev)
BLK_DEF_MAX_SECTORS);
blk_queue_max_hw_sectors(nullb->q, dev->max_sectors);
+ if (dev->virt_boundary)
+ blk_queue_virt_boundary(nullb->q, PAGE_SIZE - 1);
+
null_config_discard(nullb);
sprintf(nullb->disk_name, "nullb%d", nullb->index);
diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h
index 83504f3cc9d6..5ad5087ebe39 100644
--- a/drivers/block/null_blk/null_blk.h
+++ b/drivers/block/null_blk/null_blk.h
@@ -96,6 +96,7 @@ struct nullb_device {
bool memory_backed; /* if data is stored in memory */
bool discard; /* if support discard */
bool zoned; /* if device is zoned */
+ bool virt_boundary; /* virtual boundary on/off for the device */
};
struct nullb {
--
2.18.1
^ permalink raw reply related [flat|nested] 4+ messages in thread* Re: [PATCH v2 1/1] null_blk: add option for managing virtual boundary
2021-04-12 9:55 [PATCH v2 1/1] null_blk: add option for managing virtual boundary Max Gurtovoy
@ 2021-04-12 11:53 ` Damien Le Moal
2021-04-12 12:47 ` Jens Axboe
1 sibling, 0 replies; 4+ messages in thread
From: Damien Le Moal @ 2021-04-12 11:53 UTC (permalink / raw)
To: Max Gurtovoy, linux-block, martin.petersen, axboe
Cc: oren, idanb, yossike, Chaitanya Kulkarni
On 2021/04/12 18:55, Max Gurtovoy wrote:
> This will enable changing the virtual boundary of null blk devices. For
> now, null blk devices didn't have any restriction on the scatter/gather
> elements received from the block layer. Add a module parameter and a
> configfs option that will control the virtual boundary. This will
> enable testing the efficiency of the block layer bounce buffer in case
> a suitable application will send discontiguous IO to the given device.
>
> Initial testing with patched FIO showed the following results (64 jobs,
> 128 iodepth, 1 nullb device):
> IO size READ (virt=false) READ (virt=true) Write (virt=false) Write (virt=true)
> ---------- ------------------- ----------------- ------------------- -------------------
> 1k 10.7M 8482k 10.8M 8471k
> 2k 10.4M 8266k 10.4M 8271k
> 4k 10.4M 8274k 10.3M 8226k
> 8k 10.2M 8131k 9800k 7933k
> 16k 9567k 7764k 8081k 6828k
> 32k 8865k 7309k 5570k 5153k
> 64k 7695k 6586k 2682k 2617k
> 128k 5346k 5489k 1320k 1296k
>
> Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
> ---
>
> changes from v1:
> - added configfs option (Chaitanya and Damien)
> - added virt_boundary to feature list
>
> ---
> drivers/block/null_blk/main.c | 12 +++++++++++-
> drivers/block/null_blk/null_blk.h | 1 +
> 2 files changed, 12 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
> index d6c821d48090..c35872cc5f37 100644
> --- a/drivers/block/null_blk/main.c
> +++ b/drivers/block/null_blk/main.c
> @@ -84,6 +84,10 @@ enum {
> NULL_Q_MQ = 2,
> };
>
> +static bool g_virt_boundary = false;
> +module_param_named(virt_boundary, g_virt_boundary, bool, 0444);
> +MODULE_PARM_DESC(virt_boundary, "Require a virtual boundary for the device. Default: False");
> +
> static int g_no_sched;
> module_param_named(no_sched, g_no_sched, int, 0444);
> MODULE_PARM_DESC(no_sched, "No io scheduler");
> @@ -366,6 +370,7 @@ NULLB_DEVICE_ATTR(zone_capacity, ulong, NULL);
> NULLB_DEVICE_ATTR(zone_nr_conv, uint, NULL);
> NULLB_DEVICE_ATTR(zone_max_open, uint, NULL);
> NULLB_DEVICE_ATTR(zone_max_active, uint, NULL);
> +NULLB_DEVICE_ATTR(virt_boundary, bool, NULL);
>
> static ssize_t nullb_device_power_show(struct config_item *item, char *page)
> {
> @@ -486,6 +491,7 @@ static struct configfs_attribute *nullb_device_attrs[] = {
> &nullb_device_attr_zone_nr_conv,
> &nullb_device_attr_zone_max_open,
> &nullb_device_attr_zone_max_active,
> + &nullb_device_attr_virt_boundary,
> NULL,
> };
>
> @@ -539,7 +545,7 @@ 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_capacity,zone_nr_conv,zone_max_open,zone_max_active,blocksize,max_sectors\n");
> + "memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size,zone_capacity,zone_nr_conv,zone_max_open,zone_max_active,blocksize,max_sectors,virt_boundary\n");
> }
>
> CONFIGFS_ATTR_RO(memb_group_, features);
> @@ -605,6 +611,7 @@ static struct nullb_device *null_alloc_dev(void)
> dev->zone_nr_conv = g_zone_nr_conv;
> dev->zone_max_open = g_zone_max_open;
> dev->zone_max_active = g_zone_max_active;
> + dev->virt_boundary = g_virt_boundary;
> return dev;
> }
>
> @@ -1880,6 +1887,9 @@ static int null_add_dev(struct nullb_device *dev)
> BLK_DEF_MAX_SECTORS);
> blk_queue_max_hw_sectors(nullb->q, dev->max_sectors);
>
> + if (dev->virt_boundary)
> + blk_queue_virt_boundary(nullb->q, PAGE_SIZE - 1);
> +
> null_config_discard(nullb);
>
> sprintf(nullb->disk_name, "nullb%d", nullb->index);
> diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h
> index 83504f3cc9d6..5ad5087ebe39 100644
> --- a/drivers/block/null_blk/null_blk.h
> +++ b/drivers/block/null_blk/null_blk.h
> @@ -96,6 +96,7 @@ struct nullb_device {
> bool memory_backed; /* if data is stored in memory */
> bool discard; /* if support discard */
> bool zoned; /* if device is zoned */
> + bool virt_boundary; /* virtual boundary on/off for the device */
> };
>
> struct nullb {
>
Looks good to me.
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
--
Damien Le Moal
Western Digital Research
^ permalink raw reply [flat|nested] 4+ messages in thread* Re: [PATCH v2 1/1] null_blk: add option for managing virtual boundary
2021-04-12 9:55 [PATCH v2 1/1] null_blk: add option for managing virtual boundary Max Gurtovoy
2021-04-12 11:53 ` Damien Le Moal
@ 2021-04-12 12:47 ` Jens Axboe
2021-04-12 17:57 ` Chaitanya Kulkarni
1 sibling, 1 reply; 4+ messages in thread
From: Jens Axboe @ 2021-04-12 12:47 UTC (permalink / raw)
To: Max Gurtovoy, linux-block, martin.petersen
Cc: oren, idanb, yossike, Damien.LeMoal, Chaitanya.Kulkarni
On 4/12/21 3:55 AM, Max Gurtovoy wrote:
> This will enable changing the virtual boundary of null blk devices. For
> now, null blk devices didn't have any restriction on the scatter/gather
> elements received from the block layer. Add a module parameter and a
> configfs option that will control the virtual boundary. This will
> enable testing the efficiency of the block layer bounce buffer in case
> a suitable application will send discontiguous IO to the given device.
Applied, thanks.
--
Jens Axboe
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH v2 1/1] null_blk: add option for managing virtual boundary
2021-04-12 12:47 ` Jens Axboe
@ 2021-04-12 17:57 ` Chaitanya Kulkarni
0 siblings, 0 replies; 4+ messages in thread
From: Chaitanya Kulkarni @ 2021-04-12 17:57 UTC (permalink / raw)
To: Jens Axboe
Cc: Max Gurtovoy, linux-block, martin.petersen, oren, idanb, yossike,
Damien Le Moal
Jens,
On 4/12/21 05:48, Jens Axboe wrote:
> On 4/12/21 3:55 AM, Max Gurtovoy wrote:
>> This will enable changing the virtual boundary of null blk devices. For
>> now, null blk devices didn't have any restriction on the scatter/gather
>> elements received from the block layer. Add a module parameter and a
>> configfs option that will control the virtual boundary. This will
>> enable testing the efficiency of the block layer bounce buffer in case
>> a suitable application will send discontiguous IO to the given device.
> Applied, thanks.
>
If this is still on the top and can be done easily please add.
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2021-04-12 17:58 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-04-12 9:55 [PATCH v2 1/1] null_blk: add option for managing virtual boundary Max Gurtovoy
2021-04-12 11:53 ` Damien Le Moal
2021-04-12 12:47 ` Jens Axboe
2021-04-12 17:57 ` Chaitanya Kulkarni
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.