| Message ID | 20241119002815.600608-8-bvanassche@acm.org (mailing list archive) |
|---|---|
| State | Not Applicable |
| Headers | show |
| Series | Improve write performance for zoned UFS devices | expand |
On 11/19/24 09:27, Bart Van Assche wrote: > Many but not all storage controllers require serialization of zoned > writes. Introduce a new request queue limit member variable related to > write serialization. 'driver_preserves_write_order' allows block drivers > to indicate that the order of write commands is preserved per hardware > queue and hence that serialization of writes per zone is not required if > all pending writes are submitted to the same hardware queue. > > Cc: Damien Le Moal <dlemoal@kernel.org> > Cc: Hannes Reinecke <hare@suse.de> > Cc: Nitesh Shetty <nj.shetty@samsung.com> > Cc: Christoph Hellwig <hch@lst.de> > Cc: Ming Lei <ming.lei@redhat.com> > Signed-off-by: Bart Van Assche <bvanassche@acm.org> > --- > block/blk-settings.c | 2 ++ > include/linux/blkdev.h | 5 +++++ > 2 files changed, 7 insertions(+) > > diff --git a/block/blk-settings.c b/block/blk-settings.c > index f1d4dfdc37a7..329d8b65a8d7 100644 > --- a/block/blk-settings.c > +++ b/block/blk-settings.c > @@ -633,6 +633,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, > } > t->max_secure_erase_sectors = min_not_zero(t->max_secure_erase_sectors, > b->max_secure_erase_sectors); > + t->driver_preserves_write_order = t->driver_preserves_write_order && > + b->driver_preserves_write_order; > t->zone_write_granularity = max(t->zone_write_granularity, > b->zone_write_granularity); > if (!(t->features & BLK_FEAT_ZONED)) { > diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h > index a1fd0ddce5cf..72be33d02d1f 100644 > --- a/include/linux/blkdev.h > +++ b/include/linux/blkdev.h > @@ -397,6 +397,11 @@ struct queue_limits { > > unsigned int max_open_zones; > unsigned int max_active_zones; > + /* > + * Whether or not the block driver preserves the order of write > + * requests. Set by the block driver. > + */ > + bool driver_preserves_write_order; Why not make this a q->features flag ? > > /* > * Drivers that set dma_alignment to less than 511 must be prepared to
On 11/18/24 11:37 PM, Damien Le Moal wrote: > On 11/19/24 09:27, Bart Van Assche wrote: >> diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h >> index a1fd0ddce5cf..72be33d02d1f 100644 >> --- a/include/linux/blkdev.h >> +++ b/include/linux/blkdev.h >> @@ -397,6 +397,11 @@ struct queue_limits { >> >> unsigned int max_open_zones; >> unsigned int max_active_zones; >> + /* >> + * Whether or not the block driver preserves the order of write >> + * requests. Set by the block driver. >> + */ >> + bool driver_preserves_write_order; > > Why not make this a q->features flag ? I assume that you meant q->limits.features? I will look into this. Thanks, Bart.
diff --git a/block/blk-settings.c b/block/blk-settings.c index f1d4dfdc37a7..329d8b65a8d7 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -633,6 +633,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, } t->max_secure_erase_sectors = min_not_zero(t->max_secure_erase_sectors, b->max_secure_erase_sectors); + t->driver_preserves_write_order = t->driver_preserves_write_order && + b->driver_preserves_write_order; t->zone_write_granularity = max(t->zone_write_granularity, b->zone_write_granularity); if (!(t->features & BLK_FEAT_ZONED)) { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a1fd0ddce5cf..72be33d02d1f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -397,6 +397,11 @@ struct queue_limits { unsigned int max_open_zones; unsigned int max_active_zones; + /* + * Whether or not the block driver preserves the order of write + * requests. Set by the block driver. + */ + bool driver_preserves_write_order; /* * Drivers that set dma_alignment to less than 511 must be prepared to
Many but not all storage controllers require serialization of zoned writes. Introduce a new request queue limit member variable related to write serialization. 'driver_preserves_write_order' allows block drivers to indicate that the order of write commands is preserved per hardware queue and hence that serialization of writes per zone is not required if all pending writes are submitted to the same hardware queue. Cc: Damien Le Moal <dlemoal@kernel.org> Cc: Hannes Reinecke <hare@suse.de> Cc: Nitesh Shetty <nj.shetty@samsung.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Ming Lei <ming.lei@redhat.com> Signed-off-by: Bart Van Assche <bvanassche@acm.org> --- block/blk-settings.c | 2 ++ include/linux/blkdev.h | 5 +++++ 2 files changed, 7 insertions(+)