lib/sbitmap: allocate sb->map via kvzalloc_node
Subsystems (2)
PATCH 1/1 lib/sbitmap: allocate sb->map via kvzalloc_node
sbitmap has been used in scsi for replacing atomic operations on sdev->device_busy, so IOPS on some fast scsi storage can be improved.
However, sdev->device_busy can be changed in fast path, so we have to allocate the sb->map statically. sdev->device_busy has been capped to 1024, but some drivers may configure the default depth as < 8, then cause each sbitmap word to hold only one bit. Finally 1024 * 128( sizeof(sbitmap_word)) bytes is needed for sb->map, given it is order 5 allocation, sometimes it may fail.
Avoid the issue by using kvzalloc_node() for allocating sb->map.
--- include/linux/sbitmap.h | 2 +- lib/sbitmap.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)
include/linux/sbitmap.h +1 -1
@@ -174,7 +174,7 @@ static inline unsigned int __map_depth(const struct sbitmap *sb, int index)static inline void sbitmap_free (struct sbitmap *sb) {free_percpu (sb->alloc_hint); -kfree (sb->map); +kvfree (sb->map); sb->map =NULL ; }
lib/sbitmap.c +1 -1
@@ -110,7 +110,7 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, sb->alloc_hint =NULL ; } - sb->map =kcalloc_node (sb->map_nr,sizeof (*sb->map), flags, node); + sb->map =kvzalloc_node (sb->map_nr *sizeof (*sb->map), flags, node);if (!sb->map) {free_percpu (sb->alloc_hint);return -ENOMEM ;
Signature · 1 line
2.31.1
Quoted 10 lines · Ming Lei
sbitmap has been used in scsi for replacing atomic operations on
sdev->device_busy, so IOPS on some fast scsi storage can be improved.However,
sdev->device_busycan be changed in fast path, so we have to allocate thesb->mapstatically.sdev->device_busyhas been capped to 1024, but some drivers may configure the default depth as < 8, then cause each sbitmap word to hold only one bit. Finally 1024 * 128(sizeof(sbitmap_word)) bytes is needed forsb->map, given it is order 5 allocation, sometimes it may fail.
Quoted 6 lines
Avoid the issue by using
kvzalloc_node()for allocatingsb->map.Cc Ewan D. Milne <[email protected]>Signed-off-by Ming Lei <[email protected]>---
maybe considering the total size before actual allocation that will not buy us anything ?
Looks good.
-ck
Hello,
Quoted 10 lines · Ming Lei
sbitmap has been used in scsi for replacing atomic operations on
sdev->device_busy, so IOPS on some fast scsi storage can be improved.However,
sdev->device_busycan be changed in fast path, so we have to allocate thesb->mapstatically.sdev->device_busyhas been capped to 1024, but some drivers may configure the default depth as < 8, then cause each sbitmap word to hold only one bit. Finally 1024 * 128(sizeof(sbitmap_word)) bytes is needed forsb->map, given it is order 5 allocation, sometimes it may fail.
Quoted 4 lines
Avoid the issue by using
kvzalloc_node()for allocatingsb->map.Cc Ewan D. Milne <[email protected]>Signed-off-by Ming Lei <[email protected]>
Ping...
thanks,
Ming
Jens Axboe
maintainerQuoted 13 lines · Ming Lei
Hello,
Quoted 10 lines · Ming Lei
sbitmap has been used in scsi for replacing atomic operations on
sdev->device_busy, so IOPS on some fast scsi storage can be improved.However,
sdev->device_busycan be changed in fast path, so we have to allocate thesb->mapstatically.sdev->device_busyhas been capped to 1024, but some drivers may configure the default depth as < 8, then cause each sbitmap word to hold only one bit. Finally 1024 * 128(sizeof(sbitmap_word)) bytes is needed forsb->map, given it is order 5 allocation, sometimes it may fail.
Quoted 6 lines
Quoted 4 lines
Avoid the issue by using
kvzalloc_node()for allocatingsb->map.Cc Ewan D. Milne <[email protected]>Signed-off-by Ming Lei <[email protected]>Ping...
Was waiting on a response to the question on why we don't make this dependent on size, but upon look at kvzalloc_node(), this is already what it does. So I guess this looks fine to me too.
Signature · 1 line
Jens Axboe
Quoted 11 lines · Ming Lei
sbitmap has been used in scsi for replacing atomic operations on
sdev->device_busy, so IOPS on some fast scsi storage can be improved.However,
sdev->device_busycan be changed in fast path, so we have to allocate thesb->mapstatically.sdev->device_busyhas been capped to 1024, but some drivers may configure the default depth as < 8, then cause each sbitmap word to hold only one bit. Finally 1024 * 128(sizeof(sbitmap_word)) bytes is needed forsb->map, given it is order 5 allocation, sometimes it may fail.[...]
Applied, thanks!
[1/1] lib/sbitmap: allocate sb->map via kvzalloc_node
commit: 863a66cdb4df25fd146d9851c3289072298566d5
Best regards,
Signature · 1 line
Jens Axboe