scsi: tracking device queue depth via sbitmap
Subsystems (7)
v2 cover scsi: tracking device queue depth via sbitmap
Hi,
scsi uses one global atomic variable to track queue depth for each LUN/request queue. This way can't scale well when there is lots of CPU cores and the disk is very fast. Broadcom guys has complained that their high end HBA can't reach top performance because .device_busy is operated in IO path.
Replace the atomic variable sdev->device_busy with sbitmap for tracking scsi device queue depth.
Test on scsi_debug shows this way improve IOPS > 20%. Meantime the IOPS difference is just ~1% compared with bypassing .device_busy on scsi_debug via patches[1]
The 1st 6 patches moves percpu allocation hint into sbitmap, since the improvement by doing percpu allocation hint on sbitmap is observable. Meantime export helpers for SCSI.
Patch 7 and 8 prepares for the conversion by returning budget token from .get_budget callback, meantime passes the budget token to driver via 'struct blk_mq_queue_data' in .queue_rq().
The last two patches changes SCSI for switching to track device queue depth via sbitmap.
Broadcom Guys, please test this patchset and see if expected performance can be reached.
Please comment and review!
V2:
- fix one build failure
thanks,
Ming
[1] https://lore.kernel.org/linux-block/[email protected]/
Ming Lei (10):
sbitmap: maintain allocation round_robin in sbitmap
sbitmap: add helpers for updating allocation hint
sbitmap: remove sbitmap_clear_bit_unlock
sbitmap: move allocation hint into sbitmap
sbitmap: export sbitmap_weight
sbitmap: add helper of sbitmap_calculate_shift
blk-mq: return budget token from .get_budget callback
blk-mq: pass budget token to dirver via blk_mq_queue_data
scsi: add scsi_device_busy() to read sdev->device_busy
scsi: replace sdev->device_busy with sbitmap
block/blk-mq-sched.c | 20 ++- block/blk-mq.c | 37 +++-- block/blk-mq.h | 11 +- block/kyber-iosched.c | 3 +- drivers/dma/idxd/device.c | 2 +- drivers/dma/idxd/submit.c | 2 +- drivers/message/fusion/mptsas.c | 2 +- drivers/scsi/mpt3sas/mpt3sas_scsih.c | 2 +- drivers/scsi/scsi.c | 2 + drivers/scsi/scsi_lib.c | 47 +++--- drivers/scsi/scsi_priv.h | 1 + drivers/scsi/scsi_scan.c | 21 ++- drivers/scsi/scsi_sysfs.c | 4 +- drivers/scsi/sg.c | 2 +- include/linux/blk-mq.h | 5 +- include/linux/sbitmap.h | 84 +++++++---- include/scsi/scsi_cmnd.h | 2 + include/scsi/scsi_device.h | 8 +- lib/sbitmap.c | 213 +++++++++++++++------------ 19 files changed, 286 insertions(+), 182 deletions(-)
Ming Lei (10):
sbitmap: maintain allocation round_robin in sbitmap
sbitmap: add helpers for updating allocation hint
sbitmap: remove sbitmap_clear_bit_unlock
sbitmap: move allocation hint into sbitmap
sbitmap: export sbitmap_weight
sbitmap: add helper of sbitmap_calculate_shift
blk-mq: return budget token from .get_budget callback
blk-mq: pass budget token to dirver via blk_mq_queue_data
scsi: add scsi_device_busy() to read sdev->device_busy
scsi: replace sdev->device_busy with sbitmap
block/blk-mq-sched.c | 20 ++- block/blk-mq.c | 37 +++-- block/blk-mq.h | 11 +- block/kyber-iosched.c | 3 +- drivers/dma/idxd/device.c | 2 +- drivers/dma/idxd/submit.c | 2 +- drivers/scsi/mpt3sas/mpt3sas_scsih.c | 2 +- drivers/scsi/scsi.c | 2 + drivers/scsi/scsi_lib.c | 47 +++--- drivers/scsi/scsi_priv.h | 1 + drivers/scsi/scsi_scan.c | 21 ++- drivers/scsi/scsi_sysfs.c | 4 +- drivers/scsi/sg.c | 2 +- include/linux/blk-mq.h | 5 +- include/linux/sbitmap.h | 84 +++++++---- include/scsi/scsi_cmnd.h | 2 + include/scsi/scsi_device.h | 8 +- lib/sbitmap.c | 213 +++++++++++++++------------ 18 files changed, 285 insertions(+), 181 deletions(-)
Signature · 1 line
2.20.1
PATCH v2 1/10 sbitmap: maintain allocation round_robin in sbitmap
Now allocation round_robin info is maintained by sbitmap_queue.
Actually, bit allocation belongs to sbitmap. Also the following patch will move alloc_hint to sbitmap for users with high depth.
So move round_robin to sbitmap.
--- block/blk-mq.c | 2 +- block/kyber-iosched.c | 3 ++- drivers/dma/idxd/device.c | 2 +- drivers/dma/idxd/submit.c | 2 +- include/linux/sbitmap.h | 20 ++++++++++---------- lib/sbitmap.c | 28 ++++++++++++++-------------- 6 files changed, 29 insertions(+), 28 deletions(-)
block/blk-mq.c +1 -1
@@ -2397,7 +2397,7 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set, goto free_cpumask;if (sbitmap_init_node (&hctx->ctx_map, nr_cpu_ids,ilog2 (8 ), - gfp, node)) + gfp, node, false)) goto free_ctxs; hctx->nr_ctx =0 ;
block/kyber-iosched.c +2 -1
@@ -479,7 +479,8 @@ static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)for (i =0 ; i <KYBER_NUM_DOMAINS ; i++) {if (sbitmap_init_node (&khd->kcq_map[i], hctx->nr_ctx, -ilog2 (8 ),GFP_KERNEL , hctx->numa_node)) { +ilog2 (8 ),GFP_KERNEL , hctx->numa_node, + false)) {while (--i >=0 )sbitmap_free (&khd->kcq_map[i]); goto err_kcqs;
drivers/dma/idxd/device.c +1 -1
@@ -181,7 +181,7 @@ int idxd_wq_alloc_resources(struct idxd_wq *wq) goto fail_alloc_descs; rc =sbitmap_init_node (&wq->sbmap, num_descs,-1 ,GFP_KERNEL , -dev_to_node (dev)); +dev_to_node (dev), false);if (rc <0 ) goto fail_sbitmap_init;
drivers/dma/idxd/submit.c +1 -1
@@ -45,7 +45,7 @@ struct idxd_desc *idxd_alloc_desc(struct idxd_wq *wq, enum idxd_op_type optype)percpu_up_read (&wq->submit_lock); } - idx =sbitmap_get (&wq->sbmap,0 , false); + idx =sbitmap_get (&wq->sbmap,0 );if (idx <0 ) {atomic_dec (&wq->dq_count);return ERR_PTR (-EAGAIN );
include/linux/sbitmap.h +10 -10
@@ -61,6 +61,11 @@ struct sbitmap {*/ unsigned int map_nr; +/** +* @round_robin: Allocate bits in strict round-robin order. +*/ +bool round_robin; +/** * @map: Allocated bitmap. */
@@ -129,11 +134,6 @@ struct sbitmap_queue {*/ atomic_t ws_active; -/** -* @round_robin: Allocate bits in strict round-robin order. -*/ -bool round_robin; -/** * @min_shallow_depth: The minimum shallow depth which may be passed to * sbitmap_queue_get_shallow() or __sbitmap_queue_get_shallow().
@@ -149,11 +149,14 @@ struct sbitmap_queue {* given, a good default is chosen. * @flags: Allocation flags. * @node: Memory node to allocate on. +* @round_robin: If true, be stricter about allocation order; always allocate +* starting from the last allocated bit. This is less efficient +* than the default behavior (false). * * Return: Zero on success or negative errno on failure. */ int sbitmap_init_node (struct sbitmap *sb,unsigned int depth,int shift, -gfp_t flags,int node); +gfp_t flags,int node,bool round_robin);/** * sbitmap_free() - Free memory used by a &struct sbitmap.
@@ -179,15 +182,12 @@ void sbitmap_resize(struct sbitmap *sb, unsigned int depth);* sbitmap_get() - Try to allocate a free bit from a &struct sbitmap. * @sb: Bitmap to allocate from. * @alloc_hint: Hint for where to start searching for a free bit. -* @round_robin: If true, be stricter about allocation order; always allocate -* starting from the last allocated bit. This is less efficient -* than the default behavior (false). * * This operation provides acquire barrier semantics if it succeeds. * * Return: Non-negative allocated bit number if successful, -1 otherwise. */ -int sbitmap_get (struct sbitmap *sb,unsigned int alloc_hint,bool round_robin); +int sbitmap_get (struct sbitmap *sb,unsigned int alloc_hint);/** * sbitmap_get_shallow() - Try to allocate a free bit from a &struct sbitmap,
lib/sbitmap.c +14 -14
@@ -42,7 +42,7 @@ static inline bool sbitmap_deferred_clear(struct sbitmap *sb, int index) }int sbitmap_init_node (struct sbitmap *sb,unsigned int depth,int shift, -gfp_t flags,int node) +gfp_t flags,int node,bool round_robin) {unsigned int bits_per_word;unsigned int i;
@@ -67,6 +67,7 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, sb->shift = shift; sb->depth = depth; sb->map_nr =DIV_ROUND_UP (sb->depth, bits_per_word); + sb->round_robin = round_robin;if (depth ==0 ) { sb->map =NULL ;
@@ -137,14 +138,14 @@ static int __sbitmap_get_word(unsigned long *word, unsigned long depth, }static int sbitmap_find_bit_in_index (struct sbitmap *sb,int index, -unsigned int alloc_hint,bool round_robin) +unsigned int alloc_hint) {int nr; do { nr = __sbitmap_get_word(&sb->map[index].word, sb->map[index].depth, alloc_hint, - !round_robin); + !sb->round_robin); if (nr != -1) break; if (!sbitmap_deferred_clear(sb, index))
@@ -154,7 +155,7 @@ static int sbitmap_find_bit_in_index(struct sbitmap *sb, int index,return nr; } -int sbitmap_get (struct sbitmap *sb,unsigned int alloc_hint,bool round_robin) +int sbitmap_get (struct sbitmap *sb,unsigned int alloc_hint) {unsigned int i, index;int nr =-1 ;
@@ -166,14 +167,13 @@ int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint, bool round_robin)* alloc_hint to find the right word index. No point in looping * twice in find_next_zero_bit() for that case. */ -if (round_robin) +if (sb->round_robin) alloc_hint =SB_NR_TO_BIT (sb, alloc_hint);else alloc_hint =0 ;for (i =0 ; i < sb->map_nr; i++) { - nr =sbitmap_find_bit_in_index (sb, index, alloc_hint, - round_robin); + nr =sbitmap_find_bit_in_index (sb, index, alloc_hint);if (nr !=-1 ) { nr += index << sb->shift;break ;
@@ -355,7 +355,8 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,int ret;int i; - ret =sbitmap_init_node (&sbq->sb, depth, shift, flags, node); + ret =sbitmap_init_node (&sbq->sb, depth, shift, flags, node, + round_robin);if (ret)return ret;
@@ -387,7 +388,6 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,atomic_set (&sbq->ws[i].wait_cnt, sbq->wake_batch); } - sbq->round_robin = round_robin;return 0 ; }EXPORT_SYMBOL_GPL (sbitmap_queue_init_node);
@@ -429,12 +429,12 @@ int __sbitmap_queue_get(struct sbitmap_queue *sbq) hint = depth ?prandom_u32 () % depth :0 ;this_cpu_write (*sbq->alloc_hint, hint); } - nr =sbitmap_get (&sbq->sb, hint, sbq->round_robin); + nr =sbitmap_get (&sbq->sb, hint);if (nr ==-1 ) {/* If the map is full, a hint won't do us much good. */ this_cpu_write (*sbq->alloc_hint,0 ); - }else if (nr == hint ||unlikely (sbq->round_robin)) { + }else if (nr == hint ||unlikely (sbq->sb.round_robin)) {/* Only update the hint if we used it. */ hint = nr +1 ;if (hint >= depth -1 )
@@ -465,7 +465,7 @@ int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,if (nr ==-1 ) {/* If the map is full, a hint won't do us much good. */ this_cpu_write (*sbq->alloc_hint,0 ); - }else if (nr == hint ||unlikely (sbq->round_robin)) { + }else if (nr == hint ||unlikely (sbq->sb.round_robin)) {/* Only update the hint if we used it. */ hint = nr +1 ;if (hint >= depth -1 )
@@ -581,7 +581,7 @@ void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr,smp_mb__after_atomic ();sbitmap_queue_wake_up (sbq); -if (likely (!sbq->round_robin && nr < sbq->sb.depth)) +if (likely (!sbq->sb.round_robin && nr < sbq->sb.depth)) *per_cpu_ptr (sbq->alloc_hint, cpu) = nr; }EXPORT_SYMBOL_GPL (sbitmap_queue_clear);
@@ -638,7 +638,7 @@ void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m) }seq_puts (m,"}\n" ); -seq_printf (m,"round_robin=%d\n" , sbq->round_robin); +seq_printf (m,"round_robin=%d\n" , sbq->sb.round_robin);seq_printf (m,"min_shallow_depth=%u\n" , sbq->min_shallow_depth); }EXPORT_SYMBOL_GPL (sbitmap_queue_show);
Signature · 1 line
2.20.1
PATCH v2 2/10 sbitmap: add helpers for updating allocation hint
In reply to Ming LeiAdd helpers for updating allocation hint, so that we can avoid to duplicate code.
Prepare for moving allocation hint into sbitmap.
--- lib/sbitmap.c | 93 ++++++++++++++++++++++++++++++--------------------- 1 file changed, 54 insertions(+), 39 deletions(-)
lib/sbitmap.c +54 -39
@@ -9,6 +9,55 @@#include <linux/sbitmap.h> #include <linux/seq_file.h> +static int init_alloc_hint (struct sbitmap_queue *sbq,gfp_t flags) +{ +unsigned depth = sbq->sb.depth; + + sbq->alloc_hint = alloc_percpu_gfp(unsigned int, flags); +if (!sbq->alloc_hint) +return -ENOMEM ; + +if (depth && !sbq->sb.round_robin) { +int i; + +for_each_possible_cpu (i) + *per_cpu_ptr (sbq->alloc_hint, i) =prandom_u32 () % depth; + } + +return 0 ; +} + +static inline unsigned update_alloc_hint_before_get (struct sbitmap_queue *sbq, +unsigned int depth) +{ +unsigned hint; + + hint =this_cpu_read (*sbq->alloc_hint); +if (unlikely (hint >= depth)) { + hint = depth ?prandom_u32 () % depth :0 ; +this_cpu_write (*sbq->alloc_hint, hint); + } + +return hint; +} + +static inline void update_alloc_hint_after_get (struct sbitmap_queue *sbq, +unsigned int depth, +unsigned int hint, +unsigned int nr) +{ +if (nr ==-1 ) { +/* If the map is full, a hint won't do us much good. */ +this_cpu_write (*sbq->alloc_hint,0 ); + }else if (nr == hint ||unlikely (sbq->sb.round_robin)) { +/* Only update the hint if we used it. */ + hint = nr +1 ; +if (hint >= depth -1 ) + hint =0 ; +this_cpu_write (*sbq->alloc_hint, hint); + } +} +/* * See if we have deferred clears that we can batch move */
@@ -360,17 +409,11 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,if (ret)return ret; - sbq->alloc_hint = alloc_percpu_gfp(unsigned int, flags); -if (!sbq->alloc_hint) { +if (init_alloc_hint (sbq, flags) !=0 ) {sbitmap_free (&sbq->sb);return -ENOMEM ; } -if (depth && !round_robin) { -for_each_possible_cpu (i) - *per_cpu_ptr (sbq->alloc_hint, i) =prandom_u32 () % depth; - } - sbq->min_shallow_depth =UINT_MAX ; sbq->wake_batch =sbq_calc_wake_batch (sbq, depth);atomic_set (&sbq->wake_index,0 );
@@ -423,24 +466,10 @@ int __sbitmap_queue_get(struct sbitmap_queue *sbq)unsigned int hint, depth;int nr; - hint =this_cpu_read (*sbq->alloc_hint); depth =READ_ONCE (sbq->sb.depth); -if (unlikely (hint >= depth)) { - hint = depth ?prandom_u32 () % depth :0 ; -this_cpu_write (*sbq->alloc_hint, hint); - } + hint =update_alloc_hint_before_get (sbq, depth); nr =sbitmap_get (&sbq->sb, hint); - -if (nr ==-1 ) { -/* If the map is full, a hint won't do us much good. */ -this_cpu_write (*sbq->alloc_hint,0 ); - }else if (nr == hint ||unlikely (sbq->sb.round_robin)) { -/* Only update the hint if we used it. */ - hint = nr +1 ; -if (hint >= depth -1 ) - hint =0 ; -this_cpu_write (*sbq->alloc_hint, hint); - } +update_alloc_hint_after_get (sbq, depth, hint, nr);return nr; }
@@ -454,24 +483,10 @@ int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq,WARN_ON_ONCE (shallow_depth < sbq->min_shallow_depth); - hint =this_cpu_read (*sbq->alloc_hint); depth =READ_ONCE (sbq->sb.depth); -if (unlikely (hint >= depth)) { - hint = depth ?prandom_u32 () % depth :0 ; -this_cpu_write (*sbq->alloc_hint, hint); - } + hint =update_alloc_hint_before_get (sbq, depth); nr =sbitmap_get_shallow (&sbq->sb, hint, shallow_depth); - -if (nr ==-1 ) { -/* If the map is full, a hint won't do us much good. */ -this_cpu_write (*sbq->alloc_hint,0 ); - }else if (nr == hint ||unlikely (sbq->sb.round_robin)) { -/* Only update the hint if we used it. */ - hint = nr +1 ; -if (hint >= depth -1 ) - hint =0 ; -this_cpu_write (*sbq->alloc_hint, hint); - } +update_alloc_hint_after_get (sbq, depth, hint, nr);return nr; }
Signature · 1 line
2.20.1
PATCH v2 3/10 sbitmap: remove sbitmap_clear_bit_unlock
In reply to Ming LeiNo one uses this helper any more, so kill it.
--- include/linux/sbitmap.h | 6 ------ 1 file changed, 6 deletions(-)
include/linux/sbitmap.h +0 -6
@@ -320,12 +320,6 @@ static inline void sbitmap_deferred_clear_bit(struct sbitmap *sb, unsigned int bset_bit (SB_NR_TO_BIT (sb, bitnr), addr); } -static inline void sbitmap_clear_bit_unlock (struct sbitmap *sb, -unsigned int bitnr) -{ -clear_bit_unlock (SB_NR_TO_BIT (sb, bitnr),__sbitmap_word (sb, bitnr)); -} -static inline int sbitmap_test_bit (struct sbitmap *sb,unsigned int bitnr) {return test_bit (SB_NR_TO_BIT (sb, bitnr),__sbitmap_word (sb, bitnr));
Signature · 1 line
2.20.1
PATCH v2 4/10 sbitmap: move allocation hint into sbitmap
In reply to Ming LeiAllocation hint should have belonged to sbitmap, also when sbitmap's depth is high and no need to use mulitple wakeup queues, user can benefit from percpu allocation hint too.
So move allocation hint into sbitmap.
--- block/blk-mq.c | 2 +- block/kyber-iosched.c | 2 +- drivers/dma/idxd/device.c | 2 +- drivers/dma/idxd/submit.c | 2 +- include/linux/sbitmap.h | 41 +++++++++----- lib/sbitmap.c | 115 +++++++++++++++++++++++--------------- 6 files changed, 99 insertions(+), 65 deletions(-)
block/blk-mq.c +1 -1
@@ -2397,7 +2397,7 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set, goto free_cpumask;if (sbitmap_init_node (&hctx->ctx_map, nr_cpu_ids,ilog2 (8 ), - gfp, node, false)) + gfp, node, false, false)) goto free_ctxs; hctx->nr_ctx =0 ;
block/kyber-iosched.c +1 -1
@@ -480,7 +480,7 @@ static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)for (i =0 ; i <KYBER_NUM_DOMAINS ; i++) {if (sbitmap_init_node (&khd->kcq_map[i], hctx->nr_ctx,ilog2 (8 ),GFP_KERNEL , hctx->numa_node, - false)) { + false, false)) {while (--i >=0 )sbitmap_free (&khd->kcq_map[i]); goto err_kcqs;
drivers/dma/idxd/device.c +1 -1
@@ -181,7 +181,7 @@ int idxd_wq_alloc_resources(struct idxd_wq *wq) goto fail_alloc_descs; rc =sbitmap_init_node (&wq->sbmap, num_descs,-1 ,GFP_KERNEL , -dev_to_node (dev), false); +dev_to_node (dev), false, false);if (rc <0 ) goto fail_sbitmap_init;
drivers/dma/idxd/submit.c +1 -1
@@ -45,7 +45,7 @@ struct idxd_desc *idxd_alloc_desc(struct idxd_wq *wq, enum idxd_op_type optype)percpu_up_read (&wq->submit_lock); } - idx =sbitmap_get (&wq->sbmap,0 ); + idx =sbitmap_get (&wq->sbmap);if (idx <0 ) {atomic_dec (&wq->dq_count);return ERR_PTR (-EAGAIN );
include/linux/sbitmap.h +26 -15
103 lines not on this page · raw message
lib/sbitmap.c +69 -46
228 lines not on this page · raw message
Signature · 1 line
2.20.1
PATCH v2 5/10 sbitmap: export sbitmap_weight
In reply to Ming LeiSCSI's .device_busy will be converted to sbitmap, and sbitmap_weight is needed, so export the helper.
--- include/linux/sbitmap.h | 9 +++++++++ lib/sbitmap.c | 11 ++++++----- 2 files changed, 15 insertions(+), 5 deletions(-)
include/linux/sbitmap.h +9 -0
@@ -346,6 +346,15 @@ static inline int sbitmap_test_bit(struct sbitmap *sb, unsigned int bitnr)*/ void sbitmap_show (struct sbitmap *sb,struct seq_file *m); + +/** +* sbitmap_weight() - Return how many real bits set in a &struct sbitmap. +* @sb: Bitmap to check. +* +* Return: How many real bits set +*/ +unsigned int sbitmap_weight (const struct sbitmap *sb); +/** * sbitmap_bitmap_show() - Write a hex dump of a &struct sbitmap to a &struct * seq_file.
lib/sbitmap.c +6 -5
@@ -345,20 +345,21 @@ static unsigned int __sbitmap_weight(const struct sbitmap *sb, bool set)return weight; } -static unsigned int sbitmap_weight (const struct sbitmap *sb) +static unsigned int sbitmap_cleared (const struct sbitmap *sb) { -return __sbitmap_weight (sb, true); +return __sbitmap_weight (sb, false); } -static unsigned int sbitmap_cleared (const struct sbitmap *sb) +unsigned int sbitmap_weight (const struct sbitmap *sb) { -return __sbitmap_weight (sb, false); +return __sbitmap_weight (sb, true) -sbitmap_cleared (sb); } +EXPORT_SYMBOL_GPL (sbitmap_weight);void sbitmap_show (struct sbitmap *sb,struct seq_file *m) {seq_printf (m,"depth=%u\n" , sb->depth); -seq_printf (m,"busy=%u\n" ,sbitmap_weight (sb) -sbitmap_cleared (sb)); +seq_printf (m,"busy=%u\n" ,sbitmap_weight (sb));seq_printf (m,"cleared=%u\n" ,sbitmap_cleared (sb));seq_printf (m,"bits_per_word=%u\n" ,1U << sb->shift);seq_printf (m,"map_nr=%u\n" , sb->map_nr);
Signature · 1 line
2.20.1
PATCH v2 6/10 sbitmap: add helper of sbitmap_calculate_shift
In reply to Ming LeiMove code for calculating default shift into one public helper, which can be used for SCSI to calculate shift.
--- include/linux/sbitmap.h | 18 ++++++++++++++++++ lib/sbitmap.c | 16 +++------------- 2 files changed, 21 insertions(+), 13 deletions(-)
include/linux/sbitmap.h +18 -0
@@ -337,6 +337,24 @@ static inline int sbitmap_test_bit(struct sbitmap *sb, unsigned int bitnr)return test_bit (SB_NR_TO_BIT (sb, bitnr),__sbitmap_word (sb, bitnr)); } +static inline int sbitmap_calculate_shift (unsigned int depth) +{ +int shift =ilog2 (BITS_PER_LONG ); + +/* +* If the bitmap is small, shrink the number of bits per word so +* we spread over a few cachelines, at least. If less than 4 +* bits, just forget about it, it's not going to work optimally +* anyway. +*/ +if (depth >=4 ) { +while ((4U << shift) > depth) + shift--; + } + +return shift; +} +/** * sbitmap_show() - Dump &struct sbitmap information to a &struct seq_file. * @sb: Bitmap to show.
lib/sbitmap.c +3 -13
@@ -96,19 +96,9 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift,unsigned int bits_per_word;unsigned int i; -if (shift <0 ) { - shift =ilog2 (BITS_PER_LONG ); -/* -* If the bitmap is small, shrink the number of bits per word so -* we spread over a few cachelines, at least. If less than 4 -* bits, just forget about it, it's not going to work optimally -* anyway. -*/ -if (depth >=4 ) { -while ((4U << shift) > depth) - shift--; - } - } +if (shift <0 ) + shift =sbitmap_calculate_shift (depth); + bits_per_word =1U << shift;if (bits_per_word >BITS_PER_LONG )return -EINVAL ;
Signature · 1 line
2.20.1
PATCH v2 7/10 blk-mq: return budget token from .get_budget callback
In reply to Ming LeiSCSI uses one global atomic variable to track queue depth for each LUN/request queue.
This way doesn't scale well when there is lots of CPU cores and the disk is very fast. It has been observed that IOPS is affected a lot by tracking queue depth via sdev->device_busy in IO path.
Return budget token from .get_budget callback, and the budget token can be passed to driver, so that we can replace the atomic variable with sbitmap_queue, then the scale issue can be fixed.
--- block/blk-mq-sched.c | 20 ++++++++++++-------- block/blk-mq.c | 18 ++++++++++++------ block/blk-mq.h | 11 ++++++----- drivers/scsi/scsi_lib.c | 10 +++++----- include/linux/blk-mq.h | 4 ++-- 5 files changed, 37 insertions(+), 26 deletions(-)
block/blk-mq-sched.c +12 -8
@@ -90,6 +90,7 @@ static void blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx)struct request_queue *q = hctx->queue;struct elevator_queue *e = q->elevator;LIST_HEAD (rq_list); +int budget_token; do { struct request *rq;
@@ -97,12 +98,13 @@ static void blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx)if (e->type->ops.has_work && !e->type->ops.has_work (hctx))break ; -if (!blk_mq_get_dispatch_budget (hctx)) + budget_token =blk_mq_get_dispatch_budget (hctx); +if (budget_token <0 )break ; rq = e->type->ops.dispatch_request (hctx);if (!rq) { -blk_mq_put_dispatch_budget (hctx); +blk_mq_put_dispatch_budget (hctx, budget_token);break ; }
@@ -112,7 +114,7 @@ static void blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx)* in blk_mq_dispatch_rq_list(). */ list_add (&rq->queuelist, &rq_list); - }while (blk_mq_dispatch_rq_list (q, &rq_list, true)); + }while (blk_mq_dispatch_rq_list (q, &rq_list, budget_token)); } static struct blk_mq_ctx *blk_mq_next_ctx(struct blk_mq_hw_ctx *hctx,
@@ -136,6 +138,7 @@ static void blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx)struct request_queue *q = hctx->queue;LIST_HEAD (rq_list);struct blk_mq_ctx *ctx =READ_ONCE (hctx->dispatch_from); +int budget_token; do { struct request *rq;
@@ -143,12 +146,13 @@ static void blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx)if (!sbitmap_any_bit_set (&hctx->ctx_map))break ; -if (!blk_mq_get_dispatch_budget (hctx)) + budget_token =blk_mq_get_dispatch_budget (hctx); +if (budget_token <0 )break ; rq =blk_mq_dequeue_from_ctx (hctx, ctx);if (!rq) { -blk_mq_put_dispatch_budget (hctx); +blk_mq_put_dispatch_budget (hctx, budget_token);break ; }
@@ -162,7 +166,7 @@ static void blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx)/* round robin for fair dispatch */ ctx =blk_mq_next_ctx (hctx, rq->mq_ctx); - }while (blk_mq_dispatch_rq_list (q, &rq_list, true)); + }while (blk_mq_dispatch_rq_list (q, &rq_list, budget_token));WRITE_ONCE (hctx->dispatch_from, ctx); }
@@ -206,7 +210,7 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)*/ if (!list_empty (&rq_list)) {blk_mq_sched_mark_restart_hctx (hctx); -if (blk_mq_dispatch_rq_list (q, &rq_list, false)) { +if (blk_mq_dispatch_rq_list (q, &rq_list,-1 )) {if (has_sched_dispatch)blk_mq_do_dispatch_sched (hctx);else
@@ -219,7 +223,7 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)blk_mq_do_dispatch_ctx (hctx); }else {blk_mq_flush_busy_ctxs (hctx, &rq_list); -blk_mq_dispatch_rq_list (q, &rq_list, false); +blk_mq_dispatch_rq_list (q, &rq_list,-1 ); } }
block/blk-mq.c +12 -6
@@ -1182,13 +1182,14 @@ static void blk_mq_update_dispatch_busy(struct blk_mq_hw_ctx *hctx, bool busy)* Returns true if we did some work AND can potentially do more. */ bool blk_mq_dispatch_rq_list (struct request_queue *q,struct list_head *list, -bool got_budget) +int budget_token) {struct blk_mq_hw_ctx *hctx;struct request *rq, *nxt;bool no_tag = false;int errors, queued;blk_status_t ret =BLK_STS_OK ; +bool got_budget = budget_token >=0 ;if (list_empty (list))return false;
@@ -1205,8 +1206,11 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, rq = list_first_entry(list, struct request, queuelist); hctx = rq->mq_hctx; -if (!got_budget && !blk_mq_get_dispatch_budget (hctx)) -break ; +if (!got_budget) { + budget_token =blk_mq_get_dispatch_budget (hctx); +if (budget_token <0 ) +break ; + }if (!blk_mq_get_driver_tag (rq)) {/*
@@ -1217,7 +1221,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,* we'll re-run it below. */ if (!blk_mq_mark_tag_wait (hctx, rq)) { -blk_mq_put_dispatch_budget (hctx); +blk_mq_put_dispatch_budget (hctx, budget_token);/* * For non-shared tags, the RESTART check * will suffice.
@@ -1819,6 +1823,7 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, {struct request_queue *q = rq->q;bool run_queue = true; +int budget_token;/* * RCU or SRCU read lock is needed before checking quiesced flag.
@@ -1836,11 +1841,12 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,if (q->elevator && !bypass_insert) goto insert; -if (!blk_mq_get_dispatch_budget (hctx)) + budget_token =blk_mq_get_dispatch_budget (hctx); +if (budget_token <0 ) goto insert;if (!blk_mq_get_driver_tag (rq)) { -blk_mq_put_dispatch_budget (hctx); +blk_mq_put_dispatch_budget (hctx, budget_token); goto insert; }
block/blk-mq.h +6 -5
@@ -40,7 +40,7 @@ struct blk_mq_ctx {void blk_mq_exit_queue (struct request_queue *q);int blk_mq_update_nr_requests (struct request_queue *q,unsigned int nr);void blk_mq_wake_waiters (struct request_queue *q); -bool blk_mq_dispatch_rq_list (struct request_queue *,struct list_head *,bool ); +bool blk_mq_dispatch_rq_list (struct request_queue *,struct list_head *,int );void blk_mq_add_to_requeue_list (struct request *rq,bool at_head,bool kick_requeue_list);void blk_mq_flush_busy_ctxs (struct blk_mq_hw_ctx *hctx,struct list_head *list);
@@ -179,21 +179,22 @@ unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part);void blk_mq_in_flight_rw (struct request_queue *q,struct hd_struct *part,unsigned int inflight[2 ]); -static inline void blk_mq_put_dispatch_budget (struct blk_mq_hw_ctx *hctx) +static inline void blk_mq_put_dispatch_budget (struct blk_mq_hw_ctx *hctx, +int budget_token) {struct request_queue *q = hctx->queue;if (q->mq_ops->put_budget) - q->mq_ops->put_budget (hctx); + q->mq_ops->put_budget (hctx, budget_token); } -static inline bool blk_mq_get_dispatch_budget (struct blk_mq_hw_ctx *hctx) +static inline int blk_mq_get_dispatch_budget (struct blk_mq_hw_ctx *hctx) {struct request_queue *q = hctx->queue;if (q->mq_ops->get_budget)return q->mq_ops->get_budget (hctx); -return true; +return 0 ; } static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
drivers/scsi/scsi_lib.c +5 -5
@@ -1619,7 +1619,7 @@ static void scsi_mq_done(struct scsi_cmnd *cmd)clear_bit (SCMD_STATE_COMPLETE , &cmd->state); } -static void scsi_mq_put_budget (struct blk_mq_hw_ctx *hctx) +static void scsi_mq_put_budget (struct blk_mq_hw_ctx *hctx,int budget_token) {struct request_queue *q = hctx->queue;struct scsi_device *sdev = q->queuedata;
@@ -1627,17 +1627,17 @@ static void scsi_mq_put_budget(struct blk_mq_hw_ctx *hctx)atomic_dec (&sdev->device_busy); } -static bool scsi_mq_get_budget (struct blk_mq_hw_ctx *hctx) +static int scsi_mq_get_budget (struct blk_mq_hw_ctx *hctx) {struct request_queue *q = hctx->queue;struct scsi_device *sdev = q->queuedata;if (scsi_dev_queue_ready (q, sdev)) -return true; +return 0 ;if (atomic_read (&sdev->device_busy) ==0 && !scsi_device_blocked (sdev))blk_mq_delay_run_hw_queue (hctx,SCSI_QUEUE_DELAY ); -return false; +return -1 ; } static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
@@ -1701,7 +1701,7 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,if (scsi_target (sdev)->can_queue >0 )atomic_dec (&scsi_target (sdev)->target_busy); out_put_budget: -scsi_mq_put_budget (hctx); +scsi_mq_put_budget (hctx,0 );switch (ret) {case BLK_STS_OK :break ;
include/linux/blk-mq.h +2 -2
@@ -265,8 +265,8 @@ struct blk_mq_queue_data {typedef blk_status_t (queue_rq_fn )(struct blk_mq_hw_ctx *,const struct blk_mq_queue_data *);typedef void (commit_rqs_fn )(struct blk_mq_hw_ctx *); -typedef bool (get_budget_fn )(struct blk_mq_hw_ctx *); -typedef void (put_budget_fn )(struct blk_mq_hw_ctx *); +typedef int (get_budget_fn )(struct blk_mq_hw_ctx *); +typedef void (put_budget_fn )(struct blk_mq_hw_ctx *,int );typedef enum blk_eh_timer_return (timeout_fn )(struct request *,bool );typedef int (init_hctx_fn )(struct blk_mq_hw_ctx *,void *,unsigned int );typedef void (exit_hctx_fn )(struct blk_mq_hw_ctx *,unsigned int );
Signature · 1 line
2.20.1
PATCH v2 8/10 blk-mq: pass budget token to dirver via blk_mq_queue_data
In reply to Ming LeiPass the budget token to driver via blk_mq_queue_dada before calling .queue_rq(), and prepare for tracing SCSI's device_busy via sbitmap_queue.
--- block/blk-mq.c | 25 +++++++++++++------------ include/linux/blk-mq.h | 1 + 2 files changed, 14 insertions(+), 12 deletions(-)
block/blk-mq.c +13 -12
@@ -1235,6 +1235,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,list_del_init (&rq->queuelist); bd.rq = rq; + bd.budget_token = budget_token;/* * Flag last if we have no more requests, or if we have more
@@ -1778,14 +1779,11 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio, }static blk_status_t __blk_mq_issue_directly (struct blk_mq_hw_ctx *hctx, -struct request *rq, -blk_qc_t *cookie,bool last) +struct blk_mq_queue_data *bd, +blk_qc_t *cookie) { +struct request *rq = bd->rq;struct request_queue *q = rq->q; -struct blk_mq_queue_data bd = { - .rq = rq, - .last = last, - };blk_qc_t new_cookie;blk_status_t ret;
@@ -1796,7 +1794,7 @@ static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,* Any other error (busy), just add it to our list as we * previously would have done. */ - ret = q->mq_ops->queue_rq (hctx, &bd); + ret = q->mq_ops->queue_rq (hctx, bd);switch (ret) {case BLK_STS_OK :blk_mq_update_dispatch_busy (hctx, false);
@@ -1823,7 +1821,10 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, {struct request_queue *q = rq->q;bool run_queue = true; -int budget_token; +struct blk_mq_queue_data bd = { + .rq = rq, + .last = last, + };/* * RCU or SRCU read lock is needed before checking quiesced flag.
@@ -1841,16 +1842,16 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,if (q->elevator && !bypass_insert) goto insert; - budget_token =blk_mq_get_dispatch_budget (hctx); -if (budget_token <0 ) + bd.budget_token =blk_mq_get_dispatch_budget (hctx); +if (bd.budget_token <0 ) goto insert;if (!blk_mq_get_driver_tag (rq)) { -blk_mq_put_dispatch_budget (hctx, budget_token); +blk_mq_put_dispatch_budget (hctx, bd.budget_token); goto insert; } -return __blk_mq_issue_directly (hctx, rq, cookie, last); +return __blk_mq_issue_directly (hctx, &bd, cookie); insert:if (bypass_insert)return BLK_STS_RESOURCE ;
include/linux/blk-mq.h +1 -0
@@ -259,6 +259,7 @@ struct blk_mq_tag_set {*/ struct blk_mq_queue_data {struct request *rq; +int budget_token;bool last; };
Signature · 1 line
2.20.1
PATCH v2 9/10 scsi: add scsi_device_busy() to read sdev->device_busy
In reply to Ming LeiAdd scsi_device_busy() for drivers, so that we can prepare for tracking device queue depth via sbitmap_queue.
--- drivers/message/fusion/mptsas.c | 2 +- drivers/scsi/mpt3sas/mpt3sas_scsih.c | 2 +- drivers/scsi/scsi_lib.c | 4 ++-- drivers/scsi/scsi_sysfs.c | 2 +- drivers/scsi/sg.c | 2 +- include/scsi/scsi_device.h | 5 +++++ 6 files changed, 11 insertions(+), 6 deletions(-)
drivers/message/fusion/mptsas.c +1 -1
@@ -3756,7 +3756,7 @@ mptsas_send_link_status_event(struct fw_event_work *fw_event)printk (MYIOC_s_DEBUG_FMT"SDEV OUTSTANDING CMDS" "%d\n" , ioc->name, - atomic_read(&sdev->device_busy))); + scsi_device_busy(sdev))); } }
drivers/scsi/mpt3sas/mpt3sas_scsih.c +1 -1
@@ -3060,7 +3060,7 @@ scsih_dev_reset(struct scsi_cmnd *scmd)MPI2_SCSITASKMGMT_TASKTYPE_LOGICAL_UNIT_RESET ,0 ,0 , tr_timeout, tr_method);/* Check for busy commands after reset */ -if (r ==SUCCESS &&atomic_read (&scmd->device->device_busy)) +if (r ==SUCCESS &&scsi_device_busy (scmd->device)) r =FAILED ; out: sdev_printk(KERN_INFO, scmd->device, "device reset: %s scmd(0x%p)\n",
drivers/scsi/scsi_lib.c +2 -2
@@ -410,7 +410,7 @@ static void scsi_single_lun_run(struct scsi_device *current_sdev)static inline bool scsi_device_is_busy (struct scsi_device *sdev) { -if (atomic_read (&sdev->device_busy) >= sdev->queue_depth) +if (scsi_device_busy (sdev) >= sdev->queue_depth)return true;if (atomic_read (&sdev->device_blocked) >0 )return true;
@@ -1635,7 +1635,7 @@ static int scsi_mq_get_budget(struct blk_mq_hw_ctx *hctx)if (scsi_dev_queue_ready (q, sdev))return 0 ; -if (atomic_read (&sdev->device_busy) ==0 && !scsi_device_blocked (sdev)) +if (scsi_device_busy (sdev) ==0 && !scsi_device_blocked (sdev))blk_mq_delay_run_hw_queue (hctx,SCSI_QUEUE_DELAY );return -1 ; }
drivers/scsi/scsi_sysfs.c +1 -1
@@ -659,7 +659,7 @@ sdev_show_device_busy(struct device *dev, struct device_attribute *attr, char *buf) {struct scsi_device *sdev =to_scsi_device (dev); -return snprintf (buf,20 ,"%d\n" ,atomic_read (&sdev->device_busy)); +return snprintf (buf,20 ,"%d\n" ,scsi_device_busy (sdev)); } static DEVICE_ATTR(device_busy, S_IRUGO, sdev_show_device_busy, NULL);
drivers/scsi/sg.c +1 -1
@@ -2507,7 +2507,7 @@ static int sg_proc_seq_show_dev(struct seq_file *s, void *v) scsidp->id, scsidp->lun, (int ) scsidp->type,1 , (int ) scsidp->queue_depth, - (int )atomic_read (&scsidp->device_busy), + (int )scsi_device_busy (scsidp), (int) scsi_device_online(scsidp)); }read_unlock_irqrestore (&sg_index_lock, iflags);
include/scsi/scsi_device.h +5 -0
@@ -584,6 +584,11 @@ static inline int scsi_device_supports_vpd(struct scsi_device *sdev)return 0 ; } +static inline int scsi_device_busy (struct scsi_device *sdev) +{ +return atomic_read (&sdev->device_busy); +} +#define MODULE_ALIAS_SCSI_DEVICE (type) \ MODULE_ALIAS("scsi:t-" __stringify(type) "*")#define SCSI_DEVICE_MODALIAS_FMT "scsi:t-0x%02x"
Signature · 1 line
2.20.1
PATCH v2 10/10 scsi: replace sdev->device_busy with sbitmap
In reply to Ming Leiscsi uses one global atomic variable to track queue depth for each LUN/request queue.
This way doesn't scale well when there is lots of CPU cores and the disk is very fast. It has been observed that IOPS is affected a lot by tracking queue depth via sdev->device_busy in IO path.
So replace the atomic variable sdev->device_busy with sbitmap for tracking scsi device queue depth.
Test shows that IOPS difference is just ~1% compared with bypassing device queue depth on scsi_debug by applying patches [1]. Meantime IOPS is improved > 20% compared with linus tree.
Follows test steps:
1) test machine(32 logical CPU cores)
Thread(s) per core: 2 Core(s) per socket: 8 Socket(s): 2 NUMA node(s): 2 Model name: Intel(R) Xeon(R) CPU E5-2630 v3 @ 2.40GHz
2) setup scsi_debug:
modprobe scsi_debug virtual_gb=128 max_luns=1 submit_queues=32 delay=0 max_queue=256
3) fio script:
fio --rw=randread --size=128G --direct=1 --ioengine=libaio --iodepth=2048 \ --numjobs=32 --bs=4k --group_reporting=1 --group_reporting=1 --runtime=60 \ --loops=10000 --name=job1 --filename=/dev/sdN
[1] https://lore.kernel.org/linux-block/[email protected]/
--- drivers/scsi/scsi.c | 2 ++ drivers/scsi/scsi_lib.c | 37 ++++++++++++++++++------------------- drivers/scsi/scsi_priv.h | 1 + drivers/scsi/scsi_scan.c | 21 +++++++++++++++++++-- drivers/scsi/scsi_sysfs.c | 2 ++ include/scsi/scsi_cmnd.h | 2 ++ include/scsi/scsi_device.h | 5 +++-- 7 files changed, 47 insertions(+), 23 deletions(-)
drivers/scsi/scsi.c +2 -0
@@ -245,6 +245,8 @@ int scsi_change_queue_depth(struct scsi_device *sdev, int depth)if (sdev->request_queue)blk_set_queue_depth (sdev->request_queue, depth); +sbitmap_resize (&sdev->budget_map, sdev->queue_depth); +return sdev->queue_depth; }EXPORT_SYMBOL (scsi_change_queue_depth);
drivers/scsi/scsi_lib.c +18 -19
@@ -354,7 +354,7 @@ void scsi_device_unbusy(struct scsi_device *sdev, struct scsi_cmnd *cmd)if (starget->can_queue >0 )atomic_dec (&starget->target_busy); -atomic_dec (&sdev->device_busy); +sbitmap_put (&sdev->budget_map, cmd->budget_token); }static void scsi_kick_queue (struct request_queue *q)
@@ -1274,19 +1274,17 @@ scsi_prep_state_check(struct scsi_device *sdev, struct request *req) }/* -* scsi_dev_queue_ready: if we can send requests to sdev, return 1 else -* return 0. -* -* Called with the queue_lock held. +* scsi_dev_queue_ready: if we can send requests to sdev, assign one token +* and return the token else return -1. */ static inline int scsi_dev_queue_ready (struct request_queue *q,struct scsi_device *sdev) { -unsigned int busy; +int token; - busy =atomic_inc_return (&sdev->device_busy) -1 ; + token =sbitmap_get (&sdev->budget_map);if (atomic_read (&sdev->device_blocked)) { -if (busy) +if (token >=0 ) goto out_dec;/*
@@ -1298,13 +1296,11 @@ static inline int scsi_dev_queue_ready(struct request_queue *q, "unblocking device at zero depth\n")); } -if (busy >= sdev->queue_depth) - goto out_dec; - -return 1 ; +return token; out_dec: -atomic_dec (&sdev->device_busy); -return 0 ; +if (token >=0 ) +sbitmap_put (&sdev->budget_map, token); +return -1 ; }/*
@@ -1624,16 +1620,17 @@ static void scsi_mq_put_budget(struct blk_mq_hw_ctx *hctx, int budget_token)struct request_queue *q = hctx->queue;struct scsi_device *sdev = q->queuedata; -atomic_dec (&sdev->device_busy); +sbitmap_put (&sdev->budget_map, budget_token); }static int scsi_mq_get_budget (struct blk_mq_hw_ctx *hctx) {struct request_queue *q = hctx->queue;struct scsi_device *sdev = q->queuedata; +int token =scsi_dev_queue_ready (q, sdev); -if (scsi_dev_queue_ready (q, sdev)) -return 0 ; +if (token >=0 ) +return token;if (scsi_device_busy (sdev) ==0 && !scsi_device_blocked (sdev))blk_mq_delay_run_hw_queue (hctx,SCSI_QUEUE_DELAY );
@@ -1677,6 +1674,8 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,blk_mq_start_request (req); } + cmd->budget_token = bd->budget_token; + cmd->flags &=SCMD_PRESERVED_FLAGS ;if (sdev->simple_tags) cmd->flags |=SCMD_TAGGED ;
@@ -1701,12 +1700,12 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,if (scsi_target (sdev)->can_queue >0 )atomic_dec (&scsi_target (sdev)->target_busy); out_put_budget: -scsi_mq_put_budget (hctx,0 ); +scsi_mq_put_budget (hctx, bd->budget_token);switch (ret) {case BLK_STS_OK :break ;case BLK_STS_RESOURCE : -if (atomic_read (&sdev->device_busy) || +if (sbitmap_any_bit_set (&sdev->budget_map) ||scsi_device_blocked (sdev)) ret =BLK_STS_DEV_RESOURCE ;break ;
drivers/scsi/scsi_priv.h +1 -0
@@ -5,6 +5,7 @@#include <linux/device.h> #include <linux/async.h> #include <scsi/scsi_device.h> +#include <linux/sbitmap.h> struct request_queue ;struct request ;
drivers/scsi/scsi_scan.c +19 -2
@@ -215,6 +215,7 @@ static void scsi_unlock_floptical(struct scsi_device *sdev,static struct scsi_device *scsi_alloc_sdev (struct scsi_target *starget,u64 lun,void *hostdata) { +unsigned int depth;struct scsi_device *sdev;int display_failure_msg =1 , ret;struct Scsi_Host *shost =dev_to_shost (starget->dev.parent);
@@ -277,8 +278,23 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,WARN_ON_ONCE (!blk_get_queue (sdev->request_queue)); sdev->request_queue->queuedata = sdev; -scsi_change_queue_depth (sdev, sdev->host->cmd_per_lun ? - sdev->host->cmd_per_lun :1 ); + depth = sdev->host->cmd_per_lun ?:1 ; + +/* +* Use .can_queue as budget map's depth because we have to +* support adjusting queue depth from sysfs. Meantime use +* default device queue depth to figure out sbitmap shift +* since we use this queue depth most of times. +*/ +if (sbitmap_init_node (&sdev->budget_map, sdev->host->can_queue, +sbitmap_calculate_shift (depth), +GFP_KERNEL , sdev->request_queue->node, + false, true)) { +put_device (&starget->dev); +kfree (sdev); + } + +scsi_change_queue_depth (sdev, depth);scsi_sysfs_device_initialize (sdev);
@@ -980,6 +996,7 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result,scsi_attach_vpd (sdev); sdev->max_queue_depth = sdev->queue_depth; +WARN_ON_ONCE (sdev->max_queue_depth > sdev->budget_map.depth); sdev->sdev_bflags = *bflags;/*
drivers/scsi/scsi_sysfs.c +2 -0
@@ -466,6 +466,8 @@ static void scsi_device_dev_release_usercontext(struct work_struct *work)/* NULL queue means the device can't be used */ sdev->request_queue =NULL ; +sbitmap_free (&sdev->budget_map); +mutex_lock (&sdev->inquiry_mutex); vpd_pg0 =rcu_replace_pointer (sdev->vpd_pg0, vpd_pg0,lockdep_is_held (&sdev->inquiry_mutex));
include/scsi/scsi_cmnd.h +2 -0
@@ -76,6 +76,8 @@ struct scsi_cmnd {int eh_eflags;/* Used by error handlr */ +int budget_token; +/* * This is set to jiffies as it was when the command was first * allocated. It is used to time how long the command has
include/scsi/scsi_device.h +3 -2
@@ -8,6 +8,7 @@#include <linux/blkdev.h> #include <scsi/scsi.h> #include <linux/atomic.h> +#include <linux/sbitmap.h> struct device ;struct request_queue ;
@@ -106,7 +107,7 @@ struct scsi_device {struct list_head siblings;/* list of all devices on this host */ struct list_head same_target_siblings;/* just the devices sharing same target id */ -atomic_t device_busy;/* commands actually active on LLDD */ +struct sbitmap budget_map;atomic_t device_blocked;/* Device returned QUEUE_FULL. */ spinlock_t list_lock;
@@ -586,7 +587,7 @@ static inline int scsi_device_supports_vpd(struct scsi_device *sdev)static inline int scsi_device_busy (struct scsi_device *sdev) { -return atomic_read (&sdev->device_busy); +return sbitmap_weight (&sdev->budget_map); }#define MODULE_ALIAS_SCSI_DEVICE (type) \
Signature · 1 line
2.20.1