diff options
author | Vivek Goyal <vgoyal@redhat.com> | 2010-09-15 17:06:35 -0400 |
---|---|---|
committer | Jens Axboe <jaxboe@fusionio.com> | 2010-09-16 08:42:52 +0200 |
commit | e43473b7f223ec866f7db273697e76c337c390f9 (patch) | |
tree | e90b52dbe4ec4ae37263a00e2bd9eaf5367cf72f | |
parent | 4c9eefa16c6f124ffcc736cb719b24ea27f85017 (diff) | |
download | linux-e43473b7f223ec866f7db273697e76c337c390f9.tar.gz linux-e43473b7f223ec866f7db273697e76c337c390f9.tar.bz2 linux-e43473b7f223ec866f7db273697e76c337c390f9.zip |
blkio: Core implementation of throttle policy
o Actual implementation of throttling policy in block layer. Currently it
implements READ and WRITE bytes per second throttling logic. IOPS throttling
comes in later patches.
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
-rw-r--r-- | block/Kconfig | 12 | ||||
-rw-r--r-- | block/Makefile | 1 | ||||
-rw-r--r-- | block/blk-core.c | 24 | ||||
-rw-r--r-- | block/blk-throttle.c | 909 | ||||
-rw-r--r-- | include/linux/blk_types.h | 3 | ||||
-rw-r--r-- | include/linux/blkdev.h | 24 | ||||
-rw-r--r-- | init/Kconfig | 9 |
7 files changed, 979 insertions, 3 deletions
diff --git a/block/Kconfig b/block/Kconfig index 9be0b56eaee1..6c9213ef15a1 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -77,6 +77,18 @@ config BLK_DEV_INTEGRITY T10/SCSI Data Integrity Field or the T13/ATA External Path Protection. If in doubt, say N. +config BLK_DEV_THROTTLING + bool "Block layer bio throttling support" + depends on BLK_CGROUP=y && EXPERIMENTAL + default n + ---help--- + Block layer bio throttling support. It can be used to limit + the IO rate to a device. IO rate policies are per cgroup and + one needs to mount and use blkio cgroup controller for creating + cgroups and specifying per device IO rate policies. + + See Documentation/cgroups/blkio-controller.txt for more information. + endif # BLOCK config BLOCK_COMPAT diff --git a/block/Makefile b/block/Makefile index 0bb499a739cd..c850d5ef80a2 100644 --- a/block/Makefile +++ b/block/Makefile @@ -9,6 +9,7 @@ obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o \ obj-$(CONFIG_BLK_DEV_BSG) += bsg.o obj-$(CONFIG_BLK_CGROUP) += blk-cgroup.o +obj-$(CONFIG_BLK_DEV_THROTTLING) += blk-throttle.o obj-$(CONFIG_IOSCHED_NOOP) += noop-iosched.o obj-$(CONFIG_IOSCHED_DEADLINE) += deadline-iosched.o obj-$(CONFIG_IOSCHED_CFQ) += cfq-iosched.o diff --git a/block/blk-core.c b/block/blk-core.c index 8d07c1b7e701..797d5095eb83 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -382,6 +382,7 @@ void blk_sync_queue(struct request_queue *q) del_timer_sync(&q->unplug_timer); del_timer_sync(&q->timeout); cancel_work_sync(&q->unplug_work); + throtl_shutdown_timer_wq(q); } EXPORT_SYMBOL(blk_sync_queue); @@ -459,6 +460,8 @@ void blk_cleanup_queue(struct request_queue *q) if (q->elevator) elevator_exit(q->elevator); + blk_throtl_exit(q); + blk_put_queue(q); } EXPORT_SYMBOL(blk_cleanup_queue); @@ -515,6 +518,11 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) return NULL; } + if (blk_throtl_init(q)) { + kmem_cache_free(blk_requestq_cachep, q); + return NULL; + } + setup_timer(&q->backing_dev_info.laptop_mode_wb_timer, laptop_mode_timer_fn, (unsigned long) q); init_timer(&q->unplug_timer); @@ -1522,6 +1530,15 @@ static inline void __generic_make_request(struct bio *bio) goto end_io; } + blk_throtl_bio(q, &bio); + + /* + * If bio = NULL, bio has been throttled and will be submitted + * later. + */ + if (!bio) + break; + trace_block_bio_queue(q, bio); ret = q->make_request_fn(q, bio); @@ -2580,6 +2597,13 @@ int kblockd_schedule_work(struct request_queue *q, struct work_struct *work) } EXPORT_SYMBOL(kblockd_schedule_work); +int kblockd_schedule_delayed_work(struct request_queue *q, + struct delayed_work *dwork, unsigned long delay) +{ + return queue_delayed_work(kblockd_workqueue, dwork, delay); +} +EXPORT_SYMBOL(kblockd_schedule_delayed_work); + int __init blk_dev_init(void) { BUILD_BUG_ON(__REQ_NR_BITS > 8 * diff --git a/block/blk-throttle.c b/block/blk-throttle.c new file mode 100644 index 000000000000..4b492011e0de --- /dev/null +++ b/block/blk-throttle.c @@ -0,0 +1,909 @@ +/* + * Interface for controlling IO bandwidth on a request queue + * + * Copyright (C) 2010 Vivek Goyal <vgoyal@redhat.com> + */ + +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/blkdev.h> +#include <linux/bio.h> +#include <linux/blktrace_api.h> +#include "blk-cgroup.h" + +/* Max dispatch from a group in 1 round */ +static int throtl_grp_quantum = 8; + +/* Total max dispatch from all groups in one round */ +static int throtl_quantum = 32; + +/* Throttling is performed over 100ms slice and after that slice is renewed */ +static unsigned long throtl_slice = HZ/10; /* 100 ms */ + +struct throtl_rb_root { + struct rb_root rb; + struct rb_node *left; + unsigned int count; + unsigned long min_disptime; +}; + +#define THROTL_RB_ROOT (struct throtl_rb_root) { .rb = RB_ROOT, .left = NULL, \ + .count = 0, .min_disptime = 0} + +#define rb_entry_tg(node) rb_entry((node), struct throtl_grp, rb_node) + +struct throtl_grp { + /* List of throtl groups on the request queue*/ + struct hlist_node tg_node; + + /* active throtl group service_tree member */ + struct rb_node rb_node; + + /* + * Dispatch time in jiffies. This is the estimated time when group + * will unthrottle and is ready to dispatch more bio. It is used as + * key to sort active groups in service tree. + */ + unsigned long disptime; + + struct blkio_group blkg; + atomic_t ref; + unsigned int flags; + + /* Two lists for READ and WRITE */ + struct bio_list bio_lists[2]; + + /* Number of queued bios on READ and WRITE lists */ + unsigned int nr_queued[2]; + + /* bytes per second rate limits */ + uint64_t bps[2]; + + /* Number of bytes disptached in current slice */ + uint64_t bytes_disp[2]; + + /* When did we start a new slice */ + unsigned long slice_start[2]; + unsigned long slice_end[2]; +}; + +struct throtl_data +{ + /* List of throtl groups */ + struct hlist_head tg_list; + + /* service tree for active throtl groups */ + struct throtl_rb_root tg_service_tree; + + struct throtl_grp root_tg; + struct request_queue *queue; + + /* Total Number of queued bios on READ and WRITE lists */ + unsigned int nr_queued[2]; + + /* + * number of total undestroyed groups (excluding root group) + */ + unsigned int nr_undestroyed_grps; + + /* Work for dispatching throttled bios */ + struct delayed_work throtl_work; +}; + +enum tg_state_flags { + THROTL_TG_FLAG_on_rr = 0, /* on round-robin busy list */ +}; + +#define THROTL_TG_FNS(name) \ +static inline void throtl_mark_tg_##name(struct throtl_grp *tg) \ +{ \ + (tg)->flags |= (1 << THROTL_TG_FLAG_##name); \ +} \ +static inline void throtl_clear_tg_##name(struct throtl_grp *tg) \ +{ \ + (tg)->flags &= ~(1 << THROTL_TG_FLAG_##name); \ +} \ +static inline int throtl_tg_##name(const struct throtl_grp *tg) \ +{ \ + return ((tg)->flags & (1 << THROTL_TG_FLAG_##name)) != 0; \ +} + +THROTL_TG_FNS(on_rr); + +#define throtl_log_tg(td, tg, fmt, args...) \ + blk_add_trace_msg((td)->queue, "throtl %s " fmt, \ + blkg_path(&(tg)->blkg), ##args); \ + +#define throtl_log(td, fmt, args...) \ + blk_add_trace_msg((td)->queue, "throtl " fmt, ##args) + +static inline struct throtl_grp *tg_of_blkg(struct blkio_group *blkg) +{ + if (blkg) + return container_of(blkg, struct throtl_grp, blkg); + + return NULL; +} + +static inline int total_nr_queued(struct throtl_data *td) +{ + return (td->nr_queued[0] + td->nr_queued[1]); +} + +static inline struct throtl_grp *throtl_ref_get_tg(struct throtl_grp *tg) +{ + atomic_inc(&tg->ref); + return tg; +} + +static void throtl_put_tg(struct throtl_grp *tg) +{ + BUG_ON(atomic_read(&tg->ref) <= 0); + if (!atomic_dec_and_test(&tg->ref)) + return; + kfree(tg); +} + +static struct throtl_grp * throtl_find_alloc_tg(struct throtl_data *td, + struct cgroup *cgroup) +{ + struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup); + struct throtl_grp *tg = NULL; + void *key = td; + struct backing_dev_info *bdi = &td->queue->backing_dev_info; + unsigned int major, minor; + + /* + * TODO: Speed up blkiocg_lookup_group() by maintaining a radix + * tree of blkg (instead of traversing through hash list all + * the time. + */ + tg = tg_of_blkg(blkiocg_lookup_group(blkcg, key)); + + /* Fill in device details for root group */ + if (tg && !tg->blkg.dev && bdi->dev && dev_name(bdi->dev)) { + sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor); + tg->blkg.dev = MKDEV(major, minor); + goto done; + } + + if (tg) + goto done; + + tg = kzalloc_node(sizeof(*tg), GFP_ATOMIC, td->queue->node); + if (!tg) + goto done; + + INIT_HLIST_NODE(&tg->tg_node); + RB_CLEAR_NODE(&tg->rb_node); + bio_list_init(&tg->bio_lists[0]); + bio_list_init(&tg->bio_lists[1]); + + /* + * Take the initial reference that will be released on destroy + * This can be thought of a joint reference by cgroup and + * request queue which will be dropped by either request queue + * exit or cgroup deletion path depending on who is exiting first. + */ + atomic_set(&tg->ref, 1); + + /* Add group onto cgroup list */ + sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor); + blkiocg_add_blkio_group(blkcg, &tg->blkg, (void *)td, + MKDEV(major, minor), BLKIO_POLICY_THROTL); + + tg->bps[READ] = blkcg_get_read_bps(blkcg, tg->blkg.dev); + tg->bps[WRITE] = blkcg_get_write_bps(blkcg, tg->blkg.dev); + + hlist_add_head(&tg->tg_node, &td->tg_list); + td->nr_undestroyed_grps++; +done: + return tg; +} + +static struct throtl_grp * throtl_get_tg(struct throtl_data *td) +{ + struct cgroup *cgroup; + struct throtl_grp *tg = NULL; + + rcu_read_lock(); + cgroup = task_cgroup(current, blkio_subsys_id); + tg = throtl_find_alloc_tg(td, cgroup); + if (!tg) + tg = &td->root_tg; + rcu_read_unlock(); + return tg; +} + +static struct throtl_grp *throtl_rb_first(struct throtl_rb_root *root) +{ + /* Service tree is empty */ + if (!root->count) + return NULL; + + if (!root->left) + root->left = rb_first(&root->rb); + + if (root->left) + return rb_entry_tg(root->left); + + return NULL; +} + +static void rb_erase_init(struct rb_node *n, struct rb_root *root) +{ + rb_erase(n, root); + RB_CLEAR_NODE(n); +} + +static void throtl_rb_erase(struct rb_node *n, struct throtl_rb_root *root) +{ + if (root->left == n) + root->left = NULL; + rb_erase_init(n, &root->rb); + --root->count; +} + +static void update_min_dispatch_time(struct throtl_rb_root *st) +{ + struct throtl_grp *tg; + + tg = throtl_rb_first(st); + if (!tg) + return; + + st->min_disptime = tg->disptime; +} + +static void +tg_service_tree_add(struct throtl_rb_root *st, struct throtl_grp *tg) +{ + struct rb_node **node = &st->rb.rb_node; + struct rb_node *parent = NULL; + struct throtl_grp *__tg; + unsigned long key = tg->disptime; + int left = 1; + + while (*node != NULL) { + parent = *node; + __tg = rb_entry_tg(parent); + + if (time_before(key, __tg->disptime)) + node = &parent->rb_left; + else { + node = &parent->rb_right; + left = 0; + } + } + + if (left) + st->left = &tg->rb_node; + + rb_link_node(&tg->rb_node, parent, node); + rb_insert_color(&tg->rb_node, &st->rb); +} + +static void __throtl_enqueue_tg(struct throtl_data *td, struct throtl_grp *tg) +{ + struct throtl_rb_root *st = &td->tg_service_tree; + + tg_service_tree_add(st, tg); + throtl_mark_tg_on_rr(tg); + st->count++; +} + +static void throtl_enqueue_tg(struct throtl_data *td, struct throtl_grp *tg) +{ + if (!throtl_tg_on_rr(tg)) + __throtl_enqueue_tg(td, tg); +} + +static void __throtl_dequeue_tg(struct throtl_data *td, struct throtl_grp *tg) +{ + throtl_rb_erase(&tg->rb_node, &td->tg_service_tree); + throtl_clear_tg_on_rr(tg); +} + +static void throtl_dequeue_tg(struct throtl_data *td, struct throtl_grp *tg) +{ + if (throtl_tg_on_rr(tg)) + __throtl_dequeue_tg(td, tg); +} + +static void throtl_schedule_next_dispatch(struct throtl_data *td) +{ + struct throtl_rb_root *st = &td->tg_service_tree; + + /* + * If there are more bios pending, schedule more work. + */ + if (!total_nr_queued(td)) + return; + + BUG_ON(!st->count); + + update_min_dispatch_time(st); + + if (time_before_eq(st->min_disptime, jiffies)) + throtl_schedule_delayed_work(td->queue, 0); + else + throtl_schedule_delayed_work(td->queue, + (st->min_disptime - jiffies)); +} + +static inline void +throtl_start_new_slice(struct throtl_data *td, struct throtl_grp *tg, bool rw) +{ + tg->bytes_disp[rw] = 0; + tg->slice_start[rw] = jiffies; + tg->slice_end[rw] = jiffies + throtl_slice; + throtl_log_tg(td, tg, "[%c] new slice start=%lu end=%lu jiffies=%lu", + rw == READ ? 'R' : 'W', tg->slice_start[rw], + tg->slice_end[rw], jiffies); +} + +static inline void throtl_extend_slice(struct throtl_data *td, + struct throtl_grp *tg, bool rw, unsigned long jiffy_end) +{ + tg->slice_end[rw] = roundup(jiffy_end, throtl_slice); + throtl_log_tg(td, tg, "[%c] extend slice start=%lu end=%lu jiffies=%lu", + rw == READ ? 'R' : 'W', tg->slice_start[rw], + tg->slice_end[rw], jiffies); +} + +/* Determine if previously allocated or extended slice is complete or not */ +static bool +throtl_slice_used(struct throtl_data *td, struct throtl_grp *tg, bool rw) +{ + if (time_in_range(jiffies, tg->slice_start[rw], tg->slice_end[rw])) + return 0; + + return 1; +} + +/* Trim the used slices and adjust slice start accordingly */ +static inline void +throtl_trim_slice(struct throtl_data *td, struct throtl_grp *tg, bool rw) +{ + unsigned long nr_slices, bytes_trim, time_elapsed; + + BUG_ON(time_before(tg->slice_end[rw], tg->slice_start[rw])); + + /* + * If bps are unlimited (-1), then time slice don't get + * renewed. Don't try to trim the slice if slice is used. A new + * slice will start when appropriate. + */ + if (throtl_slice_used(td, tg, rw)) + return; + + time_elapsed = jiffies - tg->slice_start[rw]; + + nr_slices = time_elapsed / throtl_slice; + + if (!nr_slices) + return; + + bytes_trim = (tg->bps[rw] * throtl_slice * nr_slices)/HZ; + + if (!bytes_trim) + return; + + if (tg->bytes_disp[rw] >= bytes_trim) + tg->bytes_disp[rw] -= bytes_trim; + else + tg->bytes_disp[rw] = 0; + + tg->slice_start[rw] += nr_slices * throtl_slice; + + throtl_log_tg(td, tg, "[%c] trim slice nr=%lu bytes=%lu" + " start=%lu end=%lu jiffies=%lu", + rw == READ ? 'R' : 'W', nr_slices, bytes_trim, + tg->slice_start[rw], tg->slice_end[rw], jiffies); +} + +/* + * Returns whether one can dispatch a bio or not. Also returns approx number + * of jiffies to wait before this bio is with-in IO rate and can be dispatched + */ +static bool tg_may_dispatch(struct throtl_data *td, struct throtl_grp *tg, + struct bio *bio, unsigned long *wait) +{ + bool rw = bio_data_dir(bio); + u64 bytes_allowed, extra_bytes; + unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd; + + /* + * Currently whole state machine of group depends on first bio + * queued in the group bio list. So one should not be calling + * this function with a different bio if there are other bios + * queued. + */ + BUG_ON(tg->nr_queued[rw] && bio != bio_list_peek(&tg->bio_lists[rw])); + + /* If tg->bps = -1, then BW is unlimited */ + if (tg->bps[rw] == -1) { + if (wait) + *wait = 0; + return 1; + } + + /* + * If previous slice expired, start a new one otherwise renew/extend + * existing slice to make sure it is at least throtl_slice interval + * long since now. + */ + if (throtl_slice_used(td, tg, rw)) + throtl_start_new_slice(td, tg, rw); + else { + if (time_before(tg->slice_end[rw], jiffies + throtl_slice)) + throtl_extend_slice(td, tg, rw, jiffies + throtl_slice); + } + + jiffy_elapsed = jiffy_elapsed_rnd = jiffies - tg->slice_start[rw]; + + /* Slice has just started. Consider one slice interval */ + if (!jiffy_elapsed) + jiffy_elapsed_rnd = throtl_slice; + + jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, throtl_slice); + + bytes_allowed = (tg->bps[rw] * jiffies_to_msecs(jiffy_elapsed_rnd)) + / MSEC_PER_SEC; + + if (tg->bytes_disp[rw] + bio->bi_size <= bytes_allowed) { + if (wait) + *wait = 0; + return 1; + } + + /* Calc approx time to dispatch */ + extra_bytes = tg->bytes_disp[rw] + bio->bi_size - bytes_allowed; + jiffy_wait = div64_u64(extra_bytes * HZ, tg->bps[rw]); + + if (!jiffy_wait) + jiffy_wait = 1; + + /* + * This wait time is without taking into consideration the rounding + * up we did. Add that time also. + */ + jiffy_wait = jiffy_wait + (jiffy_elapsed_rnd - jiffy_elapsed); + + if (wait) + *wait = jiffy_wait; + + if (time_before(tg->slice_end[rw], jiffies + jiffy_wait)) + throtl_extend_slice(td, tg, rw, jiffies + jiffy_wait); + + return 0; +} + +static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio) +{ + bool rw = bio_data_dir(bio); + bool sync = bio->bi_rw & REQ_SYNC; + + /* Charge the bio to the group */ + tg->bytes_disp[rw] += bio->bi_size; + + /* + * TODO: This will take blkg->stats_lock. Figure out a way + * to avoid this cost. + */ + blkiocg_update_dispatch_stats(&tg->blkg, bio->bi_size, rw, sync); + +} + +static void throtl_add_bio_tg(struct throtl_data *td, struct throtl_grp *tg, + struct bio *bio) +{ + bool rw = bio_data_dir(bio); + + bio_list_add(&tg->bio_lists[rw], bio); + /* Take a bio reference on tg */ + throtl_ref_get_tg(tg); + tg->nr_queued[rw]++; + td->nr_queued[rw]++; + throtl_enqueue_tg(td, tg); +} + +static void tg_update_disptime(struct throtl_data *td, struct throtl_grp *tg) +{ + unsigned long read_wait = -1, write_wait = -1, min_wait = -1, disptime; + struct bio *bio; + + if ((bio = bio_list_peek(&tg->bio_lists[READ]))) + tg_may_dispatch(td, tg, bio, &read_wait); + + if ((bio = bio_list_peek(&tg->bio_lists[WRITE]))) + tg_may_dispatch(td, tg, bio, &write_wait); + + min_wait = min(read_wait, write_wait); + disptime = jiffies + min_wait; + + /* + * If group is already on active tree, then update dispatch time + * only if it is lesser than existing dispatch time. Otherwise + * always update the dispatch time + */ + + if (throtl_tg_on_rr(tg) && time_before(disptime, tg->disptime)) + return; + + /* Update dispatch time */ + throtl_dequeue_tg(td, tg); + tg->disptime = disptime; + throtl_enqueue_tg(td, tg); +} + +static void tg_dispatch_one_bio(struct throtl_data *td, struct throtl_grp *tg, + bool rw, struct bio_list *bl) +{ + struct bio *bio; + + bio = bio_list_pop(&tg->bio_lists[rw]); + tg->nr_queued[rw]--; + /* Drop bio reference on tg */ + throtl_put_tg(tg); + + BUG_ON(td->nr_queued[rw] <= 0); + td->nr_queued[rw]--; + + throtl_charge_bio(tg, bio); + bio_list_add(bl, bio); + bio->bi_rw |= REQ_THROTTLED; + + throtl_trim_slice(td, tg, rw); +} + +static int throtl_dispatch_tg(struct throtl_data *td, struct throtl_grp *tg, + struct bio_list *bl) +{ + unsigned int nr_reads = 0, nr_writes = 0; + unsigned int max_nr_reads = throtl_grp_quantum*3/4; + unsigned int max_nr_writes = throtl_grp_quantum - nr_reads; + struct bio *bio; + + /* Try to dispatch 75% READS and 25% WRITES */ + + while ((bio = bio_list_peek(&tg->bio_lists[READ])) + && tg_may_dispatch(td, tg, bio, NULL)) { + + tg_dispatch_one_bio(td, tg, bio_data_dir(bio), bl); + nr_reads++; + + if (nr_reads >= max_nr_reads) + break; + } + + while ((bio = bio_list_peek(&tg->bio_lists[WRITE])) + && tg_may_dispatch(td, tg, bio, NULL)) { + + tg_dispatch_one_bio(td, tg, bio_data_dir(bio), bl); + nr_writes++; + + if (nr_writes >= max_nr_writes) + break; + } + + return nr_reads + nr_writes; +} + +static int throtl_select_dispatch(struct throtl_data *td, struct bio_list *bl) +{ + unsigned int nr_disp = 0; + struct throtl_grp *tg; + struct throtl_rb_root *st = &td->tg_service_tree; + + while (1) { + tg = throtl_rb_first(st); + + if (!tg) + break; + + if (time_before(jiffies, tg->disptime)) + break; + + throtl_dequeue_tg(td, tg); + + nr_disp += throtl_dispatch_tg(td, tg, bl); + + if (tg->nr_queued[0] || tg->nr_queued[1]) { + tg_update_disptime(td, tg); + throtl_enqueue_tg(td, tg); + } + + if (nr_disp >= throtl_quantum) + break; + } + + return nr_disp; +} + +/* Dispatch throttled bios. Should be called without queue lock held. */ +static int throtl_dispatch(struct request_queue *q) +{ + struct throtl_data *td = q->td; + unsigned int nr_disp = 0; + struct bio_list bio_list_on_stack; + struct bio *bio; + + spin_lock_irq(q->queue_lock); + + if (!total_nr_queued(td)) + goto out; + + bio_list_init(&bio_list_on_stack); + + throtl_log(td, "dispatch nr_queued=%lu read=%u write=%u", + total_nr_queued(td), td->nr_queued[READ], + td->nr_queued[WRITE]); + + nr_disp = throtl_select_dispatch(td, &bio_list_on_stack); + + if (nr_disp) + throtl_log(td, "bios disp=%u", nr_disp); + + throtl_schedule_next_dispatch(td); +out: + spin_unlock_irq(q->queue_lock); + + /* + * If we dispatched some requests, unplug the queue to make sure + * immediate dispatch + */ + if (nr_disp) { + while((bio = bio_list_pop(&bio_list_on_stack))) + generic_make_request(bio); + blk_unplug(q); + } + return nr_disp; +} + +void blk_throtl_work(struct work_struct *work) +{ + struct throtl_data *td = container_of(work, struct throtl_data, + throtl_work.work); + struct request_queue *q = td->queue; + + throtl_dispatch(q); +} + +/* Call with queue lock held */ +void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay) +{ + + struct throtl_data *td = q->td; + struct delayed_work *dwork = &td->throtl_work; + + if (total_nr_queued(td) > 0) { + /* + * We might have a work scheduled to be executed in future. + * Cancel that and schedule a new one. + */ + __cancel_delayed_work(dwork); + kblockd_schedule_delayed_work(q, dwork, delay); + throtl_log(td, "schedule work. delay=%lu jiffies=%lu", + delay, jiffies); + } +} +EXPORT_SYMBOL(throtl_schedule_delayed_work); + +static void +throtl_destroy_tg(struct throtl_data *td, struct throtl_grp *tg) +{ + /* Something wrong if we are trying to remove same group twice */ + BUG_ON(hlist_unhashed(&tg->tg_node)); + + hlist_del_init(&tg->tg_node); + + /* + * Put the reference taken at the time of creation so that when all + * queues are gone, group can be destroyed. + */ + throtl_put_tg(tg); + td->nr_undestroyed_grps--; +} + +static void throtl_release_tgs(struct throtl_data *td) +{ + struct hlist_node *pos, *n; + struct throtl_grp *tg; + + hlist_for_each_entry_safe(tg, pos, n, &td->tg_list, tg_node) { + /* + * If cgroup removal path got to blk_group first and removed + * it from cgroup list, then it will take care of destroying + * cfqg also. + */ + if (!blkiocg_del_blkio_group(&tg->blkg)) + throtl_destroy_tg(td, tg); + } +} + +static void throtl_td_free(struct throtl_data *td) +{ + kfree(td); +} + +/* + * Blk cgroup controller notification saying that blkio_group object is being + * delinked as associated cgroup object is going away. That also means that + * no new IO will come in this group. So get rid of this group as soon as + * any pending IO in the group is finished. + * + * This function is called under rcu_read_lock(). key is the rcu protected + * pointer. That means "key" is a valid throtl_data pointer as long as we are + * rcu read lock. + * + * "key" was fetched from blkio_group under blkio_cgroup->lock. That means + * it should not be NULL as even if queue was going away, cgroup deltion + * path got to it first. + */ +void throtl_unlink_blkio_group(void *key, struct blkio_group *blkg) +{ + unsigned long flags; + struct throtl_data *td = key; + + spin_lock_irqsave(td->queue->queue_lock, flags); + throtl_destroy_tg(td, tg_of_blkg(blkg)); + spin_unlock_irqrestore(td->queue->queue_lock, flags); +} + +static void throtl_update_blkio_group_read_bps (struct blkio_group *blkg, + u64 read_bps) +{ + tg_of_blkg(blkg)->bps[READ] = read_bps; +} + +static void throtl_update_blkio_group_write_bps (struct blkio_group *blkg, + u64 write_bps) +{ + tg_of_blkg(blkg)->bps[WRITE] = write_bps; +} + +void throtl_shutdown_timer_wq(struct request_queue *q) +{ + struct throtl_data *td = q->td; + + cancel_delayed_work_sync(&td->throtl_work); +} + +static struct blkio_policy_type blkio_policy_throtl = { + .ops = { + .blkio_unlink_group_fn = throtl_unlink_blkio_group, + .blkio_update_group_read_bps_fn = + throtl_update_blkio_group_read_bps, + .blkio_update_group_write_bps_fn = + throtl_update_blkio_group_write_bps, + }, +}; + +int blk_throtl_bio(struct request_queue *q, struct bio **biop) +{ + struct throtl_data *td = q->td; + struct throtl_grp *tg; + struct bio *bio = *biop; + bool rw = bio_data_dir(bio), update_disptime = true; + + if (bio->bi_rw & REQ_THROTTLED) { + bio->bi_rw &= ~REQ_THROTTLED; + return 0; + } + + spin_lock_irq(q->queue_lock); + tg = throtl_get_tg(td); + + if (tg->nr_queued[rw]) { + /* + * There is already another bio queued in same dir. No + * need to update dispatch time. + */ + update_disptime = false; + goto queue_bio; + } + + /* Bio is with-in rate limit of group */ + if (tg_may_dispatch(td, tg, bio, NULL)) { + throtl_charge_bio(tg, bio); + goto out; + } + +queue_bio: + throtl_log_tg(td, tg, "[%c] bio. disp=%u sz=%u bps=%llu" + " queued=%d/%d", rw == READ ? 'R' : 'W', + tg->bytes_disp[rw], bio->bi_size, tg->bps[rw], + tg->nr_queued[READ], tg->nr_queued[WRITE]); + + throtl_add_bio_tg(q->td, tg, bio); + *biop = NULL; + + if (update_disptime) { + tg_update_disptime(td, tg); + throtl_schedule_next_dispatch(td); + } + +out: + spin_unlock_irq(q->queue_lock); + return 0; +} + +int blk_throtl_init(struct request_queue *q) +{ + struct throtl_data *td; + struct throtl_grp *tg; + + td = kzalloc_node(sizeof(*td), GFP_KERNEL, q->node); + if (!td) + return -ENOMEM; + + INIT_HLIST_HEAD(&td->tg_list); + td->tg_service_tree = THROTL_RB_ROOT; + + /* Init root group */ + tg = &td->root_tg; + INIT_HLIST_NODE(&tg->tg_node); + RB_CLEAR_NODE(&tg->rb_node); + bio_list_init(&tg->bio_lists[0]); + bio_list_init(&tg->bio_lists[1]); + + /* Practically unlimited BW */ + tg->bps[0] = tg->bps[1] = -1; + atomic_set(&tg->ref, 1); + + INIT_DELAYED_WORK(&td->throtl_work, blk_throtl_work); + + rcu_read_lock(); + blkiocg_add_blkio_group(&blkio_root_cgroup, &tg->blkg, (void *)td, + 0, BLKIO_POLICY_THROTL); + rcu_read_unlock(); + + /* Attach throtl data to request queue */ + td->queue = q; + q->td = td; + return 0; +} + +void blk_throtl_exit(struct request_queue *q) +{ + struct throtl_data *td = q->td; + bool wait = false; + + BUG_ON(!td); + + throtl_shutdown_timer_wq(q); + + spin_lock_irq(q->queue_lock); + throtl_release_tgs(td); + blkiocg_del_blkio_group(&td->root_tg.blkg); + + /* If there are other groups */ + if (td->nr_undestroyed_grps >= 1) + wait = true; + + spin_unlock_irq(q->queue_lock); + + /* + * Wait for tg->blkg->key accessors to exit their grace periods. + * Do this wait only if there are other undestroyed groups out + * there (other than root group). This can happen if cgroup deletion + * path claimed the responsibility of cleaning up a group before + * queue cleanup code get to the group. + * + * Do not call synchronize_rcu() unconditionally as there are drivers + * which create/delete request queue hundreds of times during scan/boot + * and synchronize_rcu() can take significant time and slow down boot. + */ + if (wait) + synchronize_rcu(); + throtl_td_free(td); +} + +static int __init throtl_init(void) +{ + blkio_policy_register(&blkio_policy_throtl); + return 0; +} + +module_init(throtl_init); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index ca83a97c9715..10a0c291b55a 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -130,6 +130,8 @@ enum rq_flag_bits { /* bio only flags */ __REQ_UNPLUG, /* unplug the immediately after submission */ __REQ_RAHEAD, /* read ahead, can fail anytime */ + __REQ_THROTTLED, /* This bio has already been subjected to + * throttling rules. Don't do it again. */ /* request only flags */ __REQ_SORTED, /* elevator knows about this request */ @@ -172,6 +174,7 @@ enum rq_flag_bits { #define REQ_UNPLUG (1 << __REQ_UNPLUG) #define REQ_RAHEAD (1 << __REQ_RAHEAD) +#define REQ_THROTTLED (1 << __REQ_THROTTLED) #define REQ_SORTED (1 << __REQ_SORTED) #define REQ_SOFTBARRIER (1 << __REQ_SOFTBARRIER) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 780824edac16..1341df5806df 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -371,6 +371,11 @@ struct request_queue #if defined(CONFIG_BLK_DEV_BSG) struct bsg_class_device bsg_dev; #endif + +#ifdef CONFIG_BLK_DEV_THROTTLING + /* Throttle data */ + struct throtl_data *td; +#endif }; #define QUEUE_FLAG_CLUSTER 0 /* cluster several segments into 1 */ @@ -1131,6 +1136,7 @@ static inline void put_dev_sector(Sector p) struct work_struct; int kblockd_schedule_work(struct request_queue *q, struct work_struct *work); +int kblockd_schedule_delayed_work(struct request_queue *q, struct delayed_work *dwork, unsigned long delay); #ifdef CONFIG_BLK_CGROUP /* @@ -1174,6 +1180,24 @@ static inline uint64_t rq_io_start_time_ns(struct request *req) } #endif +#ifdef CONFIG_BLK_DEV_THROTTLING +extern int blk_throtl_init(struct request_queue *q); +extern void blk_throtl_exit(struct request_queue *q); +extern int blk_throtl_bio(struct request_queue *q, struct bio **bio); +extern void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay); +extern void throtl_shutdown_timer_wq(struct request_queue *q); +#else /* CONFIG_BLK_DEV_THROTTLING */ +static inline int blk_throtl_bio(struct request_queue *q, struct bio **bio) +{ + return 0; +} + +static inline int blk_throtl_init(struct request_queue *q) { return 0; } +static inline int blk_throtl_exit(struct request_queue *q) { return 0; } +static inline void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay) {} +static inline void throtl_shutdown_timer_wq(struct request_queue *q) {} +#endif /* CONFIG_BLK_DEV_THROTTLING */ + #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \ diff --git a/init/Kconfig b/init/Kconfig index 2de5b1cbadd9..950ba26f7233 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -634,11 +634,14 @@ config BLK_CGROUP Currently, CFQ IO scheduler uses it to recognize task groups and control disk bandwidth allocation (proportional time slice allocation) - to such task groups. + to such task groups. It is also used by bio throttling logic in + block layer to implement upper limit in IO rates on a device. This option only enables generic Block IO controller infrastructure. - One needs to also enable actual IO controlling logic in CFQ for it - to take effect. (CONFIG_CFQ_GROUP_IOSCHED=y). + One needs to also enable actual IO controlling logic/policy. For + enabling proportional weight division of disk bandwidth in CFQ seti + CONFIG_CFQ_GROUP_IOSCHED=y and for enabling throttling policy set + CONFIG_BLK_THROTTLE=y. See Documentation/cgroups/blkio-controller.txt for more information. |