diff --git a/Documentation/block/null_blk.txt b/Documentation/block/null_blk.txt new file mode 100644 index 000000000000..b2830b435895 --- /dev/null +++ b/Documentation/block/null_blk.txt @@ -0,0 +1,72 @@ +Null block device driver +================================================================================ + +I. Overview + +The null block device (/dev/nullb*) is used for benchmarking the various +block-layer implementations. It emulates a block device of X gigabytes in size. +The following instances are possible: + + Single-queue block-layer + - Request-based. + - Single submission queue per device. + - Implements IO scheduling algorithms (CFQ, Deadline, noop). + Multi-queue block-layer + - Request-based. + - Configurable submission queues per device. + No block-layer (Known as bio-based) + - Bio-based. IO requests are submitted directly to the device driver. + - Directly accepts bio data structure and returns them. + +All of them have a completion queue for each core in the system. + +II. Module parameters applicable for all instances: + +queue_mode=[0-2]: Default: 2-Multi-queue + Selects which block-layer the module should instantiate with. + + 0: Bio-based. + 1: Single-queue. + 2: Multi-queue. + +home_node=[0--nr_nodes]: Default: NUMA_NO_NODE + Selects what CPU node the data structures are allocated from. + +gb=[Size in GB]: Default: 250GB + The size of the device reported to the system. + +bs=[Block size (in bytes)]: Default: 512 bytes + The block size reported to the system. + +nr_devices=[Number of devices]: Default: 2 + Number of block devices instantiated. They are instantiated as /dev/nullb0, + etc. + +irq_mode=[0-2]: Default: 1-Soft-irq + The completion mode used for completing IOs to the block-layer. + + 0: None. + 1: Soft-irq. Uses IPI to complete IOs across CPU nodes. Simulates the overhead + when IOs are issued from another CPU node than the home the device is + connected to. + 2: Timer: Waits a specific period (completion_nsec) for each IO before + completion. + +completion_nsec=[ns]: Default: 10.000ns + Combined with irq_mode=2 (timer). The time each completion event must wait. + +submit_queues=[0..nr_cpus]: + The number of submission queues attached to the device driver. If unset, it + defaults to 1 on single-queue and bio-based instances. For multi-queue, + it is ignored when use_per_node_hctx module parameter is 1. + +hw_queue_depth=[0..qdepth]: Default: 64 + The hardware queue depth of the device. + +III: Multi-queue specific parameters + +use_per_node_hctx=[0/1]: Default: 0 + 0: The number of submit queues are set to the value of the submit_queues + parameter. + 1: The multi-queue block layer is instantiated with a hardware dispatch + queue for each CPU node in the system. diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index ba6cf8e9aa0a..b91ce75bd35d 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -335,9 +335,22 @@ static struct kobj_type blk_mq_hw_ktype = { void blk_mq_unregister_disk(struct gendisk *disk) { struct request_queue *q = disk->queue; + struct blk_mq_hw_ctx *hctx; + struct blk_mq_ctx *ctx; + int i, j; + + queue_for_each_hw_ctx(q, hctx, i) { + hctx_for_each_ctx(hctx, ctx, j) { + kobject_del(&ctx->kobj); + kobject_put(&ctx->kobj); + } + kobject_del(&hctx->kobj); + kobject_put(&hctx->kobj); + } kobject_uevent(&q->mq_kobj, KOBJ_REMOVE); kobject_del(&q->mq_kobj); + kobject_put(&q->mq_kobj); kobject_put(&disk_to_dev(disk)->kobj); } diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c index f370fc13aea5..a2e69d26266d 100644 --- a/drivers/block/null_blk.c +++ b/drivers/block/null_blk.c @@ -1,4 +1,5 @@ #include + #include #include #include @@ -65,7 +66,7 @@ enum { NULL_Q_MQ = 2, }; -static int submit_queues = 1; +static int submit_queues; module_param(submit_queues, int, S_IRUGO); MODULE_PARM_DESC(submit_queues, "Number of submission queues"); @@ -101,9 +102,9 @@ static int hw_queue_depth = 64; module_param(hw_queue_depth, int, S_IRUGO); MODULE_PARM_DESC(hw_queue_depth, "Queue depth for each hardware queue. Default: 64"); -static bool use_per_node_hctx = true; +static bool use_per_node_hctx = false; module_param(use_per_node_hctx, bool, S_IRUGO); -MODULE_PARM_DESC(use_per_node_hctx, "Use per-node allocation for hardware context queues. Default: true"); +MODULE_PARM_DESC(use_per_node_hctx, "Use per-node allocation for hardware context queues. Default: false"); static void put_tag(struct nullb_queue *nq, unsigned int tag) { @@ -346,8 +347,37 @@ static int null_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *rq) static struct blk_mq_hw_ctx *null_alloc_hctx(struct blk_mq_reg *reg, unsigned int hctx_index) { - return kzalloc_node(sizeof(struct blk_mq_hw_ctx), GFP_KERNEL, - hctx_index); + int b_size = DIV_ROUND_UP(reg->nr_hw_queues, nr_online_nodes); + int tip = (reg->nr_hw_queues % nr_online_nodes); + int node = 0, i, n; + + /* + * Split submit queues evenly wrt to the number of nodes. If uneven, + * fill the first buckets with one extra, until the rest is filled with + * no extra. + */ + for (i = 0, n = 1; i < hctx_index; i++, n++) { + if (n % b_size == 0) { + n = 0; + node++; + + tip--; + if (!tip) + b_size = reg->nr_hw_queues / nr_online_nodes; + } + } + + /* + * A node might not be online, therefore map the relative node id to the + * real node id. + */ + for_each_online_node(n) { + if (!node) + break; + node--; + } + + return kzalloc_node(sizeof(struct blk_mq_hw_ctx), GFP_KERNEL, n); } static void null_free_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_index) @@ -355,16 +385,24 @@ static void null_free_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_index) kfree(hctx); } +static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq) +{ + BUG_ON(!nullb); + BUG_ON(!nq); + + init_waitqueue_head(&nq->wait); + nq->queue_depth = nullb->queue_depth; +} + static int null_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, unsigned int index) { struct nullb *nullb = data; struct nullb_queue *nq = &nullb->queues[index]; - init_waitqueue_head(&nq->wait); - nq->queue_depth = nullb->queue_depth; - nullb->nr_queues++; hctx->driver_data = nq; + null_init_queue(nullb, nq); + nullb->nr_queues++; return 0; } @@ -417,13 +455,13 @@ static int setup_commands(struct nullb_queue *nq) nq->cmds = kzalloc(nq->queue_depth * sizeof(*cmd), GFP_KERNEL); if (!nq->cmds) - return 1; + return -ENOMEM; tag_size = ALIGN(nq->queue_depth, BITS_PER_LONG) / BITS_PER_LONG; nq->tag_map = kzalloc(tag_size * sizeof(unsigned long), GFP_KERNEL); if (!nq->tag_map) { kfree(nq->cmds); - return 1; + return -ENOMEM; } for (i = 0; i < nq->queue_depth; i++) { @@ -454,33 +492,37 @@ static void cleanup_queues(struct nullb *nullb) static int setup_queues(struct nullb *nullb) { - struct nullb_queue *nq; - int i; - - nullb->queues = kzalloc(submit_queues * sizeof(*nq), GFP_KERNEL); + nullb->queues = kzalloc(submit_queues * sizeof(struct nullb_queue), + GFP_KERNEL); if (!nullb->queues) - return 1; + return -ENOMEM; nullb->nr_queues = 0; nullb->queue_depth = hw_queue_depth; - if (queue_mode == NULL_Q_MQ) - return 0; + return 0; +} + +static int init_driver_queues(struct nullb *nullb) +{ + struct nullb_queue *nq; + int i, ret = 0; for (i = 0; i < submit_queues; i++) { nq = &nullb->queues[i]; - init_waitqueue_head(&nq->wait); - nq->queue_depth = hw_queue_depth; - if (setup_commands(nq)) - break; + + null_init_queue(nullb, nq); + + ret = setup_commands(nq); + if (ret) + goto err_queue; nullb->nr_queues++; } - if (i == submit_queues) - return 0; - + return 0; +err_queue: cleanup_queues(nullb); - return 1; + return ret; } static int null_add_dev(void) @@ -518,11 +560,13 @@ static int null_add_dev(void) } else if (queue_mode == NULL_Q_BIO) { nullb->q = blk_alloc_queue_node(GFP_KERNEL, home_node); blk_queue_make_request(nullb->q, null_queue_bio); + init_driver_queues(nullb); } else { nullb->q = blk_init_queue_node(null_request_fn, &nullb->lock, home_node); blk_queue_prep_rq(nullb->q, null_rq_prep_fn); if (nullb->q) blk_queue_softirq_done(nullb->q, null_softirq_done_fn); + init_driver_queues(nullb); } if (!nullb->q) @@ -579,7 +623,13 @@ static int __init null_init(void) } #endif - if (submit_queues > nr_cpu_ids) + if (queue_mode == NULL_Q_MQ && use_per_node_hctx) { + if (submit_queues < nr_online_nodes) { + pr_warn("null_blk: submit_queues param is set to %u.", + nr_online_nodes); + submit_queues = nr_online_nodes; + } + } else if (submit_queues > nr_cpu_ids) submit_queues = nr_cpu_ids; else if (!submit_queues) submit_queues = 1; diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c index 9199c93be926..eb6e1e0e8db2 100644 --- a/drivers/block/skd_main.c +++ b/drivers/block/skd_main.c @@ -5269,7 +5269,7 @@ const char *skd_skdev_state_to_str(enum skd_drvr_state state) } } -const char *skd_skmsg_state_to_str(enum skd_fit_msg_state state) +static const char *skd_skmsg_state_to_str(enum skd_fit_msg_state state) { switch (state) { case SKD_MSG_STATE_IDLE: @@ -5281,7 +5281,7 @@ const char *skd_skmsg_state_to_str(enum skd_fit_msg_state state) } } -const char *skd_skreq_state_to_str(enum skd_req_state state) +static const char *skd_skreq_state_to_str(enum skd_req_state state) { switch (state) { case SKD_REQ_STATE_IDLE: diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c index 2b46bf1d7e40..4c9852d92b0a 100644 --- a/drivers/md/bcache/alloc.c +++ b/drivers/md/bcache/alloc.c @@ -421,9 +421,11 @@ out: if (watermark <= WATERMARK_METADATA) { SET_GC_MARK(b, GC_MARK_METADATA); + SET_GC_MOVE(b, 0); b->prio = BTREE_PRIO; } else { SET_GC_MARK(b, GC_MARK_RECLAIMABLE); + SET_GC_MOVE(b, 0); b->prio = INITIAL_PRIO; } diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 4beb55a0ff30..754f43177483 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -197,7 +197,7 @@ struct bucket { uint8_t disk_gen; uint8_t last_gc; /* Most out of date gen in the btree */ uint8_t gc_gen; - uint16_t gc_mark; + uint16_t gc_mark; /* Bitfield used by GC. See below for field */ }; /* @@ -209,7 +209,8 @@ BITMASK(GC_MARK, struct bucket, gc_mark, 0, 2); #define GC_MARK_RECLAIMABLE 0 #define GC_MARK_DIRTY 1 #define GC_MARK_METADATA 2 -BITMASK(GC_SECTORS_USED, struct bucket, gc_mark, 2, 14); +BITMASK(GC_SECTORS_USED, struct bucket, gc_mark, 2, 13); +BITMASK(GC_MOVE, struct bucket, gc_mark, 15, 1); #include "journal.h" #include "stats.h" @@ -372,14 +373,14 @@ struct cached_dev { unsigned char writeback_percent; unsigned writeback_delay; - int writeback_rate_change; - int64_t writeback_rate_derivative; uint64_t writeback_rate_target; + int64_t writeback_rate_proportional; + int64_t writeback_rate_derivative; + int64_t writeback_rate_change; unsigned writeback_rate_update_seconds; unsigned writeback_rate_d_term; unsigned writeback_rate_p_term_inverse; - unsigned writeback_rate_d_smooth; }; enum alloc_watermarks { @@ -445,7 +446,6 @@ struct cache { * call prio_write() to keep gens from wrapping. */ uint8_t need_save_prio; - unsigned gc_move_threshold; /* * If nonzero, we know we aren't going to find any buckets to invalidate diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 5e2765aadce1..31bb53fcc67a 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -1561,6 +1561,28 @@ size_t bch_btree_gc_finish(struct cache_set *c) SET_GC_MARK(PTR_BUCKET(c, &c->uuid_bucket, i), GC_MARK_METADATA); + /* don't reclaim buckets to which writeback keys point */ + rcu_read_lock(); + for (i = 0; i < c->nr_uuids; i++) { + struct bcache_device *d = c->devices[i]; + struct cached_dev *dc; + struct keybuf_key *w, *n; + unsigned j; + + if (!d || UUID_FLASH_ONLY(&c->uuids[i])) + continue; + dc = container_of(d, struct cached_dev, disk); + + spin_lock(&dc->writeback_keys.lock); + rbtree_postorder_for_each_entry_safe(w, n, + &dc->writeback_keys.keys, node) + for (j = 0; j < KEY_PTRS(&w->key); j++) + SET_GC_MARK(PTR_BUCKET(c, &w->key, j), + GC_MARK_DIRTY); + spin_unlock(&dc->writeback_keys.lock); + } + rcu_read_unlock(); + for_each_cache(ca, c, i) { uint64_t *i; @@ -1817,7 +1839,8 @@ static bool fix_overlapping_extents(struct btree *b, struct bkey *insert, if (KEY_START(k) > KEY_START(insert) + sectors_found) goto check_failed; - if (KEY_PTRS(replace_key) != KEY_PTRS(k)) + if (KEY_PTRS(k) != KEY_PTRS(replace_key) || + KEY_DIRTY(k) != KEY_DIRTY(replace_key)) goto check_failed; /* skip past gen */ @@ -2217,7 +2240,7 @@ struct btree_insert_op { struct bkey *replace_key; }; -int btree_insert_fn(struct btree_op *b_op, struct btree *b) +static int btree_insert_fn(struct btree_op *b_op, struct btree *b) { struct btree_insert_op *op = container_of(b_op, struct btree_insert_op, op); diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c index 7c1275e66025..f2f0998c4a91 100644 --- a/drivers/md/bcache/movinggc.c +++ b/drivers/md/bcache/movinggc.c @@ -25,10 +25,9 @@ static bool moving_pred(struct keybuf *buf, struct bkey *k) unsigned i; for (i = 0; i < KEY_PTRS(k); i++) { - struct cache *ca = PTR_CACHE(c, k, i); struct bucket *g = PTR_BUCKET(c, k, i); - if (GC_SECTORS_USED(g) < ca->gc_move_threshold) + if (GC_MOVE(g)) return true; } @@ -65,11 +64,16 @@ static void write_moving_finish(struct closure *cl) static void read_moving_endio(struct bio *bio, int error) { + struct bbio *b = container_of(bio, struct bbio, bio); struct moving_io *io = container_of(bio->bi_private, struct moving_io, cl); if (error) io->op.error = error; + else if (!KEY_DIRTY(&b->key) && + ptr_stale(io->op.c, &b->key, 0)) { + io->op.error = -EINTR; + } bch_bbio_endio(io->op.c, bio, error, "reading data to move"); } @@ -141,6 +145,11 @@ static void read_moving(struct cache_set *c) if (!w) break; + if (ptr_stale(c, &w->key, 0)) { + bch_keybuf_del(&c->moving_gc_keys, w); + continue; + } + io = kzalloc(sizeof(struct moving_io) + sizeof(struct bio_vec) * DIV_ROUND_UP(KEY_SIZE(&w->key), PAGE_SECTORS), GFP_KERNEL); @@ -184,7 +193,8 @@ static bool bucket_cmp(struct bucket *l, struct bucket *r) static unsigned bucket_heap_top(struct cache *ca) { - return GC_SECTORS_USED(heap_peek(&ca->heap)); + struct bucket *b; + return (b = heap_peek(&ca->heap)) ? GC_SECTORS_USED(b) : 0; } void bch_moving_gc(struct cache_set *c) @@ -226,9 +236,8 @@ void bch_moving_gc(struct cache_set *c) sectors_to_move -= GC_SECTORS_USED(b); } - ca->gc_move_threshold = bucket_heap_top(ca); - - pr_debug("threshold %u", ca->gc_move_threshold); + while (heap_pop(&ca->heap, b, bucket_cmp)) + SET_GC_MOVE(b, 1); } mutex_unlock(&c->bucket_lock); diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index dec15cd2d797..c57bfa071a57 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1676,7 +1676,7 @@ err: static bool can_attach_cache(struct cache *ca, struct cache_set *c) { return ca->sb.block_size == c->sb.block_size && - ca->sb.bucket_size == c->sb.block_size && + ca->sb.bucket_size == c->sb.bucket_size && ca->sb.nr_in_set == c->sb.nr_in_set; } diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index 80d4c2bee18a..a1f85612f0b3 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -83,7 +83,6 @@ rw_attribute(writeback_rate); rw_attribute(writeback_rate_update_seconds); rw_attribute(writeback_rate_d_term); rw_attribute(writeback_rate_p_term_inverse); -rw_attribute(writeback_rate_d_smooth); read_attribute(writeback_rate_debug); read_attribute(stripe_size); @@ -129,31 +128,41 @@ SHOW(__bch_cached_dev) var_printf(writeback_running, "%i"); var_print(writeback_delay); var_print(writeback_percent); - sysfs_print(writeback_rate, dc->writeback_rate.rate); + sysfs_hprint(writeback_rate, dc->writeback_rate.rate << 9); var_print(writeback_rate_update_seconds); var_print(writeback_rate_d_term); var_print(writeback_rate_p_term_inverse); - var_print(writeback_rate_d_smooth); if (attr == &sysfs_writeback_rate_debug) { + char rate[20]; char dirty[20]; - char derivative[20]; char target[20]; - bch_hprint(dirty, - bcache_dev_sectors_dirty(&dc->disk) << 9); - bch_hprint(derivative, dc->writeback_rate_derivative << 9); + char proportional[20]; + char derivative[20]; + char change[20]; + s64 next_io; + + bch_hprint(rate, dc->writeback_rate.rate << 9); + bch_hprint(dirty, bcache_dev_sectors_dirty(&dc->disk) << 9); bch_hprint(target, dc->writeback_rate_target << 9); + bch_hprint(proportional,dc->writeback_rate_proportional << 9); + bch_hprint(derivative, dc->writeback_rate_derivative << 9); + bch_hprint(change, dc->writeback_rate_change << 9); + + next_io = div64_s64(dc->writeback_rate.next - local_clock(), + NSEC_PER_MSEC); return sprintf(buf, - "rate:\t\t%u\n" - "change:\t\t%i\n" + "rate:\t\t%s/sec\n" "dirty:\t\t%s\n" + "target:\t\t%s\n" + "proportional:\t%s\n" "derivative:\t%s\n" - "target:\t\t%s\n", - dc->writeback_rate.rate, - dc->writeback_rate_change, - dirty, derivative, target); + "change:\t\t%s/sec\n" + "next io:\t%llims\n", + rate, dirty, target, proportional, + derivative, change, next_io); } sysfs_hprint(dirty_data, @@ -189,6 +198,7 @@ STORE(__cached_dev) struct kobj_uevent_env *env; #define d_strtoul(var) sysfs_strtoul(var, dc->var) +#define d_strtoul_nonzero(var) sysfs_strtoul_clamp(var, dc->var, 1, INT_MAX) #define d_strtoi_h(var) sysfs_hatoi(var, dc->var) sysfs_strtoul(data_csum, dc->disk.data_csum); @@ -197,16 +207,15 @@ STORE(__cached_dev) d_strtoul(writeback_metadata); d_strtoul(writeback_running); d_strtoul(writeback_delay); - sysfs_strtoul_clamp(writeback_rate, - dc->writeback_rate.rate, 1, 1000000); + sysfs_strtoul_clamp(writeback_percent, dc->writeback_percent, 0, 40); - d_strtoul(writeback_rate_update_seconds); + sysfs_strtoul_clamp(writeback_rate, + dc->writeback_rate.rate, 1, INT_MAX); + + d_strtoul_nonzero(writeback_rate_update_seconds); d_strtoul(writeback_rate_d_term); - d_strtoul(writeback_rate_p_term_inverse); - sysfs_strtoul_clamp(writeback_rate_p_term_inverse, - dc->writeback_rate_p_term_inverse, 1, INT_MAX); - d_strtoul(writeback_rate_d_smooth); + d_strtoul_nonzero(writeback_rate_p_term_inverse); d_strtoi_h(sequential_cutoff); d_strtoi_h(readahead); @@ -313,7 +322,6 @@ static struct attribute *bch_cached_dev_files[] = { &sysfs_writeback_rate_update_seconds, &sysfs_writeback_rate_d_term, &sysfs_writeback_rate_p_term_inverse, - &sysfs_writeback_rate_d_smooth, &sysfs_writeback_rate_debug, &sysfs_dirty_data, &sysfs_stripe_size, diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c index 462214eeacbe..bb37618e7664 100644 --- a/drivers/md/bcache/util.c +++ b/drivers/md/bcache/util.c @@ -209,7 +209,13 @@ uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done) { uint64_t now = local_clock(); - d->next += div_u64(done, d->rate); + d->next += div_u64(done * NSEC_PER_SEC, d->rate); + + if (time_before64(now + NSEC_PER_SEC, d->next)) + d->next = now + NSEC_PER_SEC; + + if (time_after64(now - NSEC_PER_SEC * 2, d->next)) + d->next = now - NSEC_PER_SEC * 2; return time_after64(d->next, now) ? div_u64(d->next - now, NSEC_PER_SEC / HZ) diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h index 362c4b3f8b4a..1030c6020e98 100644 --- a/drivers/md/bcache/util.h +++ b/drivers/md/bcache/util.h @@ -110,7 +110,7 @@ do { \ _r; \ }) -#define heap_peek(h) ((h)->size ? (h)->data[0] : NULL) +#define heap_peek(h) ((h)->used ? (h)->data[0] : NULL) #define heap_full(h) ((h)->used == (h)->size) diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index 99053b1251be..6c44fe059c27 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -30,38 +30,40 @@ static void __update_writeback_rate(struct cached_dev *dc) /* PD controller */ - int change = 0; - int64_t error; int64_t dirty = bcache_dev_sectors_dirty(&dc->disk); int64_t derivative = dirty - dc->disk.sectors_dirty_last; + int64_t proportional = dirty - target; + int64_t change; dc->disk.sectors_dirty_last = dirty; - derivative *= dc->writeback_rate_d_term; - derivative = clamp(derivative, -dirty, dirty); + /* Scale to sectors per second */ + + proportional *= dc->writeback_rate_update_seconds; + proportional = div_s64(proportional, dc->writeback_rate_p_term_inverse); + + derivative = div_s64(derivative, dc->writeback_rate_update_seconds); derivative = ewma_add(dc->disk.sectors_dirty_derivative, derivative, - dc->writeback_rate_d_smooth, 0); + (dc->writeback_rate_d_term / + dc->writeback_rate_update_seconds) ?: 1, 0); - /* Avoid divide by zero */ - if (!target) - goto out; + derivative *= dc->writeback_rate_d_term; + derivative = div_s64(derivative, dc->writeback_rate_p_term_inverse); - error = div64_s64((dirty + derivative - target) << 8, target); - - change = div_s64((dc->writeback_rate.rate * error) >> 8, - dc->writeback_rate_p_term_inverse); + change = proportional + derivative; /* Don't increase writeback rate if the device isn't keeping up */ if (change > 0 && time_after64(local_clock(), - dc->writeback_rate.next + 10 * NSEC_PER_MSEC)) + dc->writeback_rate.next + NSEC_PER_MSEC)) change = 0; dc->writeback_rate.rate = - clamp_t(int64_t, dc->writeback_rate.rate + change, + clamp_t(int64_t, (int64_t) dc->writeback_rate.rate + change, 1, NSEC_PER_MSEC); -out: + + dc->writeback_rate_proportional = proportional; dc->writeback_rate_derivative = derivative; dc->writeback_rate_change = change; dc->writeback_rate_target = target; @@ -87,15 +89,11 @@ static void update_writeback_rate(struct work_struct *work) static unsigned writeback_delay(struct cached_dev *dc, unsigned sectors) { - uint64_t ret; - if (test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) || !dc->writeback_percent) return 0; - ret = bch_next_delay(&dc->writeback_rate, sectors * 10000000ULL); - - return min_t(uint64_t, ret, HZ); + return bch_next_delay(&dc->writeback_rate, sectors); } struct dirty_io { @@ -241,7 +239,7 @@ static void read_dirty(struct cached_dev *dc) if (KEY_START(&w->key) != dc->last_read || jiffies_to_msecs(delay) > 50) while (!kthread_should_stop() && delay) - delay = schedule_timeout_interruptible(delay); + delay = schedule_timeout_uninterruptible(delay); dc->last_read = KEY_OFFSET(&w->key); @@ -438,7 +436,7 @@ static int bch_writeback_thread(void *arg) while (delay && !kthread_should_stop() && !test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags)) - delay = schedule_timeout_interruptible(delay); + delay = schedule_timeout_uninterruptible(delay); } } @@ -476,6 +474,8 @@ void bch_sectors_dirty_init(struct cached_dev *dc) bch_btree_map_keys(&op.op, dc->disk.c, &KEY(op.inode, 0, 0), sectors_dirty_init_fn, 0); + + dc->disk.sectors_dirty_last = bcache_dev_sectors_dirty(&dc->disk); } int bch_cached_dev_writeback_init(struct cached_dev *dc) @@ -490,18 +490,15 @@ int bch_cached_dev_writeback_init(struct cached_dev *dc) dc->writeback_delay = 30; dc->writeback_rate.rate = 1024; - dc->writeback_rate_update_seconds = 30; - dc->writeback_rate_d_term = 16; - dc->writeback_rate_p_term_inverse = 64; - dc->writeback_rate_d_smooth = 8; + dc->writeback_rate_update_seconds = 5; + dc->writeback_rate_d_term = 30; + dc->writeback_rate_p_term_inverse = 6000; dc->writeback_thread = kthread_create(bch_writeback_thread, dc, "bcache_writeback"); if (IS_ERR(dc->writeback_thread)) return PTR_ERR(dc->writeback_thread); - set_task_state(dc->writeback_thread, TASK_INTERRUPTIBLE); - INIT_DELAYED_WORK(&dc->writeback_rate_update, update_writeback_rate); schedule_delayed_work(&dc->writeback_rate_update, dc->writeback_rate_update_seconds * HZ);