123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561 |
- /*
- * background writeback - scan btree for dirty data and write it to the backing
- * device
- *
- * Copyright 2010, 2011 Kent Overstreet <kent.overstreet@gmail.com>
- * Copyright 2012 Google, Inc.
- */
- #include "bcache.h"
- #include "btree.h"
- #include "debug.h"
- #include "writeback.h"
- #include <linux/delay.h>
- #include <linux/freezer.h>
- #include <linux/kthread.h>
- #include <trace/events/bcache.h>
- /* Rate limiting */
- static void __update_writeback_rate(struct cached_dev *dc)
- {
- struct cache_set *c = dc->disk.c;
- uint64_t cache_sectors = c->nbuckets * c->sb.bucket_size -
- bcache_flash_devs_sectors_dirty(c);
- uint64_t cache_dirty_target =
- div_u64(cache_sectors * dc->writeback_percent, 100);
- int64_t target = div64_u64(cache_dirty_target * bdev_sectors(dc->bdev),
- c->cached_dev_sectors);
- /* PD controller */
- 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;
- /* 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_term /
- dc->writeback_rate_update_seconds) ?: 1, 0);
- derivative *= dc->writeback_rate_d_term;
- derivative = div_s64(derivative, 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 + NSEC_PER_MSEC))
- change = 0;
- dc->writeback_rate.rate =
- clamp_t(int64_t, (int64_t) dc->writeback_rate.rate + change,
- 1, NSEC_PER_MSEC);
- dc->writeback_rate_proportional = proportional;
- dc->writeback_rate_derivative = derivative;
- dc->writeback_rate_change = change;
- dc->writeback_rate_target = target;
- }
- static void update_writeback_rate(struct work_struct *work)
- {
- struct cached_dev *dc = container_of(to_delayed_work(work),
- struct cached_dev,
- writeback_rate_update);
- down_read(&dc->writeback_lock);
- if (atomic_read(&dc->has_dirty) &&
- dc->writeback_percent)
- __update_writeback_rate(dc);
- up_read(&dc->writeback_lock);
- schedule_delayed_work(&dc->writeback_rate_update,
- dc->writeback_rate_update_seconds * HZ);
- }
- static unsigned writeback_delay(struct cached_dev *dc, unsigned sectors)
- {
- if (test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) ||
- !dc->writeback_percent)
- return 0;
- return bch_next_delay(&dc->writeback_rate, sectors);
- }
- struct dirty_io {
- struct closure cl;
- struct cached_dev *dc;
- struct bio bio;
- };
- static void dirty_init(struct keybuf_key *w)
- {
- struct dirty_io *io = w->private;
- struct bio *bio = &io->bio;
- bio_init(bio);
- if (!io->dc->writeback_percent)
- bio_set_prio(bio, IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0));
- bio->bi_iter.bi_size = KEY_SIZE(&w->key) << 9;
- bio->bi_max_vecs = DIV_ROUND_UP(KEY_SIZE(&w->key), PAGE_SECTORS);
- bio->bi_private = w;
- bio->bi_io_vec = bio->bi_inline_vecs;
- bch_bio_map(bio, NULL);
- }
- static void dirty_io_destructor(struct closure *cl)
- {
- struct dirty_io *io = container_of(cl, struct dirty_io, cl);
- kfree(io);
- }
- static void write_dirty_finish(struct closure *cl)
- {
- struct dirty_io *io = container_of(cl, struct dirty_io, cl);
- struct keybuf_key *w = io->bio.bi_private;
- struct cached_dev *dc = io->dc;
- struct bio_vec *bv;
- int i;
- bio_for_each_segment_all(bv, &io->bio, i)
- __free_page(bv->bv_page);
- /* This is kind of a dumb way of signalling errors. */
- if (KEY_DIRTY(&w->key)) {
- int ret;
- unsigned i;
- struct keylist keys;
- bch_keylist_init(&keys);
- bkey_copy(keys.top, &w->key);
- SET_KEY_DIRTY(keys.top, false);
- bch_keylist_push(&keys);
- for (i = 0; i < KEY_PTRS(&w->key); i++)
- atomic_inc(&PTR_BUCKET(dc->disk.c, &w->key, i)->pin);
- ret = bch_btree_insert(dc->disk.c, &keys, NULL, &w->key);
- if (ret)
- trace_bcache_writeback_collision(&w->key);
- atomic_long_inc(ret
- ? &dc->disk.c->writeback_keys_failed
- : &dc->disk.c->writeback_keys_done);
- }
- bch_keybuf_del(&dc->writeback_keys, w);
- up(&dc->in_flight);
- closure_return_with_destructor(cl, dirty_io_destructor);
- }
- static void dirty_endio(struct bio *bio)
- {
- struct keybuf_key *w = bio->bi_private;
- struct dirty_io *io = w->private;
- if (bio->bi_error)
- SET_KEY_DIRTY(&w->key, false);
- closure_put(&io->cl);
- }
- static void write_dirty(struct closure *cl)
- {
- struct dirty_io *io = container_of(cl, struct dirty_io, cl);
- struct keybuf_key *w = io->bio.bi_private;
- dirty_init(w);
- io->bio.bi_rw = WRITE;
- io->bio.bi_iter.bi_sector = KEY_START(&w->key);
- io->bio.bi_bdev = io->dc->bdev;
- io->bio.bi_end_io = dirty_endio;
- closure_bio_submit(&io->bio, cl);
- continue_at(cl, write_dirty_finish, io->dc->writeback_write_wq);
- }
- static void read_dirty_endio(struct bio *bio)
- {
- struct keybuf_key *w = bio->bi_private;
- struct dirty_io *io = w->private;
- bch_count_io_errors(PTR_CACHE(io->dc->disk.c, &w->key, 0),
- bio->bi_error, "reading dirty data from cache");
- dirty_endio(bio);
- }
- static void read_dirty_submit(struct closure *cl)
- {
- struct dirty_io *io = container_of(cl, struct dirty_io, cl);
- closure_bio_submit(&io->bio, cl);
- continue_at(cl, write_dirty, io->dc->writeback_write_wq);
- }
- static void read_dirty(struct cached_dev *dc)
- {
- unsigned delay = 0;
- struct keybuf_key *w;
- struct dirty_io *io;
- struct closure cl;
- closure_init_stack(&cl);
- /*
- * XXX: if we error, background writeback just spins. Should use some
- * mempools.
- */
- while (!kthread_should_stop()) {
- try_to_freeze();
- w = bch_keybuf_next(&dc->writeback_keys);
- if (!w)
- break;
- BUG_ON(ptr_stale(dc->disk.c, &w->key, 0));
- if (KEY_START(&w->key) != dc->last_read ||
- jiffies_to_msecs(delay) > 50)
- while (!kthread_should_stop() && delay)
- delay = schedule_timeout_interruptible(delay);
- dc->last_read = KEY_OFFSET(&w->key);
- io = kzalloc(sizeof(struct dirty_io) + sizeof(struct bio_vec)
- * DIV_ROUND_UP(KEY_SIZE(&w->key), PAGE_SECTORS),
- GFP_KERNEL);
- if (!io)
- goto err;
- w->private = io;
- io->dc = dc;
- dirty_init(w);
- io->bio.bi_iter.bi_sector = PTR_OFFSET(&w->key, 0);
- io->bio.bi_bdev = PTR_CACHE(dc->disk.c,
- &w->key, 0)->bdev;
- io->bio.bi_rw = READ;
- io->bio.bi_end_io = read_dirty_endio;
- if (bio_alloc_pages(&io->bio, GFP_KERNEL))
- goto err_free;
- trace_bcache_writeback(&w->key);
- down(&dc->in_flight);
- closure_call(&io->cl, read_dirty_submit, NULL, &cl);
- delay = writeback_delay(dc, KEY_SIZE(&w->key));
- }
- if (0) {
- err_free:
- kfree(w->private);
- err:
- bch_keybuf_del(&dc->writeback_keys, w);
- }
- /*
- * Wait for outstanding writeback IOs to finish (and keybuf slots to be
- * freed) before refilling again
- */
- closure_sync(&cl);
- }
- /* Scan for dirty data */
- void bcache_dev_sectors_dirty_add(struct cache_set *c, unsigned inode,
- uint64_t offset, int nr_sectors)
- {
- struct bcache_device *d = c->devices[inode];
- unsigned stripe_offset, stripe, sectors_dirty;
- if (!d)
- return;
- stripe = offset_to_stripe(d, offset);
- stripe_offset = offset & (d->stripe_size - 1);
- while (nr_sectors) {
- int s = min_t(unsigned, abs(nr_sectors),
- d->stripe_size - stripe_offset);
- if (nr_sectors < 0)
- s = -s;
- if (stripe >= d->nr_stripes)
- return;
- sectors_dirty = atomic_add_return(s,
- d->stripe_sectors_dirty + stripe);
- if (sectors_dirty == d->stripe_size)
- set_bit(stripe, d->full_dirty_stripes);
- else
- clear_bit(stripe, d->full_dirty_stripes);
- nr_sectors -= s;
- stripe_offset = 0;
- stripe++;
- }
- }
- static bool dirty_pred(struct keybuf *buf, struct bkey *k)
- {
- struct cached_dev *dc = container_of(buf, struct cached_dev, writeback_keys);
- BUG_ON(KEY_INODE(k) != dc->disk.id);
- return KEY_DIRTY(k);
- }
- static void refill_full_stripes(struct cached_dev *dc)
- {
- struct keybuf *buf = &dc->writeback_keys;
- unsigned start_stripe, stripe, next_stripe;
- bool wrapped = false;
- stripe = offset_to_stripe(&dc->disk, KEY_OFFSET(&buf->last_scanned));
- if (stripe >= dc->disk.nr_stripes)
- stripe = 0;
- start_stripe = stripe;
- while (1) {
- stripe = find_next_bit(dc->disk.full_dirty_stripes,
- dc->disk.nr_stripes, stripe);
- if (stripe == dc->disk.nr_stripes)
- goto next;
- next_stripe = find_next_zero_bit(dc->disk.full_dirty_stripes,
- dc->disk.nr_stripes, stripe);
- buf->last_scanned = KEY(dc->disk.id,
- stripe * dc->disk.stripe_size, 0);
- bch_refill_keybuf(dc->disk.c, buf,
- &KEY(dc->disk.id,
- next_stripe * dc->disk.stripe_size, 0),
- dirty_pred);
- if (array_freelist_empty(&buf->freelist))
- return;
- stripe = next_stripe;
- next:
- if (wrapped && stripe > start_stripe)
- return;
- if (stripe == dc->disk.nr_stripes) {
- stripe = 0;
- wrapped = true;
- }
- }
- }
- /*
- * Returns true if we scanned the entire disk
- */
- static bool refill_dirty(struct cached_dev *dc)
- {
- struct keybuf *buf = &dc->writeback_keys;
- struct bkey start = KEY(dc->disk.id, 0, 0);
- struct bkey end = KEY(dc->disk.id, MAX_KEY_OFFSET, 0);
- struct bkey start_pos;
- /*
- * make sure keybuf pos is inside the range for this disk - at bringup
- * we might not be attached yet so this disk's inode nr isn't
- * initialized then
- */
- if (bkey_cmp(&buf->last_scanned, &start) < 0 ||
- bkey_cmp(&buf->last_scanned, &end) > 0)
- buf->last_scanned = start;
- if (dc->partial_stripes_expensive) {
- refill_full_stripes(dc);
- if (array_freelist_empty(&buf->freelist))
- return false;
- }
- start_pos = buf->last_scanned;
- bch_refill_keybuf(dc->disk.c, buf, &end, dirty_pred);
- if (bkey_cmp(&buf->last_scanned, &end) < 0)
- return false;
- /*
- * If we get to the end start scanning again from the beginning, and
- * only scan up to where we initially started scanning from:
- */
- buf->last_scanned = start;
- bch_refill_keybuf(dc->disk.c, buf, &start_pos, dirty_pred);
- return bkey_cmp(&buf->last_scanned, &start_pos) >= 0;
- }
- static int bch_writeback_thread(void *arg)
- {
- struct cached_dev *dc = arg;
- bool searched_full_index;
- while (!kthread_should_stop()) {
- down_write(&dc->writeback_lock);
- set_current_state(TASK_INTERRUPTIBLE);
- /*
- * If the bache device is detaching, skip here and continue
- * to perform writeback. Otherwise, if no dirty data on cache,
- * or there is dirty data on cache but writeback is disabled,
- * the writeback thread should sleep here and wait for others
- * to wake up it.
- */
- if (!test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) &&
- (!atomic_read(&dc->has_dirty) || !dc->writeback_running)) {
- up_write(&dc->writeback_lock);
- if (kthread_should_stop()) {
- set_current_state(TASK_RUNNING);
- return 0;
- }
- try_to_freeze();
- schedule();
- continue;
- }
- set_current_state(TASK_RUNNING);
- searched_full_index = refill_dirty(dc);
- if (searched_full_index &&
- RB_EMPTY_ROOT(&dc->writeback_keys.keys)) {
- atomic_set(&dc->has_dirty, 0);
- cached_dev_put(dc);
- SET_BDEV_STATE(&dc->sb, BDEV_STATE_CLEAN);
- bch_write_bdev_super(dc, NULL);
- /*
- * If bcache device is detaching via sysfs interface,
- * writeback thread should stop after there is no dirty
- * data on cache. BCACHE_DEV_DETACHING flag is set in
- * bch_cached_dev_detach().
- */
- if (test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags)) {
- up_write(&dc->writeback_lock);
- break;
- }
- }
- up_write(&dc->writeback_lock);
- bch_ratelimit_reset(&dc->writeback_rate);
- read_dirty(dc);
- if (searched_full_index) {
- unsigned delay = dc->writeback_delay * HZ;
- while (delay &&
- !kthread_should_stop() &&
- !test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags))
- delay = schedule_timeout_interruptible(delay);
- }
- }
- return 0;
- }
- /* Init */
- struct sectors_dirty_init {
- struct btree_op op;
- unsigned inode;
- };
- static int sectors_dirty_init_fn(struct btree_op *_op, struct btree *b,
- struct bkey *k)
- {
- struct sectors_dirty_init *op = container_of(_op,
- struct sectors_dirty_init, op);
- if (KEY_INODE(k) > op->inode)
- return MAP_DONE;
- if (KEY_DIRTY(k))
- bcache_dev_sectors_dirty_add(b->c, KEY_INODE(k),
- KEY_START(k), KEY_SIZE(k));
- return MAP_CONTINUE;
- }
- void bch_sectors_dirty_init(struct bcache_device *d)
- {
- struct sectors_dirty_init op;
- bch_btree_op_init(&op.op, -1);
- op.inode = d->id;
- bch_btree_map_keys(&op.op, d->c, &KEY(op.inode, 0, 0),
- sectors_dirty_init_fn, 0);
- d->sectors_dirty_last = bcache_dev_sectors_dirty(d);
- }
- void bch_cached_dev_writeback_init(struct cached_dev *dc)
- {
- sema_init(&dc->in_flight, 64);
- init_rwsem(&dc->writeback_lock);
- bch_keybuf_init(&dc->writeback_keys);
- dc->writeback_metadata = true;
- dc->writeback_running = true;
- dc->writeback_percent = 10;
- dc->writeback_delay = 30;
- dc->writeback_rate.rate = 1024;
- dc->writeback_rate_update_seconds = 5;
- dc->writeback_rate_d_term = 30;
- dc->writeback_rate_p_term_inverse = 6000;
- INIT_DELAYED_WORK(&dc->writeback_rate_update, update_writeback_rate);
- }
- int bch_cached_dev_writeback_start(struct cached_dev *dc)
- {
- dc->writeback_write_wq = alloc_workqueue("bcache_writeback_wq",
- WQ_MEM_RECLAIM, 0);
- if (!dc->writeback_write_wq)
- return -ENOMEM;
- dc->writeback_thread = kthread_create(bch_writeback_thread, dc,
- "bcache_writeback");
- if (IS_ERR(dc->writeback_thread))
- return PTR_ERR(dc->writeback_thread);
- schedule_delayed_work(&dc->writeback_rate_update,
- dc->writeback_rate_update_seconds * HZ);
- bch_writeback_queue(dc);
- return 0;
- }
|