[Bcache v15 15/16] bcache: Writeback, copying garbage collection

[Kent Overstreet]

Signed-off-by: Kent Overstreet <koverstreet@xxxxxxxxxx>
---
 drivers/md/bcache/movinggc.c  |  245 +++++++++++++++++++++++++
 drivers/md/bcache/writeback.c |  405 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 650 insertions(+), 0 deletions(-)
 create mode 100644 drivers/md/bcache/movinggc.c
 create mode 100644 drivers/md/bcache/writeback.c

diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
new file mode 100644
index 0000000..53a596f
--- /dev/null
+++ b/drivers/md/bcache/movinggc.c
@@ -0,0 +1,245 @@
+#include "bcache.h"
+#include "btree.h"
+#include "debug.h"
+#include "request.h"
+
+struct moving_io {
+	struct keybuf_key	*w;
+	struct search		s;
+	struct bbio		bio;
+};
+
+static bool moving_pred(struct keybuf *buf, struct bkey *k)
+{
+	struct cache_set *c = container_of(buf, struct cache_set,
+					   moving_gc_keys);
+
+	for (unsigned 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)
+			return true;
+	}
+
+	return false;
+}
+
+/* Moving GC - IO loop */
+
+static void moving_io_destructor(struct closure *cl)
+{
+	struct moving_io *io = container_of(cl, struct moving_io, s.cl);
+	kfree(io);
+}
+
+static void write_moving_finish(struct closure *cl)
+{
+	struct moving_io *io = container_of(cl, struct moving_io, s.cl);
+	struct bio *bio = &io->bio.bio;
+	struct bio_vec *bv = bio_iovec_idx(bio, bio->bi_vcnt);
+
+	while (bv-- != bio->bi_io_vec)
+		__free_page(bv->bv_page);
+
+	pr_debug("%s %s", io->s.op.insert_collision
+		 ? "collision moving" : "moved",
+		 pkey(&io->w->key));
+
+	bch_keybuf_del(&io->s.op.c->moving_gc_keys, io->w);
+
+	atomic_dec_bug(&io->s.op.c->in_flight);
+	closure_wake_up(&io->s.op.c->moving_gc_wait);
+
+	closure_return_with_destructor(cl, moving_io_destructor);
+}
+
+static void read_moving_endio(struct bio *bio, int error)
+{
+	struct moving_io *io = container_of(bio->bi_private,
+					    struct moving_io, s.cl);
+
+	if (error)
+		io->s.error = error;
+
+	bch_bbio_endio(io->s.op.c, bio, error, "reading data to move");
+}
+
+static void moving_init(struct moving_io *io)
+{
+	struct bio *bio = &io->bio.bio;
+
+	bio_init(bio);
+	bio_get(bio);
+	bio_set_prio(bio, IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0));
+
+	bio->bi_size		= KEY_SIZE(&io->w->key) << 9;
+	bio->bi_max_vecs	= DIV_ROUND_UP(KEY_SIZE(&io->w->key), PAGE_SECTORS);
+	bio->bi_private		= &io->s.cl;
+	bio->bi_io_vec		= bio->bi_inline_vecs;
+	bio_map(bio, NULL);
+}
+
+static void write_moving(struct closure *cl)
+{
+	struct search *s = container_of(cl, struct search, cl);
+	struct moving_io *io = container_of(s, struct moving_io, s);
+
+	if (!s->error) {
+		trace_bcache_write_moving(&io->bio.bio);
+
+		moving_init(io);
+
+		io->bio.bio.bi_sector	= KEY_START(&io->w->key);
+		s->op.lock		= -1;
+		s->op.write_prio	= 1;
+		s->op.cache_bio		= &io->bio.bio;
+
+		s->writeback		= KEY_DIRTY(&io->w->key);
+		s->op.csum		= KEY_CSUM(&io->w->key);
+
+		s->op.type = BTREE_REPLACE;
+		bkey_copy(&s->op.replace, &io->w->key);
+
+		closure_init(&s->op.cl, cl);
+		bch_insert_data(&s->op.cl);
+	}
+
+	continue_at(cl, write_moving_finish, NULL);
+}
+
+static void read_moving_submit(struct closure *cl)
+{
+	struct search *s = container_of(cl, struct search, cl);
+	struct moving_io *io = container_of(s, struct moving_io, s);
+	struct bio *bio = &io->bio.bio;
+
+	trace_bcache_read_moving(bio);
+	bch_submit_bbio(bio, s->op.c, &io->w->key, 0);
+
+	continue_at(cl, write_moving, bch_gc_wq);
+}
+
+static void read_moving(struct closure *cl)
+{
+	struct cache_set *c = container_of(cl, struct cache_set, moving_gc);
+	struct keybuf_key *w;
+	struct moving_io *io;
+	struct bio *bio;
+
+	/* XXX: if we error, background writeback could stall indefinitely */
+
+	while (!atomic_read(&c->closing)) {
+		w = bch_keybuf_next_rescan(c, &c->moving_gc_keys, &MAX_KEY);
+		if (!w)
+			break;
+
+		io = kzalloc(sizeof(struct moving_io) + sizeof(struct bio_vec)
+			     * DIV_ROUND_UP(KEY_SIZE(&w->key), PAGE_SECTORS),
+			     GFP_KERNEL);
+		if (!io)
+			goto err;
+
+		w->private	= io;
+		io->w		= w;
+		io->s.op.inode	= KEY_INODE(&w->key);
+		io->s.op.c	= c;
+
+		moving_init(io);
+		bio = &io->bio.bio;
+
+		bio->bi_rw	= READ;
+		bio->bi_end_io	= read_moving_endio;
+
+		if (bio_alloc_pages(bio, GFP_KERNEL))
+			goto err;
+
+		pr_debug("%s", pkey(&w->key));
+
+		closure_call(read_moving_submit, &io->s.cl, &c->gc.cl);
+
+		if (atomic_inc_return(&c->in_flight) >= 64) {
+			closure_wait_event(&c->moving_gc_wait, cl,
+					   atomic_read(&c->in_flight) < 64);
+			continue_at(cl, read_moving, bch_gc_wq);
+		}
+	}
+
+	if (0) {
+err:		if (!IS_ERR_OR_NULL(w->private))
+			kfree(w->private);
+
+		bch_keybuf_del(&c->moving_gc_keys, w);
+	}
+
+	closure_return(cl);
+}
+
+void bch_moving_gc(struct closure *cl)
+{
+	struct cache_set *c = container_of(cl, struct cache_set, gc.cl);
+	struct cache *ca;
+	struct bucket *b;
+
+	bool bucket_cmp(struct bucket *l, struct bucket *r)
+	{
+		return GC_SECTORS_USED(l) < GC_SECTORS_USED(r);
+	}
+
+	unsigned top(struct cache *ca)
+	{
+		return GC_SECTORS_USED(heap_peek(&ca->heap));
+	}
+
+	if (!c->copy_gc_enabled)
+		closure_return(cl);
+
+	mutex_lock(&c->bucket_lock);
+
+	for_each_cache(ca, c) {
+		unsigned sectors_to_move = 0;
+		unsigned reserve_sectors = ca->sb.bucket_size *
+			min(fifo_used(&ca->free), ca->free.size / 2);
+
+		ca->heap.used = 0;
+
+		for_each_bucket(b, ca) {
+			if (!GC_SECTORS_USED(b))
+				continue;
+
+			if (!heap_full(&ca->heap)) {
+				sectors_to_move += GC_SECTORS_USED(b);
+				heap_add(&ca->heap, b, bucket_cmp);
+			} else if (bucket_cmp(b, heap_peek(&ca->heap))) {
+				sectors_to_move -= top(ca);
+				sectors_to_move += GC_SECTORS_USED(b);
+
+				ca->heap.data[0] = b;
+				heap_sift(&ca->heap, 0, bucket_cmp);
+			}
+		}
+
+		while (sectors_to_move > reserve_sectors) {
+			heap_pop(&ca->heap, b, bucket_cmp);
+			sectors_to_move -= GC_SECTORS_USED(b);
+		}
+
+		ca->gc_move_threshold = top(ca);
+
+		pr_debug("threshold %u", ca->gc_move_threshold);
+	}
+
+	mutex_unlock(&c->bucket_lock);
+
+	c->moving_gc_keys.last_scanned = ZERO_KEY;
+
+	closure_init(&c->moving_gc, cl);
+	read_moving(&c->moving_gc);
+
+	closure_return(cl);
+}
+
+void bch_moving_init_cache_set(struct cache_set *c)
+{
+	bch_keybuf_init(&c->moving_gc_keys, moving_pred);
+}
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
new file mode 100644
index 0000000..5da5876
--- /dev/null
+++ b/drivers/md/bcache/writeback.c
@@ -0,0 +1,405 @@
+#include "bcache.h"
+#include "btree.h"
+#include "debug.h"
+
+static struct workqueue_struct *dirty_wq;
+
+static void read_dirty(struct closure *);
+
+struct dirty_io {
+	struct closure		cl;
+	struct cached_dev	*dc;
+	struct bio		bio;
+};
+
+/* 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;
+	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 */
+
+	int change = 0;
+	int64_t error;
+	int64_t dirty = atomic_long_read(&dc->disk.sectors_dirty);
+	int64_t derivative = dirty - dc->disk.sectors_dirty_last;
+
+	dc->disk.sectors_dirty_last = dirty;
+
+	derivative *= dc->writeback_rate_d_term;
+	derivative = clamp(derivative, -dirty, dirty);
+
+	derivative = ewma_add(dc->disk.sectors_dirty_derivative, derivative,
+			      dc->writeback_rate_d_smooth, 0);
+
+	/* Avoid divide by zero */
+	if (!target)
+		goto out;
+
+	error = div64_s64((dirty + derivative - target) << 8, target);
+
+	change = div_s64((dc->writeback_rate.rate * error) >> 8,
+			 dc->writeback_rate_p_term_inverse);
+
+	/* 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))
+		change = 0;
+
+	dc->writeback_rate.rate =
+		clamp_t(int64_t, dc->writeback_rate.rate + change,
+			1, NSEC_PER_MSEC);
+out:
+	dc->writeback_rate_derivative = derivative;
+	dc->writeback_rate_change = change;
+	dc->writeback_rate_target = target;
+
+	schedule_delayed_work(&dc->writeback_rate_update,
+			      dc->writeback_rate_update_seconds * HZ);
+}
+
+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);
+}
+
+static unsigned writeback_delay(struct cached_dev *dc, unsigned sectors)
+{
+	if (atomic_read(&dc->disk.detaching) ||
+	    !dc->writeback_percent)
+		return 0;
+
+	return next_delay(&dc->writeback_rate, sectors * 10000000ULL);
+}
+
+/* Background writeback */
+
+static bool dirty_pred(struct keybuf *buf, struct bkey *k)
+{
+	return KEY_DIRTY(k);
+}
+
+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_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;
+	bio_map(bio, NULL);
+}
+
+static void refill_dirty(struct closure *cl)
+{
+	struct cached_dev *dc = container_of(cl, struct cached_dev,
+					     writeback.cl);
+	struct keybuf *buf = &dc->writeback_keys;
+	bool searched_from_start = false;
+	struct bkey end = MAX_KEY;
+	SET_KEY_INODE(&end, dc->disk.id);
+
+	if (!atomic_read(&dc->disk.detaching) &&
+	    !dc->writeback_running)
+		closure_return(cl);
+
+	down_write(&dc->writeback_lock);
+
+	if (!atomic_read(&dc->has_dirty)) {
+		SET_BDEV_STATE(&dc->sb, BDEV_STATE_CLEAN);
+		bch_write_bdev_super(dc, NULL);
+
+		up_write(&dc->writeback_lock);
+		closure_return(cl);
+	}
+
+	if (bkey_cmp(&buf->last_scanned, &end) >= 0) {
+		buf->last_scanned = KEY(dc->disk.id, 0, 0);
+		searched_from_start = true;
+	}
+
+	bch_refill_keybuf(dc->disk.c, buf, &end);
+
+	if (bkey_cmp(&buf->last_scanned, &end) >= 0 && searched_from_start) {
+		/* Searched the entire btree  - delay awhile */
+
+		if (RB_EMPTY_ROOT(&buf->keys)) {
+			atomic_set(&dc->has_dirty, 0);
+			cached_dev_put(dc);
+		}
+
+		if (!atomic_read(&dc->disk.detaching))
+			closure_delay(&dc->writeback, dc->writeback_delay * HZ);
+	}
+
+	up_write(&dc->writeback_lock);
+
+	ratelimit_reset(&dc->writeback_rate);
+
+	/* Punt to workqueue only so we don't recurse and blow the stack */
+	continue_at(cl, read_dirty, dirty_wq);
+}
+
+void bch_writeback_queue(struct cached_dev *dc)
+{
+	if (closure_trylock(&dc->writeback.cl, &dc->disk.cl)) {
+		if (!atomic_read(&dc->disk.detaching))
+			closure_delay(&dc->writeback, dc->writeback_delay * HZ);
+
+		continue_at(&dc->writeback.cl, refill_dirty, dirty_wq);
+	}
+}
+
+void bch_writeback_add(struct cached_dev *dc, unsigned sectors)
+{
+	atomic_long_add(sectors, &dc->disk.sectors_dirty);
+
+	if (!atomic_read(&dc->has_dirty) &&
+	    !atomic_xchg(&dc->has_dirty, 1)) {
+		atomic_inc(&dc->count);
+
+		if (BDEV_STATE(&dc->sb) != BDEV_STATE_DIRTY) {
+			SET_BDEV_STATE(&dc->sb, BDEV_STATE_DIRTY);
+			/* XXX: should do this synchronously */
+			bch_write_bdev_super(dc, NULL);
+		}
+
+		bch_writeback_queue(dc);
+
+		if (dc->writeback_percent)
+			schedule_delayed_work(&dc->writeback_rate_update,
+				      dc->writeback_rate_update_seconds * HZ);
+	}
+}
+
+/* Background writeback - IO loop */
+
+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 = bio_iovec_idx(&io->bio, io->bio.bi_vcnt);
+
+	while (bv-- != io->bio.bi_io_vec)
+		__free_page(bv->bv_page);
+
+	/* This is kind of a dumb way of signalling errors. */
+	if (KEY_DIRTY(&w->key)) {
+		unsigned i;
+		struct btree_op op;
+		bch_btree_op_init_stack(&op);
+
+		op.type = BTREE_REPLACE;
+		bkey_copy(&op.replace, &w->key);
+
+		SET_KEY_DIRTY(&w->key, false);
+		bch_keylist_add(&op.keys, &w->key);
+
+		for (i = 0; i < KEY_PTRS(&w->key); i++)
+			atomic_inc(&PTR_BUCKET(dc->disk.c, &w->key, i)->pin);
+
+		pr_debug("clearing %s", pkey(&w->key));
+		bch_btree_insert(&op, dc->disk.c);
+		closure_sync(&op.cl);
+
+		atomic_long_inc(op.insert_collision
+				? &dc->disk.c->writeback_keys_failed
+				: &dc->disk.c->writeback_keys_done);
+	}
+
+	bch_keybuf_del(&dc->writeback_keys, w);
+	atomic_dec_bug(&dc->in_flight);
+
+	closure_wake_up(&dc->writeback_wait);
+
+	closure_return_with_destructor(cl, dirty_io_destructor);
+}
+
+static void dirty_endio(struct bio *bio, int error)
+{
+	struct keybuf_key *w = bio->bi_private;
+	struct dirty_io *io = w->private;
+
+	if (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_sector	= KEY_START(&w->key);
+	io->bio.bi_bdev		= io->dc->bdev;
+	io->bio.bi_end_io	= dirty_endio;
+
+	trace_bcache_write_dirty(&io->bio);
+	closure_bio_submit(&io->bio, cl);
+
+	continue_at(cl, write_dirty_finish, dirty_wq);
+}
+
+static void read_dirty_endio(struct bio *bio, int error)
+{
+	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),
+			    error, "reading dirty data from cache");
+
+	dirty_endio(bio, error);
+}
+
+static void read_dirty_submit(struct closure *cl)
+{
+	struct dirty_io *io = container_of(cl, struct dirty_io, cl);
+
+	trace_bcache_read_dirty(&io->bio);
+	closure_bio_submit(&io->bio, cl);
+
+	continue_at(cl, write_dirty, dirty_wq);
+}
+
+static void read_dirty(struct closure *cl)
+{
+	struct cached_dev *dc = container_of(cl, struct cached_dev,
+					     writeback.cl);
+	unsigned delay = writeback_delay(dc, 0);
+	struct keybuf_key *w;
+	struct dirty_io *io;
+
+	/*
+	 * XXX: if we error, background writeback just spins. Should use some
+	 * mempools.
+	 */
+
+	while (1) {
+		w = bch_keybuf_next(&dc->writeback_keys);
+		if (!w)
+			break;
+
+		BUG_ON(ptr_stale(dc->disk.c, &w->key, 0));
+
+		if (delay > 0 &&
+		    (KEY_START(&w->key) != dc->last_read ||
+		     jiffies_to_msecs(delay) > 50)) {
+			w->private = NULL;
+
+			closure_delay(&dc->writeback, delay);
+			continue_at(cl, read_dirty, dirty_wq);
+		}
+
+		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_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;
+
+		pr_debug("%s", pkey(&w->key));
+
+		closure_call(read_dirty_submit, &io->cl, &dc->disk.cl);
+
+		delay = writeback_delay(dc, KEY_SIZE(&w->key));
+
+		atomic_inc(&dc->in_flight);
+
+		if (!closure_wait_event(&dc->writeback_wait, cl,
+					atomic_read(&dc->in_flight) < 64))
+			continue_at(cl, read_dirty, dirty_wq);
+	}
+
+	if (0) {
+err_free:
+		kfree(w->private);
+err:
+		bch_keybuf_del(&dc->writeback_keys, w);
+	}
+
+	refill_dirty(cl);
+}
+
+void bch_writeback_init_cached_dev(struct cached_dev *dc)
+{
+	closure_init_unlocked(&dc->writeback);
+	init_rwsem(&dc->writeback_lock);
+
+	bch_keybuf_init(&dc->writeback_keys, dirty_pred);
+
+	dc->writeback_metadata		= true;
+	dc->writeback_running		= true;
+	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;
+
+	INIT_DELAYED_WORK(&dc->writeback_rate_update, update_writeback_rate);
+	schedule_delayed_work(&dc->writeback_rate_update,
+			      dc->writeback_rate_update_seconds * HZ);
+}
+
+void bch_writeback_exit(void)
+{
+	if (dirty_wq)
+		destroy_workqueue(dirty_wq);
+}
+
+int __init bch_writeback_init(void)
+{
+	dirty_wq = create_singlethread_workqueue("bcache_writeback");
+	if (!dirty_wq)
+		return -ENOMEM;
+
+	return 0;
+}
-- 
1.7.7.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/