bcache: Move sector allocator to alloc.c

Just reorganizing things a bit.

Signed-off-by: Kent Overstreet <kmo@daterainc.com>

drivers/md/bcache/alloc.c

@@ -487,8 +487,188 @@ int bch_bucket_alloc_set(struct cache_set *c, unsigned watermark,
 	return ret;
 }
 
+/* Sector allocator */
+
+struct open_bucket {
+	struct list_head	list;
+	unsigned		last_write_point;
+	unsigned		sectors_free;
+	BKEY_PADDED(key);
+};
+
+/*
+ * We keep multiple buckets open for writes, and try to segregate different
+ * write streams for better cache utilization: first we look for a bucket where
+ * the last write to it was sequential with the current write, and failing that
+ * we look for a bucket that was last used by the same task.
+ *
+ * The ideas is if you've got multiple tasks pulling data into the cache at the
+ * same time, you'll get better cache utilization if you try to segregate their
+ * data and preserve locality.
+ *
+ * For example, say you've starting Firefox at the same time you're copying a
+ * bunch of files. Firefox will likely end up being fairly hot and stay in the
+ * cache awhile, but the data you copied might not be; if you wrote all that
+ * data to the same buckets it'd get invalidated at the same time.
+ *
+ * Both of those tasks will be doing fairly random IO so we can't rely on
+ * detecting sequential IO to segregate their data, but going off of the task
+ * should be a sane heuristic.
+ */
+static struct open_bucket *pick_data_bucket(struct cache_set *c,
+					    const struct bkey *search,
+					    unsigned write_point,
+					    struct bkey *alloc)
+{
+	struct open_bucket *ret, *ret_task = NULL;
+
+	list_for_each_entry_reverse(ret, &c->data_buckets, list)
+		if (!bkey_cmp(&ret->key, search))
+			goto found;
+		else if (ret->last_write_point == write_point)
+			ret_task = ret;
+
+	ret = ret_task ?: list_first_entry(&c->data_buckets,
+					   struct open_bucket, list);
+found:
+	if (!ret->sectors_free && KEY_PTRS(alloc)) {
+		ret->sectors_free = c->sb.bucket_size;
+		bkey_copy(&ret->key, alloc);
+		bkey_init(alloc);
+	}
+
+	if (!ret->sectors_free)
+		ret = NULL;
+
+	return ret;
+}
+
+/*
+ * Allocates some space in the cache to write to, and k to point to the newly
+ * allocated space, and updates KEY_SIZE(k) and KEY_OFFSET(k) (to point to the
+ * end of the newly allocated space).
+ *
+ * May allocate fewer sectors than @sectors, KEY_SIZE(k) indicates how many
+ * sectors were actually allocated.
+ *
+ * If s->writeback is true, will not fail.
+ */
+bool bch_alloc_sectors(struct cache_set *c, struct bkey *k, unsigned sectors,
+		       unsigned write_point, unsigned write_prio, bool wait)
+{
+	struct open_bucket *b;
+	BKEY_PADDED(key) alloc;
+	unsigned i;
+
+	/*
+	 * We might have to allocate a new bucket, which we can't do with a
+	 * spinlock held. So if we have to allocate, we drop the lock, allocate
+	 * and then retry. KEY_PTRS() indicates whether alloc points to
+	 * allocated bucket(s).
+	 */
+
+	bkey_init(&alloc.key);
+	spin_lock(&c->data_bucket_lock);
+
+	while (!(b = pick_data_bucket(c, k, write_point, &alloc.key))) {
+		unsigned watermark = write_prio
+			? WATERMARK_MOVINGGC
+			: WATERMARK_NONE;
+
+		spin_unlock(&c->data_bucket_lock);
+
+		if (bch_bucket_alloc_set(c, watermark, &alloc.key, 1, wait))
+			return false;
+
+		spin_lock(&c->data_bucket_lock);
+	}
+
+	/*
+	 * If we had to allocate, we might race and not need to allocate the
+	 * second time we call find_data_bucket(). If we allocated a bucket but
+	 * didn't use it, drop the refcount bch_bucket_alloc_set() took:
+	 */
+	if (KEY_PTRS(&alloc.key))
+		__bkey_put(c, &alloc.key);
+
+	for (i = 0; i < KEY_PTRS(&b->key); i++)
+		EBUG_ON(ptr_stale(c, &b->key, i));
+
+	/* Set up the pointer to the space we're allocating: */
+
+	for (i = 0; i < KEY_PTRS(&b->key); i++)
+		k->ptr[i] = b->key.ptr[i];
+
+	sectors = min(sectors, b->sectors_free);
+
+	SET_KEY_OFFSET(k, KEY_OFFSET(k) + sectors);
+	SET_KEY_SIZE(k, sectors);
+	SET_KEY_PTRS(k, KEY_PTRS(&b->key));
+
+	/*
+	 * Move b to the end of the lru, and keep track of what this bucket was
+	 * last used for:
+	 */
+	list_move_tail(&b->list, &c->data_buckets);
+	bkey_copy_key(&b->key, k);
+	b->last_write_point = write_point;
+
+	b->sectors_free	-= sectors;
+
+	for (i = 0; i < KEY_PTRS(&b->key); i++) {
+		SET_PTR_OFFSET(&b->key, i, PTR_OFFSET(&b->key, i) + sectors);
+
+		atomic_long_add(sectors,
+				&PTR_CACHE(c, &b->key, i)->sectors_written);
+	}
+
+	if (b->sectors_free < c->sb.block_size)
+		b->sectors_free = 0;
+
+	/*
+	 * k takes refcounts on the buckets it points to until it's inserted
+	 * into the btree, but if we're done with this bucket we just transfer
+	 * get_data_bucket()'s refcount.
+	 */
+	if (b->sectors_free)
+		for (i = 0; i < KEY_PTRS(&b->key); i++)
+			atomic_inc(&PTR_BUCKET(c, &b->key, i)->pin);
+
+	spin_unlock(&c->data_bucket_lock);
+	return true;
+}
+
 /* Init */
 
+void bch_open_buckets_free(struct cache_set *c)
+{
+	struct open_bucket *b;
+
+	while (!list_empty(&c->data_buckets)) {
+		b = list_first_entry(&c->data_buckets,
+				     struct open_bucket, list);
+		list_del(&b->list);
+		kfree(b);
+	}
+}
+
+int bch_open_buckets_alloc(struct cache_set *c)
+{
+	int i;
+
+	spin_lock_init(&c->data_bucket_lock);
+
+	for (i = 0; i < 6; i++) {
+		struct open_bucket *b = kzalloc(sizeof(*b), GFP_KERNEL);
+		if (!b)
+			return -ENOMEM;
+
+		list_add(&b->list, &c->data_buckets);
+	}
+
+	return 0;
+}
+
 int bch_cache_allocator_start(struct cache *ca)
 {
 	struct task_struct *k = kthread_run(bch_allocator_thread,

drivers/md/bcache/bcache.h

@@ -1170,6 +1170,8 @@ int __bch_bucket_alloc_set(struct cache_set *, unsigned,
 			   struct bkey *, int, bool);
 int bch_bucket_alloc_set(struct cache_set *, unsigned,
 			 struct bkey *, int, bool);
+bool bch_alloc_sectors(struct cache_set *, struct bkey *, unsigned,
+		       unsigned, unsigned, bool);
 
 __printf(2, 3)
 bool bch_cache_set_error(struct cache_set *, const char *, ...);
@@ -1210,6 +1212,8 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *);
 void bch_btree_cache_free(struct cache_set *);
 int bch_btree_cache_alloc(struct cache_set *);
 void bch_moving_init_cache_set(struct cache_set *);
+int bch_open_buckets_alloc(struct cache_set *);
+void bch_open_buckets_free(struct cache_set *);
 
 int bch_cache_allocator_start(struct cache *ca);
 int bch_cache_allocator_init(struct cache *ca);

drivers/md/bcache/request.c

@@ -255,186 +255,6 @@ static void bch_data_insert_keys(struct closure *cl)
 	closure_return(cl);
 }
 
-struct open_bucket {
-	struct list_head	list;
-	struct task_struct	*last;
-	unsigned		sectors_free;
-	BKEY_PADDED(key);
-};
-
-void bch_open_buckets_free(struct cache_set *c)
-{
-	struct open_bucket *b;
-
-	while (!list_empty(&c->data_buckets)) {
-		b = list_first_entry(&c->data_buckets,
-				     struct open_bucket, list);
-		list_del(&b->list);
-		kfree(b);
-	}
-}
-
-int bch_open_buckets_alloc(struct cache_set *c)
-{
-	int i;
-
-	spin_lock_init(&c->data_bucket_lock);
-
-	for (i = 0; i < 6; i++) {
-		struct open_bucket *b = kzalloc(sizeof(*b), GFP_KERNEL);
-		if (!b)
-			return -ENOMEM;
-
-		list_add(&b->list, &c->data_buckets);
-	}
-
-	return 0;
-}
-
-/*
- * We keep multiple buckets open for writes, and try to segregate different
- * write streams for better cache utilization: first we look for a bucket where
- * the last write to it was sequential with the current write, and failing that
- * we look for a bucket that was last used by the same task.
- *
- * The ideas is if you've got multiple tasks pulling data into the cache at the
- * same time, you'll get better cache utilization if you try to segregate their
- * data and preserve locality.
- *
- * For example, say you've starting Firefox at the same time you're copying a
- * bunch of files. Firefox will likely end up being fairly hot and stay in the
- * cache awhile, but the data you copied might not be; if you wrote all that
- * data to the same buckets it'd get invalidated at the same time.
- *
- * Both of those tasks will be doing fairly random IO so we can't rely on
- * detecting sequential IO to segregate their data, but going off of the task
- * should be a sane heuristic.
- */
-static struct open_bucket *pick_data_bucket(struct cache_set *c,
-					    const struct bkey *search,
-					    struct task_struct *task,
-					    struct bkey *alloc)
-{
-	struct open_bucket *ret, *ret_task = NULL;
-
-	list_for_each_entry_reverse(ret, &c->data_buckets, list)
-		if (!bkey_cmp(&ret->key, search))
-			goto found;
-		else if (ret->last == task)
-			ret_task = ret;
-
-	ret = ret_task ?: list_first_entry(&c->data_buckets,
-					   struct open_bucket, list);
-found:
-	if (!ret->sectors_free && KEY_PTRS(alloc)) {
-		ret->sectors_free = c->sb.bucket_size;
-		bkey_copy(&ret->key, alloc);
-		bkey_init(alloc);
-	}
-
-	if (!ret->sectors_free)
-		ret = NULL;
-
-	return ret;
-}
-
-/*
- * Allocates some space in the cache to write to, and k to point to the newly
- * allocated space, and updates KEY_SIZE(k) and KEY_OFFSET(k) (to point to the
- * end of the newly allocated space).
- *
- * May allocate fewer sectors than @sectors, KEY_SIZE(k) indicates how many
- * sectors were actually allocated.
- *
- * If s->writeback is true, will not fail.
- */
-static bool bch_alloc_sectors(struct data_insert_op *op,
-			      struct bkey *k, unsigned sectors)
-{
-	struct cache_set *c = op->c;
-	struct open_bucket *b;
-	BKEY_PADDED(key) alloc;
-	unsigned i;
-
-	/*
-	 * We might have to allocate a new bucket, which we can't do with a
-	 * spinlock held. So if we have to allocate, we drop the lock, allocate
-	 * and then retry. KEY_PTRS() indicates whether alloc points to
-	 * allocated bucket(s).
-	 */
-
-	bkey_init(&alloc.key);
-	spin_lock(&c->data_bucket_lock);
-
-	while (!(b = pick_data_bucket(c, k, op->task, &alloc.key))) {
-		unsigned watermark = op->write_prio
-			? WATERMARK_MOVINGGC
-			: WATERMARK_NONE;
-
-		spin_unlock(&c->data_bucket_lock);
-
-		if (bch_bucket_alloc_set(c, watermark, &alloc.key,
-					 1, op->writeback))
-			return false;
-
-		spin_lock(&c->data_bucket_lock);
-	}
-
-	/*
-	 * If we had to allocate, we might race and not need to allocate the
-	 * second time we call find_data_bucket(). If we allocated a bucket but
-	 * didn't use it, drop the refcount bch_bucket_alloc_set() took:
-	 */
-	if (KEY_PTRS(&alloc.key))
-		__bkey_put(c, &alloc.key);
-
-	for (i = 0; i < KEY_PTRS(&b->key); i++)
-		EBUG_ON(ptr_stale(c, &b->key, i));
-
-	/* Set up the pointer to the space we're allocating: */
-
-	for (i = 0; i < KEY_PTRS(&b->key); i++)
-		k->ptr[i] = b->key.ptr[i];
-
-	sectors = min(sectors, b->sectors_free);
-
-	SET_KEY_OFFSET(k, KEY_OFFSET(k) + sectors);
-	SET_KEY_SIZE(k, sectors);
-	SET_KEY_PTRS(k, KEY_PTRS(&b->key));
-
-	/*
-	 * Move b to the end of the lru, and keep track of what this bucket was
-	 * last used for:
-	 */
-	list_move_tail(&b->list, &c->data_buckets);
-	bkey_copy_key(&b->key, k);
-	b->last = op->task;
-
-	b->sectors_free	-= sectors;
-
-	for (i = 0; i < KEY_PTRS(&b->key); i++) {
-		SET_PTR_OFFSET(&b->key, i, PTR_OFFSET(&b->key, i) + sectors);
-
-		atomic_long_add(sectors,
-				&PTR_CACHE(c, &b->key, i)->sectors_written);
-	}
-
-	if (b->sectors_free < c->sb.block_size)
-		b->sectors_free = 0;
-
-	/*
-	 * k takes refcounts on the buckets it points to until it's inserted
-	 * into the btree, but if we're done with this bucket we just transfer
-	 * get_data_bucket()'s refcount.
-	 */
-	if (b->sectors_free)
-		for (i = 0; i < KEY_PTRS(&b->key); i++)
-			atomic_inc(&PTR_BUCKET(c, &b->key, i)->pin);
-
-	spin_unlock(&c->data_bucket_lock);
-	return true;
-}
-
 static void bch_data_invalidate(struct closure *cl)
 {
 	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
@@ -545,7 +365,9 @@ static void bch_data_insert_start(struct closure *cl)
 		SET_KEY_INODE(k, op->inode);
 		SET_KEY_OFFSET(k, bio->bi_sector);
 
-		if (!bch_alloc_sectors(op, k, bio_sectors(bio)))
+		if (!bch_alloc_sectors(op->c, k, bio_sectors(bio),
+				       op->write_point, op->write_prio,
+				       op->writeback))
 			goto err;
 
 		n = bch_bio_split(bio, KEY_SIZE(k), GFP_NOIO, split);
@@ -968,7 +790,7 @@ static struct search *search_alloc(struct bio *bio, struct bcache_device *d)
 	s->iop.c		= d->c;
 	s->d			= d;
 	s->op.lock		= -1;
-	s->iop.task		= current;
+	s->iop.write_point	= hash_long((unsigned long) current, 16);
 	s->orig_bio		= bio;
 	s->write		= (bio->bi_rw & REQ_WRITE) != 0;
 	s->iop.flush_journal	= (bio->bi_rw & (REQ_FLUSH|REQ_FUA)) != 0;

drivers/md/bcache/request.h

@@ -6,10 +6,10 @@
 struct data_insert_op {
 	struct closure		cl;
 	struct cache_set	*c;
-	struct task_struct	*task;
 	struct bio		*bio;
 
 	unsigned		inode;
+	uint16_t		write_point;
 	uint16_t		write_prio;
 	short			error;
 
@@ -31,9 +31,6 @@ struct data_insert_op {
 unsigned bch_get_congested(struct cache_set *);
 void bch_data_insert(struct closure *cl);
 
-void bch_open_buckets_free(struct cache_set *);
-int bch_open_buckets_alloc(struct cache_set *);
-
 void bch_cached_dev_request_init(struct cached_dev *dc);
 void bch_flash_dev_request_init(struct bcache_device *d);