diff options
Diffstat (limited to 'drivers/md')
-rw-r--r-- | drivers/md/bcache/alloc.c | 180 | ||||
-rw-r--r-- | drivers/md/bcache/bcache.h | 4 | ||||
-rw-r--r-- | drivers/md/bcache/request.c | 186 | ||||
-rw-r--r-- | drivers/md/bcache/request.h | 5 |
4 files changed, 189 insertions, 186 deletions
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c index b9bd586..4970ddc 100644 --- a/drivers/md/bcache/alloc.c +++ b/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, diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 20fe96c..e32f6fd 100644 --- a/drivers/md/bcache/bcache.h +++ b/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); diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 05c7c21..cf7850a 100644 --- a/drivers/md/bcache/request.c +++ b/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; diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h index 54d7de2..2cd65bf 100644 --- a/drivers/md/bcache/request.h +++ b/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); |