btrfs: add the beginning of async discard, discard workqueue
When discard is enabled, everytime a pinned extent is released back to
the block_group's free space cache, a discard is issued for the extent.
This is an overeager approach when it comes to discarding and helping
the SSD maintain enough free space to prevent severe garbage collection
situations.
This adds the beginning of async discard. Instead of issuing a discard
prior to returning it to the free space, it is just marked as untrimmed.
The block_group is then added to a LRU which then feeds into a workqueue
to issue discards at a much slower rate. Full discarding of unused block
groups is still done and will be addressed in a future patch of the
series.
For now, we don't persist the discard state of extents and bitmaps.
Therefore, our failure recovery mode will be to consider extents
untrimmed. This lets us handle failure and unmounting as one in the
same.
On a number of Facebook webservers, I collected data every minute
accounting the time we spent in btrfs_finish_extent_commit() (col. 1)
and in btrfs_commit_transaction() (col. 2). btrfs_finish_extent_commit()
is where we discard extents synchronously before returning them to the
free space cache.
discard=sync:
p99 total per minute p99 total per minute
Drive | extent_commit() (ms) | commit_trans() (ms)
---------------------------------------------------------------
Drive A | 434 | 1170
Drive B | 880 | 2330
Drive C | 2943 | 3920
Drive D | 4763 | 5701
discard=async:
p99 total per minute p99 total per minute
Drive | extent_commit() (ms) | commit_trans() (ms)
--------------------------------------------------------------
Drive A | 134 | 956
Drive B | 64 | 1972
Drive C | 59 | 1032
Drive D | 62 | 1200
While it's not great that the stats are cumulative over 1m, all of these
servers are running the same workload and and the delta between the two
are substantial. We are spending significantly less time in
btrfs_finish_extent_commit() which is responsible for discarding.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Dennis Zhou <dennis@kernel.org>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 2f6c21e..f7b4292 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -440,6 +440,21 @@ struct btrfs_full_stripe_locks_tree {
struct mutex lock;
};
+/* Discard control. */
+/*
+ * Async discard uses multiple lists to differentiate the discard filter
+ * parameters.
+ */
+#define BTRFS_NR_DISCARD_LISTS 1
+
+struct btrfs_discard_ctl {
+ struct workqueue_struct *discard_workers;
+ struct delayed_work work;
+ spinlock_t lock;
+ struct btrfs_block_group *block_group;
+ struct list_head discard_list[BTRFS_NR_DISCARD_LISTS];
+};
+
/* delayed seq elem */
struct seq_list {
struct list_head list;
@@ -526,6 +541,9 @@ enum {
* so we don't need to offload checksums to workqueues.
*/
BTRFS_FS_CSUM_IMPL_FAST,
+
+ /* Indicate that the discard workqueue can service discards. */
+ BTRFS_FS_DISCARD_RUNNING,
};
struct btrfs_fs_info {
@@ -816,6 +834,8 @@ struct btrfs_fs_info {
struct btrfs_workqueue *scrub_wr_completion_workers;
struct btrfs_workqueue *scrub_parity_workers;
+ struct btrfs_discard_ctl discard_ctl;
+
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
u32 check_integrity_print_mask;
#endif
@@ -1189,6 +1209,7 @@ static inline u32 BTRFS_MAX_XATTR_SIZE(const struct btrfs_fs_info *info)
#define BTRFS_MOUNT_FREE_SPACE_TREE (1 << 26)
#define BTRFS_MOUNT_NOLOGREPLAY (1 << 27)
#define BTRFS_MOUNT_REF_VERIFY (1 << 28)
+#define BTRFS_MOUNT_DISCARD_ASYNC (1 << 29)
#define BTRFS_DEFAULT_COMMIT_INTERVAL (30)
#define BTRFS_DEFAULT_MAX_INLINE (2048)