Btrfs: reclaim the reserved metadata space at background
Before applying this patch, the task had to reclaim the metadata space
by itself if the metadata space was not enough. And When the task started
the space reclamation, all the other tasks which wanted to reserve the
metadata space were blocked. At some cases, they would be blocked for
a long time, it made the performance fluctuate wildly.
So we introduce the background metadata space reclamation, when the space
is about to be exhausted, we insert a reclaim work into the workqueue, the
worker of the workqueue helps us to reclaim the reserved space at the
background. By this way, the tasks needn't reclaim the space by themselves at
most cases, and even if the tasks have to reclaim the space or are blocked
for the space reclamation, they will get enough space more quickly.
We needn't worry about the early enospc problem because all the reclaim work
is serialized by the lock.
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 8777b61..e44d3e6 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -33,6 +33,7 @@
#include <asm/kmap_types.h>
#include <linux/pagemap.h>
#include <linux/btrfs.h>
+#include <linux/workqueue.h>
#include "extent_io.h"
#include "extent_map.h"
#include "async-thread.h"
@@ -1305,6 +1306,8 @@
#define BTRFS_STRIPE_HASH_TABLE_BITS 11
+void btrfs_init_async_reclaim_work(struct work_struct *work);
+
/* fs_info */
struct reloc_control;
struct btrfs_device;
@@ -1680,6 +1683,9 @@
struct semaphore uuid_tree_rescan_sem;
unsigned int update_uuid_tree_gen:1;
+
+ /* Used to reclaim the metadata space in the background. */
+ struct work_struct async_reclaim_work;
};
struct btrfs_subvolume_writers {
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 4aae5cf..1595435 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2274,6 +2274,7 @@
atomic_set(&fs_info->balance_cancel_req, 0);
fs_info->balance_ctl = NULL;
init_waitqueue_head(&fs_info->balance_wait_q);
+ btrfs_init_async_reclaim_work(&fs_info->async_reclaim_work);
sb->s_blocksize = 4096;
sb->s_blocksize_bits = blksize_bits(4096);
@@ -3586,6 +3587,8 @@
/* clear out the rbtree of defraggable inodes */
btrfs_cleanup_defrag_inodes(fs_info);
+ cancel_work_sync(&fs_info->async_reclaim_work);
+
if (!(fs_info->sb->s_flags & MS_RDONLY)) {
ret = btrfs_commit_super(root);
if (ret)
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 7e3e4f10..da8031b 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4200,6 +4200,98 @@
return ret;
}
+
+static inline u64
+btrfs_calc_reclaim_metadata_size(struct btrfs_root *root,
+ struct btrfs_space_info *space_info)
+{
+ u64 used;
+ u64 expected;
+ u64 to_reclaim;
+
+ to_reclaim = min_t(u64, num_online_cpus() * 1024 * 1024,
+ 16 * 1024 * 1024);
+ spin_lock(&space_info->lock);
+ if (can_overcommit(root, space_info, to_reclaim,
+ BTRFS_RESERVE_FLUSH_ALL)) {
+ to_reclaim = 0;
+ goto out;
+ }
+
+ used = space_info->bytes_used + space_info->bytes_reserved +
+ space_info->bytes_pinned + space_info->bytes_readonly +
+ space_info->bytes_may_use;
+ if (can_overcommit(root, space_info, 1024 * 1024,
+ BTRFS_RESERVE_FLUSH_ALL))
+ expected = div_factor_fine(space_info->total_bytes, 95);
+ else
+ expected = div_factor_fine(space_info->total_bytes, 90);
+ to_reclaim = used - expected;
+out:
+ spin_unlock(&space_info->lock);
+
+ return to_reclaim;
+}
+
+static inline int need_do_async_reclaim(struct btrfs_space_info *space_info,
+ struct btrfs_fs_info *fs_info, u64 used)
+{
+ return (used >= div_factor_fine(space_info->total_bytes, 95) &&
+ !btrfs_fs_closing(fs_info) &&
+ !test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state));
+}
+
+static int btrfs_need_do_async_reclaim(struct btrfs_space_info *space_info,
+ struct btrfs_fs_info *fs_info)
+{
+ u64 used;
+
+ spin_lock(&space_info->lock);
+ used = space_info->bytes_used + space_info->bytes_reserved +
+ space_info->bytes_pinned + space_info->bytes_readonly +
+ space_info->bytes_may_use;
+ if (need_do_async_reclaim(space_info, fs_info, used)) {
+ spin_unlock(&space_info->lock);
+ return 1;
+ }
+ spin_unlock(&space_info->lock);
+
+ return 0;
+}
+
+static void btrfs_async_reclaim_metadata_space(struct work_struct *work)
+{
+ struct btrfs_fs_info *fs_info;
+ struct btrfs_space_info *space_info;
+ u64 to_reclaim;
+ int flush_state;
+
+ fs_info = container_of(work, struct btrfs_fs_info, async_reclaim_work);
+ space_info = __find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA);
+
+ to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->fs_root,
+ space_info);
+ if (!to_reclaim)
+ return;
+
+ flush_state = FLUSH_DELAYED_ITEMS_NR;
+ do {
+ flush_space(fs_info->fs_root, space_info, to_reclaim,
+ to_reclaim, flush_state);
+ flush_state++;
+ if (!btrfs_need_do_async_reclaim(space_info, fs_info))
+ return;
+ } while (flush_state <= COMMIT_TRANS);
+
+ if (btrfs_need_do_async_reclaim(space_info, fs_info))
+ queue_work(system_unbound_wq, work);
+}
+
+void btrfs_init_async_reclaim_work(struct work_struct *work)
+{
+ INIT_WORK(work, btrfs_async_reclaim_metadata_space);
+}
+
/**
* reserve_metadata_bytes - try to reserve bytes from the block_rsv's space
* @root - the root we're allocating for
@@ -4307,8 +4399,13 @@
if (ret && flush != BTRFS_RESERVE_NO_FLUSH) {
flushing = true;
space_info->flush = 1;
+ } else if (!ret && space_info->flags & BTRFS_BLOCK_GROUP_METADATA) {
+ used += orig_bytes;
+ if (need_do_async_reclaim(space_info, root->fs_info, used) &&
+ !work_busy(&root->fs_info->async_reclaim_work))
+ queue_work(system_unbound_wq,
+ &root->fs_info->async_reclaim_work);
}
-
spin_unlock(&space_info->lock);
if (!ret || flush == BTRFS_RESERVE_NO_FLUSH)
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index aeddbfc..0085b1e 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1393,6 +1393,7 @@
* this also happens on 'umount -rf' or on shutdown, when
* the filesystem is busy.
*/
+ cancel_work_sync(&fs_info->async_reclaim_work);
/* wait for the uuid_scan task to finish */
down(&fs_info->uuid_tree_rescan_sem);
