btrfs: use tagged writepage to mitigate livelock of snapshot
Snapshot is expected to be fast. But if there are writers steadily
creating dirty pages in our subvolume, the snapshot may take a very long
time to complete. To fix the problem, we use tagged writepage for
snapshot flusher as we do in the generic write_cache_pages(), so we can
omit pages dirtied after the snapshot command.
This does not change the semantics regarding which data get to the
snapshot, if there are pages being dirtied during the snapshotting
operation. There's a sync called before snapshot is taken in old/new
case, any IO in flight just after that may be in the snapshot but this
depends on other system effects that might still sync the IO.
We do a simple snapshot speed test on a Intel D-1531 box:
fio --ioengine=libaio --iodepth=32 --bs=4k --rw=write --size=64G
--direct=0 --thread=1 --numjobs=1 --time_based --runtime=120
--filename=/mnt/sub/testfile --name=job1 --group_reporting & sleep 5;
time btrfs sub snap -r /mnt/sub /mnt/snap; killall fio
original: 1m58sec
patched: 6.54sec
This is the best case for this patch since for a sequential write case,
we omit nearly all pages dirtied after the snapshot command.
For a multi writers, random write test:
fio --ioengine=libaio --iodepth=32 --bs=4k --rw=randwrite --size=64G
--direct=0 --thread=1 --numjobs=4 --time_based --runtime=120
--filename=/mnt/sub/testfile --name=job1 --group_reporting & sleep 5;
time btrfs sub snap -r /mnt/sub /mnt/snap; killall fio
original: 15.83sec
patched: 10.35sec
The improvement is smaller compared to the sequential write case,
since we omit only half of the pages dirtied after snapshot command.
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Ethan Lien <ethanlien@synology.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 213a6a6..4de321a 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -29,6 +29,7 @@ enum {
BTRFS_INODE_IN_DELALLOC_LIST,
BTRFS_INODE_READDIO_NEED_LOCK,
BTRFS_INODE_HAS_PROPS,
+ BTRFS_INODE_SNAPSHOT_FLUSH,
};
/* in memory btrfs inode */
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index c48fcaf..e62824c 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3170,7 +3170,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
struct inode *inode, u64 new_size,
u32 min_type);
-int btrfs_start_delalloc_inodes(struct btrfs_root *root);
+int btrfs_start_delalloc_snapshot(struct btrfs_root *root);
int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int nr);
int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
unsigned int extra_bits,
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index c1c4a8f..926bf30 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3911,12 +3911,25 @@ static int extent_write_cache_pages(struct address_space *mapping,
range_whole = 1;
scanned = 1;
}
- if (wbc->sync_mode == WB_SYNC_ALL)
+
+ /*
+ * We do the tagged writepage as long as the snapshot flush bit is set
+ * and we are the first one who do the filemap_flush() on this inode.
+ *
+ * The nr_to_write == LONG_MAX is needed to make sure other flushers do
+ * not race in and drop the bit.
+ */
+ if (range_whole && wbc->nr_to_write == LONG_MAX &&
+ test_and_clear_bit(BTRFS_INODE_SNAPSHOT_FLUSH,
+ &BTRFS_I(inode)->runtime_flags))
+ wbc->tagged_writepages = 1;
+
+ if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag = PAGECACHE_TAG_TOWRITE;
else
tag = PAGECACHE_TAG_DIRTY;
retry:
- if (wbc->sync_mode == WB_SYNC_ALL)
+ if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, index, end);
done_index = index;
while (!done && !nr_to_write_done && (index <= end) &&
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d7fa0fb..2585200 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -9961,7 +9961,7 @@ static struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode
* some fairly slow code that needs optimization. This walks the list
* of all the inodes with pending delalloc and forces them to disk.
*/
-static int start_delalloc_inodes(struct btrfs_root *root, int nr)
+static int start_delalloc_inodes(struct btrfs_root *root, int nr, bool snapshot)
{
struct btrfs_inode *binode;
struct inode *inode;
@@ -9989,6 +9989,9 @@ static int start_delalloc_inodes(struct btrfs_root *root, int nr)
}
spin_unlock(&root->delalloc_lock);
+ if (snapshot)
+ set_bit(BTRFS_INODE_SNAPSHOT_FLUSH,
+ &binode->runtime_flags);
work = btrfs_alloc_delalloc_work(inode);
if (!work) {
iput(inode);
@@ -10022,7 +10025,7 @@ static int start_delalloc_inodes(struct btrfs_root *root, int nr)
return ret;
}
-int btrfs_start_delalloc_inodes(struct btrfs_root *root)
+int btrfs_start_delalloc_snapshot(struct btrfs_root *root)
{
struct btrfs_fs_info *fs_info = root->fs_info;
int ret;
@@ -10030,7 +10033,7 @@ int btrfs_start_delalloc_inodes(struct btrfs_root *root)
if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
return -EROFS;
- ret = start_delalloc_inodes(root, -1);
+ ret = start_delalloc_inodes(root, -1, true);
if (ret > 0)
ret = 0;
return ret;
@@ -10059,7 +10062,7 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int nr)
&fs_info->delalloc_roots);
spin_unlock(&fs_info->delalloc_root_lock);
- ret = start_delalloc_inodes(root, nr);
+ ret = start_delalloc_inodes(root, nr, false);
btrfs_put_fs_root(root);
if (ret < 0)
goto out;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 36d8dcc..3e9bf28 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -788,7 +788,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
wait_event(root->subv_writers->wait,
percpu_counter_sum(&root->subv_writers->counter) == 0);
- ret = btrfs_start_delalloc_inodes(root);
+ ret = btrfs_start_delalloc_snapshot(root);
if (ret)
goto dec_and_free;