From: Ethan Lien <ethanlien@synology.com>
Date: Thu, 1 Nov 2018 14:49:03 +0800
Subject: btrfs: use tagged writepage to mitigate livelock of snapshot
Git-commit: 3cd24c698004d2f7668e0eb9fc1f096f533c791b
Patch-mainline: v5.0-rc1
References: bsc#1135481
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>
Acked-by: Nikolay Borisov <nborisov@suse.com>
---
fs/btrfs/btrfs_inode.h | 1 +
fs/btrfs/ctree.h | 2 +-
fs/btrfs/extent_io.c | 17 +++++++++++++++--
fs/btrfs/inode.c | 20 ++++++++++----------
fs/btrfs/ioctl.c | 2 +-
5 files changed, 28 insertions(+), 14 deletions(-)
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -42,6 +42,7 @@ enum {
BTRFS_INODE_IN_DELALLOC_LIST,
BTRFS_INODE_READDIO_NEED_LOCK,
BTRFS_INODE_HAS_PROPS,
+ BTRFS_INODE_SNAPSHOT_FLUSH,
};
/* in memory btrfs inode */
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3243,7 +3243,7 @@ int btrfs_truncate_inode_items(struct bt
struct inode *inode, u64 new_size,
u32 min_type);
-int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput);
+int btrfs_start_delalloc_snapshot(struct btrfs_root *root);
int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput,
int nr);
int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3988,12 +3988,25 @@ static int extent_write_cache_pages(stru
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) &&
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -9962,8 +9962,7 @@ void btrfs_wait_and_free_delalloc_work(s
* 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 delay_iput,
- int nr)
+static int start_delalloc_inodes(struct btrfs_root *root, int nr, bool snapshot)
{
struct btrfs_inode *binode;
struct inode *inode;
@@ -9991,12 +9990,13 @@ static int __start_delalloc_inodes(struc
}
spin_unlock(&root->delalloc_lock);
- work = btrfs_alloc_delalloc_work(inode, delay_iput);
+ if (snapshot)
+ set_bit(BTRFS_INODE_SNAPSHOT_FLUSH,
+ &binode->runtime_flags);
+
+ work = btrfs_alloc_delalloc_work(inode, 0);
if (!work) {
- if (delay_iput)
- btrfs_add_delayed_iput(inode);
- else
- iput(inode);
+ iput(inode);
ret = -ENOMEM;
goto out;
}
@@ -10026,7 +10026,7 @@ out:
return ret;
}
-int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
+int btrfs_start_delalloc_snapshot(struct btrfs_root *root)
{
struct btrfs_fs_info *fs_info = root->fs_info;
int ret;
@@ -10034,7 +10034,7 @@ int btrfs_start_delalloc_inodes(struct b
if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
return -EROFS;
- ret = __start_delalloc_inodes(root, delay_iput, -1);
+ ret = start_delalloc_inodes(root, -1, true);
if (ret > 0)
ret = 0;
return ret;
@@ -10064,7 +10064,7 @@ int btrfs_start_delalloc_roots(struct bt
&fs_info->delalloc_roots);
spin_unlock(&fs_info->delalloc_root_lock);
- ret = __start_delalloc_inodes(root, delay_iput, nr);
+ ret = start_delalloc_inodes(root, nr, false);
btrfs_put_fs_root(root);
if (ret < 0)
goto out;
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -697,7 +697,7 @@ static int create_snapshot(struct btrfs_
smp_mb__after_atomic();
btrfs_wait_for_no_snapshoting_writes(root);
- ret = btrfs_start_delalloc_inodes(root, 0);
+ ret = btrfs_start_delalloc_snapshot(root);
if (ret)
goto dec_and_free;