diff options
| author | Wu Fengguang <fengguang.wu@intel.com> | 2010-06-06 10:38:15 -0600 |
|---|---|---|
| committer | Wu Fengguang <fengguang.wu@intel.com> | 2011-06-08 08:25:20 +0800 |
| commit | 6e6938b6d3130305a5960c86b1a9b21e58cf6144 (patch) | |
| tree | de5546e8390ce31cd31412d2ef78ce732a42191c /fs/ext4 | |
| parent | 59c5f46fbe01a00eedf54a23789634438bb80603 (diff) | |
writeback: introduce .tagged_writepages for the WB_SYNC_NONE sync stage
sync(2) is performed in two stages: the WB_SYNC_NONE sync and the
WB_SYNC_ALL sync. Identify the first stage with .tagged_writepages and
do livelock prevention for it, too.
Jan's commit f446daaea9 ("mm: implement writeback livelock avoidance
using page tagging") is a partial fix in that it only fixed the
WB_SYNC_ALL phase livelock.
Although ext4 is tested to no longer livelock with commit f446daaea9,
it may due to some "redirty_tail() after pages_skipped" effect which
is by no means a guarantee for _all_ the file systems.
Note that writeback_inodes_sb() is called by not only sync(), they are
treated the same because the other callers also need livelock prevention.
Impact: It changes the order in which pages/inodes are synced to disk.
Now in the WB_SYNC_NONE stage, it won't proceed to write the next inode
until finished with the current inode.
Acked-by: Jan Kara <jack@suse.cz>
CC: Dave Chinner <david@fromorbit.com>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Diffstat (limited to 'fs/ext4')
| -rw-r--r-- | fs/ext4/inode.c | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index a5763e3505b..8558b6c3450 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2741,7 +2741,7 @@ static int write_cache_pages_da(struct address_space *mapping, index = wbc->range_start >> PAGE_CACHE_SHIFT; end = wbc->range_end >> PAGE_CACHE_SHIFT; - if (wbc->sync_mode == WB_SYNC_ALL) + if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) tag = PAGECACHE_TAG_TOWRITE; else tag = PAGECACHE_TAG_DIRTY; @@ -2973,7 +2973,7 @@ static int ext4_da_writepages(struct address_space *mapping, } 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); while (!ret && wbc->nr_to_write > 0) { |