diff options
author | Sha Zhengju <handai.szj@taobao.com> | 2013-08-21 10:27:34 +0200 |
---|---|---|
committer | Sage Weil <sage@inktank.com> | 2013-08-28 01:29:44 +0200 |
commit | 7d6e1f5461d0c16eb6aa8d226976995856d85e4e (patch) | |
tree | b85d1758b3969499ff993bac4b16962f442fd559 /fs/ceph | |
parent | ceph: allow sync_read/write return partial successed size of read/write. (diff) | |
download | linux-7d6e1f5461d0c16eb6aa8d226976995856d85e4e.tar.xz linux-7d6e1f5461d0c16eb6aa8d226976995856d85e4e.zip |
ceph: use vfs __set_page_dirty_nobuffers interface instead of doing it inside filesystem
Following we will begin to add memcg dirty page accounting around
__set_page_dirty_{buffers,nobuffers} in vfs layer, so we'd better use vfs interface to
avoid exporting those details to filesystems.
Since vfs set_page_dirty() should be called under page lock, here we don't need elaborate
codes to handle racy anymore, and two WARN_ON() are added to detect such exceptions.
Thanks very much for Sage and Yan Zheng's coaching!
I tested it in a two server's ceph environment that one is client and the other is
mds/osd/mon, and run the following fsx test from xfstests:
./fsx 1MB -N 50000 -p 10000 -l 1048576
./fsx 10MB -N 50000 -p 10000 -l 10485760
./fsx 100MB -N 50000 -p 10000 -l 104857600
The fsx does lots of mmap-read/mmap-write/truncate operations and the tests completed
successfully without triggering any of WARN_ON.
Signed-off-by: Sha Zhengju <handai.szj@taobao.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Diffstat (limited to 'fs/ceph')
-rw-r--r-- | fs/ceph/addr.c | 43 |
1 files changed, 14 insertions, 29 deletions
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index cb78ce81d6a6..3bed7da38326 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -70,15 +70,16 @@ static int ceph_set_page_dirty(struct page *page) struct address_space *mapping = page->mapping; struct inode *inode; struct ceph_inode_info *ci; - int undo = 0; struct ceph_snap_context *snapc; + int ret; if (unlikely(!mapping)) return !TestSetPageDirty(page); - if (TestSetPageDirty(page)) { + if (PageDirty(page)) { dout("%p set_page_dirty %p idx %lu -- already dirty\n", mapping->host, page, page->index); + BUG_ON(!PagePrivate(page)); return 0; } @@ -107,35 +108,19 @@ static int ceph_set_page_dirty(struct page *page) snapc, snapc->seq, snapc->num_snaps); spin_unlock(&ci->i_ceph_lock); - /* now adjust page */ - spin_lock_irq(&mapping->tree_lock); - if (page->mapping) { /* Race with truncate? */ - WARN_ON_ONCE(!PageUptodate(page)); - account_page_dirtied(page, page->mapping); - radix_tree_tag_set(&mapping->page_tree, - page_index(page), PAGECACHE_TAG_DIRTY); - - /* - * Reference snap context in page->private. Also set - * PagePrivate so that we get invalidatepage callback. - */ - page->private = (unsigned long)snapc; - SetPagePrivate(page); - } else { - dout("ANON set_page_dirty %p (raced truncate?)\n", page); - undo = 1; - } - - spin_unlock_irq(&mapping->tree_lock); - - if (undo) - /* whoops, we failed to dirty the page */ - ceph_put_wrbuffer_cap_refs(ci, 1, snapc); + /* + * Reference snap context in page->private. Also set + * PagePrivate so that we get invalidatepage callback. + */ + BUG_ON(PagePrivate(page)); + page->private = (unsigned long)snapc; + SetPagePrivate(page); - __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); + ret = __set_page_dirty_nobuffers(page); + WARN_ON(!PageLocked(page)); + WARN_ON(!page->mapping); - BUG_ON(!PageDirty(page)); - return 1; + return ret; } /* |