ceph: wait on writeback after writing snapshot data

In sync mode, writepages() needs to write all dirty pages. But
it can only write dirty pages associated with the oldest snapc.
To write dirty pages associated with next snapc, it needs to wait
until current writes complete.

Without this wait, writepages() keeps looking up dirty pages, but
the found dirty pages are not writeable. It wastes CPU time.

Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>

1 files changed, 24 insertions, 0 deletions

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 1ffdb903eb79..b3e3edc09d80 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1165,6 +1165,30 @@ release_pvec_pages:
 		/* more to do; loop back to beginning of file */
 		dout("writepages looping back to beginning of file\n");
 		end = start_index - 1; /* OK even when start_index == 0 */
+
+		/* to write dirty pages associated with next snapc,
+		 * we need to wait until current writes complete */
+		if (wbc->sync_mode != WB_SYNC_NONE &&
+		    start_index == 0 && /* all dirty pages were checked */
+		    !ceph_wbc.head_snapc) {
+			struct page *page;
+			unsigned i, nr;
+			index = 0;
+			while ((index <= end) &&
+			       (nr = pagevec_lookup_tag(&pvec, mapping, &index,
+							PAGECACHE_TAG_WRITEBACK,
+							PAGEVEC_SIZE))) {
+				for (i = 0; i < nr; i++) {
+					page = pvec.pages[i];
+					if (page_snap_context(page) != snapc)
+						continue;
+					wait_on_page_writeback(page);
+				}
+				pagevec_release(&pvec);
+				cond_resched();
+			}
+		}
+
 		start_index = 0;
 		index = 0;
 		goto retry;