diff mbox

[13/13] ceph: wait on writeback after writing snapshot data

Message ID 20170904093908.57316-14-zyan@redhat.com (mailing list archive)
State New, archived
Headers show

Commit Message

Yan, Zheng Sept. 4, 2017, 9:39 a.m. UTC
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>
---
 fs/ceph/addr.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)
diff mbox

Patch

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 @@  static int ceph_writepages_start(struct address_space *mapping,
 		/* 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;