Commit 79788c69 authored by Sage Weil's avatar Sage Weil
Browse files

ceph: release all pages after successful osd write response 



We release all the pages, even if the osd response was
different than the number of pages written. This could only
happen due to truncation that arrives the osd in
different order, for which we want the pages released anyway.

Signed-off-by: default avatarYehuda Sadeh <yehuda@hq.newdream.net>
Signed-off-by: default avatarSage Weil <sage@newdream.net>
parent 0c948992

fs/ceph/addr.c

+7 −3
Original line number Diff line number Diff line
@@ -524,9 +524,13 @@ static void writepages_finish(struct ceph_osd_request *req, 
	bytes = le64_to_cpu(op->extent.length);



	if (rc >= 0) {

		wrote = (bytes + (offset & ~PAGE_CACHE_MASK) + ~PAGE_CACHE_MASK)

			>> PAGE_CACHE_SHIFT;

		WARN_ON(wrote != req->r_num_pages);

		/*

		 * Assume we wrote the pages we originally sent.  The

		 * osd might reply with fewer pages if our writeback

		 * raced with a truncation and was adjusted at the osd,

		 * so don't believe the reply.

		 */

		wrote = req->r_num_pages;

	} else {

		wrote = 0;

		mapping_set_error(mapping, rc);