Commit 06e2d7dd authored by David Disseldorp's avatar David Disseldorp Committed by Greg Kroah-Hartman

rbd: use GFP_NOIO consistently for request allocations

commit 2224d879 upstream.

As of 5a60e876, RBD object request
allocations are made via rbd_obj_request_create() with GFP_NOIO.
However, subsequent OSD request allocations in rbd_osd_req_create*()
use GFP_ATOMIC.

With heavy page cache usage (e.g. OSDs running on same host as krbd
client), rbd_osd_req_create() order-1 GFP_ATOMIC allocations have been
observed to fail, where direct reclaim would have allowed GFP_NOIO
allocations to succeed.
Suggested-by: default avatarVlastimil Babka <vbabka@suse.cz>
Suggested-by: default avatarNeil Brown <neilb@suse.com>
Signed-off-by: default avatarDavid Disseldorp <ddiss@suse.de>
Signed-off-by: default avatarIlya Dryomov <idryomov@gmail.com>
Signed-off-by: default avatarGreg Kroah-Hartman <gregkh@linuxfoundation.org>
parent e4f2138e
......@@ -1955,7 +1955,7 @@ static struct ceph_osd_request *rbd_osd_req_create(
osdc = &rbd_dev->rbd_client->client->osdc;
osd_req = ceph_osdc_alloc_request(osdc, snapc, num_ops, false,
GFP_ATOMIC);
GFP_NOIO);
if (!osd_req)
return NULL; /* ENOMEM */
......@@ -2004,7 +2004,7 @@ rbd_osd_req_create_copyup(struct rbd_obj_request *obj_request)
rbd_dev = img_request->rbd_dev;
osdc = &rbd_dev->rbd_client->client->osdc;
osd_req = ceph_osdc_alloc_request(osdc, snapc, num_osd_ops,
false, GFP_ATOMIC);
false, GFP_NOIO);
if (!osd_req)
return NULL; /* ENOMEM */
......@@ -2506,7 +2506,7 @@ static int rbd_img_request_fill(struct rbd_img_request *img_request,
bio_chain_clone_range(&bio_list,
&bio_offset,
clone_size,
GFP_ATOMIC);
GFP_NOIO);
if (!obj_request->bio_list)
goto out_unwind;
} else if (type == OBJ_REQUEST_PAGES) {
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment