Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit b2deee2d authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'ceph-for-4.11-rc1' of git://github.com/ceph/ceph-client 

Pull ceph updates from Ilya Dryomov:
 "This time around we have:

   - support for rbd data-pool feature, which enables rbd images on
     erasure-coded pools (myself). CEPH_PG_MAX_SIZE has been bumped to
     allow erasure-coded profiles with k+m up to 32.

   - a patch for ceph_d_revalidate() performance regression introduced
     in 4.9, along with some cleanups in the area (Jeff Layton)

   - a set of fixes for unsafe ->d_parent accesses in CephFS (Jeff
     Layton)

   - buffered reads are now processed in rsize windows instead of rasize
     windows (Andreas Gerstmayr). The new default for rsize mount option
     is 64M.

   - ack vs commit distinction is gone, greatly simplifying ->fsync()
     and MOSDOpReply handling code (myself)

  ... also a few filesystem bug fixes from Zheng, a CRUSH sync up (CRUSH
  computations are still serialized though) and several minor fixes and
  cleanups all over"

* tag 'ceph-for-4.11-rc1' of git://github.com/ceph/ceph-client: (52 commits)
  libceph, rbd, ceph: WRITE | ONDISK -> WRITE
  libceph: get rid of ack vs commit
  ceph: remove special ack vs commit behavior
  ceph: tidy some white space in get_nonsnap_parent()
  crush: fix dprintk compilation
  crush: do is_out test only if we do not collide
  ceph: remove req from unsafe list when unregistering it
  rbd: constify device_type structure
  rbd: kill obj_request->object_name and rbd_segment_name_cache
  rbd: store and use obj_request->object_no
  rbd: RBD_V{1,2}_DATA_FORMAT macros
  rbd: factor out __rbd_osd_req_create()
  rbd: set offset and length outside of rbd_obj_request_create()
  rbd: support for data-pool feature
  rbd: introduce rbd_init_layout()
  rbd: use rbd_obj_bytes() more
  rbd: remove now unused rbd_obj_request_wait() and helpers
  rbd: switch rbd_obj_method_sync() to ceph_osdc_call()
  libceph: pass reply buffer length through ceph_osdc_call()
  rbd: do away with obj_request in rbd_obj_read_sync()
  ...
parents d4f4cf77 54ea0046

Documentation/filesystems/ceph.txt

+2 −3
Original line number Diff line number Diff line
@@ -98,11 +98,10 @@ Mount Options 
	size.



  rsize=X

	Specify the maximum read size in bytes.  By default there is no

	maximum.

	Specify the maximum read size in bytes.  Default: 64 MB.



  rasize=X

	Specify the maximum readahead.

	Specify the maximum readahead.  Default: 8 MB.



  mount_timeout=X

	Specify the timeout value for mount (in seconds), in the case

drivers/block/rbd.c

+227 −374

File changed.

Preview size limit exceeded, changes collapsed.

drivers/block/rbd_types.h

+4 −6
Original line number Diff line number Diff line
@@ -25,8 +25,8 @@ 
 */



#define RBD_HEADER_PREFIX      "rbd_header."

#define RBD_DATA_PREFIX        "rbd_data."

#define RBD_ID_PREFIX          "rbd_id."

#define RBD_V2_DATA_FORMAT     "%s.%016llx"



#define RBD_LOCK_NAME          "rbd_lock"

#define RBD_LOCK_TAG           "internal"
@@ -42,13 +42,14 @@ enum rbd_notify_op { 
/*

 * For format version 1, rbd image 'foo' consists of objects

 *   foo.rbd		- image metadata

 *   rb.<idhi>.<idlo>.00000000

 *   rb.<idhi>.<idlo>.00000001

 *   rb.<idhi>.<idlo>.<extra>.000000000000

 *   rb.<idhi>.<idlo>.<extra>.000000000001

 *   ...		- data

 * There is no notion of a persistent image id in rbd format 1.

 */



#define RBD_SUFFIX		".rbd"

#define RBD_V1_DATA_FORMAT	"%s.%012llx"



#define RBD_DIRECTORY           "rbd_directory"

#define RBD_INFO                "rbd_info"
@@ -57,9 +58,6 @@ enum rbd_notify_op { 
#define RBD_MIN_OBJ_ORDER       16

#define RBD_MAX_OBJ_ORDER       30



#define RBD_COMP_NONE		0

#define RBD_CRYPT_NONE		0



#define RBD_HEADER_TEXT		"<<< Rados Block Device Image >>>\n"

#define RBD_HEADER_SIGNATURE	"RBD"

#define RBD_HEADER_VERSION	"001.005"

fs/ceph/addr.c

+8 −11
Original line number Diff line number Diff line
@@ -391,6 +391,7 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max) 
			nr_pages = i;

			if (nr_pages > 0) {

				len = nr_pages << PAGE_SHIFT;

				osd_req_op_extent_update(req, 0, len);

				break;

			}

			goto out_pages;
@@ -771,7 +772,7 @@ static int ceph_writepages_start(struct address_space *mapping, 
	     wbc->sync_mode == WB_SYNC_NONE ? "NONE" :

	     (wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));



	if (ACCESS_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {

	if (READ_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {

		if (ci->i_wrbuffer_ref > 0) {

			pr_warn_ratelimited(

				"writepage_start %p %lld forced umount\n",
@@ -1017,8 +1018,7 @@ static int ceph_writepages_start(struct address_space *mapping, 
					&ci->i_layout, vino,

					offset, &len, 0, num_ops,

					CEPH_OSD_OP_WRITE,

					CEPH_OSD_FLAG_WRITE |

					CEPH_OSD_FLAG_ONDISK,

					CEPH_OSD_FLAG_WRITE,

					snapc, truncate_seq,

					truncate_size, false);

		if (IS_ERR(req)) {
@@ -1028,8 +1028,7 @@ static int ceph_writepages_start(struct address_space *mapping, 
						min(num_ops,

						    CEPH_OSD_SLAB_OPS),

						CEPH_OSD_OP_WRITE,

						CEPH_OSD_FLAG_WRITE |

						CEPH_OSD_FLAG_ONDISK,

						CEPH_OSD_FLAG_WRITE,

						snapc, truncate_seq,

						truncate_size, true);

			BUG_ON(IS_ERR(req));
@@ -1194,7 +1193,7 @@ static int ceph_update_writeable_page(struct file *file, 
	int r;

	struct ceph_snap_context *snapc, *oldest;



	if (ACCESS_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {

	if (READ_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {

		dout(" page %p forced umount\n", page);

		unlock_page(page);

		return -EIO;
@@ -1681,8 +1680,7 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page) 


	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,

				    ceph_vino(inode), 0, &len, 0, 1,

				    CEPH_OSD_OP_CREATE,

				    CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE,

				    CEPH_OSD_OP_CREATE, CEPH_OSD_FLAG_WRITE,

				    NULL, 0, 0, false);

	if (IS_ERR(req)) {

		err = PTR_ERR(req);
@@ -1699,8 +1697,7 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page) 


	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,

				    ceph_vino(inode), 0, &len, 1, 3,

				    CEPH_OSD_OP_WRITE,

				    CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE,

				    CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE,

				    NULL, ci->i_truncate_seq,

				    ci->i_truncate_size, false);

	if (IS_ERR(req)) {
@@ -1873,7 +1870,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, 
		goto out_unlock;

	}



	wr_req->r_flags = CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ACK;

	wr_req->r_flags = CEPH_OSD_FLAG_WRITE;

	osd_req_op_init(wr_req, 0, CEPH_OSD_OP_CREATE, CEPH_OSD_OP_FLAG_EXCL);

	ceph_oloc_copy(&wr_req->r_base_oloc, &rd_req->r_base_oloc);

	ceph_oid_copy(&wr_req->r_base_oid, &rd_req->r_base_oid);

fs/ceph/cache.c

+1 −1
Original line number Diff line number Diff line
@@ -234,7 +234,7 @@ void ceph_fscache_file_set_cookie(struct inode *inode, struct file *filp) 
		fscache_enable_cookie(ci->fscache, ceph_fscache_can_enable,

				inode);

		if (fscache_cookie_enabled(ci->fscache)) {

			dout("fscache_file_set_cookie %p %p enabing cache\n",

			dout("fscache_file_set_cookie %p %p enabling cache\n",

			     inode, filp);

		}

	}