Commit d30291b9 authored by Ilya Dryomov's avatar Ilya Dryomov
Browse files

libceph: variable-sized ceph_object_id 



Currently ceph_object_id can hold object names of up to 100
(CEPH_MAX_OID_NAME_LEN) characters.  This is enough for all use cases,
expect one - long rbd image names:

- a format 1 header is named "<imgname>.rbd"
- an object that points to a format 2 header is named "rbd_id.<imgname>"

We operate on these potentially long-named objects during rbd map, and,
for format 1 images, during header refresh.  (A format 2 header name is
a small system-generated string.)

Lift this 100 character limit by making ceph_object_id be able to point
to an externally-allocated string.  Apart from being able to work with
almost arbitrarily-long named objects, this allows us to reduce the
size of ceph_object_id from >100 bytes to 64 bytes.

Signed-off-by: default avatarIlya Dryomov <idryomov@gmail.com>
parent 711da55d

drivers/block/rbd.c

+6 −2
Original line number Diff line number Diff line
@@ -1965,7 +1965,9 @@ static struct ceph_osd_request *rbd_osd_req_create( 
	osd_req->r_priv = obj_request;



	osd_req->r_base_oloc.pool = ceph_file_layout_pg_pool(rbd_dev->layout);

	ceph_oid_set_name(&osd_req->r_base_oid, obj_request->object_name);

	if (ceph_oid_aprintf(&osd_req->r_base_oid, GFP_NOIO, "%s",

			     obj_request->object_name))

		goto fail;



	if (ceph_osdc_alloc_messages(osd_req, GFP_NOIO))

		goto fail;
@@ -2017,7 +2019,9 @@ rbd_osd_req_create_copyup(struct rbd_obj_request *obj_request) 
	osd_req->r_priv = obj_request;



	osd_req->r_base_oloc.pool = ceph_file_layout_pg_pool(rbd_dev->layout);

	ceph_oid_set_name(&osd_req->r_base_oid, obj_request->object_name);

	if (ceph_oid_aprintf(&osd_req->r_base_oid, GFP_NOIO, "%s",

			     obj_request->object_name))

		goto fail;



	if (ceph_osdc_alloc_messages(osd_req, GFP_NOIO))

		goto fail;

fs/ceph/addr.c

+2 −4
Original line number Diff line number Diff line
@@ -1758,9 +1758,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool) 
	rd_req->r_flags = CEPH_OSD_FLAG_READ;

	osd_req_op_init(rd_req, 0, CEPH_OSD_OP_STAT, 0);

	rd_req->r_base_oloc.pool = pool;

	snprintf(rd_req->r_base_oid.name, sizeof(rd_req->r_base_oid.name),

		 "%llx.00000000", ci->i_vino.ino);

	rd_req->r_base_oid.name_len = strlen(rd_req->r_base_oid.name);

	ceph_oid_printf(&rd_req->r_base_oid, "%llx.00000000", ci->i_vino.ino);



	err = ceph_osdc_alloc_messages(rd_req, GFP_NOFS);

	if (err)
@@ -1777,7 +1775,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool) 
			  CEPH_OSD_FLAG_ACK | CEPH_OSD_FLAG_ONDISK;

	osd_req_op_init(wr_req, 0, CEPH_OSD_OP_CREATE, CEPH_OSD_OP_FLAG_EXCL);

	wr_req->r_base_oloc.pool = pool;

	wr_req->r_base_oid = rd_req->r_base_oid;

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



	err = ceph_osdc_alloc_messages(wr_req, GFP_NOFS);

	if (err)

fs/ceph/file.c

+1 −1
Original line number Diff line number Diff line
@@ -715,7 +715,7 @@ static void ceph_aio_retry_work(struct work_struct *work) 
			CEPH_OSD_FLAG_ONDISK |

			CEPH_OSD_FLAG_WRITE;

	req->r_base_oloc = orig_req->r_base_oloc;

	req->r_base_oid = orig_req->r_base_oid;

	ceph_oid_copy(&req->r_base_oid, &orig_req->r_base_oid);



	ret = ceph_osdc_alloc_messages(req, GFP_NOFS);

	if (ret) {

fs/ceph/ioctl.c

+1 −1
Original line number Diff line number Diff line
@@ -213,7 +213,7 @@ static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg) 
		 ceph_ino(inode), dl.object_no);



	oloc.pool = ceph_file_layout_pg_pool(ci->i_layout);

	ceph_oid_set_name(&oid, dl.object_name);

	ceph_oid_printf(&oid, "%s", dl.object_name);



	r = ceph_oloc_oid_to_pg(osdc->osdmap, &oloc, &oid, &pgid);

	if (r < 0) {

include/linux/ceph/osdmap.h

+37 −25
Original line number Diff line number Diff line
@@ -64,11 +64,47 @@ struct ceph_object_locator { 
 */

#define CEPH_MAX_OID_NAME_LEN 100



/*

 * 51-char inline_name is long enough for all cephfs and all but one

 * rbd requests: <imgname> in "<imgname>.rbd"/"rbd_id.<imgname>" can be

 * arbitrarily long (~PAGE_SIZE).  It's done once during rbd map; all

 * other rbd requests fit into inline_name.

 *

 * Makes ceph_object_id 64 bytes on 64-bit.

 */

#define CEPH_OID_INLINE_LEN 52



/*

 * Both inline and external buffers have space for a NUL-terminator,

 * which is carried around.  It's not required though - RADOS object

 * names don't have to be NUL-terminated and may contain NULs.

 */

struct ceph_object_id {

	char name[CEPH_MAX_OID_NAME_LEN];

	char *name;

	char inline_name[CEPH_OID_INLINE_LEN];

	int name_len;

};



static inline void ceph_oid_init(struct ceph_object_id *oid)

{

	oid->name = oid->inline_name;

	oid->name_len = 0;

}



static inline bool ceph_oid_empty(const struct ceph_object_id *oid)

{

	return oid->name == oid->inline_name && !oid->name_len;

}



void ceph_oid_copy(struct ceph_object_id *dest,

		   const struct ceph_object_id *src);

__printf(2, 3)

void ceph_oid_printf(struct ceph_object_id *oid, const char *fmt, ...);

__printf(3, 4)

int ceph_oid_aprintf(struct ceph_object_id *oid, gfp_t gfp,

		     const char *fmt, ...);

void ceph_oid_destroy(struct ceph_object_id *oid);



struct ceph_pg_mapping {

	struct rb_node node;

	struct ceph_pg pgid;
@@ -113,30 +149,6 @@ struct ceph_osdmap { 
	int crush_scratch_ary[CEPH_PG_MAX_SIZE * 3];

};



static inline void ceph_oid_set_name(struct ceph_object_id *oid,

				     const char *name)

{

	int len;



	len = strlen(name);

	if (len > sizeof(oid->name)) {

		WARN(1, "ceph_oid_set_name '%s' len %d vs %zu, truncating\n",

		     name, len, sizeof(oid->name));

		len = sizeof(oid->name);

	}



	memcpy(oid->name, name, len);

	oid->name_len = len;

}



static inline void ceph_oid_copy(struct ceph_object_id *dest,

				 struct ceph_object_id *src)

{

	BUG_ON(src->name_len > sizeof(dest->name));

	memcpy(dest->name, src->name, src->name_len);

	dest->name_len = src->name_len;

}



static inline int ceph_osd_exists(struct ceph_osdmap *map, int osd)

{

	return osd >= 0 && osd < map->max_osd &&

CRA Git | Maintained and supported by SUSTech CRA and CCSE