summaryrefslogtreecommitdiff
path: root/include/linux/ceph
diff options
context:
space:
mode:
authorIlya Dryomov <ilya.dryomov@inktank.com>2014-02-25 18:22:27 +0400
committerYan, Zheng <zheng.z.yan@intel.com>2014-04-03 06:33:51 +0400
commitc647b8a8c6366f849c2a237bfe525cb1d316d5f4 (patch)
tree8f3385992b44ba6bb5bcb1d745bb6df4dd6b5bbf /include/linux/ceph
parent7b25bf5f02c5c80adf96120e031dc3a1756ce54d (diff)
downloadlinux-c647b8a8c6366f849c2a237bfe525cb1d316d5f4.tar.xz
libceph: add support for CEPH_OSD_OP_SETALLOCHINT osd op
This is primarily for rbd's benefit and is supposed to combat fragmentation: "... knowing that rbd images have a 4m size, librbd can pass a hint that will let the osd do the xfs allocation size ioctl on new files so that they are allocated in 1m or 4m chunks. We've seen cases where users with rbd workloads have very high levels of fragmentation in xfs and this would mitigate that and probably have a pretty nice performance benefit." SETALLOCHINT is considered advisory, so our backwards compatibility mechanism here is to set FAILOK flag for all SETALLOCHINT ops. Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com> Reviewed-by: Sage Weil <sage@inktank.com> Reviewed-by: Alex Elder <elder@linaro.org>
Diffstat (limited to 'include/linux/ceph')
-rw-r--r--include/linux/ceph/osd_client.h8
-rw-r--r--include/linux/ceph/rados.h7
2 files changed, 15 insertions, 0 deletions
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index e94f5da251d6..c42d1ada685f 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -103,6 +103,10 @@ struct ceph_osd_req_op {
u32 timeout;
__u8 flag;
} watch;
+ struct {
+ u64 expected_object_size;
+ u64 expected_write_size;
+ } alloc_hint;
};
};
@@ -294,6 +298,10 @@ extern void osd_req_op_cls_init(struct ceph_osd_request *osd_req,
extern void osd_req_op_watch_init(struct ceph_osd_request *osd_req,
unsigned int which, u16 opcode,
u64 cookie, u64 version, int flag);
+extern void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req,
+ unsigned int which,
+ u64 expected_object_size,
+ u64 expected_write_size);
extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
struct ceph_snap_context *snapc,
diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index 8f9bf4570215..2caabef8d369 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -227,6 +227,9 @@ enum {
CEPH_OSD_OP_OMAPRMKEYS = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 24,
CEPH_OSD_OP_OMAP_CMP = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 25,
+ /* hints */
+ CEPH_OSD_OP_SETALLOCHINT = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 35,
+
/** multi **/
CEPH_OSD_OP_CLONERANGE = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_MULTI | 1,
CEPH_OSD_OP_ASSERT_SRC_VERSION = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_MULTI | 2,
@@ -416,6 +419,10 @@ struct ceph_osd_op {
__le64 offset, length;
__le64 src_offset;
} __attribute__ ((packed)) clonerange;
+ struct {
+ __le64 expected_object_size;
+ __le64 expected_write_size;
+ } __attribute__ ((packed)) alloc_hint;
};
__le32 payload_len;
} __attribute__ ((packed));