From c647b8a8c6366f849c2a237bfe525cb1d316d5f4 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 25 Feb 2014 16:22:27 +0200 Subject: 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 Reviewed-by: Sage Weil Reviewed-by: Alex Elder --- include/linux/ceph/rados.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux/ceph/rados.h') 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)); -- cgit v1.2.3-55-g7522