AcoSail/kernel_optimize_test
8
0
Fork 0
forked from luck/tmp_suning_uos_patched
Code Pull Requests Activity

ceph: use copy-from2 op in copy_file_range

Browse Source 
Instead of using the copy-from operation, switch copy_file_range to the
new copy-from2 operation, which allows to send the truncate_seq and
truncate_size parameters.

If an OSD does not support the copy-from2 operation it will return
-EOPNOTSUPP.  In that case, the kernel client will stop trying to do
remote object copies for this fs client and will always use the generic
VFS copy_file_range.

Signed-off-by: Luis Henriques <lhenriques@suse.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
This commit is contained in:
Luis Henriques 2020-01-08 10:03:53 +00:00 committed by Ilya Dryomov
parent 045100cd79
commit 78beb0ff2f
6 changed files with 28 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
fs/ceph/file.c
View File

@ -1974,6 +1974,9 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
if (ceph_test_mount_opt(src_fsc, NOCOPYFROM))
return -EOPNOTSUPP;
if (!src_fsc->have_copy_from2)
return -EOPNOTSUPP;
/*
* Striped file layouts require that we copy partial objects, but the
* OSD copy-from operation only supports full-object copies. Limit
@ -2101,8 +2104,14 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
CEPH_OSD_OP_FLAG_FADVISE_NOCACHE,
&dst_oid, &dst_oloc,
CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL |
CEPH_OSD_OP_FLAG_FADVISE_DONTNEED, 0);
CEPH_OSD_OP_FLAG_FADVISE_DONTNEED,
dst_ci->i_truncate_seq, dst_ci->i_truncate_size,
CEPH_OSD_COPY_FROM_FLAG_TRUNCATE_SEQ);
if (err) {
if (err == -EOPNOTSUPP) {
src_fsc->have_copy_from2 = false;
pr_notice("OSDs don't support copy-from2; disabling copy offload\n");
}
dout("ceph_osdc_copy_from returned %d\n", err);
if (!ret)
ret = err;

1
fs/ceph/super.c
View File

@ -718,6 +718,7 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
fsc->sb = NULL;
fsc->mount_state = CEPH_MOUNT_MOUNTING;
fsc->filp_gen = 1;
fsc->have_copy_from2 = true;
atomic_long_set(&fsc->writeback_count, 0);

2
fs/ceph/super.h
View File

@ -106,6 +106,8 @@ struct ceph_fs_client {
unsigned long last_auto_reconnect;
bool blacklisted;
bool have_copy_from2;
u32 filp_gen;
loff_t max_file_size;

1
include/linux/ceph/osd_client.h
View File

@ -534,6 +534,7 @@ int ceph_osdc_copy_from(struct ceph_osd_client *osdc,
struct ceph_object_id *dst_oid,
struct ceph_object_locator *dst_oloc,
u32 dst_fadvise_flags,
u32 truncate_seq, u64 truncate_size,
u8 copy_from_flags);
/* watch/notify */

2
include/linux/ceph/rados.h
View File

@ -256,6 +256,7 @@ extern const char *ceph_osd_state_name(int s);
\
/* tiering */ \
f(COPY_FROM, __CEPH_OSD_OP(WR, DATA, 26), "copy-from") \
f(COPY_FROM2, __CEPH_OSD_OP(WR, DATA, 45), "copy-from2") \
f(COPY_GET_CLASSIC, __CEPH_OSD_OP(RD, DATA, 27), "copy-get-classic") \
f(UNDIRTY, __CEPH_OSD_OP(WR, DATA, 28), "undirty") \
f(ISDIRTY, __CEPH_OSD_OP(RD, DATA, 29), "isdirty") \
@ -446,6 +447,7 @@ enum {
CEPH_OSD_COPY_FROM_FLAG_MAP_SNAP_CLONE = 8, /* map snap direct to
* cloneid */
CEPH_OSD_COPY_FROM_FLAG_RWORDERED = 16, /* order with write */
CEPH_OSD_COPY_FROM_FLAG_TRUNCATE_SEQ = 32, /* send truncate_{seq,size} */
};
enum {

18
net/ceph/osd_client.c
View File

@ -402,7 +402,7 @@ static void osd_req_op_data_release(struct ceph_osd_request *osd_req,
case CEPH_OSD_OP_LIST_WATCHERS:
ceph_osd_data_release(&op->list_watchers.response_data);
break;
case CEPH_OSD_OP_COPY_FROM:
case CEPH_OSD_OP_COPY_FROM2:
ceph_osd_data_release(&op->copy_from.osd_data);
break;
default:
@ -697,7 +697,7 @@ static void get_num_data_items(struct ceph_osd_request *req,
case CEPH_OSD_OP_SETXATTR:
case CEPH_OSD_OP_CMPXATTR:
case CEPH_OSD_OP_NOTIFY_ACK:
case CEPH_OSD_OP_COPY_FROM:
case CEPH_OSD_OP_COPY_FROM2:
*num_request_data_items += 1;
break;
@ -1029,7 +1029,7 @@ static u32 osd_req_encode_op(struct ceph_osd_op *dst,
case CEPH_OSD_OP_CREATE:
case CEPH_OSD_OP_DELETE:
break;
case CEPH_OSD_OP_COPY_FROM:
case CEPH_OSD_OP_COPY_FROM2:
dst->copy_from.snapid = cpu_to_le64(src->copy_from.snapid);
dst->copy_from.src_version =
cpu_to_le64(src->copy_from.src_version);
@ -1966,7 +1966,7 @@ static void setup_request_data(struct ceph_osd_request *req)
ceph_osdc_msg_data_add(request_msg,
&op->notify_ack.request_data);
break;
case CEPH_OSD_OP_COPY_FROM:
case CEPH_OSD_OP_COPY_FROM2:
ceph_osdc_msg_data_add(request_msg,
&op->copy_from.osd_data);
break;
@ -5315,6 +5315,7 @@ static int osd_req_op_copy_from_init(struct ceph_osd_request *req,
struct ceph_object_locator *src_oloc,
u32 src_fadvise_flags,
u32 dst_fadvise_flags,
u32 truncate_seq, u64 truncate_size,
u8 copy_from_flags)
{
struct ceph_osd_req_op *op;
@ -5325,7 +5326,8 @@ static int osd_req_op_copy_from_init(struct ceph_osd_request *req,
if (IS_ERR(pages))
return PTR_ERR(pages);
op = _osd_req_op_init(req, 0, CEPH_OSD_OP_COPY_FROM, dst_fadvise_flags);
op = _osd_req_op_init(req, 0, CEPH_OSD_OP_COPY_FROM2,
dst_fadvise_flags);
op->copy_from.snapid = src_snapid;
op->copy_from.src_version = src_version;
op->copy_from.flags = copy_from_flags;
@ -5335,6 +5337,8 @@ static int osd_req_op_copy_from_init(struct ceph_osd_request *req,
end = p + PAGE_SIZE;
ceph_encode_string(&p, end, src_oid->name, src_oid->name_len);
encode_oloc(&p, end, src_oloc);
ceph_encode_32(&p, truncate_seq);
ceph_encode_64(&p, truncate_size);
op->indata_len = PAGE_SIZE - (end - p);
ceph_osd_data_pages_init(&op->copy_from.osd_data, pages,
@ -5350,6 +5354,7 @@ int ceph_osdc_copy_from(struct ceph_osd_client *osdc,
struct ceph_object_id *dst_oid,
struct ceph_object_locator *dst_oloc,
u32 dst_fadvise_flags,
u32 truncate_seq, u64 truncate_size,
u8 copy_from_flags)
{
struct ceph_osd_request *req;
@ -5366,7 +5371,8 @@ int ceph_osdc_copy_from(struct ceph_osd_client *osdc,
ret = osd_req_op_copy_from_init(req, src_snapid, src_version, src_oid,
src_oloc, src_fadvise_flags,
dst_fadvise_flags, copy_from_flags);
dst_fadvise_flags, truncate_seq,
truncate_size, copy_from_flags);
if (ret)
goto out;