* [RFC PATCH] osd: add new 'copy-from-notrunc' operation
2019-11-18 12:09 [RFC PATCH v3] ceph: add new obj copy OSD Op Luis Henriques
@ 2019-11-18 12:09 ` Luis Henriques
2019-11-18 12:09 ` [RFC PATCH] ceph: switch copy_file_range to " Luis Henriques
2019-11-18 13:12 ` [RFC PATCH v3] ceph: add new obj copy OSD Op Jeff Layton
2 siblings, 0 replies; 6+ messages in thread
From: Luis Henriques @ 2019-11-18 12:09 UTC (permalink / raw)
To: Jeff Layton, Sage Weil, Ilya Dryomov, Yan, Zheng, Gregory Farnum
Cc: ceph-devel, linux-kernel, Luis Henriques
The new 'copy-from-notrunc' is very similar to the 'copy-from' operation,
except that it receives 2 extra parameters: truncate_seq and
truncate_size.
Signed-off-by: Luis Henriques <lhenriques@suse.com>
---
src/include/rados.h | 1 +
src/osd/OSD.cc | 3 ++-
src/osd/PrimaryLogPG.cc | 24 +++++++++++++++++++-----
3 files changed, 22 insertions(+), 6 deletions(-)
diff --git a/src/include/rados.h b/src/include/rados.h
index 44cbacffcad8..bba0168c5f07 100644
--- a/src/include/rados.h
+++ b/src/include/rados.h
@@ -297,6 +297,7 @@ extern const char *ceph_osd_state_name(int s);
\
/* tiering */ \
f(COPY_FROM, __CEPH_OSD_OP(WR, DATA, 26), "copy-from") \
+ f(COPY_FROM_NOTRUNC, __CEPH_OSD_OP(WR, DATA, 45), "copy-from-notrunc") \
/* was copy-get-classic */ \
f(UNDIRTY, __CEPH_OSD_OP(WR, DATA, 28), "undirty") \
f(ISDIRTY, __CEPH_OSD_OP(RD, DATA, 29), "isdirty") \
diff --git a/src/osd/OSD.cc b/src/osd/OSD.cc
index 6b592ff85bfa..1d34bc683562 100644
--- a/src/osd/OSD.cc
+++ b/src/osd/OSD.cc
@@ -9919,7 +9919,8 @@ int OSD::init_op_flags(OpRequestRef& op)
(iter->op.op != CEPH_OSD_OP_RMXATTR) &&
(iter->op.op != CEPH_OSD_OP_STARTSYNC) &&
(iter->op.op != CEPH_OSD_OP_COPY_GET) &&
- (iter->op.op != CEPH_OSD_OP_COPY_FROM)) {
+ (iter->op.op != CEPH_OSD_OP_COPY_FROM) &&
+ (iter->op.op != CEPH_OSD_OP_COPY_FROM_NOTRUNC)) {
op->set_promote();
}
}
diff --git a/src/osd/PrimaryLogPG.cc b/src/osd/PrimaryLogPG.cc
index 2ef4ebf8b6cf..e4f884476fc0 100644
--- a/src/osd/PrimaryLogPG.cc
+++ b/src/osd/PrimaryLogPG.cc
@@ -282,9 +282,11 @@ public:
PrimaryLogPG::CopyResults *results = nullptr;
PrimaryLogPG::OpContext *ctx;
OSDOp &osd_op;
+ uint32_t truncate_seq;
+ uint64_t truncate_size;
- CopyFromCallback(PrimaryLogPG::OpContext *ctx, OSDOp &osd_op)
- : ctx(ctx), osd_op(osd_op) {
+ CopyFromCallback(PrimaryLogPG::OpContext *ctx, OSDOp &osd_op, uint32_t seq, uint64_t size)
+ : ctx(ctx), osd_op(osd_op), truncate_seq(seq), truncate_size(size) {
}
~CopyFromCallback() override {}
@@ -292,6 +294,10 @@ public:
results = results_.get<1>();
int r = results_.get<0>();
+ if (osd_op.op.op != CEPH_OSD_OP_COPY_FROM_NOTRUNC) {
+ truncate_seq = results->truncate_seq;
+ truncate_size = results->truncate_size;
+ }
// for finish_copyfrom
ctx->user_at_version = results->user_version;
@@ -5668,6 +5674,7 @@ int PrimaryLogPG::do_osd_ops(OpContext *ctx, vector<OSDOp>& ops)
case CEPH_OSD_OP_CACHE_TRY_FLUSH:
case CEPH_OSD_OP_UNDIRTY:
case CEPH_OSD_OP_COPY_FROM: // we handle user_version update explicitly
+ case CEPH_OSD_OP_COPY_FROM_NOTRUNC:
case CEPH_OSD_OP_CACHE_PIN:
case CEPH_OSD_OP_CACHE_UNPIN:
case CEPH_OSD_OP_SET_REDIRECT:
@@ -7664,17 +7671,24 @@ int PrimaryLogPG::do_osd_ops(OpContext *ctx, vector<OSDOp>& ops)
}
break;
+ case CEPH_OSD_OP_COPY_FROM_NOTRUNC:
case CEPH_OSD_OP_COPY_FROM:
++ctx->num_write;
result = 0;
{
object_t src_name;
object_locator_t src_oloc;
+ uint32_t truncate_seq = 0;
+ uint64_t truncate_size = 0;
snapid_t src_snapid = (uint64_t)op.copy_from.snapid;
version_t src_version = op.copy_from.src_version;
try {
decode(src_name, bp);
decode(src_oloc, bp);
+ if (op.op == CEPH_OSD_OP_COPY_FROM_NOTRUNC) {
+ decode(truncate_seq, bp);
+ decode(truncate_size, bp);
+ }
}
catch (buffer::error& e) {
result = -EINVAL;
@@ -7714,7 +7728,7 @@ int PrimaryLogPG::do_osd_ops(OpContext *ctx, vector<OSDOp>& ops)
result = -EINVAL;
break;
}
- CopyFromCallback *cb = new CopyFromCallback(ctx, osd_op);
+ CopyFromCallback *cb = new CopyFromCallback(ctx, osd_op, truncate_seq, truncate_size);
ctx->op_finishers[ctx->current_osd_subop_num].reset(
new CopyFromFinisher(cb));
start_copy(cb, ctx->obc, src, src_oloc, src_version,
@@ -9546,8 +9560,8 @@ void PrimaryLogPG::finish_copyfrom(CopyFromCallback *cb)
obs.oi.clear_omap_digest();
}
- obs.oi.truncate_seq = cb->results->truncate_seq;
- obs.oi.truncate_size = cb->results->truncate_size;
+ obs.oi.truncate_seq = cb->truncate_seq;
+ obs.oi.truncate_size = cb->truncate_size;
obs.oi.mtime = ceph::real_clock::to_timespec(cb->results->mtime);
ctx->mtime = utime_t();
^ permalink raw reply related [flat|nested] 6+ messages in thread
* [RFC PATCH] ceph: switch copy_file_range to 'copy-from-notrunc' operation
2019-11-18 12:09 [RFC PATCH v3] ceph: add new obj copy OSD Op Luis Henriques
2019-11-18 12:09 ` [RFC PATCH] osd: add new 'copy-from-notrunc' operation Luis Henriques
@ 2019-11-18 12:09 ` Luis Henriques
2019-11-18 13:12 ` [RFC PATCH v3] ceph: add new obj copy OSD Op Jeff Layton
2 siblings, 0 replies; 6+ messages in thread
From: Luis Henriques @ 2019-11-18 12:09 UTC (permalink / raw)
To: Jeff Layton, Sage Weil, Ilya Dryomov, Yan, Zheng, Gregory Farnum
Cc: ceph-devel, linux-kernel, Luis Henriques
Instead of using the 'copy-from' operation, switch copy_file_range to the
new 'copy-from-notrunc' operation, which allows to send the truncate_seq
and truncate_size parameters.
Signed-off-by: Luis Henriques <lhenriques@suse.com>
---
fs/ceph/file.c | 3 ++-
include/linux/ceph/osd_client.h | 1 +
include/linux/ceph/rados.h | 1 +
net/ceph/osd_client.c | 18 ++++++++++++------
4 files changed, 16 insertions(+), 7 deletions(-)
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index d277f71abe0b..4e0d70543d8b 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -2075,7 +2075,8 @@ 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, 0);
if (err) {
dout("ceph_osdc_copy_from returned %d\n", err);
if (!ret)
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index eaffbdddf89a..5a62dbd3f4c2 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -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 */
diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index 3eb0e55665b4..54bc7648fd78 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -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_FROM_NOTRUNC, __CEPH_OSD_OP(WR, DATA, 45), "copy-from-notrunc")\
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") \
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index ba45b074a362..f43ec0f5865c 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -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_FROM_NOTRUNC:
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_FROM_NOTRUNC:
*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_FROM_NOTRUNC:
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_FROM_NOTRUNC:
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_FROM_NOTRUNC,
+ 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;
^ permalink raw reply related [flat|nested] 6+ messages in thread