* [RFC PATCH 1/5] libceph: allow ceph_msg_data_advance to advance more than a page
2022-02-15 14:50 [RFC PATCH 0/5] libceph: add support for sparse reads to msgr2/crc Jeff Layton
@ 2022-02-15 14:50 ` Jeff Layton
2022-02-15 14:50 ` [RFC PATCH 2/5] libceph: add sparse read support to msgr2 crc state machine Jeff Layton
` (3 subsequent siblings)
4 siblings, 0 replies; 6+ messages in thread
From: Jeff Layton @ 2022-02-15 14:50 UTC (permalink / raw)
To: ceph-devel; +Cc: idryomov
In later patches, we're going to need to advance deeper into the data
buffer in order to set up for a sparse read. Rename the existing
routine, and add a wrapper around it that successively calls it until it
has advanced far enougb.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
net/ceph/messenger.c | 12 +++++++++++-
1 file changed, 11 insertions(+), 1 deletion(-)
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index d3bb656308b4..005dd1a5aced 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -1084,7 +1084,7 @@ struct page *ceph_msg_data_next(struct ceph_msg_data_cursor *cursor,
* Returns true if the result moves the cursor on to the next piece
* of the data item.
*/
-void ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor, size_t bytes)
+static void __ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor, size_t bytes)
{
bool new_piece;
@@ -1120,6 +1120,16 @@ void ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor, size_t bytes)
cursor->need_crc = new_piece;
}
+void ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor, size_t bytes)
+{
+ while (bytes) {
+ size_t cur = min(bytes, PAGE_SIZE);
+
+ __ceph_msg_data_advance(cursor, cur);
+ bytes -= cur;
+ }
+}
+
u32 ceph_crc32c_page(u32 crc, struct page *page, unsigned int page_offset,
unsigned int length)
{
--
2.34.1
^ permalink raw reply related [flat|nested] 6+ messages in thread* [RFC PATCH 2/5] libceph: add sparse read support to msgr2 crc state machine
2022-02-15 14:50 [RFC PATCH 0/5] libceph: add support for sparse reads to msgr2/crc Jeff Layton
2022-02-15 14:50 ` [RFC PATCH 1/5] libceph: allow ceph_msg_data_advance to advance more than a page Jeff Layton
@ 2022-02-15 14:50 ` Jeff Layton
2022-02-15 14:50 ` [RFC PATCH 3/5] libceph: add sparse read support to OSD client Jeff Layton
` (2 subsequent siblings)
4 siblings, 0 replies; 6+ messages in thread
From: Jeff Layton @ 2022-02-15 14:50 UTC (permalink / raw)
To: ceph-devel; +Cc: idryomov
Add support for a new sparse_read ceph_connection operation. The idea is
that the client code can define this operation use it to do special
handling for incoming reads.
The alloc_msg routine can look at the request and determine whether the
reply is expected to be sparse. If it is, then we'll dispatch to a
different set of state machine states that will repeatedly call
sparse_read get length and placement info for reading the extent map,
and the extents themselves.
TODO: support for revoke during a sparse read
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
include/linux/ceph/messenger.h | 19 ++++
net/ceph/messenger_v2.c | 164 ++++++++++++++++++++++++++++++---
2 files changed, 169 insertions(+), 14 deletions(-)
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index e7f2fb2fc207..498a1b7bd3c1 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -25,6 +25,22 @@ struct ceph_connection_operations {
struct ceph_connection *(*get)(struct ceph_connection *);
void (*put)(struct ceph_connection *);
+ /**
+ * sparse_read: read sparse data
+ * @con: connection we're reading from
+ * @off: offset into msgr data caller should read into
+ * @len: len of the data that msgr should read
+ * @buf: optional buffer to read into
+ *
+ * This should be called more than once, each time setting up to
+ * receive an extent into the correct portion of the buffer (and
+ * zeroing the holes between them).
+ *
+ * Returns 1 if there is more data to be read, 0 if reading is
+ * complete, or -errno if there was an error.
+ */
+ int (*sparse_read)(struct ceph_connection *con, u64 *off, u64 *len, char **buf);
+
/* handle an incoming message. */
void (*dispatch) (struct ceph_connection *con, struct ceph_msg *m);
@@ -252,6 +268,7 @@ struct ceph_msg {
struct kref kref;
bool more_to_follow;
bool needs_out_seq;
+ bool sparse_read;
int front_alloc_len;
struct ceph_msgpool *pool;
@@ -464,6 +481,8 @@ struct ceph_connection {
struct page *bounce_page;
u32 in_front_crc, in_middle_crc, in_data_crc; /* calculated crc */
+ int sparse_resid;
+
struct timespec64 last_keepalive_ack; /* keepalive2 ack stamp */
struct delayed_work work; /* send|recv work */
diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index c6e5bfc717d5..16fcac363670 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -52,14 +52,17 @@
#define FRAME_LATE_STATUS_COMPLETE 0xe
#define FRAME_LATE_STATUS_ABORTED_MASK 0xf
-#define IN_S_HANDLE_PREAMBLE 1
-#define IN_S_HANDLE_CONTROL 2
-#define IN_S_HANDLE_CONTROL_REMAINDER 3
-#define IN_S_PREPARE_READ_DATA 4
-#define IN_S_PREPARE_READ_DATA_CONT 5
-#define IN_S_PREPARE_READ_ENC_PAGE 6
-#define IN_S_HANDLE_EPILOGUE 7
-#define IN_S_FINISH_SKIP 8
+#define IN_S_HANDLE_PREAMBLE 1
+#define IN_S_HANDLE_CONTROL 2
+#define IN_S_HANDLE_CONTROL_REMAINDER 3
+#define IN_S_PREPARE_READ_DATA 4
+#define IN_S_PREPARE_READ_DATA_CONT 5
+#define IN_S_PREPARE_READ_ENC_PAGE 6
+#define IN_S_PREPARE_SPARSE_DATA 7
+#define IN_S_PREPARE_SPARSE_DATA_HDR 8
+#define IN_S_PREPARE_SPARSE_DATA_CONT 9
+#define IN_S_HANDLE_EPILOGUE 10
+#define IN_S_FINISH_SKIP 11
#define OUT_S_QUEUE_DATA 1
#define OUT_S_QUEUE_DATA_CONT 2
@@ -1753,13 +1756,13 @@ static int prepare_read_control_remainder(struct ceph_connection *con)
return 0;
}
-static int prepare_read_data(struct ceph_connection *con)
+static int prepare_read_data_extent(struct ceph_connection *con, int off, int len)
{
struct bio_vec bv;
- con->in_data_crc = -1;
- ceph_msg_data_cursor_init(&con->v2.in_cursor, con->in_msg,
- data_len(con->in_msg));
+ ceph_msg_data_cursor_init(&con->v2.in_cursor, con->in_msg, off+len);
+ if (off)
+ ceph_msg_data_advance(&con->v2.in_cursor, off);
get_bvec_at(&con->v2.in_cursor, &bv);
if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE)) {
@@ -1775,10 +1778,20 @@ static int prepare_read_data(struct ceph_connection *con)
bv.bv_offset = 0;
}
set_in_bvec(con, &bv);
- con->v2.in_state = IN_S_PREPARE_READ_DATA_CONT;
return 0;
}
+static int prepare_read_data(struct ceph_connection *con)
+{
+ int ret;
+
+ con->in_data_crc = -1;
+ ret = prepare_read_data_extent(con, 0, data_len(con->in_msg));
+ if (ret == 0)
+ con->v2.in_state = IN_S_PREPARE_READ_DATA_CONT;
+ return ret;
+}
+
static void prepare_read_data_cont(struct ceph_connection *con)
{
struct bio_vec bv;
@@ -1819,6 +1832,116 @@ static void prepare_read_data_cont(struct ceph_connection *con)
con->v2.in_state = IN_S_HANDLE_EPILOGUE;
}
+static int prepare_sparse_read_cont(struct ceph_connection *con)
+{
+ int ret;
+ struct bio_vec bv;
+ char *buf = NULL;
+ u64 off = 0, len = 0;
+
+ if (!iov_iter_is_bvec(&con->v2.in_iter))
+ return -EIO;
+
+ if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE)) {
+ con->in_data_crc = crc32c(con->in_data_crc,
+ page_address(con->bounce_page),
+ con->v2.in_bvec.bv_len);
+
+ get_bvec_at(&con->v2.in_cursor, &bv);
+ memcpy_to_page(bv.bv_page, bv.bv_offset,
+ page_address(con->bounce_page),
+ con->v2.in_bvec.bv_len);
+ } else {
+ con->in_data_crc = ceph_crc32c_page(con->in_data_crc,
+ con->v2.in_bvec.bv_page,
+ con->v2.in_bvec.bv_offset,
+ con->v2.in_bvec.bv_len);
+ }
+
+ ceph_msg_data_advance(&con->v2.in_cursor, con->v2.in_bvec.bv_len);
+ if (con->v2.in_cursor.total_resid) {
+ get_bvec_at(&con->v2.in_cursor, &bv);
+ if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE)) {
+ bv.bv_page = con->bounce_page;
+ bv.bv_offset = 0;
+ }
+ set_in_bvec(con, &bv);
+ WARN_ON(con->v2.in_state != IN_S_PREPARE_SPARSE_DATA_CONT);
+ return 0;
+ }
+
+ /* get next extent */
+ ret = con->ops->sparse_read(con, &off, &len, &buf);
+ if (ret <= 0) {
+ if (ret < 0)
+ return ret;
+
+ reset_in_kvecs(con);
+ add_in_kvec(con, con->v2.in_buf, CEPH_EPILOGUE_PLAIN_LEN);
+ con->v2.in_state = IN_S_HANDLE_EPILOGUE;
+ return 0;
+ }
+
+ return prepare_read_data_extent(con, off, len);
+}
+
+static int prepare_sparse_read_header(struct ceph_connection *con)
+{
+ int ret;
+ char *buf = NULL;
+ u64 off = 0, len = 0;
+
+ if (!iov_iter_is_kvec(&con->v2.in_iter))
+ return -EIO;
+
+ /* On first call, we have no kvec so don't compute crc */
+ if (con->v2.in_kvec_cnt) {
+ WARN_ON_ONCE(con->v2.in_kvec_cnt > 1);
+ con->in_data_crc = crc32c(con->in_data_crc,
+ con->v2.in_kvecs[0].iov_base,
+ con->v2.in_kvecs[0].iov_len);
+ }
+
+ ret = con->ops->sparse_read(con, &off, &len, &buf);
+ if (ret < 0)
+ return ret;
+ if (ret == 0) {
+ reset_in_kvecs(con);
+ add_in_kvec(con, con->v2.in_buf, CEPH_EPILOGUE_PLAIN_LEN);
+ con->v2.in_state = IN_S_HANDLE_EPILOGUE;
+ return 0;
+ }
+
+ /* No actual data? */
+ if (WARN_ON_ONCE(!ret))
+ return -EIO;
+
+ if (!buf) {
+ ret = prepare_read_data_extent(con, off, len);
+ if (!ret)
+ con->v2.in_state = IN_S_PREPARE_SPARSE_DATA_CONT;
+ return ret;
+ }
+
+ WARN_ON_ONCE(con->v2.in_state != IN_S_PREPARE_SPARSE_DATA_HDR);
+ reset_in_kvecs(con);
+ add_in_kvec(con, buf, len);
+ return 0;
+}
+
+static int prepare_sparse_read_data(struct ceph_connection *con)
+{
+ if (WARN_ON_ONCE(!con->ops->sparse_read))
+ return -EOPNOTSUPP;
+
+ if (!con_secure(con))
+ con->in_data_crc = -1;
+
+ reset_in_kvecs(con);
+ con->v2.in_state = IN_S_PREPARE_SPARSE_DATA_HDR;
+ return prepare_sparse_read_header(con);
+}
+
static int prepare_read_tail_plain(struct ceph_connection *con)
{
struct ceph_msg *msg = con->in_msg;
@@ -1839,7 +1962,10 @@ static int prepare_read_tail_plain(struct ceph_connection *con)
}
if (data_len(msg)) {
- con->v2.in_state = IN_S_PREPARE_READ_DATA;
+ if (msg->sparse_read)
+ con->v2.in_state = IN_S_PREPARE_SPARSE_DATA;
+ else
+ con->v2.in_state = IN_S_PREPARE_READ_DATA;
} else {
add_in_kvec(con, con->v2.in_buf, CEPH_EPILOGUE_PLAIN_LEN);
con->v2.in_state = IN_S_HANDLE_EPILOGUE;
@@ -2893,6 +3019,15 @@ static int populate_in_iter(struct ceph_connection *con)
prepare_read_enc_page(con);
ret = 0;
break;
+ case IN_S_PREPARE_SPARSE_DATA:
+ ret = prepare_sparse_read_data(con);
+ break;
+ case IN_S_PREPARE_SPARSE_DATA_HDR:
+ ret = prepare_sparse_read_header(con);
+ break;
+ case IN_S_PREPARE_SPARSE_DATA_CONT:
+ ret = prepare_sparse_read_cont(con);
+ break;
case IN_S_HANDLE_EPILOGUE:
ret = handle_epilogue(con);
break;
@@ -3501,6 +3636,7 @@ static void revoke_at_handle_epilogue(struct ceph_connection *con)
void ceph_con_v2_revoke_incoming(struct ceph_connection *con)
{
switch (con->v2.in_state) {
+ case IN_S_PREPARE_SPARSE_DATA: // FIXME
case IN_S_PREPARE_READ_DATA:
revoke_at_prepare_read_data(con);
break;
--
2.34.1
^ permalink raw reply related [flat|nested] 6+ messages in thread* [RFC PATCH 3/5] libceph: add sparse read support to OSD client
2022-02-15 14:50 [RFC PATCH 0/5] libceph: add support for sparse reads to msgr2/crc Jeff Layton
2022-02-15 14:50 ` [RFC PATCH 1/5] libceph: allow ceph_msg_data_advance to advance more than a page Jeff Layton
2022-02-15 14:50 ` [RFC PATCH 2/5] libceph: add sparse read support to msgr2 crc state machine Jeff Layton
@ 2022-02-15 14:50 ` Jeff Layton
2022-02-15 14:50 ` [RFC PATCH 4/5] libceph: add revoke support for sparse data Jeff Layton
2022-02-15 14:50 ` [RFC PATCH 5/5] ceph: switch to sparse reads Jeff Layton
4 siblings, 0 replies; 6+ messages in thread
From: Jeff Layton @ 2022-02-15 14:50 UTC (permalink / raw)
To: ceph-devel; +Cc: idryomov
Add a new sparse_read operation for the OSD client, driven by its own
state machine. The messenger can repeatedly call the sparse_read
operation, and it will pass back the necessary info to set up to read
the next extent of data, while zeroing in the sparse regions.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
include/linux/ceph/osd_client.h | 37 ++++++++
net/ceph/osd_client.c | 161 +++++++++++++++++++++++++++++++-
2 files changed, 193 insertions(+), 5 deletions(-)
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index 3431011f364d..9405cf3f5b45 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -29,6 +29,42 @@ typedef void (*ceph_osdc_callback_t)(struct ceph_osd_request *);
#define CEPH_HOMELESS_OSD -1
+enum ceph_sparse_read_state {
+ CEPH_SPARSE_READ_COUNT = 0,
+ CEPH_SPARSE_READ_EXTENTS,
+ CEPH_SPARSE_READ_DATA_LEN,
+ CEPH_SPARSE_READ_DATA,
+};
+
+/* A single extent in a SPARSE_READ reply */
+struct ceph_sparse_extent {
+ __le64 off;
+ __le64 len;
+} __attribute__((packed));
+
+/*
+ * A SPARSE_READ reply is a 32-bit count of extents, followed by an array of
+ * 64-bit offset/length pairs, and then all of the actual file data
+ * concatenated after it (sans holes).
+ *
+ * Unfortunately, we don't know how long the extent array is until we've
+ * started reading the data section of the reply, so for a real sparse read, we
+ * have to allocate the array after alloc_msg returns.
+ *
+ * For the common case of a single extent, we keep an embedded extent here so
+ * we can avoid the extra allocation.
+ */
+struct ceph_sparse_read {
+ enum ceph_sparse_read_state sr_state; /* state machine state */
+ u64 sr_offset; /* request obj offset */
+ u64 sr_pos; /* current pos in buffer */
+ int sr_index; /* current extent index */
+ __le32 sr_count; /* number of extents */
+ __le32 sr_datalen; /* length of actual data */
+ struct ceph_sparse_extent *sr_extent; /* extent array */
+ struct ceph_sparse_extent sr_emb_ext[1]; /* extent (for trivial cases */
+};
+
/* a given osd we're communicating with */
struct ceph_osd {
refcount_t o_ref;
@@ -46,6 +82,7 @@ struct ceph_osd {
unsigned long lru_ttl;
struct list_head o_keepalive_item;
struct mutex lock;
+ struct ceph_sparse_read o_sparse_read;
};
#define CEPH_OSD_SLAB_OPS 2
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 1c5815530e0d..602e2315728a 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -376,6 +376,7 @@ static void osd_req_op_data_release(struct ceph_osd_request *osd_req,
switch (op->op) {
case CEPH_OSD_OP_READ:
+ case CEPH_OSD_OP_SPARSE_READ:
case CEPH_OSD_OP_WRITE:
case CEPH_OSD_OP_WRITEFULL:
ceph_osd_data_release(&op->extent.osd_data);
@@ -706,6 +707,7 @@ static void get_num_data_items(struct ceph_osd_request *req,
/* reply */
case CEPH_OSD_OP_STAT:
case CEPH_OSD_OP_READ:
+ case CEPH_OSD_OP_SPARSE_READ:
case CEPH_OSD_OP_LIST_WATCHERS:
*num_reply_data_items += 1;
break;
@@ -775,7 +777,7 @@ void osd_req_op_extent_init(struct ceph_osd_request *osd_req,
BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE &&
opcode != CEPH_OSD_OP_WRITEFULL && opcode != CEPH_OSD_OP_ZERO &&
- opcode != CEPH_OSD_OP_TRUNCATE);
+ opcode != CEPH_OSD_OP_TRUNCATE && opcode != CEPH_OSD_OP_SPARSE_READ);
op->extent.offset = offset;
op->extent.length = length;
@@ -984,6 +986,7 @@ static u32 osd_req_encode_op(struct ceph_osd_op *dst,
case CEPH_OSD_OP_STAT:
break;
case CEPH_OSD_OP_READ:
+ case CEPH_OSD_OP_SPARSE_READ:
case CEPH_OSD_OP_WRITE:
case CEPH_OSD_OP_WRITEFULL:
case CEPH_OSD_OP_ZERO:
@@ -1080,7 +1083,12 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE &&
opcode != CEPH_OSD_OP_ZERO && opcode != CEPH_OSD_OP_TRUNCATE &&
- opcode != CEPH_OSD_OP_CREATE && opcode != CEPH_OSD_OP_DELETE);
+ opcode != CEPH_OSD_OP_CREATE && opcode != CEPH_OSD_OP_DELETE &&
+ opcode != CEPH_OSD_OP_SPARSE_READ);
+
+ /* can't handle more than one sparse read data item at a time yet */
+ if (WARN_ON_ONCE(opcode == CEPH_OSD_OP_SPARSE_READ && num_ops > 1))
+ return ERR_PTR(-EINVAL);
req = ceph_osdc_alloc_request(osdc, snapc, num_ops, use_mempool,
GFP_NOFS);
@@ -2037,6 +2045,7 @@ static void setup_request_data(struct ceph_osd_request *req)
&op->raw_data_in);
break;
case CEPH_OSD_OP_READ:
+ case CEPH_OSD_OP_SPARSE_READ:
ceph_osdc_msg_data_add(reply_msg,
&op->extent.osd_data);
break;
@@ -2443,6 +2452,20 @@ static void submit_request(struct ceph_osd_request *req, bool wrlocked)
__submit_request(req, wrlocked);
}
+static void ceph_init_sparse_read(struct ceph_sparse_read *sr, u64 offset)
+{
+ if (sr->sr_extent != sr->sr_emb_ext)
+ kfree(sr->sr_extent);
+ sr->sr_state = CEPH_SPARSE_READ_COUNT;
+ sr->sr_offset = offset;
+ sr->sr_pos = 0;
+ sr->sr_count = 0;
+ sr->sr_index = 0;
+ sr->sr_extent = sr->sr_emb_ext;
+ sr->sr_extent[0].off = 0;
+ sr->sr_extent[0].len = 0;
+}
+
static void finish_request(struct ceph_osd_request *req)
{
struct ceph_osd_client *osdc = req->r_osdc;
@@ -2452,8 +2475,10 @@ static void finish_request(struct ceph_osd_request *req)
req->r_end_latency = ktime_get();
- if (req->r_osd)
+ if (req->r_osd) {
+ ceph_init_sparse_read(&req->r_osd->o_sparse_read, 0);
unlink_request(req->r_osd, req);
+ }
atomic_dec(&osdc->num_requests);
/*
@@ -3655,6 +3680,7 @@ static void handle_reply(struct ceph_osd *osd, struct ceph_msg *msg)
struct MOSDOpReply m;
u64 tid = le64_to_cpu(msg->hdr.tid);
u32 data_len = 0;
+ u32 result_len = 0;
int ret;
int i;
@@ -3749,6 +3775,13 @@ static void handle_reply(struct ceph_osd *osd, struct ceph_msg *msg)
req->r_ops[i].rval = m.rval[i];
req->r_ops[i].outdata_len = m.outdata_len[i];
data_len += m.outdata_len[i];
+ if (req->r_ops[i].op == CEPH_OSD_OP_SPARSE_READ) {
+ struct ceph_sparse_read *sr = &osd->o_sparse_read;
+
+ result_len += sr->sr_pos - sr->sr_offset;
+ } else {
+ result_len += m.outdata_len[i];
+ }
}
if (data_len != le32_to_cpu(msg->hdr.data_len)) {
pr_err("sum of lens %u != %u for tid %llu\n", data_len,
@@ -3763,7 +3796,7 @@ static void handle_reply(struct ceph_osd *osd, struct ceph_msg *msg)
* one (type of) reply back.
*/
WARN_ON(!(m.flags & CEPH_OSD_FLAG_ONDISK));
- req->r_result = m.result ?: data_len;
+ req->r_result = m.result ?: result_len;
finish_request(req);
mutex_unlock(&osd->lock);
up_read(&osdc->lock);
@@ -5398,6 +5431,22 @@ static void osd_dispatch(struct ceph_connection *con, struct ceph_msg *msg)
ceph_msg_put(msg);
}
+static bool is_sparse_read(struct ceph_osd_request *req, u64 *off)
+{
+ int i;
+
+ if (!(req->r_flags & CEPH_OSD_FLAG_READ))
+ return false;
+
+ for (i = 0; i < req->r_num_ops; ++i) {
+ if (req->r_ops[i].op == CEPH_OSD_OP_SPARSE_READ) {
+ *off = req->r_ops[i].extent.offset;
+ return true;
+ }
+ }
+ return false;
+}
+
/*
* Lookup and return message for incoming reply. Don't try to do
* anything about a larger than preallocated data portion of the
@@ -5414,6 +5463,8 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
int front_len = le32_to_cpu(hdr->front_len);
int data_len = le32_to_cpu(hdr->data_len);
u64 tid = le64_to_cpu(hdr->tid);
+ u64 sroff;
+ bool sparse;
down_read(&osdc->lock);
if (!osd_registered(osd)) {
@@ -5446,7 +5497,9 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
req->r_reply = m;
}
- if (data_len > req->r_reply->data_length) {
+ sparse = is_sparse_read(req, &sroff);
+
+ if (!sparse && (data_len > req->r_reply->data_length)) {
pr_warn("%s osd%d tid %llu data %d > preallocated %zu, skipping\n",
__func__, osd->o_osd, req->r_tid, data_len,
req->r_reply->data_length);
@@ -5456,6 +5509,10 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
}
m = ceph_msg_get(req->r_reply);
+ m->sparse_read = sparse;
+ if (sparse)
+ ceph_init_sparse_read(&osd->o_sparse_read, sroff);
+
dout("get_reply tid %lld %p\n", tid, m);
out_unlock_session:
@@ -5688,9 +5745,103 @@ static int osd_check_message_signature(struct ceph_msg *msg)
return ceph_auth_check_message_signature(auth, msg);
}
+static void zero_range(struct ceph_msg *msg, u64 off, u64 len)
+{
+ struct ceph_msg_data_cursor cursor;
+
+ ceph_msg_data_cursor_init(&cursor, msg, off + len);
+
+ while (len) {
+ struct page *page;
+ size_t poff, plen;
+ bool last = false;
+
+ page = ceph_msg_data_next(&cursor, &poff, &plen, &last);
+ if (WARN_ON_ONCE(!page))
+ break;
+ if (plen > len)
+ plen = len;
+ zero_user_segment(page, poff, plen);
+ len -= plen;
+ }
+}
+
+static int osd_sparse_read(struct ceph_connection *con, u64 *poff, u64 *plen, char **pbuf)
+{
+ struct ceph_osd *o = con->private;
+ struct ceph_sparse_read *sr = &o->o_sparse_read;
+ u32 count = __le32_to_cpu(sr->sr_count);
+ u64 eoff, elen;
+
+ switch (sr->sr_state) {
+ case CEPH_SPARSE_READ_COUNT:
+ /* number of extents */
+ *plen = sizeof(sr->sr_count);
+ *pbuf = (char *)&sr->sr_count;
+ sr->sr_state = CEPH_SPARSE_READ_EXTENTS;
+ break;
+ case CEPH_SPARSE_READ_EXTENTS:
+ dout("got %u extents\n", count);
+
+ if (count > 0) {
+ if (count > 1) {
+ /* can't use the embedded extent array */
+ sr->sr_extent = kmalloc_array(count, sizeof(*sr->sr_extent),
+ GFP_NOIO);
+ if (!sr->sr_extent)
+ return -ENOMEM;
+ }
+ *plen = count * sizeof(*sr->sr_extent);
+ *pbuf = (char *)sr->sr_extent;
+ sr->sr_state = CEPH_SPARSE_READ_DATA_LEN;
+ break;
+ }
+ /* No extents? Fall through to reading data len */
+ fallthrough;
+ case CEPH_SPARSE_READ_DATA_LEN:
+ *plen = sizeof(sr->sr_datalen);
+ *pbuf = (char *)&sr->sr_datalen;
+ sr->sr_state = CEPH_SPARSE_READ_DATA;
+ break;
+ case CEPH_SPARSE_READ_DATA:
+ /* on first extent, set last offset to starting pos */
+ if (sr->sr_index == 0)
+ sr->sr_pos = sr->sr_offset;
+
+ if (sr->sr_index >= count) {
+ dout("sr_index %d count %d\n", sr->sr_index, count);
+ return 0;
+ }
+
+ eoff = le64_to_cpu(sr->sr_extent[sr->sr_index].off);
+ elen = le64_to_cpu(sr->sr_extent[sr->sr_index].len);
+
+ dout("ext %d off 0x%llx len 0x%llx\n", sr->sr_index, eoff, elen);
+
+ /* zero out anything from sr_pos to start of extent */
+ if (sr->sr_pos < eoff)
+ zero_range(con->in_msg,
+ sr->sr_pos - sr->sr_offset,
+ eoff - sr->sr_pos);
+
+ /* Pass back extent info for msgr to set up buffer */
+ *poff = eoff - sr->sr_offset;
+ *plen = elen;
+
+ /* Set position for next extent */
+ sr->sr_pos = *poff + elen;
+
+ /* Bump the array index */
+ ++sr->sr_index;
+ break;
+ }
+ return 1;
+}
+
static const struct ceph_connection_operations osd_con_ops = {
.get = osd_get_con,
.put = osd_put_con,
+ .sparse_read = osd_sparse_read,
.alloc_msg = osd_alloc_msg,
.dispatch = osd_dispatch,
.fault = osd_fault,
--
2.34.1
^ permalink raw reply related [flat|nested] 6+ messages in thread* [RFC PATCH 4/5] libceph: add revoke support for sparse data
2022-02-15 14:50 [RFC PATCH 0/5] libceph: add support for sparse reads to msgr2/crc Jeff Layton
` (2 preceding siblings ...)
2022-02-15 14:50 ` [RFC PATCH 3/5] libceph: add sparse read support to OSD client Jeff Layton
@ 2022-02-15 14:50 ` Jeff Layton
2022-02-15 14:50 ` [RFC PATCH 5/5] ceph: switch to sparse reads Jeff Layton
4 siblings, 0 replies; 6+ messages in thread
From: Jeff Layton @ 2022-02-15 14:50 UTC (permalink / raw)
To: ceph-devel; +Cc: idryomov
Since sparse read handling is so complex, add a new field for tracking
how much data we've read out of the data blob, and decrement that
whenever we marshal up a new iov_iter for a read off the socket.
On a revoke, just ensure we skip past whatever remains in the iter, plus
the remaining data_len and epilogue.
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
include/linux/ceph/messenger.h | 1 +
net/ceph/messenger_v2.c | 37 +++++++++++++++++++++++++++++++---
2 files changed, 35 insertions(+), 3 deletions(-)
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 498a1b7bd3c1..206452d8a385 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -413,6 +413,7 @@ struct ceph_connection_v2_info {
void *conn_bufs[16];
int conn_buf_cnt;
+ int data_len_remain;
struct kvec in_sign_kvecs[8];
struct kvec out_sign_kvecs[8];
diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
index 16fcac363670..45ba59ce69e6 100644
--- a/net/ceph/messenger_v2.c
+++ b/net/ceph/messenger_v2.c
@@ -1866,6 +1866,7 @@ static int prepare_sparse_read_cont(struct ceph_connection *con)
bv.bv_offset = 0;
}
set_in_bvec(con, &bv);
+ con->v2.data_len_remain -= bv.bv_len;
WARN_ON(con->v2.in_state != IN_S_PREPARE_SPARSE_DATA_CONT);
return 0;
}
@@ -1882,7 +1883,10 @@ static int prepare_sparse_read_cont(struct ceph_connection *con)
return 0;
}
- return prepare_read_data_extent(con, off, len);
+ ret = prepare_read_data_extent(con, off, len);
+ if (ret == 0)
+ con->v2.data_len_remain -= len;
+ return ret;
}
static int prepare_sparse_read_header(struct ceph_connection *con)
@@ -1918,19 +1922,24 @@ static int prepare_sparse_read_header(struct ceph_connection *con)
if (!buf) {
ret = prepare_read_data_extent(con, off, len);
- if (!ret)
+ if (!ret) {
+ con->v2.data_len_remain -= len;
con->v2.in_state = IN_S_PREPARE_SPARSE_DATA_CONT;
+ }
return ret;
}
WARN_ON_ONCE(con->v2.in_state != IN_S_PREPARE_SPARSE_DATA_HDR);
reset_in_kvecs(con);
add_in_kvec(con, buf, len);
+ con->v2.data_len_remain -= len;
return 0;
}
static int prepare_sparse_read_data(struct ceph_connection *con)
{
+ struct ceph_msg *msg = con->in_msg;
+
if (WARN_ON_ONCE(!con->ops->sparse_read))
return -EOPNOTSUPP;
@@ -1939,6 +1948,7 @@ static int prepare_sparse_read_data(struct ceph_connection *con)
reset_in_kvecs(con);
con->v2.in_state = IN_S_PREPARE_SPARSE_DATA_HDR;
+ con->v2.data_len_remain = data_len(msg);
return prepare_sparse_read_header(con);
}
@@ -3620,6 +3630,23 @@ static void revoke_at_prepare_read_enc_page(struct ceph_connection *con)
con->v2.in_state = IN_S_FINISH_SKIP;
}
+static void revoke_at_prepare_sparse_data(struct ceph_connection *con)
+{
+ int resid; /* current piece of data */
+ int remaining;
+
+ WARN_ON(con_secure(con));
+ WARN_ON(!data_len(con->in_msg));
+ WARN_ON(!iov_iter_is_bvec(&con->v2.in_iter));
+ resid = iov_iter_count(&con->v2.in_iter);
+ dout("%s con %p resid %d\n", __func__, con, resid);
+
+ remaining = CEPH_EPILOGUE_PLAIN_LEN + con->v2.data_len_remain;
+ con->v2.in_iter.count -= resid;
+ set_in_skip(con, resid + remaining);
+ con->v2.in_state = IN_S_FINISH_SKIP;
+}
+
static void revoke_at_handle_epilogue(struct ceph_connection *con)
{
int resid;
@@ -3636,7 +3663,7 @@ static void revoke_at_handle_epilogue(struct ceph_connection *con)
void ceph_con_v2_revoke_incoming(struct ceph_connection *con)
{
switch (con->v2.in_state) {
- case IN_S_PREPARE_SPARSE_DATA: // FIXME
+ case IN_S_PREPARE_SPARSE_DATA:
case IN_S_PREPARE_READ_DATA:
revoke_at_prepare_read_data(con);
break;
@@ -3646,6 +3673,10 @@ void ceph_con_v2_revoke_incoming(struct ceph_connection *con)
case IN_S_PREPARE_READ_ENC_PAGE:
revoke_at_prepare_read_enc_page(con);
break;
+ case IN_S_PREPARE_SPARSE_DATA_HDR:
+ case IN_S_PREPARE_SPARSE_DATA_CONT:
+ revoke_at_prepare_sparse_data(con);
+ break;
case IN_S_HANDLE_EPILOGUE:
revoke_at_handle_epilogue(con);
break;
--
2.34.1
^ permalink raw reply related [flat|nested] 6+ messages in thread* [RFC PATCH 5/5] ceph: switch to sparse reads
2022-02-15 14:50 [RFC PATCH 0/5] libceph: add support for sparse reads to msgr2/crc Jeff Layton
` (3 preceding siblings ...)
2022-02-15 14:50 ` [RFC PATCH 4/5] libceph: add revoke support for sparse data Jeff Layton
@ 2022-02-15 14:50 ` Jeff Layton
4 siblings, 0 replies; 6+ messages in thread
From: Jeff Layton @ 2022-02-15 14:50 UTC (permalink / raw)
To: ceph-devel; +Cc: idryomov
Switch the cephfs client to use sparse reads instead of normal ones.
XXX: doesn't currently work since OSD doesn't support truncate_seq
on a sparse read. See: https://tracker.ceph.com/issues/54280
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
fs/ceph/addr.c | 2 +-
fs/ceph/file.c | 4 ++--
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 46e0881ae8b2..565cc2197dd1 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -317,7 +317,7 @@ static void ceph_netfs_issue_op(struct netfs_read_subrequest *subreq)
return;
req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino, subreq->start, &len,
- 0, 1, CEPH_OSD_OP_READ,
+ 0, 1, CEPH_OSD_OP_SPARSE_READ,
CEPH_OSD_FLAG_READ | fsc->client->osdc.client->options->read_from_replica,
NULL, ci->i_truncate_seq, ci->i_truncate_size, false);
if (IS_ERR(req)) {
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index feb75eb1cd82..d1956a20c627 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -934,7 +934,7 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
req = ceph_osdc_new_request(osdc, &ci->i_layout,
ci->i_vino, off, &len, 0, 1,
- CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
+ CEPH_OSD_OP_SPARSE_READ, CEPH_OSD_FLAG_READ,
NULL, ci->i_truncate_seq,
ci->i_truncate_size, false);
if (IS_ERR(req)) {
@@ -1291,7 +1291,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
vino, pos, &size, 0,
1,
write ? CEPH_OSD_OP_WRITE :
- CEPH_OSD_OP_READ,
+ CEPH_OSD_OP_SPARSE_READ,
flags, snapc,
ci->i_truncate_seq,
ci->i_truncate_size,
--
2.34.1
^ permalink raw reply related [flat|nested] 6+ messages in thread