ceph: send client provided metric flags in client metadata

Send metric flags to the MDS, indicating what metrics the client
supports. Currently that consists of cap statistics, and read, write and
metadata latencies.

URL: https://tracker.ceph.com/issues/43435
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>

2 files changed, 71 insertions, 2 deletions

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index d6cd2e4f0bc8..af7221d1c610 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1194,6 +1194,48 @@ static int encode_supported_features(void **p, void *end)
 	return 0;
 }
 
+static const unsigned char metric_bits[] = CEPHFS_METRIC_SPEC_CLIENT_SUPPORTED;
+#define METRIC_BYTES(cnt) (DIV_ROUND_UP((size_t)metric_bits[cnt - 1] + 1, 64) * 8)
+static int encode_metric_spec(void **p, void *end)
+{
+	static const size_t count = ARRAY_SIZE(metric_bits);
+
+	/* header */
+	if (WARN_ON_ONCE(*p + 2 > end))
+		return -ERANGE;
+
+	ceph_encode_8(p, 1); /* version */
+	ceph_encode_8(p, 1); /* compat */
+
+	if (count > 0) {
+		size_t i;
+		size_t size = METRIC_BYTES(count);
+
+		if (WARN_ON_ONCE(*p + 4 + 4 + size > end))
+			return -ERANGE;
+
+		/* metric spec info length */
+		ceph_encode_32(p, 4 + size);
+
+		/* metric spec */
+		ceph_encode_32(p, size);
+		memset(*p, 0, size);
+		for (i = 0; i < count; i++)
+			((unsigned char *)(*p))[i / 8] |= BIT(metric_bits[i] % 8);
+		*p += size;
+	} else {
+		if (WARN_ON_ONCE(*p + 4 + 4 > end))
+			return -ERANGE;
+
+		/* metric spec info length */
+		ceph_encode_32(p, 4);
+		/* metric spec */
+		ceph_encode_32(p, 0);
+	}
+
+	return 0;
+}
+
 /*
  * session message, specialization for CEPH_SESSION_REQUEST_OPEN
  * to include additional client metadata fields.
@@ -1234,6 +1276,13 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
 		size = FEATURE_BYTES(count);
 	extra_bytes += 4 + size;
 
+	/* metric spec */
+	size = 0;
+	count = ARRAY_SIZE(metric_bits);
+	if (count > 0)
+		size = METRIC_BYTES(count);
+	extra_bytes += 2 + 4 + 4 + size;
+
 	/* Allocate the message */
 	msg = ceph_msg_new(CEPH_MSG_CLIENT_SESSION, sizeof(*h) + extra_bytes,
 			   GFP_NOFS, false);
@@ -1252,9 +1301,9 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
 	 * Serialize client metadata into waiting buffer space, using
 	 * the format that userspace expects for map<string, string>
 	 *
-	 * ClientSession messages with metadata are v3
+	 * ClientSession messages with metadata are v4
 	 */
-	msg->hdr.version = cpu_to_le16(3);
+	msg->hdr.version = cpu_to_le16(4);
 	msg->hdr.compat_version = cpu_to_le16(1);
 
 	/* The write pointer, following the session_head structure */
@@ -1283,6 +1332,13 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
 		return ERR_PTR(ret);
 	}
 
+	ret = encode_metric_spec(&p, end);
+	if (ret) {
+		pr_err("encode_metric_spec failed!\n");
+		ceph_msg_put(msg);
+		return ERR_PTR(ret);
+	}
+
 	msg->front.iov_len = p - msg->front.iov_base;
 	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
 
diff --git a/fs/ceph/metric.h b/fs/ceph/metric.h
index fe5d07d2e63a..1d0959d669d7 100644
--- a/fs/ceph/metric.h
+++ b/fs/ceph/metric.h
@@ -18,6 +18,19 @@ enum ceph_metric_type {
 	CLIENT_METRIC_TYPE_MAX = CLIENT_METRIC_TYPE_DENTRY_LEASE,
 };
 
+/*
+ * This will always have the highest metric bit value
+ * as the last element of the array.
+ */
+#define CEPHFS_METRIC_SPEC_CLIENT_SUPPORTED {	\
+	CLIENT_METRIC_TYPE_CAP_INFO,		\
+	CLIENT_METRIC_TYPE_READ_LATENCY,	\
+	CLIENT_METRIC_TYPE_WRITE_LATENCY,	\
+	CLIENT_METRIC_TYPE_METADATA_LATENCY,	\
+						\
+	CLIENT_METRIC_TYPE_MAX,			\
+}
+
 /* metric caps header */
 struct ceph_metric_cap {
 	__le32 type;     /* ceph metric type */