[PATCH v4 0/5] ceph: periodically send perf metrics to ceph

[PATCH v4 0/5] ceph: periodically send perf metrics to ceph

[xiubli]

From: Xiubo Li <xiubli@redhat.com>

This series is based the previous patches of the metrics in kceph[1]
and mds daemons record and forward client side metrics to manager[2][3].

This will send the caps/read/write/metadata metrics to any available
MDS only once per second, which will be the same as the userland client.
We could disable it via the enable_send_metrics module parameter.

And will also send the metric flags to MDS, currently it supports the
cap, read latency, write latency and metadata latency.

Also have pushed this series to github [4].

[1] https://patchwork.kernel.org/project/ceph-devel/list/?series=238907 [Merged]
[2] https://github.com/ceph/ceph/pull/26004 [Merged]
[3] https://github.com/ceph/ceph/pull/35608 [Merged]
[4] https://github.com/lxbsz/ceph-client/commits/perf_metric4

Changes in V4:
- WARN_ON --> WARN_ON_ONCE
- do not send metrics when no mds suppor the metric collection.
- add global total_caps in mdsc->metric
- add the delayed work for each session and choose one to send the metrics to get rid of the mdsc->mutex lock

Changed in V3:
- fold "check the METRIC_COLLECT feature before sending metrics" into previous one
- use `enable_send_metrics` on/off switch instead

Changed in V2:
- split the patches into small ones as possible.
- check the METRIC_COLLECT feature before sending metrics
- switch to WARN_ON and bubble up errnos to the callers



Xiubo Li (5):
  ceph: add check_session_state helper and make it global
  ceph: add global total_caps to count the mdsc's caps number
  ceph: periodically send perf metrics to ceph
  ceph: switch to WARN_ON_ONCE and bubble up errnos to the callers
  ceph: send client provided metric flags in client metadata

 fs/ceph/caps.c               |   2 +
 fs/ceph/mds_client.c         | 158 +++++++++++++++++++++++++++++++++++--------
 fs/ceph/mds_client.h         |   8 ++-
 fs/ceph/metric.c             | 156 ++++++++++++++++++++++++++++++++++++++++++
 fs/ceph/metric.h             |  96 ++++++++++++++++++++++++++
 fs/ceph/super.c              |  42 ++++++++++++
 fs/ceph/super.h              |   2 +
 include/linux/ceph/ceph_fs.h |   1 +
 8 files changed, 434 insertions(+), 31 deletions(-)

-- 
1.8.3.1

[PATCH v4 1/5] ceph: add check_session_state helper and make it global

[xiubli]

From: Xiubo Li <xiubli@redhat.com>

This will be used by followed sending metrics patches.

URL: https://tracker.ceph.com/issues/43215
Signed-off-by: Xiubo Li <xiubli@redhat.com>
---
 fs/ceph/mds_client.c | 43 ++++++++++++++++++++++++++-----------------
 fs/ceph/mds_client.h |  4 ++++
 2 files changed, 30 insertions(+), 17 deletions(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index a504971..608fb5c 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -4263,6 +4263,30 @@ static void maybe_recover_session(struct ceph_mds_client *mdsc)
 	ceph_force_reconnect(fsc->sb);
 }
 
+bool check_session_state(struct ceph_mds_client *mdsc,
+			 struct ceph_mds_session *s)
+{
+	if (s->s_state == CEPH_MDS_SESSION_CLOSING) {
+		dout("resending session close request for mds%d\n",
+				s->s_mds);
+		request_close_session(mdsc, s);
+		return false;
+	}
+	if (s->s_ttl && time_after(jiffies, s->s_ttl)) {
+		if (s->s_state == CEPH_MDS_SESSION_OPEN) {
+			s->s_state = CEPH_MDS_SESSION_HUNG;
+			pr_info("mds%d hung\n", s->s_mds);
+		}
+	}
+	if (s->s_state == CEPH_MDS_SESSION_NEW ||
+	    s->s_state == CEPH_MDS_SESSION_RESTARTING ||
+	    s->s_state == CEPH_MDS_SESSION_REJECTED)
+		/* this mds is failed or recovering, just wait */
+		return false;
+
+	return true;
+}
+
 /*
  * delayed work -- periodically trim expired leases, renew caps with mds
  */
@@ -4294,23 +4318,8 @@ static void delayed_work(struct work_struct *work)
 		struct ceph_mds_session *s = __ceph_lookup_mds_session(mdsc, i);
 		if (!s)
 			continue;
-		if (s->s_state == CEPH_MDS_SESSION_CLOSING) {
-			dout("resending session close request for mds%d\n",
-			     s->s_mds);
-			request_close_session(mdsc, s);
-			ceph_put_mds_session(s);
-			continue;
-		}
-		if (s->s_ttl && time_after(jiffies, s->s_ttl)) {
-			if (s->s_state == CEPH_MDS_SESSION_OPEN) {
-				s->s_state = CEPH_MDS_SESSION_HUNG;
-				pr_info("mds%d hung\n", s->s_mds);
-			}
-		}
-		if (s->s_state == CEPH_MDS_SESSION_NEW ||
-		    s->s_state == CEPH_MDS_SESSION_RESTARTING ||
-		    s->s_state == CEPH_MDS_SESSION_REJECTED) {
-			/* this mds is failed or recovering, just wait */
+
+		if (!check_session_state(mdsc, s)) {
 			ceph_put_mds_session(s);
 			continue;
 		}
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 5e0c407..bcb3892 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -18,6 +18,7 @@
 #include <linux/ceph/auth.h>
 
 #include "metric.h"
+#include "super.h"
 
 /* The first 8 bits are reserved for old ceph releases */
 enum ceph_feature_type {
@@ -476,6 +477,9 @@ struct ceph_mds_client {
 
 extern const char *ceph_mds_op_name(int op);
 
+extern bool check_session_state(struct ceph_mds_client *mdsc,
+				struct ceph_mds_session *s);
+
 extern struct ceph_mds_session *
 __ceph_lookup_mds_session(struct ceph_mds_client *, int mds);
 
-- 
1.8.3.1

[PATCH v4 2/5] ceph: add global total_caps to count the mdsc's total caps number

[xiubli]

From: Xiubo Li <xiubli@redhat.com>

This will help to reduce using the global mdsc->metux lock in many
places.

URL: https://tracker.ceph.com/issues/43215
Signed-off-by: Xiubo Li <xiubli@redhat.com>
---
 fs/ceph/caps.c       |  2 ++
 fs/ceph/debugfs.c    | 14 ++------------
 fs/ceph/mds_client.c |  1 +
 fs/ceph/metric.c     |  1 +
 fs/ceph/metric.h     |  1 +
 5 files changed, 7 insertions(+), 12 deletions(-)

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 972c13a..5f48940 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -668,6 +668,7 @@ void ceph_add_cap(struct inode *inode,
 		spin_lock(&session->s_cap_lock);
 		list_add_tail(&cap->session_caps, &session->s_caps);
 		session->s_nr_caps++;
+		atomic64_inc(&mdsc->metric.total_caps);
 		spin_unlock(&session->s_cap_lock);
 	} else {
 		spin_lock(&session->s_cap_lock);
@@ -1161,6 +1162,7 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
 	} else {
 		list_del_init(&cap->session_caps);
 		session->s_nr_caps--;
+		atomic64_dec(&mdsc->metric.total_caps);
 		cap->session = NULL;
 		removed = 1;
 	}
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 070ed84..3030f55 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -145,7 +145,7 @@ static int metric_show(struct seq_file *s, void *p)
 	struct ceph_fs_client *fsc = s->private;
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	struct ceph_client_metric *m = &mdsc->metric;
-	int i, nr_caps = 0;
+	int nr_caps = 0;
 	s64 total, sum, avg, min, max, sq;
 
 	seq_printf(s, "item          total       avg_lat(us)     min_lat(us)     max_lat(us)     stdev(us)\n");
@@ -190,17 +190,7 @@ static int metric_show(struct seq_file *s, void *p)
 		   percpu_counter_sum(&m->d_lease_mis),
 		   percpu_counter_sum(&m->d_lease_hit));
 
-	mutex_lock(&mdsc->mutex);
-	for (i = 0; i < mdsc->max_sessions; i++) {
-		struct ceph_mds_session *s;
-
-		s = __ceph_lookup_mds_session(mdsc, i);
-		if (!s)
-			continue;
-		nr_caps += s->s_nr_caps;
-		ceph_put_mds_session(s);
-	}
-	mutex_unlock(&mdsc->mutex);
+	nr_caps = atomic64_read(&m->total_caps);
 	seq_printf(s, "%-14s%-16d%-16lld%lld\n", "caps", nr_caps,
 		   percpu_counter_sum(&m->i_caps_mis),
 		   percpu_counter_sum(&m->i_caps_hit));
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 608fb5c..2eeab10 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1485,6 +1485,7 @@ int ceph_iterate_session_caps(struct ceph_mds_session *session,
 			cap->session = NULL;
 			list_del_init(&cap->session_caps);
 			session->s_nr_caps--;
+			atomic64_dec(&session->s_mdsc->metric.total_caps);
 			if (cap->queue_release)
 				__ceph_queue_cap_release(session, cap);
 			else
diff --git a/fs/ceph/metric.c b/fs/ceph/metric.c
index 9217f35..269eacb 100644
--- a/fs/ceph/metric.c
+++ b/fs/ceph/metric.c
@@ -22,6 +22,7 @@ int ceph_metric_init(struct ceph_client_metric *m)
 	if (ret)
 		goto err_d_lease_mis;
 
+	atomic64_set(&m->total_caps, 0);
 	ret = percpu_counter_init(&m->i_caps_hit, 0, GFP_KERNEL);
 	if (ret)
 		goto err_i_caps_hit;
diff --git a/fs/ceph/metric.h b/fs/ceph/metric.h
index ccd8128..23a3373 100644
--- a/fs/ceph/metric.h
+++ b/fs/ceph/metric.h
@@ -12,6 +12,7 @@ struct ceph_client_metric {
 	struct percpu_counter d_lease_hit;
 	struct percpu_counter d_lease_mis;
 
+	atomic64_t            total_caps;
 	struct percpu_counter i_caps_hit;
 	struct percpu_counter i_caps_mis;
 
-- 
1.8.3.1

[PATCH v4 3/5] ceph: periodically send perf metrics to ceph

[xiubli]

From: Xiubo Li <xiubli@redhat.com>

This will send the caps/read/write/metadata metrics to any available
MDS only once per second as default, which will be the same as the
userland client. It will skip the MDS sessions which don't support
the metric collection, or the MDSs will close the socket connections
directly when it get an unknown type message.

We can disable the metric sending via the enable_send_metric module
parameter.

URL: https://tracker.ceph.com/issues/43215
Signed-off-by: Xiubo Li <xiubli@redhat.com>
---
 fs/ceph/mds_client.c         |  29 +++++++++
 fs/ceph/mds_client.h         |   6 +-
 fs/ceph/metric.c             | 142 +++++++++++++++++++++++++++++++++++++++++++
 fs/ceph/metric.h             |  75 +++++++++++++++++++++++
 fs/ceph/super.c              |  44 ++++++++++++++
 fs/ceph/super.h              |   2 +
 include/linux/ceph/ceph_fs.h |   1 +
 7 files changed, 298 insertions(+), 1 deletion(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 2eeab10..18f43a4 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -754,6 +754,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 	s->s_cap_iterator = NULL;
 	INIT_LIST_HEAD(&s->s_cap_releases);
 	INIT_WORK(&s->s_cap_release_work, ceph_cap_release_work);
+	INIT_DELAYED_WORK(&s->metric_delayed_work, ceph_metric_delayed_work);
 
 	INIT_LIST_HEAD(&s->s_cap_dirty);
 	INIT_LIST_HEAD(&s->s_cap_flushing);
@@ -1801,6 +1802,20 @@ static int request_close_session(struct ceph_mds_client *mdsc,
 	return 1;
 }
 
+static void try_reset_metric_work(struct ceph_mds_client *mdsc,
+				  struct ceph_mds_session *session)
+{
+	mutex_lock(&mdsc->mutex);
+	if (mdsc->metric.mds == session->s_mds) {
+		mdsc->metric.mds = -1;
+		cancel_delayed_work_sync(&session->metric_delayed_work);
+
+		/* Choose a new session to run the metric work */
+		ceph_choose_new_metric_session(mdsc);
+	}
+	mutex_unlock(&mdsc->mutex);
+}
+
 /*
  * Called with s_mutex held.
  */
@@ -1810,6 +1825,9 @@ static int __close_session(struct ceph_mds_client *mdsc,
 	if (session->s_state >= CEPH_MDS_SESSION_CLOSING)
 		return 0;
 	session->s_state = CEPH_MDS_SESSION_CLOSING;
+
+	try_reset_metric_work(mdsc, session);
+
 	return request_close_session(mdsc, session);
 }
 
@@ -3312,6 +3330,15 @@ static void handle_session(struct ceph_mds_session *session,
 		session->s_features = features;
 		renewed_caps(mdsc, session, 0);
 		wake = 1;
+
+		mutex_lock(&mdsc->mutex);
+		if (mdsc->metric.mds < 0 &&
+		    test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &session->s_features)) {
+			ceph_metric_schedule_delayed(session);
+			mdsc->metric.mds = session->s_mds;
+		}
+		mutex_unlock(&mdsc->mutex);
+
 		if (mdsc->stopping)
 			__close_session(mdsc, session);
 		break;
@@ -3806,6 +3833,8 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
 
 	xa_destroy(&session->s_delegated_inos);
 
+	try_reset_metric_work(mdsc, session);
+
 	mutex_lock(&session->s_mutex);
 	session->s_state = CEPH_MDS_SESSION_RECONNECTING;
 	session->s_seq = 0;
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index bcb3892..daa905f 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -28,8 +28,9 @@ enum ceph_feature_type {
 	CEPHFS_FEATURE_LAZY_CAP_WANTED,
 	CEPHFS_FEATURE_MULTI_RECONNECT,
 	CEPHFS_FEATURE_DELEG_INO,
+	CEPHFS_FEATURE_METRIC_COLLECT,
 
-	CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_DELEG_INO,
+	CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_METRIC_COLLECT,
 };
 
 /*
@@ -43,6 +44,7 @@ enum ceph_feature_type {
 	CEPHFS_FEATURE_LAZY_CAP_WANTED,		\
 	CEPHFS_FEATURE_MULTI_RECONNECT,		\
 	CEPHFS_FEATURE_DELEG_INO,		\
+	CEPHFS_FEATURE_METRIC_COLLECT,		\
 						\
 	CEPHFS_FEATURE_MAX,			\
 }
@@ -212,6 +214,8 @@ struct ceph_mds_session {
 	struct list_head  s_waiting;  /* waiting requests */
 	struct list_head  s_unsafe;   /* unsafe requests */
 	struct xarray	  s_delegated_inos;
+
+	struct delayed_work metric_delayed_work;  /* delayed work */
 };
 
 /*
diff --git a/fs/ceph/metric.c b/fs/ceph/metric.c
index 269eacb..47eba86 100644
--- a/fs/ceph/metric.c
+++ b/fs/ceph/metric.c
@@ -1,10 +1,150 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/types.h>
 #include <linux/percpu_counter.h>
 #include <linux/math64.h>
 
 #include "metric.h"
+#include "mds_client.h"
+
+void ceph_metric_delayed_work(struct work_struct *work)
+{
+	struct ceph_mds_session *s =
+		container_of(work, struct ceph_mds_session, metric_delayed_work.work);
+	struct ceph_mds_client *mdsc = s->s_mdsc;
+	u64 nr_caps = atomic64_read(&mdsc->metric.total_caps);
+	struct ceph_metric_head *head;
+	struct ceph_metric_cap *cap;
+	struct ceph_metric_read_latency *read;
+	struct ceph_metric_write_latency *write;
+	struct ceph_metric_metadata_latency *meta;
+	struct ceph_client_metric *m = &mdsc->metric;
+	struct ceph_msg *msg;
+	struct timespec64 ts;
+	s64 sum, total;
+	s32 items = 0;
+	s32 len;
+
+	len = sizeof(*head) + sizeof(*cap) + sizeof(*read) + sizeof(*write)
+	      + sizeof(*meta);
+
+	msg = ceph_msg_new(CEPH_MSG_CLIENT_METRICS, len, GFP_NOFS, true);
+	if (!msg) {
+		pr_err("send metrics to mds%d, failed to allocate message\n",
+		       s->s_mds);
+		return;
+	}
+
+	head = msg->front.iov_base;
+
+	/* encode the cap metric */
+	cap = (struct ceph_metric_cap *)(head + 1);
+	cap->type = cpu_to_le32(CLIENT_METRIC_TYPE_CAP_INFO);
+	cap->ver = 1;
+	cap->compat = 1;
+	cap->data_len = cpu_to_le32(sizeof(*cap) - 10);
+	cap->hit = cpu_to_le64(percpu_counter_sum(&mdsc->metric.i_caps_hit));
+	cap->mis = cpu_to_le64(percpu_counter_sum(&mdsc->metric.i_caps_mis));
+	cap->total = cpu_to_le64(nr_caps);
+	items++;
+
+	/* encode the read latency metric */
+	read = (struct ceph_metric_read_latency *)(cap + 1);
+	read->type = cpu_to_le32(CLIENT_METRIC_TYPE_READ_LATENCY);
+	read->ver = 1;
+	read->compat = 1;
+	read->data_len = cpu_to_le32(sizeof(*read) - 10);
+	total = m->total_reads;
+	sum = m->read_latency_sum;
+	jiffies_to_timespec64(sum, &ts);
+	read->sec = cpu_to_le32(ts.tv_sec);
+	read->nsec = cpu_to_le32(ts.tv_nsec);
+	items++;
+
+	/* encode the write latency metric */
+	write = (struct ceph_metric_write_latency *)(read + 1);
+	write->type = cpu_to_le32(CLIENT_METRIC_TYPE_WRITE_LATENCY);
+	write->ver = 1;
+	write->compat = 1;
+	write->data_len = cpu_to_le32(sizeof(*write) - 10);
+	total = m->total_writes;
+	sum = m->write_latency_sum;
+	jiffies_to_timespec64(sum, &ts);
+	write->sec = cpu_to_le32(ts.tv_sec);
+	write->nsec = cpu_to_le32(ts.tv_nsec);
+	items++;
+
+	/* encode the metadata latency metric */
+	meta = (struct ceph_metric_metadata_latency *)(write + 1);
+	meta->type = cpu_to_le32(CLIENT_METRIC_TYPE_METADATA_LATENCY);
+	meta->ver = 1;
+	meta->compat = 1;
+	meta->data_len = cpu_to_le32(sizeof(*meta) - 10);
+	total = m->total_metadatas;
+	sum = m->metadata_latency_sum;
+	jiffies_to_timespec64(sum, &ts);
+	meta->sec = cpu_to_le32(ts.tv_sec);
+	meta->nsec = cpu_to_le32(ts.tv_nsec);
+	items++;
+
+	put_unaligned_le32(items, &head->num);
+	msg->front.iov_len = cpu_to_le32(len);
+	msg->hdr.version = cpu_to_le16(1);
+	msg->hdr.compat_version = cpu_to_le16(1);
+	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
+	dout("client%llu send metrics to mds%d\n",
+	     ceph_client_gid(mdsc->fsc->client), s->s_mds);
+	ceph_con_send(&s->s_con, msg);
+
+	ceph_metric_schedule_delayed(s);
+}
+
+/*
+ * called under mdsc->mutex
+ */
+void ceph_choose_new_metric_session(struct ceph_mds_client *mdsc)
+{
+	struct ceph_mds_session *s;
+	int i;
+
+	if (mdsc->stopping)
+		return;
+
+	for (i = 0; i < mdsc->max_sessions; i++) {
+		s = __ceph_lookup_mds_session(mdsc, i);
+		if (!s)
+			continue;
+
+		if (!check_session_state(mdsc, s)) {
+			ceph_put_mds_session(s);
+			continue;
+		}
+
+		/*
+		 * Skip it if MDS doesn't support the metric collection,
+		 * or the MDS will close the session's socket connection
+		 * directly when it get this message.
+		 */
+		if (test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &s->s_features)) {
+			mdsc->metric.mds = i;
+			ceph_metric_schedule_delayed(s);
+			ceph_put_mds_session(s);
+			return;
+		}
+
+		ceph_put_mds_session(s);
+	}
+}
+
+void ceph_metric_schedule_delayed(struct ceph_mds_session *s)
+{
+	if (!enable_send_metrics)
+		return;
+
+	/* per second */
+	schedule_delayed_work(&s->metric_delayed_work, round_jiffies_relative(HZ));
+}
 
 int ceph_metric_init(struct ceph_client_metric *m)
 {
@@ -52,6 +192,8 @@ int ceph_metric_init(struct ceph_client_metric *m)
 	m->total_metadatas = 0;
 	m->metadata_latency_sum = 0;
 
+	m->mds = -1;
+
 	return 0;
 
 err_i_caps_mis:
diff --git a/fs/ceph/metric.h b/fs/ceph/metric.h
index 23a3373..1a7e3fb 100644
--- a/fs/ceph/metric.h
+++ b/fs/ceph/metric.h
@@ -6,6 +6,74 @@
 #include <linux/percpu_counter.h>
 #include <linux/ktime.h>
 
+struct ceph_mds_client;
+struct ceph_mds_session;
+
+extern bool enable_send_metrics;
+
+enum ceph_metric_type {
+	CLIENT_METRIC_TYPE_CAP_INFO,
+	CLIENT_METRIC_TYPE_READ_LATENCY,
+	CLIENT_METRIC_TYPE_WRITE_LATENCY,
+	CLIENT_METRIC_TYPE_METADATA_LATENCY,
+	CLIENT_METRIC_TYPE_DENTRY_LEASE,
+
+	CLIENT_METRIC_TYPE_MAX = CLIENT_METRIC_TYPE_DENTRY_LEASE,
+};
+
+/* metric caps header */
+struct ceph_metric_cap {
+	__le32 type;     /* ceph metric type */
+
+	__u8  ver;
+	__u8  compat;
+
+	__le32 data_len; /* length of sizeof(hit + mis + total) */
+	__le64 hit;
+	__le64 mis;
+	__le64 total;
+} __packed;
+
+/* metric read latency header */
+struct ceph_metric_read_latency {
+	__le32 type;     /* ceph metric type */
+
+	__u8  ver;
+	__u8  compat;
+
+	__le32 data_len; /* length of sizeof(sec + nsec) */
+	__le32 sec;
+	__le32 nsec;
+} __packed;
+
+/* metric write latency header */
+struct ceph_metric_write_latency {
+	__le32 type;     /* ceph metric type */
+
+	__u8  ver;
+	__u8  compat;
+
+	__le32 data_len; /* length of sizeof(sec + nsec) */
+	__le32 sec;
+	__le32 nsec;
+} __packed;
+
+/* metric metadata latency header */
+struct ceph_metric_metadata_latency {
+	__le32 type;     /* ceph metric type */
+
+	__u8  ver;
+	__u8  compat;
+
+	__le32 data_len; /* length of sizeof(sec + nsec) */
+	__le32 sec;
+	__le32 nsec;
+} __packed;
+
+struct ceph_metric_head {
+	__le32 num;	/* the number of metrics that will be sent */
+} __packed;
+
 /* This is the global metrics */
 struct ceph_client_metric {
 	atomic64_t            total_dentries;
@@ -36,8 +104,15 @@ struct ceph_client_metric {
 	ktime_t metadata_latency_sq_sum;
 	ktime_t metadata_latency_min;
 	ktime_t metadata_latency_max;
+
+	/* The MDS session running the metric work */
+	int mds;
 };
 
+extern void ceph_metric_delayed_work(struct work_struct *work);
+extern void ceph_metric_schedule_delayed(struct ceph_mds_session *s);
+extern void ceph_choose_new_metric_session(struct ceph_mds_client *mdsc);
+
 extern int ceph_metric_init(struct ceph_client_metric *m);
 extern void ceph_metric_destroy(struct ceph_client_metric *m);
 
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index c9784eb1..510ccb1 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -27,6 +27,9 @@
 #include <linux/ceph/auth.h>
 #include <linux/ceph/debugfs.h>
 
+static DEFINE_MUTEX(ceph_fsc_lock);
+static LIST_HEAD(ceph_fsc_list);
+
 /*
  * Ceph superblock operations
  *
@@ -691,6 +694,10 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 	if (!fsc->wb_pagevec_pool)
 		goto fail_cap_wq;
 
+	mutex_lock(&ceph_fsc_lock);
+	list_add_tail(&fsc->list, &ceph_fsc_list);
+	mutex_unlock(&ceph_fsc_lock);
+
 	return fsc;
 
 fail_cap_wq:
@@ -717,6 +724,10 @@ static void destroy_fs_client(struct ceph_fs_client *fsc)
 {
 	dout("destroy_fs_client %p\n", fsc);
 
+	mutex_lock(&ceph_fsc_lock);
+	list_del(&fsc->list);
+	mutex_unlock(&ceph_fsc_lock);
+
 	ceph_mdsc_destroy(fsc);
 	destroy_workqueue(fsc->inode_wq);
 	destroy_workqueue(fsc->cap_wq);
@@ -1282,6 +1293,39 @@ static void __exit exit_ceph(void)
 	destroy_caches();
 }
 
+static int param_set_metrics(const char *val, const struct kernel_param *kp)
+{
+	struct ceph_fs_client *fsc;
+	int ret;
+
+	ret = param_set_bool(val, kp);
+	if (ret) {
+		pr_err("Failed to parse sending metrics switch value '%s'\n",
+		       val);
+		return ret;
+	} else if (enable_send_metrics) {
+		// wake up all the mds clients
+		mutex_lock(&ceph_fsc_lock);
+		list_for_each_entry(fsc, &ceph_fsc_list, list) {
+			mutex_lock(&fsc->mdsc->mutex);
+			ceph_choose_new_metric_session(fsc->mdsc);
+			mutex_unlock(&fsc->mdsc->mutex);
+		}
+		mutex_unlock(&ceph_fsc_lock);
+	}
+
+	return 0;
+}
+
+static const struct kernel_param_ops param_ops_metrics = {
+	.set = param_set_metrics,
+	.get = param_get_bool,
+};
+
+bool enable_send_metrics = true;
+module_param_cb(enable_send_metrics, &param_ops_metrics, &enable_send_metrics, 0644);
+MODULE_PARM_DESC(enable_send_metrics, "Enable sending perf metrics to ceph cluster (default: on)");
+
 module_init(init_ceph);
 module_exit(exit_ceph);
 
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 5a6cdd3..05edc9a 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -101,6 +101,8 @@ struct ceph_mount_options {
 struct ceph_fs_client {
 	struct super_block *sb;
 
+	struct list_head list;
+
 	struct ceph_mount_options *mount_options;
 	struct ceph_client *client;
 
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index ebf5ba6..455e9b9 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -130,6 +130,7 @@ struct ceph_dir_layout {
 #define CEPH_MSG_CLIENT_REQUEST         24
 #define CEPH_MSG_CLIENT_REQUEST_FORWARD 25
 #define CEPH_MSG_CLIENT_REPLY           26
+#define CEPH_MSG_CLIENT_METRICS         29
 #define CEPH_MSG_CLIENT_CAPS            0x310
 #define CEPH_MSG_CLIENT_LEASE           0x311
 #define CEPH_MSG_CLIENT_SNAP            0x312
-- 
1.8.3.1

[PATCH v4 4/5] ceph: switch to WARN_ON_ONCE and bubble up errnos to the callers

[xiubli]

From: Xiubo Li <xiubli@redhat.com>

Signed-off-by: Xiubo Li <xiubli@redhat.com>
---
 fs/ceph/mds_client.c | 46 +++++++++++++++++++++++++++++++++++-----------
 1 file changed, 35 insertions(+), 11 deletions(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 18f43a4..eda788b 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1169,7 +1169,7 @@ static struct ceph_msg *create_session_msg(u32 op, u64 seq)
 
 static const unsigned char feature_bits[] = CEPHFS_FEATURES_CLIENT_SUPPORTED;
 #define FEATURE_BYTES(c) (DIV_ROUND_UP((size_t)feature_bits[c - 1] + 1, 64) * 8)
-static void encode_supported_features(void **p, void *end)
+static int encode_supported_features(void **p, void *end)
 {
 	static const size_t count = ARRAY_SIZE(feature_bits);
 
@@ -1177,16 +1177,22 @@ static void encode_supported_features(void **p, void *end)
 		size_t i;
 		size_t size = FEATURE_BYTES(count);
 
-		BUG_ON(*p + 4 + size > end);
+		if (WARN_ON_ONCE(*p + 4 + size > end))
+			return -ERANGE;
+
 		ceph_encode_32(p, size);
 		memset(*p, 0, size);
 		for (i = 0; i < count; i++)
 			((unsigned char*)(*p))[i / 8] |= BIT(feature_bits[i] % 8);
 		*p += size;
 	} else {
-		BUG_ON(*p + 4 > end);
+		if (WARN_ON_ONCE(*p + 4 > end))
+			return -ERANGE;
+
 		ceph_encode_32(p, 0);
 	}
+
+	return 0;
 }
 
 /*
@@ -1204,6 +1210,7 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
 	struct ceph_mount_options *fsopt = mdsc->fsc->mount_options;
 	size_t size, count;
 	void *p, *end;
+	int ret;
 
 	const char* metadata[][2] = {
 		{"hostname", mdsc->nodename},
@@ -1233,7 +1240,7 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
 			   GFP_NOFS, false);
 	if (!msg) {
 		pr_err("create_session_msg ENOMEM creating msg\n");
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 	p = msg->front.iov_base;
 	end = p + msg->front.iov_len;
@@ -1270,7 +1277,13 @@ static struct ceph_msg *create_session_open_msg(struct ceph_mds_client *mdsc, u6
 		p += val_len;
 	}
 
-	encode_supported_features(&p, end);
+	ret = encode_supported_features(&p, end);
+	if (ret) {
+		pr_err("encode_supported_features 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);
 
@@ -1298,8 +1311,8 @@ static int __open_session(struct ceph_mds_client *mdsc,
 
 	/* send connect message */
 	msg = create_session_open_msg(mdsc, session->s_seq);
-	if (!msg)
-		return -ENOMEM;
+	if (IS_ERR(msg))
+		return PTR_ERR(msg);
 	ceph_con_send(&session->s_con, msg);
 	return 0;
 }
@@ -1313,6 +1326,7 @@ static int __open_session(struct ceph_mds_client *mdsc,
 __open_export_target_session(struct ceph_mds_client *mdsc, int target)
 {
 	struct ceph_mds_session *session;
+	int ret;
 
 	session = __ceph_lookup_mds_session(mdsc, target);
 	if (!session) {
@@ -1321,8 +1335,11 @@ static int __open_session(struct ceph_mds_client *mdsc,
 			return session;
 	}
 	if (session->s_state == CEPH_MDS_SESSION_NEW ||
-	    session->s_state == CEPH_MDS_SESSION_CLOSING)
-		__open_session(mdsc, session);
+	    session->s_state == CEPH_MDS_SESSION_CLOSING) {
+		ret = __open_session(mdsc, session);
+		if (ret)
+			return ERR_PTR(ret);
+	}
 
 	return session;
 }
@@ -2539,7 +2556,12 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 		ceph_encode_copy(&p, &ts, sizeof(ts));
 	}
 
-	BUG_ON(p > end);
+	if (WARN_ON_ONCE(p > end)) {
+		ceph_msg_put(msg);
+		msg = ERR_PTR(-ERANGE);
+		goto out_free2;
+	}
+
 	msg->front.iov_len = p - msg->front.iov_base;
 	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
 
@@ -2775,7 +2797,9 @@ static void __do_request(struct ceph_mds_client *mdsc,
 		}
 		if (session->s_state == CEPH_MDS_SESSION_NEW ||
 		    session->s_state == CEPH_MDS_SESSION_CLOSING) {
-			__open_session(mdsc, session);
+			err = __open_session(mdsc, session);
+			if (err)
+				goto out_session;
 			/* retry the same mds later */
 			if (random)
 				req->r_resend_mds = mds;
-- 
1.8.3.1

[PATCH v4 5/5] ceph: send client provided metric flags in client metadata

[xiubli]

From: Xiubo Li <xiubli@redhat.com>

Will send the metric flags to MDS, currently it supports the cap,
read latency, write latency and metadata latency.

URL: https://tracker.ceph.com/issues/43435
Signed-off-by: Xiubo Li <xiubli@redhat.com>
---
 fs/ceph/mds_client.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++--
 fs/ceph/metric.h     | 13 ++++++++++++
 2 files changed, 71 insertions(+), 2 deletions(-)

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index eda788b..a3f75d8 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1195,6 +1195,48 @@ 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.
@@ -1235,6 +1277,13 @@ 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);
@@ -1253,9 +1302,9 @@ 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 */
@@ -1284,6 +1333,13 @@ 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 1a7e3fb..6de86d3 100644
--- a/fs/ceph/metric.h
+++ b/fs/ceph/metric.h
@@ -21,6 +21,19 @@ 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 */
-- 
1.8.3.1

Re: [PATCH v4 3/5] ceph: periodically send perf metrics to ceph

[Jeff Layton]

On Sun, 2020-06-28 at 04:42 -0400, xiubli@redhat.com wrote:
> From: Xiubo Li <xiubli@redhat.com>
> 
> This will send the caps/read/write/metadata metrics to any available
> MDS only once per second as default, which will be the same as the
> userland client. It will skip the MDS sessions which don't support
> the metric collection, or the MDSs will close the socket connections
> directly when it get an unknown type message.
> 
> We can disable the metric sending via the enable_send_metric module
> parameter.
> 
> URL: https://tracker.ceph.com/issues/43215
> Signed-off-by: Xiubo Li <xiubli@redhat.com>
> ---
>  fs/ceph/mds_client.c         |  29 +++++++++
>  fs/ceph/mds_client.h         |   6 +-
>  fs/ceph/metric.c             | 142 +++++++++++++++++++++++++++++++++++++++++++
>  fs/ceph/metric.h             |  75 +++++++++++++++++++++++
>  fs/ceph/super.c              |  44 ++++++++++++++
>  fs/ceph/super.h              |   2 +
>  include/linux/ceph/ceph_fs.h |   1 +
>  7 files changed, 298 insertions(+), 1 deletion(-)
> 
> diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
> index 2eeab10..18f43a4 100644
> --- a/fs/ceph/mds_client.c
> +++ b/fs/ceph/mds_client.c
> @@ -754,6 +754,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
>  	s->s_cap_iterator = NULL;
>  	INIT_LIST_HEAD(&s->s_cap_releases);
>  	INIT_WORK(&s->s_cap_release_work, ceph_cap_release_work);
> +	INIT_DELAYED_WORK(&s->metric_delayed_work, ceph_metric_delayed_work);
>  
>  	INIT_LIST_HEAD(&s->s_cap_dirty);
>  	INIT_LIST_HEAD(&s->s_cap_flushing);
> @@ -1801,6 +1802,20 @@ static int request_close_session(struct ceph_mds_client *mdsc,
>  	return 1;
>  }
>  
> +static void try_reset_metric_work(struct ceph_mds_client *mdsc,
> +				  struct ceph_mds_session *session)
> +{
> +	mutex_lock(&mdsc->mutex);
> +	if (mdsc->metric.mds == session->s_mds) {
> +		mdsc->metric.mds = -1;
> +		cancel_delayed_work_sync(&session->metric_delayed_work);
> +
> +		/* Choose a new session to run the metric work */
> +		ceph_choose_new_metric_session(mdsc);
> +	}
> +	mutex_unlock(&mdsc->mutex);
> +}
> +
>  /*
>   * Called with s_mutex held.
>   */
> @@ -1810,6 +1825,9 @@ static int __close_session(struct ceph_mds_client *mdsc,
>  	if (session->s_state >= CEPH_MDS_SESSION_CLOSING)
>  		return 0;
>  	session->s_state = CEPH_MDS_SESSION_CLOSING;
> +
> +	try_reset_metric_work(mdsc, session);
> +
>  	return request_close_session(mdsc, session);
>  }
>  
> @@ -3312,6 +3330,15 @@ static void handle_session(struct ceph_mds_session *session,
>  		session->s_features = features;
>  		renewed_caps(mdsc, session, 0);
>  		wake = 1;
> +
> +		mutex_lock(&mdsc->mutex);
> +		if (mdsc->metric.mds < 0 &&
> +		    test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &session->s_features)) {
> +			ceph_metric_schedule_delayed(session);
> +			mdsc->metric.mds = session->s_mds;
> +		}
> +		mutex_unlock(&mdsc->mutex);
> +
>  		if (mdsc->stopping)
>  			__close_session(mdsc, session);
>  		break;
> @@ -3806,6 +3833,8 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
>  
>  	xa_destroy(&session->s_delegated_inos);
>  
> +	try_reset_metric_work(mdsc, session);
> +
>  	mutex_lock(&session->s_mutex);
>  	session->s_state = CEPH_MDS_SESSION_RECONNECTING;
>  	session->s_seq = 0;
> diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
> index bcb3892..daa905f 100644
> --- a/fs/ceph/mds_client.h
> +++ b/fs/ceph/mds_client.h
> @@ -28,8 +28,9 @@ enum ceph_feature_type {
>  	CEPHFS_FEATURE_LAZY_CAP_WANTED,
>  	CEPHFS_FEATURE_MULTI_RECONNECT,
>  	CEPHFS_FEATURE_DELEG_INO,
> +	CEPHFS_FEATURE_METRIC_COLLECT,
>  
> -	CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_DELEG_INO,
> +	CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_METRIC_COLLECT,
>  };
>  
>  /*
> @@ -43,6 +44,7 @@ enum ceph_feature_type {
>  	CEPHFS_FEATURE_LAZY_CAP_WANTED,		\
>  	CEPHFS_FEATURE_MULTI_RECONNECT,		\
>  	CEPHFS_FEATURE_DELEG_INO,		\
> +	CEPHFS_FEATURE_METRIC_COLLECT,		\
>  						\
>  	CEPHFS_FEATURE_MAX,			\
>  }
> @@ -212,6 +214,8 @@ struct ceph_mds_session {
>  	struct list_head  s_waiting;  /* waiting requests */
>  	struct list_head  s_unsafe;   /* unsafe requests */
>  	struct xarray	  s_delegated_inos;
> +
> +	struct delayed_work metric_delayed_work;  /* delayed work */
>  };
>  

(cc'ing Venky)

My apologies, Xiubo:

The cover letter was a bit vague, and I missed an important point with
the v3 set. That made it sound like you were sending stats to all the
MDS's that support them. That's not the case though -- you're attempting
to send them to each MDS in turn and then you stop up once a send is
successful.

If you have to coordinate and ensure that the stats are only sent once,
then we're probably better off with a single workqueue job after all. I
do still think though that we need to get the mdsc->mutex out of this
code as much as possible though. That's a rather highly contended mutex
and having stats code flogging it regularly is less than ideal.

>  /*
> diff --git a/fs/ceph/metric.c b/fs/ceph/metric.c
> index 269eacb..47eba86 100644
> --- a/fs/ceph/metric.c
> +++ b/fs/ceph/metric.c
> @@ -1,10 +1,150 @@
>  /* SPDX-License-Identifier: GPL-2.0 */
> +#include <linux/ceph/ceph_debug.h>
>  
>  #include <linux/types.h>
>  #include <linux/percpu_counter.h>
>  #include <linux/math64.h>
>  
>  #include "metric.h"
> +#include "mds_client.h"
> +
> +void ceph_metric_delayed_work(struct work_struct *work)
> +{
> +	struct ceph_mds_session *s =
> +		container_of(work, struct ceph_mds_session, metric_delayed_work.work);
> +	struct ceph_mds_client *mdsc = s->s_mdsc;
> +	u64 nr_caps = atomic64_read(&mdsc->metric.total_caps);
> +	struct ceph_metric_head *head;
> +	struct ceph_metric_cap *cap;
> +	struct ceph_metric_read_latency *read;
> +	struct ceph_metric_write_latency *write;
> +	struct ceph_metric_metadata_latency *meta;
> +	struct ceph_client_metric *m = &mdsc->metric;
> +	struct ceph_msg *msg;
> +	struct timespec64 ts;
> +	s64 sum, total;
> +	s32 items = 0;
> +	s32 len;
> +
> +	len = sizeof(*head) + sizeof(*cap) + sizeof(*read) + sizeof(*write)
> +	      + sizeof(*meta);
> +
> +	msg = ceph_msg_new(CEPH_MSG_CLIENT_METRICS, len, GFP_NOFS, true);
> +	if (!msg) {
> +		pr_err("send metrics to mds%d, failed to allocate message\n",
> +		       s->s_mds);
> +		return;
> +	}
> +
> +	head = msg->front.iov_base;
> +
> +	/* encode the cap metric */
> +	cap = (struct ceph_metric_cap *)(head + 1);
> +	cap->type = cpu_to_le32(CLIENT_METRIC_TYPE_CAP_INFO);
> +	cap->ver = 1;
> +	cap->compat = 1;
> +	cap->data_len = cpu_to_le32(sizeof(*cap) - 10);
> +	cap->hit = cpu_to_le64(percpu_counter_sum(&mdsc->metric.i_caps_hit));
> +	cap->mis = cpu_to_le64(percpu_counter_sum(&mdsc->metric.i_caps_mis));
> +	cap->total = cpu_to_le64(nr_caps);
> +	items++;
> +
> +	/* encode the read latency metric */
> +	read = (struct ceph_metric_read_latency *)(cap + 1);
> +	read->type = cpu_to_le32(CLIENT_METRIC_TYPE_READ_LATENCY);
> +	read->ver = 1;
> +	read->compat = 1;
> +	read->data_len = cpu_to_le32(sizeof(*read) - 10);
> +	total = m->total_reads;
> +	sum = m->read_latency_sum;
> +	jiffies_to_timespec64(sum, &ts);
> +	read->sec = cpu_to_le32(ts.tv_sec);
> +	read->nsec = cpu_to_le32(ts.tv_nsec);
> +	items++;
> +
> +	/* encode the write latency metric */
> +	write = (struct ceph_metric_write_latency *)(read + 1);
> +	write->type = cpu_to_le32(CLIENT_METRIC_TYPE_WRITE_LATENCY);
> +	write->ver = 1;
> +	write->compat = 1;
> +	write->data_len = cpu_to_le32(sizeof(*write) - 10);
> +	total = m->total_writes;
> +	sum = m->write_latency_sum;
> +	jiffies_to_timespec64(sum, &ts);
> +	write->sec = cpu_to_le32(ts.tv_sec);
> +	write->nsec = cpu_to_le32(ts.tv_nsec);
> +	items++;
> +
> +	/* encode the metadata latency metric */
> +	meta = (struct ceph_metric_metadata_latency *)(write + 1);
> +	meta->type = cpu_to_le32(CLIENT_METRIC_TYPE_METADATA_LATENCY);
> +	meta->ver = 1;
> +	meta->compat = 1;
> +	meta->data_len = cpu_to_le32(sizeof(*meta) - 10);
> +	total = m->total_metadatas;
> +	sum = m->metadata_latency_sum;
> +	jiffies_to_timespec64(sum, &ts);
> +	meta->sec = cpu_to_le32(ts.tv_sec);
> +	meta->nsec = cpu_to_le32(ts.tv_nsec);
> +	items++;
> +
> +	put_unaligned_le32(items, &head->num);
> +	msg->front.iov_len = cpu_to_le32(len);
> +	msg->hdr.version = cpu_to_le16(1);
> +	msg->hdr.compat_version = cpu_to_le16(1);
> +	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
> +	dout("client%llu send metrics to mds%d\n",
> +	     ceph_client_gid(mdsc->fsc->client), s->s_mds);
> +	ceph_con_send(&s->s_con, msg);
> +
> +	ceph_metric_schedule_delayed(s);
> +}
> +
> +/*
> + * called under mdsc->mutex
> + */

Instead of comments like this, add this to the function:

    lockdep_assert_held(&mdsc->mutex);

That both documents the requirement and should help us catch cases where
that isn't done in lockdep-enabled builds.

> +void ceph_choose_new_metric_session(struct ceph_mds_client *mdsc)
> +{
> +	struct ceph_mds_session *s;
> +	int i;
> +
> +	if (mdsc->stopping)
> +		return;
> +
> +	for (i = 0; i < mdsc->max_sessions; i++) {
> +		s = __ceph_lookup_mds_session(mdsc, i);
> +		if (!s)
> +			continue;
> +
> +		if (!check_session_state(mdsc, s)) {
> +			ceph_put_mds_session(s);
> +			continue;
> +		}
> +
> +		/*
> +		 * Skip it if MDS doesn't support the metric collection,
> +		 * or the MDS will close the session's socket connection
> +		 * directly when it get this message.
> +		 */
> +		if (test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &s->s_features)) {
> +			mdsc->metric.mds = i;
> +			ceph_metric_schedule_delayed(s);
> +			ceph_put_mds_session(s);
> +			return;
> +		}
> +
> +		ceph_put_mds_session(s);
> +	}
> +}
> +
> +void ceph_metric_schedule_delayed(struct ceph_mds_session *s)
> +{
> +	if (!enable_send_metrics)
> +		return;
> +
> +	/* per second */
> +	schedule_delayed_work(&s->metric_delayed_work, round_jiffies_relative(HZ));
> +}
>  
>  int ceph_metric_init(struct ceph_client_metric *m)
>  {
> @@ -52,6 +192,8 @@ int ceph_metric_init(struct ceph_client_metric *m)
>  	m->total_metadatas = 0;
>  	m->metadata_latency_sum = 0;
>  
> +	m->mds = -1;
> +
>  	return 0;
>  
>  err_i_caps_mis:
> diff --git a/fs/ceph/metric.h b/fs/ceph/metric.h
> index 23a3373..1a7e3fb 100644
> --- a/fs/ceph/metric.h
> +++ b/fs/ceph/metric.h
> @@ -6,6 +6,74 @@
>  #include <linux/percpu_counter.h>
>  #include <linux/ktime.h>
>  
> +struct ceph_mds_client;
> +struct ceph_mds_session;
> +
> +extern bool enable_send_metrics;
> +
> +enum ceph_metric_type {
> +	CLIENT_METRIC_TYPE_CAP_INFO,
> +	CLIENT_METRIC_TYPE_READ_LATENCY,
> +	CLIENT_METRIC_TYPE_WRITE_LATENCY,
> +	CLIENT_METRIC_TYPE_METADATA_LATENCY,
> +	CLIENT_METRIC_TYPE_DENTRY_LEASE,
> +
> +	CLIENT_METRIC_TYPE_MAX = CLIENT_METRIC_TYPE_DENTRY_LEASE,
> +};
> +
> +/* metric caps header */
> +struct ceph_metric_cap {
> +	__le32 type;     /* ceph metric type */
> +
> +	__u8  ver;
> +	__u8  compat;
> +
> +	__le32 data_len; /* length of sizeof(hit + mis + total) */
> +	__le64 hit;
> +	__le64 mis;
> +	__le64 total;
> +} __packed;
> +
> +/* metric read latency header */
> +struct ceph_metric_read_latency {
> +	__le32 type;     /* ceph metric type */
> +
> +	__u8  ver;
> +	__u8  compat;
> +
> +	__le32 data_len; /* length of sizeof(sec + nsec) */
> +	__le32 sec;
> +	__le32 nsec;
> +} __packed;
> +
> +/* metric write latency header */
> +struct ceph_metric_write_latency {
> +	__le32 type;     /* ceph metric type */
> +
> +	__u8  ver;
> +	__u8  compat;
> +
> +	__le32 data_len; /* length of sizeof(sec + nsec) */
> +	__le32 sec;
> +	__le32 nsec;
> +} __packed;
> +
> +/* metric metadata latency header */
> +struct ceph_metric_metadata_latency {
> +	__le32 type;     /* ceph metric type */
> +
> +	__u8  ver;
> +	__u8  compat;
> +
> +	__le32 data_len; /* length of sizeof(sec + nsec) */
> +	__le32 sec;
> +	__le32 nsec;
> +} __packed;
> +
> +struct ceph_metric_head {
> +	__le32 num;	/* the number of metrics that will be sent */
> +} __packed;
> +
>  /* This is the global metrics */
>  struct ceph_client_metric {
>  	atomic64_t            total_dentries;
> @@ -36,8 +104,15 @@ struct ceph_client_metric {
>  	ktime_t metadata_latency_sq_sum;
>  	ktime_t metadata_latency_min;
>  	ktime_t metadata_latency_max;
> +
> +	/* The MDS session running the metric work */
> +	int mds;
>  };
>  
> +extern void ceph_metric_delayed_work(struct work_struct *work);
> +extern void ceph_metric_schedule_delayed(struct ceph_mds_session *s);
> +extern void ceph_choose_new_metric_session(struct ceph_mds_client *mdsc);
> +
>  extern int ceph_metric_init(struct ceph_client_metric *m);
>  extern void ceph_metric_destroy(struct ceph_client_metric *m);
>  
> diff --git a/fs/ceph/super.c b/fs/ceph/super.c
> index c9784eb1..510ccb1 100644
> --- a/fs/ceph/super.c
> +++ b/fs/ceph/super.c
> @@ -27,6 +27,9 @@
>  #include <linux/ceph/auth.h>
>  #include <linux/ceph/debugfs.h>
>  
> +static DEFINE_MUTEX(ceph_fsc_lock);
> +static LIST_HEAD(ceph_fsc_list);
> +
>  /*
>   * Ceph superblock operations
>   *
> @@ -691,6 +694,10 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
>  	if (!fsc->wb_pagevec_pool)
>  		goto fail_cap_wq;
>  
> +	mutex_lock(&ceph_fsc_lock);
> +	list_add_tail(&fsc->list, &ceph_fsc_list);
> +	mutex_unlock(&ceph_fsc_lock);
> +
>  	return fsc;
>  
>  fail_cap_wq:
> @@ -717,6 +724,10 @@ static void destroy_fs_client(struct ceph_fs_client *fsc)
>  {
>  	dout("destroy_fs_client %p\n", fsc);
>  
> +	mutex_lock(&ceph_fsc_lock);
> +	list_del(&fsc->list);
> +	mutex_unlock(&ceph_fsc_lock);
> +
>  	ceph_mdsc_destroy(fsc);
>  	destroy_workqueue(fsc->inode_wq);
>  	destroy_workqueue(fsc->cap_wq);
> @@ -1282,6 +1293,39 @@ static void __exit exit_ceph(void)
>  	destroy_caches();
>  }
>  
> +static int param_set_metrics(const char *val, const struct kernel_param *kp)
> +{
> +	struct ceph_fs_client *fsc;
> +	int ret;
> +
> +	ret = param_set_bool(val, kp);
> +	if (ret) {
> +		pr_err("Failed to parse sending metrics switch value '%s'\n",
> +		       val);
> +		return ret;
> +	} else if (enable_send_metrics) {
> +		// wake up all the mds clients
> +		mutex_lock(&ceph_fsc_lock);
> +		list_for_each_entry(fsc, &ceph_fsc_list, list) {
> +			mutex_lock(&fsc->mdsc->mutex);
> +			ceph_choose_new_metric_session(fsc->mdsc);
> +			mutex_unlock(&fsc->mdsc->mutex);
> +		}
> +		mutex_unlock(&ceph_fsc_lock);
> +	}
> +
> +	return 0;
> +}
> +
> +static const struct kernel_param_ops param_ops_metrics = {
> +	.set = param_set_metrics,
> +	.get = param_get_bool,
> +};
> +
> +bool enable_send_metrics = true;
> +module_param_cb(enable_send_metrics, &param_ops_metrics, &enable_send_metrics, 0644);
> +MODULE_PARM_DESC(enable_send_metrics, "Enable sending perf metrics to ceph cluster (default: on)");
> +
>  module_init(init_ceph);
>  module_exit(exit_ceph);
>  
> diff --git a/fs/ceph/super.h b/fs/ceph/super.h
> index 5a6cdd3..05edc9a 100644
> --- a/fs/ceph/super.h
> +++ b/fs/ceph/super.h
> @@ -101,6 +101,8 @@ struct ceph_mount_options {
>  struct ceph_fs_client {
>  	struct super_block *sb;
>  
> +	struct list_head list;
> +

Let's not name this list_head "list". It should be something more
distinctive.

>  	struct ceph_mount_options *mount_options;
>  	struct ceph_client *client;
>  
> diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
> index ebf5ba6..455e9b9 100644
> --- a/include/linux/ceph/ceph_fs.h
> +++ b/include/linux/ceph/ceph_fs.h
> @@ -130,6 +130,7 @@ struct ceph_dir_layout {
>  #define CEPH_MSG_CLIENT_REQUEST         24
>  #define CEPH_MSG_CLIENT_REQUEST_FORWARD 25
>  #define CEPH_MSG_CLIENT_REPLY           26
> +#define CEPH_MSG_CLIENT_METRICS         29
>  #define CEPH_MSG_CLIENT_CAPS            0x310
>  #define CEPH_MSG_CLIENT_LEASE           0x311
>  #define CEPH_MSG_CLIENT_SNAP            0x312

-- 
Jeff Layton <jlayton@kernel.org>

Re: [PATCH v4 3/5] ceph: periodically send perf metrics to ceph

[Xiubo Li]

On 2020/6/29 19:51, Jeff Layton wrote:
> On Sun, 2020-06-28 at 04:42 -0400, xiubli@redhat.com wrote:
>> From: Xiubo Li <xiubli@redhat.com>
>>
>> This will send the caps/read/write/metadata metrics to any available
>> MDS only once per second as default, which will be the same as the
>> userland client. It will skip the MDS sessions which don't support
>> the metric collection, or the MDSs will close the socket connections
>> directly when it get an unknown type message.
>>
>> We can disable the metric sending via the enable_send_metric module
>> parameter.
>>
>> URL: https://tracker.ceph.com/issues/43215
>> Signed-off-by: Xiubo Li <xiubli@redhat.com>
>> ---
>>   fs/ceph/mds_client.c         |  29 +++++++++
>>   fs/ceph/mds_client.h         |   6 +-
>>   fs/ceph/metric.c             | 142 +++++++++++++++++++++++++++++++++++++++++++
>>   fs/ceph/metric.h             |  75 +++++++++++++++++++++++
>>   fs/ceph/super.c              |  44 ++++++++++++++
>>   fs/ceph/super.h              |   2 +
>>   include/linux/ceph/ceph_fs.h |   1 +
>>   7 files changed, 298 insertions(+), 1 deletion(-)
>>
>> diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
>> index 2eeab10..18f43a4 100644
>> --- a/fs/ceph/mds_client.c
>> +++ b/fs/ceph/mds_client.c
>> @@ -754,6 +754,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
>>   	s->s_cap_iterator = NULL;
>>   	INIT_LIST_HEAD(&s->s_cap_releases);
>>   	INIT_WORK(&s->s_cap_release_work, ceph_cap_release_work);
>> +	INIT_DELAYED_WORK(&s->metric_delayed_work, ceph_metric_delayed_work);
>>   
>>   	INIT_LIST_HEAD(&s->s_cap_dirty);
>>   	INIT_LIST_HEAD(&s->s_cap_flushing);
>> @@ -1801,6 +1802,20 @@ static int request_close_session(struct ceph_mds_client *mdsc,
>>   	return 1;
>>   }
>>   
>> +static void try_reset_metric_work(struct ceph_mds_client *mdsc,
>> +				  struct ceph_mds_session *session)
>> +{
>> +	mutex_lock(&mdsc->mutex);
>> +	if (mdsc->metric.mds == session->s_mds) {
>> +		mdsc->metric.mds = -1;
>> +		cancel_delayed_work_sync(&session->metric_delayed_work);
>> +
>> +		/* Choose a new session to run the metric work */
>> +		ceph_choose_new_metric_session(mdsc);
>> +	}
>> +	mutex_unlock(&mdsc->mutex);
>> +}
>> +
>>   /*
>>    * Called with s_mutex held.
>>    */
>> @@ -1810,6 +1825,9 @@ static int __close_session(struct ceph_mds_client *mdsc,
>>   	if (session->s_state >= CEPH_MDS_SESSION_CLOSING)
>>   		return 0;
>>   	session->s_state = CEPH_MDS_SESSION_CLOSING;
>> +
>> +	try_reset_metric_work(mdsc, session);
>> +
>>   	return request_close_session(mdsc, session);
>>   }
>>   
>> @@ -3312,6 +3330,15 @@ static void handle_session(struct ceph_mds_session *session,
>>   		session->s_features = features;
>>   		renewed_caps(mdsc, session, 0);
>>   		wake = 1;
>> +
>> +		mutex_lock(&mdsc->mutex);
>> +		if (mdsc->metric.mds < 0 &&
>> +		    test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &session->s_features)) {
>> +			ceph_metric_schedule_delayed(session);
>> +			mdsc->metric.mds = session->s_mds;
>> +		}
>> +		mutex_unlock(&mdsc->mutex);
>> +
>>   		if (mdsc->stopping)
>>   			__close_session(mdsc, session);
>>   		break;
>> @@ -3806,6 +3833,8 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc,
>>   
>>   	xa_destroy(&session->s_delegated_inos);
>>   
>> +	try_reset_metric_work(mdsc, session);
>> +
>>   	mutex_lock(&session->s_mutex);
>>   	session->s_state = CEPH_MDS_SESSION_RECONNECTING;
>>   	session->s_seq = 0;
>> diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
>> index bcb3892..daa905f 100644
>> --- a/fs/ceph/mds_client.h
>> +++ b/fs/ceph/mds_client.h
>> @@ -28,8 +28,9 @@ enum ceph_feature_type {
>>   	CEPHFS_FEATURE_LAZY_CAP_WANTED,
>>   	CEPHFS_FEATURE_MULTI_RECONNECT,
>>   	CEPHFS_FEATURE_DELEG_INO,
>> +	CEPHFS_FEATURE_METRIC_COLLECT,
>>   
>> -	CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_DELEG_INO,
>> +	CEPHFS_FEATURE_MAX = CEPHFS_FEATURE_METRIC_COLLECT,
>>   };
>>   
>>   /*
>> @@ -43,6 +44,7 @@ enum ceph_feature_type {
>>   	CEPHFS_FEATURE_LAZY_CAP_WANTED,		\
>>   	CEPHFS_FEATURE_MULTI_RECONNECT,		\
>>   	CEPHFS_FEATURE_DELEG_INO,		\
>> +	CEPHFS_FEATURE_METRIC_COLLECT,		\
>>   						\
>>   	CEPHFS_FEATURE_MAX,			\
>>   }
>> @@ -212,6 +214,8 @@ struct ceph_mds_session {
>>   	struct list_head  s_waiting;  /* waiting requests */
>>   	struct list_head  s_unsafe;   /* unsafe requests */
>>   	struct xarray	  s_delegated_inos;
>> +
>> +	struct delayed_work metric_delayed_work;  /* delayed work */
>>   };
>>   
> (cc'ing Venky)
>
> My apologies, Xiubo:
>
> The cover letter was a bit vague, and I missed an important point with
> the v3 set. That made it sound like you were sending stats to all the
> MDS's that support them. That's not the case though -- you're attempting
> to send them to each MDS in turn and then you stop up once a send is
> successful.

Ah sorry, the comments are not that correct as the code does.

For this version we will only have one active workqueue job running on 
an MDS session which supports it and send the metrics once per second, 
all the other sessions' workqueue jobs will be in standy mode. With this 
we can totally get rid of the mdsc->mutex in the workqueue job here.


> If you have to coordinate and ensure that the stats are only sent once,

Since no matter which MDS receives the metrics it will report them to 
the MDS with rank 0, so the clients need to send the metrics to at least 
1 MDS each time.


> then we're probably better off with a single workqueue job after all. I
> do still think though that we need to get the mdsc->mutex out of this
> code as much as possible though. That's a rather highly contended mutex
> and having stats code flogging it regularly is less than ideal.

IMO both approaches should be fine, but since the workqueue job running 
periodically per second, mutlti workqueue jobs should be better ?

And the following is another approach with a single workqueue job, no 
matter we save the session itself or mds rank number in mdsc, we need to 
and cannot get rid of the mdsc->mutex lock. But mostly the code in 
mdsc->mutex lock/unlock pair should be short and fast and also should be 
rare running into the unlikely() case:

.

+/*
+ * called under mdsc->mutex
+ */
+static struct ceph_mds_session *metric_get_session(struct ceph_mds_client *mdsc)
+{
+	struct ceph_mds_session *s;
+	int i;
+
+	for (i = 0; i < mdsc->max_sessions; i++) {
+		s = __ceph_lookup_mds_session(mdsc, i);
+		if (!s)
+			continue;
+
+		if (!check_session_state(mdsc, s)) {
+			ceph_put_mds_session(s);
+			continue;
+		}
+
+		/*
+		 * Skip it if MDS doesn't support the metric collection,
+		 * or the MDS will close the session's socket connection
+		 * directly when it get this message.
+		 */
+		if (test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &s->s_features)) {
+			mdsc->metric.mds = i;
+			return s;
+		}
+
+		ceph_put_mds_session(s);
+	}
+
+	return NULL;
+}
+
+static void metric_delayed_work(struct work_struct *work)
+{
+	struct ceph_client_metric *m =
+		container_of(work, struct ceph_client_metric, delayed_work.work);
+	struct ceph_mds_client *mdsc =
+		container_of(m, struct ceph_mds_client, metric);
+	struct ceph_mds_session *s = NULL;
+	u64 nr_caps = atomic64_read(&m->total_caps);
+
+	/* No mds supports the metric collection, will stop the work */
+	if (!atomic_read(&m->mds_cnt))
+		return;
+
+	mutex_lock(&mdsc->mutex);
+	s = __ceph_lookup_mds_session(mdsc, m->mds);
+	if (unlikely(!s || !test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &s->s_features)))
+		s = metric_get_session(mdsc);
+	mutex_unlock(&mdsc->mutex);
+	if (likely(s)) {
+		/* Only send the metric once in any available session */
+		ceph_mdsc_send_metrics(mdsc, s, nr_caps);
+		ceph_put_mds_session(s);
+	}
+
+	metric_schedule_delayed(m);
+}



>>   /*
>> diff --git a/fs/ceph/metric.c b/fs/ceph/metric.c
>> index 269eacb..47eba86 100644
>> --- a/fs/ceph/metric.c
>> +++ b/fs/ceph/metric.c
>> @@ -1,10 +1,150 @@
>>   /* SPDX-License-Identifier: GPL-2.0 */
>> +#include <linux/ceph/ceph_debug.h>
>>   
>>   #include <linux/types.h>
>>   #include <linux/percpu_counter.h>
>>   #include <linux/math64.h>
>>   
>>   #include "metric.h"
>> +#include "mds_client.h"
>> +
>> +void ceph_metric_delayed_work(struct work_struct *work)
>> +{
>> +	struct ceph_mds_session *s =
>> +		container_of(work, struct ceph_mds_session, metric_delayed_work.work);
>> +	struct ceph_mds_client *mdsc = s->s_mdsc;
>> +	u64 nr_caps = atomic64_read(&mdsc->metric.total_caps);
>> +	struct ceph_metric_head *head;
>> +	struct ceph_metric_cap *cap;
>> +	struct ceph_metric_read_latency *read;
>> +	struct ceph_metric_write_latency *write;
>> +	struct ceph_metric_metadata_latency *meta;
>> +	struct ceph_client_metric *m = &mdsc->metric;
>> +	struct ceph_msg *msg;
>> +	struct timespec64 ts;
>> +	s64 sum, total;
>> +	s32 items = 0;
>> +	s32 len;
>> +
>> +	len = sizeof(*head) + sizeof(*cap) + sizeof(*read) + sizeof(*write)
>> +	      + sizeof(*meta);
>> +
>> +	msg = ceph_msg_new(CEPH_MSG_CLIENT_METRICS, len, GFP_NOFS, true);
>> +	if (!msg) {
>> +		pr_err("send metrics to mds%d, failed to allocate message\n",
>> +		       s->s_mds);
>> +		return;
>> +	}
>> +
>> +	head = msg->front.iov_base;
>> +
>> +	/* encode the cap metric */
>> +	cap = (struct ceph_metric_cap *)(head + 1);
>> +	cap->type = cpu_to_le32(CLIENT_METRIC_TYPE_CAP_INFO);
>> +	cap->ver = 1;
>> +	cap->compat = 1;
>> +	cap->data_len = cpu_to_le32(sizeof(*cap) - 10);
>> +	cap->hit = cpu_to_le64(percpu_counter_sum(&mdsc->metric.i_caps_hit));
>> +	cap->mis = cpu_to_le64(percpu_counter_sum(&mdsc->metric.i_caps_mis));
>> +	cap->total = cpu_to_le64(nr_caps);
>> +	items++;
>> +
>> +	/* encode the read latency metric */
>> +	read = (struct ceph_metric_read_latency *)(cap + 1);
>> +	read->type = cpu_to_le32(CLIENT_METRIC_TYPE_READ_LATENCY);
>> +	read->ver = 1;
>> +	read->compat = 1;
>> +	read->data_len = cpu_to_le32(sizeof(*read) - 10);
>> +	total = m->total_reads;
>> +	sum = m->read_latency_sum;
>> +	jiffies_to_timespec64(sum, &ts);
>> +	read->sec = cpu_to_le32(ts.tv_sec);
>> +	read->nsec = cpu_to_le32(ts.tv_nsec);
>> +	items++;
>> +
>> +	/* encode the write latency metric */
>> +	write = (struct ceph_metric_write_latency *)(read + 1);
>> +	write->type = cpu_to_le32(CLIENT_METRIC_TYPE_WRITE_LATENCY);
>> +	write->ver = 1;
>> +	write->compat = 1;
>> +	write->data_len = cpu_to_le32(sizeof(*write) - 10);
>> +	total = m->total_writes;
>> +	sum = m->write_latency_sum;
>> +	jiffies_to_timespec64(sum, &ts);
>> +	write->sec = cpu_to_le32(ts.tv_sec);
>> +	write->nsec = cpu_to_le32(ts.tv_nsec);
>> +	items++;
>> +
>> +	/* encode the metadata latency metric */
>> +	meta = (struct ceph_metric_metadata_latency *)(write + 1);
>> +	meta->type = cpu_to_le32(CLIENT_METRIC_TYPE_METADATA_LATENCY);
>> +	meta->ver = 1;
>> +	meta->compat = 1;
>> +	meta->data_len = cpu_to_le32(sizeof(*meta) - 10);
>> +	total = m->total_metadatas;
>> +	sum = m->metadata_latency_sum;
>> +	jiffies_to_timespec64(sum, &ts);
>> +	meta->sec = cpu_to_le32(ts.tv_sec);
>> +	meta->nsec = cpu_to_le32(ts.tv_nsec);
>> +	items++;
>> +
>> +	put_unaligned_le32(items, &head->num);
>> +	msg->front.iov_len = cpu_to_le32(len);
>> +	msg->hdr.version = cpu_to_le16(1);
>> +	msg->hdr.compat_version = cpu_to_le16(1);
>> +	msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
>> +	dout("client%llu send metrics to mds%d\n",
>> +	     ceph_client_gid(mdsc->fsc->client), s->s_mds);
>> +	ceph_con_send(&s->s_con, msg);
>> +
>> +	ceph_metric_schedule_delayed(s);
>> +}
>> +
>> +/*
>> + * called under mdsc->mutex
>> + */
> Instead of comments like this, add this to the function:
>
>      lockdep_assert_held(&mdsc->mutex);
>
> That both documents the requirement and should help us catch cases where
> that isn't done in lockdep-enabled builds.

Sure, will fix it.


>
>> +void ceph_choose_new_metric_session(struct ceph_mds_client *mdsc)
>> +{
>> +	struct ceph_mds_session *s;
>> +	int i;
>> +
>> +	if (mdsc->stopping)
>> +		return;
>> +
>> +	for (i = 0; i < mdsc->max_sessions; i++) {
>> +		s = __ceph_lookup_mds_session(mdsc, i);
>> +		if (!s)
>> +			continue;
>> +
>> +		if (!check_session_state(mdsc, s)) {
>> +			ceph_put_mds_session(s);
>> +			continue;
>> +		}
>> +
>> +		/*
>> +		 * Skip it if MDS doesn't support the metric collection,
>> +		 * or the MDS will close the session's socket connection
>> +		 * directly when it get this message.
>> +		 */
>> +		if (test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &s->s_features)) {
>> +			mdsc->metric.mds = i;
>> +			ceph_metric_schedule_delayed(s);
>> +			ceph_put_mds_session(s);
>> +			return;
>> +		}
>> +
>> +		ceph_put_mds_session(s);
>> +	}
>> +}
>> +
>> +void ceph_metric_schedule_delayed(struct ceph_mds_session *s)
>> +{
>> +	if (!enable_send_metrics)
>> +		return;
>> +
>> +	/* per second */
>> +	schedule_delayed_work(&s->metric_delayed_work, round_jiffies_relative(HZ));
>> +}
>>   
>>   int ceph_metric_init(struct ceph_client_metric *m)
>>   {
>> @@ -52,6 +192,8 @@ int ceph_metric_init(struct ceph_client_metric *m)
>>   	m->total_metadatas = 0;
>>   	m->metadata_latency_sum = 0;
>>   
>> +	m->mds = -1;
>> +
>>   	return 0;
>>   
>>   err_i_caps_mis:
>> diff --git a/fs/ceph/metric.h b/fs/ceph/metric.h
>> index 23a3373..1a7e3fb 100644
>> --- a/fs/ceph/metric.h
>> +++ b/fs/ceph/metric.h
>> @@ -6,6 +6,74 @@
>>   #include <linux/percpu_counter.h>
>>   #include <linux/ktime.h>
>>   
>> +struct ceph_mds_client;
>> +struct ceph_mds_session;
>> +
>> +extern bool enable_send_metrics;
>> +
>> +enum ceph_metric_type {
>> +	CLIENT_METRIC_TYPE_CAP_INFO,
>> +	CLIENT_METRIC_TYPE_READ_LATENCY,
>> +	CLIENT_METRIC_TYPE_WRITE_LATENCY,
>> +	CLIENT_METRIC_TYPE_METADATA_LATENCY,
>> +	CLIENT_METRIC_TYPE_DENTRY_LEASE,
>> +
>> +	CLIENT_METRIC_TYPE_MAX = CLIENT_METRIC_TYPE_DENTRY_LEASE,
>> +};
>> +
>> +/* metric caps header */
>> +struct ceph_metric_cap {
>> +	__le32 type;     /* ceph metric type */
>> +
>> +	__u8  ver;
>> +	__u8  compat;
>> +
>> +	__le32 data_len; /* length of sizeof(hit + mis + total) */
>> +	__le64 hit;
>> +	__le64 mis;
>> +	__le64 total;
>> +} __packed;
>> +
>> +/* metric read latency header */
>> +struct ceph_metric_read_latency {
>> +	__le32 type;     /* ceph metric type */
>> +
>> +	__u8  ver;
>> +	__u8  compat;
>> +
>> +	__le32 data_len; /* length of sizeof(sec + nsec) */
>> +	__le32 sec;
>> +	__le32 nsec;
>> +} __packed;
>> +
>> +/* metric write latency header */
>> +struct ceph_metric_write_latency {
>> +	__le32 type;     /* ceph metric type */
>> +
>> +	__u8  ver;
>> +	__u8  compat;
>> +
>> +	__le32 data_len; /* length of sizeof(sec + nsec) */
>> +	__le32 sec;
>> +	__le32 nsec;
>> +} __packed;
>> +
>> +/* metric metadata latency header */
>> +struct ceph_metric_metadata_latency {
>> +	__le32 type;     /* ceph metric type */
>> +
>> +	__u8  ver;
>> +	__u8  compat;
>> +
>> +	__le32 data_len; /* length of sizeof(sec + nsec) */
>> +	__le32 sec;
>> +	__le32 nsec;
>> +} __packed;
>> +
>> +struct ceph_metric_head {
>> +	__le32 num;	/* the number of metrics that will be sent */
>> +} __packed;
>> +
>>   /* This is the global metrics */
>>   struct ceph_client_metric {
>>   	atomic64_t            total_dentries;
>> @@ -36,8 +104,15 @@ struct ceph_client_metric {
>>   	ktime_t metadata_latency_sq_sum;
>>   	ktime_t metadata_latency_min;
>>   	ktime_t metadata_latency_max;
>> +
>> +	/* The MDS session running the metric work */
>> +	int mds;
>>   };
>>   
>> +extern void ceph_metric_delayed_work(struct work_struct *work);
>> +extern void ceph_metric_schedule_delayed(struct ceph_mds_session *s);
>> +extern void ceph_choose_new_metric_session(struct ceph_mds_client *mdsc);
>> +
>>   extern int ceph_metric_init(struct ceph_client_metric *m);
>>   extern void ceph_metric_destroy(struct ceph_client_metric *m);
>>   
>> diff --git a/fs/ceph/super.c b/fs/ceph/super.c
>> index c9784eb1..510ccb1 100644
>> --- a/fs/ceph/super.c
>> +++ b/fs/ceph/super.c
>> @@ -27,6 +27,9 @@
>>   #include <linux/ceph/auth.h>
>>   #include <linux/ceph/debugfs.h>
>>   
>> +static DEFINE_MUTEX(ceph_fsc_lock);
>> +static LIST_HEAD(ceph_fsc_list);
>> +
>>   /*
>>    * Ceph superblock operations
>>    *
>> @@ -691,6 +694,10 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
>>   	if (!fsc->wb_pagevec_pool)
>>   		goto fail_cap_wq;
>>   
>> +	mutex_lock(&ceph_fsc_lock);
>> +	list_add_tail(&fsc->list, &ceph_fsc_list);
>> +	mutex_unlock(&ceph_fsc_lock);
>> +
>>   	return fsc;
>>   
>>   fail_cap_wq:
>> @@ -717,6 +724,10 @@ static void destroy_fs_client(struct ceph_fs_client *fsc)
>>   {
>>   	dout("destroy_fs_client %p\n", fsc);
>>   
>> +	mutex_lock(&ceph_fsc_lock);
>> +	list_del(&fsc->list);
>> +	mutex_unlock(&ceph_fsc_lock);
>> +
>>   	ceph_mdsc_destroy(fsc);
>>   	destroy_workqueue(fsc->inode_wq);
>>   	destroy_workqueue(fsc->cap_wq);
>> @@ -1282,6 +1293,39 @@ static void __exit exit_ceph(void)
>>   	destroy_caches();
>>   }
>>   
>> +static int param_set_metrics(const char *val, const struct kernel_param *kp)
>> +{
>> +	struct ceph_fs_client *fsc;
>> +	int ret;
>> +
>> +	ret = param_set_bool(val, kp);
>> +	if (ret) {
>> +		pr_err("Failed to parse sending metrics switch value '%s'\n",
>> +		       val);
>> +		return ret;
>> +	} else if (enable_send_metrics) {
>> +		// wake up all the mds clients
>> +		mutex_lock(&ceph_fsc_lock);
>> +		list_for_each_entry(fsc, &ceph_fsc_list, list) {
>> +			mutex_lock(&fsc->mdsc->mutex);
>> +			ceph_choose_new_metric_session(fsc->mdsc);
>> +			mutex_unlock(&fsc->mdsc->mutex);
>> +		}
>> +		mutex_unlock(&ceph_fsc_lock);
>> +	}
>> +
>> +	return 0;
>> +}
>> +
>> +static const struct kernel_param_ops param_ops_metrics = {
>> +	.set = param_set_metrics,
>> +	.get = param_get_bool,
>> +};
>> +
>> +bool enable_send_metrics = true;
>> +module_param_cb(enable_send_metrics, &param_ops_metrics, &enable_send_metrics, 0644);
>> +MODULE_PARM_DESC(enable_send_metrics, "Enable sending perf metrics to ceph cluster (default: on)");
>> +
>>   module_init(init_ceph);
>>   module_exit(exit_ceph);
>>   
>> diff --git a/fs/ceph/super.h b/fs/ceph/super.h
>> index 5a6cdd3..05edc9a 100644
>> --- a/fs/ceph/super.h
>> +++ b/fs/ceph/super.h
>> @@ -101,6 +101,8 @@ struct ceph_mount_options {
>>   struct ceph_fs_client {
>>   	struct super_block *sb;
>>   
>> +	struct list_head list;
>> +
> Let's not name this list_head "list". It should be something more
> distinctive.

Okay, will fix it.

Thanks.


>
>>   	struct ceph_mount_options *mount_options;
>>   	struct ceph_client *client;
>>   
>> diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
>> index ebf5ba6..455e9b9 100644
>> --- a/include/linux/ceph/ceph_fs.h
>> +++ b/include/linux/ceph/ceph_fs.h
>> @@ -130,6 +130,7 @@ struct ceph_dir_layout {
>>   #define CEPH_MSG_CLIENT_REQUEST         24
>>   #define CEPH_MSG_CLIENT_REQUEST_FORWARD 25
>>   #define CEPH_MSG_CLIENT_REPLY           26
>> +#define CEPH_MSG_CLIENT_METRICS         29
>>   #define CEPH_MSG_CLIENT_CAPS            0x310
>>   #define CEPH_MSG_CLIENT_LEASE           0x311
>>   #define CEPH_MSG_CLIENT_SNAP            0x312