ceph: periodically send perf metrics to MDSes

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

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

[ jlayton: fix up endianness bug in ceph_mdsc_send_metrics() ]

URL: https://tracker.ceph.com/issues/43215
Signed-off-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>

1 files changed, 148 insertions, 0 deletions

diff --git a/fs/ceph/metric.c b/fs/ceph/metric.c
index 269eacbd2a15..2466b261fba2 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"
+
+static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc,
+				   struct ceph_mds_session *s)
+{
+	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;
+	u64 nr_caps = atomic64_read(&m->total_caps);
+	struct ceph_msg *msg;
+	struct timespec64 ts;
+	s64 sum;
+	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 false;
+	}
+
+	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);
+	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);
+	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);
+	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 = 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);
+
+	return true;
+}
+
+
+static void metric_get_session(struct ceph_mds_client *mdsc)
+{
+	struct ceph_mds_session *s;
+	int i;
+
+	mutex_lock(&mdsc->mutex);
+	for (i = 0; i < mdsc->max_sessions; i++) {
+		s = __ceph_lookup_mds_session(mdsc, i);
+		if (!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 (check_session_state(s) &&
+		    test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &s->s_features)) {
+			mdsc->metric.session = s;
+			break;
+		}
+
+		ceph_put_mds_session(s);
+	}
+	mutex_unlock(&mdsc->mutex);
+}
+
+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);
+
+	if (mdsc->stopping)
+		return;
+
+	if (!m->session || !check_session_state(m->session)) {
+		if (m->session) {
+			ceph_put_mds_session(m->session);
+			m->session = NULL;
+		}
+		metric_get_session(mdsc);
+	}
+	if (m->session) {
+		ceph_mdsc_send_metrics(mdsc, m->session);
+		metric_schedule_delayed(m);
+	}
+}
 
 int ceph_metric_init(struct ceph_client_metric *m)
 {
@@ -52,6 +192,9 @@ int ceph_metric_init(struct ceph_client_metric *m)
 	m->total_metadatas = 0;
 	m->metadata_latency_sum = 0;
 
+	m->session = NULL;
+	INIT_DELAYED_WORK(&m->delayed_work, metric_delayed_work);
+
 	return 0;
 
 err_i_caps_mis:
@@ -73,6 +216,11 @@ void ceph_metric_destroy(struct ceph_client_metric *m)
 	percpu_counter_destroy(&m->i_caps_hit);
 	percpu_counter_destroy(&m->d_lease_mis);
 	percpu_counter_destroy(&m->d_lease_hit);
+
+	cancel_delayed_work_sync(&m->delayed_work);
+
+	if (m->session)
+		ceph_put_mds_session(m->session);
 }
 
 static inline void __update_latency(ktime_t *totalp, ktime_t *lsump,