summaryrefslogtreecommitdiffstats
path: root/fs/ceph/metric.c
blob: 2466b261fba243a24cc0c2222e9e911ccb54b102 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
/* 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)
{
	int ret;

	if (!m)
		return -EINVAL;

	atomic64_set(&m->total_dentries, 0);
	ret = percpu_counter_init(&m->d_lease_hit, 0, GFP_KERNEL);
	if (ret)
		return ret;

	ret = percpu_counter_init(&m->d_lease_mis, 0, GFP_KERNEL);
	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;

	ret = percpu_counter_init(&m->i_caps_mis, 0, GFP_KERNEL);
	if (ret)
		goto err_i_caps_mis;

	spin_lock_init(&m->read_latency_lock);
	m->read_latency_sq_sum = 0;
	m->read_latency_min = KTIME_MAX;
	m->read_latency_max = 0;
	m->total_reads = 0;
	m->read_latency_sum = 0;

	spin_lock_init(&m->write_latency_lock);
	m->write_latency_sq_sum = 0;
	m->write_latency_min = KTIME_MAX;
	m->write_latency_max = 0;
	m->total_writes = 0;
	m->write_latency_sum = 0;

	spin_lock_init(&m->metadata_latency_lock);
	m->metadata_latency_sq_sum = 0;
	m->metadata_latency_min = KTIME_MAX;
	m->metadata_latency_max = 0;
	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:
	percpu_counter_destroy(&m->i_caps_hit);
err_i_caps_hit:
	percpu_counter_destroy(&m->d_lease_mis);
err_d_lease_mis:
	percpu_counter_destroy(&m->d_lease_hit);

	return ret;
}

void ceph_metric_destroy(struct ceph_client_metric *m)
{
	if (!m)
		return;

	percpu_counter_destroy(&m->i_caps_mis);
	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,
				    ktime_t *min, ktime_t *max,
				    ktime_t *sq_sump, ktime_t lat)
{
	ktime_t total, avg, sq, lsum;

	total = ++(*totalp);
	lsum = (*lsump += lat);

	if (unlikely(lat < *min))
		*min = lat;
	if (unlikely(lat > *max))
		*max = lat;

	if (unlikely(total == 1))
		return;

	/* the sq is (lat - old_avg) * (lat - new_avg) */
	avg = DIV64_U64_ROUND_CLOSEST((lsum - lat), (total - 1));
	sq = lat - avg;
	avg = DIV64_U64_ROUND_CLOSEST(lsum, total);
	sq = sq * (lat - avg);
	*sq_sump += sq;
}

void ceph_update_read_latency(struct ceph_client_metric *m,
			      ktime_t r_start, ktime_t r_end,
			      int rc)
{
	ktime_t lat = ktime_sub(r_end, r_start);

	if (unlikely(rc < 0 && rc != -ENOENT && rc != -ETIMEDOUT))
		return;

	spin_lock(&m->read_latency_lock);
	__update_latency(&m->total_reads, &m->read_latency_sum,
			 &m->read_latency_min, &m->read_latency_max,
			 &m->read_latency_sq_sum, lat);
	spin_unlock(&m->read_latency_lock);
}

void ceph_update_write_latency(struct ceph_client_metric *m,
			       ktime_t r_start, ktime_t r_end,
			       int rc)
{
	ktime_t lat = ktime_sub(r_end, r_start);

	if (unlikely(rc && rc != -ETIMEDOUT))
		return;

	spin_lock(&m->write_latency_lock);
	__update_latency(&m->total_writes, &m->write_latency_sum,
			 &m->write_latency_min, &m->write_latency_max,
			 &m->write_latency_sq_sum, lat);
	spin_unlock(&m->write_latency_lock);
}

void ceph_update_metadata_latency(struct ceph_client_metric *m,
				  ktime_t r_start, ktime_t r_end,
				  int rc)
{
	ktime_t lat = ktime_sub(r_end, r_start);

	if (unlikely(rc && rc != -ENOENT))
		return;

	spin_lock(&m->metadata_latency_lock);
	__update_latency(&m->total_metadatas, &m->metadata_latency_sum,
			 &m->metadata_latency_min, &m->metadata_latency_max,
			 &m->metadata_latency_sq_sum, lat);
	spin_unlock(&m->metadata_latency_lock);
}