summaryrefslogtreecommitdiffstats
path: root/block/blk-stat.c
blob: 4681c488c262088d5dee42c1aaf76651009fbb91 (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
/*
 * Block stat tracking code
 *
 * Copyright (C) 2016 Jens Axboe
 */
#include <linux/kernel.h>
#include <linux/blk-mq.h>

#include "blk-stat.h"
#include "blk-mq.h"

#define BLK_RQ_STAT_BATCH	64

static void blk_stat_flush_batch(struct blk_rq_stat *stat)
{
	const s32 nr_batch = READ_ONCE(stat->nr_batch);
	const s32 nr_samples = READ_ONCE(stat->nr_samples);

	if (!nr_batch)
		return;
	if (!nr_samples)
		stat->mean = div64_s64(stat->batch, nr_batch);
	else {
		stat->mean = div64_s64((stat->mean * nr_samples) +
					stat->batch,
					nr_batch + nr_samples);
	}

	stat->nr_samples += nr_batch;
	stat->nr_batch = stat->batch = 0;
}

static void blk_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src)
{
	blk_stat_flush_batch(src);

	if (!src->nr_samples)
		return;

	dst->min = min(dst->min, src->min);
	dst->max = max(dst->max, src->max);

	if (!dst->nr_samples)
		dst->mean = src->mean;
	else {
		dst->mean = div64_s64((src->mean * src->nr_samples) +
					(dst->mean * dst->nr_samples),
					dst->nr_samples + src->nr_samples);
	}
	dst->nr_samples += src->nr_samples;
}

static void blk_mq_stat_get(struct request_queue *q, struct blk_rq_stat *dst)
{
	struct blk_mq_hw_ctx *hctx;
	struct blk_mq_ctx *ctx;
	uint64_t latest = 0;
	int i, j, nr;

	blk_stat_init(&dst[READ]);
	blk_stat_init(&dst[WRITE]);

	nr = 0;
	do {
		uint64_t newest = 0;

		queue_for_each_hw_ctx(q, hctx, i) {
			hctx_for_each_ctx(hctx, ctx, j) {
				blk_stat_flush_batch(&ctx->stat[READ]);
				blk_stat_flush_batch(&ctx->stat[WRITE]);

				if (!ctx->stat[READ].nr_samples &&
				    !ctx->stat[WRITE].nr_samples)
					continue;
				if (ctx->stat[READ].time > newest)
					newest = ctx->stat[READ].time;
				if (ctx->stat[WRITE].time > newest)
					newest = ctx->stat[WRITE].time;
			}
		}

		/*
		 * No samples
		 */
		if (!newest)
			break;

		if (newest > latest)
			latest = newest;

		queue_for_each_hw_ctx(q, hctx, i) {
			hctx_for_each_ctx(hctx, ctx, j) {
				if (ctx->stat[READ].time == newest) {
					blk_stat_sum(&dst[READ],
						     &ctx->stat[READ]);
					nr++;
				}
				if (ctx->stat[WRITE].time == newest) {
					blk_stat_sum(&dst[WRITE],
						     &ctx->stat[WRITE]);
					nr++;
				}
			}
		}
		/*
		 * If we race on finding an entry, just loop back again.
		 * Should be very rare.
		 */
	} while (!nr);

	dst[READ].time = dst[WRITE].time = latest;
}

void blk_queue_stat_get(struct request_queue *q, struct blk_rq_stat *dst)
{
	if (q->mq_ops)
		blk_mq_stat_get(q, dst);
	else {
		blk_stat_flush_batch(&q->rq_stats[READ]);
		blk_stat_flush_batch(&q->rq_stats[WRITE]);
		memcpy(&dst[READ], &q->rq_stats[READ],
		       sizeof(struct blk_rq_stat));
		memcpy(&dst[WRITE], &q->rq_stats[WRITE],
		       sizeof(struct blk_rq_stat));
	}
}

void blk_hctx_stat_get(struct blk_mq_hw_ctx *hctx, struct blk_rq_stat *dst)
{
	struct blk_mq_ctx *ctx;
	unsigned int i, nr;

	nr = 0;
	do {
		uint64_t newest = 0;

		hctx_for_each_ctx(hctx, ctx, i) {
			blk_stat_flush_batch(&ctx->stat[READ]);
			blk_stat_flush_batch(&ctx->stat[WRITE]);

			if (!ctx->stat[READ].nr_samples &&
			    !ctx->stat[WRITE].nr_samples)
				continue;

			if (ctx->stat[READ].time > newest)
				newest = ctx->stat[READ].time;
			if (ctx->stat[WRITE].time > newest)
				newest = ctx->stat[WRITE].time;
		}

		if (!newest)
			break;

		hctx_for_each_ctx(hctx, ctx, i) {
			if (ctx->stat[READ].time == newest) {
				blk_stat_sum(&dst[READ], &ctx->stat[READ]);
				nr++;
			}
			if (ctx->stat[WRITE].time == newest) {
				blk_stat_sum(&dst[WRITE], &ctx->stat[WRITE]);
				nr++;
			}
		}
		/*
		 * If we race on finding an entry, just loop back again.
		 * Should be very rare, as the window is only updated
		 * occasionally
		 */
	} while (!nr);
}

static void __blk_stat_init(struct blk_rq_stat *stat, s64 time_now)
{
	stat->min = -1ULL;
	stat->max = stat->nr_samples = stat->mean = 0;
	stat->batch = stat->nr_batch = 0;
	stat->time = time_now & BLK_STAT_NSEC_MASK;
}

void blk_stat_init(struct blk_rq_stat *stat)
{
	__blk_stat_init(stat, ktime_to_ns(ktime_get()));
}

static bool __blk_stat_is_current(struct blk_rq_stat *stat, s64 now)
{
	return (now & BLK_STAT_NSEC_MASK) == (stat->time & BLK_STAT_NSEC_MASK);
}

bool blk_stat_is_current(struct blk_rq_stat *stat)
{
	return __blk_stat_is_current(stat, ktime_to_ns(ktime_get()));
}

void blk_stat_add(struct blk_rq_stat *stat, struct request *rq)
{
	s64 now, value;

	now = __blk_stat_time(ktime_to_ns(ktime_get()));
	if (now < blk_stat_time(&rq->issue_stat))
		return;

	if (!__blk_stat_is_current(stat, now))
		__blk_stat_init(stat, now);

	value = now - blk_stat_time(&rq->issue_stat);
	if (value > stat->max)
		stat->max = value;
	if (value < stat->min)
		stat->min = value;

	if (stat->batch + value < stat->batch ||
	    stat->nr_batch + 1 == BLK_RQ_STAT_BATCH)
		blk_stat_flush_batch(stat);

	stat->batch += value;
	stat->nr_batch++;
}

void blk_stat_clear(struct request_queue *q)
{
	if (q->mq_ops) {
		struct blk_mq_hw_ctx *hctx;
		struct blk_mq_ctx *ctx;
		int i, j;

		queue_for_each_hw_ctx(q, hctx, i) {
			hctx_for_each_ctx(hctx, ctx, j) {
				blk_stat_init(&ctx->stat[READ]);
				blk_stat_init(&ctx->stat[WRITE]);
			}
		}
	} else {
		blk_stat_init(&q->rq_stats[READ]);
		blk_stat_init(&q->rq_stats[WRITE]);
	}
}

void blk_stat_set_issue_time(struct blk_issue_stat *stat)
{
	stat->time = (stat->time & BLK_STAT_MASK) |
			(ktime_to_ns(ktime_get()) & BLK_STAT_TIME_MASK);
}

/*
 * Enable stat tracking, return whether it was enabled
 */
bool blk_stat_enable(struct request_queue *q)
{
	if (!test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
		set_bit(QUEUE_FLAG_STATS, &q->queue_flags);
		return false;
	}

	return true;
}