summaryrefslogtreecommitdiffstats
path: root/block/blk-rq-qos.c
blob: d2f2af8aa10c338e66d60bacece123edb396389d (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
#include "blk-rq-qos.h"

#include "blk-wbt.h"

/*
 * Increment 'v', if 'v' is below 'below'. Returns true if we succeeded,
 * false if 'v' + 1 would be bigger than 'below'.
 */
static bool atomic_inc_below(atomic_t *v, int below)
{
	int cur = atomic_read(v);

	for (;;) {
		int old;

		if (cur >= below)
			return false;
		old = atomic_cmpxchg(v, cur, cur + 1);
		if (old == cur)
			break;
		cur = old;
	}

	return true;
}

bool rq_wait_inc_below(struct rq_wait *rq_wait, int limit)
{
	return atomic_inc_below(&rq_wait->inflight, limit);
}

void rq_qos_cleanup(struct request_queue *q, enum wbt_flags wb_acct)
{
	struct rq_qos *rqos;

	for (rqos = q->rq_qos; rqos; rqos = rqos->next) {
		if (rqos->ops->cleanup)
			rqos->ops->cleanup(rqos, wb_acct);
	}
}

void rq_qos_done(struct request_queue *q, struct request *rq)
{
	struct rq_qos *rqos;

	for (rqos = q->rq_qos; rqos; rqos = rqos->next) {
		if (rqos->ops->done)
			rqos->ops->done(rqos, rq);
	}
}

void rq_qos_issue(struct request_queue *q, struct request *rq)
{
	struct rq_qos *rqos;

	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
		if (rqos->ops->issue)
			rqos->ops->issue(rqos, rq);
	}
}

void rq_qos_requeue(struct request_queue *q, struct request *rq)
{
	struct rq_qos *rqos;

	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
		if (rqos->ops->requeue)
			rqos->ops->requeue(rqos, rq);
	}
}

enum wbt_flags rq_qos_throttle(struct request_queue *q, struct bio *bio,
			       spinlock_t *lock)
{
	struct rq_qos *rqos;
	enum wbt_flags flags = 0;

	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
		if (rqos->ops->throttle)
			flags |= rqos->ops->throttle(rqos, bio, lock);
	}
	return flags;
}

/*
 * Return true, if we can't increase the depth further by scaling
 */
bool rq_depth_calc_max_depth(struct rq_depth *rqd)
{
	unsigned int depth;
	bool ret = false;

	/*
	 * For QD=1 devices, this is a special case. It's important for those
	 * to have one request ready when one completes, so force a depth of
	 * 2 for those devices. On the backend, it'll be a depth of 1 anyway,
	 * since the device can't have more than that in flight. If we're
	 * scaling down, then keep a setting of 1/1/1.
	 */
	if (rqd->queue_depth == 1) {
		if (rqd->scale_step > 0)
			rqd->max_depth = 1;
		else {
			rqd->max_depth = 2;
			ret = true;
		}
	} else {
		/*
		 * scale_step == 0 is our default state. If we have suffered
		 * latency spikes, step will be > 0, and we shrink the
		 * allowed write depths. If step is < 0, we're only doing
		 * writes, and we allow a temporarily higher depth to
		 * increase performance.
		 */
		depth = min_t(unsigned int, rqd->default_depth,
			      rqd->queue_depth);
		if (rqd->scale_step > 0)
			depth = 1 + ((depth - 1) >> min(31, rqd->scale_step));
		else if (rqd->scale_step < 0) {
			unsigned int maxd = 3 * rqd->queue_depth / 4;

			depth = 1 + ((depth - 1) << -rqd->scale_step);
			if (depth > maxd) {
				depth = maxd;
				ret = true;
			}
		}

		rqd->max_depth = depth;
	}

	return ret;
}

void rq_depth_scale_up(struct rq_depth *rqd)
{
	/*
	 * Hit max in previous round, stop here
	 */
	if (rqd->scaled_max)
		return;

	rqd->scale_step--;

	rqd->scaled_max = rq_depth_calc_max_depth(rqd);
}

/*
 * Scale rwb down. If 'hard_throttle' is set, do it quicker, since we
 * had a latency violation.
 */
void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle)
{
	/*
	 * Stop scaling down when we've hit the limit. This also prevents
	 * ->scale_step from going to crazy values, if the device can't
	 * keep up.
	 */
	if (rqd->max_depth == 1)
		return;

	if (rqd->scale_step < 0 && hard_throttle)
		rqd->scale_step = 0;
	else
		rqd->scale_step++;

	rqd->scaled_max = false;
	rq_depth_calc_max_depth(rqd);
}

void rq_qos_exit(struct request_queue *q)
{
	while (q->rq_qos) {
		struct rq_qos *rqos = q->rq_qos;
		q->rq_qos = rqos->next;
		rqos->ops->exit(rqos);
	}
}