aboutsummaryrefslogtreecommitdiff
path: root/block/deadline-iosched.c
blob: 8300ba1f15a09841ed0beff8a1085a5af3d5c3fc (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
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
/*
 *  Deadline i/o scheduler.
 *
 *  Copyright (C) 2002 Jens Axboe <axboe@suse.de>
 */
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/blkdev.h>
#include <linux/elevator.h>
#include <linux/bio.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/compiler.h>
#include <linux/rbtree.h>

/*
 * See Documentation/block/deadline-iosched.txt
 */
static const int read_expire = HZ / 2;  /* max time before a read is submitted. */
static const int write_expire = 5 * HZ; /* ditto for writes, these limits are SOFT! */
static const int writes_starved = 2;    /* max times reads can starve a write */
static const int fifo_batch = 16;       /* # of sequential requests treated as one
				     by the above parameters. For throughput. */

struct deadline_data {
	/*
	 * run time data
	 */

	/*
	 * requests (deadline_rq s) are present on both sort_list and fifo_list
	 */
	struct rb_root sort_list[2];	
	struct list_head fifo_list[2];
	
	/*
	 * next in sort order. read, write or both are NULL
	 */
	struct deadline_rq *next_drq[2];
	unsigned int batching;		/* number of sequential requests made */
	sector_t last_sector;		/* head position */
	unsigned int starved;		/* times reads have starved writes */

	/*
	 * settings that change how the i/o scheduler behaves
	 */
	int fifo_expire[2];
	int fifo_batch;
	int writes_starved;
	int front_merges;

	mempool_t *drq_pool;
};

/*
 * pre-request data.
 */
struct deadline_rq {
	struct request *request;

	/*
	 * expire fifo
	 */
	struct list_head fifo;
	unsigned long expires;
};

static void deadline_move_request(struct deadline_data *dd, struct deadline_rq *drq);

static kmem_cache_t *drq_pool;

#define RQ_DATA(rq)	((struct deadline_rq *) (rq)->elevator_private)

#define RQ_RB_ROOT(dd, rq)	(&(dd)->sort_list[rq_data_dir((rq))])
#define DRQ_RB_ROOT(dd, drq)	RQ_RB_ROOT((drq)->request)

static void
deadline_add_drq_rb(struct deadline_data *dd, struct request *rq)
{
	struct rb_root *root = RQ_RB_ROOT(dd, rq);
	struct request *__alias;

retry:
	__alias = elv_rb_add(root, rq);
	if (unlikely(__alias)) {
		deadline_move_request(dd, RQ_DATA(__alias));
		goto retry;
	}
}

static inline void
deadline_del_drq_rb(struct deadline_data *dd, struct deadline_rq *drq)
{
	struct request *rq = drq->request;
	const int data_dir = rq_data_dir(rq);

	if (dd->next_drq[data_dir] == drq) {
		struct rb_node *rbnext = rb_next(&rq->rb_node);

		dd->next_drq[data_dir] = NULL;
		if (rbnext)
			dd->next_drq[data_dir] = RQ_DATA(rb_entry_rq(rbnext));
	}

	elv_rb_del(RQ_RB_ROOT(dd, rq), rq);
}

/*
 * add drq to rbtree and fifo
 */
static void
deadline_add_request(struct request_queue *q, struct request *rq)
{
	struct deadline_data *dd = q->elevator->elevator_data;
	struct deadline_rq *drq = RQ_DATA(rq);
	const int data_dir = rq_data_dir(drq->request);

	deadline_add_drq_rb(dd, rq);

	/*
	 * set expire time (only used for reads) and add to fifo list
	 */
	drq->expires = jiffies + dd->fifo_expire[data_dir];
	list_add_tail(&drq->fifo, &dd->fifo_list[data_dir]);
}

/*
 * remove rq from rbtree and fifo.
 */
static void deadline_remove_request(request_queue_t *q, struct request *rq)
{
	struct deadline_rq *drq = RQ_DATA(rq);
	struct deadline_data *dd = q->elevator->elevator_data;

	list_del_init(&drq->fifo);
	deadline_del_drq_rb(dd, drq);
}

static int
deadline_merge(request_queue_t *q, struct request **req, struct bio *bio)
{
	struct deadline_data *dd = q->elevator->elevator_data;
	struct request *__rq;
	int ret;

	/*
	 * check for front merge
	 */
	if (dd->front_merges) {
		sector_t sector = bio->bi_sector + bio_sectors(bio);

		__rq = elv_rb_find(&dd->sort_list[bio_data_dir(bio)], sector);
		if (__rq) {
			BUG_ON(sector != __rq->sector);

			if (elv_rq_merge_ok(__rq, bio)) {
				ret = ELEVATOR_FRONT_MERGE;
				goto out;
			}
		}
	}

	return ELEVATOR_NO_MERGE;
out:
	*req = __rq;
	return ret;
}

static void deadline_merged_request(request_queue_t *q, struct request *req,
				    int type)
{
	struct deadline_data *dd = q->elevator->elevator_data;

	/*
	 * if the merge was a front merge, we need to reposition request
	 */
	if (type == ELEVATOR_FRONT_MERGE) {
		elv_rb_del(RQ_RB_ROOT(dd, req), req);
		deadline_add_drq_rb(dd, req);
	}
}

static void
deadline_merged_requests(request_queue_t *q, struct request *req,
			 struct request *next)
{
	struct deadline_rq *drq = RQ_DATA(req);
	struct deadline_rq *dnext = RQ_DATA(next);

	BUG_ON(!drq);
	BUG_ON(!dnext);

	/*
	 * if dnext expires before drq, assign its expire time to drq
	 * and move into dnext position (dnext will be deleted) in fifo
	 */
	if (!list_empty(&drq->fifo) && !list_empty(&dnext->fifo)) {
		if (time_before(dnext->expires, drq->expires)) {
			list_move(&drq->fifo, &dnext->fifo);
			drq->expires = dnext->expires;
		}
	}

	/*
	 * kill knowledge of next, this one is a goner
	 */
	deadline_remove_request(q, next);
}

/*
 * move request from sort list to dispatch queue.
 */
static inline void
deadline_move_to_dispatch(struct deadline_data *dd, struct deadline_rq *drq)
{
	request_queue_t *q = drq->request->q;

	deadline_remove_request(q, drq->request);
	elv_dispatch_add_tail(q, drq->request);
}

/*
 * move an entry to dispatch queue
 */
static void
deadline_move_request(struct deadline_data *dd, struct deadline_rq *drq)
{
	struct request *rq = drq->request;
	const int data_dir = rq_data_dir(rq);
	struct rb_node *rbnext = rb_next(&rq->rb_node);

	dd->next_drq[READ] = NULL;
	dd->next_drq[WRITE] = NULL;

	if (rbnext)
		dd->next_drq[data_dir] = RQ_DATA(rb_entry_rq(rbnext));
	
	dd->last_sector = drq->request->sector + drq->request->nr_sectors;

	/*
	 * take it off the sort and fifo list, move
	 * to dispatch queue
	 */
	deadline_move_to_dispatch(dd, drq);
}

#define list_entry_fifo(ptr)	list_entry((ptr), struct deadline_rq, fifo)

/*
 * deadline_check_fifo returns 0 if there are no expired reads on the fifo,
 * 1 otherwise. Requires !list_empty(&dd->fifo_list[data_dir])
 */
static inline int deadline_check_fifo(struct deadline_data *dd, int ddir)
{
	struct deadline_rq *drq = list_entry_fifo(dd->fifo_list[ddir].next);

	/*
	 * drq is expired!
	 */
	if (time_after(jiffies, drq->expires))
		return 1;

	return 0;
}

/*
 * deadline_dispatch_requests selects the best request according to
 * read/write expire, fifo_batch, etc
 */
static int deadline_dispatch_requests(request_queue_t *q, int force)
{
	struct deadline_data *dd = q->elevator->elevator_data;
	const int reads = !list_empty(&dd->fifo_list[READ]);
	const int writes = !list_empty(&dd->fifo_list[WRITE]);
	struct deadline_rq *drq;
	int data_dir;

	/*
	 * batches are currently reads XOR writes
	 */
	if (dd->next_drq[WRITE])
		drq = dd->next_drq[WRITE];
	else
		drq = dd->next_drq[READ];

	if (drq) {
		/* we have a "next request" */
		
		if (dd->last_sector != drq->request->sector)
			/* end the batch on a non sequential request */
			dd->batching += dd->fifo_batch;
		
		if (dd->batching < dd->fifo_batch)
			/* we are still entitled to batch */
			goto dispatch_request;
	}

	/*
	 * at this point we are not running a batch. select the appropriate
	 * data direction (read / write)
	 */

	if (reads) {
		BUG_ON(RB_EMPTY_ROOT(&dd->sort_list[READ]));

		if (writes && (dd->starved++ >= dd->writes_starved))
			goto dispatch_writes;

		data_dir = READ;

		goto dispatch_find_request;
	}

	/*
	 * there are either no reads or writes have been starved
	 */

	if (writes) {
dispatch_writes:
		BUG_ON(RB_EMPTY_ROOT(&dd->sort_list[WRITE]));

		dd->starved = 0;

		data_dir = WRITE;

		goto dispatch_find_request;
	}

	return 0;

dispatch_find_request:
	/*
	 * we are not running a batch, find best request for selected data_dir
	 */
	if (deadline_check_fifo(dd, data_dir)) {
		/* An expired request exists - satisfy it */
		dd->batching = 0;
		drq = list_entry_fifo(dd->fifo_list[data_dir].next);
		
	} else if (dd->next_drq[data_dir]) {
		/*
		 * The last req was the same dir and we have a next request in
		 * sort order. No expired requests so continue on from here.
		 */
		drq = dd->next_drq[data_dir];
	} else {
		struct rb_node *n;

		/*
		 * The last req was the other direction or we have run out of
		 * higher-sectored requests. Go back to the lowest sectored
		 * request (1 way elevator) and start a new batch.
		 */
		dd->batching = 0;
		n = rb_first(&dd->sort_list[data_dir]);
		if (n)
			drq = RQ_DATA(rb_entry_rq(n));
	}

dispatch_request:
	/*
	 * drq is the selected appropriate request.
	 */
	dd->batching++;
	deadline_move_request(dd, drq);

	return 1;
}

static int deadline_queue_empty(request_queue_t *q)
{
	struct deadline_data *dd = q->elevator->elevator_data;

	return list_empty(&dd->fifo_list[WRITE])
		&& list_empty(&dd->fifo_list[READ]);
}

static void deadline_exit_queue(elevator_t *e)
{
	struct deadline_data *dd = e->elevator_data;

	BUG_ON(!list_empty(&dd->fifo_list[READ]));
	BUG_ON(!list_empty(&dd->fifo_list[WRITE]));

	mempool_destroy(dd->drq_pool);
	kfree(dd);
}

/*
 * initialize elevator private data (deadline_data), and alloc a drq for
 * each request on the free lists
 */
static void *deadline_init_queue(request_queue_t *q, elevator_t *e)
{
	struct deadline_data *dd;

	if (!drq_pool)
		return NULL;

	dd = kmalloc_node(sizeof(*dd), GFP_KERNEL, q->node);
	if (!dd)
		return NULL;
	memset(dd, 0, sizeof(*dd));

	dd->drq_pool = mempool_create_node(BLKDEV_MIN_RQ, mempool_alloc_slab,
					mempool_free_slab, drq_pool, q->node);
	if (!dd->drq_pool) {
		kfree(dd);
		return NULL;
	}

	INIT_LIST_HEAD(&dd->fifo_list[READ]);
	INIT_LIST_HEAD(&dd->fifo_list[WRITE]);
	dd->sort_list[READ] = RB_ROOT;
	dd->sort_list[WRITE] = RB_ROOT;
	dd->fifo_expire[READ] = read_expire;
	dd->fifo_expire[WRITE] = write_expire;
	dd->writes_starved = writes_starved;
	dd->front_merges = 1;
	dd->fifo_batch = fifo_batch;
	return dd;
}

static void deadline_put_request(request_queue_t *q, struct request *rq)
{
	struct deadline_data *dd = q->elevator->elevator_data;
	struct deadline_rq *drq = RQ_DATA(rq);

	mempool_free(drq, dd->drq_pool);
	rq->elevator_private = NULL;
}

static int
deadline_set_request(request_queue_t *q, struct request *rq, struct bio *bio,
		     gfp_t gfp_mask)
{
	struct deadline_data *dd = q->elevator->elevator_data;
	struct deadline_rq *drq;

	drq = mempool_alloc(dd->drq_pool, gfp_mask);
	if (drq) {
		memset(drq, 0, sizeof(*drq));
		drq->request = rq;

		INIT_LIST_HEAD(&drq->fifo);

		rq->elevator_private = drq;
		return 0;
	}

	return 1;
}

/*
 * sysfs parts below
 */

static ssize_t
deadline_var_show(int var, char *page)
{
	return sprintf(page, "%d\n", var);
}

static ssize_t
deadline_var_store(int *var, const char *page, size_t count)
{
	char *p = (char *) page;

	*var = simple_strtol(p, &p, 10);
	return count;
}

#define SHOW_FUNCTION(__FUNC, __VAR, __CONV)				\
static ssize_t __FUNC(elevator_t *e, char *page)			\
{									\
	struct deadline_data *dd = e->elevator_data;			\
	int __data = __VAR;						\
	if (__CONV)							\
		__data = jiffies_to_msecs(__data);			\
	return deadline_var_show(__data, (page));			\
}
SHOW_FUNCTION(deadline_read_expire_show, dd->fifo_expire[READ], 1);
SHOW_FUNCTION(deadline_write_expire_show, dd->fifo_expire[WRITE], 1);
SHOW_FUNCTION(deadline_writes_starved_show, dd->writes_starved, 0);
SHOW_FUNCTION(deadline_front_merges_show, dd->front_merges, 0);
SHOW_FUNCTION(deadline_fifo_batch_show, dd->fifo_batch, 0);
#undef SHOW_FUNCTION

#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
static ssize_t __FUNC(elevator_t *e, const char *page, size_t count)	\
{									\
	struct deadline_data *dd = e->elevator_data;			\
	int __data;							\
	int ret = deadline_var_store(&__data, (page), count);		\
	if (__data < (MIN))						\
		__data = (MIN);						\
	else if (__data > (MAX))					\
		__data = (MAX);						\
	if (__CONV)							\
		*(__PTR) = msecs_to_jiffies(__data);			\
	else								\
		*(__PTR) = __data;					\
	return ret;							\
}
STORE_FUNCTION(deadline_read_expire_store, &dd->fifo_expire[READ], 0, INT_MAX, 1);
STORE_FUNCTION(deadline_write_expire_store, &dd->fifo_expire[WRITE], 0, INT_MAX, 1);
STORE_FUNCTION(deadline_writes_starved_store, &dd->writes_starved, INT_MIN, INT_MAX, 0);
STORE_FUNCTION(deadline_front_merges_store, &dd->front_merges, 0, 1, 0);
STORE_FUNCTION(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX, 0);
#undef STORE_FUNCTION

#define DD_ATTR(name) \
	__ATTR(name, S_IRUGO|S_IWUSR, deadline_##name##_show, \
				      deadline_##name##_store)

static struct elv_fs_entry deadline_attrs[] = {
	DD_ATTR(read_expire),
	DD_ATTR(write_expire),
	DD_ATTR(writes_starved),
	DD_ATTR(front_merges),
	DD_ATTR(fifo_batch),
	__ATTR_NULL
};

static struct elevator_type iosched_deadline = {
	.ops = {
		.elevator_merge_fn = 		deadline_merge,
		.elevator_merged_fn =		deadline_merged_request,
		.elevator_merge_req_fn =	deadline_merged_requests,
		.elevator_dispatch_fn =		deadline_dispatch_requests,
		.elevator_add_req_fn =		deadline_add_request,
		.elevator_queue_empty_fn =	deadline_queue_empty,
		.elevator_former_req_fn =	elv_rb_former_request,
		.elevator_latter_req_fn =	elv_rb_latter_request,
		.elevator_set_req_fn =		deadline_set_request,
		.elevator_put_req_fn = 		deadline_put_request,
		.elevator_init_fn =		deadline_init_queue,
		.elevator_exit_fn =		deadline_exit_queue,
	},

	.elevator_attrs = deadline_attrs,
	.elevator_name = "deadline",
	.elevator_owner = THIS_MODULE,
};

static int __init deadline_init(void)
{
	int ret;

	drq_pool = kmem_cache_create("deadline_drq", sizeof(struct deadline_rq),
				     0, 0, NULL, NULL);

	if (!drq_pool)
		return -ENOMEM;

	ret = elv_register(&iosched_deadline);
	if (ret)
		kmem_cache_destroy(drq_pool);

	return ret;
}

static void __exit deadline_exit(void)
{
	kmem_cache_destroy(drq_pool);
	elv_unregister(&iosched_deadline);
}

module_init(deadline_init);
module_exit(deadline_exit);

MODULE_AUTHOR("Jens Axboe");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("deadline IO scheduler");