as-iosched.c

/*
 *  Anticipatory & deadline i/o scheduler.
 *
 *  Copyright (C) 2002 Jens Axboe <axboe@kernel.dk>
 *                     Nick Piggin <nickpiggin@yahoo.com.au>
 *
 */
#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>
#include <linux/interrupt.h>

#define REQ_SYNC	1
#define REQ_ASYNC	0

/*
 * See Documentation/block/as-iosched.txt
 */

/*
 * max time before a read is submitted.
 */
#define default_read_expire (HZ / 8)

/*
 * ditto for writes, these limits are not hard, even
 * if the disk is capable of satisfying them.
 */
#define default_write_expire (HZ / 4)

/*
 * read_batch_expire describes how long we will allow a stream of reads to
 * persist before looking to see whether it is time to switch over to writes.
 */
#define default_read_batch_expire (HZ / 2)

/*
 * write_batch_expire describes how long we want a stream of writes to run for.
 * This is not a hard limit, but a target we set for the auto-tuning thingy.
 * See, the problem is: we can send a lot of writes to disk cache / TCQ in
 * a short amount of time...
 */
#define default_write_batch_expire (HZ / 8)

/*
 * max time we may wait to anticipate a read (default around 6ms)
 */
#define default_antic_expire ((HZ / 150) ? HZ / 150 : 1)

/*
 * Keep track of up to 20ms thinktimes. We can go as big as we like here,
 * however huge values tend to interfere and not decay fast enough. A program
 * might be in a non-io phase of operation. Waiting on user input for example,
 * or doing a lengthy computation. A small penalty can be justified there, and
 * will still catch out those processes that constantly have large thinktimes.
 */
#define MAX_THINKTIME (HZ/50UL)

/* Bits in as_io_context.state */
enum as_io_states {
	AS_TASK_RUNNING=0,	/* Process has not exited */
	AS_TASK_IOSTARTED,	/* Process has started some IO */
	AS_TASK_IORUNNING,	/* Process has completed some IO */
};

enum anticipation_status {
	ANTIC_OFF=0,		/* Not anticipating (normal operation)	*/
	ANTIC_WAIT_REQ,		/* The last read has not yet completed  */
	ANTIC_WAIT_NEXT,	/* Currently anticipating a request vs
				   last read (which has completed) */
	ANTIC_FINISHED,		/* Anticipating but have found a candidate
				 * or timed out */
};

struct as_data {
	/*
	 * run time data
	 */

	struct request_queue *q;	/* the "owner" queue */

	/*
	 * requests (as_rq s) are present on both sort_list and fifo_list
	 */
	struct rb_root sort_list[2];
	struct list_head fifo_list[2];

	struct request *next_rq[2];	/* next in sort order */
	sector_t last_sector[2];	/* last REQ_SYNC & REQ_ASYNC sectors */

	unsigned long exit_prob;	/* probability a task will exit while
					   being waited on */
	unsigned long exit_no_coop;	/* probablility an exited task will
					   not be part of a later cooperating
					   request */
	unsigned long new_ttime_total; 	/* mean thinktime on new proc */
	unsigned long new_ttime_mean;
	u64 new_seek_total;		/* mean seek on new proc */
	sector_t new_seek_mean;

	unsigned long current_batch_expires;
	unsigned long last_check_fifo[2];
	int changed_batch;		/* 1: waiting for old batch to end */
	int new_batch;			/* 1: waiting on first read complete */
	int batch_data_dir;		/* current batch REQ_SYNC / REQ_ASYNC */
	int write_batch_count;		/* max # of reqs in a write batch */
	int current_write_count;	/* how many requests left this batch */
	int write_batch_idled;		/* has the write batch gone idle? */

	enum anticipation_status antic_status;
	unsigned long antic_start;	/* jiffies: when it started */
	struct timer_list antic_timer;	/* anticipatory scheduling timer */
	struct work_struct antic_work;	/* Deferred unplugging */
	struct io_context *io_context;	/* Identify the expected process */
	int ioc_finished; /* IO associated with io_context is finished */
	int nr_dispatched;

	/*
	 * settings that change how the i/o scheduler behaves
	 */
	unsigned long fifo_expire[2];
	unsigned long batch_expire[2];
	unsigned long antic_expire;
};

/*
 * per-request data.
 */
enum arq_state {
	AS_RQ_NEW=0,		/* New - not referenced and not on any lists */
	AS_RQ_QUEUED,		/* In the request queue. It belongs to the
				   scheduler */
	AS_RQ_DISPATCHED,	/* On the dispatch list. It belongs to the
				   driver now */
	AS_RQ_PRESCHED,		/* Debug poisoning for requests being used */
	AS_RQ_REMOVED,
	AS_RQ_MERGED,
	AS_RQ_POSTSCHED,	/* when they shouldn't be */
};

#define RQ_IOC(rq)	((struct io_context *) (rq)->elevator_private)
#define RQ_STATE(rq)	((enum arq_state)(rq)->elevator_private2)
#define RQ_SET_STATE(rq, state)	((rq)->elevator_private2 = (void *) state)

static DEFINE_PER_CPU(unsigned long, ioc_count);
static struct completion *ioc_gone;
static DEFINE_SPINLOCK(ioc_gone_lock);

static void as_move_to_dispatch(struct as_data *ad, struct request *rq);
static void as_antic_stop(struct as_data *ad);

/*
 * IO Context helper functions
 */

/* Called to deallocate the as_io_context */
static void free_as_io_context(struct as_io_context *aic)
{
	kfree(aic);
	elv_ioc_count_dec(ioc_count);
	if (ioc_gone) {
		/*
		 * AS scheduler is exiting, grab exit lock and check
		 * the pending io context count. If it hits zero,
		 * complete ioc_gone and set it back to NULL.
		 */
		spin_lock(&ioc_gone_lock);
		if (ioc_gone && !elv_ioc_count_read(ioc_count)) {
			complete(ioc_gone);
			ioc_gone = NULL;
		}
		spin_unlock(&ioc_gone_lock);
	}
}

static void as_trim(struct io_context *ioc)
{
	spin_lock_irq(&ioc->lock);
	if (ioc->aic)
		free_as_io_context(ioc->aic);
	ioc->aic = NULL;
	spin_unlock_irq(&ioc->lock);
}

/* Called when the task exits */
static void exit_as_io_context(struct as_io_context *aic)
{
	WARN_ON(!test_bit(AS_TASK_RUNNING, &aic->state));
	clear_bit(AS_TASK_RUNNING, &aic->state);
}

static struct as_io_context *alloc_as_io_context(void)
{