raid1.c

来自「linux 内核源代码」· C语言 代码 · 共 2,200 行 · 第 1/4 页

/*
 * raid1.c : Multiple Devices driver for Linux
 *
 * Copyright (C) 1999, 2000, 2001 Ingo Molnar, Red Hat
 *
 * Copyright (C) 1996, 1997, 1998 Ingo Molnar, Miguel de Icaza, Gadi Oxman
 *
 * RAID-1 management functions.
 *
 * Better read-balancing code written by Mika Kuoppala <[e-mail]>, 2000
 *
 * Fixes to reconstruction by Jakob Østergaard" <[e-mail]>
 * Various fixes by Neil Brown <[e-mail]>
 *
 * Changes by Peter T. Breuer <[e-mail]> 31/1/2003 to support
 * bitmapped intelligence in resync:
 *
 *      - bitmap marked during normal i/o
 *      - bitmap used to skip nondirty blocks during sync
 *
 * Additions to bitmap code, (C) 2003-2004 Paul Clements, SteelEye Technology:
 * - persistent bitmap code
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2, or (at your option)
 * any later version.
 *
 * You should have received a copy of the GNU General Public License
 * (for example /usr/src/linux/COPYING); if not, write to the Free
 * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */

#include "dm-bio-list.h"
#include <linux/raid/raid1.h>
#include <linux/raid/bitmap.h>

#define DEBUG 0
#if DEBUG
#define PRINTK(x...) printk(x)
#else
#define PRINTK(x...)
#endif

/*
 * Number of guaranteed r1bios in case of extreme VM load:
 */
#define	NR_RAID1_BIOS 256


static void unplug_slaves(mddev_t *mddev);

static void allow_barrier(conf_t *conf);
static void lower_barrier(conf_t *conf);

static void * r1bio_pool_alloc(gfp_t gfp_flags, void *data)
{
	struct pool_info *pi = data;
	r1bio_t *r1_bio;
	int size = offsetof(r1bio_t, bios[pi->raid_disks]);

	/* allocate a r1bio with room for raid_disks entries in the bios array */
	r1_bio = kzalloc(size, gfp_flags);
	if (!r1_bio)
		unplug_slaves(pi->mddev);

	return r1_bio;
}

static void r1bio_pool_free(void *r1_bio, void *data)
{
	kfree(r1_bio);
}

#define RESYNC_BLOCK_SIZE (64*1024)
//#define RESYNC_BLOCK_SIZE PAGE_SIZE
#define RESYNC_SECTORS (RESYNC_BLOCK_SIZE >> 9)
#define RESYNC_PAGES ((RESYNC_BLOCK_SIZE + PAGE_SIZE-1) / PAGE_SIZE)
#define RESYNC_WINDOW (2048*1024)

static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
{
	struct pool_info *pi = data;
	struct page *page;
	r1bio_t *r1_bio;
	struct bio *bio;
	int i, j;

	r1_bio = r1bio_pool_alloc(gfp_flags, pi);
	if (!r1_bio) {
		unplug_slaves(pi->mddev);
		return NULL;
	}

	/*
	 * Allocate bios : 1 for reading, n-1 for writing
	 */
	for (j = pi->raid_disks ; j-- ; ) {
		bio = bio_alloc(gfp_flags, RESYNC_PAGES);
		if (!bio)
			goto out_free_bio;
		r1_bio->bios[j] = bio;
	}
	/*
	 * Allocate RESYNC_PAGES data pages and attach them to
	 * the first bio.
	 * If this is a user-requested check/repair, allocate
	 * RESYNC_PAGES for each bio.
	 */
	if (test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery))
		j = pi->raid_disks;
	else
		j = 1;
	while(j--) {
		bio = r1_bio->bios[j];
		for (i = 0; i < RESYNC_PAGES; i++) {
			page = alloc_page(gfp_flags);
			if (unlikely(!page))
				goto out_free_pages;

			bio->bi_io_vec[i].bv_page = page;
		}
	}
	/* If not user-requests, copy the page pointers to all bios */
	if (!test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery)) {
		for (i=0; i<RESYNC_PAGES ; i++)
			for (j=1; j<pi->raid_disks; j++)
				r1_bio->bios[j]->bi_io_vec[i].bv_page =
					r1_bio->bios[0]->bi_io_vec[i].bv_page;
	}

	r1_bio->master_bio = NULL;

	return r1_bio;

out_free_pages:
	for (i=0; i < RESYNC_PAGES ; i++)
		for (j=0 ; j < pi->raid_disks; j++)
			safe_put_page(r1_bio->bios[j]->bi_io_vec[i].bv_page);
	j = -1;
out_free_bio:
	while ( ++j < pi->raid_disks )
		bio_put(r1_bio->bios[j]);
	r1bio_pool_free(r1_bio, data);
	return NULL;
}

static void r1buf_pool_free(void *__r1_bio, void *data)
{
	struct pool_info *pi = data;
	int i,j;
	r1bio_t *r1bio = __r1_bio;

	for (i = 0; i < RESYNC_PAGES; i++)
		for (j = pi->raid_disks; j-- ;) {
			if (j == 0 ||
			    r1bio->bios[j]->bi_io_vec[i].bv_page !=
			    r1bio->bios[0]->bi_io_vec[i].bv_page)
				safe_put_page(r1bio->bios[j]->bi_io_vec[i].bv_page);
		}
	for (i=0 ; i < pi->raid_disks; i++)
		bio_put(r1bio->bios[i]);

	r1bio_pool_free(r1bio, data);
}

static void put_all_bios(conf_t *conf, r1bio_t *r1_bio)
{
	int i;

	for (i = 0; i < conf->raid_disks; i++) {
		struct bio **bio = r1_bio->bios + i;
		if (*bio && *bio != IO_BLOCKED)
			bio_put(*bio);
		*bio = NULL;
	}
}

static void free_r1bio(r1bio_t *r1_bio)
{
	conf_t *conf = mddev_to_conf(r1_bio->mddev);

	/*
	 * Wake up any possible resync thread that waits for the device
	 * to go idle.
	 */
	allow_barrier(conf);

	put_all_bios(conf, r1_bio);
	mempool_free(r1_bio, conf->r1bio_pool);
}

static void put_buf(r1bio_t *r1_bio)
{
	conf_t *conf = mddev_to_conf(r1_bio->mddev);
	int i;

	for (i=0; i<conf->raid_disks; i++) {
		struct bio *bio = r1_bio->bios[i];
		if (bio->bi_end_io)
			rdev_dec_pending(conf->mirrors[i].rdev, r1_bio->mddev);
	}

	mempool_free(r1_bio, conf->r1buf_pool);

	lower_barrier(conf);
}

static void reschedule_retry(r1bio_t *r1_bio)
{
	unsigned long flags;
	mddev_t *mddev = r1_bio->mddev;
	conf_t *conf = mddev_to_conf(mddev);

	spin_lock_irqsave(&conf->device_lock, flags);
	list_add(&r1_bio->retry_list, &conf->retry_list);
	conf->nr_queued ++;
	spin_unlock_irqrestore(&conf->device_lock, flags);

	wake_up(&conf->wait_barrier);
	md_wakeup_thread(mddev->thread);
}

/*
 * raid_end_bio_io() is called when we have finished servicing a mirrored
 * operation and are ready to return a success/failure code to the buffer
 * cache layer.
 */
static void raid_end_bio_io(r1bio_t *r1_bio)
{
	struct bio *bio = r1_bio->master_bio;

	/* if nobody has done the final endio yet, do it now */
	if (!test_and_set_bit(R1BIO_Returned, &r1_bio->state)) {
		PRINTK(KERN_DEBUG "raid1: sync end %s on sectors %llu-%llu\n",
			(bio_data_dir(bio) == WRITE) ? "write" : "read",
			(unsigned long long) bio->bi_sector,
			(unsigned long long) bio->bi_sector +
				(bio->bi_size >> 9) - 1);

		bio_endio(bio,
			test_bit(R1BIO_Uptodate, &r1_bio->state) ? 0 : -EIO);
	}
	free_r1bio(r1_bio);
}

/*
 * Update disk head position estimator based on IRQ completion info.
 */
static inline void update_head_pos(int disk, r1bio_t *r1_bio)
{
	conf_t *conf = mddev_to_conf(r1_bio->mddev);

	conf->mirrors[disk].head_position =
		r1_bio->sector + (r1_bio->sectors);
}

static void raid1_end_read_request(struct bio *bio, int error)
{
	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
	r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
	int mirror;
	conf_t *conf = mddev_to_conf(r1_bio->mddev);

	mirror = r1_bio->read_disk;
	/*
	 * this branch is our 'one mirror IO has finished' event handler:
	 */
	update_head_pos(mirror, r1_bio);

	if (uptodate)
		set_bit(R1BIO_Uptodate, &r1_bio->state);
	else {
		/* If all other devices have failed, we want to return
		 * the error upwards rather than fail the last device.
		 * Here we redefine "uptodate" to mean "Don't want to retry"
		 */
		unsigned long flags;
		spin_lock_irqsave(&conf->device_lock, flags);
		if (r1_bio->mddev->degraded == conf->raid_disks ||
		    (r1_bio->mddev->degraded == conf->raid_disks-1 &&
		     !test_bit(Faulty, &conf->mirrors[mirror].rdev->flags)))
			uptodate = 1;
		spin_unlock_irqrestore(&conf->device_lock, flags);
	}

	if (uptodate)
		raid_end_bio_io(r1_bio);
	else {
		/*
		 * oops, read error:
		 */
		char b[BDEVNAME_SIZE];
		if (printk_ratelimit())
			printk(KERN_ERR "raid1: %s: rescheduling sector %llu\n",
			       bdevname(conf->mirrors[mirror].rdev->bdev,b), (unsigned long long)r1_bio->sector);
		reschedule_retry(r1_bio);
	}

	rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev);
}

static void raid1_end_write_request(struct bio *bio, int error)
{
	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
	r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
	int mirror, behind = test_bit(R1BIO_BehindIO, &r1_bio->state);
	conf_t *conf = mddev_to_conf(r1_bio->mddev);
	struct bio *to_put = NULL;


	for (mirror = 0; mirror < conf->raid_disks; mirror++)
		if (r1_bio->bios[mirror] == bio)
			break;

	if (error == -EOPNOTSUPP && test_bit(R1BIO_Barrier, &r1_bio->state)) {
		set_bit(BarriersNotsupp, &conf->mirrors[mirror].rdev->flags);
		set_bit(R1BIO_BarrierRetry, &r1_bio->state);
		r1_bio->mddev->barriers_work = 0;
		/* Don't rdev_dec_pending in this branch - keep it for the retry */
	} else {
		/*
		 * this branch is our 'one mirror IO has finished' event handler:
		 */
		r1_bio->bios[mirror] = NULL;
		to_put = bio;
		if (!uptodate) {
			md_error(r1_bio->mddev, conf->mirrors[mirror].rdev);
			/* an I/O failed, we can't clear the bitmap */
			set_bit(R1BIO_Degraded, &r1_bio->state);
		} else
			/*
			 * Set R1BIO_Uptodate in our master bio, so that
			 * we will return a good error code for to the higher
			 * levels even if IO on some other mirrored buffer fails.
			 *
			 * The 'master' represents the composite IO operation to
			 * user-side. So if something waits for IO, then it will
			 * wait for the 'master' bio.
			 */
			set_bit(R1BIO_Uptodate, &r1_bio->state);

		update_head_pos(mirror, r1_bio);

		if (behind) {
			if (test_bit(WriteMostly, &conf->mirrors[mirror].rdev->flags))
				atomic_dec(&r1_bio->behind_remaining);

			/* In behind mode, we ACK the master bio once the I/O has safely
			 * reached all non-writemostly disks. Setting the Returned bit
			 * ensures that this gets done only once -- we don't ever want to
			 * return -EIO here, instead we'll wait */

			if (atomic_read(&r1_bio->behind_remaining) >= (atomic_read(&r1_bio->remaining)-1) &&
			    test_bit(R1BIO_Uptodate, &r1_bio->state)) {
				/* Maybe we can return now */
				if (!test_and_set_bit(R1BIO_Returned, &r1_bio->state)) {
					struct bio *mbio = r1_bio->master_bio;
					PRINTK(KERN_DEBUG "raid1: behind end write sectors %llu-%llu\n",
					       (unsigned long long) mbio->bi_sector,
					       (unsigned long long) mbio->bi_sector +
					       (mbio->bi_size >> 9) - 1);
					bio_endio(mbio, 0);
				}
			}
		}
		rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev);
	}
	/*
	 *
	 * Let's see if all mirrored write operations have finished
	 * already.
	 */
	if (atomic_dec_and_test(&r1_bio->remaining)) {
		if (test_bit(R1BIO_BarrierRetry, &r1_bio->state))
			reschedule_retry(r1_bio);
		else {
			/* it really is the end of this request */
			if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
				/* free extra copy of the data pages */
				int i = bio->bi_vcnt;
				while (i--)
					safe_put_page(bio->bi_io_vec[i].bv_page);
			}
			/* clear the bitmap if all writes complete successfully */
			bitmap_endwrite(r1_bio->mddev->bitmap, r1_bio->sector,
					r1_bio->sectors,
					!test_bit(R1BIO_Degraded, &r1_bio->state),
					behind);
			md_write_end(r1_bio->mddev);
			raid_end_bio_io(r1_bio);
		}
	}

	if (to_put)
		bio_put(to_put);
}


/*
 * This routine returns the disk from which the requested read should
 * be done. There is a per-array 'next expected sequential IO' sector
 * number - if this matches on the next IO then we use the last disk.
 * There is also a per-disk 'last know head position' sector that is
 * maintained from IRQ contexts, both the normal and the resync IO
 * completion handlers update this position correctly. If there is no
 * perfect sequential match then we pick the disk whose head is closest.
 *
 * If there are 2 mirrors in the same 2 devices, performance degrades
 * because position is mirror, not device based.
 *
 * The rdev for the device selected will have nr_pending incremented.
 */
static int read_balance(conf_t *conf, r1bio_t *r1_bio)
{
	const unsigned long this_sector = r1_bio->sector;
	int new_disk = conf->last_used, disk = new_disk;
	int wonly_disk = -1;
	const int sectors = r1_bio->sectors;
	sector_t new_distance, current_distance;
	mdk_rdev_t *rdev;

	rcu_read_lock();
	/*
	 * Check if we can balance. We can balance on the whole
	 * device if no resync is going on, or below the resync window.
	 * We take the first readable disk when above the resync window.
	 */
 retry:
	if (conf->mddev->recovery_cp < MaxSector &&
	    (this_sector + sectors >= conf->next_resync)) {
		/* Choose the first operation device, for consistancy */
		new_disk = 0;

		for (rdev = rcu_dereference(conf->mirrors[new_disk].rdev);
		     r1_bio->bios[new_disk] == IO_BLOCKED ||
		     !rdev || !test_bit(In_sync, &rdev->flags)
			     || test_bit(WriteMostly, &rdev->flags);
		     rdev = rcu_dereference(conf->mirrors[++new_disk].rdev)) {

			if (rdev && test_bit(In_sync, &rdev->flags) &&
				r1_bio->bios[new_disk] != IO_BLOCKED)
				wonly_disk = new_disk;

			if (new_disk == conf->raid_disks - 1) {
				new_disk = wonly_disk;
				break;
			}
		}
		goto rb_out;
	}


	/* make sure the disk is operational */
	for (rdev = rcu_dereference(conf->mirrors[new_disk].rdev);
	     r1_bio->bios[new_disk] == IO_BLOCKED ||
	     !rdev || !test_bit(In_sync, &rdev->flags) ||
		     test_bit(WriteMostly, &rdev->flags);
	     rdev = rcu_dereference(conf->mirrors[new_disk].rdev)) {

		if (rdev && test_bit(In_sync, &rdev->flags) &&
		    r1_bio->bios[new_disk] != IO_BLOCKED)
			wonly_disk = new_disk;

		if (new_disk <= 0)
			new_disk = conf->raid_disks;
		new_disk--;
		if (new_disk == disk) {
			new_disk = wonly_disk;
			break;
		}
	}

	if (new_disk < 0)
		goto rb_out;

	disk = new_disk;
	/* now disk == new_disk == starting point for search */

	/*
	 * Don't change to another disk for sequential reads:
	 */
	if (conf->next_seq_sect == this_sector)
		goto rb_out;
	if (this_sector == conf->mirrors[new_disk].head_position)
		goto rb_out;

	current_distance = abs(this_sector - conf->mirrors[disk].head_position);

	/* Find the disk whose head is closest */

	do {
		if (disk <= 0)
			disk = conf->raid_disks;
		disk--;

		rdev = rcu_dereference(conf->mirrors[disk].rdev);

		if (!rdev || r1_bio->bios[disk] == IO_BLOCKED ||
		    !test_bit(In_sync, &rdev->flags) ||
		    test_bit(WriteMostly, &rdev->flags))
			continue;

		if (!atomic_read(&rdev->nr_pending)) {
			new_disk = disk;
			break;
		}
		new_distance = abs(this_sector - conf->mirrors[disk].head_position);
		if (new_distance < current_distance) {
			current_distance = new_distance;
			new_disk = disk;
		}
	} while (disk != conf->last_used);

 rb_out:


	if (new_disk >= 0) {
		rdev = rcu_dereference(conf->mirrors[new_disk].rdev);
		if (!rdev)
			goto retry;
		atomic_inc(&rdev->nr_pending);
		if (!test_bit(In_sync, &rdev->flags)) {
			/* cannot risk returning a device that failed
			 * before we inc'ed nr_pending
			 */
			rdev_dec_pending(rdev, conf->mddev);
			goto retry;
		}
		conf->next_seq_sect = this_sector + sectors;
		conf->last_used = new_disk;
	}
	rcu_read_unlock();

	return new_disk;
}

static void unplug_slaves(mddev_t *mddev)
{
	conf_t *conf = mddev_to_conf(mddev);
	int i;

	rcu_read_lock();
	for (i=0; i<mddev->raid_disks; i++) {
		mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
		if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) {
			struct request_queue *r_queue = bdev_get_queue(rdev->bdev);

			atomic_inc(&rdev->nr_pending);
			rcu_read_unlock();