raid1.c

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

		 */
		if (mddev->curr_resync < max_sector) /* aborted */
			bitmap_end_sync(mddev->bitmap, mddev->curr_resync,
						&sync_blocks, 1);
		else /* completed sync */
			conf->fullsync = 0;

		bitmap_close_sync(mddev->bitmap);
		close_sync(conf);
		return 0;
	}

	if (mddev->bitmap == NULL &&
	    mddev->recovery_cp == MaxSector &&
	    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
	    conf->fullsync == 0) {
		*skipped = 1;
		return max_sector - sector_nr;
	}
	/* before building a request, check if we can skip these blocks..
	 * This call the bitmap_start_sync doesn't actually record anything
	 */
	if (!bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 1) &&
	    !conf->fullsync && !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
		/* We can skip this block, and probably several more */
		*skipped = 1;
		return sync_blocks;
	}
	/*
	 * If there is non-resync activity waiting for a turn,
	 * and resync is going fast enough,
	 * then let it though before starting on this new sync request.
	 */
	if (!go_faster && conf->nr_waiting)
		msleep_interruptible(1000);

	raise_barrier(conf);

	conf->next_resync = sector_nr;

	r1_bio = mempool_alloc(conf->r1buf_pool, GFP_NOIO);
	rcu_read_lock();
	/*
	 * If we get a correctably read error during resync or recovery,
	 * we might want to read from a different device.  So we
	 * flag all drives that could conceivably be read from for READ,
	 * and any others (which will be non-In_sync devices) for WRITE.
	 * If a read fails, we try reading from something else for which READ
	 * is OK.
	 */

	r1_bio->mddev = mddev;
	r1_bio->sector = sector_nr;
	r1_bio->state = 0;
	set_bit(R1BIO_IsSync, &r1_bio->state);

	for (i=0; i < conf->raid_disks; i++) {
		mdk_rdev_t *rdev;
		bio = r1_bio->bios[i];

		/* take from bio_init */
		bio->bi_next = NULL;
		bio->bi_flags |= 1 << BIO_UPTODATE;
		bio->bi_rw = READ;
		bio->bi_vcnt = 0;
		bio->bi_idx = 0;
		bio->bi_phys_segments = 0;
		bio->bi_hw_segments = 0;
		bio->bi_size = 0;
		bio->bi_end_io = NULL;
		bio->bi_private = NULL;

		rdev = rcu_dereference(conf->mirrors[i].rdev);
		if (rdev == NULL ||
			   test_bit(Faulty, &rdev->flags)) {
			still_degraded = 1;
			continue;
		} else if (!test_bit(In_sync, &rdev->flags)) {
			bio->bi_rw = WRITE;
			bio->bi_end_io = end_sync_write;
			write_targets ++;
		} else {
			/* may need to read from here */
			bio->bi_rw = READ;
			bio->bi_end_io = end_sync_read;
			if (test_bit(WriteMostly, &rdev->flags)) {
				if (wonly < 0)
					wonly = i;
			} else {
				if (disk < 0)
					disk = i;
			}
			read_targets++;
		}
		atomic_inc(&rdev->nr_pending);
		bio->bi_sector = sector_nr + rdev->data_offset;
		bio->bi_bdev = rdev->bdev;
		bio->bi_private = r1_bio;
	}
	rcu_read_unlock();
	if (disk < 0)
		disk = wonly;
	r1_bio->read_disk = disk;

	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) && read_targets > 0)
		/* extra read targets are also write targets */
		write_targets += read_targets-1;

	if (write_targets == 0 || read_targets == 0) {
		/* There is nowhere to write, so all non-sync
		 * drives must be failed - so we are finished
		 */
		sector_t rv = max_sector - sector_nr;
		*skipped = 1;
		put_buf(r1_bio);
		return rv;
	}

	nr_sectors = 0;
	sync_blocks = 0;
	do {
		struct page *page;
		int len = PAGE_SIZE;
		if (sector_nr + (len>>9) > max_sector)
			len = (max_sector - sector_nr) << 9;
		if (len == 0)
			break;
		if (sync_blocks == 0) {
			if (!bitmap_start_sync(mddev->bitmap, sector_nr,
					       &sync_blocks, still_degraded) &&
			    !conf->fullsync &&
			    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
				break;
			BUG_ON(sync_blocks < (PAGE_SIZE>>9));
			if (len > (sync_blocks<<9))
				len = sync_blocks<<9;
		}

		for (i=0 ; i < conf->raid_disks; i++) {
			bio = r1_bio->bios[i];
			if (bio->bi_end_io) {
				page = bio->bi_io_vec[bio->bi_vcnt].bv_page;
				if (bio_add_page(bio, page, len, 0) == 0) {
					/* stop here */
					bio->bi_io_vec[bio->bi_vcnt].bv_page = page;
					while (i > 0) {
						i--;
						bio = r1_bio->bios[i];
						if (bio->bi_end_io==NULL)
							continue;
						/* remove last page from this bio */
						bio->bi_vcnt--;
						bio->bi_size -= len;
						bio->bi_flags &= ~(1<< BIO_SEG_VALID);
					}
					goto bio_full;
				}
			}
		}
		nr_sectors += len>>9;
		sector_nr += len>>9;
		sync_blocks -= (len>>9);
	} while (r1_bio->bios[disk]->bi_vcnt < RESYNC_PAGES);
 bio_full:
	r1_bio->sectors = nr_sectors;

	/* For a user-requested sync, we read all readable devices and do a
	 * compare
	 */
	if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
		atomic_set(&r1_bio->remaining, read_targets);
		for (i=0; i<conf->raid_disks; i++) {
			bio = r1_bio->bios[i];
			if (bio->bi_end_io == end_sync_read) {
				md_sync_acct(bio->bi_bdev, nr_sectors);
				generic_make_request(bio);
			}
		}
	} else {
		atomic_set(&r1_bio->remaining, 1);
		bio = r1_bio->bios[r1_bio->read_disk];
		md_sync_acct(bio->bi_bdev, nr_sectors);
		generic_make_request(bio);

	}
	return nr_sectors;
}

static int run(mddev_t *mddev)
{
	conf_t *conf;
	int i, j, disk_idx;
	mirror_info_t *disk;
	mdk_rdev_t *rdev;
	struct list_head *tmp;

	if (mddev->level != 1) {
		printk("raid1: %s: raid level not set to mirroring (%d)\n",
		       mdname(mddev), mddev->level);
		goto out;
	}
	if (mddev->reshape_position != MaxSector) {
		printk("raid1: %s: reshape_position set but not supported\n",
		       mdname(mddev));
		goto out;
	}
	/*
	 * copy the already verified devices into our private RAID1
	 * bookkeeping area. [whatever we allocate in run(),
	 * should be freed in stop()]
	 */
	conf = kzalloc(sizeof(conf_t), GFP_KERNEL);
	mddev->private = conf;
	if (!conf)
		goto out_no_mem;

	conf->mirrors = kzalloc(sizeof(struct mirror_info)*mddev->raid_disks,
				 GFP_KERNEL);
	if (!conf->mirrors)
		goto out_no_mem;

	conf->tmppage = alloc_page(GFP_KERNEL);
	if (!conf->tmppage)
		goto out_no_mem;

	conf->poolinfo = kmalloc(sizeof(*conf->poolinfo), GFP_KERNEL);
	if (!conf->poolinfo)
		goto out_no_mem;
	conf->poolinfo->mddev = mddev;
	conf->poolinfo->raid_disks = mddev->raid_disks;
	conf->r1bio_pool = mempool_create(NR_RAID1_BIOS, r1bio_pool_alloc,
					  r1bio_pool_free,
					  conf->poolinfo);
	if (!conf->r1bio_pool)
		goto out_no_mem;

	ITERATE_RDEV(mddev, rdev, tmp) {
		disk_idx = rdev->raid_disk;
		if (disk_idx >= mddev->raid_disks
		    || disk_idx < 0)
			continue;
		disk = conf->mirrors + disk_idx;

		disk->rdev = rdev;

		blk_queue_stack_limits(mddev->queue,
				       rdev->bdev->bd_disk->queue);
		/* as we don't honour merge_bvec_fn, we must never risk
		 * violating it, so limit ->max_sector to one PAGE, as
		 * a one page request is never in violation.
		 */
		if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
		    mddev->queue->max_sectors > (PAGE_SIZE>>9))
			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);

		disk->head_position = 0;
	}
	conf->raid_disks = mddev->raid_disks;
	conf->mddev = mddev;
	spin_lock_init(&conf->device_lock);
	INIT_LIST_HEAD(&conf->retry_list);

	spin_lock_init(&conf->resync_lock);
	init_waitqueue_head(&conf->wait_barrier);

	bio_list_init(&conf->pending_bio_list);
	bio_list_init(&conf->flushing_bio_list);


	mddev->degraded = 0;
	for (i = 0; i < conf->raid_disks; i++) {

		disk = conf->mirrors + i;

		if (!disk->rdev ||
		    !test_bit(In_sync, &disk->rdev->flags)) {
			disk->head_position = 0;
			mddev->degraded++;
			if (disk->rdev)
				conf->fullsync = 1;
		}
	}
	if (mddev->degraded == conf->raid_disks) {
		printk(KERN_ERR "raid1: no operational mirrors for %s\n",
			mdname(mddev));
		goto out_free_conf;
	}
	if (conf->raid_disks - mddev->degraded == 1)
		mddev->recovery_cp = MaxSector;

	/*
	 * find the first working one and use it as a starting point
	 * to read balancing.
	 */
	for (j = 0; j < conf->raid_disks &&
		     (!conf->mirrors[j].rdev ||
		      !test_bit(In_sync, &conf->mirrors[j].rdev->flags)) ; j++)
		/* nothing */;
	conf->last_used = j;


	mddev->thread = md_register_thread(raid1d, mddev, "%s_raid1");
	if (!mddev->thread) {
		printk(KERN_ERR
		       "raid1: couldn't allocate thread for %s\n",
		       mdname(mddev));
		goto out_free_conf;
	}

	printk(KERN_INFO 
		"raid1: raid set %s active with %d out of %d mirrors\n",
		mdname(mddev), mddev->raid_disks - mddev->degraded, 
		mddev->raid_disks);
	/*
	 * Ok, everything is just fine now
	 */
	mddev->array_size = mddev->size;

	mddev->queue->unplug_fn = raid1_unplug;
	mddev->queue->backing_dev_info.congested_fn = raid1_congested;
	mddev->queue->backing_dev_info.congested_data = mddev;

	return 0;

out_no_mem:
	printk(KERN_ERR "raid1: couldn't allocate memory for %s\n",
	       mdname(mddev));

out_free_conf:
	if (conf) {
		if (conf->r1bio_pool)
			mempool_destroy(conf->r1bio_pool);
		kfree(conf->mirrors);
		safe_put_page(conf->tmppage);
		kfree(conf->poolinfo);
		kfree(conf);
		mddev->private = NULL;
	}
out:
	return -EIO;
}

static int stop(mddev_t *mddev)
{
	conf_t *conf = mddev_to_conf(mddev);
	struct bitmap *bitmap = mddev->bitmap;
	int behind_wait = 0;

	/* wait for behind writes to complete */
	while (bitmap && atomic_read(&bitmap->behind_writes) > 0) {
		behind_wait++;
		printk(KERN_INFO "raid1: behind writes in progress on device %s, waiting to stop (%d)\n", mdname(mddev), behind_wait);
		set_current_state(TASK_UNINTERRUPTIBLE);
		schedule_timeout(HZ); /* wait a second */
		/* need to kick something here to make sure I/O goes? */
	}

	md_unregister_thread(mddev->thread);
	mddev->thread = NULL;
	blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
	if (conf->r1bio_pool)
		mempool_destroy(conf->r1bio_pool);
	kfree(conf->mirrors);
	kfree(conf->poolinfo);
	kfree(conf);
	mddev->private = NULL;
	return 0;
}

static int raid1_resize(mddev_t *mddev, sector_t sectors)
{
	/* no resync is happening, and there is enough space
	 * on all devices, so we can resize.
	 * We need to make sure resync covers any new space.
	 * If the array is shrinking we should possibly wait until
	 * any io in the removed space completes, but it hardly seems
	 * worth it.
	 */
	mddev->array_size = sectors>>1;
	set_capacity(mddev->gendisk, mddev->array_size << 1);
	mddev->changed = 1;
	if (mddev->array_size > mddev->size && mddev->recovery_cp == MaxSector) {
		mddev->recovery_cp = mddev->size << 1;
		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
	}
	mddev->size = mddev->array_size;
	mddev->resync_max_sectors = sectors;
	return 0;
}

static int raid1_reshape(mddev_t *mddev)
{
	/* We need to:
	 * 1/ resize the r1bio_pool
	 * 2/ resize conf->mirrors
	 *
	 * We allocate a new r1bio_pool if we can.
	 * Then raise a device barrier and wait until all IO stops.
	 * Then resize conf->mirrors and swap in the new r1bio pool.
	 *
	 * At the same time, we "pack" the devices so that all the missing
	 * devices have the higher raid_disk numbers.
	 */
	mempool_t *newpool, *oldpool;
	struct pool_info *newpoolinfo;
	mirror_info_t *newmirrors;
	conf_t *conf = mddev_to_conf(mddev);
	int cnt, raid_disks;
	unsigned long flags;
	int d, d2;

	/* Cannot change chunk_size, layout, or level */
	if (mddev->chunk_size != mddev->new_chunk ||
	    mddev->layout != mddev->new_layout ||
	    mddev->level != mddev->new_level) {
		mddev->new_chunk = mddev->chunk_size;
		mddev->new_layout = mddev->layout;
		mddev->new_level = mddev->level;
		return -EINVAL;
	}

	md_allow_write(mddev);

	raid_disks = mddev->raid_disks + mddev->delta_disks;

	if (raid_disks < conf->raid_disks) {
		cnt=0;
		for (d= 0; d < conf->raid_disks; d++)
			if (conf->mirrors[d].rdev)
				cnt++;
		if (cnt > raid_disks)
			return -EBUSY;
	}

	newpoolinfo = kmalloc(sizeof(*newpoolinfo), GFP_KERNEL);
	if (!newpoolinfo)
		return -ENOMEM;
	newpoolinfo->mddev = mddev;
	newpoolinfo->raid_disks = raid_disks;

	newpool = mempool_create(NR_RAID1_BIOS, r1bio_pool_alloc,
				 r1bio_pool_free, newpoolinfo);
	if (!newpool) {
		kfree(newpoolinfo);
		return -ENOMEM;
	}
	newmirrors = kzalloc(sizeof(struct mirror_info) * raid_disks, GFP_KERNEL);
	if (!newmirrors) {
		kfree(newpoolinfo);
		mempool_destroy(newpool);
		return -ENOMEM;
	}

	raise_barrier(conf);

	/* ok, everything is stopped */
	oldpool = conf->r1bio_pool;
	conf->r1bio_pool = newpool;

	for (d = d2 = 0; d < conf->raid_disks; d++) {
		mdk_rdev_t *rdev = conf->mirrors[d].rdev;
		if (rdev && rdev->raid_disk != d2) {
			char nm[20];
			sprintf(nm, "rd%d", rdev->raid_disk);
			sysfs_remove_link(&mddev->kobj, nm);
			rdev->raid_disk = d2;
			sprintf(nm, "rd%d", rdev->raid_disk);
			sysfs_remove_link(&mddev->kobj, nm);
			if (sysfs_create_link(&mddev->kobj,
					      &rdev->kobj, nm))
				printk(KERN_WARNING
				       "md/raid1: cannot register "
				       "%s for %s\n",
				       nm, mdname(mddev));
		}
		if (rdev)
			newmirrors[d2++].rdev = rdev;
	}
	kfree(conf->mirrors);
	conf->mirrors = newmirrors;
	kfree(conf->poolinfo);
	conf->poolinfo = newpoolinfo;

	spin_lock_irqsave(&conf->device_lock, flags);
	mddev->degraded += (raid_disks - conf->raid_disks);
	spin_unlock_irqrestore(&conf->device_lock, flags);
	conf->raid_disks = mddev->raid_disks = raid_disks;
	mddev->delta_disks = 0;

	conf->last_used = 0; /* just make sure it is in-range */
	lower_barrier(conf);

	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
	md_wakeup_thread(mddev->thread);

	mempool_destroy(oldpool);
	return 0;
}

static void raid1_quiesce(mddev_t *mddev, int state)
{
	conf_t *conf = mddev_to_conf(mddev);

	switch(state) {
	case 1:
		raise_barrier(conf);
		break;
	case 0:
		lower_barrier(conf);
		break;
	}
}


static struct mdk_personality raid1_personality =
{
	.name		= "raid1",
	.level		= 1,
	.owner		= THIS_MODULE,
	.make_request	= make_request,
	.run		= run,
	.stop		= stop,
	.status		= status,
	.error_handler	= error,
	.hot_add_disk	= raid1_add_disk,
	.hot_remove_disk= raid1_remove_disk,
	.spare_active	= raid1_spare_active,
	.sync_request	= sync_request,
	.resize		= raid1_resize,
	.check_reshape	= raid1_reshape,
	.quiesce	= raid1_quiesce,
};

static int __init raid_init(void)
{
	return register_md_personality(&raid1_personality);
}

static void raid_exit(void)
{
	unregister_md_personality(&raid1_personality);
}

module_init(raid_init);
module_exit(raid_exit);
MODULE_LICENSE("GPL");
MODULE_ALIAS("md-personality-3"); /* RAID1 */
MODULE_ALIAS("md-raid1");
MODULE_ALIAS("md-level-1");