From c6563a8c38fde3c1c7fc925a10bde3ca20799301 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 21 May 2012 09:27:00 +1000 Subject: md: add possibility to change data-offset for devices. When reshaping we can avoid costly intermediate backup by changing the 'start' address of the array on the device (if there is enough room). So as a first step, allow such a change to be requested through sysfs, and recorded in v1.x metadata. (As we didn't previous check that all 'pad' fields were zero, we need a new FEATURE flag for this. A (belatedly) check that all remaining 'pad' fields are zero to avoid a repeat of this) The new data offset must be requested separately for each device. This allows each to have a different change in the data offset. This is not likely to be used often but as data_offset can be set per-device, new_data_offset should be too. This patch also removes the 'acknowledged' arg to rdev_set_badblocks as it is never used and never will be. At the same time we add a new arg ('in_new') which is currently always zero but will be used more soon. When a reshape finishes we will need to update the data_offset and rdev->sectors. So provide an exported function to do that. Signed-off-by: NeilBrown --- drivers/md/raid1.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/md/raid1.c') diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 15dd59b84e9..71a7dc038a8 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -2024,7 +2024,7 @@ static void handle_sync_write_finished(struct r1conf *conf, struct r1bio *r1_bio continue; if (test_bit(BIO_UPTODATE, &bio->bi_flags) && test_bit(R1BIO_MadeGood, &r1_bio->state)) { - rdev_clear_badblocks(rdev, r1_bio->sector, s); + rdev_clear_badblocks(rdev, r1_bio->sector, s, 0); } if (!test_bit(BIO_UPTODATE, &bio->bi_flags) && test_bit(R1BIO_WriteError, &r1_bio->state)) { @@ -2044,7 +2044,7 @@ static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio) struct md_rdev *rdev = conf->mirrors[m].rdev; rdev_clear_badblocks(rdev, r1_bio->sector, - r1_bio->sectors); + r1_bio->sectors, 0); rdev_dec_pending(rdev, conf->mddev); } else if (r1_bio->bios[m] != NULL) { /* This drive got a write error. We need to -- cgit v1.2.3-70-g09d2 From da8840a747c0dbf49506ec906757a6b87b9741e9 Mon Sep 17 00:00:00 2001 From: majianpeng Date: Tue, 22 May 2012 13:55:03 +1000 Subject: md/raid1: allow fix_read_error to read from recovering device. When attempting to fix a read error, it is acceptable to read from a device that is recovering, provided the recovery has got past the place we are reading from. This makes the test for "can we read from here" the same as the test in read_balance. Signed-off-by: majianpeng Signed-off-by: NeilBrown --- drivers/md/raid1.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'drivers/md/raid1.c') diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 71a7dc038a8..22cfc6660b1 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1859,7 +1859,9 @@ static void fix_read_error(struct r1conf *conf, int read_disk, rdev = conf->mirrors[d].rdev; if (rdev && - test_bit(In_sync, &rdev->flags) && + (test_bit(In_sync, &rdev->flags) || + (!test_bit(Faulty, &rdev->flags) && + rdev->recovery_offset >= sect + s)) && is_badblock(rdev, sect, s, &first_bad, &bad_sectors) == 0 && sync_page_io(rdev, sect, s<<9, -- cgit v1.2.3-70-g09d2 From a4a6125a074e1b08ee8ae34f700c5bca19eb9d18 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 22 May 2012 13:55:27 +1000 Subject: md: allow array to be resized while bitmap is present. Now that bitmaps can be resized, we can allow an array to be resized while the bitmap is present. This only covers resizing that involves changing the effective size of member devices, not resizing that changes the number of devices. Signed-off-by: NeilBrown --- drivers/md/md.c | 6 +----- drivers/md/raid1.c | 11 +++++++++-- drivers/md/raid10.c | 10 ++++++++-- drivers/md/raid5.c | 14 ++++++++++---- 4 files changed, 28 insertions(+), 13 deletions(-) (limited to 'drivers/md/raid1.c') diff --git a/drivers/md/md.c b/drivers/md/md.c index 9e2336fbbd3..86adf4ac46c 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -6153,11 +6153,7 @@ static int update_size(struct mddev *mddev, sector_t num_sectors) */ if (mddev->sync_thread) return -EBUSY; - if (mddev->bitmap) - /* Sorry, cannot grow a bitmap yet, just remove it, - * grow, and re-add. - */ - return -EBUSY; + rdev_for_each(rdev, mddev) { sector_t avail = rdev->sectors; diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 22cfc6660b1..8e717bd518e 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -2752,9 +2752,16 @@ static int raid1_resize(struct mddev *mddev, sector_t sectors) * any io in the removed space completes, but it hardly seems * worth it. */ - md_set_array_sectors(mddev, raid1_size(mddev, sectors, 0)); - if (mddev->array_sectors > raid1_size(mddev, sectors, 0)) + sector_t newsize = raid1_size(mddev, sectors, 0); + if (mddev->external_size && + mddev->array_sectors > newsize) return -EINVAL; + if (mddev->bitmap) { + int ret = bitmap_resize(mddev->bitmap, newsize, 0, 0); + if (ret) + return ret; + } + md_set_array_sectors(mddev, newsize); set_capacity(mddev->gendisk, mddev->array_sectors); revalidate_disk(mddev->gendisk); if (sectors > mddev->dev_sectors && diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index fb9062b5022..8fe3aa46998 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -3678,9 +3678,15 @@ static int raid10_resize(struct mddev *mddev, sector_t sectors) oldsize = raid10_size(mddev, 0, 0); size = raid10_size(mddev, sectors, 0); - md_set_array_sectors(mddev, size); - if (mddev->array_sectors > size) + if (mddev->external_size && + mddev->array_sectors > size) return -EINVAL; + if (mddev->bitmap) { + int ret = bitmap_resize(mddev->bitmap, size, 0, 0); + if (ret) + return ret; + } + md_set_array_sectors(mddev, size); set_capacity(mddev->gendisk, mddev->array_sectors); revalidate_disk(mddev->gendisk); if (sectors > mddev->dev_sectors && diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 7bfd59b313d..eab6168bb7f 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5503,12 +5503,18 @@ static int raid5_resize(struct mddev *mddev, sector_t sectors) * any io in the removed space completes, but it hardly seems * worth it. */ + sector_t newsize; sectors &= ~((sector_t)mddev->chunk_sectors - 1); - md_set_array_sectors(mddev, raid5_size(mddev, sectors, - mddev->raid_disks)); - if (mddev->array_sectors > - raid5_size(mddev, sectors, mddev->raid_disks)) + newsize = raid5_size(mddev, sectors, mddev->raid_disks); + if (mddev->external_size && + mddev->array_sectors > newsize) return -EINVAL; + if (mddev->bitmap) { + int ret = bitmap_resize(mddev->bitmap, sectors, 0, 0); + if (ret) + return ret; + } + md_set_array_sectors(mddev, newsize); set_capacity(mddev->gendisk, mddev->array_sectors); revalidate_disk(mddev->gendisk); if (sectors > mddev->dev_sectors && -- cgit v1.2.3-70-g09d2 From 4f0a5e012cf41321d611e7cad63e1017d143d138 Mon Sep 17 00:00:00 2001 From: Jonathan Brassow Date: Tue, 22 May 2012 13:55:31 +1000 Subject: MD RAID1: Further conditionalize 'fullsync' A RAID1 device does not necessarily need a fullsync if the bitmap can be used instead. Similar to commit d6b212f4b19da5301e6b6eca562e5c7a2a6e8c8d in raid5.c, if a raid1 device can be brought back (i.e. from a transient failure) it shouldn't need a complete resync. Provided the bitmap is not to old, it will have recorded the areas of the disk that need recovery. Signed-off-by: Jonathan Brassow Signed-off-by: NeilBrown --- drivers/md/raid1.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers/md/raid1.c') diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 8e717bd518e..835de7168cd 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -2600,7 +2600,8 @@ static struct r1conf *setup_conf(struct mddev *mddev) if (!disk->rdev || !test_bit(In_sync, &disk->rdev->flags)) { disk->head_position = 0; - if (disk->rdev) + if (disk->rdev && + (disk->rdev->saved_raid_disk < 0)) conf->fullsync = 1; } else if (conf->last_used < 0) /* -- cgit v1.2.3-70-g09d2