From c8dc9c654794a765ca61baed07f84ed8aaa7ca8c Mon Sep 17 00:00:00 2001 From: Joe Lawrence Date: Thu, 21 Feb 2013 13:28:09 +1100 Subject: md: raid1,10: Handle REQ_WRITE_SAME flag in write bios Set mddev queue's max_write_same_sectors to its chunk_sector value (before disk_stack_limits merges the underlying disk limits.) With that in place, be sure to handle writes coming down from the block layer that have the REQ_WRITE_SAME flag set. That flag needs to be copied into any newly cloned write bio. Signed-off-by: Joe Lawrence Acked-by: "Martin K. Petersen" Signed-off-by: NeilBrown --- drivers/md/raid10.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'drivers/md/raid10.c') diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 64d48249c03b..1a74c12f0a6e 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1105,6 +1105,7 @@ static void make_request(struct mddev *mddev, struct bio * bio) const unsigned long do_fua = (bio->bi_rw & REQ_FUA); const unsigned long do_discard = (bio->bi_rw & (REQ_DISCARD | REQ_SECURE)); + const unsigned long do_same = (bio->bi_rw & REQ_WRITE_SAME); unsigned long flags; struct md_rdev *blocked_rdev; struct blk_plug_cb *cb; @@ -1460,7 +1461,8 @@ retry_write: rdev)); mbio->bi_bdev = rdev->bdev; mbio->bi_end_io = raid10_end_write_request; - mbio->bi_rw = WRITE | do_sync | do_fua | do_discard; + mbio->bi_rw = + WRITE | do_sync | do_fua | do_discard | do_same; mbio->bi_private = r10_bio; atomic_inc(&r10_bio->remaining); @@ -1502,7 +1504,8 @@ retry_write: r10_bio, rdev)); mbio->bi_bdev = rdev->bdev; mbio->bi_end_io = raid10_end_write_request; - mbio->bi_rw = WRITE | do_sync | do_fua | do_discard; + mbio->bi_rw = + WRITE | do_sync | do_fua | do_discard | do_same; mbio->bi_private = r10_bio; atomic_inc(&r10_bio->remaining); @@ -3569,6 +3572,8 @@ static int run(struct mddev *mddev) if (mddev->queue) { blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors); + blk_queue_max_write_same_sectors(mddev->queue, + mddev->chunk_sectors); blk_queue_io_min(mddev->queue, chunk_size); if (conf->geo.raid_disks % conf->geo.near_copies) blk_queue_io_opt(mddev->queue, chunk_size * conf->geo.raid_disks); -- cgit v1.2.3 From 4c0ca26bd260dddf3b9781758cb5e2df3f74d4a3 Mon Sep 17 00:00:00 2001 From: Jonathan Brassow Date: Thu, 21 Feb 2013 13:28:09 +1100 Subject: MD RAID10: Minor non-functional code changes Changes include assigning 'addr' from 's' instead of 'sector' to be consistent with the way the code does it just a few lines later and using '%=' vs a conditional and subtraction. Signed-off-by: Jonathan Brassow Signed-off-by: NeilBrown --- drivers/md/raid10.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'drivers/md/raid10.c') diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 1a74c12f0a6e..de174ad6f8bd 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -552,14 +552,13 @@ static void __raid10_find_phys(struct geom *geo, struct r10bio *r10bio) for (n = 0; n < geo->near_copies; n++) { int d = dev; sector_t s = sector; - r10bio->devs[slot].addr = sector; r10bio->devs[slot].devnum = d; + r10bio->devs[slot].addr = s; slot++; for (f = 1; f < geo->far_copies; f++) { d += geo->near_copies; - if (d >= geo->raid_disks) - d -= geo->raid_disks; + d %= geo->raid_disks; s += geo->stride; r10bio->devs[slot].devnum = d; r10bio->devs[slot].addr = s; -- cgit v1.2.3 From 475901aff15841fb0a81e7546517407779a9b061 Mon Sep 17 00:00:00 2001 From: Jonathan Brassow Date: Thu, 21 Feb 2013 13:28:10 +1100 Subject: MD RAID10: Improve redundancy for 'far' and 'offset' algorithms (part 1) The MD RAID10 'far' and 'offset' algorithms make copies of entire stripe widths - copying them to a different location on the same devices after shifting the stripe. An example layout of each follows below: "far" algorithm dev1 dev2 dev3 dev4 dev5 dev6 ==== ==== ==== ==== ==== ==== A B C D E F G H I J K L ... F A B C D E --> Copy of stripe0, but shifted by 1 L G H I J K ... "offset" algorithm dev1 dev2 dev3 dev4 dev5 dev6 ==== ==== ==== ==== ==== ==== A B C D E F F A B C D E --> Copy of stripe0, but shifted by 1 G H I J K L L G H I J K ... Redundancy for these algorithms is gained by shifting the copied stripes one device to the right. This patch proposes that array be divided into sets of adjacent devices and when the stripe copies are shifted, they wrap on set boundaries rather than the array size boundary. That is, for the purposes of shifting, the copies are confined to their sets within the array. The sets are 'near_copies * far_copies' in size. The above "far" algorithm example would change to: "far" algorithm dev1 dev2 dev3 dev4 dev5 dev6 ==== ==== ==== ==== ==== ==== A B C D E F G H I J K L ... B A D C F E --> Copy of stripe0, shifted 1, 2-dev sets H G J I L K Dev sets are 1-2, 3-4, 5-6 ... This has the affect of improving the redundancy of the array. We can always sustain at least one failure, but sometimes more than one can be handled. In the first examples, the pairs of devices that CANNOT fail together are: (1,2) (2,3) (3,4) (4,5) (5,6) (1, 6) [40% of possible pairs] In the example where the copies are confined to sets, the pairs of devices that cannot fail together are: (1,2) (3,4) (5,6) [20% of possible pairs] We cannot simply replace the old algorithms, so the 17th bit of the 'layout' variable is used to indicate whether we use the old or new method of computing the shift. (This is similar to the way the 16th bit indicates whether the "far" algorithm or the "offset" algorithm is being used.) This patch only handles the cases where the number of total raid disks is a multiple of 'far_copies'. A follow-on patch addresses the condition where this is not true. Signed-off-by: Jonathan Brassow Signed-off-by: NeilBrown --- drivers/md/raid10.c | 58 ++++++++++++++++++++++++++++++++++++----------------- drivers/md/raid10.h | 5 +++++ 2 files changed, 45 insertions(+), 18 deletions(-) (limited to 'drivers/md/raid10.c') diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index de174ad6f8bd..70b58b4bcf89 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -38,21 +38,36 @@ * near_copies (stored in low byte of layout) * far_copies (stored in second byte of layout) * far_offset (stored in bit 16 of layout ) + * use_far_sets (stored in bit 17 of layout ) * - * The data to be stored is divided into chunks using chunksize. - * Each device is divided into far_copies sections. - * In each section, chunks are laid out in a style similar to raid0, but - * near_copies copies of each chunk is stored (each on a different drive). - * The starting device for each section is offset near_copies from the starting - * device of the previous section. - * Thus they are (near_copies*far_copies) of each chunk, and each is on a different - * drive. - * near_copies and far_copies must be at least one, and their product is at most - * raid_disks. + * The data to be stored is divided into chunks using chunksize. Each device + * is divided into far_copies sections. In each section, chunks are laid out + * in a style similar to raid0, but near_copies copies of each chunk is stored + * (each on a different drive). The starting device for each section is offset + * near_copies from the starting device of the previous section. Thus there + * are (near_copies * far_copies) of each chunk, and each is on a different + * drive. near_copies and far_copies must be at least one, and their product + * is at most raid_disks. * * If far_offset is true, then the far_copies are handled a bit differently. - * The copies are still in different stripes, but instead of be very far apart - * on disk, there are adjacent stripes. + * The copies are still in different stripes, but instead of being very far + * apart on disk, there are adjacent stripes. + * + * The far and offset algorithms are handled slightly differently if + * 'use_far_sets' is true. In this case, the array's devices are grouped into + * sets that are (near_copies * far_copies) in size. The far copied stripes + * are still shifted by 'near_copies' devices, but this shifting stays confined + * to the set rather than the entire array. This is done to improve the number + * of device combinations that can fail without causing the array to fail. + * Example 'far' algorithm w/o 'use_far_sets' (each letter represents a chunk + * on a device): + * A B C D A B C D E + * ... ... + * D A B C E A B C D + * Example 'far' algorithm w/ 'use_far_sets' enabled (sets illustrated w/ []'s): + * [A B] [C D] [A B] [C D E] + * |...| |...| |...| | ... | + * [B A] [D C] [B A] [E C D] */ /* @@ -551,14 +566,18 @@ static void __raid10_find_phys(struct geom *geo, struct r10bio *r10bio) /* and calculate all the others */ for (n = 0; n < geo->near_copies; n++) { int d = dev; + int set; sector_t s = sector; r10bio->devs[slot].devnum = d; r10bio->devs[slot].addr = s; slot++; for (f = 1; f < geo->far_copies; f++) { + set = d / geo->far_set_size; d += geo->near_copies; - d %= geo->raid_disks; + d %= geo->far_set_size; + d += geo->far_set_size * set; + s += geo->stride; r10bio->devs[slot].devnum = d; r10bio->devs[slot].addr = s; @@ -594,6 +613,8 @@ static sector_t raid10_find_virt(struct r10conf *conf, sector_t sector, int dev) * or recovery, so reshape isn't happening */ struct geom *geo = &conf->geo; + int far_set_start = (dev / geo->far_set_size) * geo->far_set_size; + int far_set_size = geo->far_set_size; offset = sector & geo->chunk_mask; if (geo->far_offset) { @@ -601,13 +622,13 @@ static sector_t raid10_find_virt(struct r10conf *conf, sector_t sector, int dev) chunk = sector >> geo->chunk_shift; fc = sector_div(chunk, geo->far_copies); dev -= fc * geo->near_copies; - if (dev < 0) - dev += geo->raid_disks; + if (dev < far_set_start) + dev += far_set_size; } else { while (sector >= geo->stride) { sector -= geo->stride; - if (dev < geo->near_copies) - dev += geo->raid_disks - geo->near_copies; + if (dev < (geo->near_copies + far_set_start)) + dev += far_set_size - geo->near_copies; else dev -= geo->near_copies; } @@ -3438,7 +3459,7 @@ static int setup_geo(struct geom *geo, struct mddev *mddev, enum geo_type new) disks = mddev->raid_disks + mddev->delta_disks; break; } - if (layout >> 17) + if (layout >> 18) return -1; if (chunk < (PAGE_SIZE >> 9) || !is_power_of_2(chunk)) @@ -3450,6 +3471,7 @@ static int setup_geo(struct geom *geo, struct mddev *mddev, enum geo_type new) geo->near_copies = nc; geo->far_copies = fc; geo->far_offset = fo; + geo->far_set_size = (layout & (1<<17)) ? disks / fc : disks; geo->chunk_mask = chunk - 1; geo->chunk_shift = ffz(~chunk); return nc*fc; diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h index 1054cf602345..157d69e83ff4 100644 --- a/drivers/md/raid10.h +++ b/drivers/md/raid10.h @@ -33,6 +33,11 @@ struct r10conf { * far_offset, in which case it is * 1 stripe. */ + int far_set_size; /* The number of devices in a set, + * where a 'set' are devices that + * contain far/offset copies of + * each other. + */ int chunk_shift; /* shift from chunks to sectors */ sector_t chunk_mask; } prev, geo; -- cgit v1.2.3 From 9a3152ab024867100f2f50d124b998d05fb1c3f6 Mon Sep 17 00:00:00 2001 From: Jonathan Brassow Date: Thu, 21 Feb 2013 13:28:10 +1100 Subject: MD RAID10: Improve redundancy for 'far' and 'offset' algorithms (part 2) MD RAID10: Improve redundancy for 'far' and 'offset' algorithms (part 2) This patch addresses raid arrays that have a number of devices that cannot be evenly divided by 'far_copies'. (E.g. 5 devices, far_copies = 2) This case must be handled differently because it causes that last set to be of a different size than the rest of the sets. We must compute a new modulo for this last set so that copied chunks are properly wrapped around. Example use_far_sets=1, far_copies=2, near_copies=1, devices=5: "far" algorithm dev1 dev2 dev3 dev4 dev5 ==== ==== ==== ==== ==== [ A B ] [ C D E ] [ G H ] [ I J K ] ... [ B A ] [ E C D ] --> nominal set of 2 and last set of 3 [ H G ] [ K I J ] []'s show far/offset sets Signed-off-by: Jonathan Brassow Signed-off-by: NeilBrown --- drivers/md/raid10.c | 30 ++++++++++++++++++++++++++++-- 1 file changed, 28 insertions(+), 2 deletions(-) (limited to 'drivers/md/raid10.c') diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 70b58b4bcf89..61ed150bd0cf 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -550,6 +550,13 @@ static void __raid10_find_phys(struct geom *geo, struct r10bio *r10bio) sector_t stripe; int dev; int slot = 0; + int last_far_set_start, last_far_set_size; + + last_far_set_start = (geo->raid_disks / geo->far_set_size) - 1; + last_far_set_start *= geo->far_set_size; + + last_far_set_size = geo->far_set_size; + last_far_set_size += (geo->raid_disks % geo->far_set_size); /* now calculate first sector/dev */ chunk = r10bio->sector >> geo->chunk_shift; @@ -575,9 +582,16 @@ static void __raid10_find_phys(struct geom *geo, struct r10bio *r10bio) for (f = 1; f < geo->far_copies; f++) { set = d / geo->far_set_size; d += geo->near_copies; - d %= geo->far_set_size; - d += geo->far_set_size * set; + if ((geo->raid_disks % geo->far_set_size) && + (d > last_far_set_start)) { + d -= last_far_set_start; + d %= last_far_set_size; + d += last_far_set_start; + } else { + d %= geo->far_set_size; + d += geo->far_set_size * set; + } s += geo->stride; r10bio->devs[slot].devnum = d; r10bio->devs[slot].addr = s; @@ -615,6 +629,18 @@ static sector_t raid10_find_virt(struct r10conf *conf, sector_t sector, int dev) struct geom *geo = &conf->geo; int far_set_start = (dev / geo->far_set_size) * geo->far_set_size; int far_set_size = geo->far_set_size; + int last_far_set_start; + + if (geo->raid_disks % geo->far_set_size) { + last_far_set_start = (geo->raid_disks / geo->far_set_size) - 1; + last_far_set_start *= geo->far_set_size; + + if (dev >= last_far_set_start) { + far_set_size = geo->far_set_size; + far_set_size += (geo->raid_disks % geo->far_set_size); + far_set_start = last_far_set_start; + } + } offset = sector & geo->chunk_mask; if (geo->far_offset) { -- cgit v1.2.3 From ee0b0244030434cdda26777bfb98962447e080cd Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 25 Feb 2013 12:38:29 +1100 Subject: md/raid1,raid10: fix deadlock with freeze_array() When raid1/raid10 needs to fix a read error, it first drains all pending requests by calling freeze_array(). This calls flush_pending_writes() if it needs to sleep, but some writes may be pending in a per-process plug rather than in the per-array request queue. When raid1{,0}_unplug() moves the request from the per-process plug to the per-array request queue (from which flush_pending_writes() can flush them), it needs to wake up freeze_array(), or freeze_array() will never flush them and so it will block forever. So add the requires wake_up() calls. This bug was introduced by commit f54a9d0e59c4bea3db733921ca9147612a6f292c for raid1 and a similar commit for RAID10, and so has been present since linux-3.6. As the bug causes a deadlock I believe this fix is suitable for -stable. Cc: stable@vger.kernel.org (3.6.y 3.7.y 3.8.y) Reported-by: Tregaron Bayly Tested-by: Tregaron Bayly Signed-off-by: NeilBrown --- drivers/md/raid1.c | 1 + drivers/md/raid10.c | 1 + 2 files changed, 2 insertions(+) (limited to 'drivers/md/raid10.c') diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 6e5d5a5f9cb4..fd86b372692d 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -967,6 +967,7 @@ static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule) bio_list_merge(&conf->pending_bio_list, &plug->pending); conf->pending_count += plug->pending_cnt; spin_unlock_irq(&conf->device_lock); + wake_up(&conf->wait_barrier); md_wakeup_thread(mddev->thread); kfree(plug); return; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 61ed150bd0cf..77b562d18a90 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1119,6 +1119,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule) bio_list_merge(&conf->pending_bio_list, &plug->pending); conf->pending_count += plug->pending_cnt; spin_unlock_irq(&conf->device_lock); + wake_up(&conf->wait_barrier); md_wakeup_thread(mddev->thread); kfree(plug); return; -- cgit v1.2.3