From 0232605d987d8230b254aa139805bbb56a7ca30c Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 3 Jul 2012 15:56:52 +1000 Subject: md: make 'name' arg to md_register_thread non-optional. Having the 'name' arg optional and defaulting to the current personality name is no necessary and leads to errors, as when changing the level of an array we can end up using the name of the old level instead of the new one. So make it non-optional and always explicitly pass the name of the level that the array will be. Reported-by: majianpeng Signed-off-by: NeilBrown --- drivers/md/raid1.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/md/raid1.c') diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index a9c7981ddd24..39b2a8aa3b23 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -2621,7 +2621,7 @@ static struct r1conf *setup_conf(struct mddev *mddev) goto abort; } err = -ENOMEM; - conf->thread = md_register_thread(raid1d, mddev, NULL); + conf->thread = md_register_thread(raid1d, mddev, "raid1"); if (!conf->thread) { printk(KERN_ERR "md/raid1:%s: couldn't allocate thread\n", -- cgit v1.2.3 From 32644afd8975d19174bcb9ba34687c32dd810a09 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 3 Jul 2012 15:58:42 +1000 Subject: md/raid1: fix bug in read_balance introduced by hot-replace When we added hot_replace we doubled the number of devices that could be in a RAID1 array. So we doubled how far read_balance would search. Unfortunately we didn't double the point at which it looped back to the beginning - so it effectively loops over all non-replacement disks twice. This doesn't cause bad behaviour, but it pointless and means we never read from replacement devices. 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 39b2a8aa3b23..34b4665cb0b6 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -517,8 +517,8 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect int bad_sectors; int disk = start_disk + i; - if (disk >= conf->raid_disks) - disk -= conf->raid_disks; + if (disk >= conf->raid_disks * 2) + disk -= conf->raid_disks * 2; rdev = rcu_dereference(conf->mirrors[disk].rdev); if (r1_bio->bios[disk] == IO_BLOCKED -- cgit v1.2.3 From b357f04a67c2aeee828b240863cd3f21d6cb3179 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 3 Jul 2012 17:45:31 +1000 Subject: md: fix up plugging (again). The value returned by "mddev_check_plug" is only valid until the next 'schedule' as that will unplug things. This could happen at any call to mempool_alloc. So just calling mddev_check_plug at the start doesn't really make sense. So call it just before, or just after, queuing things for the thread. As the action that happens at unplug is to wake the thread, this makes lots of sense. If we cannot add a plug (which requires a small GFP_ATOMIC alloc) we wake thread immediately. RAID5 is a bit different. Requests are queued for the thread and the thread is woken by release_stripe. So we don't need to wake the thread on failure. However the thread doesn't perform certain actions when there is any active plug, so it is important to install a plug before waking the thread. So for RAID5 we install the plug *before* queuing the request and waking the thread. Without this patch it is possible for raid1 or raid10 to queue a request without then waking the thread, resulting in the array locking up. Also change raid10 to only flush_pending_write when there are not active plugs, just like raid1. This patch is suitable for 3.0 or later. I plan to submit it to -stable, but I'll like to let it spend a few weeks in mainline first to be sure it is completely safe. Signed-off-by: NeilBrown --- drivers/md/raid1.c | 7 ++----- drivers/md/raid10.c | 12 ++++++------ drivers/md/raid5.c | 6 +----- 3 files changed, 9 insertions(+), 16 deletions(-) (limited to 'drivers/md/raid1.c') diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 34b4665cb0b6..8c2754f835ef 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -883,7 +883,6 @@ static void make_request(struct mddev *mddev, struct bio * bio) const unsigned long do_sync = (bio->bi_rw & REQ_SYNC); const unsigned long do_flush_fua = (bio->bi_rw & (REQ_FLUSH | REQ_FUA)); struct md_rdev *blocked_rdev; - int plugged; int first_clone; int sectors_handled; int max_sectors; @@ -1034,7 +1033,6 @@ read_again: * the bad blocks. Each set of writes gets it's own r1bio * with a set of bios attached. */ - plugged = mddev_check_plugged(mddev); disks = conf->raid_disks * 2; retry_write: @@ -1191,6 +1189,8 @@ read_again: bio_list_add(&conf->pending_bio_list, mbio); conf->pending_count++; spin_unlock_irqrestore(&conf->device_lock, flags); + if (!mddev_check_plugged(mddev)) + md_wakeup_thread(mddev->thread); } /* Mustn't call r1_bio_write_done before this next test, * as it could result in the bio being freed. @@ -1213,9 +1213,6 @@ read_again: /* In case raid1d snuck in to freeze_array */ wake_up(&conf->wait_barrier); - - if (do_sync || !bitmap || !plugged) - md_wakeup_thread(mddev->thread); } static void status(struct seq_file *seq, struct mddev *mddev) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index edc1088a1320..acf5a828c7e1 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1039,7 +1039,6 @@ static void make_request(struct mddev *mddev, struct bio * bio) const unsigned long do_fua = (bio->bi_rw & REQ_FUA); unsigned long flags; struct md_rdev *blocked_rdev; - int plugged; int sectors_handled; int max_sectors; int sectors; @@ -1239,7 +1238,6 @@ read_again: * of r10_bios is recored in bio->bi_phys_segments just as with * the read case. */ - plugged = mddev_check_plugged(mddev); r10_bio->read_slot = -1; /* make sure repl_bio gets freed */ raid10_find_phys(conf, r10_bio); @@ -1396,6 +1394,8 @@ retry_write: bio_list_add(&conf->pending_bio_list, mbio); conf->pending_count++; spin_unlock_irqrestore(&conf->device_lock, flags); + if (!mddev_check_plugged(mddev, 0, 0)) + md_wakeup_thread(mddev->thread); if (!r10_bio->devs[i].repl_bio) continue; @@ -1423,6 +1423,8 @@ retry_write: bio_list_add(&conf->pending_bio_list, mbio); conf->pending_count++; spin_unlock_irqrestore(&conf->device_lock, flags); + if (!mddev_check_plugged(mddev)) + md_wakeup_thread(mddev->thread); } /* Don't remove the bias on 'remaining' (one_write_done) until @@ -1448,9 +1450,6 @@ retry_write: /* In case raid10d snuck in to freeze_array */ wake_up(&conf->wait_barrier); - - if (do_sync || !mddev->bitmap || !plugged) - md_wakeup_thread(mddev->thread); } static void status(struct seq_file *seq, struct mddev *mddev) @@ -2661,7 +2660,8 @@ static void raid10d(struct mddev *mddev) blk_start_plug(&plug); for (;;) { - flush_pending_writes(conf); + if (atomic_read(&mddev->plug_cnt) == 0) + flush_pending_writes(conf); spin_lock_irqsave(&conf->device_lock, flags); if (list_empty(head)) { diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 7245a9df35a9..04348d76bb30 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -3997,7 +3997,6 @@ static void make_request(struct mddev *mddev, struct bio * bi) struct stripe_head *sh; const int rw = bio_data_dir(bi); int remaining; - int plugged; if (unlikely(bi->bi_rw & REQ_FLUSH)) { md_flush_request(mddev, bi); @@ -4016,7 +4015,6 @@ static void make_request(struct mddev *mddev, struct bio * bi) bi->bi_next = NULL; bi->bi_phys_segments = 1; /* over-loaded to count active stripes */ - plugged = mddev_check_plugged(mddev); for (;logical_sector < last_sector; logical_sector += STRIPE_SECTORS) { DEFINE_WAIT(w); int previous; @@ -4118,6 +4116,7 @@ static void make_request(struct mddev *mddev, struct bio * bi) if ((bi->bi_rw & REQ_SYNC) && !test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) atomic_inc(&conf->preread_active_stripes); + mddev_check_plugged(mddev); release_stripe(sh); } else { /* cannot get stripe for read-ahead, just give-up */ @@ -4125,10 +4124,7 @@ static void make_request(struct mddev *mddev, struct bio * bi) finish_wait(&conf->wait_for_overlap, &w); break; } - } - if (!plugged) - md_wakeup_thread(mddev->thread); spin_lock_irq(&conf->device_lock); remaining = raid5_dec_bi_phys_segments(bi); -- cgit v1.2.3