From 0ea9924abe125a0c1277484f1a3d512b3f45c320 Mon Sep 17 00:00:00 2001
From: Guoqing Jiang <gqjiang@suse.com>
Date: Mon, 9 Apr 2018 17:01:21 +0800
Subject: [PATCH 1/3] md-cluster: don't update recovery_offset for faulty
device
Device could become faulty when clustered array handling
METADATA_UPDATED msg, so we don't need to call read_rdev
for this device.
Signed-off-by: Guoqing Jiang <gqjiang@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
---
drivers/md/md.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 3bea45e8ccff..c208c01f63a5 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -9256,8 +9256,10 @@ void md_reload_sb(struct mddev *mddev, int nr)
check_sb_changes(mddev, rdev);
/* Read all rdev's to update recovery_offset */
- rdev_for_each_rcu(rdev, mddev)
- read_rdev(mddev, rdev);
+ rdev_for_each_rcu(rdev, mddev) {
+ if (!test_bit(Faulty, &rdev->flags))
+ read_rdev(mddev, rdev);
+ }
}
EXPORT_SYMBOL(md_reload_sb);
From 8c2425932398a160f687534efe71f0ec4b92833e Mon Sep 17 00:00:00 2001
From: Yufen Yu <yuyufen@huawei.com>
Date: Mon, 9 Apr 2018 09:50:44 +0800
Subject: [PATCH 2/3] md/raid1: exit sync request if MD_RECOVERY_INTR is set
We met a sync thread stuck as follows:
raid1_sync_request+0x2c9/0xb50
md_do_sync+0x983/0xfa0
md_thread+0x11c/0x160
kthread+0x111/0x130
ret_from_fork+0x35/0x40
0xffffffffffffffff
At the same time, there is a stuck mdadm thread (mdadm --manage
/dev/md2 --add /dev/sda). It is trying to stop the sync thread:
kthread_stop+0x42/0xf0
md_unregister_thread+0x3a/0x70
md_reap_sync_thread+0x15/0x160
action_store+0x142/0x2a0
md_attr_store+0x6c/0xb0
kernfs_fop_write+0x102/0x180
__vfs_write+0x33/0x170
vfs_write+0xad/0x1a0
SyS_write+0x52/0xc0
do_syscall_64+0x6e/0x190
entry_SYSCALL_64_after_hwframe+0x3d/0xa2
Debug tools show that the sync thread is waiting in raise_barrier(),
until raid1d() end all normal IO bios into bio_end_io_list(introduced
in commit 55ce74d4bfe1). But, raid1d() cannot end these bios if
MD_CHANGE_PENDING bit is set. It needs to get mddev->reconfig_mutex lock
and then clear the bit in md_check_recovery().
However, the lock is holding by mdadm in action_store().
Thus, there is a loop:
mdadm waiting for sync thread to stop, sync thread waiting for
raid1d() to end bios, raid1d() waiting for mdadm to release
mddev->reconfig_mutex lock and then it can end bios.
Fix this by checking MD_RECOVERY_INTR while waiting in raise_barrier(),
so that sync thread can exit while mdadm is stoping the sync thread.
Fixes: 55ce74d4bfe1 ("md/raid1: ensure device failure recorded before write request returns.")
Signed-off-by: Jason Yan <yanaijie@huawei.com>
Signed-off-by: Yufen Yu <yuyufen@huawei.com>
Signed-off-by: Shaohua Li <shli@fb.com>
---
drivers/md/raid1.c | 23 ++++++++++++++++++-----
1 file changed, 18 insertions(+), 5 deletions(-)
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index e2943fb74056..6f624311cec2 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -854,7 +854,7 @@ static void flush_pending_writes(struct r1conf *conf)
* there is no normal IO happeing. It must arrange to call
* lower_barrier when the particular background IO completes.
*/
-static void raise_barrier(struct r1conf *conf, sector_t sector_nr)
+static sector_t raise_barrier(struct r1conf *conf, sector_t sector_nr)
{
int idx = sector_to_idx(sector_nr);
@@ -885,13 +885,23 @@ static void raise_barrier(struct r1conf *conf, sector_t sector_nr)
* max resync count which allowed on current I/O barrier bucket.
*/
wait_event_lock_irq(conf->wait_barrier,
- !conf->array_frozen &&
+ (!conf->array_frozen &&
!atomic_read(&conf->nr_pending[idx]) &&
- atomic_read(&conf->barrier[idx]) < RESYNC_DEPTH,
+ atomic_read(&conf->barrier[idx]) < RESYNC_DEPTH) ||
+ test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery),
conf->resync_lock);
+ if (test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) {
+ atomic_dec(&conf->barrier[idx]);
+ spin_unlock_irq(&conf->resync_lock);
+ wake_up(&conf->wait_barrier);
+ return -EINTR;
+ }
+
atomic_inc(&conf->nr_sync_pending);
spin_unlock_irq(&conf->resync_lock);
+
+ return 0;
}
static void lower_barrier(struct r1conf *conf, sector_t sector_nr)
@@ -2662,9 +2672,12 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
bitmap_cond_end_sync(mddev->bitmap, sector_nr,
mddev_is_clustered(mddev) && (sector_nr + 2 * RESYNC_SECTORS > conf->cluster_sync_high));
- r1_bio = raid1_alloc_init_r1buf(conf);
- raise_barrier(conf, sector_nr);
+
+ if (raise_barrier(conf, sector_nr))
+ return 0;
+
+ r1_bio = raid1_alloc_init_r1buf(conf);
rcu_read_lock();
/*
From dba40d46ebf41e3f7ac9480609529bb6037a918d Mon Sep 17 00:00:00 2001
From: Mariusz Dabrowski <mariusz.dabrowski@intel.com>
Date: Wed, 14 Feb 2018 14:23:30 +0100
Subject: [PATCH 3/3] raid1: copy write hint from master bio to behind bio
Signed-off-by: Mariusz Dabrowski <mariusz.dabrowski@intel.com>
Reviewed-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Reviewed-by: Pawel Baldysiak <pawel.baldysiak@intel.com>
Signed-off-by: Shaohua Li <shli@fb.com>
---
drivers/md/raid1.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 6f624311cec2..e9e3308cb0a7 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1102,6 +1102,8 @@ static void alloc_behind_master_bio(struct r1bio *r1_bio,
goto skip_copy;
}
+ behind_bio->bi_write_hint = bio->bi_write_hint;
+
while (i < vcnt && size) {
struct page *page;
int len = min_t(int, PAGE_SIZE, size);