* [md PATCH 07/26] md: make ->congested robust against personality changes.
From: NeilBrown @ 2015-02-03 21:42 UTC (permalink / raw)
To: linux-raid
In-Reply-To: <20150203213948.3448.80258.stgit@notabene.brown>
There is currently no locking around calls to the 'congested'
bdi function. If called at an awkward time while an array is
being converted from one level (or personality) to another, there
is a tiny chance of running code in an unreferenced module etc.
So add a 'congested' function to the md_personality operations
structure, and call it with appropriate locking from a central
'mddev_congested'.
When the array personality is changing the array will be 'suspended'
so no IO is processed.
If mddev_congested detects this, it simply reports that the
array is congested, which is a safe guess.
As mddev_suspend calls synchronize_rcu(), mddev_congested can
avoid races by included the whole call inside an rcu_read_lock()
region.
This require that the congested functions for all subordinate devices
can be run under rcu_lock. Fortunately this is the case.
Signed-off-by: NeilBrown <neilb@suse.de>
---
drivers/md/dm-raid.c | 8 +-------
drivers/md/linear.c | 9 ++-------
drivers/md/md.c | 22 ++++++++++++++++++++--
drivers/md/md.h | 3 +++
drivers/md/multipath.c | 10 ++--------
drivers/md/raid0.c | 9 ++-------
drivers/md/raid1.c | 14 ++------------
drivers/md/raid1.h | 3 ---
drivers/md/raid10.c | 14 ++------------
drivers/md/raid10.h | 3 ---
drivers/md/raid5.c | 19 ++++---------------
drivers/md/raid5.h | 1 -
12 files changed, 38 insertions(+), 77 deletions(-)
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 07c0fa0fa284..777d9ba2acad 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -746,13 +746,7 @@ static int raid_is_congested(struct dm_target_callbacks *cb, int bits)
{
struct raid_set *rs = container_of(cb, struct raid_set, callbacks);
- if (rs->raid_type->level == 1)
- return md_raid1_congested(&rs->md, bits);
-
- if (rs->raid_type->level == 10)
- return md_raid10_congested(&rs->md, bits);
-
- return md_raid5_congested(&rs->md, bits);
+ return mddev_congested(&rs->md, bits);
}
/*
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 64713b77df1c..05108510d9cd 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -97,15 +97,11 @@ static int linear_mergeable_bvec(struct request_queue *q,
return maxsectors << 9;
}
-static int linear_congested(void *data, int bits)
+static int linear_congested(struct mddev *mddev, int bits)
{
- struct mddev *mddev = data;
struct linear_conf *conf;
int i, ret = 0;
- if (mddev_congested(mddev, bits))
- return 1;
-
rcu_read_lock();
conf = rcu_dereference(mddev->private);
@@ -218,8 +214,6 @@ static int linear_run (struct mddev *mddev)
md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
blk_queue_merge_bvec(mddev->queue, linear_mergeable_bvec);
- mddev->queue->backing_dev_info.congested_fn = linear_congested;
- mddev->queue->backing_dev_info.congested_data = mddev;
ret = md_integrity_register(mddev);
if (ret) {
@@ -366,6 +360,7 @@ static struct md_personality linear_personality =
.status = linear_status,
.hot_add_disk = linear_add,
.size = linear_size,
+ .congested = linear_congested,
};
static int __init linear_init (void)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 17e7fd776034..d45f52edb314 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -321,9 +321,23 @@ EXPORT_SYMBOL_GPL(mddev_resume);
int mddev_congested(struct mddev *mddev, int bits)
{
- return mddev->suspended;
+ struct md_personality *pers = mddev->pers;
+ int ret = 0;
+
+ rcu_read_lock();
+ if (mddev->suspended)
+ ret = 1;
+ else if (pers && pers->congested)
+ ret = pers->congested(mddev, bits);
+ rcu_read_unlock();
+ return ret;
+}
+EXPORT_SYMBOL_GPL(mddev_congested);
+static int md_congested(void *data, int bits)
+{
+ struct mddev *mddev = data;
+ return mddev_congested(mddev, bits);
}
-EXPORT_SYMBOL(mddev_congested);
/*
* Generic flush handling for md
@@ -4908,6 +4922,10 @@ int md_run(struct mddev *mddev)
bitmap_destroy(mddev);
return err;
}
+ if (mddev->queue) {
+ mddev->queue->backing_dev_info.congested_data = mddev;
+ mddev->queue->backing_dev_info.congested_fn = md_congested;
+ }
if (mddev->pers->sync_request) {
if (mddev->kobj.sd &&
sysfs_create_group(&mddev->kobj, &md_redundancy_group))
diff --git a/drivers/md/md.h b/drivers/md/md.h
index f0d15bdd96d4..f2602280fac1 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -496,6 +496,9 @@ struct md_personality
* array.
*/
void *(*takeover) (struct mddev *mddev);
+ /* congested implements bdi.congested_fn().
+ * Will not be called while array is 'suspended' */
+ int (*congested)(struct mddev *mddev, int bits);
};
struct md_sysfs_entry {
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 399272f9c042..fedb1b31877d 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -153,15 +153,11 @@ static void multipath_status (struct seq_file *seq, struct mddev *mddev)
seq_printf (seq, "]");
}
-static int multipath_congested(void *data, int bits)
+static int multipath_congested(struct mddev *mddev, int bits)
{
- struct mddev *mddev = data;
struct mpconf *conf = mddev->private;
int i, ret = 0;
- if (mddev_congested(mddev, bits))
- return 1;
-
rcu_read_lock();
for (i = 0; i < mddev->raid_disks ; i++) {
struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev);
@@ -489,9 +485,6 @@ static int multipath_run (struct mddev *mddev)
*/
md_set_array_sectors(mddev, multipath_size(mddev, 0, 0));
- mddev->queue->backing_dev_info.congested_fn = multipath_congested;
- mddev->queue->backing_dev_info.congested_data = mddev;
-
if (md_integrity_register(mddev))
goto out_free_conf;
@@ -533,6 +526,7 @@ static struct md_personality multipath_personality =
.hot_add_disk = multipath_add_disk,
.hot_remove_disk= multipath_remove_disk,
.size = multipath_size,
+ .congested = multipath_congested,
};
static int __init multipath_init (void)
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index ba6b85de96d2..4b521eac5b69 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -25,17 +25,13 @@
#include "raid0.h"
#include "raid5.h"
-static int raid0_congested(void *data, int bits)
+static int raid0_congested(struct mddev *mddev, int bits)
{
- struct mddev *mddev = data;
struct r0conf *conf = mddev->private;
struct md_rdev **devlist = conf->devlist;
int raid_disks = conf->strip_zone[0].nb_dev;
int i, ret = 0;
- if (mddev_congested(mddev, bits))
- return 1;
-
for (i = 0; i < raid_disks && !ret ; i++) {
struct request_queue *q = bdev_get_queue(devlist[i]->bdev);
@@ -263,8 +259,6 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
mdname(mddev),
(unsigned long long)smallest->sectors);
}
- mddev->queue->backing_dev_info.congested_fn = raid0_congested;
- mddev->queue->backing_dev_info.congested_data = mddev;
/*
* now since we have the hard sector sizes, we can make sure
@@ -729,6 +723,7 @@ static struct md_personality raid0_personality=
.size = raid0_size,
.takeover = raid0_takeover,
.quiesce = raid0_quiesce,
+ .congested = raid0_congested,
};
static int __init raid0_init (void)
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 40b35be34f8d..9ad7ce7091be 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -734,7 +734,7 @@ static int raid1_mergeable_bvec(struct request_queue *q,
}
-int md_raid1_congested(struct mddev *mddev, int bits)
+static int raid1_congested(struct mddev *mddev, int bits)
{
struct r1conf *conf = mddev->private;
int i, ret = 0;
@@ -763,15 +763,6 @@ int md_raid1_congested(struct mddev *mddev, int bits)
rcu_read_unlock();
return ret;
}
-EXPORT_SYMBOL_GPL(md_raid1_congested);
-
-static int raid1_congested(void *data, int bits)
-{
- struct mddev *mddev = data;
-
- return mddev_congested(mddev, bits) ||
- md_raid1_congested(mddev, bits);
-}
static void flush_pending_writes(struct r1conf *conf)
{
@@ -2955,8 +2946,6 @@ static int run(struct mddev *mddev)
md_set_array_sectors(mddev, raid1_size(mddev, 0, 0));
if (mddev->queue) {
- mddev->queue->backing_dev_info.congested_fn = raid1_congested;
- mddev->queue->backing_dev_info.congested_data = mddev;
blk_queue_merge_bvec(mddev->queue, raid1_mergeable_bvec);
if (discard_supported)
@@ -3193,6 +3182,7 @@ static struct md_personality raid1_personality =
.check_reshape = raid1_reshape,
.quiesce = raid1_quiesce,
.takeover = raid1_takeover,
+ .congested = raid1_congested,
};
static int __init raid_init(void)
diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h
index 33bda55ef9f7..14ebb288c1ef 100644
--- a/drivers/md/raid1.h
+++ b/drivers/md/raid1.h
@@ -170,7 +170,4 @@ struct r1bio {
*/
#define R1BIO_MadeGood 7
#define R1BIO_WriteError 8
-
-extern int md_raid1_congested(struct mddev *mddev, int bits);
-
#endif
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 32e282f4c83c..fb6b88674e87 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -910,7 +910,7 @@ retry:
return rdev;
}
-int md_raid10_congested(struct mddev *mddev, int bits)
+static int raid10_congested(struct mddev *mddev, int bits)
{
struct r10conf *conf = mddev->private;
int i, ret = 0;
@@ -934,15 +934,6 @@ int md_raid10_congested(struct mddev *mddev, int bits)
rcu_read_unlock();
return ret;
}
-EXPORT_SYMBOL_GPL(md_raid10_congested);
-
-static int raid10_congested(void *data, int bits)
-{
- struct mddev *mddev = data;
-
- return mddev_congested(mddev, bits) ||
- md_raid10_congested(mddev, bits);
-}
static void flush_pending_writes(struct r10conf *conf)
{
@@ -3757,8 +3748,6 @@ static int run(struct mddev *mddev)
if (mddev->queue) {
int stripe = conf->geo.raid_disks *
((mddev->chunk_sectors << 9) / PAGE_SIZE);
- mddev->queue->backing_dev_info.congested_fn = raid10_congested;
- mddev->queue->backing_dev_info.congested_data = mddev;
/* Calculate max read-ahead size.
* We need to readahead at least twice a whole stripe....
@@ -4727,6 +4716,7 @@ static struct md_personality raid10_personality =
.check_reshape = raid10_check_reshape,
.start_reshape = raid10_start_reshape,
.finish_reshape = raid10_finish_reshape,
+ .congested = raid10_congested,
};
static int __init raid_init(void)
diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h
index 157d69e83ff4..5ee6473ddc2c 100644
--- a/drivers/md/raid10.h
+++ b/drivers/md/raid10.h
@@ -150,7 +150,4 @@ enum r10bio_state {
*/
R10BIO_Previous,
};
-
-extern int md_raid10_congested(struct mddev *mddev, int bits);
-
#endif
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index a03cf2d889bf..502a908149c6 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -4149,7 +4149,7 @@ static void activate_bit_delay(struct r5conf *conf,
}
}
-int md_raid5_congested(struct mddev *mddev, int bits)
+static int raid5_congested(struct mddev *mddev, int bits)
{
struct r5conf *conf = mddev->private;
@@ -4166,15 +4166,6 @@ int md_raid5_congested(struct mddev *mddev, int bits)
return 0;
}
-EXPORT_SYMBOL_GPL(md_raid5_congested);
-
-static int raid5_congested(void *data, int bits)
-{
- struct mddev *mddev = data;
-
- return mddev_congested(mddev, bits) ||
- md_raid5_congested(mddev, bits);
-}
/* We want read requests to align with chunks where possible,
* but write requests don't need to.
@@ -6248,9 +6239,6 @@ static int run(struct mddev *mddev)
blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec);
- mddev->queue->backing_dev_info.congested_data = mddev;
- mddev->queue->backing_dev_info.congested_fn = raid5_congested;
-
chunk_size = mddev->chunk_sectors << 9;
blk_queue_io_min(mddev->queue, chunk_size);
blk_queue_io_opt(mddev->queue, chunk_size *
@@ -6333,8 +6321,6 @@ static int stop(struct mddev *mddev)
struct r5conf *conf = mddev->private;
md_unregister_thread(&mddev->thread);
- if (mddev->queue)
- mddev->queue->backing_dev_info.congested_fn = NULL;
free_conf(conf);
mddev->private = NULL;
mddev->to_remove = &raid5_attrs_group;
@@ -7126,6 +7112,7 @@ static struct md_personality raid6_personality =
.finish_reshape = raid5_finish_reshape,
.quiesce = raid5_quiesce,
.takeover = raid6_takeover,
+ .congested = raid5_congested,
};
static struct md_personality raid5_personality =
{
@@ -7148,6 +7135,7 @@ static struct md_personality raid5_personality =
.finish_reshape = raid5_finish_reshape,
.quiesce = raid5_quiesce,
.takeover = raid5_takeover,
+ .congested = raid5_congested,
};
static struct md_personality raid4_personality =
@@ -7171,6 +7159,7 @@ static struct md_personality raid4_personality =
.finish_reshape = raid5_finish_reshape,
.quiesce = raid5_quiesce,
.takeover = raid4_takeover,
+ .congested = raid5_congested,
};
static int __init raid5_init(void)
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index d59f5ca743cd..983e18a83db1 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -558,7 +558,6 @@ static inline int algorithm_is_DDF(int layout)
return layout >= 8 && layout <= 10;
}
-extern int md_raid5_congested(struct mddev *mddev, int bits);
extern void md_raid5_kick_device(struct r5conf *conf);
extern int raid5_set_cache_size(struct mddev *mddev, int size);
#endif
^ permalink raw reply related
* [md PATCH 08/26] md: make merge_bvec_fn more robust in face of personality changes.
From: NeilBrown @ 2015-02-03 21:42 UTC (permalink / raw)
To: linux-raid
In-Reply-To: <20150203213948.3448.80258.stgit@notabene.brown>
There is no locking around calls to merge_bvec_fn(), so
it is possible that calls which coincide with a level (or personality)
change could go wrong.
So create a central dispatch point for these functions and use
rcu_read_lock().
If the array is suspended, reject any merge that can be rejected.
If not, we know it is safe to call the function.
Signed-off-by: NeilBrown <neilb@suse.de>
---
drivers/md/linear.c | 6 ++----
drivers/md/md.c | 24 ++++++++++++++++++++++++
drivers/md/md.h | 4 ++++
drivers/md/raid0.c | 7 +++----
drivers/md/raid1.c | 6 ++----
drivers/md/raid10.c | 7 +++----
drivers/md/raid5.c | 8 ++++----
7 files changed, 42 insertions(+), 20 deletions(-)
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 05108510d9cd..4c2a92ce2b0b 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -60,11 +60,10 @@ static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector)
*
* Return amount of bytes we can take at this offset
*/
-static int linear_mergeable_bvec(struct request_queue *q,
+static int linear_mergeable_bvec(struct mddev *mddev,
struct bvec_merge_data *bvm,
struct bio_vec *biovec)
{
- struct mddev *mddev = q->queuedata;
struct dev_info *dev0;
unsigned long maxsectors, bio_sectors = bvm->bi_size >> 9;
sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
@@ -213,8 +212,6 @@ static int linear_run (struct mddev *mddev)
mddev->private = conf;
md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
- blk_queue_merge_bvec(mddev->queue, linear_mergeable_bvec);
-
ret = md_integrity_register(mddev);
if (ret) {
kfree(conf);
@@ -361,6 +358,7 @@ static struct md_personality linear_personality =
.hot_add_disk = linear_add,
.size = linear_size,
.congested = linear_congested,
+ .mergeable_bvec = linear_mergeable_bvec,
};
static int __init linear_init (void)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index d45f52edb314..9f0ff7187136 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -339,6 +339,29 @@ static int md_congested(void *data, int bits)
return mddev_congested(mddev, bits);
}
+static int md_mergeable_bvec(struct request_queue *q,
+ struct bvec_merge_data *bvm,
+ struct bio_vec *biovec)
+{
+ struct mddev *mddev = q->queuedata;
+ int ret;
+ rcu_read_lock();
+ if (mddev->suspended) {
+ /* Must always allow one vec */
+ if (bvm->bi_size == 0)
+ ret = biovec->bv_len;
+ else
+ ret = 0;
+ } else {
+ struct md_personality *pers = mddev->pers;
+ if (pers && pers->mergeable_bvec)
+ ret = pers->mergeable_bvec(mddev, bvm, biovec);
+ else
+ ret = biovec->bv_len;
+ }
+ rcu_read_unlock();
+ return ret;
+}
/*
* Generic flush handling for md
*/
@@ -4925,6 +4948,7 @@ int md_run(struct mddev *mddev)
if (mddev->queue) {
mddev->queue->backing_dev_info.congested_data = mddev;
mddev->queue->backing_dev_info.congested_fn = md_congested;
+ blk_queue_merge_bvec(mddev->queue, md_mergeable_bvec);
}
if (mddev->pers->sync_request) {
if (mddev->kobj.sd &&
diff --git a/drivers/md/md.h b/drivers/md/md.h
index f2602280fac1..bee5b852c33f 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -499,6 +499,10 @@ struct md_personality
/* congested implements bdi.congested_fn().
* Will not be called while array is 'suspended' */
int (*congested)(struct mddev *mddev, int bits);
+ /* mergeable_bvec is use to implement ->merge_bvec_fn */
+ int (*mergeable_bvec)(struct mddev *mddev,
+ struct bvec_merge_data *bvm,
+ struct bio_vec *biovec);
};
struct md_sysfs_entry {
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 4b521eac5b69..3770c9675b17 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -350,17 +350,16 @@ static struct md_rdev *map_sector(struct mddev *mddev, struct strip_zone *zone,
/**
* raid0_mergeable_bvec -- tell bio layer if two requests can be merged
- * @q: request queue
+ * @mddev: the md device
* @bvm: properties of new bio
* @biovec: the request that could be merged to it.
*
* Return amount of bytes we can accept at this offset
*/
-static int raid0_mergeable_bvec(struct request_queue *q,
+static int raid0_mergeable_bvec(struct mddev *mddev,
struct bvec_merge_data *bvm,
struct bio_vec *biovec)
{
- struct mddev *mddev = q->queuedata;
struct r0conf *conf = mddev->private;
sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
sector_t sector_offset = sector;
@@ -465,7 +464,6 @@ static int raid0_run(struct mddev *mddev)
mddev->queue->backing_dev_info.ra_pages = 2* stripe;
}
- blk_queue_merge_bvec(mddev->queue, raid0_mergeable_bvec);
dump_zones(mddev);
ret = md_integrity_register(mddev);
@@ -724,6 +722,7 @@ static struct md_personality raid0_personality=
.takeover = raid0_takeover,
.quiesce = raid0_quiesce,
.congested = raid0_congested,
+ .mergeable_bvec = raid0_mergeable_bvec,
};
static int __init raid0_init (void)
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 9ad7ce7091be..45c512a4b75d 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -701,11 +701,10 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
return best_disk;
}
-static int raid1_mergeable_bvec(struct request_queue *q,
+static int raid1_mergeable_bvec(struct mddev *mddev,
struct bvec_merge_data *bvm,
struct bio_vec *biovec)
{
- struct mddev *mddev = q->queuedata;
struct r1conf *conf = mddev->private;
sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
int max = biovec->bv_len;
@@ -2946,8 +2945,6 @@ static int run(struct mddev *mddev)
md_set_array_sectors(mddev, raid1_size(mddev, 0, 0));
if (mddev->queue) {
- blk_queue_merge_bvec(mddev->queue, raid1_mergeable_bvec);
-
if (discard_supported)
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD,
mddev->queue);
@@ -3183,6 +3180,7 @@ static struct md_personality raid1_personality =
.quiesce = raid1_quiesce,
.takeover = raid1_takeover,
.congested = raid1_congested,
+ .mergeable_bvec = raid1_mergeable_bvec,
};
static int __init raid_init(void)
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index fb6b88674e87..407c81a820f4 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -674,7 +674,7 @@ static sector_t raid10_find_virt(struct r10conf *conf, sector_t sector, int dev)
/**
* raid10_mergeable_bvec -- tell bio layer if a two requests can be merged
- * @q: request queue
+ * @mddev: the md device
* @bvm: properties of new bio
* @biovec: the request that could be merged to it.
*
@@ -682,11 +682,10 @@ static sector_t raid10_find_virt(struct r10conf *conf, sector_t sector, int dev)
* This requires checking for end-of-chunk if near_copies != raid_disks,
* and for subordinate merge_bvec_fns if merge_check_needed.
*/
-static int raid10_mergeable_bvec(struct request_queue *q,
+static int raid10_mergeable_bvec(struct mddev *mddev,
struct bvec_merge_data *bvm,
struct bio_vec *biovec)
{
- struct mddev *mddev = q->queuedata;
struct r10conf *conf = mddev->private;
sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
int max;
@@ -3756,7 +3755,6 @@ static int run(struct mddev *mddev)
stripe /= conf->geo.near_copies;
if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
- blk_queue_merge_bvec(mddev->queue, raid10_mergeable_bvec);
}
if (md_integrity_register(mddev))
@@ -4717,6 +4715,7 @@ static struct md_personality raid10_personality =
.start_reshape = raid10_start_reshape,
.finish_reshape = raid10_finish_reshape,
.congested = raid10_congested,
+ .mergeable_bvec = raid10_mergeable_bvec,
};
static int __init raid_init(void)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 502a908149c6..2d4a2cc85eb2 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -4170,11 +4170,10 @@ static int raid5_congested(struct mddev *mddev, int bits)
/* We want read requests to align with chunks where possible,
* but write requests don't need to.
*/
-static int raid5_mergeable_bvec(struct request_queue *q,
+static int raid5_mergeable_bvec(struct mddev *mddev,
struct bvec_merge_data *bvm,
struct bio_vec *biovec)
{
- struct mddev *mddev = q->queuedata;
sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
int max;
unsigned int chunk_sectors = mddev->chunk_sectors;
@@ -6237,8 +6236,6 @@ static int run(struct mddev *mddev)
if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
- blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec);
-
chunk_size = mddev->chunk_sectors << 9;
blk_queue_io_min(mddev->queue, chunk_size);
blk_queue_io_opt(mddev->queue, chunk_size *
@@ -7113,6 +7110,7 @@ static struct md_personality raid6_personality =
.quiesce = raid5_quiesce,
.takeover = raid6_takeover,
.congested = raid5_congested,
+ .mergeable_bvec = raid5_mergeable_bvec,
};
static struct md_personality raid5_personality =
{
@@ -7136,6 +7134,7 @@ static struct md_personality raid5_personality =
.quiesce = raid5_quiesce,
.takeover = raid5_takeover,
.congested = raid5_congested,
+ .mergeable_bvec = raid5_mergeable_bvec,
};
static struct md_personality raid4_personality =
@@ -7160,6 +7159,7 @@ static struct md_personality raid4_personality =
.quiesce = raid5_quiesce,
.takeover = raid4_takeover,
.congested = raid5_congested,
+ .mergeable_bvec = raid5_mergeable_bvec,
};
static int __init raid5_init(void)
^ permalink raw reply related
* [md PATCH 09/26] md/linear: remove rcu protections in favour of suspend/resume
From: NeilBrown @ 2015-02-03 21:42 UTC (permalink / raw)
To: linux-raid
In-Reply-To: <20150203213948.3448.80258.stgit@notabene.brown>
The use of 'rcu' to protect accesses to ->private_data so that
the ->private_data could be updated predates the introduction
of mddev_suspend/mddev_resume.
These are a cleaner mechanism for providing stability while
swapping in a new ->private data - it is used by level_store()
to support changing of raid levels.
So get rid of the RCU stuff and just use mddev_suspend, mddev_resume.
As these function call ->quiesce(), we add an empty function for
linear just like for raid0.
Signed-off-by: NeilBrown <neilb@suse.de>
---
drivers/md/linear.c | 44 ++++++++++++++------------------------------
1 file changed, 14 insertions(+), 30 deletions(-)
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 4c2a92ce2b0b..b3e717adbc9b 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -34,7 +34,7 @@ static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector)
lo = 0;
hi = mddev->raid_disks - 1;
- conf = rcu_dereference(mddev->private);
+ conf = mddev->private;
/*
* Binary Search
@@ -70,7 +70,6 @@ static int linear_mergeable_bvec(struct mddev *mddev,
int maxbytes = biovec->bv_len;
struct request_queue *subq;
- rcu_read_lock();
dev0 = which_dev(mddev, sector);
maxsectors = dev0->end_sector - sector;
subq = bdev_get_queue(dev0->rdev->bdev);
@@ -80,7 +79,6 @@ static int linear_mergeable_bvec(struct mddev *mddev,
maxbytes = min(maxbytes, subq->merge_bvec_fn(subq, bvm,
biovec));
}
- rcu_read_unlock();
if (maxsectors < bio_sectors)
maxsectors = 0;
@@ -101,15 +99,13 @@ static int linear_congested(struct mddev *mddev, int bits)
struct linear_conf *conf;
int i, ret = 0;
- rcu_read_lock();
- conf = rcu_dereference(mddev->private);
+ conf = mddev->private;
for (i = 0; i < mddev->raid_disks && !ret ; i++) {
struct request_queue *q = bdev_get_queue(conf->disks[i].rdev->bdev);
ret |= bdi_congested(&q->backing_dev_info, bits);
}
- rcu_read_unlock();
return ret;
}
@@ -118,12 +114,10 @@ static sector_t linear_size(struct mddev *mddev, sector_t sectors, int raid_disk
struct linear_conf *conf;
sector_t array_sectors;
- rcu_read_lock();
- conf = rcu_dereference(mddev->private);
+ conf = mddev->private;
WARN_ONCE(sectors || raid_disks,
"%s does not support generic reshape\n", __func__);
array_sectors = conf->array_sectors;
- rcu_read_unlock();
return array_sectors;
}
@@ -243,33 +237,22 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
if (!newconf)
return -ENOMEM;
- oldconf = rcu_dereference_protected(mddev->private,
- lockdep_is_held(
- &mddev->reconfig_mutex));
+ mddev_suspend(mddev);
+ oldconf = mddev->private;
mddev->raid_disks++;
- rcu_assign_pointer(mddev->private, newconf);
+ mddev->private = newconf;
md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
set_capacity(mddev->gendisk, mddev->array_sectors);
+ mddev_resume(mddev);
revalidate_disk(mddev->gendisk);
- kfree_rcu(oldconf, rcu);
+ kfree(oldconf);
return 0;
}
static int linear_stop (struct mddev *mddev)
{
- struct linear_conf *conf =
- rcu_dereference_protected(mddev->private,
- lockdep_is_held(
- &mddev->reconfig_mutex));
+ struct linear_conf *conf = mddev->private;
- /*
- * We do not require rcu protection here since
- * we hold reconfig_mutex for both linear_add and
- * linear_stop, so they cannot race.
- * We should make sure any old 'conf's are properly
- * freed though.
- */
- rcu_barrier();
blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
kfree(conf);
mddev->private = NULL;
@@ -290,16 +273,12 @@ static void linear_make_request(struct mddev *mddev, struct bio *bio)
}
do {
- rcu_read_lock();
-
tmp_dev = which_dev(mddev, bio->bi_iter.bi_sector);
start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors;
end_sector = tmp_dev->end_sector;
data_offset = tmp_dev->rdev->data_offset;
bio->bi_bdev = tmp_dev->rdev->bdev;
- rcu_read_unlock();
-
if (unlikely(bio->bi_iter.bi_sector >= end_sector ||
bio->bi_iter.bi_sector < start_sector))
goto out_of_bounds;
@@ -346,6 +325,10 @@ static void linear_status (struct seq_file *seq, struct mddev *mddev)
seq_printf(seq, " %dk rounding", mddev->chunk_sectors / 2);
}
+static void linear_quiesce(struct mddev *mddev, int state)
+{
+}
+
static struct md_personality linear_personality =
{
.name = "linear",
@@ -357,6 +340,7 @@ static struct md_personality linear_personality =
.status = linear_status,
.hot_add_disk = linear_add,
.size = linear_size,
+ .quiesce = linear_quiesce,
.congested = linear_congested,
.mergeable_bvec = linear_mergeable_bvec,
};
^ permalink raw reply related
* [md PATCH 10/26] md: split detach operation out from ->stop.
From: NeilBrown @ 2015-02-03 21:42 UTC (permalink / raw)
To: linux-raid
In-Reply-To: <20150203213948.3448.80258.stgit@notabene.brown>
Each md personality has a 'stop' operation which does two
things:
1/ it finalizes some aspects of the array to ensure nothing
is accessing the ->private data
2/ it frees the ->private data.
All the steps in '1' can apply to all arrays and so can be
performed in common code.
This is useful as in the case where we change the personality which
manages an array (in level_store()), it would be helpful to do
step 1 early, and step 2 later.
So split the 'step 1' functionality out into a new mddev_detach().
Signed-off-by: NeilBrown <neilb@suse.de>
---
drivers/md/linear.c | 1 -
drivers/md/md.c | 30 ++++++++++++++++++++++++++----
drivers/md/multipath.c | 2 --
drivers/md/raid0.c | 1 -
drivers/md/raid1.c | 18 +++---------------
drivers/md/raid10.c | 8 --------
drivers/md/raid5.c | 1 -
7 files changed, 29 insertions(+), 32 deletions(-)
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index b3e717adbc9b..c201555b9c6c 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -253,7 +253,6 @@ static int linear_stop (struct mddev *mddev)
{
struct linear_conf *conf = mddev->private;
- blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
kfree(conf);
mddev->private = NULL;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 9f0ff7187136..58f140bef999 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -72,6 +72,7 @@ static struct workqueue_struct *md_misc_wq;
static int remove_and_add_spares(struct mddev *mddev,
struct md_rdev *this);
+static void mddev_detach(struct mddev *mddev);
/*
* Default number of read corrections we'll attempt on an rdev
@@ -3372,6 +3373,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
/* Looks like we have a winner */
mddev_suspend(mddev);
+ mddev_detach(mddev);
mddev->pers->stop(mddev);
if (mddev->pers->sync_request == NULL &&
@@ -4928,18 +4930,17 @@ int md_run(struct mddev *mddev)
(unsigned long long)mddev->array_sectors / 2,
(unsigned long long)mddev->pers->size(mddev, 0, 0) / 2);
err = -EINVAL;
- mddev->pers->stop(mddev);
}
if (err == 0 && mddev->pers->sync_request &&
(mddev->bitmap_info.file || mddev->bitmap_info.offset)) {
err = bitmap_create(mddev);
- if (err) {
+ if (err)
printk(KERN_ERR "%s: failed to create bitmap (%d)\n",
mdname(mddev), err);
- mddev->pers->stop(mddev);
- }
}
if (err) {
+ mddev_detach(mddev);
+ mddev->pers->stop(mddev);
module_put(mddev->pers->owner);
mddev->pers = NULL;
bitmap_destroy(mddev);
@@ -5112,9 +5113,30 @@ void md_stop_writes(struct mddev *mddev)
}
EXPORT_SYMBOL_GPL(md_stop_writes);
+static void mddev_detach(struct mddev *mddev)
+{
+ struct bitmap *bitmap = mddev->bitmap;
+ /* wait for behind writes to complete */
+ if (bitmap && atomic_read(&bitmap->behind_writes) > 0) {
+ printk(KERN_INFO "md:%s: behind writes in progress - waiting to stop.\n",
+ mdname(mddev));
+ /* need to kick something here to make sure I/O goes? */
+ wait_event(bitmap->behind_wait,
+ atomic_read(&bitmap->behind_writes) == 0);
+ }
+ if (mddev->pers->quiesce) {
+ mddev->pers->quiesce(mddev, 1);
+ mddev->pers->quiesce(mddev, 0);
+ }
+ md_unregister_thread(&mddev->thread);
+ if (mddev->queue)
+ blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
+}
+
static void __md_stop(struct mddev *mddev)
{
mddev->ready = 0;
+ mddev_detach(mddev);
mddev->pers->stop(mddev);
if (mddev->pers->sync_request && mddev->to_remove == NULL)
mddev->to_remove = &md_redundancy_group;
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index fedb1b31877d..9fe34453835b 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -504,8 +504,6 @@ static int multipath_stop (struct mddev *mddev)
{
struct mpconf *conf = mddev->private;
- md_unregister_thread(&mddev->thread);
- blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
mempool_destroy(conf->pool);
kfree(conf->multipaths);
kfree(conf);
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 3770c9675b17..01dfca94b663 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -477,7 +477,6 @@ static int raid0_stop(struct mddev *mddev)
{
struct r0conf *conf = mddev->private;
- blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
kfree(conf->strip_zone);
kfree(conf->devlist);
kfree(conf);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 45c512a4b75d..fccea0b39808 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -2954,29 +2954,17 @@ static int run(struct mddev *mddev)
}
ret = md_integrity_register(mddev);
- if (ret)
+ if (ret) {
+ md_unregister_thread(&mddev->thread);
stop(mddev);
+ }
return ret;
}
static int stop(struct mddev *mddev)
{
struct r1conf *conf = mddev->private;
- struct bitmap *bitmap = mddev->bitmap;
-
- /* wait for behind writes to complete */
- if (bitmap && atomic_read(&bitmap->behind_writes) > 0) {
- printk(KERN_INFO "md/raid1:%s: behind writes in progress - waiting to stop.\n",
- mdname(mddev));
- /* need to kick something here to make sure I/O goes? */
- wait_event(bitmap->behind_wait,
- atomic_read(&bitmap->behind_writes) == 0);
- }
-
- freeze_array(conf, 0);
- unfreeze_array(conf);
- md_unregister_thread(&mddev->thread);
if (conf->r1bio_pool)
mempool_destroy(conf->r1bio_pool);
kfree(conf->mirrors);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 407c81a820f4..654fdae906aa 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -3802,14 +3802,6 @@ static int stop(struct mddev *mddev)
{
struct r10conf *conf = mddev->private;
- raise_barrier(conf, 0);
- lower_barrier(conf);
-
- md_unregister_thread(&mddev->thread);
- if (mddev->queue)
- /* the unplug fn references 'conf'*/
- blk_sync_queue(mddev->queue);
-
if (conf->r10bio_pool)
mempool_destroy(conf->r10bio_pool);
safe_put_page(conf->tmppage);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 2d4a2cc85eb2..482526077647 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -6317,7 +6317,6 @@ static int stop(struct mddev *mddev)
{
struct r5conf *conf = mddev->private;
- md_unregister_thread(&mddev->thread);
free_conf(conf);
mddev->private = NULL;
mddev->to_remove = &raid5_attrs_group;
^ permalink raw reply related
* [md PATCH 11/26] md: rename ->stop to ->free
From: NeilBrown @ 2015-02-03 21:42 UTC (permalink / raw)
To: linux-raid
In-Reply-To: <20150203213948.3448.80258.stgit@notabene.brown>
Now that the ->stop function only frees the private data,
rename is accordingly.
Also pass in the private pointer as an arg rather than using
mddev->private. This flexibility will be useful in level_store().
Finally, don't clear ->private. It doesn't make sense to clear
it seeing that isn't what we free, and it is no longer necessary
to clear ->private (it was some time ago before ->to_remove was
introduced).
Setting ->to_remove in ->free() is a bit of a wart, but not a
big problem at the moment.
Signed-off-by: NeilBrown <neilb@suse.de>
---
drivers/md/faulty.c | 8 +++-----
drivers/md/linear.c | 9 +++------
drivers/md/md.c | 10 +++++-----
drivers/md/md.h | 2 +-
drivers/md/multipath.c | 10 ++++------
drivers/md/raid0.c | 12 +++++-------
drivers/md/raid1.c | 14 ++++++--------
drivers/md/raid10.c | 8 +++-----
drivers/md/raid5.c | 12 +++++-------
9 files changed, 35 insertions(+), 50 deletions(-)
diff --git a/drivers/md/faulty.c b/drivers/md/faulty.c
index e8b4574956c7..1277eb26b58a 100644
--- a/drivers/md/faulty.c
+++ b/drivers/md/faulty.c
@@ -332,13 +332,11 @@ static int run(struct mddev *mddev)
return 0;
}
-static int stop(struct mddev *mddev)
+static void faulty_free(struct mddev *mddev, void *priv)
{
- struct faulty_conf *conf = mddev->private;
+ struct faulty_conf *conf = priv;
kfree(conf);
- mddev->private = NULL;
- return 0;
}
static struct md_personality faulty_personality =
@@ -348,7 +346,7 @@ static struct md_personality faulty_personality =
.owner = THIS_MODULE,
.make_request = make_request,
.run = run,
- .stop = stop,
+ .free = faulty_free,
.status = status,
.check_reshape = reshape,
.size = faulty_size,
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index c201555b9c6c..fa7d577f3d12 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -249,14 +249,11 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
return 0;
}
-static int linear_stop (struct mddev *mddev)
+static void linear_free(struct mddev *mddev, void *priv)
{
- struct linear_conf *conf = mddev->private;
+ struct linear_conf *conf = priv;
kfree(conf);
- mddev->private = NULL;
-
- return 0;
}
static void linear_make_request(struct mddev *mddev, struct bio *bio)
@@ -335,7 +332,7 @@ static struct md_personality linear_personality =
.owner = THIS_MODULE,
.make_request = linear_make_request,
.run = linear_run,
- .stop = linear_stop,
+ .free = linear_free,
.status = linear_status,
.hot_add_disk = linear_add,
.size = linear_size,
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 58f140bef999..2920fd004865 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -293,8 +293,8 @@ static void md_make_request(struct request_queue *q, struct bio *bio)
/* mddev_suspend makes sure no new requests are submitted
* to the device, and that any requests that have been submitted
* are completely handled.
- * Once ->stop is called and completes, the module will be completely
- * unused.
+ * Once mddev_detach() is called and completes, the module will be
+ * completely unused.
*/
void mddev_suspend(struct mddev *mddev)
{
@@ -3374,7 +3374,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
/* Looks like we have a winner */
mddev_suspend(mddev);
mddev_detach(mddev);
- mddev->pers->stop(mddev);
+ mddev->pers->free(mddev, mddev->private);
if (mddev->pers->sync_request == NULL &&
pers->sync_request != NULL) {
@@ -4940,7 +4940,7 @@ int md_run(struct mddev *mddev)
}
if (err) {
mddev_detach(mddev);
- mddev->pers->stop(mddev);
+ mddev->pers->free(mddev, mddev->private);
module_put(mddev->pers->owner);
mddev->pers = NULL;
bitmap_destroy(mddev);
@@ -5137,7 +5137,7 @@ static void __md_stop(struct mddev *mddev)
{
mddev->ready = 0;
mddev_detach(mddev);
- mddev->pers->stop(mddev);
+ mddev->pers->free(mddev, mddev->private);
if (mddev->pers->sync_request && mddev->to_remove == NULL)
mddev->to_remove = &md_redundancy_group;
module_put(mddev->pers->owner);
diff --git a/drivers/md/md.h b/drivers/md/md.h
index bee5b852c33f..37e7c17e56a6 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -465,7 +465,7 @@ struct md_personality
struct module *owner;
void (*make_request)(struct mddev *mddev, struct bio *bio);
int (*run)(struct mddev *mddev);
- int (*stop)(struct mddev *mddev);
+ void (*free)(struct mddev *mddev, void *priv);
void (*status)(struct seq_file *seq, struct mddev *mddev);
/* error_handler must set ->faulty and clear ->in_sync
* if appropriate, and should abort recovery if needed
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 9fe34453835b..ac3ede2bd00e 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -399,7 +399,7 @@ static int multipath_run (struct mddev *mddev)
/*
* copy the already verified devices into our private MULTIPATH
* bookkeeping area. [whatever we allocate in multipath_run(),
- * should be freed in multipath_stop()]
+ * should be freed in multipath_free()]
*/
conf = kzalloc(sizeof(struct mpconf), GFP_KERNEL);
@@ -500,15 +500,13 @@ out:
return -EIO;
}
-static int multipath_stop (struct mddev *mddev)
+static void multipath_free(struct mddev *mddev, void *priv)
{
- struct mpconf *conf = mddev->private;
+ struct mpconf *conf = priv;
mempool_destroy(conf->pool);
kfree(conf->multipaths);
kfree(conf);
- mddev->private = NULL;
- return 0;
}
static struct md_personality multipath_personality =
@@ -518,7 +516,7 @@ static struct md_personality multipath_personality =
.owner = THIS_MODULE,
.make_request = multipath_make_request,
.run = multipath_run,
- .stop = multipath_stop,
+ .free = multipath_free,
.status = multipath_status,
.error_handler = multipath_error,
.hot_add_disk = multipath_add_disk,
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 01dfca94b663..a13f738a7b39 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -415,7 +415,7 @@ static sector_t raid0_size(struct mddev *mddev, sector_t sectors, int raid_disks
return array_sectors;
}
-static int raid0_stop(struct mddev *mddev);
+static void raid0_free(struct mddev *mddev, void *priv);
static int raid0_run(struct mddev *mddev)
{
@@ -468,20 +468,18 @@ static int raid0_run(struct mddev *mddev)
ret = md_integrity_register(mddev);
if (ret)
- raid0_stop(mddev);
+ raid0_free(mddev, conf);
return ret;
}
-static int raid0_stop(struct mddev *mddev)
+static void raid0_free(struct mddev *mddev, void *priv)
{
- struct r0conf *conf = mddev->private;
+ struct r0conf *conf = priv;
kfree(conf->strip_zone);
kfree(conf->devlist);
kfree(conf);
- mddev->private = NULL;
- return 0;
}
/*
@@ -715,7 +713,7 @@ static struct md_personality raid0_personality=
.owner = THIS_MODULE,
.make_request = raid0_make_request,
.run = raid0_run,
- .stop = raid0_stop,
+ .free = raid0_free,
.status = raid0_status,
.size = raid0_size,
.takeover = raid0_takeover,
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index fccea0b39808..5dd0c2e59ab9 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -2872,7 +2872,7 @@ static struct r1conf *setup_conf(struct mddev *mddev)
return ERR_PTR(err);
}
-static int stop(struct mddev *mddev);
+static void raid1_free(struct mddev *mddev, void *priv);
static int run(struct mddev *mddev)
{
struct r1conf *conf;
@@ -2894,7 +2894,7 @@ static int run(struct mddev *mddev)
/*
* copy the already verified devices into our private RAID1
* bookkeeping area. [whatever we allocate in run(),
- * should be freed in stop()]
+ * should be freed in raid1_free()]
*/
if (mddev->private == NULL)
conf = setup_conf(mddev);
@@ -2956,14 +2956,14 @@ static int run(struct mddev *mddev)
ret = md_integrity_register(mddev);
if (ret) {
md_unregister_thread(&mddev->thread);
- stop(mddev);
+ raid1_free(mddev, conf);
}
return ret;
}
-static int stop(struct mddev *mddev)
+static void raid1_free(struct mddev *mddev, void *priv)
{
- struct r1conf *conf = mddev->private;
+ struct r1conf *conf = priv;
if (conf->r1bio_pool)
mempool_destroy(conf->r1bio_pool);
@@ -2971,8 +2971,6 @@ static int stop(struct mddev *mddev)
safe_put_page(conf->tmppage);
kfree(conf->poolinfo);
kfree(conf);
- mddev->private = NULL;
- return 0;
}
static int raid1_resize(struct mddev *mddev, sector_t sectors)
@@ -3155,7 +3153,7 @@ static struct md_personality raid1_personality =
.owner = THIS_MODULE,
.make_request = make_request,
.run = run,
- .stop = stop,
+ .free = raid1_free,
.status = status,
.error_handler = error,
.hot_add_disk = raid1_add_disk,
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 654fdae906aa..d1203cddb024 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -3798,9 +3798,9 @@ out:
return -EIO;
}
-static int stop(struct mddev *mddev)
+static void raid10_free(struct mddev *mddev, void *priv)
{
- struct r10conf *conf = mddev->private;
+ struct r10conf *conf = priv;
if (conf->r10bio_pool)
mempool_destroy(conf->r10bio_pool);
@@ -3809,8 +3809,6 @@ static int stop(struct mddev *mddev)
kfree(conf->mirrors_old);
kfree(conf->mirrors_new);
kfree(conf);
- mddev->private = NULL;
- return 0;
}
static void raid10_quiesce(struct mddev *mddev, int state)
@@ -4692,7 +4690,7 @@ static struct md_personality raid10_personality =
.owner = THIS_MODULE,
.make_request = make_request,
.run = run,
- .stop = stop,
+ .free = raid10_free,
.status = status,
.error_handler = error,
.hot_add_disk = raid10_add_disk,
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 482526077647..dab908b2aa9a 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -6313,14 +6313,12 @@ abort:
return -EIO;
}
-static int stop(struct mddev *mddev)
+static void raid5_free(struct mddev *mddev, void *priv)
{
- struct r5conf *conf = mddev->private;
+ struct r5conf *conf = priv;
free_conf(conf);
- mddev->private = NULL;
mddev->to_remove = &raid5_attrs_group;
- return 0;
}
static void status(struct seq_file *seq, struct mddev *mddev)
@@ -7094,7 +7092,7 @@ static struct md_personality raid6_personality =
.owner = THIS_MODULE,
.make_request = make_request,
.run = run,
- .stop = stop,
+ .free = raid5_free,
.status = status,
.error_handler = error,
.hot_add_disk = raid5_add_disk,
@@ -7118,7 +7116,7 @@ static struct md_personality raid5_personality =
.owner = THIS_MODULE,
.make_request = make_request,
.run = run,
- .stop = stop,
+ .free = raid5_free,
.status = status,
.error_handler = error,
.hot_add_disk = raid5_add_disk,
@@ -7143,7 +7141,7 @@ static struct md_personality raid4_personality =
.owner = THIS_MODULE,
.make_request = make_request,
.run = run,
- .stop = stop,
+ .free = raid5_free,
.status = status,
.error_handler = error,
.hot_add_disk = raid5_add_disk,
^ permalink raw reply related
* [md PATCH 12/26] md: level_store: group all important changes into one place.
From: NeilBrown @ 2015-02-03 21:42 UTC (permalink / raw)
To: linux-raid
In-Reply-To: <20150203213948.3448.80258.stgit@notabene.brown>
Gather all the changes that can happen atomically and might
be relevant to other code into one place. This will
make it easier to refine the locking.
Note that this puts quite a few things between mddev_detach()
and ->free(). Enabling this was the point of some recent patches.
Signed-off-by: NeilBrown <neilb@suse.de>
---
drivers/md/md.c | 62 ++++++++++++++++++++++++++++---------------------------
1 file changed, 32 insertions(+), 30 deletions(-)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 2920fd004865..58f531f8dcc2 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -3280,9 +3280,9 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
{
char clevel[16];
ssize_t rv = len;
- struct md_personality *pers;
+ struct md_personality *pers, *oldpers;
long level;
- void *priv;
+ void *priv, *oldpriv;
struct md_rdev *rdev;
if (mddev->pers == NULL) {
@@ -3374,9 +3374,35 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
/* Looks like we have a winner */
mddev_suspend(mddev);
mddev_detach(mddev);
- mddev->pers->free(mddev, mddev->private);
+ oldpers = mddev->pers;
+ oldpriv = mddev->private;
+ mddev->pers = pers;
+ mddev->private = priv;
+ strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
+ mddev->level = mddev->new_level;
+ mddev->layout = mddev->new_layout;
+ mddev->chunk_sectors = mddev->new_chunk_sectors;
+ mddev->delta_disks = 0;
+ mddev->reshape_backwards = 0;
+ mddev->degraded = 0;
+
+ if (oldpers->sync_request == NULL &&
+ mddev->external) {
+ /* We are converting from a no-redundancy array
+ * to a redundancy array and metadata is managed
+ * externally so we need to be sure that writes
+ * won't block due to a need to transition
+ * clean->dirty
+ * until external management is started.
+ */
+ mddev->in_sync = 0;
+ mddev->safemode_delay = 0;
+ mddev->safemode = 0;
+ }
- if (mddev->pers->sync_request == NULL &&
+ oldpers->free(mddev, oldpriv);
+
+ if (oldpers->sync_request == NULL &&
pers->sync_request != NULL) {
/* need to add the md_redundancy_group */
if (sysfs_create_group(&mddev->kobj, &md_redundancy_group))
@@ -3385,27 +3411,13 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
mdname(mddev));
mddev->sysfs_action = sysfs_get_dirent(mddev->kobj.sd, "sync_action");
}
- if (mddev->pers->sync_request != NULL &&
+ if (oldpers->sync_request != NULL &&
pers->sync_request == NULL) {
/* need to remove the md_redundancy_group */
if (mddev->to_remove == NULL)
mddev->to_remove = &md_redundancy_group;
}
- if (mddev->pers->sync_request == NULL &&
- mddev->external) {
- /* We are converting from a no-redundancy array
- * to a redundancy array and metadata is managed
- * externally so we need to be sure that writes
- * won't block due to a need to transition
- * clean->dirty
- * until external management is started.
- */
- mddev->in_sync = 0;
- mddev->safemode_delay = 0;
- mddev->safemode = 0;
- }
-
rdev_for_each(rdev, mddev) {
if (rdev->raid_disk < 0)
continue;
@@ -3431,17 +3443,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
}
}
- module_put(mddev->pers->owner);
- mddev->pers = pers;
- mddev->private = priv;
- strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
- mddev->level = mddev->new_level;
- mddev->layout = mddev->new_layout;
- mddev->chunk_sectors = mddev->new_chunk_sectors;
- mddev->delta_disks = 0;
- mddev->reshape_backwards = 0;
- mddev->degraded = 0;
- if (mddev->pers->sync_request == NULL) {
+ if (pers->sync_request == NULL) {
/* this is now an array without redundancy, so
* it must always be in_sync
*/
^ permalink raw reply related
* [md PATCH 13/26] md: protect ->pers changes with mddev->lock
From: NeilBrown @ 2015-02-03 21:42 UTC (permalink / raw)
To: linux-raid
In-Reply-To: <20150203213948.3448.80258.stgit@notabene.brown>
->pers is already protected by ->reconfig_mutex, and
cannot possibly change when there are threads running or
outstanding IO.
However there are some places where we access ->pers
not in a thread or IO context, and where ->reconfig_mutex
is unnecessarily heavy-weight: level_show and md_seq_show().
So protect all changes, and those accesses, with ->lock.
This is a step toward taking those accesses out from under
reconfig_mutex.
Signed-off-by: NeilBrown <neilb@suse.de>
---
drivers/md/md.c | 51 ++++++++++++++++++++++++++++++++-------------------
drivers/md/md.h | 1 +
2 files changed, 33 insertions(+), 19 deletions(-)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 58f531f8dcc2..421d47e2d457 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -3264,15 +3264,20 @@ __ATTR(safe_mode_delay, S_IRUGO|S_IWUSR,safe_delay_show, safe_delay_store);
static ssize_t
level_show(struct mddev *mddev, char *page)
{
- struct md_personality *p = mddev->pers;
+ struct md_personality *p;
+ int ret;
+ spin_lock(&mddev->lock);
+ p = mddev->pers;
if (p)
- return sprintf(page, "%s\n", p->name);
+ ret = sprintf(page, "%s\n", p->name);
else if (mddev->clevel[0])
- return sprintf(page, "%s\n", mddev->clevel);
+ ret = sprintf(page, "%s\n", mddev->clevel);
else if (mddev->level != LEVEL_NONE)
- return sprintf(page, "%d\n", mddev->level);
+ ret = sprintf(page, "%d\n", mddev->level);
else
- return 0;
+ ret = 0;
+ spin_unlock(&mddev->lock);
+ return ret;
}
static ssize_t
@@ -3374,6 +3379,8 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
/* Looks like we have a winner */
mddev_suspend(mddev);
mddev_detach(mddev);
+
+ spin_lock(&mddev->lock);
oldpers = mddev->pers;
oldpriv = mddev->private;
mddev->pers = pers;
@@ -3385,6 +3392,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
mddev->delta_disks = 0;
mddev->reshape_backwards = 0;
mddev->degraded = 0;
+ spin_unlock(&mddev->lock);
if (oldpers->sync_request == NULL &&
mddev->external) {
@@ -4866,7 +4874,6 @@ int md_run(struct mddev *mddev)
mddev->clevel);
return -EINVAL;
}
- mddev->pers = pers;
spin_unlock(&pers_lock);
if (mddev->level != pers->level) {
mddev->level = pers->level;
@@ -4877,7 +4884,6 @@ int md_run(struct mddev *mddev)
if (mddev->reshape_position != MaxSector &&
pers->start_reshape == NULL) {
/* This personality cannot handle reshaping... */
- mddev->pers = NULL;
module_put(pers->owner);
return -EINVAL;
}
@@ -4921,10 +4927,10 @@ int md_run(struct mddev *mddev)
if (start_readonly && mddev->ro == 0)
mddev->ro = 2; /* read-only, but switch on first write */
- err = mddev->pers->run(mddev);
+ err = pers->run(mddev);
if (err)
printk(KERN_ERR "md: pers->run() failed ...\n");
- else if (mddev->pers->size(mddev, 0, 0) < mddev->array_sectors) {
+ else if (pers->size(mddev, 0, 0) < mddev->array_sectors) {
WARN_ONCE(!mddev->external_size, "%s: default size too small,"
" but 'external_size' not in effect?\n", __func__);
printk(KERN_ERR
@@ -4933,7 +4939,7 @@ int md_run(struct mddev *mddev)
(unsigned long long)mddev->pers->size(mddev, 0, 0) / 2);
err = -EINVAL;
}
- if (err == 0 && mddev->pers->sync_request &&
+ if (err == 0 && pers->sync_request &&
(mddev->bitmap_info.file || mddev->bitmap_info.offset)) {
err = bitmap_create(mddev);
if (err)
@@ -4942,9 +4948,8 @@ int md_run(struct mddev *mddev)
}
if (err) {
mddev_detach(mddev);
- mddev->pers->free(mddev, mddev->private);
- module_put(mddev->pers->owner);
- mddev->pers = NULL;
+ pers->free(mddev, mddev->private);
+ module_put(pers->owner);
bitmap_destroy(mddev);
return err;
}
@@ -4953,7 +4958,7 @@ int md_run(struct mddev *mddev)
mddev->queue->backing_dev_info.congested_fn = md_congested;
blk_queue_merge_bvec(mddev->queue, md_mergeable_bvec);
}
- if (mddev->pers->sync_request) {
+ if (pers->sync_request) {
if (mddev->kobj.sd &&
sysfs_create_group(&mddev->kobj, &md_redundancy_group))
printk(KERN_WARNING
@@ -4972,7 +4977,10 @@ int md_run(struct mddev *mddev)
mddev->safemode_delay = (200 * HZ)/1000 +1; /* 200 msec delay */
mddev->in_sync = 1;
smp_wmb();
+ spin_lock(&mddev->lock);
+ mddev->pers = pers;
mddev->ready = 1;
+ spin_unlock(&mddev->lock);
rdev_for_each(rdev, mddev)
if (rdev->raid_disk >= 0)
if (sysfs_link_rdev(mddev, rdev))
@@ -5137,13 +5145,16 @@ static void mddev_detach(struct mddev *mddev)
static void __md_stop(struct mddev *mddev)
{
- mddev->ready = 0;
+ struct md_personality *pers = mddev->pers;
mddev_detach(mddev);
- mddev->pers->free(mddev, mddev->private);
- if (mddev->pers->sync_request && mddev->to_remove == NULL)
- mddev->to_remove = &md_redundancy_group;
- module_put(mddev->pers->owner);
+ spin_lock(&mddev->lock);
+ mddev->ready = 0;
mddev->pers = NULL;
+ spin_unlock(&mddev->lock);
+ pers->free(mddev, mddev->private);
+ if (pers->sync_request && mddev->to_remove == NULL)
+ mddev->to_remove = &md_redundancy_group;
+ module_put(pers->owner);
clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
}
@@ -6942,6 +6953,7 @@ static int md_seq_show(struct seq_file *seq, void *v)
if (mddev_lock(mddev) < 0)
return -EINTR;
+ spin_lock(&mddev->lock);
if (mddev->pers || mddev->raid_disks || !list_empty(&mddev->disks)) {
seq_printf(seq, "%s : %sactive", mdname(mddev),
mddev->pers ? "" : "in");
@@ -7012,6 +7024,7 @@ static int md_seq_show(struct seq_file *seq, void *v)
seq_printf(seq, "\n");
}
+ spin_unlock(&mddev->lock);
mddev_unlock(mddev);
return 0;
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 37e7c17e56a6..e41559dccdc9 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -391,6 +391,7 @@ struct mddev {
* rdev superblocks, events
* clearing MD_CHANGE_*
* in_sync - and related safemode and MD_CHANGE changes
+ * pers (also protected by reconfig_mutex and pending IO).
*/
spinlock_t lock;
wait_queue_head_t sb_wait; /* for waiting on superblock updates */
^ permalink raw reply related
* [md PATCH 14/26] md/bitmap: protect clearing of ->bitmap by mddev->lock
From: NeilBrown @ 2015-02-03 21:42 UTC (permalink / raw)
To: linux-raid
In-Reply-To: <20150203213948.3448.80258.stgit@notabene.brown>
This makes it safe to inspect the struct while holding only
the spinlock.
Signed-off-by: NeilBrown <neilb@suse.de>
---
drivers/md/bitmap.c | 2 ++
drivers/md/md.h | 1 +
2 files changed, 3 insertions(+)
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 1695ee5f3ffc..3424b1915fc4 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -1619,7 +1619,9 @@ void bitmap_destroy(struct mddev *mddev)
return;
mutex_lock(&mddev->bitmap_info.mutex);
+ spin_lock(&mddev->lock);
mddev->bitmap = NULL; /* disconnect from the md device */
+ spin_unlock(&mddev->lock);
mutex_unlock(&mddev->bitmap_info.mutex);
if (mddev->thread)
mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT;
diff --git a/drivers/md/md.h b/drivers/md/md.h
index e41559dccdc9..8770308a8052 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -392,6 +392,7 @@ struct mddev {
* clearing MD_CHANGE_*
* in_sync - and related safemode and MD_CHANGE changes
* pers (also protected by reconfig_mutex and pending IO).
+ * clearing ->bitmap
*/
spinlock_t lock;
wait_queue_head_t sb_wait; /* for waiting on superblock updates */
^ permalink raw reply related
* [md PATCH 16/26] md/raid5: use ->lock to protect accessing raid5 sysfs attributes.
From: NeilBrown @ 2015-02-03 21:42 UTC (permalink / raw)
To: linux-raid
In-Reply-To: <20150203213948.3448.80258.stgit@notabene.brown>
It is important that mddev->private isn't freed while
a sysfs attribute function is accessing it.
So use mddev->lock to protect the setting of ->private to NULL, and
take that lock when checking ->private for NULL and de-referencing it
in the sysfs access functions.
This only applies to the read ('show') side of access. Write
access will be handled separately.
Signed-off-by: NeilBrown <neilb@suse.de>
---
drivers/md/raid5.c | 44 ++++++++++++++++++++++++++++----------------
1 file changed, 28 insertions(+), 16 deletions(-)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index dab908b2aa9a..d5b80174b3b3 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5354,11 +5354,14 @@ static void raid5d(struct md_thread *thread)
static ssize_t
raid5_show_stripe_cache_size(struct mddev *mddev, char *page)
{
- struct r5conf *conf = mddev->private;
+ struct r5conf *conf;
+ int ret = 0;
+ spin_lock(&mddev->lock);
+ conf = mddev->private;
if (conf)
- return sprintf(page, "%d\n", conf->max_nr_stripes);
- else
- return 0;
+ ret = sprintf(page, "%d\n", conf->max_nr_stripes);
+ spin_unlock(&mddev->lock);
+ return ret;
}
int
@@ -5422,11 +5425,14 @@ raid5_stripecache_size = __ATTR(stripe_cache_size, S_IRUGO | S_IWUSR,
static ssize_t
raid5_show_preread_threshold(struct mddev *mddev, char *page)
{
- struct r5conf *conf = mddev->private;
+ struct r5conf *conf;
+ int ret = 0;
+ spin_lock(&mddev->lock);
+ conf = mddev->private;
if (conf)
- return sprintf(page, "%d\n", conf->bypass_threshold);
- else
- return 0;
+ ret = sprintf(page, "%d\n", conf->bypass_threshold);
+ spin_unlock(&mddev->lock);
+ return ret;
}
static ssize_t
@@ -5456,11 +5462,14 @@ raid5_preread_bypass_threshold = __ATTR(preread_bypass_threshold,
static ssize_t
raid5_show_skip_copy(struct mddev *mddev, char *page)
{
- struct r5conf *conf = mddev->private;
+ struct r5conf *conf;
+ int ret = 0;
+ spin_lock(&mddev->lock);
+ conf = mddev->private;
if (conf)
- return sprintf(page, "%d\n", conf->skip_copy);
- else
- return 0;
+ ret = sprintf(page, "%d\n", conf->skip_copy);
+ spin_unlock(&mddev->lock);
+ return ret;
}
static ssize_t
@@ -5512,11 +5521,14 @@ raid5_stripecache_active = __ATTR_RO(stripe_cache_active);
static ssize_t
raid5_show_group_thread_cnt(struct mddev *mddev, char *page)
{
- struct r5conf *conf = mddev->private;
+ struct r5conf *conf;
+ int ret = 0;
+ spin_lock(&mddev->lock);
+ conf = mddev->private;
if (conf)
- return sprintf(page, "%d\n", conf->worker_cnt_per_group);
- else
- return 0;
+ ret = sprintf(page, "%d\n", conf->worker_cnt_per_group);
+ spin_unlock(&mddev->lock);
+ return ret;
}
static int alloc_thread_groups(struct r5conf *conf, int cnt,
^ permalink raw reply related
* [md PATCH 15/26] md: remove need for mddev_lock() in md_seq_show()
From: NeilBrown @ 2015-02-03 21:42 UTC (permalink / raw)
To: linux-raid
In-Reply-To: <20150203213948.3448.80258.stgit@notabene.brown>
The only access in md_seq_show that could suffer from races
not protected by ->lock is walking the rdev list.
This can receive sufficient protection from 'rcu'.
So use rdev_for_each_rcu() and get rid of mddev_lock().
Now reading /proc/mdstat will never block in md_seq_show.
Signed-off-by: NeilBrown <neilb@suse.de>
---
drivers/md/md.c | 8 +++-----
1 file changed, 3 insertions(+), 5 deletions(-)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 421d47e2d457..4caa414fe6a3 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -6950,9 +6950,6 @@ static int md_seq_show(struct seq_file *seq, void *v)
return 0;
}
- if (mddev_lock(mddev) < 0)
- return -EINTR;
-
spin_lock(&mddev->lock);
if (mddev->pers || mddev->raid_disks || !list_empty(&mddev->disks)) {
seq_printf(seq, "%s : %sactive", mdname(mddev),
@@ -6966,7 +6963,8 @@ static int md_seq_show(struct seq_file *seq, void *v)
}
sectors = 0;
- rdev_for_each(rdev, mddev) {
+ rcu_read_lock();
+ rdev_for_each_rcu(rdev, mddev) {
char b[BDEVNAME_SIZE];
seq_printf(seq, " %s[%d]",
bdevname(rdev->bdev,b), rdev->desc_nr);
@@ -6982,6 +6980,7 @@ static int md_seq_show(struct seq_file *seq, void *v)
seq_printf(seq, "(R)");
sectors += rdev->sectors;
}
+ rcu_read_unlock();
if (!list_empty(&mddev->disks)) {
if (mddev->pers)
@@ -7025,7 +7024,6 @@ static int md_seq_show(struct seq_file *seq, void *v)
seq_printf(seq, "\n");
}
spin_unlock(&mddev->lock);
- mddev_unlock(mddev);
return 0;
}
^ permalink raw reply related
* [md PATCH 17/26] md: remove mddev_lock() from md_attr_show()
From: NeilBrown @ 2015-02-03 21:42 UTC (permalink / raw)
To: linux-raid
In-Reply-To: <20150203213948.3448.80258.stgit@notabene.brown>
Most attributes can be read safely without any locking.
A race might lead to a slightly out-dated value, but nothing wrong.
We already have locking in some places where needed.
All that remains is can_clear_show(), behind_writes_used_show()
and action_show() which are easily fixed.
Signed-off-by: NeilBrown <neilb@suse.de>
---
drivers/md/bitmap.c | 13 ++++++++++---
drivers/md/md.c | 23 ++++++++++-------------
2 files changed, 20 insertions(+), 16 deletions(-)
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 3424b1915fc4..3a5767968ba0 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -2211,11 +2211,13 @@ __ATTR(metadata, S_IRUGO|S_IWUSR, metadata_show, metadata_store);
static ssize_t can_clear_show(struct mddev *mddev, char *page)
{
int len;
+ spin_lock(&mddev->lock);
if (mddev->bitmap)
len = sprintf(page, "%s\n", (mddev->bitmap->need_sync ?
"false" : "true"));
else
len = sprintf(page, "\n");
+ spin_unlock(&mddev->lock);
return len;
}
@@ -2240,10 +2242,15 @@ __ATTR(can_clear, S_IRUGO|S_IWUSR, can_clear_show, can_clear_store);
static ssize_t
behind_writes_used_show(struct mddev *mddev, char *page)
{
+ ssize_t ret;
+ spin_lock(&mddev->lock);
if (mddev->bitmap == NULL)
- return sprintf(page, "0\n");
- return sprintf(page, "%lu\n",
- mddev->bitmap->behind_writes_used);
+ ret = sprintf(page, "0\n");
+ else
+ ret = sprintf(page, "%lu\n",
+ mddev->bitmap->behind_writes_used);
+ spin_unlock(&mddev->lock);
+ return ret;
}
static ssize_t
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 4caa414fe6a3..b7f48238a92d 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -4042,20 +4042,21 @@ static ssize_t
action_show(struct mddev *mddev, char *page)
{
char *type = "idle";
- if (test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
+ unsigned long recovery = mddev->recovery;
+ if (test_bit(MD_RECOVERY_FROZEN, &recovery))
type = "frozen";
- else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
- (!mddev->ro && test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))) {
- if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
+ else if (test_bit(MD_RECOVERY_RUNNING, &recovery) ||
+ (!mddev->ro && test_bit(MD_RECOVERY_NEEDED, &recovery))) {
+ if (test_bit(MD_RECOVERY_RESHAPE, &recovery))
type = "reshape";
- else if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
- if (!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
+ else if (test_bit(MD_RECOVERY_SYNC, &recovery)) {
+ if (!test_bit(MD_RECOVERY_REQUESTED, &recovery))
type = "resync";
- else if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery))
+ else if (test_bit(MD_RECOVERY_CHECK, &recovery))
type = "check";
else
type = "repair";
- } else if (test_bit(MD_RECOVERY_RECOVER, &mddev->recovery))
+ } else if (test_bit(MD_RECOVERY_RECOVER, &recovery))
type = "recover";
}
return sprintf(page, "%s\n", type);
@@ -4572,11 +4573,7 @@ md_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
mddev_get(mddev);
spin_unlock(&all_mddevs_lock);
- rv = mddev_lock(mddev);
- if (!rv) {
- rv = entry->show(mddev, page);
- mddev_unlock(mddev);
- }
+ rv = entry->show(mddev, page);
mddev_put(mddev);
return rv;
}
^ permalink raw reply related
* [md PATCH 18/26] md: remove mddev_lock from rdev_attr_show()
From: NeilBrown @ 2015-02-03 21:42 UTC (permalink / raw)
To: linux-raid
In-Reply-To: <20150203213948.3448.80258.stgit@notabene.brown>
No rdev attributes need locking for 'show', though
state_show() might benefit from ensuring it sees a
consistent set of flags.
None even use rdev->mddev, so testing for it isn't really
needed and it certainly doesn't need to be held constant.
So improve state_show() and remove the locking.
Signed-off-by: NeilBrown <neilb@suse.de>
---
drivers/md/md.c | 36 ++++++++++++++----------------------
1 file changed, 14 insertions(+), 22 deletions(-)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index b7f48238a92d..cbbac7b7238a 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2419,40 +2419,41 @@ state_show(struct md_rdev *rdev, char *page)
{
char *sep = "";
size_t len = 0;
+ unsigned long flags = ACCESS_ONCE(rdev->flags);
- if (test_bit(Faulty, &rdev->flags) ||
+ if (test_bit(Faulty, &flags) ||
rdev->badblocks.unacked_exist) {
len+= sprintf(page+len, "%sfaulty",sep);
sep = ",";
}
- if (test_bit(In_sync, &rdev->flags)) {
+ if (test_bit(In_sync, &flags)) {
len += sprintf(page+len, "%sin_sync",sep);
sep = ",";
}
- if (test_bit(WriteMostly, &rdev->flags)) {
+ if (test_bit(WriteMostly, &flags)) {
len += sprintf(page+len, "%swrite_mostly",sep);
sep = ",";
}
- if (test_bit(Blocked, &rdev->flags) ||
+ if (test_bit(Blocked, &flags) ||
(rdev->badblocks.unacked_exist
- && !test_bit(Faulty, &rdev->flags))) {
+ && !test_bit(Faulty, &flags))) {
len += sprintf(page+len, "%sblocked", sep);
sep = ",";
}
- if (!test_bit(Faulty, &rdev->flags) &&
- !test_bit(In_sync, &rdev->flags)) {
+ if (!test_bit(Faulty, &flags) &&
+ !test_bit(In_sync, &flags)) {
len += sprintf(page+len, "%sspare", sep);
sep = ",";
}
- if (test_bit(WriteErrorSeen, &rdev->flags)) {
+ if (test_bit(WriteErrorSeen, &flags)) {
len += sprintf(page+len, "%swrite_error", sep);
sep = ",";
}
- if (test_bit(WantReplacement, &rdev->flags)) {
+ if (test_bit(WantReplacement, &flags)) {
len += sprintf(page+len, "%swant_replacement", sep);
sep = ",";
}
- if (test_bit(Replacement, &rdev->flags)) {
+ if (test_bit(Replacement, &flags)) {
len += sprintf(page+len, "%sreplacement", sep);
sep = ",";
}
@@ -2965,21 +2966,12 @@ rdev_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
{
struct rdev_sysfs_entry *entry = container_of(attr, struct rdev_sysfs_entry, attr);
struct md_rdev *rdev = container_of(kobj, struct md_rdev, kobj);
- struct mddev *mddev = rdev->mddev;
- ssize_t rv;
if (!entry->show)
return -EIO;
-
- rv = mddev ? mddev_lock(mddev) : -EBUSY;
- if (!rv) {
- if (rdev->mddev == NULL)
- rv = -EBUSY;
- else
- rv = entry->show(rdev, page);
- mddev_unlock(mddev);
- }
- return rv;
+ if (!rdev->mddev)
+ return -EBUSY;
+ return entry->show(rdev, page);
}
static ssize_t
^ permalink raw reply related
* [md PATCH 19/26] md: remove unnecessary 'buf' from get_bitmap_file.
From: NeilBrown @ 2015-02-03 21:42 UTC (permalink / raw)
To: linux-raid
In-Reply-To: <20150203213948.3448.80258.stgit@notabene.brown>
'buf' is only used because d_path fills from the end of the
buffer instead of from the start.
We don't need a separate buf to handle that, we just need to use
memmove() to move the string to the start.
Signed-off-by: NeilBrown <neilb@suse.de>
---
drivers/md/md.c | 12 ++++--------
1 file changed, 4 insertions(+), 8 deletions(-)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index cbbac7b7238a..01793f24f8de 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5502,7 +5502,7 @@ static int get_array_info(struct mddev *mddev, void __user *arg)
static int get_bitmap_file(struct mddev *mddev, void __user * arg)
{
mdu_bitmap_file_t *file = NULL; /* too big for stack allocation */
- char *ptr, *buf = NULL;
+ char *ptr;
int err = -ENOMEM;
file = kmalloc(sizeof(*file), GFP_NOIO);
@@ -5516,23 +5516,19 @@ static int get_bitmap_file(struct mddev *mddev, void __user * arg)
goto copy_out;
}
- buf = kmalloc(sizeof(file->pathname), GFP_KERNEL);
- if (!buf)
- goto out;
-
ptr = d_path(&mddev->bitmap->storage.file->f_path,
- buf, sizeof(file->pathname));
+ file->pathname, sizeof(file->pathname));
if (IS_ERR(ptr))
goto out;
- strcpy(file->pathname, ptr);
+ memmove(file->pathname, ptr,
+ sizeof(file->pathname)-(ptr-file->pathname));
copy_out:
err = 0;
if (copy_to_user(arg, file, sizeof(*file)))
err = -EFAULT;
out:
- kfree(buf);
kfree(file);
return err;
}
^ permalink raw reply related
* [md PATCH 20/26] md: tidy up set_bitmap_file
From: NeilBrown @ 2015-02-03 21:42 UTC (permalink / raw)
To: linux-raid
In-Reply-To: <20150203213948.3448.80258.stgit@notabene.brown>
1/ delay setting mddev->bitmap_info.file until 'f' looks
usable, so we don't have to unset it.
2/ Don't allow bitmap file to be set if bitmap_info.file
is already set.
Signed-off-by: NeilBrown <neilb@suse.de>
---
drivers/md/md.c | 16 +++++++++-------
1 file changed, 9 insertions(+), 7 deletions(-)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 01793f24f8de..1e32f2e93d1d 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5851,22 +5851,24 @@ static int set_bitmap_file(struct mddev *mddev, int fd)
if (fd >= 0) {
struct inode *inode;
- if (mddev->bitmap)
+ struct file *f;
+
+ if (mddev->bitmap || mddev->bitmap_info.file)
return -EEXIST; /* cannot add when bitmap is present */
- mddev->bitmap_info.file = fget(fd);
+ f = fget(fd);
- if (mddev->bitmap_info.file == NULL) {
+ if (f == NULL) {
printk(KERN_ERR "%s: error: failed to get bitmap file\n",
mdname(mddev));
return -EBADF;
}
- inode = mddev->bitmap_info.file->f_mapping->host;
+ inode = f->f_mapping->host;
if (!S_ISREG(inode->i_mode)) {
printk(KERN_ERR "%s: error: bitmap file must be a regular file\n",
mdname(mddev));
err = -EBADF;
- } else if (!(mddev->bitmap_info.file->f_mode & FMODE_WRITE)) {
+ } else if (!(f->f_mode & FMODE_WRITE)) {
printk(KERN_ERR "%s: error: bitmap file must open for write\n",
mdname(mddev));
err = -EBADF;
@@ -5876,10 +5878,10 @@ static int set_bitmap_file(struct mddev *mddev, int fd)
err = -EBUSY;
}
if (err) {
- fput(mddev->bitmap_info.file);
- mddev->bitmap_info.file = NULL;
+ fput(f);
return err;
}
+ mddev->bitmap_info.file = f;
mddev->bitmap_info.offset = 0; /* file overrides offset */
} else if (mddev->bitmap == NULL)
return -ENOENT; /* cannot remove what isn't there */
^ permalink raw reply related
* [md PATCH 21/26] md: move GET_BITMAP_FILE ioctl out from mddev_lock.
From: NeilBrown @ 2015-02-03 21:42 UTC (permalink / raw)
To: linux-raid
In-Reply-To: <20150203213948.3448.80258.stgit@notabene.brown>
It makes more sense to report bitmap_info->file, rather than
bitmap->file (the later is only available once the array is
active).
With that change, use mddev->lock to protect bitmap_info being
set to NULL, and we can call get_bitmap_file() without taking
the mutex.
Signed-off-by: NeilBrown <neilb@suse.de>
---
drivers/md/md.c | 58 ++++++++++++++++++++++++++++++-------------------------
drivers/md/md.h | 1 +
2 files changed, 33 insertions(+), 26 deletions(-)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 1e32f2e93d1d..f11aff6bd5e2 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5292,8 +5292,11 @@ static int do_md_stop(struct mddev *mddev, int mode,
bitmap_destroy(mddev);
if (mddev->bitmap_info.file) {
- fput(mddev->bitmap_info.file);
+ struct file *f = mddev->bitmap_info.file;
+ spin_lock(&mddev->lock);
mddev->bitmap_info.file = NULL;
+ spin_unlock(&mddev->lock);
+ fput(f);
}
mddev->bitmap_info.offset = 0;
@@ -5503,32 +5506,30 @@ static int get_bitmap_file(struct mddev *mddev, void __user * arg)
{
mdu_bitmap_file_t *file = NULL; /* too big for stack allocation */
char *ptr;
- int err = -ENOMEM;
+ int err;
file = kmalloc(sizeof(*file), GFP_NOIO);
-
if (!file)
- goto out;
+ return -ENOMEM;
+ err = 0;
+ spin_lock(&mddev->lock);
/* bitmap disabled, zero the first byte and copy out */
- if (!mddev->bitmap || !mddev->bitmap->storage.file) {
+ if (!mddev->bitmap_info.file)
file->pathname[0] = '\0';
- goto copy_out;
- }
-
- ptr = d_path(&mddev->bitmap->storage.file->f_path,
- file->pathname, sizeof(file->pathname));
- if (IS_ERR(ptr))
- goto out;
-
- memmove(file->pathname, ptr,
- sizeof(file->pathname)-(ptr-file->pathname));
+ else if ((ptr = d_path(&mddev->bitmap_info.file->f_path,
+ file->pathname, sizeof(file->pathname))),
+ IS_ERR(ptr))
+ err = PTR_ERR(ptr);
+ else
+ memmove(file->pathname, ptr,
+ sizeof(file->pathname)-(ptr-file->pathname));
+ spin_unlock(&mddev->lock);
-copy_out:
- err = 0;
- if (copy_to_user(arg, file, sizeof(*file)))
+ if (err == 0 &&
+ copy_to_user(arg, file, sizeof(*file)))
err = -EFAULT;
-out:
+
kfree(file);
return err;
}
@@ -5900,9 +5901,13 @@ static int set_bitmap_file(struct mddev *mddev, int fd)
mddev->pers->quiesce(mddev, 0);
}
if (fd < 0) {
- if (mddev->bitmap_info.file)
- fput(mddev->bitmap_info.file);
- mddev->bitmap_info.file = NULL;
+ struct file *f = mddev->bitmap_info.file;
+ if (f) {
+ spin_lock(&mddev->lock);
+ mddev->bitmap_info.file = NULL;
+ spin_unlock(&mddev->lock);
+ fput(f);
+ }
}
return err;
@@ -6315,6 +6320,11 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
case SET_DISK_FAULTY:
err = set_disk_faulty(mddev, new_decode_dev(arg));
goto out;
+
+ case GET_BITMAP_FILE:
+ err = get_bitmap_file(mddev, argp);
+ goto out;
+
}
if (cmd == ADD_NEW_DISK)
@@ -6406,10 +6416,6 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
* Commands even a read-only array can execute:
*/
switch (cmd) {
- case GET_BITMAP_FILE:
- err = get_bitmap_file(mddev, argp);
- goto unlock;
-
case RESTART_ARRAY_RW:
err = restart_array(mddev);
goto unlock;
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 8770308a8052..b4fbd6a63fcf 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -393,6 +393,7 @@ struct mddev {
* in_sync - and related safemode and MD_CHANGE changes
* pers (also protected by reconfig_mutex and pending IO).
* clearing ->bitmap
+ * clearing ->bitmap_info.file
*/
spinlock_t lock;
wait_queue_head_t sb_wait; /* for waiting on superblock updates */
^ permalink raw reply related
* [md PATCH 23/26] md: use mddev->lock to protect updates to resync_{min, max}.
From: NeilBrown @ 2015-02-03 21:42 UTC (permalink / raw)
To: linux-raid
In-Reply-To: <20150203213948.3448.80258.stgit@notabene.brown>
There are interdependencies between these two sysfs attributes
and whether a resync is currently running.
Rather than depending on reconfig_mutex to ensure no races when
testing these interdependencies are met, use the spinlock.
This will allow the mutex to be remove from protecting this
code in a subsequent patch.
Signed-off-by: NeilBrown <neilb@suse.de>
---
drivers/md/md.c | 58 +++++++++++++++++++++++++++++++++++++++++++------------
drivers/md/md.h | 2 ++
2 files changed, 47 insertions(+), 13 deletions(-)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index e68824d2d21e..c17de6d0fb42 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -4269,22 +4269,36 @@ static ssize_t
min_sync_store(struct mddev *mddev, const char *buf, size_t len)
{
unsigned long long min;
+ int err;
+ int chunk;
+
if (kstrtoull(buf, 10, &min))
return -EINVAL;
+
+ spin_lock(&mddev->lock);
+ err = -EINVAL;
if (min > mddev->resync_max)
- return -EINVAL;
+ goto out_unlock;
+
+ err = -EBUSY;
if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
- return -EBUSY;
+ goto out_unlock;
/* Must be a multiple of chunk_size */
- if (mddev->chunk_sectors) {
+ chunk = mddev->chunk_sectors;
+ if (chunk) {
sector_t temp = min;
- if (sector_div(temp, mddev->chunk_sectors))
- return -EINVAL;
+
+ err = -EINVAL;
+ if (sector_div(temp, chunk))
+ goto out_unlock;
}
mddev->resync_min = min;
+ err = 0;
- return len;
+out_unlock:
+ spin_unlock(&mddev->lock);
+ return err ?: len;
}
static struct md_sysfs_entry md_min_sync =
@@ -4302,29 +4316,42 @@ max_sync_show(struct mddev *mddev, char *page)
static ssize_t
max_sync_store(struct mddev *mddev, const char *buf, size_t len)
{
+ int err;
+ spin_lock(&mddev->lock);
if (strncmp(buf, "max", 3) == 0)
mddev->resync_max = MaxSector;
else {
unsigned long long max;
+ int chunk;
+
+ err = -EINVAL;
if (kstrtoull(buf, 10, &max))
- return -EINVAL;
+ goto out_unlock;
if (max < mddev->resync_min)
- return -EINVAL;
+ goto out_unlock;
+
+ err = -EBUSY;
if (max < mddev->resync_max &&
mddev->ro == 0 &&
test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
- return -EBUSY;
+ goto out_unlock;
/* Must be a multiple of chunk_size */
- if (mddev->chunk_sectors) {
+ chunk = mddev->chunk_sectors;
+ if (chunk) {
sector_t temp = max;
- if (sector_div(temp, mddev->chunk_sectors))
- return -EINVAL;
+
+ err = -EINVAL;
+ if (sector_div(temp, chunk))
+ goto out_unlock;
}
mddev->resync_max = max;
}
wake_up(&mddev->recovery_wait);
- return len;
+ err = 0;
+out_unlock:
+ spin_unlock(&mddev->lock);
+ return err ?: len;
}
static struct md_sysfs_entry md_max_sync =
@@ -7585,6 +7612,7 @@ void md_do_sync(struct md_thread *thread)
skip:
set_bit(MD_CHANGE_DEVS, &mddev->flags);
+ spin_lock(&mddev->lock);
if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
/* We completed so min/max setting can be forgotten if used. */
if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
@@ -7593,6 +7621,8 @@ void md_do_sync(struct md_thread *thread)
} else if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
mddev->resync_min = mddev->curr_resync_completed;
mddev->curr_resync = 0;
+ spin_unlock(&mddev->lock);
+
wake_up(&resync_wait);
set_bit(MD_RECOVERY_DONE, &mddev->recovery);
md_wakeup_thread(mddev->thread);
@@ -7793,7 +7823,9 @@ void md_check_recovery(struct mddev *mddev)
* any transients in the value of "sync_action".
*/
mddev->curr_resync_completed = 0;
+ spin_lock(&mddev->lock);
set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
+ spin_unlock(&mddev->lock);
/* Clear some bits that don't mean anything, but
* might be left set
*/
diff --git a/drivers/md/md.h b/drivers/md/md.h
index b4fbd6a63fcf..6bf3faa951ec 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -394,6 +394,8 @@ struct mddev {
* pers (also protected by reconfig_mutex and pending IO).
* clearing ->bitmap
* clearing ->bitmap_info.file
+ * changing ->resync_{min,max}
+ * setting MD_RECOVERY_RUNNING (which interacts with resync_{min,max})
*/
spinlock_t lock;
wait_queue_head_t sb_wait; /* for waiting on superblock updates */
^ permalink raw reply related
* [md PATCH 22/26] md: minor cleanup in safe_delay_store.
From: NeilBrown @ 2015-02-03 21:42 UTC (permalink / raw)
To: linux-raid
In-Reply-To: <20150203213948.3448.80258.stgit@notabene.brown>
There isn't really much room for races with ->safemode_delay.
But as I am trying to clean up any racy code and will soon
be removing reconfig_mutex protection from most _store()
functions:
- only set mddev->safemode_delay once, to ensure no code
can see an intermediate value
- use safemode_timer to call md_safemode_timeout() rather than
calling it directly, to ensure it never races with itself.
Signed-off-by: NeilBrown <neilb@suse.de>
---
drivers/md/md.c | 12 +++++++-----
1 file changed, 7 insertions(+), 5 deletions(-)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index f11aff6bd5e2..e68824d2d21e 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -3242,11 +3242,13 @@ safe_delay_store(struct mddev *mddev, const char *cbuf, size_t len)
mddev->safemode_delay = 0;
else {
unsigned long old_delay = mddev->safemode_delay;
- mddev->safemode_delay = (msec*HZ)/1000;
- if (mddev->safemode_delay == 0)
- mddev->safemode_delay = 1;
- if (mddev->safemode_delay < old_delay || old_delay == 0)
- md_safemode_timeout((unsigned long)mddev);
+ unsigned long new_delay = (msec*HZ)/1000;
+
+ if (new_delay == 0)
+ new_delay = 1;
+ mddev->safemode_delay = new_delay;
+ if (new_delay < old_delay || old_delay == 0)
+ mod_timer(&mddev->safemode_timer, jiffies+1);
}
return len;
}
^ permalink raw reply related
* [md PATCH 24/26] md: move mddev_lock and related to md.h
From: NeilBrown @ 2015-02-03 21:42 UTC (permalink / raw)
To: linux-raid
In-Reply-To: <20150203213948.3448.80258.stgit@notabene.brown>
The one which is not inline (mddev_unlock) gets EXPORTed.
This makes the locking available to personality modules so that it
doesn't have to be imposed upon them.
Signed-off-by: NeilBrown <neilb@suse.de>
---
drivers/md/md.c | 26 ++------------------------
drivers/md/md.h | 24 ++++++++++++++++++++++++
2 files changed, 26 insertions(+), 24 deletions(-)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index c17de6d0fb42..6517f4ece44e 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -590,32 +590,9 @@ static struct mddev *mddev_find(dev_t unit)
goto retry;
}
-static inline int __must_check mddev_lock(struct mddev *mddev)
-{
- return mutex_lock_interruptible(&mddev->reconfig_mutex);
-}
-
-/* Sometimes we need to take the lock in a situation where
- * failure due to interrupts is not acceptable.
- */
-static inline void mddev_lock_nointr(struct mddev *mddev)
-{
- mutex_lock(&mddev->reconfig_mutex);
-}
-
-static inline int mddev_is_locked(struct mddev *mddev)
-{
- return mutex_is_locked(&mddev->reconfig_mutex);
-}
-
-static inline int mddev_trylock(struct mddev *mddev)
-{
- return mutex_trylock(&mddev->reconfig_mutex);
-}
-
static struct attribute_group md_redundancy_group;
-static void mddev_unlock(struct mddev *mddev)
+void mddev_unlock(struct mddev *mddev)
{
if (mddev->to_remove) {
/* These cannot be removed under reconfig_mutex as
@@ -657,6 +634,7 @@ static void mddev_unlock(struct mddev *mddev)
md_wakeup_thread(mddev->thread);
spin_unlock(&pers_lock);
}
+EXPORT_SYMBOL_GPL(mddev_unlock);
static struct md_rdev *find_rdev_nr_rcu(struct mddev *mddev, int nr)
{
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 6bf3faa951ec..14367d919351 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -450,6 +450,30 @@ struct mddev {
void (*sync_super)(struct mddev *mddev, struct md_rdev *rdev);
};
+static inline int __must_check mddev_lock(struct mddev *mddev)
+{
+ return mutex_lock_interruptible(&mddev->reconfig_mutex);
+}
+
+/* Sometimes we need to take the lock in a situation where
+ * failure due to interrupts is not acceptable.
+ */
+static inline void mddev_lock_nointr(struct mddev *mddev)
+{
+ mutex_lock(&mddev->reconfig_mutex);
+}
+
+static inline int mddev_is_locked(struct mddev *mddev)
+{
+ return mutex_is_locked(&mddev->reconfig_mutex);
+}
+
+static inline int mddev_trylock(struct mddev *mddev)
+{
+ return mutex_trylock(&mddev->reconfig_mutex);
+}
+extern void mddev_unlock(struct mddev *mddev);
+
static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev)
{
int faulty = test_bit(Faulty, &rdev->flags);
^ permalink raw reply related
* [md PATCH 25/26] md: make reconfig_mutex optional for writes to md sysfs files.
From: NeilBrown @ 2015-02-03 21:42 UTC (permalink / raw)
To: linux-raid
In-Reply-To: <20150203213948.3448.80258.stgit@notabene.brown>
Rather than using mddev_lock() to take the reconfig_mutex
when writing to any md sysfs file, we only take mddev_lock()
in the particular _store() functions that require it.
Admittedly this is most, but it isn't all.
This also allows us to remove special-case handling for new_dev_store
(in md_attr_store).
Signed-off-by: NeilBrown <neilb@suse.de>
---
drivers/md/md.c | 346 ++++++++++++++++++++++++++++++++++++----------------
drivers/md/raid5.c | 134 +++++++++++---------
2 files changed, 316 insertions(+), 164 deletions(-)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 6517f4ece44e..4c3ab0639c58 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -3256,26 +3256,32 @@ static ssize_t
level_store(struct mddev *mddev, const char *buf, size_t len)
{
char clevel[16];
- ssize_t rv = len;
+ ssize_t rv;
+ size_t slen = len;
struct md_personality *pers, *oldpers;
long level;
void *priv, *oldpriv;
struct md_rdev *rdev;
+ if (slen == 0 || slen >= sizeof(clevel))
+ return -EINVAL;
+
+ rv = mddev_lock(mddev);
+ if (rv)
+ return rv;
+
if (mddev->pers == NULL) {
- if (len == 0)
- return 0;
- if (len >= sizeof(mddev->clevel))
- return -ENOSPC;
- strncpy(mddev->clevel, buf, len);
- if (mddev->clevel[len-1] == '\n')
- len--;
- mddev->clevel[len] = 0;
+ strncpy(mddev->clevel, buf, slen);
+ if (mddev->clevel[slen-1] == '\n')
+ slen--;
+ mddev->clevel[slen] = 0;
mddev->level = LEVEL_NONE;
- return rv;
+ rv = len;
+ goto out_unlock;
}
+ rv = -EROFS;
if (mddev->ro)
- return -EROFS;
+ goto out_unlock;
/* request to change the personality. Need to ensure:
* - array is not engaged in resync/recovery/reshape
@@ -3283,25 +3289,25 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
* - new personality will access other array.
*/
+ rv = -EBUSY;
if (mddev->sync_thread ||
test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
mddev->reshape_position != MaxSector ||
mddev->sysfs_active)
- return -EBUSY;
+ goto out_unlock;
+ rv = -EINVAL;
if (!mddev->pers->quiesce) {
printk(KERN_WARNING "md: %s: %s does not support online personality change\n",
mdname(mddev), mddev->pers->name);
- return -EINVAL;
+ goto out_unlock;
}
/* Now find the new personality */
- if (len == 0 || len >= sizeof(clevel))
- return -EINVAL;
- strncpy(clevel, buf, len);
- if (clevel[len-1] == '\n')
- len--;
- clevel[len] = 0;
+ strncpy(clevel, buf, slen);
+ if (clevel[slen-1] == '\n')
+ slen--;
+ clevel[slen] = 0;
if (kstrtol(clevel, 10, &level))
level = LEVEL_NONE;
@@ -3312,20 +3318,23 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
if (!pers || !try_module_get(pers->owner)) {
spin_unlock(&pers_lock);
printk(KERN_WARNING "md: personality %s not loaded\n", clevel);
- return -EINVAL;
+ rv = -EINVAL;
+ goto out_unlock;
}
spin_unlock(&pers_lock);
if (pers == mddev->pers) {
/* Nothing to do! */
module_put(pers->owner);
- return rv;
+ rv = len;
+ goto out_unlock;
}
if (!pers->takeover) {
module_put(pers->owner);
printk(KERN_WARNING "md: %s: %s does not support personality takeover\n",
mdname(mddev), clevel);
- return -EINVAL;
+ rv = -EINVAL;
+ goto out_unlock;
}
rdev_for_each(rdev, mddev)
@@ -3345,7 +3354,8 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
module_put(pers->owner);
printk(KERN_WARNING "md: %s: %s would not accept array\n",
mdname(mddev), clevel);
- return PTR_ERR(priv);
+ rv = PTR_ERR(priv);
+ goto out_unlock;
}
/* Looks like we have a winner */
@@ -3438,6 +3448,9 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
md_update_sb(mddev, 1);
sysfs_notify(&mddev->kobj, NULL, "level");
md_new_event(mddev);
+ rv = len;
+out_unlock:
+ mddev_unlock(mddev);
return rv;
}
@@ -3460,28 +3473,32 @@ layout_store(struct mddev *mddev, const char *buf, size_t len)
{
char *e;
unsigned long n = simple_strtoul(buf, &e, 10);
+ int err;
if (!*buf || (*e && *e != '\n'))
return -EINVAL;
+ err = mddev_lock(mddev);
+ if (err)
+ return err;
if (mddev->pers) {
- int err;
if (mddev->pers->check_reshape == NULL)
- return -EBUSY;
- if (mddev->ro)
- return -EROFS;
- mddev->new_layout = n;
- err = mddev->pers->check_reshape(mddev);
- if (err) {
- mddev->new_layout = mddev->layout;
- return err;
+ err = -EBUSY;
+ else if (mddev->ro)
+ err = -EROFS;
+ else {
+ mddev->new_layout = n;
+ err = mddev->pers->check_reshape(mddev);
+ if (err)
+ mddev->new_layout = mddev->layout;
}
} else {
mddev->new_layout = n;
if (mddev->reshape_position == MaxSector)
mddev->layout = n;
}
- return len;
+ mddev_unlock(mddev);
+ return err ?: len;
}
static struct md_sysfs_entry md_layout =
__ATTR(layout, S_IRUGO|S_IWUSR, layout_show, layout_store);
@@ -3504,32 +3521,39 @@ static ssize_t
raid_disks_store(struct mddev *mddev, const char *buf, size_t len)
{
char *e;
- int rv = 0;
+ int err;
unsigned long n = simple_strtoul(buf, &e, 10);
if (!*buf || (*e && *e != '\n'))
return -EINVAL;
+ err = mddev_lock(mddev);
+ if (err)
+ return err;
if (mddev->pers)
- rv = update_raid_disks(mddev, n);
+ err = update_raid_disks(mddev, n);
else if (mddev->reshape_position != MaxSector) {
struct md_rdev *rdev;
int olddisks = mddev->raid_disks - mddev->delta_disks;
+ err = -EINVAL;
rdev_for_each(rdev, mddev) {
if (olddisks < n &&
rdev->data_offset < rdev->new_data_offset)
- return -EINVAL;
+ goto out_unlock;
if (olddisks > n &&
rdev->data_offset > rdev->new_data_offset)
- return -EINVAL;
+ goto out_unlock;
}
+ err = 0;
mddev->delta_disks = n - olddisks;
mddev->raid_disks = n;
mddev->reshape_backwards = (mddev->delta_disks < 0);
} else
mddev->raid_disks = n;
- return rv ? rv : len;
+out_unlock:
+ mddev_unlock(mddev);
+ return err ? err : len;
}
static struct md_sysfs_entry md_raid_disks =
__ATTR(raid_disks, S_IRUGO|S_IWUSR, raid_disks_show, raid_disks_store);
@@ -3548,30 +3572,34 @@ chunk_size_show(struct mddev *mddev, char *page)
static ssize_t
chunk_size_store(struct mddev *mddev, const char *buf, size_t len)
{
+ int err;
char *e;
unsigned long n = simple_strtoul(buf, &e, 10);
if (!*buf || (*e && *e != '\n'))
return -EINVAL;
+ err = mddev_lock(mddev);
+ if (err)
+ return err;
if (mddev->pers) {
- int err;
if (mddev->pers->check_reshape == NULL)
- return -EBUSY;
- if (mddev->ro)
- return -EROFS;
- mddev->new_chunk_sectors = n >> 9;
- err = mddev->pers->check_reshape(mddev);
- if (err) {
- mddev->new_chunk_sectors = mddev->chunk_sectors;
- return err;
+ err = -EBUSY;
+ else if (mddev->ro)
+ err = -EROFS;
+ else {
+ mddev->new_chunk_sectors = n >> 9;
+ err = mddev->pers->check_reshape(mddev);
+ if (err)
+ mddev->new_chunk_sectors = mddev->chunk_sectors;
}
} else {
mddev->new_chunk_sectors = n >> 9;
if (mddev->reshape_position == MaxSector)
mddev->chunk_sectors = n >> 9;
}
- return len;
+ mddev_unlock(mddev);
+ return err ?: len;
}
static struct md_sysfs_entry md_chunk_size =
__ATTR(chunk_size, S_IRUGO|S_IWUSR, chunk_size_show, chunk_size_store);
@@ -3587,20 +3615,27 @@ resync_start_show(struct mddev *mddev, char *page)
static ssize_t
resync_start_store(struct mddev *mddev, const char *buf, size_t len)
{
+ int err;
char *e;
unsigned long long n = simple_strtoull(buf, &e, 10);
+ err = mddev_lock(mddev);
+ if (err)
+ return err;
if (mddev->pers && !test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
- return -EBUSY;
- if (cmd_match(buf, "none"))
+ err = -EBUSY;
+ else if (cmd_match(buf, "none"))
n = MaxSector;
else if (!*buf || (*e && *e != '\n'))
- return -EINVAL;
+ err = -EINVAL;
- mddev->recovery_cp = n;
- if (mddev->pers)
- set_bit(MD_CHANGE_CLEAN, &mddev->flags);
- return len;
+ if (!err) {
+ mddev->recovery_cp = n;
+ if (mddev->pers)
+ set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+ }
+ mddev_unlock(mddev);
+ return err ?: len;
}
static struct md_sysfs_entry md_resync_start =
__ATTR(resync_start, S_IRUGO|S_IWUSR, resync_start_show, resync_start_store);
@@ -3698,8 +3733,39 @@ static int restart_array(struct mddev *mddev);
static ssize_t
array_state_store(struct mddev *mddev, const char *buf, size_t len)
{
- int err = -EINVAL;
+ int err;
enum array_state st = match_word(buf, array_states);
+
+ if (mddev->pers && (st == active || st == clean) && mddev->ro != 1) {
+ /* don't take reconfig_mutex when toggling between
+ * clean and active
+ */
+ spin_lock(&mddev->lock);
+ if (st == active) {
+ restart_array(mddev);
+ clear_bit(MD_CHANGE_PENDING, &mddev->flags);
+ wake_up(&mddev->sb_wait);
+ err = 0;
+ } else /* st == clean */ {
+ restart_array(mddev);
+ if (atomic_read(&mddev->writes_pending) == 0) {
+ if (mddev->in_sync == 0) {
+ mddev->in_sync = 1;
+ if (mddev->safemode == 1)
+ mddev->safemode = 0;
+ set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+ }
+ err = 0;
+ } else
+ err = -EBUSY;
+ }
+ spin_unlock(&mddev->lock);
+ return err;
+ }
+ err = mddev_lock(mddev);
+ if (err)
+ return err;
+ err = -EINVAL;
switch(st) {
case bad_word:
break;
@@ -3775,14 +3841,14 @@ array_state_store(struct mddev *mddev, const char *buf, size_t len)
/* these cannot be set */
break;
}
- if (err)
- return err;
- else {
+
+ if (!err) {
if (mddev->hold_active == UNTIL_IOCTL)
mddev->hold_active = 0;
sysfs_notify_dirent_safe(mddev->sysfs_state);
- return len;
}
+ mddev_unlock(mddev);
+ return err ?: len;
}
static struct md_sysfs_entry md_array_state =
__ATTR(array_state, S_IRUGO|S_IWUSR, array_state_show, array_state_store);
@@ -3843,6 +3909,11 @@ new_dev_store(struct mddev *mddev, const char *buf, size_t len)
minor != MINOR(dev))
return -EOVERFLOW;
+ flush_workqueue(md_misc_wq);
+
+ err = mddev_lock(mddev);
+ if (err)
+ return err;
if (mddev->persistent) {
rdev = md_import_device(dev, mddev->major_version,
mddev->minor_version);
@@ -3866,6 +3937,7 @@ new_dev_store(struct mddev *mddev, const char *buf, size_t len)
out:
if (err)
export_rdev(rdev);
+ mddev_unlock(mddev);
return err ? err : len;
}
@@ -3877,7 +3949,11 @@ bitmap_store(struct mddev *mddev, const char *buf, size_t len)
{
char *end;
unsigned long chunk, end_chunk;
+ int err;
+ err = mddev_lock(mddev);
+ if (err)
+ return err;
if (!mddev->bitmap)
goto out;
/* buf should be <chunk> <chunk> ... or <chunk>-<chunk> ... (range) */
@@ -3895,6 +3971,7 @@ bitmap_store(struct mddev *mddev, const char *buf, size_t len)
}
bitmap_unplug(mddev->bitmap); /* flush the bits to disk */
out:
+ mddev_unlock(mddev);
return len;
}
@@ -3922,6 +3999,9 @@ size_store(struct mddev *mddev, const char *buf, size_t len)
if (err < 0)
return err;
+ err = mddev_lock(mddev);
+ if (err)
+ return err;
if (mddev->pers) {
err = update_size(mddev, sectors);
md_update_sb(mddev, 1);
@@ -3932,6 +4012,7 @@ size_store(struct mddev *mddev, const char *buf, size_t len)
else
err = -ENOSPC;
}
+ mddev_unlock(mddev);
return err ? err : len;
}
@@ -3961,21 +4042,28 @@ metadata_store(struct mddev *mddev, const char *buf, size_t len)
{
int major, minor;
char *e;
+ int err;
/* Changing the details of 'external' metadata is
* always permitted. Otherwise there must be
* no devices attached to the array.
*/
+
+ err = mddev_lock(mddev);
+ if (err)
+ return err;
+ err = -EBUSY;
if (mddev->external && strncmp(buf, "external:", 9) == 0)
;
else if (!list_empty(&mddev->disks))
- return -EBUSY;
+ goto out_unlock;
+ err = 0;
if (cmd_match(buf, "none")) {
mddev->persistent = 0;
mddev->external = 0;
mddev->major_version = 0;
mddev->minor_version = 90;
- return len;
+ goto out_unlock;
}
if (strncmp(buf, "external:", 9) == 0) {
size_t namelen = len-9;
@@ -3989,22 +4077,27 @@ metadata_store(struct mddev *mddev, const char *buf, size_t len)
mddev->external = 1;
mddev->major_version = 0;
mddev->minor_version = 90;
- return len;
+ goto out_unlock;
}
major = simple_strtoul(buf, &e, 10);
+ err = -EINVAL;
if (e==buf || *e != '.')
- return -EINVAL;
+ goto out_unlock;
buf = e+1;
minor = simple_strtoul(buf, &e, 10);
if (e==buf || (*e && *e != '\n') )
- return -EINVAL;
+ goto out_unlock;
+ err = -ENOENT;
if (major >= ARRAY_SIZE(super_types) || super_types[major].name == NULL)
- return -ENOENT;
+ goto out_unlock;
mddev->major_version = major;
mddev->minor_version = minor;
mddev->persistent = 1;
mddev->external = 0;
- return len;
+ err = 0;
+out_unlock:
+ mddev_unlock(mddev);
+ return err ?: len;
}
static struct md_sysfs_entry md_metadata =
@@ -4049,7 +4142,10 @@ action_store(struct mddev *mddev, const char *page, size_t len)
flush_workqueue(md_misc_wq);
if (mddev->sync_thread) {
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
- md_reap_sync_thread(mddev);
+ if (mddev_lock(mddev) == 0) {
+ md_reap_sync_thread(mddev);
+ mddev_unlock(mddev);
+ }
}
} else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
@@ -4063,7 +4159,11 @@ action_store(struct mddev *mddev, const char *page, size_t len)
int err;
if (mddev->pers->start_reshape == NULL)
return -EINVAL;
- err = mddev->pers->start_reshape(mddev);
+ err = mddev_lock(mddev);
+ if (!err) {
+ err = mddev->pers->start_reshape(mddev);
+ mddev_unlock(mddev);
+ }
if (err)
return err;
sysfs_notify(&mddev->kobj, NULL, "degraded");
@@ -4346,14 +4446,20 @@ suspend_lo_store(struct mddev *mddev, const char *buf, size_t len)
{
char *e;
unsigned long long new = simple_strtoull(buf, &e, 10);
- unsigned long long old = mddev->suspend_lo;
+ unsigned long long old;
+ int err;
- if (mddev->pers == NULL ||
- mddev->pers->quiesce == NULL)
- return -EINVAL;
if (buf == e || (*e && *e != '\n'))
return -EINVAL;
+ err = mddev_lock(mddev);
+ if (err)
+ return err;
+ err = -EINVAL;
+ if (mddev->pers == NULL ||
+ mddev->pers->quiesce == NULL)
+ goto unlock;
+ old = mddev->suspend_lo;
mddev->suspend_lo = new;
if (new >= old)
/* Shrinking suspended region */
@@ -4363,7 +4469,10 @@ suspend_lo_store(struct mddev *mddev, const char *buf, size_t len)
mddev->pers->quiesce(mddev, 1);
mddev->pers->quiesce(mddev, 0);
}
- return len;
+ err = 0;
+unlock:
+ mddev_unlock(mddev);
+ return err ?: len;
}
static struct md_sysfs_entry md_suspend_lo =
__ATTR(suspend_lo, S_IRUGO|S_IWUSR, suspend_lo_show, suspend_lo_store);
@@ -4379,14 +4488,20 @@ suspend_hi_store(struct mddev *mddev, const char *buf, size_t len)
{
char *e;
unsigned long long new = simple_strtoull(buf, &e, 10);
- unsigned long long old = mddev->suspend_hi;
+ unsigned long long old;
+ int err;
- if (mddev->pers == NULL ||
- mddev->pers->quiesce == NULL)
- return -EINVAL;
if (buf == e || (*e && *e != '\n'))
return -EINVAL;
+ err = mddev_lock(mddev);
+ if (err)
+ return err;
+ err = -EINVAL;
+ if (mddev->pers == NULL ||
+ mddev->pers->quiesce == NULL)
+ goto unlock;
+ old = mddev->suspend_hi;
mddev->suspend_hi = new;
if (new <= old)
/* Shrinking suspended region */
@@ -4396,7 +4511,10 @@ suspend_hi_store(struct mddev *mddev, const char *buf, size_t len)
mddev->pers->quiesce(mddev, 1);
mddev->pers->quiesce(mddev, 0);
}
- return len;
+ err = 0;
+unlock:
+ mddev_unlock(mddev);
+ return err ?: len;
}
static struct md_sysfs_entry md_suspend_hi =
__ATTR(suspend_hi, S_IRUGO|S_IWUSR, suspend_hi_show, suspend_hi_store);
@@ -4416,11 +4534,17 @@ reshape_position_store(struct mddev *mddev, const char *buf, size_t len)
{
struct md_rdev *rdev;
char *e;
+ int err;
unsigned long long new = simple_strtoull(buf, &e, 10);
- if (mddev->pers)
- return -EBUSY;
+
if (buf == e || (*e && *e != '\n'))
return -EINVAL;
+ err = mddev_lock(mddev);
+ if (err)
+ return err;
+ err = -EBUSY;
+ if (mddev->pers)
+ goto unlock;
mddev->reshape_position = new;
mddev->delta_disks = 0;
mddev->reshape_backwards = 0;
@@ -4429,7 +4553,10 @@ reshape_position_store(struct mddev *mddev, const char *buf, size_t len)
mddev->new_chunk_sectors = mddev->chunk_sectors;
rdev_for_each(rdev, mddev)
rdev->new_data_offset = rdev->data_offset;
- return len;
+ err = 0;
+unlock:
+ mddev_unlock(mddev);
+ return err ?: len;
}
static struct md_sysfs_entry md_reshape_position =
@@ -4447,6 +4574,8 @@ static ssize_t
reshape_direction_store(struct mddev *mddev, const char *buf, size_t len)
{
int backwards = 0;
+ int err;
+
if (cmd_match(buf, "forwards"))
backwards = 0;
else if (cmd_match(buf, "backwards"))
@@ -4456,16 +4585,19 @@ reshape_direction_store(struct mddev *mddev, const char *buf, size_t len)
if (mddev->reshape_backwards == backwards)
return len;
+ err = mddev_lock(mddev);
+ if (err)
+ return err;
/* check if we are allowed to change */
if (mddev->delta_disks)
- return -EBUSY;
-
- if (mddev->persistent &&
+ err = -EBUSY;
+ else if (mddev->persistent &&
mddev->major_version == 0)
- return -EINVAL;
-
- mddev->reshape_backwards = backwards;
- return len;
+ err = -EINVAL;
+ else
+ mddev->reshape_backwards = backwards;
+ mddev_unlock(mddev);
+ return err ?: len;
}
static struct md_sysfs_entry md_reshape_direction =
@@ -4486,6 +4618,11 @@ static ssize_t
array_size_store(struct mddev *mddev, const char *buf, size_t len)
{
sector_t sectors;
+ int err;
+
+ err = mddev_lock(mddev);
+ if (err)
+ return err;
if (strncmp(buf, "default", 7) == 0) {
if (mddev->pers)
@@ -4496,19 +4633,22 @@ array_size_store(struct mddev *mddev, const char *buf, size_t len)
mddev->external_size = 0;
} else {
if (strict_blocks_to_sectors(buf, §ors) < 0)
- return -EINVAL;
- if (mddev->pers && mddev->pers->size(mddev, 0, 0) < sectors)
- return -E2BIG;
-
- mddev->external_size = 1;
+ err = -EINVAL;
+ else if (mddev->pers && mddev->pers->size(mddev, 0, 0) < sectors)
+ err = -E2BIG;
+ else
+ mddev->external_size = 1;
}
- mddev->array_sectors = sectors;
- if (mddev->pers) {
- set_capacity(mddev->gendisk, mddev->array_sectors);
- revalidate_disk(mddev->gendisk);
+ if (!err) {
+ mddev->array_sectors = sectors;
+ if (mddev->pers) {
+ set_capacity(mddev->gendisk, mddev->array_sectors);
+ revalidate_disk(mddev->gendisk);
+ }
}
- return len;
+ mddev_unlock(mddev);
+ return err ?: len;
}
static struct md_sysfs_entry md_array_size =
@@ -4596,13 +4736,7 @@ md_attr_store(struct kobject *kobj, struct attribute *attr,
}
mddev_get(mddev);
spin_unlock(&all_mddevs_lock);
- if (entry->store == new_dev_store)
- flush_workqueue(md_misc_wq);
- rv = mddev_lock(mddev);
- if (!rv) {
- rv = entry->store(mddev, page, length);
- mddev_unlock(mddev);
- }
+ rv = entry->store(mddev, page, length);
mddev_put(mddev);
return rv;
}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index d5b80174b3b3..aa76865b804b 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5400,21 +5400,25 @@ EXPORT_SYMBOL(raid5_set_cache_size);
static ssize_t
raid5_store_stripe_cache_size(struct mddev *mddev, const char *page, size_t len)
{
- struct r5conf *conf = mddev->private;
+ struct r5conf *conf;
unsigned long new;
int err;
if (len >= PAGE_SIZE)
return -EINVAL;
- if (!conf)
- return -ENODEV;
-
if (kstrtoul(page, 10, &new))
return -EINVAL;
- err = raid5_set_cache_size(mddev, new);
+ err = mddev_lock(mddev);
if (err)
return err;
- return len;
+ conf = mddev->private;
+ if (!conf)
+ err = -ENODEV;
+ else
+ err = raid5_set_cache_size(mddev, new);
+ mddev_unlock(mddev);
+
+ return err ?: len;
}
static struct md_sysfs_entry
@@ -5438,19 +5442,27 @@ raid5_show_preread_threshold(struct mddev *mddev, char *page)
static ssize_t
raid5_store_preread_threshold(struct mddev *mddev, const char *page, size_t len)
{
- struct r5conf *conf = mddev->private;
+ struct r5conf *conf;
unsigned long new;
+ int err;
+
if (len >= PAGE_SIZE)
return -EINVAL;
- if (!conf)
- return -ENODEV;
-
if (kstrtoul(page, 10, &new))
return -EINVAL;
- if (new > conf->max_nr_stripes)
- return -EINVAL;
- conf->bypass_threshold = new;
- return len;
+
+ err = mddev_lock(mddev);
+ if (err)
+ return err;
+ conf = mddev->private;
+ if (!conf)
+ err = -ENODEV;
+ else if (new > conf->max_nr_stripes)
+ err = -EINVAL;
+ else
+ conf->bypass_threshold = new;
+ mddev_unlock(mddev);
+ return err ?: len;
}
static struct md_sysfs_entry
@@ -5475,29 +5487,35 @@ raid5_show_skip_copy(struct mddev *mddev, char *page)
static ssize_t
raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len)
{
- struct r5conf *conf = mddev->private;
+ struct r5conf *conf;
unsigned long new;
+ int err;
+
if (len >= PAGE_SIZE)
return -EINVAL;
- if (!conf)
- return -ENODEV;
-
if (kstrtoul(page, 10, &new))
return -EINVAL;
new = !!new;
- if (new == conf->skip_copy)
- return len;
- mddev_suspend(mddev);
- conf->skip_copy = new;
- if (new)
- mddev->queue->backing_dev_info.capabilities |=
- BDI_CAP_STABLE_WRITES;
- else
- mddev->queue->backing_dev_info.capabilities &=
- ~BDI_CAP_STABLE_WRITES;
- mddev_resume(mddev);
- return len;
+ err = mddev_lock(mddev);
+ if (err)
+ return err;
+ conf = mddev->private;
+ if (!conf)
+ err = -ENODEV;
+ else if (new != conf->skip_copy) {
+ mddev_suspend(mddev);
+ conf->skip_copy = new;
+ if (new)
+ mddev->queue->backing_dev_info.capabilities |=
+ BDI_CAP_STABLE_WRITES;
+ else
+ mddev->queue->backing_dev_info.capabilities &=
+ ~BDI_CAP_STABLE_WRITES;
+ mddev_resume(mddev);
+ }
+ mddev_unlock(mddev);
+ return err ?: len;
}
static struct md_sysfs_entry
@@ -5538,7 +5556,7 @@ static int alloc_thread_groups(struct r5conf *conf, int cnt,
static ssize_t
raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len)
{
- struct r5conf *conf = mddev->private;
+ struct r5conf *conf;
unsigned long new;
int err;
struct r5worker_group *new_groups, *old_groups;
@@ -5546,41 +5564,41 @@ raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len)
if (len >= PAGE_SIZE)
return -EINVAL;
- if (!conf)
- return -ENODEV;
-
if (kstrtoul(page, 10, &new))
return -EINVAL;
- if (new == conf->worker_cnt_per_group)
- return len;
-
- mddev_suspend(mddev);
+ err = mddev_lock(mddev);
+ if (err)
+ return err;
+ conf = mddev->private;
+ if (!conf)
+ err = -ENODEV;
+ else if (new != conf->worker_cnt_per_group) {
+ mddev_suspend(mddev);
- old_groups = conf->worker_groups;
- if (old_groups)
- flush_workqueue(raid5_wq);
+ old_groups = conf->worker_groups;
+ if (old_groups)
+ flush_workqueue(raid5_wq);
- err = alloc_thread_groups(conf, new,
- &group_cnt, &worker_cnt_per_group,
- &new_groups);
- if (!err) {
- spin_lock_irq(&conf->device_lock);
- conf->group_cnt = group_cnt;
- conf->worker_cnt_per_group = worker_cnt_per_group;
- conf->worker_groups = new_groups;
- spin_unlock_irq(&conf->device_lock);
+ err = alloc_thread_groups(conf, new,
+ &group_cnt, &worker_cnt_per_group,
+ &new_groups);
+ if (!err) {
+ spin_lock_irq(&conf->device_lock);
+ conf->group_cnt = group_cnt;
+ conf->worker_cnt_per_group = worker_cnt_per_group;
+ conf->worker_groups = new_groups;
+ spin_unlock_irq(&conf->device_lock);
- if (old_groups)
- kfree(old_groups[0].workers);
- kfree(old_groups);
+ if (old_groups)
+ kfree(old_groups[0].workers);
+ kfree(old_groups);
+ }
+ mddev_resume(mddev);
}
+ mddev_unlock(mddev);
- mddev_resume(mddev);
-
- if (err)
- return err;
- return len;
+ return err ?: len;
}
static struct md_sysfs_entry
^ permalink raw reply related
* [md PATCH 26/26] md: wakeup thread upon rdev_dec_pending()
From: NeilBrown @ 2015-02-03 21:42 UTC (permalink / raw)
To: linux-raid
In-Reply-To: <20150203213948.3448.80258.stgit@notabene.brown>
From: Hannes Reinecke <hare@suse.de>
After each call to rdev_dec_pending() we should wakeup the
md thread if the device is found to be faulty.
Otherwise we'll incur heavy delays on failing devices.
Signed-off-by: Neil Brown <nfbrown@suse.de>
Signed-off-by: Hannes Reinecke <hare@suse.de>
---
drivers/md/md.h | 17 ++++++++++-------
1 file changed, 10 insertions(+), 7 deletions(-)
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 14367d919351..318ca8fd430f 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -474,13 +474,6 @@ static inline int mddev_trylock(struct mddev *mddev)
}
extern void mddev_unlock(struct mddev *mddev);
-static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev)
-{
- int faulty = test_bit(Faulty, &rdev->flags);
- if (atomic_dec_and_test(&rdev->nr_pending) && faulty)
- set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-}
-
static inline void md_sync_acct(struct block_device *bdev, unsigned long nr_sectors)
{
atomic_add(nr_sectors, &bdev->bd_contains->bd_disk->sync_io);
@@ -666,4 +659,14 @@ static inline int mddev_check_plugged(struct mddev *mddev)
return !!blk_check_plugged(md_unplug, mddev,
sizeof(struct blk_plug_cb));
}
+
+static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev)
+{
+ int faulty = test_bit(Faulty, &rdev->flags);
+ if (atomic_dec_and_test(&rdev->nr_pending) && faulty) {
+ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ md_wakeup_thread(mddev->thread);
+ }
+}
+
#endif /* _MD_MD_H */
^ permalink raw reply related
* Re: Off-Topic Write cache disabling?
From: Roger Heflin @ 2015-02-04 0:38 UTC (permalink / raw)
To: Alireza Haghdoost; +Cc: Weedy, Linux RAID
In-Reply-To: <CAB-428kgGgMTiyUgq=0geAMsLGju2QeJvL=GfcChX0W5cBfPBg@mail.gmail.com>
When dirty_cache hits 50mb it writes enough out to get the dirty_cache
down to 25MB (since 25000000 is the lower setting)
On Tue, Feb 3, 2015 at 1:16 PM, Alireza Haghdoost <alireza@cs.umn.edu> wrote:
>> and it syncs down to 25mb when it syncs.
>
> What do you mean by "syncs down to 25mb" ?
^ permalink raw reply
* Re: Off-Topic Write cache disabling?
From: Weedy @ 2015-02-04 5:00 UTC (permalink / raw)
To: Roger Heflin; +Cc: Linux RAID
In-Reply-To: <CAAMCDedvF+Nv9LYqM7Ddgg2xMQKtgQDntOsG0krxWCV4H+zQmA@mail.gmail.com>
On Tue, Feb 3, 2015 at 1:49 PM, Roger Heflin <rogerheflin@gmail.com> wrote:
> In general if you completely disable write caching things will likely
> be unusable. When I have benchmarked things attempting to turn off
> write cache performance has been mostly unusable.
This has little to do with the problem I wanted help with.
^ permalink raw reply
* RE: md_raid5 using 100% CPU and hang with status resync=PENDING, if a drive is removed during initialization
From: Manibalan P @ 2015-02-04 5:56 UTC (permalink / raw)
To: NeilBrown, linux-raid; +Cc: Pasi Kärkkäinen
In-Reply-To: <20150203093040.569aa5e1@notabene.brown>
>> Dear All,
>> Any updates on this issue.
>Probably the same as:
> http://marc.info/?l=linux-raid&m=142283560704091&w=2
Dear Neil
This patch is not fixing this issue.
This issue happens only if a drive removed from a RAID5 array, which is "initializing" and "heavy IO" is performed on the array.
In such case, as soon as the drive removed, the array state changed to resync=PENDING and md0_raid5 thread using 100% of CPU.
Thanks,
Manibalan.
>which follows on from
> http://marc.info/?t=142221642300001&r=1&w=2
>and
> http://marc.info/?t=142172432500001&r=1&w=2
>NeilBrown
-----Original Message-----
From: NeilBrown [mailto:neilb@suse.de]
Sent: Tuesday, February 3, 2015 4:01 AM
To: Manibalan P
Cc: Pasi Kärkkäinen; linux-raid
Subject: Re: md_raid5 using 100% CPU and hang with status resync=PENDING, if a drive is removed during initialization
On Mon, 2 Feb 2015 07:10:14 +0000 Manibalan P <pmanibalan@amiindia.co.in>
wrote:
> Dear All,
> Any updates on this issue.
Probably the same as:
http://marc.info/?l=linux-raid&m=142283560704091&w=2
which follows on from
http://marc.info/?t=142221642300001&r=1&w=2
and
http://marc.info/?t=142172432500001&r=1&w=2
NeilBrown
> Thanks,
> Manibalan.
>
> -----Original Message-----
> From: Manibalan P
> Sent: Wednesday, January 14, 2015 3:55 PM
> To: 'Pasi Kärkkäinen'
> Cc: 'neilb@suse.de'; 'linux-raid'
> Subject: RE: md_raid5 using 100% CPU and hang with status
> resync=PENDING, if a drive is removed during initialization
>
> Dear Pasi,
> Could you able to find something on this issue.
>
> Thanks,
> Manibalan.
>
> -----Original Message-----
> From: Manibalan P
> Sent: Friday, January 2, 2015 12:08 PM
> To: 'Pasi Kärkkäinen'
> Cc: neilb@suse.de; linux-raid
> Subject: RE: md_raid5 using 100% CPU and hang with status
> resync=PENDING, if a drive is removed during initialization
>
> Dear Pasi,
>
> I have add the bug in
> https://bugzilla.redhat.com/show_bug.cgi?id=1178080
>
> Thanks,
> Manibalan.
>
> -----Original Message-----
> From: Pasi Kärkkäinen [mailto:pasik@iki.fi]
> Sent: Wednesday, December 31, 2014 10:18 PM
> To: Manibalan P
> Cc: neilb@suse.de; linux-raid
> Subject: Re: md_raid5 using 100% CPU and hang with status
> resync=PENDING, if a drive is removed during initialization
>
> On Tue, Dec 30, 2014 at 11:06:47AM +0000, Manibalan P wrote:
> > Dear Neil,
> >
>
> Hello,
>
> > Few this for you kind attention,
> > 1. I tried the same test with FC11 (2.6.32 kernel before MD code
> > change). And the issue is not there 2. But with Centos 6.4 (2.6.32 kernel after MD code change). I am getting this issue.. and also even with the latest kernel, able to reproduce the issue.
> >
> > Also, a bug has been raise with RHEL regarding this issue. Please find the bug link "https://access.redhat.com/support/cases/#/case/01320319"
> >
>
> That support case URL can only be accessed by you and Redhat. Do you happen to have a public bugzilla link?
>
>
> Thanks,
>
> -- Pasi
>
> > Thanks,
> > Manibalan.
> >
> > -----Original Message-----
> > From: Manibalan P
> > Sent: Wednesday, December 24, 2014 12:15 PM
> > To: neilb@suse.de; 'linux-raid'
> > Cc: 'NeilBrown'
> > Subject: RE: md_raid5 using 100% CPU and hang with status
> > resync=PENDING, if a drive is removed during initialization
> >
> >
> > Dear Neil,
> >
> > Few this for you kind attention,
> > 1. I tried the same tesst with FC11 (2.6 kernel before MD code change). And the issue is not there 2. But with Centos 6.4 (2.6 after MD code change). I am getting this issue.. and also even with the latest kernel, able to reproduce the issue.
> >
> > Thanks,
> > Manibalan.
> >
> > -----Original Message-----
> > From: Manibalan P
> > Sent: Thursday, December 18, 2014 11:38 AM
> > To: 'linux-raid'
> > Cc: 'NeilBrown'; Vijayarankan Muthirisavengopal; Dinakaran N
> > Subject: RE: md_raid5 using 100% CPU and hang with status
> > resync=PENDING, if a drive is removed during initialization
> >
> > Dear neil,
> >
> > I also compiled the latest 3.18 kernel on CentOS 6.4 with GIT MD pull patches form 3.19, that also ran in to the same issue after removing a drive during resync.
> >
> > Dec 17 19:07:32 ITX002590129362 kernel: Linux version 3.18.0 (root@mycentos6) (gcc version 4.4.7 20120313 (Red Hat 4.4.7-11) (GCC) ) #1 SMP Wed Dec 17 15:59:09 EST 2014 Dec 17 19:07:32 ITX002590129362 kernel: Command line: ro root=/dev/md255 rd_NO_LVM rd_NO_DM rhgb quiet md_mod.start_ro=1 nmi_watchdog=1 md_mod.start_dirty_degraded=1 ??? Dec 17 19:10:15 ITX002590129362 kernel: md: bind<sda6> Dec 17 19:10:15 ITX002590129362 kernel: md: bind<sdb6> Dec 17 19:10:15 ITX002590129362 kernel: md: bind<sdc6> Dec 17 19:10:15 ITX002590129362 kernel: md: bind<sdh6> Dec 17 19:10:15 ITX002590129362 kernel: md: bind<sdi6> Dec 17 19:10:15 ITX002590129362 kernel: md: bind<sdj6> Dec 17 19:10:15 ITX002590129362 kernel: async_tx: api initialized (async) Dec 17 19:10:15 ITX002590129362 kernel: xor: measuring software checksum speed
> > Dec 17 19:10:15 ITX002590129362 kernel: prefetch64-sse: 10048.000 MB/sec
> > Dec 17 19:10:15 ITX002590129362 kernel: generic_sse: 8824.000 MB/sec
> > Dec 17 19:10:15 ITX002590129362 kernel: xor: using function: prefetch64-sse (10048.000 MB/sec)
> > Dec 17 19:10:15 ITX002590129362 kernel: raid6: sse2x1 5921 MB/s
> > Dec 17 19:10:15 ITX002590129362 kernel: raid6: sse2x2 6933 MB/s
> > Dec 17 19:10:15 ITX002590129362 kernel: raid6: sse2x4 7476 MB/s
> > Dec 17 19:10:15 ITX002590129362 kernel: raid6: using algorithm
> > sse2x4
> > (7476 MB/s) Dec 17 19:10:15 ITX002590129362 kernel: raid6: using
> > ssse3x2 recovery algorithm Dec 17 19:10:15 ITX002590129362 kernel: md:
> > raid6 personality registered for level 6 Dec 17 19:10:15
> > ITX002590129362 kernel: md: raid5 personality registered for level 5
> > Dec 17 19:10:15 ITX002590129362 kernel: md: raid4 personality
> > registered for level 4 Dec 17 19:10:15 ITX002590129362 kernel:
> > md/raid:md0: not clean -- starting background reconstruction Dec 17
> > 19:10:15 ITX002590129362 kernel: md/raid:md0: device sdj6
> > operational as raid disk 5 Dec 17 19:10:15 ITX002590129362 kernel: md/raid:md0:
> > device sdi6 operational as raid disk 4 Dec 17 19:10:15
> > ITX002590129362
> > kernel: md/raid:md0: device sdh6 operational as raid disk 3 Dec 17
> > 19:10:15 ITX002590129362 kernel: md/raid:md0: device sdc6
> > operational as raid disk 2 Dec 17 19:10:15 ITX002590129362 kernel: md/raid:md0:
> > device sdb6 operational as raid disk 1 Dec 17 19:10:15
> > ITX002590129362
> > kernel: md/ra
> > id:md0: device sda6 operational as raid disk 0 Dec 17 19:10:15 ITX002590129362 kernel: md/raid:md0: allocated 0kB Dec 17 19:10:15 ITX002590129362 kernel: md/raid:md0: raid level 5 active with 6 out of 6 devices, algorithm 2 Dec 17 19:10:15 ITX002590129362 kernel: md0: detected capacity change from 0 to 2361059573760 Dec 17 19:10:15 ITX002590129362 kernel: md0: unknown partition table Dec 17 19:10:35 ITX002590129362 kernel: md: md0 switched to read-write mode.
> > Dec 17 19:10:35 ITX002590129362 kernel: md: resync of RAID array md0 Dec 17 19:10:35 ITX002590129362 kernel: md: minimum _guaranteed_ speed: 10000 KB/sec/disk.
> > Dec 17 19:10:35 ITX002590129362 kernel: md: using maximum available idle IO bandwidth (but not more than 30000 KB/sec) for resync.
> > Dec 17 19:10:35 ITX002590129362 kernel: md: using 128k window, over a total of 461144448k.
> > ???
> > Started IOs using fio tool.
> >
> > ./fio --name=md0 --filename=/dev/md0 --thread --numjobs=10
> > --direct=1 --group_reporting --unlink=0 --loops=1 --offset=0
> > --randrepeat=1 --norandommap --scramble_buffers=1 --stonewall
> > --ioengine=libaio --rw=randwrite --bs=8704 --iodepth=4000
> > --runtime=3000
> > --blockalign=512
> >
> > ???
> > Removed a drive form the system..
> >
> > Dec 17 19:13:23 ITX002590129362 kernel: mpt2sas0: log_info(0x31120101): originator(PL), code(0x12), sub_code(0x0101) Dec 17 19:13:23 ITX002590129362 kernel: mpt2sas0: log_info(0x31120101): originator(PL), code(0x12), sub_code(0x0101) Dec 17 19:13:23 ITX002590129362 kernel: mpt2sas0: log_info(0x31120101): originator(PL), code(0x12), sub_code(0x0101) Dec 17 19:13:23 ITX002590129362 kernel: mpt2sas0: log_info(0x31120101): originator(PL), code(0x12), sub_code(0x0101) ..
> > Dec 17 19:13:23 ITX002590129362 kernel: sd 0:0:7:0: [sdh] Dec 17 19:13:23 ITX002590129362 kernel: Result: hostbyte=DID_TRANSPORT_DISRUPTED driverbyte=DRIVER_OK Dec 17 19:13:23 ITX002590129362 kernel: sd 0:0:7:0: [sdh] CDB:
> > Dec 17 19:13:23 ITX002590129362 kernel: Read(10): 28 00 02 69 03 70 00 00 10 00 Dec 17 19:13:23 ITX002590129362 kernel: blk_update_request: I/O error, dev sdh, sector 40436592 Dec 17 19:13:23 ITX002590129362 kernel: sd 0:0:7:0: [sdh] Dec 17 19:13:23 ITX002590129362 kernel: Result: hostbyte=DID_TRANSPORT_DISRUPTED driverbyte=DRIVER_OK Dec 17 19:13:23 ITX002590129362 kernel: sd 0:0:7:0: [sdh] CDB:
> > Dec 17 19:13:23 ITX002590129362 kernel: Read(10): 28 00 0c 51 b3 d0 00 00 18 00 Dec 17 19:13:23 ITX002590129362 kernel: blk_update_request: I/O error, dev sdh, sector 206681040 Dec 17 19:13:23 ITX002590129362 kernel: sd 0:0:7:0: [sdh] Dec 17 19:13:23 ITX002590129362 kernel: Result: hostbyte=DID_TRANSPORT_DISRUPTED driverbyte=DRIVER_OK Dec 17 19:13:23 ITX002590129362 kernel: sd 0:0:7:0: [sdh] CDB:
> > Dec 17 19:13:23 ITX002590129362 kernel: Read(10): 28 00 0c 3a f3 40 00 00 18 00 Dec 17 19:13:23 ITX002590129362 kernel: blk_update_request: I/O error, dev sdh, sector 205189952 Dec 17 19:13:23 ITX002590129362 kernel: sd 0:0:7:0: [sdh] Dec 17 19:13:23 ITX002590129362 kernel: Result: hostbyte=DID_TRANSPORT_DISRUPTED driverbyte=DRIVER_OK ??? Dec 17 19:13:25 ITX002590129362 kernel: sd 0:0:7:0: [sdh] CDB:
> > Dec 17 19:13:25 ITX002590129362 kernel: Read(10): 28 00 26 8d eb 00 00 00 08 00 Dec 17 19:13:25 ITX002590129362 kernel: sd 0:0:7:0: [sdh] Dec 17 19:13:25 ITX002590129362 kernel: Result: hostbyte=DID_NO_CONNECT driverbyte=DRIVER_OK Dec 17 19:13:25 ITX002590129362 kernel: sd 0:0:7:0: [sdh] CDB:
> > Dec 17 19:13:25 ITX002590129362 kernel: Read(10): 28 00 26 8d eb f0 00 00 10 00 Dec 17 19:13:25 ITX002590129362 aghswap: devpath [0:0:7:0] action [remove] devtype [scsi_disk] Dec 17 19:13:25 ITX002590129362 aghswap: MHSA: Sent event 0 0 7 0 remove scsi_disk Dec 17 19:13:25 ITX002590129362 kernel: mpt2sas0: removing handle(0x0011), sas_addr(0x500605ba0101e305) Dec 17 19:13:25 ITX002590129362 kernel: md/raid:md0: Disk failure on sdh6, disabling device.
> > Dec 17 19:13:25 ITX002590129362 kernel: md/raid:md0: Operation continuing on 5 devices.
> > Dec 17 19:13:25 ITX002590129362 kernel: md: md0: resync interrupted.
> > Dec 17 19:13:25 ITX002590129362 kernel: md: checkpointing resync of md0.
> > ..
> > Log messages after enabling debufgs on raid5.c, it is getting repeated continuously.
> >
> > __get_priority_stripe: handle: busy hold: empty full_writes: 0
> > bypass_count: 0
> > __get_priority_stripe: handle: busy hold: empty full_writes: 0
> > bypass_count: 0
> > __get_priority_stripe: handle: busy hold: empty full_writes: 0
> > bypass_count: 0
> > __get_priority_stripe: handle: busy hold: empty full_writes: 0
> > bypass_count: 0
> > __get_priority_stripe: handle: busy hold: empty full_writes: 0 bypass_count: 0 handling stripe 273480328, state=0x2041 cnt=1, pd_idx=5, qd_idx=-1 , check:0, reconstruct:0
> > check 5: state 0x10 read (null) write (null) written (null)
> > check 4: state 0x11 read (null) write (null) written (null)
> > check 3: state 0x0 read (null) write (null) written (null)
> > check 2: state 0x11 read (null) write (null) written (null)
> > check 1: state 0x11 read (null) write (null) written (null)
> > check 0: state 0x18 read (null) write ffff8808029b6b00 written (null)
> > locked=0 uptodate=3 to_read=0 to_write=1 failed=1 failed_num=3,-1 force RCW max_degraded=1, recovery_cp=7036944 sh->sector=273480328 for sector 273480328, rmw=2 rcw=1 handling stripe 65238568, state=0x2041 cnt=1, pd_idx=5, qd_idx=-1 , check:0, reconstruct:0
> > check 5: state 0x10 read (null) write (null) written (null)
> > check 4: state 0x11 read (null) write (null) written (null)
> > check 3: state 0x0 read (null) write (null) written (null)
> > check 2: state 0x18 read (null) write ffff88081a956b00 written (null)
> > check 1: state 0x11 read (null) write (null) written (null)
> > check 0: state 0x11 read (null) write (null) written (null)
> > locked=0 uptodate=3 to_read=0 to_write=1 failed=1 failed_num=3,-1 force RCW max_degraded=1, recovery_cp=7036944 sh->sector=65238568 for sector 65238568, rmw=2 rcw=1 handling stripe 713868672, state=0x2041 cnt=1, pd_idx=4, qd_idx=-1 , check:0, reconstruct:0
> > check 5: state 0x11 read (null) write (null) written (null)
> > check 4: state 0x10 read (null) write (null) written (null)
> > check 3: state 0x0 read (null) write (null) written (null)
> > check 2: state 0x18 read (null) write ffff88081f020100 written (null)
> > check 1: state 0x11 read (null) write (null) written (null)
> > check 0: state 0x11 read (null) write (null) written (null)
> > locked=0 uptodate=3 to_read=0 to_write=1 failed=1 failed_num=3,-1 force RCW max_degraded=1, recovery_cp=7036944 sh->sector=713868672 for sector 713868672, rmw=2 rcw=1 handling stripe 729622496, state=0x2041 cnt=1, pd_idx=2, qd_idx=-1 , check:0, reconstruct:0
> > check 5: state 0x11 read (null) write (null) written (null)
> > check 4: state 0x11 read (null) write (null) written (null)
> > check 3: state 0x0 read (null) write (null) written (null)
> > check 2: state 0x10 read (null) write (null) written (null)
> > check 1: state 0x18 read (null) write ffff88081b9bae00 written (null)
> > check 0: state 0x11 read (null) write (null) written (null)
> > locked=0 uptodate=3 to_read=0 to_write=1 failed=1 failed_num=3,-1 force RCW max_degraded=1, recovery_cp=7036944 sh->sector=729622496 for sector 729622496, rmw=2 rcw=1 handling stripe 729622504, state=0x2041 cnt=1, pd_idx=2, qd_idx=-1 , check:0, reconstruct:0
> > check 5: state 0x11 read (null) write (null) written (null)
> > check 4: state 0x11 read (null) write (null) written (null)
> > check 3: state 0x0 read (null) write (null) written (null)
> > check 2: state 0x10 read (null) write (null) written (null)
> > check 1: state 0x18 read (null) write ffff88081b9bae00 written (null)
> > check 0: state 0x11 read (null) write (null) written (null)
> > locked=0 uptodate=3 to_read=0 to_write=1 failed=1 failed_num=3,-1 force RCW max_degraded=1, recovery_cp=7036944 sh->sector=729622504 for sector 729622504, rmw=2 rcw=1 handling stripe 245773680, state=0x2041 cnt=1, pd_idx=0, qd_idx=-1 , check:0, reconstruct:0
> > check 5: state 0x11 read (null) write (null) written (null)
> > check 4: state 0x11 read (null) write (null) written (null)
> > check 3: state 0x0 read (null) write (null) written (null)
> > check 2: state 0x11 read (null) write (null) written (null)
> > check 1: state 0x18 read (null) write ffff88081cab7a00 written (null)
> > check 0: state 0x10 read (null) write (null) written (null)
> > locked=0 uptodate=3 to_read=0 to_write=1 failed=1 failed_num=3,-1 force RCW max_degraded=1, recovery_cp=7036944 sh->sector=245773680 for sector 245773680, rmw=2 rcw=1 handling stripe 867965560, state=0x2041 cnt=1, pd_idx=1, qd_idx=-1 , check:0, reconstruct:0
> > check 5: state 0x11 read (null) write (null) written (null)
> > check 4: state 0x11 read (null) write (null) written (null)
> > check 3: state 0x0 read (null) write (null) written (null)
> > check 2: state 0x18 read (null) write ffff880802b2bf00 written (null)
> > check 1: state 0x10 read (null) write (null) written (null)
> > check 0: state 0x11 read (null) write (null) written (null)
> > locked=0 uptodate=3 to_read=0 to_write=1 failed=1 failed_num=3,-1 force RCW max_degraded=1, recovery_cp=7036944 sh->sector=867965560 for sector 867965560, rmw=2 rcw=1 handling stripe 550162280, state=0x2041 cnt=1, pd_idx=2, qd_idx=-1 , check:0, reconstruct:0
> > check 5: state 0x11 read (null) write (null) written (null)
> > check 4: state 0x18 read (null) write ffff880802b08800 written (null)
> > check 3: state 0x0 read (null) write (null) written (null)
> > check 2: state 0x10 read (null) write (null) written (null)
> > check 1: state 0x11 read (null) write (null) written (null)
> > check 0: state 0x11 read (null) write (null) written (null)
> > locked=0 uptodate=3 to_read=0 to_write=1 failed=1 failed_num=3,-1
> > force RCW max_degraded=1, recovery_cp=7036944 sh->sector=550162280
> > for sector 550162280, rmw=2 rcw=1
> >
> >
> > Thanks,
> > Manibalan
> >
> >
> > -----Original Message-----
> > From: Manibalan P
> > Sent: Wednesday, December 17, 2014 12:11 PM
> > To: 'linux-raid'
> > Cc: 'NeilBrown'; Vijayarankan Muthirisavengopal; Dinakaran N
> > Subject: RE: md_raid5 using 100% CPU and hang with status
> > resync=PENDING, if a drive is removed during initialization
> >
> > Dear Neil,
> >
> > The same Issue is reproducible in the latest upstream kernel also.
> >
> > Tested in "3.17.6" latest stable upstream kernel and find the same issue.
> >
> > [root@root ~]# modinfo raid456
> > filename: /lib/modules/3.17.6/kernel/drivers/md/raid456.ko
> > alias: raid6
> > alias: raid5
> > alias: md-level-6
> > alias: md-raid6
> > alias: md-personality-8
> > alias: md-level-4
> > alias: md-level-5
> > alias: md-raid4
> > alias: md-raid5
> > alias: md-personality-4
> > description: RAID4/5/6 (striping with parity) personality for MD
> > license: GPL
> > srcversion: 0EEF680023FDC7410F7989A
> > depends: async_raid6_recov,async_pq,async_tx,async_memcpy,async_xor
> > intree: Y
> > vermagic: 3.17.6 SMP mod_unload modversions
> > parm: devices_handle_discard_safely:Set to Y if all devices in each array reliably return zeroes on reads from discarded regions (bool)
> >
> > Thanks,
> > Manibalan.
> >
> > -----Original Message-----
> > From: Manibalan P
> > Sent: Wednesday, December 17, 2014 12:01 PM
> > To: 'linux-raid'
> > Cc: 'NeilBrown'
> > Subject: RE: md_raid5 using 100% CPU and hang with status
> > resync=PENDING, if a drive is removed during initialization
> >
> > Dear Neil,
> >
> > We are facing IO struck issue with raid5 in the following scenario.
> > (please see the attachment for the complete information) In RAID5
> > array, if a drive is removed while initialization and the same time
> > if IO is happening to that md. Then IO is getting struck, and
> > md_raid5 thread is using 100 % of CPU. Also the md state showing as
> > resync=PENDING
> >
> > Kernel : Issue found in the following kernels RHEL 6.5
> > (2.6.32-431.el6.x86_64) CentOS 7 (kernel-3.10.0-123.13.1.el7.x86_64)
> >
> > Steps to Reproduce the issue:
> >
> > 1. Created a raid 5 md with 4 drives using the below mdadm command.
> > mdadm -C /dev/md0 -c 64 -l 5 -f -n 4 -e 1.2 /dev/sdb6 /dev/sdc6
> > /dev/sdd6 /dev/sde6
> >
> > 2. Make the md writable
> > mdadm ???readwrite /dev/md0
> >
> > 3. Now md will start initialization
> >
> > 4. Run FIO Tool, the the below said configuration /usr/bin/fio
> > --name=md0 --filename=/dev/md0 --thread --numjobs=10 --direct=1
> > --group_reporting --unlink=0 --loops=1 --offset=0 --randrepeat=1
> > --norandommap --scramble_buffers=1 --stonewall --ioengine=libaio
> > --rw=randwrite --bs=8704 --iodepth=4000 --runtime=3000
> > --blockalign=512
> >
> > 4. During MD initialzing, remove a drive(either using MDADM set
> > faulty/remove or remove manually)
> >
> > 5. Now the IO will struck, and cat /proc/mdstat shows states with
> > resync=PENDING
> > --------------------------------------------------------------------
> > --
> > ----------------------- top - output show, md_raid5 using 100% cpu
> >
> > top - 17:55:06 up 1:09, 3 users, load average: 11.98, 8.53, 3.99
> > PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
> > 2690 root 20 0 0 0 0 R 100.0 0.0 6:44.41 md0_raid5
> > --------------------------------------------------------------------
> > --
> > -----------------------
> > dmesg - show the stack trace
> >
> > INFO: task fio:2715 blocked for more than 120 seconds.
> > Not tainted 2.6.32-431.el6.x86_64 #1 "echo 0 >
> > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
> > fio D 000000000000000a 0 2715 2654 0x00000080
> > ffff88043b623598 0000000000000082 0000000000000000 ffffffff81058d53
> > ffff88043b623548 ffff880230e49cc0 ffff8802389aa228 ffff88043b2ad1b8
> > ffff88043b40b098 ffff88043b623fd8 000000000000fbc8 ffff88043b40b098 Call Trace:
> > [<ffffffff81058d53>] ? __wake_up+0x53/0x70 [<ffffffffa0304146>]
> > get_active_stripe+0x236/0x830 [raid456] [<ffffffff81065df0>] ?
> > default_wake_function+0x0/0x20 [<ffffffff8109b5ce>] ?
> > prepare_to_wait+0x4e/0x80 [<ffffffffa0308e15>]
> > make_request+0x1b5/0xc6c [raid456] [<ffffffff8109b2a0>] ?
> > autoremove_wake_function+0x0/0x40 [<ffffffff8140fa39>] ?
> > md_wakeup_thread+0x39/0x70 [<ffffffff81415b41>]
> > md_make_request+0xe1/0x230 [<ffffffffa0308f66>] ?
> > make_request+0x306/0xc6c [raid456] [<ffffffff81266c50>]
> > generic_make_request+0x240/0x5a0 [<ffffffff811220e5>] ?
> > mempool_alloc_slab+0x15/0x20 [<ffffffff81122283>] ?
> > mempool_alloc+0x63/0x140 [<ffffffff81267020>] submit_bio+0x70/0x120
> > [<ffffffff811c767a>] do_direct_IO+0x7ca/0xfa0 [<ffffffff811c8196>]
> > __blockdev_direct_IO_newtrunc+0x346/0x1270
> > [<ffffffff811c4330>] ? blkdev_get_block+0x0/0x20
> > [<ffffffff811c9137>]
> > __blockdev_direct_IO+0x77/0xe0 [<ffffffff811c4330>] ?
> > blkdev_get_block+0x0/0x20 [<ffffffff811c53b7>]
> > blkdev_direct_IO+0x57/0x60 [<ffffffff811c4330>] ?
> > blkdev_get_block+0x0/0x20 [<ffffffff81120552>]
> > generic_file_direct_write+0xc2/0x190
> > [<ffffffff81121e71>] __generic_file_aio_write+0x3a1/0x490
> > [<ffffffff811d64c0>] ? aio_read_evt+0xa0/0x170 [<ffffffff811c490c>]
> > blkdev_aio_write+0x3c/0xa0 [<ffffffff811c48d0>] ?
> > blkdev_aio_write+0x0/0xa0 [<ffffffff811d4f64>]
> > aio_rw_vect_retry+0x84/0x200 [<ffffffff811d6924>]
> > aio_run_iocb+0x64/0x170 [<ffffffff811d7d51>]
> > do_io_submit+0x291/0x920 [<ffffffff811d83f0>]
> > sys_io_submit+0x10/0x20 [<ffffffff8100b072>]
> > system_call_fastpath+0x16/0x1b
> > INFO: task fio:2717 blocked for more than 120 seconds.
> > Not tainted 2.6.32-431.el6.x86_64 #1 "echo 0 >
> > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
> > fio D 0000000000000004 0 2717 2654 0x00000080
> > ffff880439e97698 0000000000000082 ffff880439e97628 ffffffff81058d53
> > ffff880439e97648 ffff880230e49cc0 ffff8802389aa228 ffff88043b2ad1b8
> > ffff88043b0adab8 ffff880439e97fd8 000000000000fbc8 ffff88043b0adab8 Call Trace:
> > [<ffffffff81058d53>] ? __wake_up+0x53/0x70 [<ffffffffa030334b>] ?
> > md_raid5_unplug_device+0x7b/0x100 [raid456] [<ffffffffa0304146>]
> > get_active_stripe+0x236/0x830 [raid456] [<ffffffff81065df0>] ?
> > default_wake_function+0x0/0x20 [<ffffffff8109b5ce>] ?
> > prepare_to_wait+0x4e/0x80 [<ffffffffa0308e15>]
> > make_request+0x1b5/0xc6c [raid456] [<ffffffff8109b2a0>] ?
> > autoremove_wake_function+0x0/0x40 [<ffffffff811220e5>] ?
> > mempool_alloc_slab+0x15/0x20 [<ffffffff81415b41>]
> > md_make_request+0xe1/0x230 [<ffffffff811c32f0>] ?
> > __bio_add_page+0x110/0x230 [<ffffffff81266c50>]
> > generic_make_request+0x240/0x5a0 [<ffffffff811c742c>] ?
> > do_direct_IO+0x57c/0xfa0 [<ffffffff81267020>] submit_bio+0x70/0x120
> > [<ffffffff811c8e50>] __blockdev_direct_IO_newtrunc+0x1000/0x1270
> > [<ffffffff811c4330>] ? blkdev_get_block+0x0/0x20
> > [<ffffffff811c9137>]
> > __blockdev_direct_IO+0x77/0xe0 [<ffffffff811c4330>] ?
> > blkdev_get_block+0x0/0x20 [<ffffffff811c53b7>]
> > blkdev_direct_IO+0x57/0x60 [<ffffffff811c4330>] ?
> > blkdev_get_block+0x0/0x20 [<ffffffff81120552>]
> > generic_file_direct_write+0xc2/0x190
> > [<ffffffff81121e71>] __generic_file_aio_write+0x3a1/0x490
> > [<ffffffff811d64c0>] ? aio_read_evt+0xa0/0x170 [<ffffffff811c490c>]
> > blkdev_aio_write+0x3c/0xa0 [<ffffffff811c48d0>] ?
> > blkdev_aio_write+0x0/0xa0 [<ffffffff811d4f64>]
> > aio_rw_vect_retry+0x84/0x200 [<ffffffff811d6924>]
> > aio_run_iocb+0x64/0x170 [<ffffffff811d7d51>]
> > do_io_submit+0x291/0x920 [<ffffffff811d83f0>]
> > sys_io_submit+0x10/0x20 [<ffffffff8100b072>]
> > system_call_fastpath+0x16/0x1b
> > INFO: task fio:2718 blocked for more than 120 seconds.
> > Not tainted 2.6.32-431.el6.x86_64 #1 "echo 0 >
> > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
> > fio D 0000000000000005 0 2718 2654 0x00000080
> > ffff88043bc13698 0000000000000082 ffff88043bc13628 ffffffff81058d53
> > ffff88043bc13648 ffff880230e49cc0 ffff8802389aa228 ffff88043b2ad1b8
> > ffff88043b0ad058 ffff88043bc13fd8 000000000000fbc8 ffff88043b0ad058 Call Trace:
> > [<ffffffff81058d53>] ? __wake_up+0x53/0x70 [<ffffffffa030334b>] ?
> > md_raid5_unplug_device+0x7b/0x100 [raid456] [<ffffffffa0304146>]
> > get_active_stripe+0x236/0x830 [raid456] [<ffffffff81065df0>] ?
> > default_wake_function+0x0/0x20 [<ffffffff8109b5ce>] ?
> > prepare_to_wait+0x4e/0x80 [<ffffffffa0308e15>]
> > make_request+0x1b5/0xc6c [raid456] [<ffffffff8109b2a0>] ?
> > autoremove_wake_function+0x0/0x40 [<ffffffff811220e5>] ?
> > mempool_alloc_slab+0x15/0x20 [<ffffffff81415b41>]
> > md_make_request+0xe1/0x230 [<ffffffff811c3fd2>] ?
> > bvec_alloc_bs+0x62/0x110 [<ffffffff811c32f0>] ?
> > __bio_add_page+0x110/0x230 [<ffffffff81266c50>]
> > generic_make_request+0x240/0x5a0 [<ffffffff811c742c>] ?
> > do_direct_IO+0x57c/0xfa0 [<ffffffff81267020>] submit_bio+0x70/0x120
> > [<ffffffff811c8e50>] __blockdev_direct_IO_newtrunc+0x1000/0x1270
> > [<ffffffff811c4330>] ? blkdev_get_block+0x0/0x20
> > [<ffffffff811c9137>]
> > __blockdev_direct_IO+0x77/0xe0 [<ffffffff811c4330>] ?
> > blkdev_get_block+0x0/0x20 [<ffffffff811c53b7>]
> > blkdev_direct_IO+0x57/0x60 [<ffffffff811c4330>] ?
> > blkdev_get_block+0x0/0x20 [<ffffffff81120552>]
> > generic_file_direct_write+0xc2/0x190
> > [<ffffffff81121e71>] __generic_file_aio_write+0x3a1/0x490
> > [<ffffffff811d64c0>] ? aio_read_evt+0xa0/0x170 [<ffffffff811c490c>]
> > blkdev_aio_write+0x3c/0xa0 [<ffffffff811c48d0>] ?
> > blkdev_aio_write+0x0/0xa0 [<ffffffff811d4f64>]
> > aio_rw_vect_retry+0x84/0x200 [<ffffffff811d6924>]
> > aio_run_iocb+0x64/0x170 [<ffffffff811d7d51>]
> > do_io_submit+0x291/0x920 [<ffffffff811d83f0>]
> > sys_io_submit+0x10/0x20 [<ffffffff8100b072>]
> > system_call_fastpath+0x16/0x1b
> > INFO: task fio:2719 blocked for more than 120 seconds.
> > Not tainted 2.6.32-431.el6.x86_64 #1 "echo 0 >
> > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
> > fio D 0000000000000001 0 2719 2654 0x00000080
> > ffff880439ebb698 0000000000000082 ffff880439ebb628 ffffffff81058d53
> > ffff880439ebb648 ffff880230e49cc0 ffff8802389aa228 ffff88043b2ad1b8
> > ffff88043b0ac5f8 ffff880439ebbfd8 000000000000fbc8 ffff88043b0ac5f8 Call Trace:
> > [<ffffffff81058d53>] ? __wake_up+0x53/0x70 [<ffffffffa030334b>] ?
> > md_raid5_unplug_device+0x7b/0x100 [raid456] [<ffffffffa0304146>]
> > get_active_stripe+0x236/0x830 [raid456] [<ffffffff81065df0>] ?
> > default_wake_function+0x0/0x20 [<ffffffff8109b5ce>] ?
> > prepare_to_wait+0x4e/0x80 [<ffffffffa0308e15>]
> > make_request+0x1b5/0xc6c [raid456] [<ffffffff8109b2a0>] ?
> > autoremove_wake_function+0x0/0x40 [<ffffffff811220e5>] ?
> > mempool_alloc_slab+0x15/0x20 [<ffffffff81415b41>]
> > md_make_request+0xe1/0x230 [<ffffffff811c3fd2>] ?
> > bvec_alloc_bs+0x62/0x110 [<ffffffff811c32f0>] ?
> > __bio_add_page+0x110/0x230 [<ffffffff81266c50>]
> > generic_make_request+0x240/0x5a0 [<ffffffff811c742c>] ?
> > do_direct_IO+0x57c/0xfa0 [<ffffffff81267020>] submit_bio+0x70/0x120
> > [<ffffffff811c8acd>] __blockdev_direct_IO_newtrunc+0xc7d/0x1270
> > [<ffffffff811c4330>] ? blkdev_get_block+0x0/0x20
> > [<ffffffff811c9137>]
> > __blockdev_direct_IO+0x77/0xe0 [<ffffffff811c4330>] ?
> > blkdev_get_block+0x0/0x20 [<ffffffff811c53b7>]
> > blkdev_direct_IO+0x57/0x60 [<ffffffff811c4330>] ?
> > blkdev_get_block+0x0/0x20 [<ffffffff81120552>]
> > generic_file_direct_write+0xc2/0x190
> > [<ffffffff81121e71>] __generic_file_aio_write+0x3a1/0x490
> > [<ffffffff811d64c0>] ? aio_read_evt+0xa0/0x170 [<ffffffff811c490c>]
> > blkdev_aio_write+0x3c/0xa0 [<ffffffff811c48d0>] ?
> > blkdev_aio_write+0x0/0xa0 [<ffffffff811d4f64>]
> > aio_rw_vect_retry+0x84/0x200 [<ffffffff811d6924>]
> > aio_run_iocb+0x64/0x170 [<ffffffff811d7d51>]
> > do_io_submit+0x291/0x920 [<ffffffff811d83f0>]
> > sys_io_submit+0x10/0x20 [<ffffffff8100b072>]
> > system_call_fastpath+0x16/0x1b
> > INFO: task fio:2720 blocked for more than 120 seconds.
> > Not tainted 2.6.32-431.el6.x86_64 #1 "echo 0 >
> > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
> > fio D 0000000000000008 0 2720 2654 0x00000080
> > ffff88043b8cf698 0000000000000082 ffff88043b8cf628 ffffffff81058d53
> > ffff88043b8cf648 ffff880230e49cc0 ffff8802389aa228 ffff88043b2ad1b8
> > ffff880439e89af8 ffff88043b8cffd8 000000000000fbc8 ffff880439e89af8 Call Trace:
> > [<ffffffff81058d53>] ? __wake_up+0x53/0x70 [<ffffffffa030334b>] ?
> > md_raid5_unplug_device+0x7b/0x100 [raid456] [<ffffffffa0304146>]
> > get_active_stripe+0x236/0x830 [raid456] [<ffffffff81065df0>] ?
> > default_wake_function+0x0/0x20 [<ffffffff8109b5ce>] ?
> > prepare_to_wait+0x4e/0x80 [<ffffffffa0308e15>]
> > make_request+0x1b5/0xc6c [raid456] [<ffffffff8109b2a0>] ?
> > autoremove_wake_function+0x0/0x40 [<ffffffff811220e5>] ?
> > mempool_alloc_slab+0x15/0x20 [<ffffffff81415b41>]
> > md_make_request+0xe1/0x230 [<ffffffff811c3fd2>] ?
> > bvec_alloc_bs+0x62/0x110 [<ffffffff811c32f0>] ?
> > __bio_add_page+0x110/0x230 [<ffffffff81266c50>]
> > generic_make_request+0x240/0x5a0 [<ffffffff811c742c>] ?
> > do_direct_IO+0x57c/0xfa0 [<ffffffff81267020>] submit_bio+0x70/0x120
> > [<ffffffff811c8acd>] __blockdev_direct_IO_newtrunc+0xc7d/0x1270
> > [<ffffffff811c4330>] ? blkdev_get_block+0x0/0x20
> > [<ffffffff811c9137>]
> > __blockdev_direct_IO+0x77/0xe0 [<ffffffff811c4330>] ?
> > blkdev_get_block+0x0/0x20 [<ffffffff811c53b7>]
> > blkdev_direct_IO+0x57/0x60 [<ffffffff811c4330>] ?
> > blkdev_get_block+0x0/0x20 [<ffffffff81120552>]
> > generic_file_direct_write+0xc2/0x190
> > [<ffffffff81121e71>] __generic_file_aio_write+0x3a1/0x490
> > [<ffffffff811d64c0>] ? aio_read_evt+0xa0/0x170 [<ffffffff811c490c>]
> > blkdev_aio_write+0x3c/0xa0 [<ffffffff811c48d0>] ?
> > blkdev_aio_write+0x0/0xa0 [<ffffffff811d4f64>]
> > aio_rw_vect_retry+0x84/0x200 [<ffffffff811d6924>]
> > aio_run_iocb+0x64/0x170 [<ffffffff811d7d51>]
> > do_io_submit+0x291/0x920 [<ffffffff811d83f0>]
> > sys_io_submit+0x10/0x20 [<ffffffff8100b072>]
> > system_call_fastpath+0x16/0x1b
> > INFO: task fio:2721 blocked for more than 120 seconds.
> > Not tainted 2.6.32-431.el6.x86_64 #1 "echo 0 >
> > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
> > fio D 0000000000000000 0 2721 2654 0x00000080
> > ffff88043b047698 0000000000000082 ffff88043b047628 ffffffff81058d53
> > ffff88043b047648 ffff880230e49cc0 ffff8802389aa228 ffff88043b2ad1b8
> > ffff880439e89098 ffff88043b047fd8 000000000000fbc8 ffff880439e89098 Call Trace:
> > [<ffffffff81058d53>] ? __wake_up+0x53/0x70 [<ffffffffa030334b>] ?
> > md_raid5_unplug_device+0x7b/0x100 [raid456] [<ffffffffa0304146>]
> > get_active_stripe+0x236/0x830 [raid456] [<ffffffff81065df0>] ?
> > default_wake_function+0x0/0x20 [<ffffffff8109b5ce>] ?
> > prepare_to_wait+0x4e/0x80 [<ffffffffa0308e15>]
> > make_request+0x1b5/0xc6c [raid456] [<ffffffff8109b2a0>] ?
> > autoremove_wake_function+0x0/0x40 [<ffffffff811220e5>] ?
> > mempool_alloc_slab+0x15/0x20 [<ffffffff81415b41>]
> > md_make_request+0xe1/0x230 [<ffffffff811c3fd2>] ?
> > bvec_alloc_bs+0x62/0x110 [<ffffffff811c32f0>] ?
> > __bio_add_page+0x110/0x230 [<ffffffff81266c50>]
> > generic_make_request+0x240/0x5a0 [<ffffffff811c742c>] ?
> > do_direct_IO+0x57c/0xfa0 [<ffffffff81267020>] submit_bio+0x70/0x120
> > [<ffffffff811c8acd>] __blockdev_direct_IO_newtrunc+0xc7d/0x1270
> > [<ffffffff811c4330>] ? blkdev_get_block+0x0/0x20
> > [<ffffffff811c9137>]
> > __blockdev_direct_IO+0x77/0xe0 [<ffffffff811c4330>] ?
> > blkdev_get_block+0x0/0x20 [<ffffffff811c53b7>]
> > blkdev_direct_IO+0x57/0x60 [<ffffffff811c4330>] ?
> > blkdev_get_block+0x0/0x20 [<ffffffff81120552>]
> > generic_file_direct_write+0xc2/0x190
> > [<ffffffff81121e71>] __generic_file_aio_write+0x3a1/0x490
> > [<ffffffff811d64c0>] ? aio_read_evt+0xa0/0x170 [<ffffffff811c490c>]
> > blkdev_aio_write+0x3c/0xa0 [<ffffffff811c48d0>] ?
> > blkdev_aio_write+0x0/0xa0 [<ffffffff811d4f64>]
> > aio_rw_vect_retry+0x84/0x200 [<ffffffff811d6924>]
> > aio_run_iocb+0x64/0x170 [<ffffffff811d7d51>]
> > do_io_submit+0x291/0x920 [<ffffffff811d83f0>]
> > sys_io_submit+0x10/0x20 [<ffffffff8100b072>]
> > system_call_fastpath+0x16/0x1b
> > INFO: task fio:2722 blocked for more than 120 seconds.
> > Not tainted 2.6.32-431.el6.x86_64 #1 "echo 0 >
> > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
> > fio D 0000000000000000 0 2722 2654 0x00000080
> > ffff880439ea3698 0000000000000082 ffff880439ea3628 ffffffff81058d53
> > ffff880439ea3648 ffff880230e49cc0 ffff8802389aa228 ffff88043b2ad1b8
> > ffff880439e88638 ffff880439ea3fd8 000000000000fbc8 ffff880439e88638 Call Trace:
> > [<ffffffff81058d53>] ? __wake_up+0x53/0x70 [<ffffffffa030334b>] ?
> > md_raid5_unplug_device+0x7b/0x100 [raid456] [<ffffffffa0304146>]
> > get_active_stripe+0x236/0x830 [raid456] [<ffffffff81065df0>] ?
> > default_wake_function+0x0/0x20 [<ffffffff8109b5ce>] ?
> > prepare_to_wait+0x4e/0x80 [<ffffffffa0308e15>]
> > make_request+0x1b5/0xc6c [raid456] [<ffffffff8109b2a0>] ?
> > autoremove_wake_function+0x0/0x40 [<ffffffff811220e5>] ?
> > mempool_alloc_slab+0x15/0x20 [<ffffffff81415b41>]
> > md_make_request+0xe1/0x230 [<ffffffff811c3fd2>] ?
> > bvec_alloc_bs+0x62/0x110 [<ffffffff811c32f0>] ?
> > __bio_add_page+0x110/0x230 [<ffffffff81266c50>]
> > generic_make_request+0x240/0x5a0 [<ffffffff811c742c>] ?
> > do_direct_IO+0x57c/0xfa0 [<ffffffff81267020>] submit_bio+0x70/0x120
> > [<ffffffff811c8acd>] __blockdev_direct_IO_newtrunc+0xc7d/0x1270
> > [<ffffffff811c4330>] ? blkdev_get_block+0x0/0x20
> > [<ffffffff811c9137>]
> > __blockdev_direct_IO+0x77/0xe0 [<ffffffff811c4330>] ?
> > blkdev_get_block+0x0/0x20 [<ffffffff811c53b7>]
> > blkdev_direct_IO+0x57/0x60 [<ffffffff811c4330>] ?
> > blkdev_get_block+0x0/0x20 [<ffffffff81120552>]
> > generic_file_direct_write+0xc2/0x190
> > [<ffffffff81121e71>] __generic_file_aio_write+0x3a1/0x490
> > [<ffffffff811d64c0>] ? aio_read_evt+0xa0/0x170 [<ffffffff811c490c>]
> > blkdev_aio_write+0x3c/0xa0 [<ffffffff811c48d0>] ?
> > blkdev_aio_write+0x0/0xa0 [<ffffffff811d4f64>]
> > aio_rw_vect_retry+0x84/0x200 [<ffffffff811d6924>]
> > aio_run_iocb+0x64/0x170 [<ffffffff811d7d51>]
> > do_io_submit+0x291/0x920 [<ffffffff811d83f0>]
> > sys_io_submit+0x10/0x20 [<ffffffff8100b072>]
> > system_call_fastpath+0x16/0x1b
> > INFO: task fio:2723 blocked for more than 120 seconds.
> > Not tainted 2.6.32-431.el6.x86_64 #1 "echo 0 >
> > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
> > fio D 0000000000000006 0 2723 2654 0x00000080
> > ffff88043bf5f698 0000000000000082 ffff88043bf5f628 ffffffff81058d53
> > ffff88043bf5f648 ffff880230e49cc0 ffff8802389aa228 ffff88043b2ad1b8
> > ffff88043a183ab8 ffff88043bf5ffd8 000000000000fbc8 ffff88043a183ab8 Call Trace:
> > [<ffffffff81058d53>] ? __wake_up+0x53/0x70 [<ffffffffa030334b>] ?
> > md_raid5_unplug_device+0x7b/0x100 [raid456] [<ffffffffa0304146>]
> > get_active_stripe+0x236/0x830 [raid456] [<ffffffff81065df0>] ?
> > default_wake_function+0x0/0x20 [<ffffffff8109b5ce>] ?
> > prepare_to_wait+0x4e/0x80 [<ffffffffa0308e15>]
> > make_request+0x1b5/0xc6c [raid456] [<ffffffff8109b2a0>] ?
> > autoremove_wake_function+0x0/0x40 [<ffffffff811220e5>] ?
> > mempool_alloc_slab+0x15/0x20 [<ffffffff81415b41>]
> > md_make_request+0xe1/0x230 [<ffffffff811c3fd2>] ?
> > bvec_alloc_bs+0x62/0x110 [<ffffffff811c32f0>] ?
> > __bio_add_page+0x110/0x230 [<ffffffff81266c50>]
> > generic_make_request+0x240/0x5a0 [<ffffffff811c742c>] ?
> > do_direct_IO+0x57c/0xfa0 [<ffffffff81267020>] submit_bio+0x70/0x120
> > [<ffffffff811c8acd>] __blockdev_direct_IO_newtrunc+0xc7d/0x1270
> > [<ffffffff811c4330>] ? blkdev_get_block+0x0/0x20
> > [<ffffffff811c9137>]
> > __blockdev_direct_IO+0x77/0xe0 [<ffffffff811c4330>] ?
> > blkdev_get_block+0x0/0x20 [<ffffffff811c53b7>]
> > blkdev_direct_IO+0x57/0x60 [<ffffffff811c4330>] ?
> > blkdev_get_block+0x0/0x20 [<ffffffff81120552>]
> > generic_file_direct_write+0xc2/0x190
> > [<ffffffff81121e71>] __generic_file_aio_write+0x3a1/0x490
> > [<ffffffff811d64c0>] ? aio_read_evt+0xa0/0x170 [<ffffffff811c490c>]
> > blkdev_aio_write+0x3c/0xa0 [<ffffffff811c48d0>] ?
> > blkdev_aio_write+0x0/0xa0 [<ffffffff811d4f64>]
> > aio_rw_vect_retry+0x84/0x200 [<ffffffff811d6924>]
> > aio_run_iocb+0x64/0x170 [<ffffffff811d7d51>]
> > do_io_submit+0x291/0x920 [<ffffffff811d83f0>]
> > sys_io_submit+0x10/0x20 [<ffffffff8100b072>]
> > system_call_fastpath+0x16/0x1b
> > INFO: task fio:2724 blocked for more than 120 seconds.
> > Not tainted 2.6.32-431.el6.x86_64 #1 "echo 0 >
> > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
> > fio D 000000000000000b 0 2724 2654 0x00000080
> > ffff88043be05698 0000000000000082 ffff88043be05628 ffffffff81058d53
> > ffff88043be05648 ffff880230e49cc0 ffff8802389aa228 ffff88043b2ad1b8
> > ffff88043a183058 ffff88043be05fd8 000000000000fbc8 ffff88043a183058 Call Trace:
> > [<ffffffff81058d53>] ? __wake_up+0x53/0x70 [<ffffffffa030334b>] ?
> > md_raid5_unplug_device+0x7b/0x100 [raid456] [<ffffffffa0304146>]
> > get_active_stripe+0x236/0x830 [raid456] [<ffffffff81065df0>] ?
> > default_wake_function+0x0/0x20 [<ffffffff8109b5ce>] ?
> > prepare_to_wait+0x4e/0x80 [<ffffffffa0308e15>]
> > make_request+0x1b5/0xc6c [raid456] [<ffffffff8109b2a0>] ?
> > autoremove_wake_function+0x0/0x40 [<ffffffff811220e5>] ?
> > mempool_alloc_slab+0x15/0x20 [<ffffffff81415b41>]
> > md_make_request+0xe1/0x230 [<ffffffff811c3fd2>] ?
> > bvec_alloc_bs+0x62/0x110 [<ffffffff811c32f0>] ?
> > __bio_add_page+0x110/0x230 [<ffffffff81266c50>]
> > generic_make_request+0x240/0x5a0 [<ffffffff811c742c>] ?
> > do_direct_IO+0x57c/0xfa0 [<ffffffff81267020>] submit_bio+0x70/0x120
> > [<ffffffff811c8acd>] __blockdev_direct_IO_newtrunc+0xc7d/0x1270
> > [<ffffffff811c4330>] ? blkdev_get_block+0x0/0x20
> > [<ffffffff811c9137>]
> > __blockdev_direct_IO+0x77/0xe0 [<ffffffff811c4330>] ?
> > blkdev_get_block+0x0/0x20 [<ffffffff811c53b7>]
> > blkdev_direct_IO+0x57/0x60 [<ffffffff811c4330>] ?
> > blkdev_get_block+0x0/0x20 [<ffffffff81120552>]
> > generic_file_direct_write+0xc2/0x190
> > [<ffffffff81121e71>] __generic_file_aio_write+0x3a1/0x490
> > [<ffffffff811d64c0>] ? aio_read_evt+0xa0/0x170 [<ffffffff811c490c>]
> > blkdev_aio_write+0x3c/0xa0 [<ffffffff811c48d0>] ?
> > blkdev_aio_write+0x0/0xa0 [<ffffffff811d4f64>]
> > aio_rw_vect_retry+0x84/0x200 [<ffffffff811d6924>]
> > aio_run_iocb+0x64/0x170 [<ffffffff811d7d51>]
> > do_io_submit+0x291/0x920 [<ffffffff811d83f0>]
> > sys_io_submit+0x10/0x20 [<ffffffff8100b072>]
> > system_call_fastpath+0x16/0x1b
> > INFO: task fio:2725 blocked for more than 120 seconds.
> > Not tainted 2.6.32-431.el6.x86_64 #1 "echo 0 >
> > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
> > fio D 0000000000000003 0 2725 2654 0x00000080
> > ffff88043be07698 0000000000000082 ffff88043be07628 ffffffff81058d53
> > ffff88043be07648 ffff880230e49cc0 ffff8802389aa228 ffff88043b2ad1b8
> > ffff88043a1825f8 ffff88043be07fd8 000000000000fbc8 ffff88043a1825f8 Call Trace:
> > [<ffffffff81058d53>] ? __wake_up+0x53/0x70 [<ffffffffa030334b>] ?
> > md_raid5_unplug_device+0x7b/0x100 [raid456] [<ffffffffa0304146>]
> > get_active_stripe+0x236/0x830 [raid456] [<ffffffff81065df0>] ?
> > default_wake_function+0x0/0x20 [<ffffffff8109b5ce>] ?
> > prepare_to_wait+0x4e/0x80 [<ffffffffa0308e15>]
> > make_request+0x1b5/0xc6c [raid456] [<ffffffff8109b2a0>] ?
> > autoremove_wake_function+0x0/0x40 [<ffffffff811220e5>] ?
> > mempool_alloc_slab+0x15/0x20 [<ffffffff81415b41>]
> > md_make_request+0xe1/0x230 [<ffffffff811c3fd2>] ?
> > bvec_alloc_bs+0x62/0x110 [<ffffffff811c32f0>] ?
> > __bio_add_page+0x110/0x230 [<ffffffff81266c50>]
> > generic_make_request+0x240/0x5a0 [<ffffffff811c742c>] ?
> > do_direct_IO+0x57c/0xfa0 [<ffffffff81267020>] submit_bio+0x70/0x120
> > [<ffffffff811c8acd>] __blockdev_direct_IO_newtrunc+0xc7d/0x1270
> > [<ffffffff811c4330>] ? blkdev_get_block+0x0/0x20
> > [<ffffffff811c9137>]
> > __blockdev_direct_IO+0x77/0xe0 [<ffffffff811c4330>] ?
> > blkdev_get_block+0x0/0x20 [<ffffffff811c53b7>]
> > blkdev_direct_IO+0x57/0x60 [<ffffffff811c4330>] ?
> > blkdev_get_block+0x0/0x20 [<ffffffff81120552>]
> > generic_file_direct_write+0xc2/0x190
> > [<ffffffff81121e71>] __generic_file_aio_write+0x3a1/0x490
> > [<ffffffff811d64c0>] ? aio_read_evt+0xa0/0x170 [<ffffffff811c490c>]
> > blkdev_aio_write+0x3c/0xa0 [<ffffffff811c48d0>] ?
> > blkdev_aio_write+0x0/0xa0 [<ffffffff811d4f64>]
> > aio_rw_vect_retry+0x84/0x200 [<ffffffff811d6924>]
> > aio_run_iocb+0x64/0x170 [<ffffffff811d7d51>]
> > do_io_submit+0x291/0x920 [<ffffffff811d83f0>]
> > sys_io_submit+0x10/0x20 [<ffffffff8100b072>]
> > system_call_fastpath+0x16/0x1b
> >
> > [root@root ~]# cat /proc/2690/stack
> > [<ffffffff810686da>] __cond_resched+0x2a/0x40 [<ffffffffa030361c>]
> > ops_run_io+0x2c/0x920 [raid456] [<ffffffffa03052cc>]
> > handle_stripe+0x9cc/0x2980 [raid456] [<ffffffffa03078a4>]
> > raid5d+0x624/0x850 [raid456] [<ffffffff81416f05>]
> > md_thread+0x115/0x150 [<ffffffff8109aef6>] kthread+0x96/0xa0
> > [<ffffffff8100c20a>] child_rip+0xa/0x20 [<ffffffffffffffff>]
> > 0xffffffffffffffff
> >
> > [root@root ~]# cat /proc/2690/stat
> > 2690 (md0_raid5) R 2 0 0 0 -1 2149613632 0 0 0 0 0 68495 0 0 20 0 1
> > 0
> > 350990 0 0 18446744073709551615 0 0 0 0 0 0 0 2147483391 256 0 0 0
> > 17
> > 2 0 0 6855 0 0 [root@root ~]# cat /proc/2690/statm
> > 0 0 0 0 0 0 0
> > [root@root ~]# cat /proc/2690/stat
> > stat statm status
> > [root@root ~]# cat /proc/2690/status
> > Name: md0_raid5
> > State: R (running)
> > Tgid: 2690
> > Pid: 2690
> > PPid: 2
> > TracerPid: 0
> > Uid: 0 0 0 0
> > Gid: 0 0 0 0
> > Utrace: 0
> > FDSize: 64
> > Groups:
> > Threads: 1
> > SigQ: 2/128402
> > SigPnd: 0000000000000000
> > ShdPnd: 0000000000000000
> > SigBlk: 0000000000000000
> > SigIgn: fffffffffffffeff
> > SigCgt: 0000000000000100
> > CapInh: 0000000000000000
> > CapPrm: ffffffffffffffff
> > CapEff: fffffffffffffeff
> > CapBnd: ffffffffffffffff
> > Cpus_allowed: ffffff
> > Cpus_allowed_list: 0-23
> > Mems_allowed: 00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000003
> > Mems_allowed_list: 0-1
> > voluntary_ctxt_switches: 5411612
> > nonvoluntary_ctxt_switches: 257032
> >
> >
> > Thanks,
> > Manibalan.
> --
> To unsubscribe from this list: send the line "unsubscribe linux-raid"
> in the body of a message to majordomo@vger.kernel.org More majordomo
> info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: Can't reshape raid0 to raid10
From: NeilBrown @ 2015-02-04 6:39 UTC (permalink / raw)
To: Xiao Ni; +Cc: linux-raid
In-Reply-To: <484995116.1735572.1419909221275.JavaMail.zimbra@redhat.com>
[-- Attachment #1: Type: text/plain, Size: 4916 bytes --]
On Mon, 29 Dec 2014 22:13:41 -0500 (EST) Xiao Ni <xni@redhat.com> wrote:
> Hi Neil
>
> When I try to reshape a raid0 to raid10, it'll fail like this:
>
> [root@dhcp-12-133 mdadm-3.3.2]# lsblk
> NAME MAJ:MIN RM SIZE RO TYPE MOUNTPOINT
> sda 8:0 0 111.8G 0 disk
> ├─sda1 8:1 0 1000M 0 part /boot
> ├─sda2 8:2 0 29.3G 0 part /
> ├─sda3 8:3 0 512M 0 part [SWAP]
> ├─sda4 8:4 0 1K 0 part
> ├─sda5 8:5 0 102M 0 part
> └─sda6 8:6 0 10.1G 0 part
> └─VolGroup00-LogVol00 254:0 0 9.9G 0 lvm
> sdb 8:16 0 111.8G 0 disk
> ├─sdb1 8:17 0 2G 0 part
> └─sdb2 8:18 0 10G 0 part
> sdc 8:32 0 186.3G 0 disk
> ├─sdc1 8:33 0 2G 0 part
> └─sdc2 8:34 0 10G 0 part
> sdd 8:48 0 111.8G 0 disk
> ├─sdd1 8:49 0 2G 0 part
> └─sdd2 8:50 0 10G 0 part
> [root@dhcp-12-133 mdadm-3.3.2]# mdadm -CR /dev/md0 -l0 -n3 /dev/sdb1 /dev/sdc1 /dev/sdd1
> mdadm: Defaulting to version 1.2 metadata
> mdadm: array /dev/md0 started.
> [root@dhcp-12-133 mdadm-3.3.2]# mdadm --grow /dev/md0 -l10 -a /dev/sdb2 /dev/sdc2 /dev/sdd2
> mdadm: level of /dev/md0 changed to raid10
> mdadm: add new device failed for /dev/sdb2 as 6: No space left on device
>
>
> But if I reshape the raid0 to raid5, reshape raid5 to raid0, then reshape raid0 to raid10 use
> the same command it'll succeed.
>
> [root@dhcp-12-133 mdadm-3.3.2]# mdadm -CR /dev/md0 -l0 -n3 /dev/sdb1 /dev/sdc1 /dev/sdd1
> [root@dhcp-12-133 mdadm-3.3.2]# mdadm --grow /dev/md0 -l5
> [root@dhcp-12-133 mdadm-3.3.2]# cat /proc/mdstat
> Personalities : [raid6] [raid5] [raid4] [raid0] [raid10]
> md0 : active raid5 sdd1[2] sdc1[1] sdb1[0]
> 6285312 blocks super 1.2 level 5, 512k chunk, algorithm 2 [4/3] [UUU_]
>
> unused devices: <none>
>
> [root@dhcp-12-133 mdadm-3.3.2]# mdadm --grow /dev/md0 -l0
> [root@dhcp-12-133 mdadm-3.3.2]# cat /proc/mdstat
> Personalities : [raid6] [raid5] [raid4] [raid0] [raid10]
> md0 : active raid0 sdd1[2] sdc1[1] sdb1[0]
> 6285312 blocks super 1.2 512k chunks
>
> unused devices: <none>
> [root@dhcp-12-133 mdadm-3.3.2]# mdadm --grow /dev/md0 -l10 -a /dev/sdb2 /dev/sdc2 /dev/sdd2
> mdadm: level of /dev/md0 changed to raid10
> mdadm: added /dev/sdb2
> mdadm: added /dev/sdc2
> mdadm: added /dev/sdd2
>
> So I guess it's the problem add the disk to raid10 after the reshaping. In the function
> super_1_validate, it'll set the mddev->dev_sectors using the superblock read from disks.
> If it's raid0, the le64_to_cpu(sb-size) is 0. So when add disk to raid10 bind_rdev_to_array
> return -ENOSPC.
>
> When create raid0, it doesn't write give the value to s->size. So the sb-size is 0.
> I modify the code about Create.c. I'm not sure whether it's right to do so. But it can resolve
> the problem.
Thanks for the report.
I think this need to be fixing in the md driver, when the reshape happens.
Something like the following.
NeilBrown
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index d1203cddb024..b8d76b1fba64 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -3872,7 +3872,7 @@ static int raid10_resize(struct mddev *mddev, sector_t sectors)
return 0;
}
-static void *raid10_takeover_raid0(struct mddev *mddev)
+static void *raid10_takeover_raid0(struct mddev *mddev, sector_t size, int devs)
{
struct md_rdev *rdev;
struct r10conf *conf;
@@ -3882,6 +3882,7 @@ static void *raid10_takeover_raid0(struct mddev *mddev)
mdname(mddev));
return ERR_PTR(-EINVAL);
}
+ sector_div(size, devs);
/* Set new parameters */
mddev->new_level = 10;
@@ -3892,12 +3893,15 @@ static void *raid10_takeover_raid0(struct mddev *mddev)
mddev->raid_disks *= 2;
/* make sure it will be not marked as dirty */
mddev->recovery_cp = MaxSector;
+ mddev->dev_sectors = size;
conf = setup_conf(mddev);
if (!IS_ERR(conf)) {
rdev_for_each(rdev, mddev)
- if (rdev->raid_disk >= 0)
+ if (rdev->raid_disk >= 0) {
rdev->new_raid_disk = rdev->raid_disk * 2;
+ rdev->sectors = size;
+ }
conf->barrier = 1;
}
@@ -3920,7 +3924,9 @@ static void *raid10_takeover(struct mddev *mddev)
mdname(mddev));
return ERR_PTR(-EINVAL);
}
- return raid10_takeover_raid0(mddev);
+ return raid10_takeover_raid0(mddev,
+ raid0_conf->strip_zone->zone_end,
+ raid0_conf->strip_zone->nb_dev);
}
return ERR_PTR(-EINVAL);
}
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 811 bytes --]
^ permalink raw reply related
* Re: Array died during grow; now resync stopped
From: NeilBrown @ 2015-02-04 6:45 UTC (permalink / raw)
To: Jörg Habenicht; +Cc: linux-raid
In-Reply-To: <trinity-d6d8d6b9-e19b-4ff6-a39f-3748b5fb2e13-1422959753855@3capp-gmx-bs42>
[-- Attachment #1: Type: text/plain, Size: 7305 bytes --]
On Tue, 3 Feb 2015 11:35:53 +0100 "Jörg Habenicht" <j.habenicht@gmx.de> wrote:
> Hello Neil,
>
> thank you for caring.
>
> (And sorry for the malformed structure, I have to use webmail.. )
>
>
> On Mon, 2 Feb 2015 09:41:02 +0000 (UTC) Jörg Habenicht <j.habenicht@gmx.de>
> wrote:
>
> > Hi all,
> >
> > I had a server crash during an array grow.
> > Commandline was "mdadm --grow /dev/md0 --raid-devices=6 --chunk=1M"
> >
> >
> >
> > Could this be caused by a software lock?
>
> >Some sort of software problem I suspect.
> >What does
> >cat /proc/1671/stack
> >cat /proc/1672/stack
> >show?
>
> $ cat /proc/1671/stack
> cat: /proc/1671/stack: No such file or directory
I guess you don't have that feature compiled into your kernel.
>
> Huch?
> $ ls /proc/1671
> ls: cannot read symbolic link /proc/1671/exe: No such file or directory
> attr comm fdinfo mounts oom_score stat
> autogroup coredump_filter io mountstats oom_score_adj statm
> auxv cwd limits net pagemap status
> cgroup environ maps ns personality syscall
> clear_refs exe mem numa_maps root task
> cmdline fd mountinfo oom_adj smaps wchan
> $ id
> uid=0(root) gid=0(root) groups=0(root), ...
>
> $ cat /proc/1672/stack
> cat: /proc/1672/stack: No such file or directory
>
>
> >Alternatively,
> >echo w > /proc/sysrq-trigger
> >and see what appears in 'dmesg'.
>
> No good:
Quite the reverse, this is exactly what I wanted. It shows the stack trace
of pid 1671 and 1672..
>
> [99166.625796] SysRq : Show Blocked State
> [99166.625829] task PC stack pid father
> [99166.625845] md0_reshape D ffff88006cb81e08 0 1671 2 0x00000000
> [99166.625854] ffff88006a17fb30 0000000000000046 000000000000a000 ffff88006cc9b7e0
> [99166.625861] ffff88006a17ffd8 ffff88006cc9b7e0 ffff88006fc11830 ffff88006fc11830
> [99166.625866] 0000000000000001 ffffffff81068670 ffff88006ca56848 ffff88006fc11830
> [99166.625871] Call Trace:
> [99166.625884] [<ffffffff81068670>] ? __dequeue_entity+0x40/0x50
> [99166.625891] [<ffffffff8106b966>] ? pick_next_task_fair+0x56/0x1b0
> [99166.625898] [<ffffffff813f4a50>] ? __schedule+0x2a0/0x820
> [99166.625905] [<ffffffff8106273d>] ? ttwu_do_wakeup+0xd/0x80
> [99166.625914] [<ffffffffa027b4c5>] ? get_active_stripe+0x185/0x5c0 [raid456]
> [99166.625922] [<ffffffff81072110>] ? __wake_up_sync+0x10/0x10
> [99166.625929] [<ffffffffa027e83a>] ? reshape_request+0x21a/0x860 [raid456]
> [99166.625935] [<ffffffff81072110>] ? __wake_up_sync+0x10/0x10
> [99166.625942] [<ffffffffa02744f6>] ? sync_request+0x236/0x380 [raid456]
> [99166.625955] [<ffffffffa01557ad>] ? md_do_sync+0x82d/0xd00 [md_mod]
> [99166.625961] [<ffffffff810684b4>] ? update_curr+0x64/0xe0
> [99166.625971] [<ffffffffa0152197>] ? md_thread+0xf7/0x110 [md_mod]
> [99166.625977] [<ffffffff81072110>] ? __wake_up_sync+0x10/0x10
> [99166.625985] [<ffffffffa01520a0>] ? md_register_thread+0xf0/0xf0 [md_mod]
> [99166.625991] [<ffffffff81059de8>] ? kthread+0xb8/0xd0
> [99166.625997] [<ffffffff81059d30>] ? kthread_create_on_node+0x180/0x180
> [99166.626003] [<ffffffff813f837c>] ? ret_from_fork+0x7c/0xb0
> [99166.626008] [<ffffffff81059d30>] ? kthread_create_on_node+0x180/0x180
That's not surprise. Whenever anything goes wrong in raid5, something gets
stuck in get_active_stripe()...
> [99166.626012] udevd D ffff88006cb81e08 0 1672 1289 0x00000004
> [99166.626017] ffff88006a1819e8 0000000000000086 000000000000a000 ffff88006c4967a0
> [99166.626022] ffff88006a181fd8 ffff88006c4967a0 0000000000000000 0000000000000000
> [99166.626027] 0000000000000000 0000000000000000 0000000000000000 0000000000000000
> [99166.626032] Call Trace:
> [99166.626039] [<ffffffff810c24ed>] ? zone_statistics+0x9d/0xa0
> [99166.626044] [<ffffffff810c24ed>] ? zone_statistics+0x9d/0xa0
> [99166.626050] [<ffffffff810b13e7>] ? get_page_from_freelist+0x507/0x850
> [99166.626057] [<ffffffffa027b4c5>] ? get_active_stripe+0x185/0x5c0 [raid456]
> [99166.626063] [<ffffffff81072110>] ? __wake_up_sync+0x10/0x10
> [99166.626069] [<ffffffffa027f627>] ? make_request+0x7a7/0xa00 [raid456]
> [99166.626075] [<ffffffff81080afd>] ? ktime_get_ts+0x3d/0xd0
> [99166.626080] [<ffffffff81072110>] ? __wake_up_sync+0x10/0x10
> [99166.626089] [<ffffffffa014ea12>] ? md_make_request+0xd2/0x210 [md_mod]
> [99166.626096] [<ffffffff811e649d>] ? generic_make_request_checks+0x23d/0x270
> [99166.626100] [<ffffffff810acc68>] ? mempool_alloc+0x58/0x140
> [99166.626106] [<ffffffff811e7238>] ? generic_make_request+0xa8/0xf0
> [99166.626111] [<ffffffff811e72e7>] ? submit_bio+0x67/0x130
> [99166.626117] [<ffffffff8112a638>] ? bio_alloc_bioset+0x1b8/0x2a0
> [99166.626123] [<ffffffff81126a57>] ? _submit_bh+0x127/0x200
> [99166.626129] [<ffffffff8112815d>] ? block_read_full_page+0x1fd/0x290
> [99166.626133] [<ffffffff8112b680>] ? I_BDEV+0x10/0x10
> [99166.626140] [<ffffffff810aad2b>] ? add_to_page_cache_locked+0x6b/0xc0
> [99166.626146] [<ffffffff810b5520>] ? __do_page_cache_readahead+0x1b0/0x220
> [99166.626152] [<ffffffff810b5812>] ? force_page_cache_readahead+0x62/0xa0
> [99166.626159] [<ffffffff810ac936>] ? generic_file_aio_read+0x4b6/0x6c0
> [99166.626166] [<ffffffff810f9f87>] ? do_sync_read+0x57/0x90
> [99166.626172] [<ffffffff810fa571>] ? vfs_read+0xa1/0x180
> [99166.626178] [<ffffffff810fb0ab>] ? SyS_read+0x4b/0xc0
> [99166.626183] [<ffffffff813f7f72>] ? page_fault+0x22/0x30
> [99166.626190] [<ffffffff813f8422>] ? system_call_fastpath+0x16/0x1b
And this is stuck in the same place.... what what is consuming all the
stripes I wonder....
>
>
> >
> > The system got 2G RAM and 2G swap. Is this sufficient to complete?
>
> >Memory shouldn't be a problem.
> >However it wouldn't hurt to see what value is in
> >/sys/block/md0/md/stripe_cache_size
> >and double it.
>
> $ cat /sys/block/md0/md/stripe_cache_size
> 256
You are setting the chunk size to 1M, which is 256 4K pages.
So this stripe_cache only just has enough space to store one full stripe at
the new chunk size. That isn't enough.
If you double it, the problem should go away.
mdadm should do that for you .... I wonder why it didn't.
>
> I did not change it due to the crash in md_reshape
What crash is that? The above stack traces that you said "No good" about?
That isn't a crash. That is the kernel showing you stack traces because you
asked for them.
echo 1024 > /sys/block/md0/md/stripe_cache_size
should make it work.
NeilBrown
>
>
> >If all else fails a reboot should be safe and will probably start the reshape
> >properly. md is very careful about surviving reboots.
>
> I already did reboot twice before I wrote to the list. Same result.
>
>
> >NeilBrown
>
>
> cu,
> Joerg
>
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-raid" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 811 bytes --]
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox