md/raid10: convert resync_lock to use seqlock
Currently, wait_barrier() will hold 'resync_lock' to read 'conf->barrier', and io can't be dispatched until 'barrier' is dropped. Since holding the 'barrier' is not common, convert 'resync_lock' to use seqlock so that holding lock can be avoided in fast path. Signed-off-by: Yu Kuai <yukuai3@huawei.com> Reviewed-and-Tested-by: Logan Gunthorpe <logang@deltatee.com> Signed-off-by: Song Liu <song@kernel.org>
This commit is contained in:
parent
4f350284a7
commit
b9b083f904
|
@ -79,6 +79,21 @@ static void end_reshape(struct r10conf *conf);
|
|||
|
||||
#include "raid1-10.c"
|
||||
|
||||
#define NULL_CMD
|
||||
#define cmd_before(conf, cmd) \
|
||||
do { \
|
||||
write_sequnlock_irq(&(conf)->resync_lock); \
|
||||
cmd; \
|
||||
} while (0)
|
||||
#define cmd_after(conf) write_seqlock_irq(&(conf)->resync_lock)
|
||||
|
||||
#define wait_event_barrier_cmd(conf, cond, cmd) \
|
||||
wait_event_cmd((conf)->wait_barrier, cond, cmd_before(conf, cmd), \
|
||||
cmd_after(conf))
|
||||
|
||||
#define wait_event_barrier(conf, cond) \
|
||||
wait_event_barrier_cmd(conf, cond, NULL_CMD)
|
||||
|
||||
/*
|
||||
* for resync bio, r10bio pointer can be retrieved from the per-bio
|
||||
* 'struct resync_pages'.
|
||||
|
@ -936,30 +951,29 @@ static void flush_pending_writes(struct r10conf *conf)
|
|||
|
||||
static void raise_barrier(struct r10conf *conf, int force)
|
||||
{
|
||||
spin_lock_irq(&conf->resync_lock);
|
||||
write_seqlock_irq(&conf->resync_lock);
|
||||
BUG_ON(force && !conf->barrier);
|
||||
|
||||
/* Wait until no block IO is waiting (unless 'force') */
|
||||
wait_event_lock_irq(conf->wait_barrier, force || !conf->nr_waiting,
|
||||
conf->resync_lock);
|
||||
wait_event_barrier(conf, force || !conf->nr_waiting);
|
||||
|
||||
/* block any new IO from starting */
|
||||
conf->barrier++;
|
||||
WRITE_ONCE(conf->barrier, conf->barrier + 1);
|
||||
|
||||
/* Now wait for all pending IO to complete */
|
||||
wait_event_lock_irq(conf->wait_barrier,
|
||||
!atomic_read(&conf->nr_pending) && conf->barrier < RESYNC_DEPTH,
|
||||
conf->resync_lock);
|
||||
wait_event_barrier(conf, !atomic_read(&conf->nr_pending) &&
|
||||
conf->barrier < RESYNC_DEPTH);
|
||||
|
||||
spin_unlock_irq(&conf->resync_lock);
|
||||
write_sequnlock_irq(&conf->resync_lock);
|
||||
}
|
||||
|
||||
static void lower_barrier(struct r10conf *conf)
|
||||
{
|
||||
unsigned long flags;
|
||||
spin_lock_irqsave(&conf->resync_lock, flags);
|
||||
conf->barrier--;
|
||||
spin_unlock_irqrestore(&conf->resync_lock, flags);
|
||||
|
||||
write_seqlock_irqsave(&conf->resync_lock, flags);
|
||||
WRITE_ONCE(conf->barrier, conf->barrier - 1);
|
||||
write_sequnlock_irqrestore(&conf->resync_lock, flags);
|
||||
wake_up(&conf->wait_barrier);
|
||||
}
|
||||
|
||||
|
@ -990,11 +1004,31 @@ static bool stop_waiting_barrier(struct r10conf *conf)
|
|||
return false;
|
||||
}
|
||||
|
||||
static bool wait_barrier_nolock(struct r10conf *conf)
|
||||
{
|
||||
unsigned int seq = read_seqbegin(&conf->resync_lock);
|
||||
|
||||
if (READ_ONCE(conf->barrier))
|
||||
return false;
|
||||
|
||||
atomic_inc(&conf->nr_pending);
|
||||
if (!read_seqretry(&conf->resync_lock, seq))
|
||||
return true;
|
||||
|
||||
if (atomic_dec_and_test(&conf->nr_pending))
|
||||
wake_up_barrier(conf);
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
static bool wait_barrier(struct r10conf *conf, bool nowait)
|
||||
{
|
||||
bool ret = true;
|
||||
|
||||
spin_lock_irq(&conf->resync_lock);
|
||||
if (wait_barrier_nolock(conf))
|
||||
return true;
|
||||
|
||||
write_seqlock_irq(&conf->resync_lock);
|
||||
if (conf->barrier) {
|
||||
/* Return false when nowait flag is set */
|
||||
if (nowait) {
|
||||
|
@ -1002,9 +1036,7 @@ static bool wait_barrier(struct r10conf *conf, bool nowait)
|
|||
} else {
|
||||
conf->nr_waiting++;
|
||||
raid10_log(conf->mddev, "wait barrier");
|
||||
wait_event_lock_irq(conf->wait_barrier,
|
||||
stop_waiting_barrier(conf),
|
||||
conf->resync_lock);
|
||||
wait_event_barrier(conf, stop_waiting_barrier(conf));
|
||||
conf->nr_waiting--;
|
||||
}
|
||||
if (!conf->nr_waiting)
|
||||
|
@ -1013,7 +1045,7 @@ static bool wait_barrier(struct r10conf *conf, bool nowait)
|
|||
/* Only increment nr_pending when we wait */
|
||||
if (ret)
|
||||
atomic_inc(&conf->nr_pending);
|
||||
spin_unlock_irq(&conf->resync_lock);
|
||||
write_sequnlock_irq(&conf->resync_lock);
|
||||
return ret;
|
||||
}
|
||||
|
||||
|
@ -1038,27 +1070,24 @@ static void freeze_array(struct r10conf *conf, int extra)
|
|||
* must match the number of pending IOs (nr_pending) before
|
||||
* we continue.
|
||||
*/
|
||||
spin_lock_irq(&conf->resync_lock);
|
||||
write_seqlock_irq(&conf->resync_lock);
|
||||
conf->array_freeze_pending++;
|
||||
conf->barrier++;
|
||||
WRITE_ONCE(conf->barrier, conf->barrier + 1);
|
||||
conf->nr_waiting++;
|
||||
wait_event_lock_irq_cmd(conf->wait_barrier,
|
||||
atomic_read(&conf->nr_pending) == conf->nr_queued+extra,
|
||||
conf->resync_lock,
|
||||
flush_pending_writes(conf));
|
||||
|
||||
wait_event_barrier_cmd(conf, atomic_read(&conf->nr_pending) ==
|
||||
conf->nr_queued + extra, flush_pending_writes(conf));
|
||||
conf->array_freeze_pending--;
|
||||
spin_unlock_irq(&conf->resync_lock);
|
||||
write_sequnlock_irq(&conf->resync_lock);
|
||||
}
|
||||
|
||||
static void unfreeze_array(struct r10conf *conf)
|
||||
{
|
||||
/* reverse the effect of the freeze */
|
||||
spin_lock_irq(&conf->resync_lock);
|
||||
conf->barrier--;
|
||||
write_seqlock_irq(&conf->resync_lock);
|
||||
WRITE_ONCE(conf->barrier, conf->barrier - 1);
|
||||
conf->nr_waiting--;
|
||||
wake_up(&conf->wait_barrier);
|
||||
spin_unlock_irq(&conf->resync_lock);
|
||||
write_sequnlock_irq(&conf->resync_lock);
|
||||
}
|
||||
|
||||
static sector_t choose_data_offset(struct r10bio *r10_bio,
|
||||
|
@ -4045,7 +4074,7 @@ static struct r10conf *setup_conf(struct mddev *mddev)
|
|||
INIT_LIST_HEAD(&conf->retry_list);
|
||||
INIT_LIST_HEAD(&conf->bio_end_io_list);
|
||||
|
||||
spin_lock_init(&conf->resync_lock);
|
||||
seqlock_init(&conf->resync_lock);
|
||||
init_waitqueue_head(&conf->wait_barrier);
|
||||
atomic_set(&conf->nr_pending, 0);
|
||||
|
||||
|
@ -4364,7 +4393,7 @@ static void *raid10_takeover_raid0(struct mddev *mddev, sector_t size, int devs)
|
|||
rdev->new_raid_disk = rdev->raid_disk * 2;
|
||||
rdev->sectors = size;
|
||||
}
|
||||
conf->barrier = 1;
|
||||
WRITE_ONCE(conf->barrier, 1);
|
||||
}
|
||||
|
||||
return conf;
|
||||
|
|
|
@ -76,7 +76,7 @@ struct r10conf {
|
|||
/* queue pending writes and submit them on unplug */
|
||||
struct bio_list pending_bio_list;
|
||||
|
||||
spinlock_t resync_lock;
|
||||
seqlock_t resync_lock;
|
||||
atomic_t nr_pending;
|
||||
int nr_waiting;
|
||||
int nr_queued;
|
||||
|
|
Loading…
Reference in New Issue