All of lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH V4] md: move bitmap_destroy to the beginning of __md_stop
@ 2017-03-14  1:40 Guoqing Jiang
  2017-03-14 18:05 ` Shaohua Li
  0 siblings, 1 reply; 2+ messages in thread
From: Guoqing Jiang @ 2017-03-14  1:40 UTC (permalink / raw)
  To: linux-raid; +Cc: neilb, shli, Guoqing Jiang

Since we have switched to sync way to handle METADATA_UPDATED
msg for md-cluster, then process_metadata_update is depended
on mddev->thread->wqueue.

With the new change, clustered raid could possible hang if
array received a METADATA_UPDATED msg after array unregistered
mddev->thread, so we need to stop clustered raid (bitmap_destroy
-> bitmap_free -> md_cluster_stop) earlier than unregister
thread (mddev_detach -> md_unregister_thread).

And this change should be safe for non-clustered raid since
all writes are stopped before the destroy. Also in md_run,
we activate the personality (pers->run()) before activating
the bitmap (bitmap_create()). So it is pleasingly symmetric
to stop the bitmap (bitmap_destroy()) before stopping the
personality (__md_stop() calls pers->free()), we achieve this
by move bitmap_destroy to the beginning of __md_stop.

But we don't want to break the codes for waiting behind IO as
Shaohua mentioned, so introduce bitmap_wait_behind_writes to
call the codes, and call the new fun in both mddev_detach and
bitmap_destroy, then we will not break original behind IO code
and also fit the new condition well.

Signed-off-by: Guoqing Jiang <gqjiang@suse.com>
---
Changes from v3:
1. move bitmap_destroy to __md_stop
2. add bitmap_wait_behind_writes to handle behind IO

 drivers/md/bitmap.c | 17 +++++++++++++++++
 drivers/md/bitmap.h |  1 +
 drivers/md/md.c     | 13 ++-----------
 3 files changed, 20 insertions(+), 11 deletions(-)

diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index b6fa55a3cff8..20cad80d6e34 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -1764,6 +1764,21 @@ void bitmap_free(struct bitmap *bitmap)
 }
 EXPORT_SYMBOL(bitmap_free);
 
+void bitmap_wait_behind_writes(struct mddev *mddev)
+{
+	struct bitmap *bitmap = mddev->bitmap;
+
+	/* wait for behind writes to complete */
+	if (bitmap && atomic_read(&bitmap->behind_writes) > 0) {
+		pr_debug("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);
+	}
+}
+EXPORT_SYMBOL(bitmap_wait_behind_writes);
+
 void bitmap_destroy(struct mddev *mddev)
 {
 	struct bitmap *bitmap = mddev->bitmap;
@@ -1771,6 +1786,8 @@ void bitmap_destroy(struct mddev *mddev)
 	if (!bitmap) /* there was no bitmap */
 		return;
 
+	bitmap_wait_behind_writes(mddev);
+
 	mutex_lock(&mddev->bitmap_info.mutex);
 	spin_lock(&mddev->lock);
 	mddev->bitmap = NULL; /* disconnect from the md device */
diff --git a/drivers/md/bitmap.h b/drivers/md/bitmap.h
index 9f761097aab2..d15721ac07a6 100644
--- a/drivers/md/bitmap.h
+++ b/drivers/md/bitmap.h
@@ -271,6 +271,7 @@ struct bitmap *get_bitmap_from_slot(struct mddev *mddev, int slot);
 int bitmap_copy_from_slot(struct mddev *mddev, int slot,
 				sector_t *lo, sector_t *hi, bool clear_bits);
 void bitmap_free(struct bitmap *bitmap);
+void bitmap_wait_behind_writes(struct mddev *mddev);
 #endif
 
 #endif
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 79a99a1c9ce7..dc131fabfc7c 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5534,15 +5534,7 @@ 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) {
-		pr_debug("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);
-	}
+	bitmap_wait_behind_writes(mddev);
 	if (mddev->pers && mddev->pers->quiesce) {
 		mddev->pers->quiesce(mddev, 1);
 		mddev->pers->quiesce(mddev, 0);
@@ -5555,6 +5547,7 @@ static void mddev_detach(struct mddev *mddev)
 static void __md_stop(struct mddev *mddev)
 {
 	struct md_personality *pers = mddev->pers;
+	bitmap_destroy(mddev);
 	mddev_detach(mddev);
 	/* Ensure ->event_work is done */
 	flush_workqueue(md_misc_wq);
@@ -5575,7 +5568,6 @@ void md_stop(struct mddev *mddev)
 	 * This is called from dm-raid
 	 */
 	__md_stop(mddev);
-	bitmap_destroy(mddev);
 	if (mddev->bio_set)
 		bioset_free(mddev->bio_set);
 }
@@ -5713,7 +5705,6 @@ static int do_md_stop(struct mddev *mddev, int mode,
 	if (mode == 0) {
 		pr_info("md: %s stopped.\n", mdname(mddev));
 
-		bitmap_destroy(mddev);
 		if (mddev->bitmap_info.file) {
 			struct file *f = mddev->bitmap_info.file;
 			spin_lock(&mddev->lock);
-- 
2.6.2


^ permalink raw reply related	[flat|nested] 2+ messages in thread

* Re: [PATCH V4] md: move bitmap_destroy to the beginning of __md_stop
  2017-03-14  1:40 [PATCH V4] md: move bitmap_destroy to the beginning of __md_stop Guoqing Jiang
@ 2017-03-14 18:05 ` Shaohua Li
  0 siblings, 0 replies; 2+ messages in thread
From: Shaohua Li @ 2017-03-14 18:05 UTC (permalink / raw)
  To: Guoqing Jiang; +Cc: linux-raid, neilb, shli

On Tue, Mar 14, 2017 at 09:40:20AM +0800, Guoqing Jiang wrote:
> Since we have switched to sync way to handle METADATA_UPDATED
> msg for md-cluster, then process_metadata_update is depended
> on mddev->thread->wqueue.
> 
> With the new change, clustered raid could possible hang if
> array received a METADATA_UPDATED msg after array unregistered
> mddev->thread, so we need to stop clustered raid (bitmap_destroy
> -> bitmap_free -> md_cluster_stop) earlier than unregister
> thread (mddev_detach -> md_unregister_thread).
> 
> And this change should be safe for non-clustered raid since
> all writes are stopped before the destroy. Also in md_run,
> we activate the personality (pers->run()) before activating
> the bitmap (bitmap_create()). So it is pleasingly symmetric
> to stop the bitmap (bitmap_destroy()) before stopping the
> personality (__md_stop() calls pers->free()), we achieve this
> by move bitmap_destroy to the beginning of __md_stop.
> 
> But we don't want to break the codes for waiting behind IO as
> Shaohua mentioned, so introduce bitmap_wait_behind_writes to
> call the codes, and call the new fun in both mddev_detach and
> bitmap_destroy, then we will not break original behind IO code
> and also fit the new condition well.
> 
> Signed-off-by: Guoqing Jiang <gqjiang@suse.com>
> ---
> Changes from v3:
> 1. move bitmap_destroy to __md_stop
> 2. add bitmap_wait_behind_writes to handle behind IO
> 
>  drivers/md/bitmap.c | 17 +++++++++++++++++
>  drivers/md/bitmap.h |  1 +
>  drivers/md/md.c     | 13 ++-----------
>  3 files changed, 20 insertions(+), 11 deletions(-)
> 
> diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
> index b6fa55a3cff8..20cad80d6e34 100644
> --- a/drivers/md/bitmap.c
> +++ b/drivers/md/bitmap.c
> @@ -1764,6 +1764,21 @@ void bitmap_free(struct bitmap *bitmap)
>  }
>  EXPORT_SYMBOL(bitmap_free);
>  
> +void bitmap_wait_behind_writes(struct mddev *mddev)
> +{
> +	struct bitmap *bitmap = mddev->bitmap;
> +
> +	/* wait for behind writes to complete */
> +	if (bitmap && atomic_read(&bitmap->behind_writes) > 0) {
> +		pr_debug("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);
> +	}
> +}
> +EXPORT_SYMBOL(bitmap_wait_behind_writes);

Applied, thanks! I deleted the EXPORT_SYMBOL here, it's not used by a module.

>  void bitmap_destroy(struct mddev *mddev)
>  {
>  	struct bitmap *bitmap = mddev->bitmap;
> @@ -1771,6 +1786,8 @@ void bitmap_destroy(struct mddev *mddev)
>  	if (!bitmap) /* there was no bitmap */
>  		return;
>  
> +	bitmap_wait_behind_writes(mddev);
> +
>  	mutex_lock(&mddev->bitmap_info.mutex);
>  	spin_lock(&mddev->lock);
>  	mddev->bitmap = NULL; /* disconnect from the md device */
> diff --git a/drivers/md/bitmap.h b/drivers/md/bitmap.h
> index 9f761097aab2..d15721ac07a6 100644
> --- a/drivers/md/bitmap.h
> +++ b/drivers/md/bitmap.h
> @@ -271,6 +271,7 @@ struct bitmap *get_bitmap_from_slot(struct mddev *mddev, int slot);
>  int bitmap_copy_from_slot(struct mddev *mddev, int slot,
>  				sector_t *lo, sector_t *hi, bool clear_bits);
>  void bitmap_free(struct bitmap *bitmap);
> +void bitmap_wait_behind_writes(struct mddev *mddev);
>  #endif
>  
>  #endif
> diff --git a/drivers/md/md.c b/drivers/md/md.c
> index 79a99a1c9ce7..dc131fabfc7c 100644
> --- a/drivers/md/md.c
> +++ b/drivers/md/md.c
> @@ -5534,15 +5534,7 @@ 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) {
> -		pr_debug("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);
> -	}
> +	bitmap_wait_behind_writes(mddev);
>  	if (mddev->pers && mddev->pers->quiesce) {
>  		mddev->pers->quiesce(mddev, 1);
>  		mddev->pers->quiesce(mddev, 0);
> @@ -5555,6 +5547,7 @@ static void mddev_detach(struct mddev *mddev)
>  static void __md_stop(struct mddev *mddev)
>  {
>  	struct md_personality *pers = mddev->pers;
> +	bitmap_destroy(mddev);
>  	mddev_detach(mddev);
>  	/* Ensure ->event_work is done */
>  	flush_workqueue(md_misc_wq);
> @@ -5575,7 +5568,6 @@ void md_stop(struct mddev *mddev)
>  	 * This is called from dm-raid
>  	 */
>  	__md_stop(mddev);
> -	bitmap_destroy(mddev);
>  	if (mddev->bio_set)
>  		bioset_free(mddev->bio_set);
>  }
> @@ -5713,7 +5705,6 @@ static int do_md_stop(struct mddev *mddev, int mode,
>  	if (mode == 0) {
>  		pr_info("md: %s stopped.\n", mdname(mddev));
>  
> -		bitmap_destroy(mddev);
>  		if (mddev->bitmap_info.file) {
>  			struct file *f = mddev->bitmap_info.file;
>  			spin_lock(&mddev->lock);
> -- 
> 2.6.2
> 
> --
> 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	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2017-03-14 18:05 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2017-03-14  1:40 [PATCH V4] md: move bitmap_destroy to the beginning of __md_stop Guoqing Jiang
2017-03-14 18:05 ` Shaohua Li

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.