Re: [patch 06/10 v3] raid5: reduce chance release_stripe() taking device_lock

[NeilBrown <neilb@xxxxxxx>]

On Mon, 25 Jun 2012 15:24:53 +0800 Shaohua Li <shli@xxxxxxxxxx> wrote:

> release_stripe() is a place conf->device_lock is heavily contended. We take the
> lock even stripe count isn't 1, which isn't required.
> 
> Signed-off-by: Shaohua Li <shli@xxxxxxxxxxxx>
> ---
>  drivers/md/raid5.c |   73 +++++++++++++++++++++++++++++------------------------
>  1 file changed, 40 insertions(+), 33 deletions(-)
> 
> Index: linux/drivers/md/raid5.c
> ===================================================================
> --- linux.orig/drivers/md/raid5.c	2012-06-25 14:37:21.000000000 +0800
> +++ linux/drivers/md/raid5.c	2012-06-25 14:38:13.899130571 +0800
> @@ -196,49 +196,56 @@ static int stripe_operations_active(stru
>  	       test_bit(STRIPE_COMPUTE_RUN, &sh->state);
>  }
>  
> -static void __release_stripe(struct r5conf *conf, struct stripe_head *sh)
> +static void handle_release_stripe(struct r5conf *conf, struct stripe_head *sh)
>  {
> -	if (atomic_dec_and_test(&sh->count)) {
> -		BUG_ON(!list_empty(&sh->lru));
> -		BUG_ON(atomic_read(&conf->active_stripes)==0);
> -		if (test_bit(STRIPE_HANDLE, &sh->state)) {
> -			if (test_bit(STRIPE_DELAYED, &sh->state) &&
> -			    !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
> -				list_add_tail(&sh->lru, &conf->delayed_list);
> -			else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
> -				   sh->bm_seq - conf->seq_write > 0)
> -				list_add_tail(&sh->lru, &conf->bitmap_list);
> -			else {
> -				clear_bit(STRIPE_DELAYED, &sh->state);
> -				clear_bit(STRIPE_BIT_DELAY, &sh->state);
> -				list_add_tail(&sh->lru, &conf->handle_list);
> -			}
> -			md_wakeup_thread(conf->mddev->thread);
> -		} else {
> -			BUG_ON(stripe_operations_active(sh));
> -			if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
> -				if (atomic_dec_return(&conf->preread_active_stripes)
> -				    < IO_THRESHOLD)
> -					md_wakeup_thread(conf->mddev->thread);
> -			atomic_dec(&conf->active_stripes);
> -			if (!test_bit(STRIPE_EXPANDING, &sh->state)) {
> -				list_add_tail(&sh->lru, &conf->inactive_list);
> -				wake_up(&conf->wait_for_stripe);
> -				if (conf->retry_read_aligned)
> -					md_wakeup_thread(conf->mddev->thread);
> -			}
> +	BUG_ON(!list_empty(&sh->lru));
> +	BUG_ON(atomic_read(&conf->active_stripes)==0);
> +	if (test_bit(STRIPE_HANDLE, &sh->state)) {
> +		if (test_bit(STRIPE_DELAYED, &sh->state) &&
> +		    !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
> +			list_add_tail(&sh->lru, &conf->delayed_list);
> +		else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
> +			   sh->bm_seq - conf->seq_write > 0)
> +			list_add_tail(&sh->lru, &conf->bitmap_list);
> +		else {
> +			clear_bit(STRIPE_DELAYED, &sh->state);
> +			clear_bit(STRIPE_BIT_DELAY, &sh->state);
> +			list_add_tail(&sh->lru, &conf->handle_list);
> +		}
> +		md_wakeup_thread(conf->mddev->thread);
> +	} else {
> +		BUG_ON(stripe_operations_active(sh));
> +		if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
> +			if (atomic_dec_return(&conf->preread_active_stripes)
> +			    < IO_THRESHOLD)
> +				md_wakeup_thread(conf->mddev->thread);
> +		atomic_dec(&conf->active_stripes);
> +		if (!test_bit(STRIPE_EXPANDING, &sh->state)) {
> +			list_add_tail(&sh->lru, &conf->inactive_list);
> +			wake_up(&conf->wait_for_stripe);
> +			if (conf->retry_read_aligned)
> +				md_wakeup_thread(conf->mddev->thread);
>  		}
>  	}
>  }
>  
> +static void __release_stripe(struct r5conf *conf, struct stripe_head *sh)
> +{
> +	if (atomic_dec_and_test(&sh->count))
> +		handle_release_stripe(conf, sh);
> +}
> +
>  static void release_stripe(struct stripe_head *sh)
>  {
>  	struct r5conf *conf = sh->raid_conf;
>  	unsigned long flags;
>  
> -	spin_lock_irqsave(&conf->device_lock, flags);
> -	__release_stripe(conf, sh);
> -	spin_unlock_irqrestore(&conf->device_lock, flags);
> +	local_irq_save(flags);
> +	if (atomic_dec_and_lock(&sh->count, &conf->device_lock)) {
> +		handle_release_stripe(conf, sh);
> +		spin_unlock(&conf->device_lock);
> +	}
> +	local_irq_restore(flags);
>  }
>  
>  static inline void remove_hash(struct stripe_head *sh)


Thanks.  I've applied this patch and it should appear in my -next shortly.
I renamed "handle_release_stripe" to "do_release_stripe", partly because I
think that is more consistent with practice in Linux, but mostly because
"handle" means something else inside raid5.c and I don't want to encourage
confusion.

Thanks,
NeilBrown

Attachment: signature.asc
Description: PGP signature