Re: [patch 1/8] raid5: add a per-stripe lock

[NeilBrown <neilb@suse.de>]

[-- Attachment #1: Type: text/plain, Size: 5978 bytes --]

On Mon, 04 Jun 2012 16:01:53 +0800 Shaohua Li <shli@kernel.org> wrote:

> Add a per-stripe lock to protect stripe specific data, like dev->read,
> written, ... The purpose is to reduce lock contention of conf->device_lock.

I'm not convinced that you need to add a lock.
I am convinced that if you do add one you need to explain exactly what it is
protecting.

The STRIPE_ACTIVE bit serves as a lock and ensures that only one process can
be in handle_stripe at a time.
So I don't think dev->read actually needs any protection (though I haven't
checked thoroughly).

I think the only things that device_lock protects are things shared by
multiple stripes, so adding a per-stripe spinlock isn't going to help remove
device_lock.

Thanks,
NeilBrown


> 
> Signed-off-by: Shaohua Li <shli@fusionio.com>
> ---
>  drivers/md/raid5.c |   17 +++++++++++++++++
>  drivers/md/raid5.h |    1 +
>  2 files changed, 18 insertions(+)
> 
> Index: linux/drivers/md/raid5.c
> ===================================================================
> --- linux.orig/drivers/md/raid5.c	2012-06-01 13:38:54.705210229 +0800
> +++ linux/drivers/md/raid5.c	2012-06-01 13:43:05.594056130 +0800
> @@ -749,6 +749,7 @@ static void ops_complete_biofill(void *s
>  
>  	/* clear completed biofills */
>  	spin_lock_irq(&conf->device_lock);
> +	spin_lock_irq(&sh->stripe_lock);
>  	for (i = sh->disks; i--; ) {
>  		struct r5dev *dev = &sh->dev[i];
>  
> @@ -774,6 +775,7 @@ static void ops_complete_biofill(void *s
>  			}
>  		}
>  	}
> +	spin_unlock_irq(&sh->stripe_lock);
>  	spin_unlock_irq(&conf->device_lock);
>  	clear_bit(STRIPE_BIOFILL_RUN, &sh->state);
>  
> @@ -798,8 +800,10 @@ static void ops_run_biofill(struct strip
>  		if (test_bit(R5_Wantfill, &dev->flags)) {
>  			struct bio *rbi;
>  			spin_lock_irq(&conf->device_lock);
> +			spin_lock_irq(&sh->stripe_lock);
>  			dev->read = rbi = dev->toread;
>  			dev->toread = NULL;
> +			spin_unlock_irq(&sh->stripe_lock);
>  			spin_unlock_irq(&conf->device_lock);
>  			while (rbi && rbi->bi_sector <
>  				dev->sector + STRIPE_SECTORS) {
> @@ -1137,10 +1141,12 @@ ops_run_biodrain(struct stripe_head *sh,
>  			struct bio *wbi;
>  
>  			spin_lock_irq(&sh->raid_conf->device_lock);
> +			spin_lock_irq(&sh->stripe_lock);
>  			chosen = dev->towrite;
>  			dev->towrite = NULL;
>  			BUG_ON(dev->written);
>  			wbi = dev->written = chosen;
> +			spin_unlock_irq(&sh->stripe_lock);
>  			spin_unlock_irq(&sh->raid_conf->device_lock);
>  
>  			while (wbi && wbi->bi_sector <
> @@ -1446,6 +1452,8 @@ static int grow_one_stripe(struct r5conf
>  	init_waitqueue_head(&sh->ops.wait_for_ops);
>  	#endif
>  
> +	spin_lock_init(&sh->stripe_lock);
> +
>  	if (grow_buffers(sh)) {
>  		shrink_buffers(sh);
>  		kmem_cache_free(conf->slab_cache, sh);
> @@ -2327,6 +2335,7 @@ static int add_stripe_bio(struct stripe_
>  
>  
>  	spin_lock_irq(&conf->device_lock);
> +	spin_lock_irq(&sh->stripe_lock);
>  	if (forwrite) {
>  		bip = &sh->dev[dd_idx].towrite;
>  		if (*bip == NULL && sh->dev[dd_idx].written == NULL)
> @@ -2360,6 +2369,7 @@ static int add_stripe_bio(struct stripe_
>  		if (sector >= sh->dev[dd_idx].sector + STRIPE_SECTORS)
>  			set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags);
>  	}
> +	spin_unlock_irq(&sh->stripe_lock);
>  	spin_unlock_irq(&conf->device_lock);
>  
>  	pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n",
> @@ -2376,6 +2386,7 @@ static int add_stripe_bio(struct stripe_
>  
>   overlap:
>  	set_bit(R5_Overlap, &sh->dev[dd_idx].flags);
> +	spin_unlock_irq(&sh->stripe_lock);
>  	spin_unlock_irq(&conf->device_lock);
>  	return 0;
>  }
> @@ -2427,6 +2438,7 @@ handle_failed_stripe(struct r5conf *conf
>  			}
>  		}
>  		spin_lock_irq(&conf->device_lock);
> +		spin_lock_irq(&sh->stripe_lock);
>  		/* fail all writes first */
>  		bi = sh->dev[i].towrite;
>  		sh->dev[i].towrite = NULL;
> @@ -2488,6 +2500,7 @@ handle_failed_stripe(struct r5conf *conf
>  				bi = nextbi;
>  			}
>  		}
> +		spin_unlock_irq(&sh->stripe_lock);
>  		spin_unlock_irq(&conf->device_lock);
>  		if (bitmap_end)
>  			bitmap_endwrite(conf->mddev->bitmap, sh->sector,
> @@ -2695,6 +2708,7 @@ static void handle_stripe_clean_event(st
>  				int bitmap_end = 0;
>  				pr_debug("Return write for disc %d\n", i);
>  				spin_lock_irq(&conf->device_lock);
> +				spin_lock_irq(&sh->stripe_lock);
>  				wbi = dev->written;
>  				dev->written = NULL;
>  				while (wbi && wbi->bi_sector <
> @@ -2709,6 +2723,7 @@ static void handle_stripe_clean_event(st
>  				}
>  				if (dev->towrite == NULL)
>  					bitmap_end = 1;
> +				spin_unlock_irq(&sh->stripe_lock);
>  				spin_unlock_irq(&conf->device_lock);
>  				if (bitmap_end)
>  					bitmap_endwrite(conf->mddev->bitmap,
> @@ -3168,6 +3183,7 @@ static void analyse_stripe(struct stripe
>  	/* Now to look around and see what can be done */
>  	rcu_read_lock();
>  	spin_lock_irq(&conf->device_lock);
> +	spin_lock_irq(&sh->stripe_lock);
>  	for (i=disks; i--; ) {
>  		struct md_rdev *rdev;
>  		sector_t first_bad;
> @@ -3313,6 +3329,7 @@ static void analyse_stripe(struct stripe
>  				do_recovery = 1;
>  		}
>  	}
> +	spin_unlock_irq(&sh->stripe_lock);
>  	spin_unlock_irq(&conf->device_lock);
>  	if (test_bit(STRIPE_SYNCING, &sh->state)) {
>  		/* If there is a failed device being replaced,
> Index: linux/drivers/md/raid5.h
> ===================================================================
> --- linux.orig/drivers/md/raid5.h	2012-06-01 13:38:54.717210079 +0800
> +++ linux/drivers/md/raid5.h	2012-06-01 13:44:19.229127709 +0800
> @@ -210,6 +210,7 @@ struct stripe_head {
>  	int			disks;		/* disks in stripe */
>  	enum check_states	check_state;
>  	enum reconstruct_states reconstruct_state;
> +	spinlock_t		stripe_lock;
>  	/**
>  	 * struct stripe_operations
>  	 * @target - STRIPE_OP_COMPUTE_BLK target


[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 828 bytes --]