linux-raid.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Namhyung Kim <namhyung@gmail.com>
To: NeilBrown <neilb@suse.de>
Cc: linux-raid@vger.kernel.org
Subject: Re: [md PATCH 08/34] md/raid5: replace sh->lock with an 'active' flag.
Date: Fri, 22 Jul 2011 13:27:36 +0900	[thread overview]
Message-ID: <87hb6fdjnr.fsf@gmail.com> (raw)
In-Reply-To: <20110721023225.6728.96772.stgit@notabene.brown> (NeilBrown's message of "Thu, 21 Jul 2011 12:32:25 +1000")

NeilBrown <neilb@suse.de> writes:

> sh->lock is now mainly used to ensure that two threads aren't running
> in the locked part of handle_stripe[56] at the same time.
>
> That can more neatly be achieved with an 'active' flag which we set
> while running handle_stripe.  If we find the flag is set, we simply
> requeue the stripe for later by setting STRIPE_HANDLE.
>
> For safety we take ->device_lock while examining the state of the
> stripe and creating a summary in 'stripe_head_state / r6_state'.
> This possibly isn't needed but as shared fields like ->toread,
> ->towrite are checked it is safer for now at least.
>
> We leave the label after the old 'unlock' called "unlock" because it
> will disappear in a few patches, so renaming seems pointless.
>
> This leaves the stripe 'locked' for longer as we clear STRIPE_ACTIVE
> later, but that is not a problem.
>
> Signed-off-by: NeilBrown <neilb@suse.de>

Reviewed-by: Namhyung Kim <namhyung@gmail.com>

But I have a question, please see below.


> ---
>
>  drivers/md/raid5.c |   26 +++++++++++++-------------
>  drivers/md/raid5.h |    2 +-
>  2 files changed, 14 insertions(+), 14 deletions(-)
>
> diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
> index 9985138..f8275b5 100644
> --- a/drivers/md/raid5.c
> +++ b/drivers/md/raid5.c
> @@ -1020,14 +1020,12 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
>  		if (test_and_clear_bit(R5_Wantdrain, &dev->flags)) {
>  			struct bio *wbi;
>  
> -			spin_lock(&sh->lock);
>  			spin_lock_irq(&sh->raid_conf->device_lock);
>  			chosen = dev->towrite;
>  			dev->towrite = NULL;
>  			BUG_ON(dev->written);
>  			wbi = dev->written = chosen;
>  			spin_unlock_irq(&sh->raid_conf->device_lock);
> -			spin_unlock(&sh->lock);
>  
>  			while (wbi && wbi->bi_sector <
>  				dev->sector + STRIPE_SECTORS) {
> @@ -1322,7 +1320,6 @@ static int grow_one_stripe(raid5_conf_t *conf)
>  		return 0;
>  
>  	sh->raid_conf = conf;
> -	spin_lock_init(&sh->lock);
>  	#ifdef CONFIG_MULTICORE_RAID456
>  	init_waitqueue_head(&sh->ops.wait_for_ops);
>  	#endif
> @@ -1442,7 +1439,6 @@ static int resize_stripes(raid5_conf_t *conf, int newsize)
>  			break;
>  
>  		nsh->raid_conf = conf;
> -		spin_lock_init(&nsh->lock);
>  		#ifdef CONFIG_MULTICORE_RAID456
>  		init_waitqueue_head(&nsh->ops.wait_for_ops);
>  		#endif
> @@ -2148,7 +2144,6 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
>  		(unsigned long long)sh->sector);
>  
>  
> -	spin_lock(&sh->lock);
>  	spin_lock_irq(&conf->device_lock);
>  	if (forwrite) {
>  		bip = &sh->dev[dd_idx].towrite;
> @@ -2184,7 +2179,6 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
>  			set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags);
>  	}
>  	spin_unlock_irq(&conf->device_lock);
> -	spin_unlock(&sh->lock);
>  
>  	pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n",
>  		(unsigned long long)(*bip)->bi_sector,
> @@ -2201,7 +2195,6 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in
>   overlap:
>  	set_bit(R5_Overlap, &sh->dev[dd_idx].flags);
>  	spin_unlock_irq(&conf->device_lock);
> -	spin_unlock(&sh->lock);
>  	return 0;
>  }
>  
> @@ -3023,12 +3016,10 @@ static void handle_stripe5(struct stripe_head *sh)
>  		 atomic_read(&sh->count), sh->pd_idx, sh->check_state,
>  		 sh->reconstruct_state);
>  
> -	spin_lock(&sh->lock);
>  	if (test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) {
>  		set_bit(STRIPE_SYNCING, &sh->state);
>  		clear_bit(STRIPE_INSYNC, &sh->state);
>  	}
> -	clear_bit(STRIPE_HANDLE, &sh->state);
>  	clear_bit(STRIPE_DELAYED, &sh->state);
>  
>  	s.syncing = test_bit(STRIPE_SYNCING, &sh->state);
> @@ -3037,6 +3028,7 @@ static void handle_stripe5(struct stripe_head *sh)
>  
>  	/* Now to look around and see what can be done */
>  	rcu_read_lock();
> +	spin_lock_irq(&conf->device_lock);

Do we still need rcu_read_lock()? AFAIK rcu_read_lock() only prevents
task from preemption but spin_lock does same thing as well.

I know it's been already there under sh->lock before this patch, and
it doesn't hurt anything, but I'm not sure it is really needed.


>  	for (i=disks; i--; ) {
>  		mdk_rdev_t *rdev;
>  
> @@ -3099,6 +3091,7 @@ static void handle_stripe5(struct stripe_head *sh)
>  			s.failed_num = i;
>  		}
>  	}
> +	spin_unlock_irq(&conf->device_lock);
>  	rcu_read_unlock();
>  
>  	if (unlikely(blocked_rdev)) {
> @@ -3275,7 +3268,6 @@ static void handle_stripe5(struct stripe_head *sh)
>  		handle_stripe_expansion(conf, sh, NULL);
>  
>   unlock:
> -	spin_unlock(&sh->lock);
>  
>  	/* wait for this device to become unblocked */
>  	if (unlikely(blocked_rdev))
> @@ -3318,12 +3310,10 @@ static void handle_stripe6(struct stripe_head *sh)
>  	       sh->check_state, sh->reconstruct_state);
>  	memset(&s, 0, sizeof(s));
>  
> -	spin_lock(&sh->lock);
>  	if (test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) {
>  		set_bit(STRIPE_SYNCING, &sh->state);
>  		clear_bit(STRIPE_INSYNC, &sh->state);
>  	}
> -	clear_bit(STRIPE_HANDLE, &sh->state);
>  	clear_bit(STRIPE_DELAYED, &sh->state);
>  
>  	s.syncing = test_bit(STRIPE_SYNCING, &sh->state);
> @@ -3332,6 +3322,7 @@ static void handle_stripe6(struct stripe_head *sh)
>  	/* Now to look around and see what can be done */
>  
>  	rcu_read_lock();
> +	spin_lock_irq(&conf->device_lock);

Same here.


>  	for (i=disks; i--; ) {
>  		mdk_rdev_t *rdev;
>  		dev = &sh->dev[i];
> @@ -3395,6 +3386,7 @@ static void handle_stripe6(struct stripe_head *sh)
>  			s.failed++;
>  		}
>  	}
> +	spin_unlock_irq(&conf->device_lock);
>  	rcu_read_unlock();
>  
>  	if (unlikely(blocked_rdev)) {
> @@ -3580,7 +3572,6 @@ static void handle_stripe6(struct stripe_head *sh)
>  		handle_stripe_expansion(conf, sh, &r6s);
>  
>   unlock:
> -	spin_unlock(&sh->lock);
>  
>  	/* wait for this device to become unblocked */
>  	if (unlikely(blocked_rdev))
> @@ -3608,10 +3599,19 @@ static void handle_stripe6(struct stripe_head *sh)
>  
>  static void handle_stripe(struct stripe_head *sh)
>  {
> +	clear_bit(STRIPE_HANDLE, &sh->state);
> +	if (test_and_set_bit(STRIPE_ACTIVE, &sh->state)) {
> +		/* already being handled, ensure it gets handled
> +		 * again when current action finishes */
> +		set_bit(STRIPE_HANDLE, &sh->state);
> +		return;
> +	}
> +
>  	if (sh->raid_conf->level == 6)
>  		handle_stripe6(sh);
>  	else
>  		handle_stripe5(sh);
> +	clear_bit(STRIPE_ACTIVE, &sh->state);
>  }
>  
>  static void raid5_activate_delayed(raid5_conf_t *conf)
> diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
> index a330011..217a9d4 100644
> --- a/drivers/md/raid5.h
> +++ b/drivers/md/raid5.h
> @@ -209,7 +209,6 @@ struct stripe_head {
>  	short			ddf_layout;/* use DDF ordering to calculate Q */
>  	unsigned long		state;		/* state flags */
>  	atomic_t		count;	      /* nr of active thread/requests */
> -	spinlock_t		lock;
>  	int			bm_seq;	/* sequence number for bitmap flushes */
>  	int			disks;		/* disks in stripe */
>  	enum check_states	check_state;
> @@ -290,6 +289,7 @@ struct r6_state {
>   * Stripe state
>   */
>  enum {
> +	STRIPE_ACTIVE,
>  	STRIPE_HANDLE,
>  	STRIPE_SYNC_REQUESTED,
>  	STRIPE_SYNCING,
>
>
> --
> 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

  reply	other threads:[~2011-07-22  4:27 UTC|newest]

Thread overview: 71+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-07-21  2:32 [md PATCH 00/34] md patches for 3.1 - part 1 NeilBrown
2011-07-21  2:32 ` [md PATCH 03/34] md/raid10: share pages between read and write bio's during recovery NeilBrown
2011-07-21  2:32 ` [md PATCH 01/34] md/raid10: get rid of duplicated conditional expression NeilBrown
2011-07-21  2:32 ` [md PATCH 02/34] md/raid10: factor out common bio handling code NeilBrown
2011-07-21  2:32 ` [md PATCH 10/34] md/raid5: unify stripe_head_state and r6_state NeilBrown
2011-07-22  4:49   ` Namhyung Kim
2011-07-22  5:15     ` NeilBrown
2011-07-22  5:37       ` NeilBrown
2011-07-22  5:53         ` Namhyung Kim
2011-07-26  6:44           ` Namhyung Kim
2011-07-21  2:32 ` [md PATCH 09/34] md/raid5: move common code into handle_stripe NeilBrown
2011-07-22  4:30   ` Namhyung Kim
2011-07-21  2:32 ` [md PATCH 05/34] md/raid5: get rid of duplicated call to bio_data_dir() NeilBrown
2011-07-21  2:32 ` [md PATCH 07/34] md/raid5: Protect some more code with ->device_lock NeilBrown
2011-07-22  3:54   ` Namhyung Kim
2011-07-21  2:32 ` [md PATCH 08/34] md/raid5: replace sh->lock with an 'active' flag NeilBrown
2011-07-22  4:27   ` Namhyung Kim [this message]
2011-07-22  4:49     ` NeilBrown
2011-07-22  5:03       ` Namhyung Kim
2011-08-03 22:47   ` Dan Williams
2011-08-03 23:35     ` NeilBrown
2011-08-03 23:45       ` Williams, Dan J
2011-08-04  0:18         ` NeilBrown
2011-07-21  2:32 ` [md PATCH 04/34] md/raid5: use kmem_cache_zalloc() NeilBrown
2011-07-21  2:32 ` [md PATCH 11/34] md/raid5: add some more fields to stripe_head_state NeilBrown
2011-07-22  5:31   ` Namhyung Kim
2011-07-26  1:35     ` NeilBrown
2011-07-21  2:32 ` [md PATCH 06/34] md/raid5: Remove use of sh->lock in sync_request NeilBrown
2011-07-22  3:39   ` Namhyung Kim
2011-07-21  2:32 ` [md PATCH 19/34] md/raid5: move some more common code into handle_stripe NeilBrown
2011-07-22  9:29   ` Namhyung Kim
2011-07-26  1:59     ` NeilBrown
2011-07-21  2:32 ` [md PATCH 13/34] md/raid5: Move code for finishing a reconstruction " NeilBrown
2011-07-22  7:09   ` Namhyung Kim
2011-07-26  1:44     ` NeilBrown
2011-07-21  2:32 ` [md PATCH 18/34] md/raid5: move more common code " NeilBrown
2011-07-22  9:20   ` Namhyung Kim
2011-07-21  2:32 ` [md PATCH 17/34] md/raid5: unite handle_stripe_dirtying5 and handle_stripe_dirtying6 NeilBrown
2011-07-22  9:10   ` Namhyung Kim
2011-07-26  1:52     ` NeilBrown
2011-07-26  2:41       ` H. Peter Anvin
2011-07-26  9:40       ` David Brown
2011-07-26 13:23         ` Namhyung Kim
2011-07-26 15:01           ` David Brown
2011-07-21  2:32 ` [md PATCH 12/34] md/raid5: move stripe_head_state and more code into handle_stripe NeilBrown
2011-07-22  5:41   ` Namhyung Kim
2011-07-21  2:32 ` [md PATCH 16/34] md/raid5: unite fetch_block5 and fetch_block6 NeilBrown
2011-07-22  8:24   ` Namhyung Kim
2011-07-21  2:32 ` [md PATCH 14/34] md/raid5: move more code into common handle_stripe NeilBrown
2011-07-22  7:32   ` Namhyung Kim
2011-07-26  1:48     ` NeilBrown
2011-07-21  2:32 ` [md PATCH 15/34] md/raid5: rearrange a test in fetch_block6 NeilBrown
2011-07-22  7:37   ` Namhyung Kim
2011-07-21  2:32 ` [md PATCH 24/34] md: remove ro check in md_check_recovery() NeilBrown
2011-07-21  2:32 ` [md PATCH 22/34] md/raid: use printk_ratelimited instead of printk_ratelimit NeilBrown
2011-07-21  2:32 ` [md PATCH 25/34] md: change managed of recovery_disabled NeilBrown
2011-07-21  2:32 ` [md PATCH 20/34] md/raid5: finalise new merged handle_stripe NeilBrown
2011-07-22  9:36   ` Namhyung Kim
2011-07-26  2:02     ` NeilBrown
2011-07-26  4:50       ` Namhyung Kim
2011-07-21  2:32 ` [md PATCH 26/34] md/raid10: Make use of new recovery_disabled handling NeilBrown
2011-07-21  2:32 ` [md PATCH 27/34] md/raid10: Improve decision on whether to fail a device with a read error NeilBrown
2011-07-21  2:32 ` [md PATCH 21/34] md: use proper little-endian bitops NeilBrown
2011-07-21  2:32 ` [md PATCH 23/34] md: introduce link/unlink_rdev() helpers NeilBrown
2011-07-21  2:32 ` [md PATCH 31/34] md/raid10: move rdev->corrected_errors counting NeilBrown
2011-07-21  2:32 ` [md PATCH 34/34] MD bitmap: Revert DM dirty log hooks NeilBrown
2011-07-21  2:32 ` [md PATCH 32/34] md/raid5: Avoid BUG caused by multiple failures NeilBrown
2011-07-21  2:32 ` [md PATCH 33/34] MD: raid1 s/sysfs_notify_dirent/sysfs_notify_dirent_safe NeilBrown
2011-07-21  2:32 ` [md PATCH 29/34] md/raid1: move rdev->corrected_errors counting NeilBrown
2011-07-21  2:32 ` [md PATCH 28/34] md: get rid of unnecessary casts on page_address() NeilBrown
2011-07-21  2:32 ` [md PATCH 30/34] md/raid5: move rdev->corrected_errors counting NeilBrown

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=87hb6fdjnr.fsf@gmail.com \
    --to=namhyung@gmail.com \
    --cc=linux-raid@vger.kernel.org \
    --cc=neilb@suse.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).