linux-raid.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Shaohua Li <shli@kernel.org>
To: linux-raid@vger.kernel.org
Cc: neilb@suse.de, axboe@kernel.dk, dan.j.williams@intel.com,
	shli@fusionio.com
Subject: [patch 03/10 v3] raid5: add a per-stripe lock
Date: Mon, 25 Jun 2012 15:24:50 +0800	[thread overview]
Message-ID: <20120625072613.620625574@kernel.org> (raw)
In-Reply-To: 20120625072447.268095276@kernel.org

[-- Attachment #1: raid5-add-perstripe-lock.patch --]
[-- Type: text/plain, Size: 4862 bytes --]

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.

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	2012-06-25 14:36:57.280096788 +0800
+++ linux/drivers/md/raid5.c	2012-06-25 14:37:13.651888057 +0800
@@ -751,6 +751,7 @@ static void ops_complete_biofill(void *s
 
 	/* clear completed biofills */
 	spin_lock_irq(&conf->device_lock);
+	spin_lock(&sh->stripe_lock);
 	for (i = sh->disks; i--; ) {
 		struct r5dev *dev = &sh->dev[i];
 
@@ -776,6 +777,7 @@ static void ops_complete_biofill(void *s
 			}
 		}
 	}
+	spin_unlock(&sh->stripe_lock);
 	spin_unlock_irq(&conf->device_lock);
 	clear_bit(STRIPE_BIOFILL_RUN, &sh->state);
 
@@ -800,8 +802,10 @@ 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(&sh->stripe_lock);
 			dev->read = rbi = dev->toread;
 			dev->toread = NULL;
+			spin_unlock(&sh->stripe_lock);
 			spin_unlock_irq(&conf->device_lock);
 			while (rbi && rbi->bi_sector <
 				dev->sector + STRIPE_SECTORS) {
@@ -1139,10 +1143,12 @@ ops_run_biodrain(struct stripe_head *sh,
 			struct bio *wbi;
 
 			spin_lock_irq(&sh->raid_conf->device_lock);
+			spin_lock(&sh->stripe_lock);
 			chosen = dev->towrite;
 			dev->towrite = NULL;
 			BUG_ON(dev->written);
 			wbi = dev->written = chosen;
+			spin_unlock(&sh->stripe_lock);
 			spin_unlock_irq(&sh->raid_conf->device_lock);
 
 			while (wbi && wbi->bi_sector <
@@ -1448,6 +1454,8 @@ 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);
@@ -2329,6 +2337,7 @@ static int add_stripe_bio(struct stripe_
 
 
 	spin_lock_irq(&conf->device_lock);
+	spin_lock(&sh->stripe_lock);
 	if (forwrite) {
 		bip = &sh->dev[dd_idx].towrite;
 		if (*bip == NULL && sh->dev[dd_idx].written == NULL)
@@ -2362,6 +2371,7 @@ 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(&sh->stripe_lock);
 	spin_unlock_irq(&conf->device_lock);
 
 	pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n",
@@ -2378,6 +2388,7 @@ static int add_stripe_bio(struct stripe_
 
  overlap:
 	set_bit(R5_Overlap, &sh->dev[dd_idx].flags);
+	spin_unlock(&sh->stripe_lock);
 	spin_unlock_irq(&conf->device_lock);
 	return 0;
 }
@@ -2429,6 +2440,7 @@ handle_failed_stripe(struct r5conf *conf
 			}
 		}
 		spin_lock_irq(&conf->device_lock);
+		spin_lock(&sh->stripe_lock);
 		/* fail all writes first */
 		bi = sh->dev[i].towrite;
 		sh->dev[i].towrite = NULL;
@@ -2490,6 +2502,7 @@ handle_failed_stripe(struct r5conf *conf
 				bi = nextbi;
 			}
 		}
+		spin_unlock(&sh->stripe_lock);
 		spin_unlock_irq(&conf->device_lock);
 		if (bitmap_end)
 			bitmap_endwrite(conf->mddev->bitmap, sh->sector,
@@ -2697,6 +2710,7 @@ 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(&sh->stripe_lock);
 				wbi = dev->written;
 				dev->written = NULL;
 				while (wbi && wbi->bi_sector <
@@ -2711,6 +2725,7 @@ static void handle_stripe_clean_event(st
 				}
 				if (dev->towrite == NULL)
 					bitmap_end = 1;
+				spin_unlock(&sh->stripe_lock);
 				spin_unlock_irq(&conf->device_lock);
 				if (bitmap_end)
 					bitmap_endwrite(conf->mddev->bitmap,
@@ -3170,6 +3185,7 @@ 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(&sh->stripe_lock);
 	for (i=disks; i--; ) {
 		struct md_rdev *rdev;
 		sector_t first_bad;
@@ -3315,6 +3331,7 @@ static void analyse_stripe(struct stripe
 				do_recovery = 1;
 		}
 	}
+	spin_unlock(&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	2012-06-25 14:36:13.940638627 +0800
+++ linux/drivers/md/raid5.h	2012-06-25 14:37:13.651888057 +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


  parent reply	other threads:[~2012-06-25  7:24 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-06-25  7:24 [patch 00/10 v3] raid5: improve write performance for fast storage Shaohua Li
2012-06-25  7:24 ` [patch 01/10 v3] raid5: use wake_up_all for overlap waking Shaohua Li
2012-06-28  7:26   ` NeilBrown
2012-06-28  8:53     ` Shaohua Li
2012-06-25  7:24 ` [patch 02/10 v3] raid5: delayed stripe fix Shaohua Li
2012-07-02  0:46   ` NeilBrown
2012-07-02  0:49     ` Shaohua Li
2012-07-02  0:55       ` NeilBrown
2012-06-25  7:24 ` Shaohua Li [this message]
2012-07-02  0:50   ` [patch 03/10 v3] raid5: add a per-stripe lock NeilBrown
2012-07-02  3:16     ` Shaohua Li
2012-07-02  7:39       ` NeilBrown
2012-07-03  1:27         ` Shaohua Li
2012-07-03 12:16         ` majianpeng
2012-07-03 23:56           ` NeilBrown
2012-07-04  1:09             ` majianpeng
2012-06-25  7:24 ` [patch 04/10 v3] raid5: lockless access raid5 overrided bi_phys_segments Shaohua Li
2012-06-25  7:24 ` [patch 05/10 v3] raid5: remove some device_lock locking places Shaohua Li
2012-06-25  7:24 ` [patch 06/10 v3] raid5: reduce chance release_stripe() taking device_lock Shaohua Li
2012-07-02  0:57   ` NeilBrown
2012-06-25  7:24 ` [patch 07/10 v3] md: personality can provide unplug private data Shaohua Li
2012-07-02  1:06   ` NeilBrown
2012-06-25  7:24 ` [patch 08/10 v3] raid5: make_request use batch stripe release Shaohua Li
2012-07-02  2:31   ` NeilBrown
2012-07-02  2:59     ` Shaohua Li
2012-07-02  5:07       ` NeilBrown
2012-06-25  7:24 ` [patch 09/10 v3] raid5: raid5d handle stripe in batch way Shaohua Li
2012-07-02  2:32   ` NeilBrown
2012-06-25  7:24 ` [patch 10/10 v3] raid5: create multiple threads to handle stripes Shaohua Li
2012-07-02  2:39   ` NeilBrown
2012-07-02 20:03   ` Dan Williams
2012-07-03  8:04     ` Shaohua Li

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=20120625072613.620625574@kernel.org \
    --to=shli@kernel.org \
    --cc=axboe@kernel.dk \
    --cc=dan.j.williams@intel.com \
    --cc=linux-raid@vger.kernel.org \
    --cc=neilb@suse.de \
    --cc=shli@fusionio.com \
    /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).