raid5: make release_stripe lockless

release_stripe still has big lock contention. We just add the stripe to a llist
without taking device_lock. We let the raid5d thread to do the real stripe
release, which must hold device_lock anyway. In this way, release_stripe
doesn't hold any locks.

The side effect is the released stripes order is changed. But sounds not a big
deal, stripes are never handled in order. And I thought block layer can already
do nice request merge, which means order isn't that important.

I kept the unplug release batch, which is unnecessary with this patch from lock
contention avoid point of view, and actually if we delete it, the stripe_head
release_list and lru can share storage. But the unplug release batch is also
helpful for request merge. We probably can delay wakeup raid5d till unplug, but
I'm still afraid of the case which raid5d is running.

Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 78ea44336e75e06d5769b4a6158f2a1e506214e0..287cc3b30043a61e45af3635a437893dff9e3ccb 100644 (file)
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -239,12 +239,47 @@ static void __release_stripe(struct r5conf *conf, struct stripe_head *sh)
                do_release_stripe(conf, sh);
 }
 
+/* should hold conf->device_lock already */
+static int release_stripe_list(struct r5conf *conf)
+{
+       struct stripe_head *sh;
+       int count = 0;
+       struct llist_node *head;
+
+       head = llist_del_all(&conf->released_stripes);
+       while (head) {
+               sh = llist_entry(head, struct stripe_head, release_list);
+               head = llist_next(head);
+               /* sh could be readded after STRIPE_ON_RELEASE_LIST is cleard */
+               smp_mb();
+               clear_bit(STRIPE_ON_RELEASE_LIST, &sh->state);
+               /*
+                * Don't worry the bit is set here, because if the bit is set
+                * again, the count is always > 1. This is true for
+                * STRIPE_ON_UNPLUG_LIST bit too.
+                */
+               __release_stripe(conf, sh);
+               count++;
+       }
+
+       return count;
+}
+
 static void release_stripe(struct stripe_head *sh)
 {
        struct r5conf *conf = sh->raid_conf;
        unsigned long flags;
+       bool wakeup;
 
+       if (test_and_set_bit(STRIPE_ON_RELEASE_LIST, &sh->state))
+               goto slow_path;
+       wakeup = llist_add(&sh->release_list, &conf->released_stripes);
+       if (wakeup)
+               md_wakeup_thread(conf->mddev->thread);
+       return;
+slow_path:
        local_irq_save(flags);
+       /* we are ok here if STRIPE_ON_RELEASE_LIST is set or not */
        if (atomic_dec_and_lock(&sh->count, &conf->device_lock)) {
                do_release_stripe(conf, sh);
                spin_unlock(&conf->device_lock);
@@ -491,7 +526,8 @@ get_active_stripe(struct r5conf *conf, sector_t sector,
                        if (atomic_read(&sh->count)) {
                                BUG_ON(!list_empty(&sh->lru)
                                    && !test_bit(STRIPE_EXPANDING, &sh->state)
-                                   && !test_bit(STRIPE_ON_UNPLUG_LIST, &sh->state));
+                                   && !test_bit(STRIPE_ON_UNPLUG_LIST, &sh->state)
+                                   && !test_bit(STRIPE_ON_RELEASE_LIST, &sh->state));
                        } else {
                                if (!test_bit(STRIPE_HANDLE, &sh->state))
                                        atomic_inc(&conf->active_stripes);
@@ -4127,6 +4163,10 @@ static void raid5_unplug(struct blk_plug_cb *blk_cb, bool from_schedule)
                         */
                        smp_mb__before_clear_bit();
                        clear_bit(STRIPE_ON_UNPLUG_LIST, &sh->state);
+                       /*
+                        * STRIPE_ON_RELEASE_LIST could be set here. In that
+                        * case, the count is always > 1 here
+                        */
                        __release_stripe(conf, sh);
                        cnt++;
                }
@@ -4836,7 +4876,9 @@ static void raid5d(struct md_thread *thread)
        spin_lock_irq(&conf->device_lock);
        while (1) {
                struct bio *bio;
-               int batch_size;
+               int batch_size, released;
+
+               released = release_stripe_list(conf);
 
                if (
                    !list_empty(&conf->bitmap_list)) {
@@ -4861,7 +4903,7 @@ static void raid5d(struct md_thread *thread)
                }
 
                batch_size = handle_active_stripes(conf);
-               if (!batch_size)
+               if (!batch_size && !released)
                        break;
                handled += batch_size;
 
@@ -5176,6 +5218,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
        INIT_LIST_HEAD(&conf->delayed_list);
        INIT_LIST_HEAD(&conf->bitmap_list);
        INIT_LIST_HEAD(&conf->inactive_list);
+       init_llist_head(&conf->released_stripes);
        atomic_set(&conf->active_stripes, 0);
        atomic_set(&conf->preread_active_stripes, 0);
        atomic_set(&conf->active_aligned_reads, 0);

diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 70c49329ca9a23fbbad73061477ac0a0cfe80e6e..a98f99d2a58f52a8eabc62872cb04ef3fede9c51 100644 (file)
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -197,6 +197,7 @@ enum reconstruct_states {
 struct stripe_head {
        struct hlist_node       hash;
        struct list_head        lru;          /* inactive_list or handle_list */
+       struct llist_node       release_list;
        struct r5conf           *raid_conf;
        short                   generation;     /* increments with every
                                                 * reshape */
@@ -321,6 +322,7 @@ enum {
        STRIPE_OPS_REQ_PENDING,
        STRIPE_ON_UNPLUG_LIST,
        STRIPE_DISCARD,
+       STRIPE_ON_RELEASE_LIST,
 };
 
 /*
@@ -445,6 +447,7 @@ struct r5conf {
         */
        atomic_t                active_stripes;
        struct list_head        inactive_list;
+       struct llist_head       released_stripes;
        wait_queue_head_t       wait_for_stripe;
        wait_queue_head_t       wait_for_overlap;
        int                     inactive_blocked;       /* release of inactive stripes blocked,