md/raid5-cache: exclude reclaiming stripes in reclaim check

stripes which are being reclaimed are still accounted into cached
stripes. The reclaim takes time. r5c_do_reclaim isn't aware of the
stripes and does unnecessary stripe reclaim. In practice, I saw one
stripe is reclaimed one time. This will cause bad IO pattern. Fixing
this by excluding the reclaing stripes in the check.

Cc: Song Liu <songliubraving@fb.com>
Signed-off-by: Shaohua Li <shli@fb.com>

diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index a01f4da..3f307be 100644 (file)
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -1327,6 +1327,10 @@ static void r5c_flush_stripe(struct r5conf *conf, struct stripe_head *sh)
        atomic_inc(&conf->active_stripes);
        r5c_make_stripe_write_out(sh);
 
+       if (test_bit(STRIPE_R5C_PARTIAL_STRIPE, &sh->state))
+               atomic_inc(&conf->r5c_flushing_partial_stripes);
+       else
+               atomic_inc(&conf->r5c_flushing_full_stripes);
        raid5_release_stripe(sh);
 }
 
@@ -1369,12 +1373,16 @@ static void r5c_do_reclaim(struct r5conf *conf)
        unsigned long flags;
        int total_cached;
        int stripes_to_flush;
+       int flushing_partial, flushing_full;
 
        if (!r5c_is_writeback(log))
                return;
 
+       flushing_partial = atomic_read(&conf->r5c_flushing_partial_stripes);
+       flushing_full = atomic_read(&conf->r5c_flushing_full_stripes);
        total_cached = atomic_read(&conf->r5c_cached_partial_stripes) +
-               atomic_read(&conf->r5c_cached_full_stripes);
+               atomic_read(&conf->r5c_cached_full_stripes) -
+               flushing_full - flushing_partial;
 
        if (total_cached > conf->min_nr_stripes * 3 / 4 ||
            atomic_read(&conf->empty_inactive_list_nr) > 0)
@@ -1384,7 +1392,7 @@ static void r5c_do_reclaim(struct r5conf *conf)
                 */
                stripes_to_flush = R5C_RECLAIM_STRIPE_GROUP;
        else if (total_cached > conf->min_nr_stripes * 1 / 2 ||
-                atomic_read(&conf->r5c_cached_full_stripes) >
+                atomic_read(&conf->r5c_cached_full_stripes) - flushing_full >
                 R5C_FULL_STRIPE_FLUSH_BATCH)
                /*
                 * if stripe cache pressure moderate, or if there is many full
@@ -2601,11 +2609,13 @@ void r5c_finish_stripe_write_out(struct r5conf *conf,
 
        if (test_and_clear_bit(STRIPE_R5C_PARTIAL_STRIPE, &sh->state)) {
                BUG_ON(atomic_read(&conf->r5c_cached_partial_stripes) == 0);
+               atomic_dec(&conf->r5c_flushing_partial_stripes);
                atomic_dec(&conf->r5c_cached_partial_stripes);
        }
 
        if (test_and_clear_bit(STRIPE_R5C_FULL_STRIPE, &sh->state)) {
                BUG_ON(atomic_read(&conf->r5c_cached_full_stripes) == 0);
+               atomic_dec(&conf->r5c_flushing_full_stripes);
                atomic_dec(&conf->r5c_cached_full_stripes);
        }
 }

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index b0d1345..e2fa88f 100644 (file)
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -6838,6 +6838,8 @@ static struct r5conf *setup_conf(struct mddev *mddev)
        INIT_LIST_HEAD(&conf->r5c_full_stripe_list);
        atomic_set(&conf->r5c_cached_partial_stripes, 0);
        INIT_LIST_HEAD(&conf->r5c_partial_stripe_list);
+       atomic_set(&conf->r5c_flushing_full_stripes, 0);
+       atomic_set(&conf->r5c_flushing_partial_stripes, 0);
 
        conf->level = mddev->new_level;
        conf->chunk_sectors = mddev->new_chunk_sectors;

diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index c0687df..4bb27b9 100644 (file)
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -663,6 +663,8 @@ struct r5conf {
        struct list_head        r5c_full_stripe_list;
        atomic_t                r5c_cached_partial_stripes;
        struct list_head        r5c_partial_stripe_list;
+       atomic_t                r5c_flushing_full_stripes;
+       atomic_t                r5c_flushing_partial_stripes;
 
        atomic_t                empty_inactive_list_nr;
        struct llist_head       released_stripes;