xfs: bound maximum wait time for inodegc work

Currently inodegc work can sit queued on the per-cpu queue until
the workqueue is either flushed of the queue reaches a depth that
triggers work queuing (and later throttling). This means that we
could queue work that waits for a long time for some other event to
trigger flushing.

Hence instead of just queueing work at a specific depth, use a
delayed work that queues the work at a bound time. We can still
schedule the work immediately at a given depth, but we no long need
to worry about leaving a number of items on the list that won't get
processed until external events prevail.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>

diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 5269354..7867022 100644 (file)
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -440,7 +440,7 @@ xfs_inodegc_queue_all(
        for_each_online_cpu(cpu) {
                gc = per_cpu_ptr(mp->m_inodegc, cpu);
                if (!llist_empty(&gc->list))
-                       queue_work_on(cpu, mp->m_inodegc_wq, &gc->work);
+                       mod_delayed_work_on(cpu, mp->m_inodegc_wq, &gc->work, 0);
        }
 }
 
@@ -1841,8 +1841,8 @@ void
 xfs_inodegc_worker(
        struct work_struct      *work)
 {
-       struct xfs_inodegc      *gc = container_of(work, struct xfs_inodegc,
-                                                       work);
+       struct xfs_inodegc      *gc = container_of(to_delayed_work(work),
+                                               struct xfs_inodegc, work);
        struct llist_node       *node = llist_del_all(&gc->list);
        struct xfs_inode        *ip, *n;
 
@@ -2014,6 +2014,7 @@ xfs_inodegc_queue(
        struct xfs_inodegc      *gc;
        int                     items;
        unsigned int            shrinker_hits;
+       unsigned long           queue_delay = 1;
 
        trace_xfs_inode_set_need_inactive(ip);
        spin_lock(&ip->i_flags_lock);
@@ -2025,19 +2026,26 @@ xfs_inodegc_queue(
        items = READ_ONCE(gc->items);
        WRITE_ONCE(gc->items, items + 1);
        shrinker_hits = READ_ONCE(gc->shrinker_hits);
-       put_cpu_ptr(gc);
 
-       if (!xfs_is_inodegc_enabled(mp))
+       /*
+        * We queue the work while holding the current CPU so that the work
+        * is scheduled to run on this CPU.
+        */
+       if (!xfs_is_inodegc_enabled(mp)) {
+               put_cpu_ptr(gc);
                return;
-
-       if (xfs_inodegc_want_queue_work(ip, items)) {
-               trace_xfs_inodegc_queue(mp, __return_address);
-               queue_work(mp->m_inodegc_wq, &gc->work);
        }
 
+       if (xfs_inodegc_want_queue_work(ip, items))
+               queue_delay = 0;
+
+       trace_xfs_inodegc_queue(mp, __return_address);
+       mod_delayed_work(mp->m_inodegc_wq, &gc->work, queue_delay);
+       put_cpu_ptr(gc);
+
        if (xfs_inodegc_want_flush_work(ip, items, shrinker_hits)) {
                trace_xfs_inodegc_throttle(mp, __return_address);
-               flush_work(&gc->work);
+               flush_delayed_work(&gc->work);
        }
 }
 
@@ -2054,7 +2062,7 @@ xfs_inodegc_cpu_dead(
        unsigned int            count = 0;
 
        dead_gc = per_cpu_ptr(mp->m_inodegc, dead_cpu);
-       cancel_work_sync(&dead_gc->work);
+       cancel_delayed_work_sync(&dead_gc->work);
 
        if (llist_empty(&dead_gc->list))
                return;
@@ -2073,12 +2081,12 @@ xfs_inodegc_cpu_dead(
        llist_add_batch(first, last, &gc->list);
        count += READ_ONCE(gc->items);
        WRITE_ONCE(gc->items, count);
-       put_cpu_ptr(gc);
 
        if (xfs_is_inodegc_enabled(mp)) {
                trace_xfs_inodegc_queue(mp, __return_address);
-               queue_work(mp->m_inodegc_wq, &gc->work);
+               mod_delayed_work(mp->m_inodegc_wq, &gc->work, 0);
        }
+       put_cpu_ptr(gc);
 }
 
 /*
@@ -2173,7 +2181,7 @@ xfs_inodegc_shrinker_scan(
                        unsigned int    h = READ_ONCE(gc->shrinker_hits);
 
                        WRITE_ONCE(gc->shrinker_hits, h + 1);
-                       queue_work_on(cpu, mp->m_inodegc_wq, &gc->work);
+                       mod_delayed_work_on(cpu, mp->m_inodegc_wq, &gc->work, 0);
                        no_items = false;
                }
        }

diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index ba5d42a..d2eaebd 100644 (file)
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -61,7 +61,7 @@ struct xfs_error_cfg {
  */
 struct xfs_inodegc {
        struct llist_head       list;
-       struct work_struct      work;
+       struct delayed_work     work;
 
        /* approximate count of inodes in the list */
        unsigned int            items;

diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index ed18160..90d9c41 100644 (file)
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1074,7 +1074,7 @@ xfs_inodegc_init_percpu(
                gc = per_cpu_ptr(mp->m_inodegc, cpu);
                init_llist_head(&gc->list);
                gc->items = 0;
-               INIT_WORK(&gc->work, xfs_inodegc_worker);
+               INIT_DELAYED_WORK(&gc->work, xfs_inodegc_worker);
        }
        return 0;
 }