From: Artem Bityutskiy <Artem.Bityutskiy@xxxxxxxxx>
This patch simplifies bdi code a little by removing the 'pending_list'
which is redundant. Indeed, currently the forker thread
('bdi_forker_thread()') is working like this:
1. In a loop, fetch all bdi's which have works but have no writeback
thread and move them to the 'pending_list'.
2. If the list is empty, sleep for 5 s.
3. Otherwise, take one BDI from the list, fork the writeback thread for
this bdi, and repeat the loop again.
IOW, it first moves everything to the 'pending_list', then process only
one element, and so on. With this patch the algorithm is:
1. Find the first bdi which has work and remove it from the global
list of bdi's (bdi_list).
2. If there were not such bdi, sleep 5 s.
3. Fork the writeback thread for this bdi and repeat the loop again.
IOW, now we find the first bdi to process, process it, and so on. This
is simpler and involves less lists.
This patch also removes unneeded and unused complications which involve
'rcu_call()' and 'bdi->rcu_head' - now we use simple 'synchronize_rcu()'
and remove the 'rcu_head' field from 'struct backing_dev_info'.
Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@xxxxxxxxx>
---
include/linux/backing-dev.h | 1 -
mm/backing-dev.c | 85 ++++++++++++-------------------------------
2 files changed, 23 insertions(+), 63 deletions(-)
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 14648b9..a9f35c6 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -58,7 +58,6 @@ struct bdi_writeback {
struct backing_dev_info {
struct list_head bdi_list;
- struct rcu_head rcu_head;
unsigned long ra_pages; /* max readahead in PAGE_CACHE_SIZE units */
unsigned long state; /* Always use atomic bitops on this */
unsigned int capabilities; /* Device capabilities */
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 2df2af6..0a69066 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -50,8 +50,6 @@ static struct timer_list sync_supers_timer;
static int bdi_sync_supers(void *);
static void sync_supers_timer_fn(unsigned long);
-static void bdi_add_default_flusher_thread(struct backing_dev_info *bdi);
-
#ifdef CONFIG_DEBUG_FS
#include <linux/debugfs.h>
#include <linux/seq_file.h>
@@ -331,6 +329,7 @@ static int bdi_forker_thread(void *ptr)
set_user_nice(current, 0);
for (;;) {
+ bool no_work = 1;
struct backing_dev_info *bdi, *tmp;
struct bdi_writeback *wb;
@@ -353,13 +352,26 @@ static int bdi_forker_thread(void *ptr)
if (list_empty(&bdi->work_list) &&
!bdi_has_dirty_io(bdi))
continue;
+ if (!bdi_cap_writeback_dirty(bdi))
+ continue;
+
+ WARN(!test_bit(BDI_registered, &bdi->state),
+ "bdi %p/%s is not registered!\n", bdi, bdi->name);
+
+ list_del_rcu(&bdi->bdi_list);
- bdi_add_default_flusher_thread(bdi);
+ /*
+ * Set the pending bit - if someone will try to
+ * unregister this bdi - it'll wait on this bit.
+ */
+ set_bit(BDI_pending, &bdi->state);
+ no_work = 0;
+ break;
}
set_current_state(TASK_INTERRUPTIBLE);
- if (list_empty(&bdi_pending_list)) {
+ if (no_work) {
unsigned long wait;
spin_unlock_bh(&bdi_lock);
@@ -373,24 +385,18 @@ static int bdi_forker_thread(void *ptr)
}
__set_current_state(TASK_RUNNING);
-
- /*
- * This is our real job - check for pending entries in
- * bdi_pending_list, and create the threads that got added
- */
- bdi = list_entry(bdi_pending_list.next, struct backing_dev_info,
- bdi_list);
- list_del_init(&bdi->bdi_list);
spin_unlock_bh(&bdi_lock);
+ /* Make sure no one uses the picked bdi */
+ synchronize_rcu();
+
wb = &bdi->wb;
wb->thread = kthread_run(bdi_writeback_thread, wb, "flush-%s",
dev_name(bdi->dev));
/*
- * If thread creation fails, then readd the bdi to
- * the pending list and force writeout of the bdi
- * from this forker thread. That will free some memory
- * and we can try again.
+ * If thread creation fails, then readd the bdi back to the
+ * list and force writeout of the bdi from this forker thread.
+ * That will free some memory and we can try again.
*/
if (IS_ERR(wb->thread)) {
wb->thread = NULL;
@@ -401,7 +407,7 @@ static int bdi_forker_thread(void *ptr)
* memory.
*/
spin_lock_bh(&bdi_lock);
- list_add_tail(&bdi->bdi_list, &bdi_pending_list);
+ list_add(&bdi->bdi_list, &bdi_list);
spin_unlock_bh(&bdi_lock);
bdi_flush_io(bdi);
@@ -411,50 +417,6 @@ static int bdi_forker_thread(void *ptr)
return 0;
}
-static void bdi_add_to_pending(struct rcu_head *head)
-{
- struct backing_dev_info *bdi;
-
- bdi = container_of(head, struct backing_dev_info, rcu_head);
-
- spin_lock(&bdi_lock);
- list_add_tail(&bdi->bdi_list, &bdi_pending_list);
- spin_unlock(&bdi_lock);
-}
-
-/*
- * Add the default flusher thread that gets created for any bdi
- * that has dirty data pending writeout
- */
-void static bdi_add_default_flusher_thread(struct backing_dev_info *bdi)
-{
- if (!bdi_cap_writeback_dirty(bdi))
- return;
-
- if (WARN_ON(!test_bit(BDI_registered, &bdi->state))) {
- printk(KERN_ERR "bdi %p/%s is not registered!\n",
- bdi, bdi->name);
- return;
- }
-
- /*
- * Check with the helper whether to proceed adding a thread. Will only
- * abort if we two or more simultanous calls to
- * bdi_add_default_flusher_thread() occured, further additions will
- * block waiting for previous additions to finish.
- */
- if (!test_and_set_bit(BDI_pending, &bdi->state)) {
- list_del_rcu(&bdi->bdi_list);
-
- /*
- * We must wait for the current RCU period to end before
- * moving to the pending list. So schedule that operation
- * from an RCU callback.
- */
- call_rcu(&bdi->rcu_head, bdi_add_to_pending);
- }
-}
-
/*
* Remove bdi from bdi_list, and ensure that it is no longer visible
*/
@@ -595,7 +557,6 @@ int bdi_init(struct backing_dev_info *bdi)
bdi->max_ratio = 100;
bdi->max_prop_frac = PROP_FRAC_BASE;
spin_lock_init(&bdi->wb_lock);
- INIT_RCU_HEAD(&bdi->rcu_head);
INIT_LIST_HEAD(&bdi->bdi_list);
INIT_LIST_HEAD(&bdi->work_list);
--
1.7.1.1
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
