#define CREATE_TRACE_POINTS
#include <trace/events/writeback.h>
-#define inode_to_bdi(inode) ((inode)->i_mapping->backing_dev_info)
-
/*
* We don't actually have pdflush, but this one is exported though /proc...
*/
*/
int writeback_in_progress(struct backing_dev_info *bdi)
{
- return !list_empty(&bdi->work_list);
+ return test_bit(BDI_writeback_running, &bdi->state);
+}
+
+static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
+{
+ struct super_block *sb = inode->i_sb;
+
+ if (strcmp(sb->s_type->name, "bdev") == 0)
+ return inode->i_mapping->backing_dev_info;
+
+ return sb->s_bdi;
}
static void bdi_queue_work(struct backing_dev_info *bdi,
{
trace_writeback_queue(bdi, work);
- spin_lock(&bdi->wb_lock);
+ spin_lock_bh(&bdi->wb_lock);
list_add_tail(&work->list, &bdi->work_list);
if (bdi->wb.task) {
wake_up_process(bdi->wb.task);
trace_writeback_nothread(bdi, work);
wake_up_process(default_backing_dev_info.wb.task);
}
- spin_unlock(&bdi->wb_lock);
+ spin_unlock_bh(&bdi->wb_lock);
}
static void
/*
* Queue all expired dirty inodes for io, eldest first.
+ * Before
+ * newly dirtied b_dirty b_io b_more_io
+ * =============> gf edc BA
+ * After
+ * newly dirtied b_dirty b_io b_more_io
+ * =============> g fBAedc
+ * |
+ * +--> dequeue for IO
*/
static void queue_io(struct bdi_writeback *wb, unsigned long *older_than_this)
{
- list_splice_init(&wb->b_more_io, wb->b_io.prev);
+ list_splice_init(&wb->b_more_io, &wb->b_io);
move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this);
}
spin_lock(&inode_lock);
inode->i_state &= ~I_SYNC;
- if (!(inode->i_state & (I_FREEING | I_CLEAR))) {
- if ((inode->i_state & I_DIRTY_PAGES) && wbc->for_kupdate) {
- /*
- * More pages get dirtied by a fast dirtier.
- */
- goto select_queue;
- } else if (inode->i_state & I_DIRTY) {
- /*
- * At least XFS will redirty the inode during the
- * writeback (delalloc) and on io completion (isize).
- */
- redirty_tail(inode);
- } else if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
+ if (!(inode->i_state & I_FREEING)) {
+ if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
/*
* We didn't write back all the pages. nfs_writepages()
- * sometimes bales out without doing anything. Redirty
- * the inode; Move it from b_io onto b_more_io/b_dirty.
- */
- /*
- * akpm: if the caller was the kupdate function we put
- * this inode at the head of b_dirty so it gets first
- * consideration. Otherwise, move it to the tail, for
- * the reasons described there. I'm not really sure
- * how much sense this makes. Presumably I had a good
- * reasons for doing it this way, and I'd rather not
- * muck with it at present.
+ * sometimes bales out without doing anything.
*/
- if (wbc->for_kupdate) {
+ inode->i_state |= I_DIRTY_PAGES;
+ if (wbc->nr_to_write <= 0) {
/*
- * For the kupdate function we move the inode
- * to b_more_io so it will get more writeout as
- * soon as the queue becomes uncongested.
+ * slice used up: queue for next turn
*/
- inode->i_state |= I_DIRTY_PAGES;
-select_queue:
- if (wbc->nr_to_write <= 0) {
- /*
- * slice used up: queue for next turn
- */
- requeue_io(inode);
- } else {
- /*
- * somehow blocked: retry later
- */
- redirty_tail(inode);
- }
+ requeue_io(inode);
} else {
/*
- * Otherwise fully redirty the inode so that
- * other inodes on this superblock will get some
- * writeout. Otherwise heavy writing to one
- * file would indefinitely suspend writeout of
- * all the other files.
+ * Writeback blocked by something other than
+ * congestion. Delay the inode for some time to
+ * avoid spinning on the CPU (100% iowait)
+ * retrying writeback of the dirty page/inode
+ * that cannot be performed immediately.
*/
- inode->i_state |= I_DIRTY_PAGES;
redirty_tail(inode);
}
+ } else if (inode->i_state & I_DIRTY) {
+ /*
+ * Filesystems can dirty the inode during writeback
+ * operations, such as delayed allocation during
+ * submission or metadata updates after data IO
+ * completion.
+ */
+ redirty_tail(inode);
} else if (atomic_read(&inode->i_count)) {
/*
* The inode is clean, inuse
if (inode_dirtied_after(inode, wbc->wb_start))
return 1;
- BUG_ON(inode->i_state & (I_FREEING | I_CLEAR));
+ BUG_ON(inode->i_state & I_FREEING);
__iget(inode);
pages_skipped = wbc->pages_skipped;
writeback_single_inode(inode, wbc);
{
int ret = 0;
- wbc->wb_start = jiffies; /* livelock avoidance */
+ if (!wbc->wb_start)
+ wbc->wb_start = jiffies; /* livelock avoidance */
spin_lock(&inode_lock);
if (!wbc->for_kupdate || list_empty(&wb->b_io))
queue_io(wb, wbc->older_than_this);
{
WARN_ON(!rwsem_is_locked(&sb->s_umount));
- wbc->wb_start = jiffies; /* livelock avoidance */
spin_lock(&inode_lock);
if (!wbc->for_kupdate || list_empty(&wb->b_io))
queue_io(wb, wbc->older_than_this);
{
unsigned long background_thresh, dirty_thresh;
- get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
+ global_dirty_limits(&background_thresh, &dirty_thresh);
return (global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS) >= background_thresh);
wbc.range_end = LLONG_MAX;
}
+ wbc.wb_start = jiffies; /* livelock avoidance */
for (;;) {
/*
* Stop writeback when nr_pages has been consumed
{
struct wb_writeback_work *work = NULL;
- spin_lock(&bdi->wb_lock);
+ spin_lock_bh(&bdi->wb_lock);
if (!list_empty(&bdi->work_list)) {
work = list_entry(bdi->work_list.next,
struct wb_writeback_work, list);
list_del_init(&work->list);
}
- spin_unlock(&bdi->wb_lock);
+ spin_unlock_bh(&bdi->wb_lock);
return work;
}
struct wb_writeback_work *work;
long wrote = 0;
+ set_bit(BDI_writeback_running, &wb->bdi->state);
while ((work = get_next_work_item(bdi)) != NULL) {
/*
* Override sync mode, in case we must wait for completion
* Check for periodic writeback, kupdated() style
*/
wrote += wb_check_old_data_flush(wb);
+ clear_bit(BDI_writeback_running, &wb->bdi->state);
return wrote;
}
trace_writeback_thread_start(bdi);
while (!kthread_should_stop()) {
+ /*
+ * Remove own delayed wake-up timer, since we are already awake
+ * and we'll take care of the preriodic write-back.
+ */
+ del_timer(&wb->wakeup_timer);
+
pages_written = wb_do_writeback(wb, 0);
trace_writeback_pages_written(pages_written);
wb->last_active = jiffies;
set_current_state(TASK_INTERRUPTIBLE);
- if (!list_empty(&bdi->work_list)) {
+ if (!list_empty(&bdi->work_list) || kthread_should_stop()) {
__set_current_state(TASK_RUNNING);
continue;
}
rcu_read_unlock();
}
-/*
- * This function is used when the first inode for this bdi is marked dirty. It
- * wakes-up the corresponding bdi thread which should then take care of the
- * periodic background write-out of dirty inodes.
- */
-static void wakeup_bdi_thread(struct backing_dev_info *bdi)
-{
- spin_lock(&bdi->wb_lock);
- if (bdi->wb.task)
- wake_up_process(bdi->wb.task);
- else
- /*
- * When bdi tasks are inactive for long time, they are killed.
- * In this case we have to wake-up the forker thread which
- * should create and run the bdi thread.
- */
- wake_up_process(default_backing_dev_info.wb.task);
- spin_unlock(&bdi->wb_lock);
-}
-
static noinline void block_dump___mark_inode_dirty(struct inode *inode)
{
if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) {
if (hlist_unhashed(&inode->i_hash))
goto out;
}
- if (inode->i_state & (I_FREEING|I_CLEAR))
+ if (inode->i_state & I_FREEING)
goto out;
/*
spin_unlock(&inode_lock);
if (wakeup_bdi)
- wakeup_bdi_thread(bdi);
+ bdi_wakeup_thread_delayed(bdi);
}
EXPORT_SYMBOL(__mark_inode_dirty);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
struct address_space *mapping;
- if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
+ if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW))
continue;
mapping = inode->i_mapping;
if (mapping->nrpages == 0)
git.openpandora.org / pandora-kernel.git / blobdiff