writeback: make writeback_control.nr_to_write straight
Pass struct wb_writeback_work all the way down to writeback_sb_inodes(),
and initialize the struct writeback_control there.
struct writeback_control is basically designed to control writeback of a
single file, but we keep abuse it for writing multiple files in
writeback_sb_inodes() and its callers.
It immediately clean things up, e.g. suddenly wbc.nr_to_write vs
work->nr_pages starts to make sense, and instead of saving and restoring
pages_skipped in writeback_sb_inodes it can always start with a clean
zero value.
It also makes a neat IO pattern change: large dirty files are now
written in the full 4MB writeback chunk size, rather than whatever
remained quota in wbc->nr_to_write.
Acked-by: Jan Kara <jack@suse.cz>
Proposed-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 5f6553e..7ba303b 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -260,18 +260,6 @@
return wb_has_dirty_io(&bdi->wb);
}
-static void bdi_flush_io(struct backing_dev_info *bdi)
-{
- struct writeback_control wbc = {
- .sync_mode = WB_SYNC_NONE,
- .older_than_this = NULL,
- .range_cyclic = 1,
- .nr_to_write = 1024,
- };
-
- writeback_inodes_wb(&bdi->wb, &wbc);
-}
-
/*
* kupdated() used to do this. We cannot do it from the bdi_forker_thread()
* or we risk deadlocking on ->s_umount. The longer term solution would be
@@ -457,9 +445,10 @@
if (IS_ERR(task)) {
/*
* If thread creation fails, force writeout of
- * the bdi from the thread.
+ * the bdi from the thread. Hopefully 1024 is
+ * large enough for efficient IO.
*/
- bdi_flush_io(bdi);
+ writeback_inodes_wb(&bdi->wb, 1024);
} else {
/*
* The spinlock makes sure we do not lose
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 1965d05..9d6ac2b 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -491,13 +491,6 @@
struct backing_dev_info *bdi = mapping->backing_dev_info;
for (;;) {
- struct writeback_control wbc = {
- .sync_mode = WB_SYNC_NONE,
- .older_than_this = NULL,
- .nr_to_write = write_chunk,
- .range_cyclic = 1,
- };
-
nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
global_page_state(NR_UNSTABLE_NFS);
nr_writeback = global_page_state(NR_WRITEBACK);
@@ -559,17 +552,17 @@
* threshold otherwise wait until the disk writes catch
* up.
*/
- trace_wbc_balance_dirty_start(&wbc, bdi);
+ trace_balance_dirty_start(bdi);
if (bdi_nr_reclaimable > bdi_thresh) {
- writeback_inodes_wb(&bdi->wb, &wbc);
- pages_written += write_chunk - wbc.nr_to_write;
- trace_wbc_balance_dirty_written(&wbc, bdi);
+ pages_written += writeback_inodes_wb(&bdi->wb,
+ write_chunk);
+ trace_balance_dirty_written(bdi, pages_written);
if (pages_written >= write_chunk)
break; /* We've done our duty */
}
- trace_wbc_balance_dirty_wait(&wbc, bdi);
__set_current_state(TASK_UNINTERRUPTIBLE);
io_schedule_timeout(pause);
+ trace_balance_dirty_wait(bdi);
/*
* Increase the delay for each loop, up to our previous