Currently we are somewhat inconsistent in which inodes we put to
b_more_io. We put there inodes which have exhausted their writeback
chunk but we also put there inodes which could not be written because
someone else was already writing them (the inode had I_SYNC set). OTOH
if inodes couldn't be written for other reasons (filesystem indicates
this with pages_skipped or by simply not writing anything) we
redirty_tail() the inode.
So make things more consistent by putting to b_more_io list only inodes
that exhausted their writeback chunk and call redirty_tail() in every
case where inode couldn't be written for some reason. This also makes
the busyloop prevention in wb_writeback() unnecessary since unwriteable
inodes will be moved back to b_dirty list and thus won't confuse us in
b_io or b_more_io lists.
Signed-off-by: Jan Kara <jack@xxxxxxx>
---
fs/fs-writeback.c | 26 ++++----------------------
include/trace/events/writeback.h | 1 -
2 files changed, 4 insertions(+), 23 deletions(-)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index dbace1c09b7f..6ee9ee52e3de 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -611,15 +611,12 @@ static long writeback_inodes(struct bdi_writeback *wb,
if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) {
/*
* If this inode is locked for writeback and we are not
- * doing writeback-for-data-integrity, move it to
- * b_more_io so that writeback can proceed with the
- * other inodes on s_io.
- *
- * We'll have another go at writing back this inode
- * when we completed a full scan of b_io.
+ * doing writeback-for-data-integrity, move it back to
+ * the dirty list so that writeback can proceed with the
+ * other inodes on b_io.
*/
spin_unlock(&inode->i_lock);
- requeue_io(inode, wb);
+ redirty_tail(inode, wb);
trace_writeback_inodes_requeue(inode);
continue;
}
@@ -722,7 +719,6 @@ static long wb_writeback(struct bdi_writeback *wb,
unsigned long wb_start = jiffies;
long nr_pages = work->nr_pages;
unsigned long oldest_jif;
- struct inode *inode;
long progress;
oldest_jif = jiffies;
@@ -788,20 +784,6 @@ static long wb_writeback(struct bdi_writeback *wb,
*/
if (list_empty(&wb->b_more_io))
break;
- /*
- * Nothing written. Wait for some inode to
- * become available for writeback. Otherwise
- * we'll just busyloop.
- */
- if (!list_empty(&wb->b_more_io)) {
- trace_writeback_wait(wb->bdi, work);
- inode = wb_inode(wb->b_more_io.prev);
- spin_lock(&inode->i_lock);
- spin_unlock(&wb->list_lock);
- /* This function drops i_lock... */
- inode_sleep_on_writeback(inode);
- spin_lock(&wb->list_lock);
- }
}
spin_unlock(&wb->list_lock);
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 9bf6f2da32d2..102e2ad9f90f 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -188,7 +188,6 @@ DEFINE_WRITEBACK_WORK_EVENT(writeback_queue);
DEFINE_WRITEBACK_WORK_EVENT(writeback_exec);
DEFINE_WRITEBACK_WORK_EVENT(writeback_start);
DEFINE_WRITEBACK_WORK_EVENT(writeback_written);
-DEFINE_WRITEBACK_WORK_EVENT(writeback_wait);
TRACE_EVENT(writeback_pages_written,
TP_PROTO(long pages_written),
--
1.8.1.4
--
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
