Introduce super_block.s_more_io_wait to park inodes that for some reason cannot
be synced immediately. They will be revisited in the next s_io enqueue 
time(<=5s).

The new data flow after this patchset:

s_dirty --> s_io --> s_more_io/s_more_io_wait --+
             ^                                  |
             |                                  |
             +----------------------------------+

- to fill s_io:
                s_more_io +
                s_dirty(expired) +
                s_more_io_wait
                                ---> s_io
- to drain s_io:
                s_io -+--> clean inodes goto inode_in_use/inode_unused
                      |
                      +--> s_more_io
                      |
                      +--> s_more_io_wait

Obviously there're no ordering or starvation problems in the queues:
- s_dirty is now a strict FIFO queue
- inode.dirtied_when is only set when made dirty
- once exipired, the dirty inode will stay in s_*io* queues until made clean
- the dirty inodes in s_*io* will be revisted in order, hence small files won't
  be starved by big dirty files.

Cc: Michael Rubin <[EMAIL PROTECTED]>
Cc: Peter Zijlstra <[EMAIL PROTECTED]>
Signed-off-by: Fengguang Wu <[EMAIL PROTECTED]>
---
 fs/fs-writeback.c  |   16 +++++++++++++---
 fs/super.c         |    1 +
 include/linux/fs.h |    1 +
 3 files changed, 15 insertions(+), 3 deletions(-)

--- linux-mm.orig/fs/fs-writeback.c
+++ linux-mm/fs/fs-writeback.c
@@ -172,6 +172,14 @@ static void requeue_io(struct inode *ino
        list_move(&inode->i_list, &inode->i_sb->s_more_io);
 }
 
+/*
+ * The inode should be retried after _sleeping_ for a while.
+ */
+static void requeue_io_wait(struct inode *inode)
+{
+       list_move(&inode->i_list, &inode->i_sb->s_more_io_wait);
+}
+
 static void inode_sync_complete(struct inode *inode)
 {
        /*
@@ -206,13 +214,15 @@ static void queue_io(struct super_block 
 {
        list_splice_init(&sb->s_more_io, sb->s_io.prev);
        move_expired_inodes(&sb->s_dirty, &sb->s_io, older_than_this);
+       list_splice_init(&sb->s_more_io_wait, sb->s_io.prev);
 }
 
 int sb_has_dirty_inodes(struct super_block *sb)
 {
-       return !list_empty(&sb->s_dirty) ||
-              !list_empty(&sb->s_io) ||
-              !list_empty(&sb->s_more_io);
+       return !list_empty(&sb->s_dirty)   ||
+              !list_empty(&sb->s_io)      ||
+              !list_empty(&sb->s_more_io) ||
+              !list_empty(&sb->s_more_io_wait);
 }
 EXPORT_SYMBOL(sb_has_dirty_inodes);
 
--- linux-mm.orig/fs/super.c
+++ linux-mm/fs/super.c
@@ -64,6 +64,7 @@ static struct super_block *alloc_super(s
                INIT_LIST_HEAD(&s->s_dirty);
                INIT_LIST_HEAD(&s->s_io);
                INIT_LIST_HEAD(&s->s_more_io);
+               INIT_LIST_HEAD(&s->s_more_io_wait);
                INIT_LIST_HEAD(&s->s_files);
                INIT_LIST_HEAD(&s->s_instances);
                INIT_HLIST_HEAD(&s->s_anon);
--- linux-mm.orig/include/linux/fs.h
+++ linux-mm/include/linux/fs.h
@@ -1011,6 +1011,7 @@ struct super_block {
        struct list_head        s_dirty;        /* dirty inodes */
        struct list_head        s_io;           /* parked for writeback */
        struct list_head        s_more_io;      /* parked for more writeback */
+       struct list_head        s_more_io_wait; /* parked for sleep-then-retry 
*/
        struct hlist_head       s_anon;         /* anonymous dentries for (nfs) 
exporting */
        struct list_head        s_files;
 

-- 
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Reply via email to