Re: [PATCH 1/5] writeback: introduce wbc.for_sync to cover the two sync stages

[Jan Kara <jack@suse.cz>]

On Thu 29-07-10 19:51:43, Wu Fengguang wrote:
> The sync() is performed in two stages: the WB_SYNC_NONE sync and
> the WB_SYNC_ALL sync. It is necessary to tag both stages with
> wbc.for_sync, so as to prevent either of them being livelocked.
> 
> The basic livelock scheme will be based on the sync_after timestamp.
> Inodes dirtied after that won't be queued for IO. The timestamp could be
> recorded as early as the sync() time, this patch lazily sets it in
> writeback_inodes_sb()/sync_inodes_sb(). This will stop livelock, but
> may do more work than necessary.
> 
> Note that writeback_inodes_sb() is called by not only sync(), they
> are treated the same because the other callers need the same livelock
> prevention.
  OK, but the patch does nothing, doesn't it? I'd prefer if the fields
you introduce were actually used in this patch.

								Honza

> CC: Jan Kara <jack@suse.cz>
> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
> ---
>  fs/fs-writeback.c         |   21 ++++++++++++---------
>  include/linux/writeback.h |    1 +
>  2 files changed, 13 insertions(+), 9 deletions(-)
> 
> --- linux-next.orig/fs/fs-writeback.c	2010-07-28 17:05:17.000000000 +0800
> +++ linux-next/fs/fs-writeback.c	2010-07-28 21:21:31.000000000 +0800
> @@ -36,6 +36,8 @@ struct wb_writeback_work {
>  	long nr_pages;
>  	struct super_block *sb;
>  	enum writeback_sync_modes sync_mode;
> +	unsigned long sync_after;
> +	unsigned int for_sync:1;
>  	unsigned int for_kupdate:1;
>  	unsigned int range_cyclic:1;
>  	unsigned int for_background:1;
> @@ -1086,20 +1090,17 @@ static void wait_sb_inodes(struct super_
>   */
>  void writeback_inodes_sb(struct super_block *sb)
>  {
> -	unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
> -	unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
>  	DECLARE_COMPLETION_ONSTACK(done);
>  	struct wb_writeback_work work = {
>  		.sb		= sb,
>  		.sync_mode	= WB_SYNC_NONE,
> +		.for_sync	= 1,
> +		.sync_after	= jiffies,
>  		.done		= &done,
>  	};
>  
>  	WARN_ON(!rwsem_is_locked(&sb->s_umount));
>  
> -	work.nr_pages = nr_dirty + nr_unstable +
> -			(inodes_stat.nr_inodes - inodes_stat.nr_unused);
> -
>  	bdi_queue_work(sb->s_bdi, &work);
>  	wait_for_completion(&done);
>  }
> @@ -1137,6 +1138,8 @@ void sync_inodes_sb(struct super_block *
>  	struct wb_writeback_work work = {
>  		.sb		= sb,
>  		.sync_mode	= WB_SYNC_ALL,
> +		.for_sync	= 1,
> +		.sync_after	= jiffies,
>  		.nr_pages	= LONG_MAX,
>  		.range_cyclic	= 0,
>  		.done		= &done,
> --- linux-next.orig/include/linux/writeback.h	2010-07-28 17:05:17.000000000 +0800
> +++ linux-next/include/linux/writeback.h	2010-07-28 21:24:54.000000000 +0800
> @@ -48,6 +48,7 @@ struct writeback_control {
>  	unsigned encountered_congestion:1; /* An output: a queue is full */
>  	unsigned for_kupdate:1;		/* A kupdate writeback */
>  	unsigned for_background:1;	/* A background writeback */
> +	unsigned for_sync:1;		/* A writeback for sync */
>  	unsigned for_reclaim:1;		/* Invoked from the page allocator */
>  	unsigned range_cyclic:1;	/* range_start is cyclic */
>  };
> 
> 
-- 
Jan Kara <jack@suse.cz>
SUSE Labs, CR

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>