Re: [PATCH 3/4] writeback: only use bdi_writeback_all() forWB_SYNC_NONE writeout
From: Jens Axboe
Date: Sun Sep 13 2009 - 14:20:45 EST
On Fri, Sep 11 2009, Christoph Hellwig wrote:
>
> -static struct bdi_work *bdi_alloc_work(struct writeback_control *wbc)
>
> +static void bdi_alloc_queue_work(struct backing_dev_info *bdi,
>
> + struct writeback_control *wbc)
>
> {
>
> struct bdi_work *work;
>
>
>
> @@ -195,7 +196,7 @@ static struct bdi_work *bdi_alloc_work(struct writeback_control *wbc)
>
> if (work)
>
> bdi_work_init(work, wbc);
>
>
>
> - return work;
>
> + bdi_queue_work(bdi, work);
>
>
This is now the only caller of bdi_queue_work that has a NULL work
>
argument. I would recommend removing the !work half of bdi_queue_work
>
and just inline it into this function (or make it a separate helper).
http://git.kernel.dk/?p=linux-2.6-block.git;a=commit;h=cd932613c5b86a5bb2eefee726749acb0ed1a5b8
>
> @@ -1157,6 +1115,7 @@ long sync_inodes_sb(struct super_block *sb)
>
> {
>
> struct writeback_control wbc = {
>
> .sb = sb,
>
> + .bdi = sb->s_bdi,
>
> .sync_mode = WB_SYNC_ALL,
>
> .range_start = 0,
>
> .range_end = LLONG_MAX,
>
> @@ -1164,7 +1123,7 @@ long sync_inodes_sb(struct super_block *sb)
>
> long nr_to_write = LONG_MAX; /* doesn't actually matter */
>
>
>
> wbc.nr_to_write = nr_to_write;
>
> - bdi_writeback_all(&wbc);
>
> + bdi_start_writeback(&wbc);
>
>
So here we have a WB_SYNC_ALL caller of bdi_writeback_all and the
>
only other caller is WB_SYNC_NONE. Given that after patch two those
>
are entirely different codepathes in bdi_start_writeback I would just
>
split bdi_start_writeback into two separate functions.
http://git.kernel.dk/?p=linux-2.6-block.git;a=commit;h=479364efda68ae0d954f325fa52a3bbe94916783
--
Jens Axboe
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at
http://vger.kernel.org/majordomo-info.html
Please read the FAQ at
http://www.tux.org/lkml/