On Sun, 2010-07-11 at 10:06 +0800, Wu Fengguang wrote:
>
> CC: Jan Kara <jack@xxxxxxx>
I can more or less remember this patch, and the result looks good.
Acked-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
> Signed-off-by: Richard Kennedy <richard@xxxxxxxxxxxxxxx>
> Signed-off-by: Wu Fengguang <fengguang.wu@xxxxxxxxx>
> ---
> mm/page-writeback.c | 95 ++++++++++++++----------------------------
> 1 file changed, 33 insertions(+), 62 deletions(-)
>
> --- linux-next.orig/mm/page-writeback.c 2010-07-11 08:42:14.000000000 +0800
> +++ linux-next/mm/page-writeback.c 2010-07-11 08:44:49.000000000 +0800
> @@ -253,32 +253,6 @@ static void bdi_writeout_fraction(struct
> }
> }
>
> static inline void task_dirties_fraction(struct task_struct *tsk,
> long *numerator, long *denominator)
> {
> @@ -469,7 +443,6 @@ get_dirty_limits(unsigned long *pbackgro
> bdi_dirty = dirty * bdi->max_ratio / 100;
>
> *pbdi_dirty = bdi_dirty;
> task_dirty_limit(current, pbdi_dirty);
> }
> }
> @@ -491,7 +464,7 @@ static void balance_dirty_pages(struct a
> unsigned long bdi_thresh;
> unsigned long pages_written = 0;
> unsigned long pause = 1;
> + int dirty_exceeded;
> struct backing_dev_info *bdi = mapping->backing_dev_info;
>
> for (;;) {
> @@ -510,10 +483,35 @@ static void balance_dirty_pages(struct a
> nr_writeback = global_page_state(NR_WRITEBACK) +
> global_page_state(NR_WRITEBACK_TEMP);
>
> + /*
> + * In order to avoid the stacked BDI deadlock we need
> + * to ensure we accurately count the 'dirty' pages when
> + * the threshold is low.
> + *
> + * Otherwise it would be possible to get thresh+n pages
> + * reported dirty, even though there are thresh-m pages
> + * actually dirty; with m+n sitting in the percpu
> + * deltas.
> + */
> + if (bdi_thresh < 2*bdi_stat_error(bdi)) {
> + bdi_nr_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE);
> + bdi_nr_writeback = bdi_stat_sum(bdi, BDI_WRITEBACK);
> + } else {
> + bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE);
> + bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK);
> + }
> +
> + /*
> + * The bdi thresh is somehow "soft" limit derived from the
> + * global "hard" limit. The former helps to prevent heavy IO
> + * bdi or process from holding back light ones; The latter is
> + * the last resort safeguard.
> + */
> + dirty_exceeded =
> + (bdi_nr_reclaimable + bdi_nr_writeback >= bdi_thresh)
> + || (nr_reclaimable + nr_writeback >= dirty_thresh);
>
> + if (!dirty_exceeded)
> break;
>
> /*
> @@ -541,34 +539,10 @@ static void balance_dirty_pages(struct a
> 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);
> + if (pages_written >= write_chunk)
> + break; /* We've done our duty */
> }
> trace_wbc_balance_dirty_wait(&wbc, bdi);
> __set_current_state(TASK_INTERRUPTIBLE);
> io_schedule_timeout(pause);
> @@ -582,8 +556,7 @@ static void balance_dirty_pages(struct a
> pause = HZ / 10;
> }
>
> + if (!dirty_exceeded && bdi->dirty_exceeded)
> bdi->dirty_exceeded = 0;
>
> if (writeback_in_progress(bdi))
> @@ -598,9 +571,7 @@ static void balance_dirty_pages(struct a
> * background_thresh, to keep the amount of dirty memory low.
> */
> if ((laptop_mode && pages_written) ||
> + (!laptop_mode && (nr_reclaimable > background_thresh)))
> bdi_start_background_writeback(bdi);
> }
--
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
