For small memory systems, sleeping for 200ms at a time is an overkill. Given 4MB dirty limit, all the dirty/writeback pages will be written to a 80MB/s disk within 50ms. If the task goes sleep for 200ms after it dirtied 4MB, the disk will go idle for 150ms without any new data feed. So allow up to N milliseconds pause time for (4*N) MB bdi dirty limit. On a typical 4GB desktop, the max pause time will be ~150ms. Signed-off-by: Wu Fengguang --- mm/page-writeback.c | 25 ++++++++++++++++++++++--- 1 file changed, 22 insertions(+), 3 deletions(-) --- linux-next.orig/mm/page-writeback.c 2010-12-09 12:19:22.000000000 +0800 +++ linux-next/mm/page-writeback.c 2010-12-09 12:23:26.000000000 +0800 @@ -650,6 +650,22 @@ unlock: } /* + * Limit pause time for small memory systems. If sleeping for too long time, + * the small pool of dirty/writeback pages may go empty and disk go idle. + */ +static unsigned long max_pause(unsigned long bdi_thresh) +{ + unsigned long t; + + /* 1ms for every 4MB */ + t = bdi_thresh >> (32 - PAGE_CACHE_SHIFT - + ilog2(roundup_pow_of_two(HZ))); + t += 2; + + return min_t(unsigned long, t, MAX_PAUSE); +} + +/* * balance_dirty_pages() must be called by processes which are generating dirty * data. It looks at the number of dirty pages in the machine and will force * the caller to perform writeback if the system is over `vm_dirty_ratio'. @@ -671,6 +687,7 @@ static void balance_dirty_pages(struct a unsigned long long bw; unsigned long period; unsigned long pause = 0; + unsigned long pause_max; bool dirty_exceeded = false; struct backing_dev_info *bdi = mapping->backing_dev_info; unsigned long start_time = jiffies; @@ -744,8 +761,10 @@ static void balance_dirty_pages(struct a if (avg_dirty < bdi_dirty || avg_dirty > task_thresh) avg_dirty = bdi_dirty; + pause_max = max_pause(bdi_thresh); + if (avg_dirty >= task_thresh || nr_dirty > dirty_thresh) { - pause = MAX_PAUSE; + pause = pause_max; goto pause; } @@ -779,7 +798,7 @@ static void balance_dirty_pages(struct a pause = 1; break; } - pause = clamp_val(pause, 1, MAX_PAUSE); + pause = clamp_val(pause, 1, pause_max); pause: trace_balance_dirty_pages(bdi, @@ -816,7 +835,7 @@ pause: current->nr_dirtied_pause = ratelimit_pages(bdi); else if (pause == 1) current->nr_dirtied_pause += current->nr_dirtied_pause / 32 + 1; - else if (pause >= MAX_PAUSE) + else if (pause >= pause_max) /* * when repeated, writing 1 page per 100ms on slow devices, * i-(i+2)/4 will be able to reach 1 but never reduce to 0. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/