When there are only one (or several) dirtiers, dirty_exceeded is always
(or mostly) off. Converting to timestamp avoids this problem. It helps
to use smaller write_chunk for smoother throttling.
We'll lower ratelimit if saw dirty exceeded in the last 1 second.
Signed-off-by: Wu Fengguang <fengguang.wu@xxxxxxxxx>
---
Before patch, the wait time in balance_dirty_pages() are ~200ms:
[ 1093.397700] write_bandwidth: comm=swapper pages=1536 time=204ms
[ 1093.594319] write_bandwidth: comm=swapper pages=1536 time=196ms
[ 1093.796642] write_bandwidth: comm=swapper pages=1536 time=200ms
After patch, ~25ms:
[ 90.261339] write_bandwidth: comm=swapper pages=192 time=20ms
[ 90.293168] write_bandwidth: comm=swapper pages=192 time=24ms
[ 90.323853] write_bandwidth: comm=swapper pages=192 time=24ms
[ 90.354510] write_bandwidth: comm=swapper pages=192 time=28ms
[ 90.389890] write_bandwidth: comm=swapper pages=192 time=28ms
[ 90.421787] write_bandwidth: comm=swapper pages=192 time=24ms
include/linux/backing-dev.h | 2 +-
mm/backing-dev.c | 1 -
mm/page-writeback.c | 9 +++------
3 files changed, 4 insertions(+), 8 deletions(-)
--- linux.orig/mm/page-writeback.c 2009-10-07 14:32:43.000000000 +0800
+++ linux/mm/page-writeback.c 2009-10-07 14:32:46.000000000 +0800
@@ -523,14 +523,10 @@ static void balance_dirty_pages(struct a
goto out;
throttle:
- if (!bdi->dirty_exceeded)
- bdi->dirty_exceeded = 1;
+ bdi->dirty_exceed_time = jiffies;
bdi_writeback_wait(bdi, write_chunk);
- if (bdi->dirty_exceeded)
- bdi->dirty_exceeded = 0;
-
out:
/*
* In laptop mode, we wait until hitting the higher threshold before
@@ -578,7 +574,8 @@ void balance_dirty_pages_ratelimited_nr(
unsigned long *p;
ratelimit = ratelimit_pages;
- if (mapping->backing_dev_info->dirty_exceeded)
+ if (jiffies - mapping->backing_dev_info->dirty_exceed_time <
+ (unsigned long) HZ)
ratelimit >>= 3;
/*
--- linux.orig/include/linux/backing-dev.h 2009-10-07 14:31:53.000000000 +0800
+++ linux/include/linux/backing-dev.h 2009-10-07 14:32:46.000000000 +0800
@@ -74,7 +74,7 @@ struct backing_dev_info {
struct percpu_counter bdi_stat[NR_BDI_STAT_ITEMS];
struct prop_local_percpu completions;
- int dirty_exceeded;
+ unsigned long dirty_exceed_time;
unsigned int min_ratio;
unsigned int max_ratio, max_prop_frac;
--- linux.orig/mm/backing-dev.c 2009-10-07 14:31:53.000000000 +0800
+++ linux/mm/backing-dev.c 2009-10-07 14:32:46.000000000 +0800
@@ -661,7 +661,6 @@ int bdi_init(struct backing_dev_info *bd
goto err;
}
- bdi->dirty_exceeded = 0;
err = prop_local_init_percpu(&bdi->completions);
if (err) {
--
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
