The patch titled
writeback: bdi write bandwidth estimation
has been added to the -mm tree. Its filename is
writeback-bdi-write-bandwidth-estimation.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: writeback: bdi write bandwidth estimation
From: Wu Fengguang <fengguang.wu@xxxxxxxxx>
The estimation value will start from 100MB/s and adapt to the real
bandwidth in seconds. It's pretty accurate for common filesystems.
As the first use case, it replaces the fixed 100MB/s value used for
throttle bandwidth calculation in balance_dirty_pages().
The overheads won't be high because the bdi bandwidth udpate only occurs
in >10ms intervals.
Initially it's only estimated in balance_dirty_pages() because this is the
most reliable place to get reasonable large bandwidth -- the bdi is
normally fully utilized when bdi_thresh is reached.
Then Shaohua recommends to also do it in the flusher thread, to keep the
value updated when there are only periodic/background writeback and no
tasks throttled.
The estimation cannot be done purely in the flusher thread because it's
not sufficient for NFS. NFS writeback won't block at get_request_wait(),
so tend to complete quickly. Another problem is, slow devices may take
dozens of seconds to write the initial 64MB chunk (write_bandwidth starts
with 100MB/s, this translates to 64MB nr_to_write). So it may take more
than 1 minute to adapt to the smallish bandwidth if the bandwidth is only
updated in the flusher thread.
Signed-off-by: Wu Fengguang <fengguang.wu@xxxxxxxxx>
Cc: Chris Mason <chris.mason@xxxxxxxxxx>
Cc: Dave Chinner <david@xxxxxxxxxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
Cc: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Cc: Li Shaohua <shaohua.li@xxxxxxxxx>
Cc: Theodore Ts'o <tytso@xxxxxxx>
Cc: Richard Kennedy <richard@xxxxxxxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Mel Gorman <mel@xxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Michael Rubin <mrubin@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/fs-writeback.c | 5 ++++
include/linux/backing-dev.h | 2 +
include/linux/writeback.h | 3 ++
mm/backing-dev.c | 1
mm/page-writeback.c | 41 +++++++++++++++++++++++++++++++++-
5 files changed, 51 insertions(+), 1 deletion(-)
diff -puN fs/fs-writeback.c~writeback-bdi-write-bandwidth-estimation fs/fs-writeback.c
--- a/fs/fs-writeback.c~writeback-bdi-write-bandwidth-estimation
+++ a/fs/fs-writeback.c
@@ -635,6 +635,8 @@ static long wb_writeback(struct bdi_writ
.range_cyclic = work->range_cyclic,
};
unsigned long oldest_jif;
+ unsigned long bw_time;
+ s64 bw_written = 0;
long wrote = 0;
long write_chunk;
struct inode *inode;
@@ -668,6 +670,8 @@ static long wb_writeback(struct bdi_writ
write_chunk = LONG_MAX;
wbc.wb_start = jiffies; /* livelock avoidance */
+ bdi_update_write_bandwidth(wb->bdi, &bw_time, &bw_written);
+
for (;;) {
/*
* Stop writeback when nr_pages has been consumed
@@ -702,6 +706,7 @@ static long wb_writeback(struct bdi_writ
else
writeback_inodes_wb(wb, &wbc);
trace_wbc_writeback_written(&wbc, wb->bdi);
+ bdi_update_write_bandwidth(wb->bdi, &bw_time, &bw_written);
work->nr_pages -= write_chunk - wbc.nr_to_write;
wrote += write_chunk - wbc.nr_to_write;
diff -puN include/linux/backing-dev.h~writeback-bdi-write-bandwidth-estimation include/linux/backing-dev.h
--- a/include/linux/backing-dev.h~writeback-bdi-write-bandwidth-estimation
+++ a/include/linux/backing-dev.h
@@ -75,6 +75,8 @@ struct backing_dev_info {
struct percpu_counter bdi_stat[NR_BDI_STAT_ITEMS];
struct prop_local_percpu completions;
+ unsigned long write_bandwidth_update_time;
+ int write_bandwidth;
int dirty_exceeded;
unsigned int min_ratio;
diff -puN include/linux/writeback.h~writeback-bdi-write-bandwidth-estimation include/linux/writeback.h
--- a/include/linux/writeback.h~writeback-bdi-write-bandwidth-estimation
+++ a/include/linux/writeback.h
@@ -137,6 +137,9 @@ int dirty_writeback_centisecs_handler(st
void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty);
unsigned long bdi_dirty_limit(struct backing_dev_info *bdi,
unsigned long dirty);
+void bdi_update_write_bandwidth(struct backing_dev_info *bdi,
+ unsigned long *bw_time,
+ s64 *bw_written);
void page_writeback_init(void);
void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
diff -puN mm/backing-dev.c~writeback-bdi-write-bandwidth-estimation mm/backing-dev.c
--- a/mm/backing-dev.c~writeback-bdi-write-bandwidth-estimation
+++ a/mm/backing-dev.c
@@ -660,6 +660,7 @@ int bdi_init(struct backing_dev_info *bd
goto err;
}
+ bdi->write_bandwidth = 100 << 20;
bdi->dirty_exceeded = 0;
err = prop_local_init_percpu(&bdi->completions);
diff -puN mm/page-writeback.c~writeback-bdi-write-bandwidth-estimation mm/page-writeback.c
--- a/mm/page-writeback.c~writeback-bdi-write-bandwidth-estimation
+++ a/mm/page-writeback.c
@@ -479,6 +479,41 @@ out:
return 1 + int_sqrt(dirty_thresh - dirty_pages);
}
+void bdi_update_write_bandwidth(struct backing_dev_info *bdi,
+ unsigned long *bw_time,
+ s64 *bw_written)
+{
+ unsigned long written;
+ unsigned long elapsed;
+ unsigned long bw;
+ unsigned long w;
+
+ if (*bw_written == 0)
+ goto snapshot;
+
+ elapsed = jiffies - *bw_time;
+ if (elapsed < HZ/100)
+ return;
+
+ /*
+ * When there lots of tasks throttled in balance_dirty_pages(), they
+ * will each try to update the bandwidth for the same period, making
+ * the bandwidth drift much faster than the desired rate (as in the
+ * single dirtier case). So do some rate limiting.
+ */
+ if (jiffies - bdi->write_bandwidth_update_time < elapsed)
+ goto snapshot;
+
+ written = percpu_counter_read(&bdi->bdi_stat[BDI_WRITTEN]) - *bw_written;
+ bw = (HZ * PAGE_CACHE_SIZE * written + elapsed/2) / elapsed;
+ w = min(elapsed / (HZ/100), 128UL);
+ bdi->write_bandwidth = (bdi->write_bandwidth * (1024-w) + bw * w) >> 10;
+ bdi->write_bandwidth_update_time = jiffies;
+snapshot:
+ *bw_written = percpu_counter_read(&bdi->bdi_stat[BDI_WRITTEN]);
+ *bw_time = jiffies;
+}
+
/*
* 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
@@ -498,6 +533,8 @@ static void balance_dirty_pages(struct a
unsigned long pause = 0;
bool dirty_exceeded = false;
struct backing_dev_info *bdi = mapping->backing_dev_info;
+ unsigned long bw_time;
+ s64 bw_written = 0;
for (;;) {
/*
@@ -546,7 +583,7 @@ static void balance_dirty_pages(struct a
goto pause;
}
- bw = 100 << 20; /* use static 100MB/s for the moment */
+ bw = bdi->write_bandwidth;
bw = bw * (bdi_thresh - bdi_dirty);
bw = bw / (bdi_thresh / TASK_SOFT_DIRTY_LIMIT + 1);
@@ -555,8 +592,10 @@ static void balance_dirty_pages(struct a
pause = clamp_val(pause, 1, HZ/10);
pause:
+ bdi_update_write_bandwidth(bdi, &bw_time, &bw_written);
__set_current_state(TASK_INTERRUPTIBLE);
io_schedule_timeout(pause);
+ bdi_update_write_bandwidth(bdi, &bw_time, &bw_written);
/*
* The bdi thresh is somehow "soft" limit derived from the
_
Patches currently in -mm which might be from fengguang.wu@xxxxxxxxx are
linux-next.patch
writeback-integrated-background-writeback-work.patch
writeback-trace-wakeup-event-for-background-writeback.patch
writeback-stop-background-kupdate-works-from-livelocking-other-works.patch
writeback-stop-background-kupdate-works-from-livelocking-other-works-update.patch
writeback-avoid-livelocking-wb_sync_all-writeback.patch
writeback-avoid-livelocking-wb_sync_all-writeback-update.patch
writeback-check-skipped-pages-on-wb_sync_all.patch
writeback-check-skipped-pages-on-wb_sync_all-update.patch
writeback-check-skipped-pages-on-wb_sync_all-update-fix.patch
writeback-io-less-balance_dirty_pages.patch
writeback-consolidate-variable-names-in-balance_dirty_pages.patch
writeback-per-task-rate-limit-on-balance_dirty_pages.patch
writeback-per-task-rate-limit-on-balance_dirty_pages-fix.patch
writeback-prevent-duplicate-balance_dirty_pages_ratelimited-calls.patch
writeback-account-per-bdi-accumulated-written-pages.patch
writeback-bdi-write-bandwidth-estimation.patch
writeback-show-bdi-write-bandwidth-in-debugfs.patch
writeback-quit-throttling-when-bdi-dirty-pages-dropped-low.patch
writeback-reduce-per-bdi-dirty-threshold-ramp-up-time.patch
writeback-make-reasonable-gap-between-the-dirty-background-thresholds.patch
writeback-scale-down-max-throttle-bandwidth-on-concurrent-dirtiers.patch
writeback-add-trace-event-for-balance_dirty_pages.patch
writeback-make-nr_to_write-a-per-file-limit.patch
mm-page-writebackc-fix-__set_page_dirty_no_writeback-return-value.patch
mm-find_get_pages_contig-fixlet.patch
mm-smaps-export-mlock-information.patch
memcg-add-page_cgroup-flags-for-dirty-page-tracking.patch
memcg-document-cgroup-dirty-memory-interfaces.patch
memcg-document-cgroup-dirty-memory-interfaces-fix.patch
memcg-create-extensible-page-stat-update-routines.patch
memcg-add-lock-to-synchronize-page-accounting-and-migration.patch
writeback-create-dirty_info-structure.patch
memcg-add-dirty-page-accounting-infrastructure.patch
memcg-add-kernel-calls-for-memcg-dirty-page-stats.patch
memcg-add-dirty-limits-to-mem_cgroup.patch
memcg-add-dirty-limits-to-mem_cgroup-use-native-word-to-represent-dirtyable-pages.patch
memcg-add-dirty-limits-to-mem_cgroup-catch-negative-per-cpu-sums-in-dirty-info.patch
memcg-add-dirty-limits-to-mem_cgroup-avoid-overflow-in-memcg_hierarchical_free_pages.patch
memcg-add-dirty-limits-to-mem_cgroup-correct-memcg_hierarchical_free_pages-return-type.patch
memcg-add-dirty-limits-to-mem_cgroup-avoid-free-overflow-in-memcg_hierarchical_free_pages.patch
memcg-cpu-hotplug-lockdep-warning-fix.patch
memcg-add-cgroupfs-interface-to-memcg-dirty-limits.patch
memcg-break-out-event-counters-from-other-stats.patch
memcg-check-memcg-dirty-limits-in-page-writeback.patch
memcg-use-native-word-page-statistics-counters.patch
memcg-use-native-word-page-statistics-counters-fix.patch
memcg-add-mem_cgroup-parameter-to-mem_cgroup_page_stat.patch
memcg-pass-mem_cgroup-to-mem_cgroup_dirty_info.patch
memcg-make-throttle_vm_writeout-memcg-aware.patch
memcg-make-throttle_vm_writeout-memcg-aware-fix.patch
memcg-simplify-mem_cgroup_page_stat.patch
memcg-simplify-mem_cgroup_dirty_info.patch
memcg-make-mem_cgroup_page_stat-return-value-unsigned.patch
memcg-use-zalloc-rather-than-mallocmemset.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
