writeback: use higher precision calculation in domain_dirty_limits()

As vm.dirty_[background_]bytes can't be applied verbatim to multiple
cgroup writeback domains, they get converted to percentages in
domain_dirty_limits() and applied the same way as
vm.dirty_[background]ratio.  However, if the specified bytes is lower
than 1% of available memory, the calculated ratios become zero and the
writeback domain gets throttled constantly.

Fix it by using per-PAGE_SIZE instead of percentage for ratio
calculations.  Also, the updated DIV_ROUND_UP() usages now should
yield 1/4096 (0.0244%) as the minimum ratio as long as the specified
bytes are above zero.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Miao Xie <miaoxie@huawei.com>
Link: http://lkml.kernel.org/g/57333E75.3080309@huawei.com
Cc: stable@vger.kernel.org # v4.2+
Fixes: 9fc3a43e17 ("writeback: separate out domain_dirty_limits()")
Reviewed-by: Jan Kara <jack@suse.cz>

Adjusted comment based on Jan's suggestion.
Signed-off-by: Jens Axboe <axboe@fb.com>
This commit is contained in:
Tejun Heo 2016-05-27 14:34:46 -04:00 committed by Jens Axboe
parent b02b1fbdd3
commit 62a584fe05

View file

@ -373,8 +373,9 @@ static void domain_dirty_limits(struct dirty_throttle_control *dtc)
struct dirty_throttle_control *gdtc = mdtc_gdtc(dtc); struct dirty_throttle_control *gdtc = mdtc_gdtc(dtc);
unsigned long bytes = vm_dirty_bytes; unsigned long bytes = vm_dirty_bytes;
unsigned long bg_bytes = dirty_background_bytes; unsigned long bg_bytes = dirty_background_bytes;
unsigned long ratio = vm_dirty_ratio; /* convert ratios to per-PAGE_SIZE for higher precision */
unsigned long bg_ratio = dirty_background_ratio; unsigned long ratio = (vm_dirty_ratio * PAGE_SIZE) / 100;
unsigned long bg_ratio = (dirty_background_ratio * PAGE_SIZE) / 100;
unsigned long thresh; unsigned long thresh;
unsigned long bg_thresh; unsigned long bg_thresh;
struct task_struct *tsk; struct task_struct *tsk;
@ -386,26 +387,28 @@ static void domain_dirty_limits(struct dirty_throttle_control *dtc)
/* /*
* The byte settings can't be applied directly to memcg * The byte settings can't be applied directly to memcg
* domains. Convert them to ratios by scaling against * domains. Convert them to ratios by scaling against
* globally available memory. * globally available memory. As the ratios are in
* per-PAGE_SIZE, they can be obtained by dividing bytes by
* number of pages.
*/ */
if (bytes) if (bytes)
ratio = min(DIV_ROUND_UP(bytes, PAGE_SIZE) * 100 / ratio = min(DIV_ROUND_UP(bytes, global_avail),
global_avail, 100UL); PAGE_SIZE);
if (bg_bytes) if (bg_bytes)
bg_ratio = min(DIV_ROUND_UP(bg_bytes, PAGE_SIZE) * 100 / bg_ratio = min(DIV_ROUND_UP(bg_bytes, global_avail),
global_avail, 100UL); PAGE_SIZE);
bytes = bg_bytes = 0; bytes = bg_bytes = 0;
} }
if (bytes) if (bytes)
thresh = DIV_ROUND_UP(bytes, PAGE_SIZE); thresh = DIV_ROUND_UP(bytes, PAGE_SIZE);
else else
thresh = (ratio * available_memory) / 100; thresh = (ratio * available_memory) / PAGE_SIZE;
if (bg_bytes) if (bg_bytes)
bg_thresh = DIV_ROUND_UP(bg_bytes, PAGE_SIZE); bg_thresh = DIV_ROUND_UP(bg_bytes, PAGE_SIZE);
else else
bg_thresh = (bg_ratio * available_memory) / 100; bg_thresh = (bg_ratio * available_memory) / PAGE_SIZE;
if (bg_thresh >= thresh) if (bg_thresh >= thresh)
bg_thresh = thresh / 2; bg_thresh = thresh / 2;