Commit eead0056 authored by Yu Kuai's avatar Yu Kuai Committed by Jens Axboe

blk-throttle: consider 'carryover_ios/bytes' in throtl_trim_slice()

Currently, 'carryover_ios/bytes' is not handled in throtl_trim_slice(),
for consequence, 'carryover_ios/bytes' will be used to throttle bio
multiple times, for example:

1) set iops limit to 100, and slice start is 0, slice end is 100ms;
2) current time is 0, and 10 ios are dispatched, those io won't be
   throttled and io_disp is 10;
3) still at current time 0, update iops limit to 1000, carryover_ios is
   updated to (0 - 10) = -10;
4) in this slice(0 - 100ms), io_allowed = 100 + (-10) = 90, which means
   only 90 ios can be dispatched without waiting;
5) assume that io is throttled in slice(0 - 100ms), and
   throtl_trim_slice() update silce to (100ms - 200ms). In this case,
   'carryover_ios/bytes' is not cleared and still only 90 ios can be
   dispatched between 100ms - 200ms.

Fix this problem by updating 'carryover_ios/bytes' in
throtl_trim_slice().

Fixes: a880ae93 ("blk-throttle: fix io hung due to configuration updates")
Reported-by: default avatarzhuxiaohui <zhuxiaohui.400@bytedance.com>
Link: https://lore.kernel.org/all/20230812072116.42321-1-zhuxiaohui.400@bytedance.com/Signed-off-by: default avatarYu Kuai <yukuai3@huawei.com>
Acked-by: default avatarTejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20230816012708.1193747-5-yukuai1@huaweicloud.comSigned-off-by: default avatarJens Axboe <axboe@kernel.dk>
parent e8368b57
...@@ -729,8 +729,9 @@ static u64 calculate_bytes_allowed(u64 bps_limit, unsigned long jiffy_elapsed) ...@@ -729,8 +729,9 @@ static u64 calculate_bytes_allowed(u64 bps_limit, unsigned long jiffy_elapsed)
/* Trim the used slices and adjust slice start accordingly */ /* Trim the used slices and adjust slice start accordingly */
static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw) static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)
{ {
unsigned long time_elapsed, io_trim; unsigned long time_elapsed;
u64 bytes_trim; long long bytes_trim;
int io_trim;
BUG_ON(time_before(tg->slice_end[rw], tg->slice_start[rw])); BUG_ON(time_before(tg->slice_end[rw], tg->slice_start[rw]));
...@@ -758,17 +759,21 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw) ...@@ -758,17 +759,21 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)
return; return;
bytes_trim = calculate_bytes_allowed(tg_bps_limit(tg, rw), bytes_trim = calculate_bytes_allowed(tg_bps_limit(tg, rw),
time_elapsed); time_elapsed) +
io_trim = calculate_io_allowed(tg_iops_limit(tg, rw), time_elapsed); tg->carryover_bytes[rw];
if (!bytes_trim && !io_trim) io_trim = calculate_io_allowed(tg_iops_limit(tg, rw), time_elapsed) +
tg->carryover_ios[rw];
if (bytes_trim <= 0 && io_trim <= 0)
return; return;
if (tg->bytes_disp[rw] >= bytes_trim) tg->carryover_bytes[rw] = 0;
if ((long long)tg->bytes_disp[rw] >= bytes_trim)
tg->bytes_disp[rw] -= bytes_trim; tg->bytes_disp[rw] -= bytes_trim;
else else
tg->bytes_disp[rw] = 0; tg->bytes_disp[rw] = 0;
if (tg->io_disp[rw] >= io_trim) tg->carryover_ios[rw] = 0;
if ((int)tg->io_disp[rw] >= io_trim)
tg->io_disp[rw] -= io_trim; tg->io_disp[rw] -= io_trim;
else else
tg->io_disp[rw] = 0; tg->io_disp[rw] = 0;
...@@ -776,7 +781,7 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw) ...@@ -776,7 +781,7 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)
tg->slice_start[rw] += time_elapsed; tg->slice_start[rw] += time_elapsed;
throtl_log(&tg->service_queue, throtl_log(&tg->service_queue,
"[%c] trim slice nr=%lu bytes=%llu io=%lu start=%lu end=%lu jiffies=%lu", "[%c] trim slice nr=%lu bytes=%lld io=%d start=%lu end=%lu jiffies=%lu",
rw == READ ? 'R' : 'W', time_elapsed / tg->td->throtl_slice, rw == READ ? 'R' : 'W', time_elapsed / tg->td->throtl_slice,
bytes_trim, io_trim, tg->slice_start[rw], tg->slice_end[rw], bytes_trim, io_trim, tg->slice_start[rw], tg->slice_end[rw],
jiffies); jiffies);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment