Files
linux/lib
Yu Kuai 42e6c6ce03 lib/sbitmap: convert shallow_depth from one word to the whole sbitmap
Currently elevators will record internal 'async_depth' to throttle
asynchronous requests, and they both calculate shallow_dpeth based on
sb->shift, with the respect that sb->shift is the available tags in one
word.

However, sb->shift is not the availbale tags in the last word, see
__map_depth:

if (index == sb->map_nr - 1)
  return sb->depth - (index << sb->shift);

For consequence, if the last word is used, more tags can be get than
expected, for example, assume nr_requests=256 and there are four words,
in the worst case if user set nr_requests=32, then the first word is
the last word, and still use bits per word, which is 64, to calculate
async_depth is wrong.

One the ohter hand, due to cgroup qos, bfq can allow only one request
to be allocated, and set shallow_dpeth=1 will still allow the number
of words request to be allocated.

Fix this problems by using shallow_depth to the whole sbitmap instead
of per word, also change kyber, mq-deadline and bfq to follow this,
a new helper __map_depth_with_shallow() is introduced to calculate
available bits in each word.

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20250807032413.1469456-2-yukuai1@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2025-08-07 06:30:17 -06:00
..
2024-12-12 18:26:32 +01:00
2025-03-16 22:30:49 -07:00
2025-04-11 17:32:38 -07:00
2025-04-11 17:32:37 -07:00
2024-07-12 16:39:53 -07:00
2024-02-01 13:06:40 +01:00
2023-02-02 22:50:01 -08:00
2023-02-02 22:50:01 -08:00
2025-05-15 20:24:40 +02:00
2025-03-25 10:18:31 -03:00
2025-01-12 20:21:15 -08:00
2025-06-30 09:31:57 -07:00
2025-01-14 19:45:35 +01:00
2024-10-14 16:33:24 -05:00
2023-10-16 12:44:06 -04:00
2025-03-17 12:17:00 -07:00
2025-05-11 17:54:04 -07:00
2024-02-15 12:17:28 -05:00
2025-03-25 10:18:31 -03:00
2024-12-09 13:48:29 -08:00