[PATCH 6.1 59/71] blk-wbt: Fix detection of dirty-throttled tasks

From: Sasha Levin
Date: Wed Mar 13 2024 - 13:17:24 EST


From: Jan Kara <jack@xxxxxxx>

[ Upstream commit f814bdda774c183b0cc15ec8f3b6e7c6f4527ba5 ]

The detection of dirty-throttled tasks in blk-wbt has been subtly broken
since its beginning in 2016. Namely if we are doing cgroup writeback and
the throttled task is not in the root cgroup, balance_dirty_pages() will
set dirty_sleep for the non-root bdi_writeback structure. However
blk-wbt checks dirty_sleep only in the root cgroup bdi_writeback
structure. Thus detection of recently throttled tasks is not working in
this case (we noticed this when we switched to cgroup v2 and suddently
writeback was slow).

Since blk-wbt has no easy way to get to proper bdi_writeback and
furthermore its intention has always been to work on the whole device
rather than on individual cgroups, just move the dirty_sleep timestamp
from bdi_writeback to backing_dev_info. That fixes the checking for
recently throttled task and saves memory for everybody as a bonus.

CC: stable@xxxxxxxxxxxxxxx
Fixes: b57d74aff9ab ("writeback: track if we're sleeping on progress in balance_dirty_pages()")
Signed-off-by: Jan Kara <jack@xxxxxxx>
Link: https://lore.kernel.org/r/20240123175826.21452-1-jack@xxxxxxx
[axboe: fixup indentation errors]
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
block/blk-wbt.c | 4 ++--
include/linux/backing-dev-defs.h | 7 +++++--
mm/backing-dev.c | 2 +-
mm/page-writeback.c | 2 +-
4 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index e9206b1406e76..fcacdff8af93b 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -98,9 +98,9 @@ static void wb_timestamp(struct rq_wb *rwb, unsigned long *var)
*/
static bool wb_recent_wait(struct rq_wb *rwb)
{
- struct bdi_writeback *wb = &rwb->rqos.disk->bdi->wb;
+ struct backing_dev_info *bdi = rwb->rqos.disk->bdi;

- return time_before(jiffies, wb->dirty_sleep + HZ);
+ return time_before(jiffies, bdi->last_bdp_sleep + HZ);
}

static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb,
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index ae12696ec492c..2ad261082bba5 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -141,8 +141,6 @@ struct bdi_writeback {
struct delayed_work dwork; /* work item used for writeback */
struct delayed_work bw_dwork; /* work item used for bandwidth estimate */

- unsigned long dirty_sleep; /* last wait */
-
struct list_head bdi_node; /* anchored at bdi->wb_list */

#ifdef CONFIG_CGROUP_WRITEBACK
@@ -179,6 +177,11 @@ struct backing_dev_info {
* any dirty wbs, which is depended upon by bdi_has_dirty().
*/
atomic_long_t tot_write_bandwidth;
+ /*
+ * Jiffies when last process was dirty throttled on this bdi. Used by
+ * blk-wbt.
+ */
+ unsigned long last_bdp_sleep;

struct bdi_writeback wb; /* the root writeback info for this bdi */
struct list_head wb_list; /* list of all wbs */
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index bf5525c2e561a..c070ff9ef9cf3 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -305,7 +305,6 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
INIT_LIST_HEAD(&wb->work_list);
INIT_DELAYED_WORK(&wb->dwork, wb_workfn);
INIT_DELAYED_WORK(&wb->bw_dwork, wb_update_bandwidth_workfn);
- wb->dirty_sleep = jiffies;

err = fprop_local_init_percpu(&wb->completions, gfp);
if (err)
@@ -793,6 +792,7 @@ int bdi_init(struct backing_dev_info *bdi)
INIT_LIST_HEAD(&bdi->bdi_list);
INIT_LIST_HEAD(&bdi->wb_list);
init_waitqueue_head(&bdi->wb_waitq);
+ bdi->last_bdp_sleep = jiffies;

return cgwb_bdi_init(bdi);
}
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index d3e9d12860b9f..9046d1f1b408e 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1809,7 +1809,7 @@ static int balance_dirty_pages(struct bdi_writeback *wb,
break;
}
__set_current_state(TASK_KILLABLE);
- wb->dirty_sleep = now;
+ bdi->last_bdp_sleep = jiffies;
io_schedule_timeout(pause);

current->dirty_paused_when = now + pause;
--
2.43.0