[RFC PATCH 0/2] mm/damon/stat: expose auto-tuned intervals and non-idle ages

SeongJae Park posted 2 patches 3 weeks, 1 day ago
There is a newer version of this series
mm/damon/stat.c | 16 +++++++++++-----
1 file changed, 11 insertions(+), 5 deletions(-)
[RFC PATCH 0/2] mm/damon/stat: expose auto-tuned intervals and non-idle ages
Posted by SeongJae Park 3 weeks, 1 day ago
DAMON_STAT is intentionally providing limited information for easy
consumption.  From production fleet level usages, below limitations are
found, though.

The aggregation interval of DAMON_STAT represents the granularity of the
memory_idle_ms_percentiles.  But it is auto-tuned and not exposed to
users, so users cannot know the granularity.

All memory regions of non-zero (positive) nr_accesses are treated as
having zero idle time.  A significant portion of production systems have
such zero idle time.  Hence breakdown of warm and hot data is
impossible.

To overcome the limitations, expose the auto-tuned aggregation interval
with a new parameter named xxx and the age of non-zero nr_accesses
regions as negative idle time, via the existing idle time percentiles
parameter.

SeongJae Park (2):
  mm/damon/stat: expose the current tuned aggregation interval
  mm/damon/stat: expose negative idle time

 mm/damon/stat.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)


base-commit: adc22cc8eb821b7d8274403ad7bdafb411fcc9d7
-- 
2.39.5
Re: [RFC PATCH 0/2] mm/damon/stat: expose auto-tuned intervals and non-idle ages
Posted by SeongJae Park 2 weeks, 6 days ago
On Tue,  9 Sep 2025 21:00:20 -0700 SeongJae Park <sj@kernel.org> wrote:

> DAMON_STAT is intentionally providing limited information for easy
> consumption.  From production fleet level usages, below limitations are
> found, though.
> 
> The aggregation interval of DAMON_STAT represents the granularity of the
> memory_idle_ms_percentiles.  But it is auto-tuned and not exposed to
> users, so users cannot know the granularity.
> 
> All memory regions of non-zero (positive) nr_accesses are treated as
> having zero idle time.  A significant portion of production systems have
> such zero idle time.  Hence breakdown of warm and hot data is
> impossible.
> 
> To overcome the limitations, expose the auto-tuned aggregation interval
> with a new parameter named xxx and the age of non-zero nr_accesses

s/xx/aggr_interval_us/

Forgot updating that before posting, sorry.  The next version should fix it.


Thanks,
SJ

[...]