On 6/17/21 9:30 AM, Charan Teja Kalla wrote:

Thanks Vlastimil for your inputs!!

On 6/16/2021 5:29 PM, Vlastimil Babka wrote:

quoted

quoted

This triggering of proactive compaction is done on a write to
sysctl.compaction_proactiveness by user.

[1]https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit?id=facdaa917c4d5a376d09d25865f5a863f906234a

Signed-off-by: Charan Teja Reddy <redacted>
---
changes in V2:

You forgot to also summarize the changes. Please do in next version.

I think we can get rid off 'proactive_defer' thread variable with the
timeout approach you suggested. But it is still requires to have one
additional variable 'proactive_compact_trigger', which main purpose is
to decide if the kcompactd wakeup is for proactive compaction or not.
Please see below code:
   if (wait_event_freezable_timeout() && !proactive_compact_trigger) {
	// do the non-proactive work
	continue
   }
   // do the proactive work
     .................

Thus I feel that on writing new proactiveness, it is required to do
wakeup_kcomppactd() + set a flag that this wakeup is for proactive work.

Am I failed to get your point here?

The check whether to do non-proactive work is already guarded by
kcompactd_work_requested(), which looks at pgdat->kcompactd_max_order and this
is set by wakeup_kcompactd().

So with a plain wakeup where we don't set pgdat->kcompactd_max_order will make
it consider proactive work instead and we don't need another trigger variable
AFAICS.