linux-kernel - Re: [BUG] mm, thp: khugepaged can't allocate on requested node when confined to a cpuset

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Fri, 10 Oct 2014 23:57:09 +0200
From:	Vlastimil Babka <vbabka@...e.cz>
To:	Alex Thorlton <athorlton@....com>,
	Peter Zijlstra <peterz@...radead.org>
CC:	linux-kernel@...r.kernel.org,
	Andrew Morton <akpm@...ux-foundation.org>,
	Mel Gorman <mgorman@...e.de>, Rik van Riel <riel@...hat.com>,
	Ingo Molnar <mingo@...nel.org>,
	"Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>,
	Hugh Dickins <hughd@...gle.com>, Bob Liu <lliubbo@...il.com>,
	Johannes Weiner <hannes@...xchg.org>, linux-mm@...ck.org
Subject: Re: [BUG] mm, thp: khugepaged can't allocate on requested node when
 confined to a cpuset

On 10.10.2014 20:56, Alex Thorlton wrote:
> On Fri, Oct 10, 2014 at 11:20:52AM +0200, Peter Zijlstra wrote:
>> So for the numa thing we do everything from the affected tasks context.
>> There was a lot of arguments early on that that could never really work,
>> but here we are.
>>
>> Should we convert khugepaged to the same? Drive the whole thing from
>> task_work? That would make this issue naturally go away.

Mel was suggesting to me few weeks ago that this would be desirable and 
I was
planning to look at this soonish. But if you volunteer, great :)

> If we move the compaction scan over to a task_work style function, we'll
> only be able to scan the one task's mm at a time.  While the underlying
> compaction infrastructure can function more or less the same, the timing
> of when these scans occur, and exactly what the scans cover, will have
> to change.  If we go for the most rudimentary approach, the scans will
> occur each time a thread is about to return to userland after faulting
> in a THP (we'll just replace the khugepaged_enter call with a

I don't understand the motivation of doing this after "faulting in a 
THP"? If you already
have a THP then maybe it's useful to scan for more candidates for a THP, 
but why
would a THP fault be the trigger?

> task_work_add), and will cover the mm for the current task.  A slightly
> more advanced approach would involve a timer to ensure that scans don't
> occur too often, as is currently handled by

Maybe not a timer, but just a timestamp of last scan and the "wait time" 
to compare
against current timestamp. The wait time could be extended and reduced 
based on
how successful the scanner was in the recent past (somewhat similar to the
deferred compaction mechanism).

> khugepaged_scan_sleep_millisecs. In any case, I don't see a way around
> the fact that we'll lose the multi-mm scanning functionality our
> khugepaged_scan list provides, but maybe that's not a huge issue.

It should be actually a benefit, as you can tune the scanning frequency 
per mm,
to avoid useless scaning (see above) and also you don't scan tasks that 
are sleeping
at all.

> Before I run off and start writing patches, here's a brief summary of
> what I think we could do here:
>
> 1) Dissolve the khugepaged thread and related structs/timers (I'm
>     expecting some backlash on this one).
> 2) Replace khugepged_enter calls with calls to task_work_add(work,
>     our_new_scan_function) - new scan function will look almost exactly
>     like khugepaged_scan_mm_slot.
> 3) Set up a timer similar to khugepaged_scan_sleep_millisecs that gets
>     checked during/before our_new_scan_function to ensure that we're not
>     scanning more often than necessary.  Also, set up progress markers to
>     limit the number of pages scanned in a single pass.

Hm tuning the "number of pages in single pass" could be another way to 
change
the scanning frequency based on recent history.

> By doing this, scans will get triggered each time a thread that has
> faulted THPs is about to return to userland execution, throttled by our
> new timer/progress indicators.  The major benefit here is that scans
> will now occur in the desired task's context.
>
> Let me know if you anybody sees any major flaws in this approach.

Hm I haven't seen the code yet, but is perhaps the NUMA scanning working
similarly enough that a single scanner could handle both the NUMA and THP
bits to save time?

Vlastimil

> Thanks a lot for your input, Peter!
>
> - Alex
>

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/