Message-ID: <9ccc6d6b-c077-4b8a-b8da-99cabf182e17@linux.alibaba.com>
Date: Wed, 3 Sep 2025 11:27:54 +0800
From: Baolin Wang <baolin.wang@...ux.alibaba.com>
To: Usama Arif <usamaarif642@...il.com>, David Hildenbrand
 <david@...hat.com>, Dev Jain <dev.jain@....com>,
 Lorenzo Stoakes <lorenzo.stoakes@...cle.com>
Cc: Nico Pache <npache@...hat.com>, linux-mm@...ck.org,
 linux-doc@...r.kernel.org, linux-kernel@...r.kernel.org,
 linux-trace-kernel@...r.kernel.org, ziy@...dia.com, Liam.Howlett@...cle.com,
 ryan.roberts@....com, corbet@....net, rostedt@...dmis.org,
 mhiramat@...nel.org, mathieu.desnoyers@...icios.com,
 akpm@...ux-foundation.org, baohua@...nel.org, willy@...radead.org,
 peterx@...hat.com, wangkefeng.wang@...wei.com, sunnanyong@...wei.com,
 vishal.moola@...il.com, thomas.hellstrom@...ux.intel.com,
 yang@...amperecomputing.com, kirill.shutemov@...ux.intel.com,
 aarcange@...hat.com, raquini@...hat.com, anshuman.khandual@....com,
 catalin.marinas@....com, tiwai@...e.de, will@...nel.org,
 dave.hansen@...ux.intel.com, jack@...e.cz, cl@...two.org,
 jglisse@...gle.com, surenb@...gle.com, zokeefe@...gle.com,
 hannes@...xchg.org, rientjes@...gle.com, mhocko@...e.com,
 rdunlap@...radead.org, hughd@...gle.com
Subject: Re: [PATCH v10 00/13] khugepaged: mTHP support



On 2025/9/3 04:23, Usama Arif wrote:
> 
> 
> On 02/09/2025 12:03, David Hildenbrand wrote:
>> On 02.09.25 12:34, Usama Arif wrote:
>>>
>>>
>>> On 02/09/2025 10:03, David Hildenbrand wrote:
>>>> On 02.09.25 04:28, Baolin Wang wrote:
>>>>>
>>>>>
>>>>> On 2025/9/2 00:46, David Hildenbrand wrote:
>>>>>> On 29.08.25 03:55, Baolin Wang wrote:
>>>>>>>
>>>>>>>
>>>>>>> On 2025/8/28 18:48, Dev Jain wrote:
>>>>>>>>
>>>>>>>> On 28/08/25 3:16 pm, Baolin Wang wrote:
>>>>>>>>> (Sorry for chiming in late)
>>>>>>>>>
>>>>>>>>> On 2025/8/22 22:10, David Hildenbrand wrote:
>>>>>>>>>>>> Once could also easily support the value 255 (HPAGE_PMD_NR / 2- 1),
>>>>>>>>>>>> but not sure
>>>>>>>>>>>> if we have to add that for now.
>>>>>>>>>>>
>>>>>>>>>>> Yeah not so sure about this, this is a 'just have to know' too, and
>>>>>>>>>>> yes you
>>>>>>>>>>> might add it to the docs, but people are going to be mightily
>>>>>>>>>>> confused, esp if
>>>>>>>>>>> it's a calculated value.
>>>>>>>>>>>
>>>>>>>>>>> I don't see any other way around having a separate tunable if we
>>>>>>>>>>> don't just have
>>>>>>>>>>> something VERY simple like on/off.
>>>>>>>>>>
>>>>>>>>>> Yeah, not advocating that we add support for other values than 0/511,
>>>>>>>>>> really.
>>>>>>>>>>
>>>>>>>>>>>
>>>>>>>>>>> Also the mentioned issue sounds like something that needs to be
>>>>>>>>>>> fixed elsewhere
>>>>>>>>>>> honestly in the algorithm used to figure out mTHP ranges (I may be
>>>>>>>>>>> wrong - and
>>>>>>>>>>> happy to stand corrected if this is somehow inherent, but reallly
>>>>>>>>>>> feels that
>>>>>>>>>>> way).
>>>>>>>>>>
>>>>>>>>>> I think the creep is unavoidable for certain values.
>>>>>>>>>>
>>>>>>>>>> If you have the first two pages of a PMD area populated, and you
>>>>>>>>>> allow for at least half of the #PTEs to be non/zero, you'd collapse
>>>>>>>>>> first a
>>>>>>>>>> order-2 folio, then and order-3 ... until you reached PMD order.
>>>>>>>>>>
>>>>>>>>>> So for now we really should just support 0 / 511 to say "don't
>>>>>>>>>> collapse if there are holes" vs. "always collapse if there is at
>>>>>>>>>> least one pte used".
>>>>>>>>>
>>>>>>>>> If we only allow setting 0 or 511, as Nico mentioned before, "At 511,
>>>>>>>>> no mTHP collapses would ever occur anyway, unless you have 2MB
>>>>>>>>> disabled and other mTHP sizes enabled. Technically, at 511, only the
>>>>>>>>> highest enabled order would ever be collapsed."
>>>>>>>> I didn't understand this statement. At 511, mTHP collapses will occur if
>>>>>>>> khugepaged cannot get a PMD folio. Our goal is to collapse to the
>>>>>>>> highest order folio.
>>>>>>>
>>>>>>> Yes, I’m not saying that it’s incorrect behavior when set to 511. What I
>>>>>>> mean is, as in the example I gave below, users may only want to allow a
>>>>>>> large order collapse when the number of present PTEs reaches half of the
>>>>>>> large folio, in order to avoid RSS bloat.
>>>>>>
>>>>>> How do these users control allocation at fault time where this parameter
>>>>>> is completely ignored?
>>>>>
>>>>> Sorry, I did not get your point. Why does the 'max_pte_none' need to
>>>>> control allocation at fault time? Could you be more specific? Thanks.
>>>>
>>>> The comment over khugepaged_max_ptes_none gives a hint:
>>>>
>>>> /*
>>>>    * default collapse hugepages if there is at least one pte mapped like
>>>>    * it would have happened if the vma was large enough during page
>>>>    * fault.
>>>>    *
>>>>    * Note that these are only respected if collapse was initiated by khugepaged.
>>>>    */
>>>>
>>>> In the common case (for anything that really cares about RSS bloat) you will just a
>>>> get a THP during page fault and consequently RSS bloat.
>>>>
>>>> As raised in my other reply, the only documented reason to set max_ptes_none=0 seems
>>>> to be when an application later (after once possibly getting a THP already during
>>>> page faults) did some MADV_DONTNEED and wants to control the usage of THPs itself using
>>>> MADV_COLLAPSE.
>>>>
>>>> It's a questionable use case, that already got more problematic with mTHP and page
>>>> table reclaim.
>>>>
>>>> Let me explain:
>>>>
>>>> Before mTHP, if someone would MADV_DONTNEED (resulting in
>>>> a page table with at least one pte_none entry), there would have been no way we would
>>>> get memory over-allocated afterwards with max_ptes_none=0.
>>>>
>>>> (1) Page faults would spot "there is a page table" and just fallback to order-0 pages.
>>>> (2) khugepaged was told to not collapse through max_ptes_none=0.
>>>>
>>>> But now:
>>>>
>>>> (A) With mTHP during page-faults, we can just end up over-allocating memory in such
>>>>       an area again: page faults will simply spot a bunch of pte_nones around the fault area
>>>>       and install an mTHP.
>>>>
>>>> (B) With page table reclaim (when zapping all PTEs in a table at once), we will reclaim the
>>>>       page table. The next page fault will just try installing a PMD THP again, because there is
>>>>       no PTE table anymore.
>>>>
>>>> So I question the utility of max_ptes_none. If you can't tame page faults, then there is only
>>>> limited sense in taming khugepaged. I think there is vale in setting max_ptes_none=0 for some
>>>> corner cases, but I am yet to learn why max_ptes_none=123 would make any sense.

Thanks David for your explanation. I see your point now.

>>> For PMD mapped THPs with THP shrinker, this has changed. You can basically tame pagefaults, as when you encounter
>>> memory pressure, the shrinker kicks in if the value is less than HPAGE_PMD_NR -1 (i.e. 511 for x86), and
>>> will break down those hugepages and free up zero-filled memory.
>>
>> You are not really taming page faults, though, you are undoing what page faults might have messed up :)
>>
>> I have seen in our prod workloads where
>>> the memory usage and THP usage can spike (usually when the workload starts), but with memory pressure,
>>> the memory usage is lower compared to with max_ptes_none = 511, while still still keeping the benefits
>>> of THPs like lower TLB misses.
>>
>> Thanks for raising that: I think the current behavior is in place such that you don't bounce back-and-forth between khugepaged collapse and shrinker-split.
>>
> 
> Yes, both collapse and shrinker split hinge on max_ptes_none to prevent one of these things thrashing the effect of the other.
> 
>> There are likely other ways to achieve that, when we have in mind that the thp shrinker will install zero pages and max_ptes_none includes
>> zero pages.
>>
>>>
>>> I do agree that the value of max_ptes_none is magical and different workloads can react very differently
>>> to it. The relationship is definitely not linear. i.e. if I use max_ptes_none = 256, it does not mean
>>> that the memory regression of using THP=always vs THP=madvise is halved.
>>
>> To which value would you set it? Just 510? 0?
>>
> 
> There are some very large workloads in the meta fleet that I experimented with and found that having
> a small value works out. I experimented with 0, 51 (10%) and 256 (50%). 51 was found to be an optimal
> comprimise in terms of application metrics improving, having an acceptable amount of memory regression and
> improved system level metrics (lower TLB misses, lower page faults). I am sure there was a better value out
> there for these workloads, but not possible to experiment with every value.
> 
> In terms of wider rollout across the fleet, we are going to target 0 (or a very very small value)
> when moving from THP=madvise to always. Mainly because it is the least likely to cause a memory regression as
> THP shrinker will deal with page faults faulting in mostly zero-filled pages and khugepaged wont collapse
> pages that are dominated by 4K zero-filled chunks.

Thanks for sharing this. We're also investigating what max_ptes_none 
should be set to in order to use the THP shrinker properly, and 
currently, our customers always set max_ptes_none to its default value: 
511, which is not good.

If 0 is better, it seems like there isn't much conflict with the values 
expected by mTHP collapse (0 and 511). Sounds good to me.

Powered by blists - more mailing lists