9 files changed, 684 insertions(+), 8 deletions(-) create mode 100644 Documentation/admin-guide/mm/damon/hugepage.rst create mode 100644 samples/damon/hugepage.c
From: Asier Gutierrez <gutierrez.asier@huawei-partners.com>
Overview
========
This patch set introduces a new autotuning which allows to collapse
hot regions into hugepages.
Motivation
==========
Since TLB is a bottleneck for many systems[1], a way to optimize TLB
misses (or hits) is to use huge pages. Unfortunately, using "always"
in THP leads to memory fragmentation and memory waste. For this reason,
most application guides and system administrators suggest to disable THP.
Currently DAMON has DAMOS_HUGEPAGE, DAMOS_NONHUGEPAGE and DAMOS_COLLAPSE.
However, there is no way to tune the settings. It will collapse all the
hot regions that meet the access pattern. If the server is a bare metal
database or big data server, this will also lead to eventual fragmentation.
Additionally, currently THP is set globally. Ideally, there should be a
way to control which tasks can use huge pages.
Solution
========
DAMON has now a way to autotune some of the variables and adjust quotas
automatically, so that DAMON is fired only under the right circumstances.
It would be nice to have something similar, but for huge pages.
A new autotuning quota goal[2], damos_get_used_hugepage_mem_bp, is
introduced, which checks the huge page consumption to total anonymous
memory consumption. This new quota mechanism reuses current autotuning
architecture.
A new module is introduced to demonstrate the use of huge pages
collapse autotuning. The goal is to collapse hot regions of a given
process into huge pages. The module launches a kdamond thread for a
certain task provided by the user through monitored_pid module argument.
Hugepage goal autotuning will automatically adjust the aggressiveness
of hot region collapses.
This module also has a user autotuning knob which allows the user to
adjust the aggressiveness of page collapsing.
Benchmarks
==========
Huge page collapse autotuning was tested in a physicial machine with
MariaDB 10.5.29 and sysbench as the benchmark framework.
The hugepage module was set up in the following way:
# echo 1000 > min_age
# echo 1000 > quota_percentage_hugepage
# echo $(pidof mariadbd) > monitored_pid
# echo on > enabled
The goal was to achieve 5% of the total memory used as hugepage.
The table below shows the memory consumption over time. Gaps in the
timestamp means that no changes in the hugepage consumption happened
over that period of time.
+-----------+----------------+----------------+----------------------+
| timestamp | total mem used | huge page used | percentage hugepage |
+-----------+----------------+----------------+----------------------+
| 0 | 4721188 | 0 | 0% |
| 28 | 4216848 | 4 | 0% |
| 37 | 4189912 | 38912 | 1% |
| 39 | 4195188 | 47104 | 1% |
| 55 | 4111612 | 51200 | 1% |
| 59 | 4137012 | 53248 | 1% |
| 60 | 4137052 | 55296 | 1% |
| 61 | 4156832 | 57344 | 1% |
| 62 | 4136920 | 59392 | 1% |
| 64 | 4109872 | 61440 | 1% |
| 65 | 4119108 | 63488 | 2% |
| 66 | 4145532 | 65536 | 2% |
| 67 | 4134544 | 67584 | 2% |
| 68 | 4158244 | 126976 | 3% |
| 69 | 4124276 | 204800 | 5% |
| 70 | 4100680 | 333824 | 8% |
| 71 | 4095540 | 462848 | 11% |
+-----------+----------------+----------------+----------------------+
Performance:
Baseline -> 18,162.45 transactions per second
Hugepage autotune -> 18,211.82 transactions per second
Eventually, the amount of huge pages reached 20%. This is consistent
with how quota goals autotuning work. We are more aggresive when the
quota is less than 10%, and less aggresive when the quota is higher.
At some point, the aggressiveness just fades and no more collapses
occur.
TODO
====
- Support page splitting for cold hugepages.
Patches Sequence
================
Patch 1 -> Introduce DAMOS_QUOTA_HUGEPAGE and autotuning
Patch 2 -> damon_modules_new_vaddr_ctx_target
Patch 3 -> Module that demonstrates how to use DAMOS_QUOTA_HUGEPAGE
and the new VADDR ctx creation
Patch 4 -> Documentation
Changes from previous versions
==============================
RFC 2[3] -> RFC 3
- Module moved to samples
- Change autotune to monitor total memory and hugepage
- Added performnace benchmarks to the cover letter
- Bail out gracefully when trying to start disable
the module after the monitored task exited. This
issue was discovered by sashiko [4]
- Fixed typos and added quota_sz to the documentation
discovered by sashiko [5]
RFC 1[6] -> RFC 2
- Rebased into mm-new
- Use DAMOS_COLLAPSE instead of DAMOS_HUGEPAGE
- Fixed an issue that returned silently an error when the PID
didn't exist in the system.[7]
[1] https://dl.acm.org/doi/pdf/10.1145/3307650.3322227
[2] https://lore.kernel.org/e67f05ad-dbb9-45e6-ba30-b167a99ac67d@huawei-partners.com
[3] https://lore.kernel.org/20260522145518.158910-1-gutierrez.asier@huawei-partners.com
[4] https://lore.kernel.org/20260522171210.900B11F00A3D@smtp.kernel.org
[5] https://lore.kernel.org/20260522171633.AAF5B1F000E9@smtp.kernel.org
[6] https://lore.kernel.org/20260430134139.2446417-1-gutierrez.asier@huawei-partners.com
[7] https://lore.kernel.org/all/20260430154338.E22E6C2BCB3@smtp.kernel.org/
Asier Gutierrez (4):
mm/damon: Generalize ctx_target creation for damon_ops_id and add vaddr support
mm/damon: Introduce DAMOS_QUOTA_HUGEPAGE auto tuning
mm/damon: introduce DAMON_HUGEPAGE for hot region hugepage collapsing
Documentation/admin-guide/mm/damon: add DAMON-based Hugepage Management documentation
Asier Gutierrez (4):
Introduce DAMOS_QUOTA_HUGEPAGE auto tuning Add a new DAMOS quota goal
metric to measure the amount of huge page consumption to total
anonymous memory consumption ratio.
This patch adds a new function damon_modules_new_vaddr_ctx_target.
Since ctx_target creation for vaddr and paddr is almost identical,
the logic is extracted to a new function,
damon_modules_new_ctx_target, and vaddr and paddr functions are left
just as interfaces.
This patch introduces a new DAMON module (SAMPLE_DAMON_HUGEPAGE) which
collapses hot regions into huge pages.
Add documentation for the DAMON-based Hugepage Management
(DAMON_HUGEPAGE) feature, which automatically manages huge pages by
identifying hot memory regions and collapsing them back to regular
pages. The documentation covers the module's features, operation,
and all available module parameters.
.../admin-guide/mm/damon/hugepage.rst (new) | 271 ++++++++++++++
include/linux/damon.h | 1 +
mm/damon/Makefile | 8 +-
mm/damon/core.c | 14 +
mm/damon/modules-common.c | 31 +-
mm/damon/modules-common.h | 3 +
samples/damon/Kconfig | 12 +
samples/damon/Makefile | 2 +
samples/damon/hugepage.c (new) | 350 ++++++++++++++++++
9 files changed, 684 insertions(+), 8 deletions(-)
create mode 100644 Documentation/admin-guide/mm/damon/hugepage.rst
create mode 100644 samples/damon/hugepage.c
--
2.43.0
Hello Asier, Thank you for revisioning this great patch! On Thu, 4 Jun 2026 15:03:33 +0000 <gutierrez.asier@huawei-partners.com> wrote: > From: Asier Gutierrez <gutierrez.asier@huawei-partners.com> > > Overview > ======== > > This patch set introduces a new autotuning which allows to collapse > hot regions into hugepages. > > Motivation > ========== > > Since TLB is a bottleneck for many systems[1], a way to optimize TLB > misses (or hits) is to use huge pages. Unfortunately, using "always" > in THP leads to memory fragmentation and memory waste. For this reason, > most application guides and system administrators suggest to disable THP. > > Currently DAMON has DAMOS_HUGEPAGE, DAMOS_NONHUGEPAGE and DAMOS_COLLAPSE. > However, there is no way to tune the settings. It will collapse all the > hot regions that meet the access pattern. If the server is a bare metal > database or big data server, this will also lead to eventual fragmentation. > > Additionally, currently THP is set globally. Ideally, there should be a > way to control which tasks can use huge pages. We can do process level control using prctl(PR_SET_THP_DISABLE) [1], isn't it? I think the last above sentence is better to be reworded or simply dropped. > > Solution > ======== > > DAMON has now a way to autotune some of the variables and adjust quotas > automatically, so that DAMON is fired only under the right circumstances. > It would be nice to have something similar, but for huge pages. > > A new autotuning quota goal[2], damos_get_used_hugepage_mem_bp, is > introduced, which checks the huge page consumption to total anonymous In the previous revision I suggested to s/damos_get_used_hugepage_mem_bp/damos_hugepage_mem_bp/ and you agreed. Seems it was forgotten? > memory consumption. This new quota mechanism reuses current autotuning > architecture. > > A new module is introduced to demonstrate the use of huge pages Let's clarify it is a sample module. That is, s/A new module/A new sample module/ ? > collapse autotuning. The goal is to collapse hot regions of a given > process into huge pages. The module launches a kdamond thread for a > certain task provided by the user through monitored_pid module argument. Following other vaddr based sample modues' pattern, what about s/monitored_pid/target_pid/ ? As I also commented on the third patch of this series, apparently it is not following the sample modules' pattern but that for non-sample modules. Could you please rewrite in a more simple way? > Hugepage goal autotuning will automatically adjust the aggressiveness > of hot region collapses. > > This module also has a user autotuning knob which allows the user to > adjust the aggressiveness of page collapsing. > > Benchmarks > ========== > > Huge page collapse autotuning was tested in a physicial machine with > MariaDB 10.5.29 and sysbench as the benchmark framework. > > The hugepage module was set up in the following way: > > # echo 1000 > min_age > # echo 1000 > quota_percentage_hugepage > # echo $(pidof mariadbd) > monitored_pid > # echo on > enabled > > The goal was to achieve 5% of the total memory used as hugepage. Any reason to set it 5% ? > > The table below shows the memory consumption over time. Gaps in the > timestamp means that no changes in the hugepage consumption happened > over that period of time. > > +-----------+----------------+----------------+----------------------+ > | timestamp | total mem used | huge page used | percentage hugepage | > +-----------+----------------+----------------+----------------------+ > | 0 | 4721188 | 0 | 0% | > | 28 | 4216848 | 4 | 0% | > | 37 | 4189912 | 38912 | 1% | > | 39 | 4195188 | 47104 | 1% | > | 55 | 4111612 | 51200 | 1% | > | 59 | 4137012 | 53248 | 1% | > | 60 | 4137052 | 55296 | 1% | > | 61 | 4156832 | 57344 | 1% | > | 62 | 4136920 | 59392 | 1% | > | 64 | 4109872 | 61440 | 1% | > | 65 | 4119108 | 63488 | 2% | > | 66 | 4145532 | 65536 | 2% | > | 67 | 4134544 | 67584 | 2% | > | 68 | 4158244 | 126976 | 3% | > | 69 | 4124276 | 204800 | 5% | > | 70 | 4100680 | 333824 | 8% | > | 71 | 4095540 | 462848 | 11% | > +-----------+----------------+----------------+----------------------+ What is the timestamp unit? Second? What is the mem used unit? Byytes? Kiloboytes? I also remember you mentioned you will compare the numbers for more setups including module disabled case (baseline) and THP disabled case. I think "THP disabled" case was my typo. Maybe I wanted to say "THP enabled" case. Is that still on your TODO list? Given this series is adding relatively small change (assuming the sample module will be simplified), I wouldn't strictly request all such tests. I'm just curious about your plan. > > Performance: > Baseline -> 18,162.45 transactions per second > Hugepage autotune -> 18,211.82 transactions per second So, 2.7% improvement! I think it is not bad for this simple approach. Could you further elaborate how the performance is measured? From when the transactions per second measurement is started, and when it was stopped? Are the numbers average? Mean? Or something else? > > > Eventually, the amount of huge pages reached 20%. This is consistent > with how quota goals autotuning work. We are more aggresive when the > quota is less than 10%, and less aggresive when the quota is higher. > At some point, the aggressiveness just fades and no more collapses > occur. Could you share more hugepage utilization change for long term that captures it converges to 20% but after that doesn't increase more? Also, have you tried temporal quota tuner? > > TODO > ==== > - Support page splitting for cold hugepages. This is a future work out of the scope of this series, right? I think that is better to be clarified. In the previous revision, I was reading this as a TODO for a future revision of this patch series. Also, do you have specific changes you want to make to this series before it is merged, or dropping the RFC tag? > > Patches Sequence > ================ > Patch 1 -> Introduce DAMOS_QUOTA_HUGEPAGE and autotuning > Patch 2 -> damon_modules_new_vaddr_ctx_target > Patch 3 -> Module that demonstrates how to use DAMOS_QUOTA_HUGEPAGE > and the new VADDR ctx creation > Patch 4 -> Documentation As I commented to each patch, patch 1 looks good except a few trivial things. Patch 2 seems unnecessary. I hope patch 3 to be much simplified and wrote again following the sample modules' pattern. Patch 4 seems too much for a sample module. > > Changes from previous versions > ============================== > RFC 2[3] -> RFC 3 > - Module moved to samples > - Change autotune to monitor total memory and hugepage > - Added performnace benchmarks to the cover letter > - Bail out gracefully when trying to start disable > the module after the monitored task exited. This > issue was discovered by sashiko [4] > - Fixed typos and added quota_sz to the documentation > discovered by sashiko [5] > RFC 1[6] -> RFC 2 > - Rebased into mm-new > - Use DAMOS_COLLAPSE instead of DAMOS_HUGEPAGE > - Fixed an issue that returned silently an error when the PID > didn't exist in the system.[7] Thank you for continuing this great work, Asier. > > [1] https://dl.acm.org/doi/pdf/10.1145/3307650.3322227 > [2] https://lore.kernel.org/e67f05ad-dbb9-45e6-ba30-b167a99ac67d@huawei-partners.com > [3] https://lore.kernel.org/20260522145518.158910-1-gutierrez.asier@huawei-partners.com > [4] https://lore.kernel.org/20260522171210.900B11F00A3D@smtp.kernel.org > [5] https://lore.kernel.org/20260522171633.AAF5B1F000E9@smtp.kernel.org > [6] https://lore.kernel.org/20260430134139.2446417-1-gutierrez.asier@huawei-partners.com > [7] https://lore.kernel.org/all/20260430154338.E22E6C2BCB3@smtp.kernel.org/ Thanks, SJ [...]
Hi SJ, On 6/5/2026 4:34 AM, SeongJae Park wrote: > Hello Asier, > > > Thank you for revisioning this great patch! > > On Thu, 4 Jun 2026 15:03:33 +0000 <gutierrez.asier@huawei-partners.com> wrote: > >> From: Asier Gutierrez <gutierrez.asier@huawei-partners.com> >> >> Overview >> ======== >> >> This patch set introduces a new autotuning which allows to collapse >> hot regions into hugepages. >> >> Motivation >> ========== >> >> Since TLB is a bottleneck for many systems[1], a way to optimize TLB >> misses (or hits) is to use huge pages. Unfortunately, using "always" >> in THP leads to memory fragmentation and memory waste. For this reason, >> most application guides and system administrators suggest to disable THP. >> >> Currently DAMON has DAMOS_HUGEPAGE, DAMOS_NONHUGEPAGE and DAMOS_COLLAPSE. >> However, there is no way to tune the settings. It will collapse all the >> hot regions that meet the access pattern. If the server is a bare metal >> database or big data server, this will also lead to eventual fragmentation. >> >> Additionally, currently THP is set globally. Ideally, there should be a >> way to control which tasks can use huge pages. > > We can do process level control using prctl(PR_SET_THP_DISABLE) [1], isn't it? > I think the last above sentence is better to be reworded or simply dropped. Yes, although you will not disable it for all the processes except onein the system. I will reword it to make it more clear. >> >> Solution >> ======== >> >> DAMON has now a way to autotune some of the variables and adjust quotas >> automatically, so that DAMON is fired only under the right circumstances. >> It would be nice to have something similar, but for huge pages. >> >> A new autotuning quota goal[2], damos_get_used_hugepage_mem_bp, is >> introduced, which checks the huge page consumption to total anonymous > > In the previous revision I suggested to > s/damos_get_used_hugepage_mem_bp/damos_hugepage_mem_bp/ and you agreed. Seems > it was forgotten? Actually, I changed the code to damos_hugepage_mem_bp. I forgot to update the cover letter. Will do it for the next RFC version. >> memory consumption. This new quota mechanism reuses current autotuning >> architecture. >> >> A new module is introduced to demonstrate the use of huge pages > > Let's clarify it is a sample module. That is, > s/A new module/A new sample module/ ? Right, I will update the cover letter. >> collapse autotuning. The goal is to collapse hot regions of a given >> process into huge pages. The module launches a kdamond thread for a >> certain task provided by the user through monitored_pid module argument. > > Following other vaddr based sample modues' pattern, what about > s/monitored_pid/target_pid/ ? Makes sense. I will change it. > > As I also commented on the third patch of this series, apparently it is not > following the sample modules' pattern but that for non-sample modules. Could > you please rewrite in a more simple way? OK, I will remove a lot of the module parameters. I'll use the prcl.c as an example. >> Hugepage goal autotuning will automatically adjust the aggressiveness >> of hot region collapses. >> >> This module also has a user autotuning knob which allows the user to >> adjust the aggressiveness of page collapsing. >> >> Benchmarks >> ========== >> >> Huge page collapse autotuning was tested in a physicial machine with >> MariaDB 10.5.29 and sysbench as the benchmark framework. >> >> The hugepage module was set up in the following way: >> >> # echo 1000 > min_age >> # echo 1000 > quota_percentage_hugepage >> # echo $(pidof mariadbd) > monitored_pid >> # echo on > enabled >> >> The goal was to achieve 5% of the total memory used as hugepage. > > Any reason to set it 5% ? The database was not particularly big. This means that I set the target too high, it may never reach it. Not all the database is hot, actually. I will make it more clear in the following cover letters >> >> The table below shows the memory consumption over time. Gaps in the >> timestamp means that no changes in the hugepage consumption happened >> over that period of time. >> >> +-----------+----------------+----------------+----------------------+ >> | timestamp | total mem used | huge page used | percentage hugepage | >> +-----------+----------------+----------------+----------------------+ >> | 0 | 4721188 | 0 | 0% | >> | 28 | 4216848 | 4 | 0% | >> | 37 | 4189912 | 38912 | 1% | >> | 39 | 4195188 | 47104 | 1% | >> | 55 | 4111612 | 51200 | 1% | >> | 59 | 4137012 | 53248 | 1% | >> | 60 | 4137052 | 55296 | 1% | >> | 61 | 4156832 | 57344 | 1% | >> | 62 | 4136920 | 59392 | 1% | >> | 64 | 4109872 | 61440 | 1% | >> | 65 | 4119108 | 63488 | 2% | >> | 66 | 4145532 | 65536 | 2% | >> | 67 | 4134544 | 67584 | 2% | >> | 68 | 4158244 | 126976 | 3% | >> | 69 | 4124276 | 204800 | 5% | >> | 70 | 4100680 | 333824 | 8% | >> | 71 | 4095540 | 462848 | 11% | >> +-----------+----------------+----------------+----------------------+ > > What is the timestamp unit? Second? > > What is the mem used unit? Byytes? Kiloboytes? > > I also remember you mentioned you will compare the numbers for more setups > including module disabled case (baseline) and THP disabled case. I think "THP > disabled" case was my typo. Maybe I wanted to say "THP enabled" case. > > Is that still on your TODO list? > > Given this series is adding relatively small change (assuming the sample module > will be simplified), I wouldn't strictly request all such tests. I'm just > curious about your plan. > >> >> Performance: >> Baseline -> 18,162.45 transactions per second >> Hugepage autotune -> 18,211.82 transactions per second > > So, 2.7% improvement! I think it is not bad for this simple approach. > > Could you further elaborate how the performance is measured? From when the > transactions per second measurement is started, and when it was stopped? Are > the numbers average? Mean? Or something else? > >> >> >> Eventually, the amount of huge pages reached 20%. This is consistent >> with how quota goals autotuning work. We are more aggresive when the >> quota is less than 10%, and less aggresive when the quota is higher. >> At some point, the aggressiveness just fades and no more collapses >> occur. > > Could you share more hugepage utilization change for long term that captures it > converges to 20% but after that doesn't increase more? Correct. > Also, have you tried temporal quota tuner? OK, I will give it try. >> >> TODO >> ==== >> - Support page splitting for cold hugepages. > > This is a future work out of the scope of this series, right? I think that is > better to be clarified. In the previous revision, I was reading this as a TODO > for a future revision of this patch series. > > Also, do you have specific changes you want to make to this series before it is > merged, or dropping the RFC tag? > >> >> Patches Sequence >> ================ >> Patch 1 -> Introduce DAMOS_QUOTA_HUGEPAGE and autotuning >> Patch 2 -> damon_modules_new_vaddr_ctx_target >> Patch 3 -> Module that demonstrates how to use DAMOS_QUOTA_HUGEPAGE >> and the new VADDR ctx creation >> Patch 4 -> Documentation > > As I commented to each patch, patch 1 looks good except a few trivial things. > Patch 2 seems unnecessary. I hope patch 3 to be much simplified and wrote > again following the sample modules' pattern. Patch 4 seems too much for a > sample module. Thanks for the feedback, I will work out the patches. >> >> Changes from previous versions >> ============================== >> RFC 2[3] -> RFC 3 >> - Module moved to samples >> - Change autotune to monitor total memory and hugepage >> - Added performnace benchmarks to the cover letter >> - Bail out gracefully when trying to start disable >> the module after the monitored task exited. This >> issue was discovered by sashiko [4] >> - Fixed typos and added quota_sz to the documentation >> discovered by sashiko [5] >> RFC 1[6] -> RFC 2 >> - Rebased into mm-new >> - Use DAMOS_COLLAPSE instead of DAMOS_HUGEPAGE >> - Fixed an issue that returned silently an error when the PID >> didn't exist in the system.[7] > > Thank you for continuing this great work, Asier. > >> >> [1] https://dl.acm.org/doi/pdf/10.1145/3307650.3322227 >> [2] https://lore.kernel.org/e67f05ad-dbb9-45e6-ba30-b167a99ac67d@huawei-partners.com >> [3] https://lore.kernel.org/20260522145518.158910-1-gutierrez.asier@huawei-partners.com >> [4] https://lore.kernel.org/20260522171210.900B11F00A3D@smtp.kernel.org >> [5] https://lore.kernel.org/20260522171633.AAF5B1F000E9@smtp.kernel.org >> [6] https://lore.kernel.org/20260430134139.2446417-1-gutierrez.asier@huawei-partners.com >> [7] https://lore.kernel.org/all/20260430154338.E22E6C2BCB3@smtp.kernel.org/ > > > Thanks, > SJ > > [...] > -- Asier Gutierrez Huawei
On Fri, 5 Jun 2026 13:25:56 +0300 Gutierrez Asier <gutierrez.asier@huawei-partners.com> wrote: > Hi SJ, > > On 6/5/2026 4:34 AM, SeongJae Park wrote: > > Hello Asier, > > > > > > Thank you for revisioning this great patch! > > > > On Thu, 4 Jun 2026 15:03:33 +0000 <gutierrez.asier@huawei-partners.com> wrote: [...] > >> Benchmarks > >> ========== [...] > > Also, have you tried temporal quota tuner? > > OK, I will give it try. Sounds good! These test results are great contributions for DAMON community. Nonetheless I don't think those are blocker of this series. You could run more tests and share results even after this series is merged first if you want to. [...] > >> Patches Sequence > >> ================ > >> Patch 1 -> Introduce DAMOS_QUOTA_HUGEPAGE and autotuning > >> Patch 2 -> damon_modules_new_vaddr_ctx_target > >> Patch 3 -> Module that demonstrates how to use DAMOS_QUOTA_HUGEPAGE > >> and the new VADDR ctx creation > >> Patch 4 -> Documentation > > > > As I commented to each patch, patch 1 looks good except a few trivial things. > > Patch 2 seems unnecessary. I hope patch 3 to be much simplified and wrote > > again following the sample modules' pattern. Patch 4 seems too much for a > > sample module. > Thanks for the feedback, I will work out the patches. I have a trivial comment about the 32-bit overflow issue, but everythinng except that look good to me. I feel like we are going on the right direction and this series is getting closer to land! Thanks, SJ [...]
© 2016 - 2026 Red Hat, Inc.