Re: [linus:master] [mm] f822a9a81a: stress-ng.bigheap.realloc_calls_per_sec 37.3% regression

[Lorenzo Stoakes <lorenzo.stoakes@oracle.com>]

On Thu, Aug 07, 2025 at 11:20:13PM +0530, Dev Jain wrote:
>
> On 07/08/25 11:16 pm, Jann Horn wrote:
> > On Thu, Aug 7, 2025 at 7:41 PM Lorenzo Stoakes
> > <lorenzo.stoakes@oracle.com> wrote:
> > > On Thu, Aug 07, 2025 at 07:37:38PM +0200, Jann Horn wrote:
> > > > On Thu, Aug 7, 2025 at 10:28 AM Lorenzo Stoakes
> > > > <lorenzo.stoakes@oracle.com> wrote:
> > > > > On Thu, Aug 07, 2025 at 04:17:09PM +0800, kernel test robot wrote:
> > > > > > 94dab12d86cf77ff f822a9a81a31311d67f260aea96
> > > > > > ---------------- ---------------------------
> > > > > >           %stddev     %change         %stddev
> > > > > >               \          |                \
> > > > > >       13777 ą 37%     +45.0%      19979 ą 27%  numa-vmstat.node1.nr_slab_reclaimable
> > > > > >      367205            +2.3%     375703        vmstat.system.in
> > > > > >       55106 ą 37%     +45.1%      79971 ą 27%  numa-meminfo.node1.KReclaimable
> > > > > >       55106 ą 37%     +45.1%      79971 ą 27%  numa-meminfo.node1.SReclaimable
> > > > > >      559381           -37.3%     350757        stress-ng.bigheap.realloc_calls_per_sec
> > > > > >       11468            +1.2%      11603        stress-ng.time.system_time
> > > > > >      296.25            +4.5%     309.70        stress-ng.time.user_time
> > > > > >        0.81 ą187%    -100.0%       0.00        perf-sched.sch_delay.avg.ms.__cond_resched.zap_pte_range.zap_pmd_range.isra.0
> > > > > >        9.36 ą165%    -100.0%       0.00        perf-sched.sch_delay.max.ms.__cond_resched.zap_pte_range.zap_pmd_range.isra.0
> > > > > >        0.81 ą187%    -100.0%       0.00        perf-sched.wait_time.avg.ms.__cond_resched.zap_pte_range.zap_pmd_range.isra.0
> > > > > >        9.36 ą165%    -100.0%       0.00        perf-sched.wait_time.max.ms.__cond_resched.zap_pte_range.zap_pmd_range.isra.0
> > > > > >        5.50 ą 17%    +390.9%      27.00 ą 56%  perf-c2c.DRAM.local
> > > > > >      388.50 ą 10%    +114.7%     834.17 ą 33%  perf-c2c.DRAM.remote
> > > > > >        1214 ą 13%    +107.3%       2517 ą 31%  perf-c2c.HITM.local
> > > > > >      135.00 ą 19%    +130.9%     311.67 ą 32%  perf-c2c.HITM.remote
> > > > > >        1349 ą 13%    +109.6%       2829 ą 31%  perf-c2c.HITM.total
> > > > > Yeah this also looks pretty consistent too...
> > > > FWIW, HITM hat different meanings depending on exactly which
> > > > microarchitecture that test happened on; the message says it is from
> > > > Sapphire Rapids, which is a successor of Ice Lake, so HITM is less
> > > > meaningful than if it came from a pre-IceLake system (see
> > > > https://lore.kernel.org/all/CAG48ez3RmV6SsVw9oyTXxQXHp3rqtKDk2qwJWo9TGvXCq7Xr-w@mail.gmail.com/).
> > > >
> > > > To me those numbers mainly look like you're accessing a lot more
> > > > cache-cold data. (On pre-IceLake they would indicate cacheline
> > > > bouncing, but I guess here they probably don't.) And that makes sense,
> > > > since before the patch, this path was just moving PTEs around without
> > > > looking at the associated pages/folios; basically more or less like a
> > > > memcpy() on x86-64. But after the patch, for every 8 bytes that you
> > > > copy, you have to load a cacheline from the vmemmap to get the page.
> > > Yup this is representative of what my investigation is showing.
> > >
> > > I've narrowed it down but want to wait to report until I'm sure...
> > >
> > > But yeah we're doing a _lot_ more work.
> > >
> > > I'm leaning towards disabling except for arm64 atm tbh, seems mremap is
> > > especially sensitive to this (I found issues with this with my abortive mremap
> > > anon merging stuff too, but really expected it there...)
> > Another approach would be to always read and write PTEs in
> > contpte-sized chunks here, without caring whether they're actually
> > contiguous or whatever, or something along those lines.
>
> The initial approach was to wrap all of this around pte_batch_hint(),
> effectively making the optimization only on arm64. I guess that sounds
> reasonable now.
>

I wish people would just wait for me to finish checking this on my box...

Anyway, as with Jann's point, I have empirical evidence to support that yes
it's the folio lookup that's the issue.

I also was thinking exactly to try this hint thing and to see.

Let me try...