Re: [RFC PATCH v3 0/4] mm: enable lru cache for smaller large folios

[Garg, Shivank]

On Sat, 2026-09-12 at 05:20 +0800, Barry Song wrote:
> On Fri, Sep 11, 2026 at 11:39 PM Garg, Shivank <shivankg@xxxxxxx> wrote:
> [...]
> > 
> > Thanks for this series.
> > I tested this against a Graph500 regression with 16K mTHP.
> > The series removes the regression and reduces folio_lruvec_lock_irqsave contention to approximately the 4K rate.
> > 
> > 
> > Tested-by: Shivank Garg <shivankg@xxxxxxx>
> > 
> 
> Thanks very much, Shivank. I’m very happy to see that
> mTHP LRUCACHE not only resolves your regression but also
> improves the performance of your case.
> 
> As discussed with David, this series will be respun after Hugh’s
> work[1] is merged.
> 
> In the meantime, I’d really appreciate it if you could test an
> updated version that I haven’t sent out before:
> 
> https://git.kernel.org/pub/scm/linux/kernel/git/baohua/linux.git/log/?h=mthp_lrucache
> 
> It includes some modifications based on Sashiko’s review comments
> on the version you tested. I’d like to know whether it still provides
> the same performance gains you saw with that version.
> 
> [1] https://lore.kernel.org/linux-mm/e28f9a94-4339-f8ac-8301-6be3c9b5b7ce@xxxxxxxxxx/
> 

I tested this branch.

  Base:     4b65683fd ("mm/swap, PM: hibernate: atomically replace
            hibernation pin")
  Patched (Base+series):  5dfdf87ee (branch tip, the 4 lru_cache patches)

                       Base              Patched           reduction
    4K            839281   2.30 m      842435   2.91 m    
    mTHP-16K     7032797  28.79 m      839301   4.53 m    8.4x / 6.4x
    mTHP-64K      267948   1.19 s       36073  93.48 ms   7.4x / 12.7x

Numbers are almost unchanged, except some run-to-run variations.

Thanks
Shivank


> > 
> > System and Workload
> > ===================
> > 
> > AMD EPYC Zen 5 System, 2 sockets, 160 cores/socket,
> > SMT on -> 320 cores / 640 threads
> > 2 NUMA nodes, ~512 GB/node
> > node 0 CPUs: 0-159,320-479
> > 
> > Base: v7.3-rc2+ (50d05c7c76c9)
> > Runtime: performance governor, preempt=full (lazy)
> > 
> > Workload: Graph500, Scale 27, edgefactor 16
> > Metric: median_time in ms (lower is better)
> > 
> > Bind to node 0 with numactl -C 0-159,320-479 -m 0
> > 
> > 
> > Performance
> > ===========
> > 
> >                   Base       Patched    delta
> > 4K                109.60     109.11     -0.4%
> > mTHP-16K          144.10      99.00    -31.3%
> > mTHP-64K          104.75     104.25     -0.5%
> > 
> > mTHP-16K was ~31% slower than THP-never, due to lock contentions.
> > With your series, mTHP-16 performs ~9% faster than THP-never.
> > 
> > 
> > The dominant folio_lruvec_lock_irqsave entries were:
> > 
> >                    Base                  Patched
> >                contended  wait         contended  wait
> > 4K               834603   2.41 m         844193   2.61 m
> > mTHP-16K        7008834   28.88 m        840695   4.87 m
> > mTHP-64K         188144   752 ms         40874    93.46 ms
> > 
> > 
>