Linux-mm Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Zhang Peng <zippermonkey@icloud.com>
To: "Barry Song (Xiaomi)" <baohua@kernel.org>
Cc: akpm@linux-foundation.org, axelrasmussen@google.com,
	 baolin.wang@linux.alibaba.com, baoquan.he@linux.dev,
	bruzzhang@tencent.com, david@kernel.org,  hannes@cmpxchg.org,
	kasong@tencent.com, linux-kernel@vger.kernel.org,
	 linux-mm@kvack.org, ljs@kernel.org, mhocko@kernel.org,
	qi.zheng@linux.dev,  shakeel.butt@linux.dev, weixugc@google.com,
	yuanchu@google.com
Subject: Re: [PATCH v6 0/5] mm: batch TLB flushing for dirty folios in vmscan
Date: Mon, 16 Nov 2026 21:00:15 +0800	[thread overview]
Message-ID: <avr8QDO3CPyCoipF@lima-kernel-dev> (raw)
In-Reply-To: <20261115230231.21194-1-baohua@kernel.org>

On Mon, Nov 16, 2026 at 07:02:31AM +0800, Barry Song (Xiaomi) wrote:
> On Sat, Oct 31, 2026 at 6:35 PM Zhang Peng <zippermonkey@icloud.com> wrote:
> >
> > This series introduces batch TLB flushing optimization for dirty folios
> > during memory reclaim, aiming to reduce IPI overhead on multi-core systems.
> >
> > Background
> > ----------
> > Reclaim calls try_to_unmap_flush_dirty() before writing out each dirty
> > folio. When writable TLB entries are pending, this triggers a flush.
> > On systems that use IPIs for TLB shootdowns, frequent flushes can add
> > significant overhead.
> >
> > Approach
> > --------
> > Collect dirty folios into a folio_batch, releasing their locks while
> > collecting the batch so swap faults can progress. Before writeout, try
> > locking each folio again and recheck writeback, mappings and DMA pins.
> > Keep eligible folios locked, flush pending writable TLB entries once,
> > then page them out. Process a final partial batch at the end of the scan.
> >
> > Changes
> > -------
> > Patch 1: Extract the folio activation block at activate_locked into
> >          folio_activate_locked().
> > Patch 2: Extract the folio-freeing path (buffer release, lazyfree,
> >          __remove_mapping, folio_batch drain) into folio_try_reclaim_free().
> >          Group retained folios, deferred frees and the reclaimed count
> >          in reclaim_folio_state, local to each shrink_folio_list() call.
> > Patch 3: Extract the pageout() dispatch state machine into folio_try_pageout().
> > Patch 4: Extract the TTU setup and try_to_unmap() block into folio_try_unmap().
> > Patch 5: Implement batch TLB flushing logic. Dirty folios are accumulated in
> >          batches and a single TLB flush is performed for each batch before
> >          calling pageout.
> >
> > Testing
> > -------
> > The benchmark script uses stress-ng to compare TLB shootdown behavior before and
> > after this patch. It constrains a stress-ng workload via memcg to force reclaim
> > through shrink_folio_list(), reporting TLB shootdowns and IPIs.
> >
> > Core benchmark command: stress-ng --vm 16 --vm-bytes 2G --vm-keep --timeout 60
> >
> > ==========================================================================
> >                  batch_dirty_tlb_flush Benchmark Results
> > ==========================================================================
> >   Kernel: 7.0.0-rc1+   CPUs: 16
> >   MemTotal: 31834M   SwapTotal: 8191M
> >   memcg limit: 512M   alloc: 2G   workers: 16   duration: 60s
> > --------------------------------------------------------------------------
> > Metric                 Before        After             Delta (abs / %)
> > --------------------------------------------------------------------------
> > bogo ops/s             28238.63      35833.97          +7595.34 (+26.9%)
> > TLB shootdowns         55428953      17621697          -37807256 (-68.2%)
> > Function call IPIs     34073695      14498768          -19574927 (-57.4%)
> > pgscan_anon (pages)    52856224      60252894          7396670 (+14.0%)
> > pgsteal_anon (pages)   29004962      34054753          5049791 (+17.4%)
> > --------------------------------------------------------------------------
> >
> > Suggested-by: Kairui Song <kasong@tencent.com>
> > Signed-off-by: Zhang Peng <bruzzhang@tencent.com>
> > ---
> 
> Hi Peng,
> 
> Just a quick update: this patch is still on my radar. I ran a
> quick perf test while building the kernel. Without your patch,
> try_to_unmap_flush_dirty() accounted for 1.75% of CPU cycles.
> 
> I guess there could be workloads where try_to_unmap_flush_dirty()
> accounts for an even larger share of CPU cycles.
> 
> # Children      Self  Command  Shared Object      Symbol                      
> # ........  ........  .......  .................  ............................
> #
> 
>      1.75%     0.01%  cc1              [kernel.kallsyms]  [.] try_to_unmap_flush_dirty
>             |          
>              --1.74%--try_to_unmap_flush_dirty
>                        try_to_unmap_flush (inlined)
>                        |          
>                         --1.73%--arch_tlbbatch_flush
>                                   |          
>                                    --1.70%--flush_tlb_multi (inlined)
>                                              __flush_tlb_multi (inlined)
>                                              |          
>                                               --1.69%--native_flush_tlb_multi
>                                                         |          
>                                                          --1.68%--on_each_cpu_cond_mask
>                                                                    |          
>                                                                     --1.62%--smp_call_function_many_cond
>                                                                               |          
>                                                                                --1.23%--csd_lock_wait (inlined)
> 
> 
> With your patch, the CPU overhead drops by roughly 7x:
> 
> 
> # Children      Self  Command  Shared Object      Symbol                      
> # ........  ........  .......  .................  ............................
> #
>      0.25%     0.00%  cc1      [kernel.kallsyms]  [.] try_to_unmap_flush_dirty
>             |          
>              --0.24%--try_to_unmap_flush_dirty
>                        try_to_unmap_flush (inlined)
>                        |          
>                         --0.24%--arch_tlbbatch_flush
>                                   |          
>                                    --0.24%--flush_tlb_multi (inlined)
>                                              __flush_tlb_multi (inlined)
>                                              |          
>                                               --0.24%--native_flush_tlb_multi
>                                                         |          
>                                                          --0.23%--on_each_cpu_cond_mask
>                                                                    |          
>                                                                     --0.21%--smp_call_function_many_cond
>                                                                               |          
>                                                                                --0.14%--csd_lock_wait (inlined)
> 
>      0.00%     0.00%  fixdep   [kernel.kallsyms]  [.] try_to_unmap_flush_dirty
> 
> 
> Overall, I think this is a good approach. I'll be traveling soon
> and will return to this patchset for more testing and a thorough
> review in about two and a half weeks.
> 
> Thanks
> Barry
> 
Hi Barry,

Thanks for the update and for taking the time to run the perf test.
The breakdown is helpful, and it's encouraging to see that
try_to_unmap_flush_dirty() accounts for a significant share of the
cycles in shrink_folio_list().

Safe travels!

Thanks,
Peng



  parent reply	other threads:[~2026-11-16 13:00 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-10-31 10:35 [PATCH v6 0/5] mm: batch TLB flushing for dirty folios in vmscan Zhang Peng
2026-10-31 10:35 ` [PATCH v6 1/5] mm/vmscan: introduce folio_activate_locked() helper Zhang Peng
2026-10-31 10:35 ` [PATCH v6 2/5] mm/vmscan: extract folio reclaim freeing from shrink_folio_list() Zhang Peng
2026-10-31 10:35 ` [PATCH v6 3/5] mm/vmscan: extract folio pageout " Zhang Peng
2026-10-31 10:35 ` [PATCH v6 4/5] mm/vmscan: extract folio unmap logic into folio_try_unmap() Zhang Peng
2026-10-31 10:35 ` [PATCH v6 5/5] mm/vmscan: batch dirty TLB flushes before pageout Zhang Peng
2026-11-01  2:51   ` sashiko-bot
2026-11-15 23:02 ` [PATCH v6 0/5] mm: batch TLB flushing for dirty folios in vmscan Barry Song (Xiaomi)
2026-11-15 23:27   ` Barry Song
2026-11-16 13:00   ` Zhang Peng [this message]
2026-11-16 12:10 ` David Hildenbrand (Arm)
2026-11-16 12:47   ` Zhang Peng

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=avr8QDO3CPyCoipF@lima-kernel-dev \
    --to=zippermonkey@icloud.com \
    --cc=akpm@linux-foundation.org \
    --cc=axelrasmussen@google.com \
    --cc=baohua@kernel.org \
    --cc=baolin.wang@linux.alibaba.com \
    --cc=baoquan.he@linux.dev \
    --cc=bruzzhang@tencent.com \
    --cc=david@kernel.org \
    --cc=hannes@cmpxchg.org \
    --cc=kasong@tencent.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=ljs@kernel.org \
    --cc=mhocko@kernel.org \
    --cc=qi.zheng@linux.dev \
    --cc=shakeel.butt@linux.dev \
    --cc=weixugc@google.com \
    --cc=yuanchu@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox