From: Punit Agrawal <punit.agrawal@bytedance•com>
To: Yicong Yang <yangyicong@huawei•com>
Cc: wangkefeng.wang@huawei•com, prime.zeng@hisilicon•com,
realmz6@gmail•com, linux-doc@vger•kernel.org,
peterz@infradead•org, catalin.marinas@arm•com,
linux-kernel@vger•kernel.org, linux-mm@kvack•org,
punit.agrawal@bytedance•com, linux-riscv@lists•infradead.org,
will@kernel•org, linux-s390@vger•kernel.org,
zhangshiming@oppo•com, lipeifeng@oppo•com, corbet@lwn•net,
x86@kernel•org, Barry Song <21cnbao@gmail•com>,
arnd@arndb•de, anshuman.khandual@arm•com,
openrisc@lists•librecores.org, darren@os•amperecomputing.com,
yangyicong@hisilicon•com, linux-arm-kernel@lists•infradead.org,
guojian@oppo•com, xhao@linux•alibaba.com,
linux-mips@vger•kernel.org, huzhanyuan@oppo•com,
akpm@linux-foundation•org, linuxppc-dev@lists•ozlabs.org
Subject: Re: [External] [PATCH v5 0/2] arm64: support batched/deferred tlb shootdown during page reclamation
Date: Fri, 11 Nov 2022 10:17:09 +0000 [thread overview]
Message-ID: <87pmdtztga.fsf@stealth> (raw)
In-Reply-To: <20221028081255.19157-1-yangyicong@huawei.com> (Yicong Yang's message of "Fri, 28 Oct 2022 16:12:53 +0800")
Yicong Yang <yangyicong@huawei•com> writes:
> From: Yicong Yang <yangyicong@hisilicon•com>
>
> Though ARM64 has the hardware to do tlb shootdown, the hardware
> broadcasting is not free.
> A simplest micro benchmark shows even on snapdragon 888 with only
> 8 cores, the overhead for ptep_clear_flush is huge even for paging
> out one page mapped by only one process:
> 5.36% a.out [kernel.kallsyms] [k] ptep_clear_flush
>
> While pages are mapped by multiple processes or HW has more CPUs,
> the cost should become even higher due to the bad scalability of
> tlb shootdown.
>
> The same benchmark can result in 16.99% CPU consumption on ARM64
> server with around 100 cores according to Yicong's test on patch
> 4/4.
>
> This patchset leverages the existing BATCHED_UNMAP_TLB_FLUSH by
> 1. only send tlbi instructions in the first stage -
> arch_tlbbatch_add_mm()
> 2. wait for the completion of tlbi by dsb while doing tlbbatch
> sync in arch_tlbbatch_flush()
> Testing on snapdragon shows the overhead of ptep_clear_flush
> is removed by the patchset. The micro benchmark becomes 5% faster
> even for one page mapped by single process on snapdragon 888.
>
> With this support we're possible to do more optimization for memory
> reclamation and migration[*].
I applied the patches on v6.1-rc4 and was able to see the drop in
ptep_clear_flush() in the perf report when running the test program from
Patch 2. The tests were done on a rk3399 based system with benefits
visible when running the tests on either of the clusters.
So, for the series,
Tested-by: Punit Agrawal <punit.agrawal@bytedance•com>
Thanks,
Punit
[...]
prev parent reply other threads:[~2022-11-11 10:18 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-10-28 8:12 [PATCH v5 0/2] arm64: support batched/deferred tlb shootdown during page reclamation Yicong Yang
2022-10-28 8:12 ` [PATCH v5 1/2] mm/tlbbatch: Introduce arch_tlbbatch_should_defer() Yicong Yang
2022-10-28 8:12 ` [PATCH v5 2/2] arm64: support batched/deferred tlb shootdown during page reclamation Yicong Yang
2022-11-14 3:29 ` Anshuman Khandual
2022-11-14 8:46 ` Yicong Yang
2022-11-14 14:19 ` Anshuman Khandual
2022-11-15 3:34 ` Yicong Yang
2022-11-14 8:00 ` haoxin
2022-11-11 10:17 ` Punit Agrawal [this message]
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=87pmdtztga.fsf@stealth \
--to=punit.agrawal@bytedance$(echo .)com \
--cc=21cnbao@gmail$(echo .)com \
--cc=akpm@linux-foundation$(echo .)org \
--cc=anshuman.khandual@arm$(echo .)com \
--cc=arnd@arndb$(echo .)de \
--cc=catalin.marinas@arm$(echo .)com \
--cc=corbet@lwn$(echo .)net \
--cc=darren@os$(echo .)amperecomputing.com \
--cc=guojian@oppo$(echo .)com \
--cc=huzhanyuan@oppo$(echo .)com \
--cc=linux-arm-kernel@lists$(echo .)infradead.org \
--cc=linux-doc@vger$(echo .)kernel.org \
--cc=linux-kernel@vger$(echo .)kernel.org \
--cc=linux-mips@vger$(echo .)kernel.org \
--cc=linux-mm@kvack$(echo .)org \
--cc=linux-riscv@lists$(echo .)infradead.org \
--cc=linux-s390@vger$(echo .)kernel.org \
--cc=linuxppc-dev@lists$(echo .)ozlabs.org \
--cc=lipeifeng@oppo$(echo .)com \
--cc=openrisc@lists$(echo .)librecores.org \
--cc=peterz@infradead$(echo .)org \
--cc=prime.zeng@hisilicon$(echo .)com \
--cc=realmz6@gmail$(echo .)com \
--cc=wangkefeng.wang@huawei$(echo .)com \
--cc=will@kernel$(echo .)org \
--cc=x86@kernel$(echo .)org \
--cc=xhao@linux$(echo .)alibaba.com \
--cc=yangyicong@hisilicon$(echo .)com \
--cc=yangyicong@huawei$(echo .)com \
--cc=zhangshiming@oppo$(echo .)com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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