From: Punit Agrawal <punit.agrawal@bytedance.com>
To: Barry Song <21cnbao@gmail.com>
Cc: wangkefeng.wang@huawei.com, prime.zeng@hisilicon.com,
Anshuman Khandual <anshuman.khandual@arm.com>,
linux-doc@vger.kernel.org, peterz@infradead.org,
catalin.marinas@arm.com, yangyicong@hisilicon.com,
linux-mm@kvack.org, Nadav Amit <namit@vmware.com>,
guojian@oppo.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, Mel Gorman <mgorman@suse.de>,
linux-mips@vger.kernel.org, arnd@arndb.de, realmz6@gmail.com,
Barry Song <v-songbaohua@oppo.com>,
openrisc@lists.librecores.org, darren@os.amperecomputing.com,
Punit Agrawal <punit.agrawal@bytedance.com>,
linux-arm-kernel@lists.infradead.org, xhao@linux.alibaba.com,
linux-kernel@vger.kernel.org, huzhanyuan@oppo.com,
Yicong Yang <yangyicong@huawei.com>,
akpm@linux-foundation.org, linuxppc-dev@lists.ozlabs.org
Subject: Re: [PATCH v4 2/2] arm64: support batched/deferred tlb shootdown during page reclamation
Date: Mon, 31 Oct 2022 18:36:51 +0000 [thread overview]
Message-ID: <87zgdb4z7g.fsf@stealth> (raw)
In-Reply-To: <CAGsJ_4xj2fKLOEHYC46P8ZhUPX8rw=yTNv3Zs=CPxLON6Xxvqw@mail.gmail.com> (Barry Song's message of "Sat, 29 Oct 2022 10:40:11 +1300")
Barry Song <21cnbao@gmail.com> writes:
> On Sat, Oct 29, 2022 at 2:11 AM Punit Agrawal
> <punit.agrawal@bytedance.com> wrote:
>>
>> Yicong Yang <yangyicong@huawei.com> writes:
>>
>> > On 2022/10/27 22:19, Punit Agrawal wrote:
>> >>
>> >> [ Apologies for chiming in late in the conversation ]
>> >>
>> >> Anshuman Khandual <anshuman.khandual@arm.com> writes:
>> >>
>> >>> On 9/28/22 05:53, Barry Song wrote:
>> >>>> On Tue, Sep 27, 2022 at 10:15 PM Yicong Yang <yangyicong@huawei.com> wrote:
>> >>>>>
>> >>>>> On 2022/9/27 14:16, Anshuman Khandual wrote:
>> >>>>>> [...]
>> >>>>>>
>> >>>>>> On 9/21/22 14:13, Yicong Yang wrote:
>> >>>>>>> +static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm)
>> >>>>>>> +{
>> >>>>>>> + /* for small systems with small number of CPUs, TLB shootdown is cheap */
>> >>>>>>> + if (num_online_cpus() <= 4)
>> >>>>>>
>> >>>>>> It would be great to have some more inputs from others, whether 4 (which should
>> >>>>>> to be codified into a macro e.g ARM64_NR_CPU_DEFERRED_TLB, or something similar)
>> >>>>>> is optimal for an wide range of arm64 platforms.
>> >>>>>>
>> >>>>
>> >>>> I have tested it on a 4-cpus and 8-cpus machine. but i have no machine
>> >>>> with 5,6,7
>> >>>> cores.
>> >>>> I saw improvement on 8-cpus machines and I found 4-cpus machines don't need
>> >>>> this patch.
>> >>>>
>> >>>> so it seems safe to have
>> >>>> if (num_online_cpus() < 8)
>> >>>>
>> >>>>>
>> >>>>> Do you prefer this macro to be static or make it configurable through kconfig then
>> >>>>> different platforms can make choice based on their own situations? It maybe hard to
>> >>>>> test on all the arm64 platforms.
>> >>>>
>> >>>> Maybe we can have this default enabled on machines with 8 and more cpus and
>> >>>> provide a tlbflush_batched = on or off to allow users enable or
>> >>>> disable it according
>> >>>> to their hardware and products. Similar example: rodata=on or off.
>> >>>
>> >>> No, sounds bit excessive. Kernel command line options should not be added
>> >>> for every possible run time switch options.
>> >>>
>> >>>>
>> >>>> Hi Anshuman, Will, Catalin, Andrew,
>> >>>> what do you think about this approach?
>> >>>>
>> >>>> BTW, haoxin mentioned another important user scenarios for tlb bach on arm64:
>> >>>> https://lore.kernel.org/lkml/393d6318-aa38-01ed-6ad8-f9eac89bf0fc@linux.alibaba.com/
>> >>>>
>> >>>> I do believe we need it based on the expensive cost of tlb shootdown in arm64
>> >>>> even by hardware broadcast.
>> >>>
>> >>> Alright, for now could we enable ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH selectively
>> >>> with CONFIG_EXPERT and for num_online_cpus() > 8 ?
>> >>
>> >> When running the test program in the commit in a VM, I saw benefits from
>> >> the patches at all sizes from 2, 4, 8, 32 vcpus. On the test machine,
>> >> ptep_clear_flush() went from ~1% in the unpatched version to not showing
>> >> up.
>> >>
>> >
>> > Maybe you're booting VM on a server with more than 32 cores and Barry tested
>> > on his 4 CPUs embedded platform. I guess a 4 CPU VM is not fully equivalent to
>> > a 4 CPU real machine as the tbli and dsb in the VM may influence the host
>> > as well.
>>
>> Yeah, I also wondered about this.
>>
>> I was able to test on a 6-core RK3399 based system - there the
>> ptep_clear_flush() was only 0.10% of the overall execution time. The
>> hardware seems to do a pretty good job of keeping the TLB flushing
>> overhead low.
I found a problem with my measurements (missing volatile). Correcting
that increased the overhead somewhat - more below.
> RK3399 has Dual-core ARM Cortex-A72 MPCore processor and
> Quad-core ARM Cortex-A53 MPCore processor. you are probably
> going to see different overhead of ptep_clear_flush() when you
> bind the micro-benchmark on different cores.
Indeed - binding the code on the A53 shows half the overhead from
ptep_clear_flush() compared to the A72.
On the A53 -
$ perf report --stdio -i perf.vanilla.a53.data | grep ptep_clear_flush
0.63% pageout [kernel.kallsyms] [k] ptep_clear_flush
On the A72
$ perf report --stdio -i perf.vanilla.a72.data | grep ptep_clear_flush
1.34% pageout [kernel.kallsyms] [k] ptep_clear_flush
[...]
next prev parent reply other threads:[~2022-11-06 21:15 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-21 8:43 [PATCH v4 0/2] mm: arm64: bring up BATCHED_UNMAP_TLB_FLUSH Yicong Yang
2022-09-21 8:43 ` [PATCH v4 1/2] mm/tlbbatch: Introduce arch_tlbbatch_should_defer() Yicong Yang
2022-09-21 8:54 ` Barry Song
2022-09-21 8:43 ` [PATCH v4 2/2] arm64: support batched/deferred tlb shootdown during page reclamation Yicong Yang
2022-09-27 6:16 ` Anshuman Khandual
2022-09-27 9:15 ` Yicong Yang
2022-09-28 0:23 ` Barry Song
2022-10-27 10:41 ` Anshuman Khandual
2022-10-27 14:19 ` Punit Agrawal
2022-10-27 21:55 ` Barry Song
2022-10-28 2:14 ` Anshuman Khandual
2022-10-28 13:12 ` Punit Agrawal
2022-10-28 1:20 ` Yicong Yang
2022-10-28 13:11 ` Punit Agrawal
2022-10-28 21:40 ` Barry Song
2022-10-31 18:36 ` Punit Agrawal [this message]
2022-10-27 22:07 ` Barry Song
2022-10-28 1:56 ` Anshuman Khandual
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=87zgdb4z7g.fsf@stealth \
--to=punit.agrawal@bytedance.com \
--cc=21cnbao@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=anshuman.khandual@arm.com \
--cc=arnd@arndb.de \
--cc=catalin.marinas@arm.com \
--cc=corbet@lwn.net \
--cc=darren@os.amperecomputing.com \
--cc=guojian@oppo.com \
--cc=huzhanyuan@oppo.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mips@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-riscv@lists.infradead.org \
--cc=linux-s390@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=lipeifeng@oppo.com \
--cc=mgorman@suse.de \
--cc=namit@vmware.com \
--cc=openrisc@lists.librecores.org \
--cc=peterz@infradead.org \
--cc=prime.zeng@hisilicon.com \
--cc=realmz6@gmail.com \
--cc=v-songbaohua@oppo.com \
--cc=wangkefeng.wang@huawei.com \
--cc=will@kernel.org \
--cc=x86@kernel.org \
--cc=xhao@linux.alibaba.com \
--cc=yangyicong@hisilicon.com \
--cc=yangyicong@huawei.com \
--cc=zhangshiming@oppo.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;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).