From: Matthew Wilcox <willy@infradead.org>
To: Dave Hansen <dave.hansen@intel.com>
Cc: Byungchul Park <lkml.byungchul.park@gmail.com>,
Byungchul Park <byungchul@sk.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
kernel_team@skhynix.com, akpm@linux-foundation.org,
ying.huang@intel.com, vernhao@tencent.com,
mgorman@techsingularity.net, hughd@google.com, david@redhat.com,
peterz@infradead.org, luto@kernel.org, tglx@linutronix.de,
mingo@redhat.com, bp@alien8.de, dave.hansen@linux.intel.com,
rjgolo@gmail.com
Subject: Re: [PATCH v11 09/12] mm: implement LUF(Lazy Unmap Flush) defering tlb flush when folios get unmapped
Date: Fri, 31 May 2024 23:09:46 +0100 [thread overview]
Message-ID: <ZlpKqrm7d57gmoG5@casper.infradead.org> (raw)
In-Reply-To: <f17f33e8-1c1f-460f-8c5a-713476f524a3@intel.com>
On Fri, May 31, 2024 at 02:46:23PM -0700, Dave Hansen wrote:
> On 5/31/24 11:04, Byungchul Park wrote:
> ...
> > I don't believe you do not agree with the concept itself. Thing is
> > the current version is not good enough. I will do my best by doing
> > what I can do.
>
> More performance is good. I agree with that.
>
> But it has to be weighed against the risk and the complexity. The more
> I look at this approach, the more I think this is not a good trade off.
> There's a lot of risk and a lot of complexity and we haven't seen the
> full complexity picture. The gaps are being fixed by adding complexity
> in new subsystems (the VFS in this case).
>
> There are going to be winners and losers, and this version for example
> makes file writes lose performance.
>
> Just to be crystal clear: I disagree with the concept of leaving stale
> TLB entries in place in an attempt to gain performance.
FWIW, I agree with Dave. This feels insanely dangerous and I don't
think you're paranoid enough about things that can go wrong.
next prev parent reply other threads:[~2024-05-31 22:10 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-05-31 9:19 [PATCH v11 00/12] LUF(Lazy Unmap Flush) reducing tlb numbers over 90% Byungchul Park
2024-05-31 9:19 ` [PATCH v11 01/12] x86/tlb: add APIs manipulating tlb batch's arch data Byungchul Park
2024-05-31 9:19 ` [PATCH v11 02/12] arm64: tlbflush: " Byungchul Park
2024-05-31 9:19 ` [PATCH v11 03/12] riscv, tlb: " Byungchul Park
2024-05-31 9:19 ` [PATCH v11 04/12] x86/tlb, riscv/tlb, mm/rmap: separate arch_tlbbatch_clear() out of arch_tlbbatch_flush() Byungchul Park
2024-05-31 9:19 ` [PATCH v11 05/12] mm: buddy: make room for a new variable, ugen, in struct page Byungchul Park
2024-05-31 9:19 ` [PATCH v11 06/12] mm: add folio_put_ugen() to deliver unmap generation number to pcp or buddy Byungchul Park
2024-05-31 9:19 ` [PATCH v11 07/12] mm: add a parameter, unmap generation number, to free_unref_folios() Byungchul Park
2024-05-31 9:19 ` [PATCH v11 08/12] mm/rmap: recognize read-only tlb entries during batched tlb flush Byungchul Park
2024-05-31 9:19 ` [PATCH v11 09/12] mm: implement LUF(Lazy Unmap Flush) defering tlb flush when folios get unmapped Byungchul Park
2024-05-31 16:12 ` Dave Hansen
2024-05-31 18:04 ` Byungchul Park
2024-05-31 21:46 ` Dave Hansen
2024-05-31 22:09 ` Matthew Wilcox [this message]
2024-06-01 2:20 ` Byungchul Park
2024-06-01 7:22 ` David Hildenbrand
2024-06-03 9:35 ` Byungchul Park
2024-06-03 13:23 ` Dave Hansen
2024-06-03 16:05 ` David Hildenbrand
2024-06-03 16:37 ` Dave Hansen
2024-06-03 17:01 ` Matthew Wilcox
2024-06-03 18:00 ` David Hildenbrand
2024-06-04 8:16 ` Huang, Ying
2024-06-04 0:34 ` Byungchul Park
2024-06-10 13:23 ` Michal Hocko
2024-06-11 0:55 ` Byungchul Park
2024-06-11 11:55 ` Michal Hocko
2024-06-14 2:45 ` Byungchul Park
2024-06-04 1:53 ` Byungchul Park
2024-06-04 4:43 ` Byungchul Park
2024-06-06 8:33 ` David Hildenbrand
2024-06-14 1:57 ` Byungchul Park
2024-06-11 9:12 ` Byungchul Park
2024-05-31 9:19 ` [PATCH v11 10/12] mm: separate move/undo parts from migrate_pages_batch() Byungchul Park
2024-05-31 9:20 ` [PATCH v11 11/12] mm, migrate: apply luf mechanism to unmapping during migration Byungchul Park
2024-05-31 9:20 ` [PATCH v11 12/12] mm, vmscan: apply luf mechanism to unmapping during folio reclaim Byungchul Park
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=ZlpKqrm7d57gmoG5@casper.infradead.org \
--to=willy@infradead.org \
--cc=akpm@linux-foundation.org \
--cc=bp@alien8.de \
--cc=byungchul@sk.com \
--cc=dave.hansen@intel.com \
--cc=dave.hansen@linux.intel.com \
--cc=david@redhat.com \
--cc=hughd@google.com \
--cc=kernel_team@skhynix.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lkml.byungchul.park@gmail.com \
--cc=luto@kernel.org \
--cc=mgorman@techsingularity.net \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=rjgolo@gmail.com \
--cc=tglx@linutronix.de \
--cc=vernhao@tencent.com \
--cc=ying.huang@intel.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