From: Yu Zhao <yuzhao@google.com>
To: Prarit Bhargava <prarit@redhat.com>,
Justin Forbes <jforbes@fedoraproject.org>
Cc: "Andi Kleen" <ak@linux.intel.com>,
kernel-team@lists.ubuntu.com,
"Vaibhav Jain" <vaibhav@linux.ibm.com>,
"Rik van Riel" <riel@surriel.com>, "Mel Gorman" <mgorman@suse.de>,
"Catalin Marinas" <catalin.marinas@arm.com>,
"Johannes Weiner" <hannes@cmpxchg.org>,
"Aneesh Kumar" <aneesh.kumar@linux.ibm.com>,
"Brian Geffon" <bgeffon@google.com>,
"open list:DOCUMENTATION" <linux-doc@vger.kernel.org>,
"Jesse Barnes" <jsbarnes@google.com>,
"Sofia Trinh" <sofia.trinh@edi.works>,
"Huang, Ying" <ying.huang@intel.com>,
linux-kernel <linux-kernel@vger.kernel.org>,
"Steven Barrett" <steven@liquorix.net>,
"Shuang Zhai" <szhai2@cs.rochester.edu>,
"Donald Carr" <d@chaos-reins.com>,
"Oleksandr Natalenko" <oleksandr@natalenko.name>,
"Holger Hoffstätte" <holger@applied-asynchrony.com>,
"Will Deacon" <will@kernel.org>,
"Dave Hansen" <dave.hansen@linux.intel.com>,
"Jonathan Corbet" <corbet@lwn.net>,
"Mike Rapoport" <rppt@kernel.org>,
"Andrew Morton" <akpm@linux-foundation.org>,
"Jens Axboe" <axboe@kernel.dk>, "Hillf Danton" <hdanton@sina.com>,
"Michal Hocko" <mhocko@kernel.org>,
kernel <kernel@lists.fedoraproject.org>,
"Suleiman Souhlal" <suleiman@google.com>,
"Daniel Byrne" <djbyrne@mtu.edu>,
"the arch/x86 maintainers" <x86@kernel.org>,
"Konstantin Kharlamov" <Hi-Angel@yandex.ru>,
"Matthew Wilcox" <willy@infradead.org>,
"Linus Torvalds" <torvalds@linux-foundation.org>,
"Michael Larabel" <Michael@michaellarabel.com>,
Linux-MM <linux-mm@kvack.org>,
"Kernel Page Reclaim v2" <page-reclaim@google.com>,
"Jan Alexander Steffens" <heftig@archlinux.org>,
"Linux ARM" <linux-arm-kernel@lists.infradead.org>
Subject: Re: [PATCH v9 05/14] mm: multi-gen LRU: groundwork
Date: Mon, 21 Mar 2022 22:52:42 -0600 [thread overview]
Message-ID: <CAOUHufbkSffDkUgv03kGdNs2-6V-fTHRKr7hjsZJubA_yWU7bQ@mail.gmail.com> (raw)
In-Reply-To: <cf736b49-57e3-51df-56af-5b71d0304e4a@redhat.com>
On Mon, Mar 21, 2022 at 1:18 PM Prarit Bhargava <prarit@redhat.com> wrote:
>
> On 3/21/22 14:58, Justin Forbes wrote:
> > On Mon, Mar 14, 2022 at 4:30 AM Yu Zhao <yuzhao@google.com> wrote:
> >>
> >> On Mon, Mar 14, 2022 at 2:09 AM Huang, Ying <ying.huang@intel.com> wrote:
> >>>
> >>> Hi, Yu,
> >>>
> >>> Yu Zhao <yuzhao@google.com> writes:
> >>>> diff --git a/mm/Kconfig b/mm/Kconfig
> >>>> index 3326ee3903f3..747ab1690bcf 100644
> >>>> --- a/mm/Kconfig
> >>>> +++ b/mm/Kconfig
> >>>> @@ -892,6 +892,16 @@ config ANON_VMA_NAME
> >>>> area from being merged with adjacent virtual memory areas due to the
> >>>> difference in their name.
> >>>>
> >>>> +# the multi-gen LRU {
> >>>> +config LRU_GEN
> >>>> + bool "Multi-Gen LRU"
> >>>> + depends on MMU
> >>>> + # the following options can use up the spare bits in page flags
> >>>> + depends on !MAXSMP && (64BIT || !SPARSEMEM || SPARSEMEM_VMEMMAP)
> >>>
> >>> LRU_GEN depends on !MAXSMP. So, What is the maximum NR_CPUS supported
> >>> by LRU_GEN?
> >>
> >> LRU_GEN doesn't really care about NR_CPUS. IOW, it doesn't impose a
> >> max number. The dependency is with NODES_SHIFT selected by MAXSMP:
> >> default "10" if MAXSMP
> >> This combined with LAST_CPUPID_SHIFT can exhaust the spare bits in page flags.
> >>
> >> MAXSMP is meant for kernel developers to test their code, and it
> >> should not be used in production [1]. But some distros unfortunately
> >> ship kernels built with this option, e.g., Fedora and Ubuntu. And
> >> their users reported build errors to me after they applied MGLRU on
> >> those kernels ("Not enough bits in page flags"). Let me add Fedora and
> >> Ubuntu to this thread.
> >>
> >> Fedora and Ubuntu,
> >>
> >> Could you please clarify if there is a reason to ship kernels built
> >> with MAXSMP? Otherwise, please consider disabling this option. Thanks.
> >>
> >> As per above, MAXSMP enables ridiculously large numbers of CPUs and
> >> NUMA nodes for testing purposes. It is detrimental to performance,
> >> e.g., CPUMASK_OFFSTACK.
> >
> > It was enabled for Fedora, and RHEL because we did need more than 512
> > CPUs, originally only in RHEL until SGI (years ago) complained that
> > they were testing very large machines with Fedora. The testing done
> > on RHEL showed that the performance impact was minimal. For a very
> > long time we had MAXSMP off and carried a patch which allowed us to
> > turn on CPUMASK_OFFSTACK without debugging because there was supposed
> > to be "something else" coming. In 2019 we gave up, dropped that patch
> > and just turned on MAXSMP.
> >
> > I do not have any metrics for how often someone runs Fedora on a
> > ridiculously large machine these days, but I would guess that number
> > is not 0.
>
> It is not 0. I've seen data from large systems (1000+ logical threads)
> that are running Fedora albeit with a modified Fedora kernel.
>
> Additionally the max limit for CPUS in RHEL is 1792, however, we have
> recently had a request to *double* that to 3584. You should just assume
> that number will continue to increase.
Good to know. Thanks.
From the standpoint of overhead, I'd consider NR_CPUS=4096 and
NODES_SHIFT=7 as the next step, before going with MAXSMP.
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
next prev parent reply other threads:[~2022-03-22 4:55 UTC|newest]
Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-03-09 2:12 [PATCH v9 00/14] Multi-Gen LRU Framework Yu Zhao
2022-03-09 2:12 ` [PATCH v9 01/14] mm: x86, arm64: add arch_has_hw_pte_young() Yu Zhao
2022-03-11 10:55 ` Barry Song
2022-03-11 22:57 ` Yu Zhao
2022-03-09 2:12 ` [PATCH v9 02/14] mm: x86: add CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG Yu Zhao
2022-03-16 22:15 ` Barry Song
2022-03-09 2:12 ` [PATCH v9 03/14] mm/vmscan.c: refactor shrink_node() Yu Zhao
2022-03-18 1:15 ` Barry Song
2022-03-09 2:12 ` [PATCH v9 04/14] Revert "include/linux/mm_inline.h: fold __update_lru_size() into its sole caller" Yu Zhao
2022-03-09 2:12 ` [PATCH v9 05/14] mm: multi-gen LRU: groundwork Yu Zhao
2022-03-14 8:08 ` Huang, Ying
2022-03-14 9:30 ` Yu Zhao
2022-03-15 0:34 ` Huang, Ying
2022-03-15 0:50 ` Yu Zhao
2022-03-21 18:58 ` Justin Forbes
2022-03-21 19:17 ` Prarit Bhargava
2022-03-22 4:52 ` Yu Zhao [this message]
2022-03-16 23:25 ` Barry Song
2022-03-21 9:04 ` Yu Zhao
2022-03-21 11:47 ` Barry Song
2022-03-09 2:12 ` [PATCH v9 06/14] mm: multi-gen LRU: minimal implementation Yu Zhao
2022-03-16 5:55 ` Huang, Ying
2022-03-16 7:54 ` Yu Zhao
2022-03-19 3:01 ` Barry Song
2022-03-19 3:11 ` Yu Zhao
2022-03-23 7:47 ` Barry Song
2022-03-24 6:24 ` Yu Zhao
2022-03-24 8:13 ` Barry Song
2022-03-19 10:14 ` Barry Song
2022-03-21 23:51 ` Yu Zhao
2022-03-19 11:15 ` Barry Song
2022-03-22 0:30 ` Yu Zhao
2022-03-21 12:51 ` Aneesh Kumar K.V
2022-03-22 4:02 ` Yu Zhao
2022-03-21 13:01 ` Aneesh Kumar K.V
2022-03-22 4:39 ` Yu Zhao
2022-03-22 5:26 ` Aneesh Kumar K.V
2022-03-22 5:55 ` Yu Zhao
2022-03-09 2:12 ` [PATCH v9 07/14] mm: multi-gen LRU: exploit locality in rmap Yu Zhao
2022-04-07 2:29 ` Barry Song
2022-04-07 3:04 ` Yu Zhao
2022-04-07 3:46 ` Barry Song
2022-04-07 23:51 ` Yu Zhao
2022-03-09 2:12 ` [PATCH v9 08/14] mm: multi-gen LRU: support page table walks Yu Zhao
2022-03-09 2:12 ` [PATCH v9 09/14] mm: multi-gen LRU: optimize multiple memcgs Yu Zhao
2022-03-09 2:12 ` [PATCH v9 10/14] mm: multi-gen LRU: kill switch Yu Zhao
2022-03-22 7:47 ` Barry Song
2022-03-22 8:20 ` Yu Zhao
2022-03-22 8:45 ` Barry Song
2022-03-22 9:00 ` Yu Zhao
2022-03-09 2:12 ` [PATCH v9 11/14] mm: multi-gen LRU: thrashing prevention Yu Zhao
2022-03-22 7:22 ` Barry Song
2022-03-22 8:14 ` Yu Zhao
2022-03-09 2:12 ` [PATCH v9 12/14] mm: multi-gen LRU: debugfs interface Yu Zhao
2022-03-09 2:12 ` [PATCH v9 13/14] mm: multi-gen LRU: admin guide Yu Zhao
2022-03-10 12:29 ` Mike Rapoport
2022-03-11 0:37 ` Yu Zhao
2022-03-09 2:12 ` [PATCH v9 14/14] mm: multi-gen LRU: design doc Yu Zhao
2022-03-11 8:22 ` Mike Rapoport
2022-03-11 9:38 ` Yu Zhao
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=CAOUHufbkSffDkUgv03kGdNs2-6V-fTHRKr7hjsZJubA_yWU7bQ@mail.gmail.com \
--to=yuzhao@google.com \
--cc=Hi-Angel@yandex.ru \
--cc=Michael@michaellarabel.com \
--cc=ak@linux.intel.com \
--cc=akpm@linux-foundation.org \
--cc=aneesh.kumar@linux.ibm.com \
--cc=axboe@kernel.dk \
--cc=bgeffon@google.com \
--cc=catalin.marinas@arm.com \
--cc=corbet@lwn.net \
--cc=d@chaos-reins.com \
--cc=dave.hansen@linux.intel.com \
--cc=djbyrne@mtu.edu \
--cc=hannes@cmpxchg.org \
--cc=hdanton@sina.com \
--cc=heftig@archlinux.org \
--cc=holger@applied-asynchrony.com \
--cc=jforbes@fedoraproject.org \
--cc=jsbarnes@google.com \
--cc=kernel-team@lists.ubuntu.com \
--cc=kernel@lists.fedoraproject.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=mhocko@kernel.org \
--cc=oleksandr@natalenko.name \
--cc=page-reclaim@google.com \
--cc=prarit@redhat.com \
--cc=riel@surriel.com \
--cc=rppt@kernel.org \
--cc=sofia.trinh@edi.works \
--cc=steven@liquorix.net \
--cc=suleiman@google.com \
--cc=szhai2@cs.rochester.edu \
--cc=torvalds@linux-foundation.org \
--cc=vaibhav@linux.ibm.com \
--cc=will@kernel.org \
--cc=willy@infradead.org \
--cc=x86@kernel.org \
--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;
as well as URLs for NNTP newsgroup(s).