mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Vlastimil Babka <vbabka@suse.cz>
To: Hillf Danton <hdanton@sina.com>, Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	Johannes Weiner <hannes@cmpxchg.org>,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	kernel-team@meta.com, Chris Mason <clm@fb.com>,
	Kiryl Shutsemau <kirill@shutemov.name>,
	"Liam R. Howlett" <Liam.Howlett@oracle.com>,
	Brendan Jackman <jackmanb@google.com>,
	David Hildenbrand <david@redhat.com>,
	Lorenzo Stoakes <lorenzo.stoakes@oracle.com>,
	Michal Hocko <mhocko@suse.com>, Mike Rapoport <rppt@kernel.org>,
	Suren Baghdasaryan <surenb@google.com>,
	Vlastimil Babka <vbabka@suse.cz>, Zi Yan <ziy@nvidia.com>,
	Hillf Danton <hdanton@sina.com>,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	kernel-team@meta.com
Subject: Re: [PATCH v2 2/4] mm/page_alloc: Perform appropriate batching in drain_pages_zone
Date: Fri, 3 Oct 2025 10:35:46 +0200	[thread overview]
Message-ID: <db51bcc5-aaf6-4cb4-ab62-fed9d40d6caa@suse.cz> (raw)
In-Reply-To: <20251001234814.7896-1-hdanton@sina.com>

On 10/2/25 01:48, Hillf Danton wrote:
> On Wed,  1 Oct 2025 08:37:16 -0700 Joshua Hahn wrote:
>> 
>> While I definitely agree that spreading out 1TB across multiple NUMA nodes
>> is an option that should be considered, I am unsure if it makes sense to
>> dismiss this issue as simply a misconfiguration problem.
>> 
>> The reality is that these machines do exist, and we see zone lock contention
>> on these machines. You can also see that I ran performance evaluation tests
>> on relatively smaller machines (250G) and saw some performance gains.
>> 
> If NUMA node could not be an option, there is still much room in the zone types
> for adding new zones on top of the current pcp and zone mechanism to mitigate
> zone lock contention, see diff below. Then the issue falls in the config category.
> 
>> The other point that I wanted to mention is that simply adding more NUMA
>> nodes is not always strictly beneficial; it changes how the scheduler
>> has to work, workloads would require more numa-aware tuning, etc.
> 
> Feel safe to sit back with Netflix on as PeterZ is taking care of NUMA nodes
> and eevdf, haha.

Feel free to stop making such weird "jokes"?

Also you should really stop dropping CC's on your replies, especially for
maintainers of given code. I've only learned in the v3 changelog from "as
suggested by Hillf Danton" that there was this subthread. This is not
acceptable. When the feedback is wrong and uncorrected by others, it can
mislead the patch author to do wrong changes in the next version.

If this Cc reduction is due to a problem with your e-mail provider, get a
different one?

> --- x/include/linux/mmzone.h
> +++ y/include/linux/mmzone.h
> @@ -779,6 +779,9 @@ enum zone_type {
>  #ifdef CONFIG_ZONE_DMA32
>  	ZONE_DMA32,
>  #endif
> +#ifdef CONFIG_ZONE_EXP
> +	ZONE_EXP0, ZONE_EXP1, ZONE_EXP2, /* experiment */
> +#endif
>  	/*
>  	 * Normal addressable memory is in ZONE_NORMAL. DMA operations can be
>  	 * performed on pages in ZONE_NORMAL if the DMA devices support
> 


  reply	other threads:[~2025-10-03  8:35 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-09-24 20:44 [PATCH v2 0/4] mm/page_alloc: Batch callers of free_pcppages_bulk Joshua Hahn
2025-09-24 20:44 ` [PATCH v2 1/4] mm/page_alloc/vmstat: Simplify refresh_cpu_vm_stats change detection Joshua Hahn
2025-09-24 22:51   ` Christoph Lameter (Ampere)
2025-09-25 18:26     ` Joshua Hahn
2025-09-26 15:34   ` Dan Carpenter
2025-09-26 16:40     ` Joshua Hahn
2025-09-26 17:50   ` SeongJae Park
2025-09-26 18:24     ` Joshua Hahn
2025-09-26 18:33       ` SeongJae Park
2025-09-24 20:44 ` [PATCH v2 2/4] mm/page_alloc: Perform appropriate batching in drain_pages_zone Joshua Hahn
2025-09-24 23:09   ` Christoph Lameter (Ampere)
2025-09-25 18:44     ` Joshua Hahn
2025-09-26 16:21       ` Christoph Lameter (Ampere)
2025-09-26 17:25         ` Joshua Hahn
2025-10-01 11:23         ` Vlastimil Babka
2025-09-26 14:01   ` Brendan Jackman
2025-09-26 15:48     ` Joshua Hahn
2025-09-26 16:57       ` Brendan Jackman
2025-09-26 17:33         ` Joshua Hahn
2025-09-27  0:46   ` Hillf Danton
2025-09-30 14:42     ` Joshua Hahn
2025-09-30 22:14       ` Hillf Danton
2025-10-01 15:37         ` Joshua Hahn
2025-10-01 23:48           ` Hillf Danton
2025-10-03  8:35             ` Vlastimil Babka [this message]
2025-10-03 10:02               ` Hillf Danton
2025-10-04  9:03                 ` Mike Rapoport
2025-09-24 20:44 ` [PATCH v2 3/4] mm/page_alloc: Batch page freeing in decay_pcp_high Joshua Hahn
2025-09-24 20:44 ` [PATCH v2 4/4] mm/page_alloc: Batch page freeing in free_frozen_page_commit Joshua Hahn
2025-09-28  5:17   ` kernel test robot
2025-09-29 15:17     ` Joshua Hahn
2025-10-01 10:04       ` Vlastimil Babka
2025-10-01 15:55         ` Joshua Hahn

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=db51bcc5-aaf6-4cb4-ab62-fed9d40d6caa@suse.cz \
    --to=vbabka@suse.cz \
    --cc=Liam.Howlett@oracle.com \
    --cc=akpm@linux-foundation.org \
    --cc=clm@fb.com \
    --cc=david@redhat.com \
    --cc=hannes@cmpxchg.org \
    --cc=hdanton@sina.com \
    --cc=jackmanb@google.com \
    --cc=joshua.hahnjy@gmail.com \
    --cc=kernel-team@meta.com \
    --cc=kirill@shutemov.name \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lorenzo.stoakes@oracle.com \
    --cc=mhocko@suse.com \
    --cc=rppt@kernel.org \
    --cc=surenb@google.com \
    --cc=ziy@nvidia.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

all inboxes | Powered by JetHome®