From: Pengfei Li <fly@kernel.page>
To: Christopher Lameter <cl@linux.com>
Cc: David Hildenbrand <david@redhat.com>,
akpm@linux-foundation.org, mgorman@techsingularity.net,
mhocko@kernel.org, vbabka@suse.cz, iamjoonsoo.kim@lge.com,
guro@fb.com, linux-kernel@vger.kernel.org, linux-mm@kvack.org,
fly@kernel.page
Subject: Re: [RFC v1 00/19] Modify zonelist to nodelist v1
Date: Sat, 23 Nov 2019 01:36:13 +0800 [thread overview]
Message-ID: <20191123013613.566bb40a.fly@kernel.page> (raw)
In-Reply-To: <alpine.DEB.2.21.1911221551570.10063@www.lameter.com>
On Fri, 22 Nov 2019 15:53:57 +0000 (UTC)
Christopher Lameter <cl@linux.com> wrote:
> On Fri, 22 Nov 2019, Pengfei Li wrote:
>
> > I am sorry that I did not make it clear. I want to express this
> > series of patches will benefit NUMA systems with multiple nodes.
>
> Ok but that benefit needs to be quantified somehow.
>
Thanks for your comments.
Yes, I will add detailed performance test data in v2.
> > The main benefit is that it will be more efficient when traversing
> > all nodes (for example when performing page reclamation).
>
> And you loose the prioritization of allocations through these
> different zones.
Sorry, I forgot to mention that the information about the zones that
are available to the node is still there.
The old for_each_zone_zonelist has been replaced with
for_each_zone_nodelist.
I will add some key implementation details in v2.
> We create zonelists with a certain sequence of the
> zones in order to prefer allocations from certain zones. This is in
> particular important for the smaller DMA zones which may be easily
> exhausted.
>
I'm not sure if I understand what you mean, but since commit
c9bff3eebc09 ("mm, page_alloc: rip out ZONELIST_ORDER_ZONE"), the
zonelist is always in "Node" order, so building the nodelist is fine.
--
Pengfei
next prev parent reply other threads:[~2019-11-22 17:36 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-11-21 15:17 [RFC v1 00/19] Modify zonelist to nodelist v1 Pengfei Li
2019-11-21 15:17 ` [RFC v1 01/19] mm, mmzone: modify zonelist to nodelist Pengfei Li
2019-11-21 15:17 ` [RFC v1 02/19] mm, hugetlb: use for_each_node in dequeue_huge_page_nodemask() Pengfei Li
2019-11-21 15:17 ` [RFC v1 03/19] mm, oom_kill: use for_each_node in constrained_alloc() Pengfei Li
2019-11-21 15:17 ` [RFC v1 04/19] mm, slub: use for_each_node in get_any_partial() Pengfei Li
2019-11-21 15:17 ` [RFC v1 05/19] mm, slab: use for_each_node in fallback_alloc() Pengfei Li
2019-11-21 15:17 ` [RFC v1 06/19] mm, vmscan: use for_each_node in do_try_to_free_pages() Pengfei Li
2019-11-21 15:17 ` [RFC v1 07/19] mm, vmscan: use first_node in throttle_direct_reclaim() Pengfei Li
2019-11-21 15:18 ` [RFC v1 08/19] mm, vmscan: pass pgdat to wakeup_kswapd() Pengfei Li
2019-11-21 15:18 ` [RFC v1 09/19] mm, vmscan: use for_each_node in shrink_zones() Pengfei Li
2019-11-21 15:18 ` [RFC v1 10/19] mm, page_alloc: use for_each_node in wake_all_kswapds() Pengfei Li
2019-11-21 15:18 ` [RFC v1 11/19] mm, mempolicy: use first_node in mempolicy_slab_node() Pengfei Li
2019-11-21 15:18 ` [RFC v1 12/19] mm, mempolicy: use first_node in mpol_misplaced() Pengfei Li
2019-11-21 15:18 ` [RFC v1 13/19] mm, page_alloc: use first_node in local_memory_node() Pengfei Li
2019-11-21 15:18 ` [RFC v1 14/19] mm, compaction: rename compaction_zonelist_suitable Pengfei Li
2019-11-21 15:18 ` [RFC v1 15/19] mm, mm_init: rename mminit_verify_zonelist Pengfei Li
2019-11-21 15:18 ` [RFC v1 16/19] mm, page_alloc: cleanup build_zonelists Pengfei Li
2019-11-21 15:18 ` [RFC v1 17/19] mm, memory_hotplug: cleanup online_pages() Pengfei Li
2019-11-21 15:18 ` [RFC v1 18/19] kernel, sysctl: cleanup numa_zonelist_order Pengfei Li
2019-11-21 15:18 ` [RFC v1 19/19] mm, mmzone: cleanup zonelist in comments Pengfei Li
2019-11-21 18:04 ` [RFC v1 00/19] Modify zonelist to nodelist v1 Michal Hocko
2019-11-22 15:05 ` Pengfei Li
2019-11-25 8:40 ` Michal Hocko
2019-11-25 14:46 ` Pengfei Li
2019-11-25 15:46 ` Michal Hocko
2019-11-22 7:25 ` lixinhai.lxh
2019-11-22 10:14 ` David Hildenbrand
2019-11-22 15:28 ` Pengfei Li
2019-11-22 15:53 ` Qian Cai
2019-11-22 17:44 ` Pengfei Li
2019-11-25 8:39 ` Michal Hocko
2019-11-26 15:30 ` Qian Cai
2019-11-26 15:41 ` Michal Hocko
2019-11-26 19:04 ` Qian Cai
2019-11-27 8:50 ` Michal Hocko
2019-11-22 10:03 ` David Hildenbrand
2019-11-22 15:49 ` Pengfei Li
2019-11-22 15:53 ` Christopher Lameter
2019-11-22 16:06 ` David Hildenbrand
2019-11-22 17:36 ` Pengfei Li [this message]
2019-11-22 18:24 ` Christopher Lameter
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=20191123013613.566bb40a.fly@kernel.page \
--to=fly@kernel.page \
--cc=akpm@linux-foundation.org \
--cc=cl@linux.com \
--cc=david@redhat.com \
--cc=guro@fb.com \
--cc=iamjoonsoo.kim@lge.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@techsingularity.net \
--cc=mhocko@kernel.org \
--cc=vbabka@suse.cz \
/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).