linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Mike Kravetz <mike.kravetz@oracle.com>
To: Muchun Song <muchun.song@linux.dev>
Cc: Usama Arif <usama.arif@bytedance.com>,
	Linux-MM <linux-mm@kvack.org>, Mike Rapoport <rppt@kernel.org>,
	LKML <linux-kernel@vger.kernel.org>,
	Muchun Song <songmuchun@bytedance.com>,
	fam.zheng@bytedance.com, liangma@liangbit.com,
	punit.agrawal@bytedance.com
Subject: Re: [v3 1/4] mm: hugetlb_vmemmap: Use nid of the head page to reallocate it
Date: Mon, 28 Aug 2023 11:25:35 -0700	[thread overview]
Message-ID: <20230828182535.GB3290@monkey> (raw)
In-Reply-To: <4BE9BCF9-AD29-484B-BBB0-3709B77E2236@linux.dev>

On 08/28/23 15:15, Muchun Song wrote:
> 
> 
> > On Aug 25, 2023, at 19:18, Usama Arif <usama.arif@bytedance.com> wrote:
> > 
> > If tail page prep and initialization is skipped, then the "start"
> > page will not contain the correct nid. Use the nid from first
> > vmemap page.
> > 
> > Signed-off-by: Usama Arif <usama.arif@bytedance.com>
> 
> Make sense even if without your optimization. Because the nid is
> used for allocation for "reuse" page, it really should be extracted
> from "reuse" page instead of "start" page.
> 
> Reviewed-by: Muchun Song <songmuchun@bytedance.com>

Agree that using reuse is better than start here.  However, IIUC there is no
way start and reuse could be on different nodes today.

Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
-- 
Mike Kravetz


  reply	other threads:[~2023-08-28 18:26 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-08-25 11:18 [v3 0/4] mm: hugetlb: Skip initialization of gigantic tail struct pages if freed by HVO Usama Arif
2023-08-25 11:18 ` [v3 1/4] mm: hugetlb_vmemmap: Use nid of the head page to reallocate it Usama Arif
2023-08-28  7:15   ` Muchun Song
2023-08-28 18:25     ` Mike Kravetz [this message]
2023-08-25 11:18 ` [v3 2/4] memblock: pass memblock_type to memblock_setclr_flag Usama Arif
2023-08-28  7:16   ` Muchun Song
2023-08-28  7:37   ` Mike Rapoport
2023-08-28 18:39   ` Mike Kravetz
2023-08-25 11:18 ` [v3 3/4] memblock: introduce MEMBLOCK_RSRV_NOINIT_VMEMMAP flag Usama Arif
2023-08-28  7:26   ` Muchun Song
2023-08-28  7:47   ` Mike Rapoport
2023-08-28  8:52     ` Muchun Song
2023-08-28  9:09       ` Mike Rapoport
2023-08-28  9:18         ` Muchun Song
2023-08-25 11:18 ` [v3 4/4] mm: hugetlb: Skip initialization of gigantic tail struct pages if freed by HVO Usama Arif
2023-08-28 11:33   ` Muchun Song
2023-08-28 21:04     ` Mike Kravetz
2023-08-29  3:33       ` Muchun Song
2023-08-29  3:47         ` Mike Kravetz
2023-08-30 10:27     ` [External] " Usama Arif
2023-08-31  6:21       ` [External] " Muchun Song
2023-08-31  9:58         ` Mel Gorman
2023-08-31 10:01           ` Muchun Song
2023-08-31 10:28             ` Mel Gorman
2023-08-31  7:33       ` [External] " Mike Rapoport

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=20230828182535.GB3290@monkey \
    --to=mike.kravetz@oracle.com \
    --cc=fam.zheng@bytedance.com \
    --cc=liangma@liangbit.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=muchun.song@linux.dev \
    --cc=punit.agrawal@bytedance.com \
    --cc=rppt@kernel.org \
    --cc=songmuchun@bytedance.com \
    --cc=usama.arif@bytedance.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