linux-kernel - Re: [RFC PATCH] mm: thp: implement THP reservations for anonymous memory

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Tue, 20 Nov 2018 12:11:22 +0300
From:   "Kirill A. Shutemov" <kirill@...temov.name>
To:     Andrea Arcangeli <aarcange@...hat.com>
Cc:     Mel Gorman <mgorman@...hsingularity.net>,
        Anthony Yznaga <anthony.yznaga@...cle.com>, linux-mm@...ck.org,
        linux-kernel@...r.kernel.org, aneesh.kumar@...ux.ibm.com,
        akpm@...ux-foundation.org, jglisse@...hat.com,
        khandual@...ux.vnet.ibm.com, kirill.shutemov@...ux.intel.com,
        mhocko@...nel.org, minchan@...nel.org, peterz@...radead.org,
        rientjes@...gle.com, vbabka@...e.cz, willy@...radead.org,
        ying.huang@...el.com, nitingupta910@...il.com
Subject: Re: [RFC PATCH] mm: thp: implement THP reservations for anonymous
 memory

On Sat, Nov 10, 2018 at 11:44:12AM -0500, Andrea Arcangeli wrote:
> I would prefer to add intelligence to detect when COWs after fork
> should be done at 2m or 4k granularity (in the latter case by
> splitting the pmd before the actual COW while leaving the transhuge
> pmd intact in the other mm), because that would save CPU (and it'd
> automatically optimize redis). The snapshot process especially would
> run faster as it will read with THP performance.

I would argue we should switch to 4k COW everywhere. But it requires some
work on khugepaged side to be able to recover THP back after multiple 4k
COW in the range. Currently khugepaged is not able to collapse PTE entires
backed by compound page back to PMD.

I have this on my todo list for long time, but...

-- 
 Kirill A. Shutemov