[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <23b14717-0f4a-10f2-5118-7cb8445fbdab@oracle.com>
Date: Fri, 4 May 2018 12:53:40 -0400
From: Pavel Tatashin <pasha.tatashin@...cle.com>
To: Daniel Vacek <neelx@...hat.com>, Jia He <hejianet@...il.com>
Cc: Russell King <linux@...linux.org.uk>,
Catalin Marinas <catalin.marinas@....com>,
Will Deacon <will.deacon@....com>,
Mark Rutland <mark.rutland@....com>,
Ard Biesheuvel <ard.biesheuvel@...aro.org>,
Andrew Morton <akpm@...ux-foundation.org>,
Michal Hocko <mhocko@...e.com>,
Wei Yang <richard.weiyang@...il.com>,
Kees Cook <keescook@...omium.org>,
Laura Abbott <labbott@...hat.com>,
Vladimir Murzin <vladimir.murzin@....com>,
Philip Derrin <philip@....systems>,
AKASHI Takahiro <takahiro.akashi@...aro.org>,
James Morse <james.morse@....com>,
Steve Capper <steve.capper@....com>,
Gioh Kim <gi-oh.kim@...fitbricks.com>,
Vlastimil Babka <vbabka@...e.cz>, Mel Gorman <mgorman@...e.de>,
Johannes Weiner <hannes@...xchg.org>,
Kemi Wang <kemi.wang@...el.com>,
Petr Tesarik <ptesarik@...e.com>,
YASUAKI ISHIMATSU <yasu.isimatu@...il.com>,
Andrey Ryabinin <aryabinin@...tuozzo.com>,
Nikolay Borisov <nborisov@...e.com>,
Daniel Jordan <daniel.m.jordan@...cle.com>,
Eugeniu Rosca <erosca@...adit-jv.com>,
linux-arm-kernel <linux-arm-kernel@...ts.infradead.org>,
open list <linux-kernel@...r.kernel.org>,
Linux-MM <linux-mm@...ck.org>
Subject: Re: [PATCH v8 0/6] optimize memblock_next_valid_pfn and
early_pfn_valid on arm and arm64
> I'm wondering, ain't simple enabling of config
> DEFERRED_STRUCT_PAGE_INIT provide even better speed-up? If that is the
> case then it seems like this series is not needed at all, right?
> I am not sure why is this config optional. It looks like it could be
> enabled by default or even unconditionally considering that with
> commit c9e97a1997fb ("mm: initialize pages on demand during boot") the
> deferred code is statically disabled after all the pages are
> initialized.
Hi Daniel,
Currently, deferred struct pages are initialized in parallel only on NUMA machines. I would like to make a change to use all the available CPUs even on a single socket systems, but that is not there yet. So, I believe Jia's performance improvements are still relevant.
Thank you,
Pavel
Powered by blists - more mailing lists