[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20220512123021.GP20579@suse.de>
Date: Thu, 12 May 2022 13:30:21 +0100
From: Mel Gorman <mgorman@...e.de>
To: Wonhyuk Yang <vvghjk1234@...il.com>
Cc: Steven Rostedt <rostedt@...dmis.org>,
Ingo Molnar <mingo@...hat.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Baik Song An <bsahn@...i.re.kr>,
Hong Yeon Kim <kimhy@...i.re.kr>,
Taeung Song <taeung@...llinux.co.kr>, linuxgeek@...uxgeek.io,
linux-kernel@...r.kernel.org, linux-mm@...ck.org
Subject: Re: [Patch v2] [PATCH] mm/page_alloc: Fix tracepoint
mm_page_alloc_zone_locked()
On Thu, May 12, 2022 at 11:53:07AM +0900, Wonhyuk Yang wrote:
> Currently, trace point mm_page_alloc_zone_locked() doesn't show
> correct information.
>
> First, when alloc_flag has ALLOC_HARDER/ALLOC_CMA, page can
> be allocated from MIGRATE_HIGHATOMIC/MIGRATE_CMA. Nevertheless,
> tracepoint use requested migration type not MIGRATE_HIGHATOMIC and
> MIGRATE_CMA.
>
> Second, after Commit 44042b4498728 ("mm/page_alloc: allow high-order
> pages to be stored on the per-cpu lists") percpu-list can store
> high order pages. But trace point determine whether it is a refiil
> of percpu-list by comparing requested order and 0.
>
> To handle these problems, make mm_page_alloc_zone_locked() only be
> called by __rmqueue_smallest with correct migration type. With a
> new argument called percpu_refill, it can show roughly whether it
> is a refill of percpu-list.
>
> Cc: Baik Song An <bsahn@...i.re.kr>
> Cc: Hong Yeon Kim <kimhy@...i.re.kr>
> Cc: Taeung Song <taeung@...llinux.co.kr>
> Cc: linuxgeek@...uxgeek.io
> Signed-off-by: Wonhyuk Yang <vvghjk1234@...il.com>
Acked-by: Mel Gorman <mgorman@...e.de>
--
Mel Gorman
SUSE Labs
Powered by blists - more mailing lists