linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Michal Hocko <mhocko@suse.com>
To: Wei Yang <richard.weiyang@gmail.com>
Cc: Mel Gorman <mgorman@suse.de>,
	akpm@linux-foundation.org, linux-mm@kvack.org
Subject: Re: [PATCH] mm/page_alloc: call set_pageblock_order() once for each node
Date: Tue, 3 Apr 2018 09:57:37 +0200	[thread overview]
Message-ID: <20180403075737.GB5501@dhcp22.suse.cz> (raw)
In-Reply-To: <20180330010243.GA14446@WeideMacBook-Pro.local>

On Fri 30-03-18 09:02:43, Wei Yang wrote:
> On Thu, Mar 29, 2018 at 01:11:09PM +0100, Mel Gorman wrote:
> >On Thu, Mar 29, 2018 at 11:36:07AM +0800, Wei Yang wrote:
> >> set_pageblock_order() is a standalone function which sets pageblock_order,
> >> while current implementation calls this function on each ZONE of each node
> >> in free_area_init_core().
> >> 
> >> Since free_area_init_node() is the only user of free_area_init_core(),
> >> this patch moves set_pageblock_order() up one level to invoke
> >> set_pageblock_order() only once on each node.
> >> 
> >> Signed-off-by: Wei Yang <richard.weiyang@gmail.com>
> >
> >The patch looks ok but given that set_pageblock_order returns immediately
> >if it has already been called, I expect the benefit is marginal. Was any
> >improvement in boot time measured?
> 
> No, I don't expect measurable improvement from this since the number of nodes
> and zones are limited.
> 
> This is just a code refine from logic point of view.

Then, please make sure it is a real refinement. Calling this function
per node is only half way to get there as the function is by no means
per node.

-- 
Michal Hocko
SUSE Labs

  reply	other threads:[~2018-04-03  7:57 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-03-29  3:36 [PATCH] mm/page_alloc: call set_pageblock_order() once for each node Wei Yang
2018-03-29 12:11 ` Mel Gorman
2018-03-30  1:02   ` Wei Yang
2018-04-03  7:57     ` Michal Hocko [this message]
2018-04-04  1:27       ` Wei Yang
2018-04-05  9:55         ` Michal Hocko
2018-04-06  1:46           ` Wei Yang

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=20180403075737.GB5501@dhcp22.suse.cz \
    --to=mhocko@suse.com \
    --cc=akpm@linux-foundation.org \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@suse.de \
    --cc=richard.weiyang@gmail.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;
as well as URLs for NNTP newsgroup(s).