linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Mel Gorman <mgorman@suse.de>
To: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	Tejun Heo <tj@kernel.org>, Len Brown <lenb@kernel.org>,
	Thomas Gleixner <tglx@linutronix.de>, Ingo Molnar <mingo@elte.hu>,
	"H. Peter Anvin" <hpa@zytor.com>, Toshi Kani <toshi.kani@hp.com>,
	Wanpeng Li <liwanp@linux.vnet.ibm.com>,
	Thomas Renninger <trenn@suse.de>, Yinghai Lu <yinghai@kernel.org>,
	Jiang Liu <jiang.liu@huawei.com>,
	Wen Congyang <wency@cn.fujitsu.com>,
	Lai Jiangshan <laijs@cn.fujitsu.com>,
	Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>,
	Taku Izumi <izumi.taku@jp.fujitsu.com>,
	Minchan Kim <minchan@kernel.org>,
	"mina86@mina86.com" <mina86@mina86.com>,
	"gong.chen@linux.intel.com" <gong.chen@linux.intel.com>,
	Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com>,
	"lwoodman@redhat.com" <lwoodman@redhat.com>,
	Rik van Riel <riel@redhat.com>,
	"jweiner@redhat.com" <jweiner@redhat.com>,
	Prarit Bhargava <prarit@redhat.com>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	Linux MM <linux-mm@kvack.org>, Chen Tang <imtangchen@gmail.com>,
	Tang Chen <tangchen@cn.fujitsu.com>,
	Zhang Yanfei <zhangyanfei.yes@gmail.com>
Subject: Re: [PATCH RESEND part2 v2 8/8] x86, numa, acpi, memory-hotplug: Make movable_node have higher priority
Date: Thu, 16 Jan 2014 17:03:19 +0000	[thread overview]
Message-ID: <20140116170253.GA24740@suse.de> (raw)
In-Reply-To: <529D423F.3030200@cn.fujitsu.com>

On Tue, Dec 03, 2013 at 10:30:23AM +0800, Zhang Yanfei wrote:
> From: Tang Chen <tangchen@cn.fujitsu.com>
> 
> If users specify the original movablecore=nn@ss boot option, the kernel will
> arrange [ss, ss+nn) as ZONE_MOVABLE. The kernelcore=nn@ss boot option is similar
> except it specifies ZONE_NORMAL ranges.
> 
> Now, if users specify "movable_node" in kernel commandline, the kernel will
> arrange hotpluggable memory in SRAT as ZONE_MOVABLE. And if users do this, all
> the other movablecore=nn@ss and kernelcore=nn@ss options should be ignored.
> 
> For those who don't want this, just specify nothing. The kernel will act as
> before.
> 
> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com>
> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
> Reviewed-by: Wanpeng Li <liwanp@linux.vnet.ibm.com>
> ---
>  mm/page_alloc.c |   28 ++++++++++++++++++++++++++--
>  1 files changed, 26 insertions(+), 2 deletions(-)
> 
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index dd886fa..768ea0e 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -5021,9 +5021,33 @@ static void __init find_zone_movable_pfns_for_nodes(void)
>  	nodemask_t saved_node_state = node_states[N_MEMORY];
>  	unsigned long totalpages = early_calculate_totalpages();
>  	int usable_nodes = nodes_weight(node_states[N_MEMORY]);
> +	struct memblock_type *type = &memblock.memory;
> +
> +	/* Need to find movable_zone earlier when movable_node is specified. */
> +	find_usable_zone_for_movable();
> +
> +	/*
> +	 * If movable_node is specified, ignore kernelcore and movablecore
> +	 * options.
> +	 */
> +	if (movable_node_is_enabled()) {
> +		for (i = 0; i < type->cnt; i++) {
> +			if (!memblock_is_hotpluggable(&type->regions[i]))
> +				continue;
> +
> +			nid = type->regions[i].nid;
> +
> +			usable_startpfn = PFN_DOWN(type->regions[i].base);
> +			zone_movable_pfn[nid] = zone_movable_pfn[nid] ?
> +				min(usable_startpfn, zone_movable_pfn[nid]) :
> +				usable_startpfn;
> +		}
> +
> +		goto out2;

out2 is not the most descriptive variable that ever existed. out_align?

There is an assumption here that the hot-pluggable regions of memory
are always at the upper end of the physical address space for that NUMA
node. What prevents the hardware having something like

node0:	0-4G	Not removable
node0:	4-8G	Removable
node0:	8-12G	Not removable

?

By the looks of things, the current code would make ZONE_MOVABLE for the
while 4-12G range of memory even though the 8-12G region cannot be
hot-removed. That would compound any problems related to lowmem-like
pressure as the 8-12G region cannot be used for kernel allocations like
inodes.

-- 
Mel Gorman
SUSE Labs

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply	other threads:[~2014-01-16 17:03 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-12-03  2:19 [PATCH RESEND part2 v2 0/8] Arrange hotpluggable memory as ZONE_MOVABLE Zhang Yanfei
2013-12-03  2:22 ` [PATCH RESEND part2 v2 1/8] x86: get pg_data_t's memory from other node Zhang Yanfei
2014-01-16 17:11   ` Mel Gorman
2014-01-17  0:15     ` H. Peter Anvin
2014-01-20  7:29     ` Tang Chen
2014-01-20 15:14       ` Mel Gorman
2014-02-06 10:12         ` Mel Gorman
2014-02-10  5:44           ` Tang Chen
2014-02-11 11:08             ` Mel Gorman
2014-02-12  7:11               ` Tang Chen
2013-12-03  2:24 ` [PATCH RESEND part2 v2 2/8] memblock, numa: Introduce flag into memblock Zhang Yanfei
2013-12-03  2:25 ` [PATCH RESEND part2 v2 3/8] memblock, mem_hotplug: Introduce MEMBLOCK_HOTPLUG flag to mark hotpluggable regions Zhang Yanfei
2013-12-03  2:25 ` [PATCH RESEND part2 v2 4/8] memblock: Make memblock_set_node() support different memblock_type Zhang Yanfei
2013-12-03  2:27 ` [PATCH RESEND part2 v2 5/8] acpi, numa, mem_hotplug: Mark hotpluggable memory in memblock Zhang Yanfei
2013-12-03  2:28 ` [PATCH RESEND part2 v2 6/8] acpi, numa, mem_hotplug: Mark all nodes the kernel resides un-hotpluggable Zhang Yanfei
2013-12-03 23:44   ` Andrew Morton
2013-12-04  2:09     ` [PATCH update " Zhang Yanfei
2013-12-03  2:29 ` [PATCH RESEND part2 v2 7/8] memblock, mem_hotplug: Make memblock skip hotpluggable regions if needed Zhang Yanfei
2013-12-03  2:30 ` [PATCH RESEND part2 v2 8/8] x86, numa, acpi, memory-hotplug: Make movable_node have higher priority Zhang Yanfei
2014-01-16 17:03   ` Mel Gorman [this message]
2013-12-03  2:45 ` [PATCH RESEND part2 v2 0/8] Arrange hotpluggable memory as ZONE_MOVABLE Zhang Yanfei
2013-12-03 23:48 ` Andrew Morton
2013-12-04  0:02   ` Zhang Yanfei
2013-12-04  9:53     ` Ingo Molnar

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=20140116170253.GA24740@suse.de \
    --to=mgorman@suse.de \
    --cc=akpm@linux-foundation.org \
    --cc=gong.chen@linux.intel.com \
    --cc=hpa@zytor.com \
    --cc=imtangchen@gmail.com \
    --cc=isimatu.yasuaki@jp.fujitsu.com \
    --cc=izumi.taku@jp.fujitsu.com \
    --cc=jiang.liu@huawei.com \
    --cc=jweiner@redhat.com \
    --cc=laijs@cn.fujitsu.com \
    --cc=lenb@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=liwanp@linux.vnet.ibm.com \
    --cc=lwoodman@redhat.com \
    --cc=mina86@mina86.com \
    --cc=minchan@kernel.org \
    --cc=mingo@elte.hu \
    --cc=prarit@redhat.com \
    --cc=riel@redhat.com \
    --cc=tangchen@cn.fujitsu.com \
    --cc=tglx@linutronix.de \
    --cc=tj@kernel.org \
    --cc=toshi.kani@hp.com \
    --cc=trenn@suse.de \
    --cc=vasilis.liaskovitis@profitbricks.com \
    --cc=wency@cn.fujitsu.com \
    --cc=yinghai@kernel.org \
    --cc=zhangyanfei.yes@gmail.com \
    --cc=zhangyanfei@cn.fujitsu.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).