All of lore.kernel.org
 help / color / mirror / Atom feed
From: Shaohui Zheng <shaohui.zheng@intel.com>
To: David Rientjes <rientjes@google.com>
Cc: Paul Mundt <lethal@linux-sh.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	haicheng.li@linux.intel.com, ak@linux.intel.com,
	shaohui.zheng@linux.intel.com, Yinghai Lu <yinghai@kernel.org>,
	Haicheng Li <haicheng.li@intel.com>
Subject: Re: [2/8,v3] NUMA Hotplug Emulator: infrastructure of NUMA hotplug emulation
Date: Fri, 19 Nov 2010 08:32:25 +0800	[thread overview]
Message-ID: <20101119003225.GB3327@shaohui> (raw)
In-Reply-To: <alpine.DEB.2.00.1011181321470.26680@chino.kir.corp.google.com>

On Thu, Nov 18, 2010 at 01:24:52PM -0800, David Rientjes wrote:
> On Thu, 18 Nov 2010, Shaohui Zheng wrote:
> 
> > in our draft patch, we re-setup nr_node_ids when CONFIG_ARCH_MEMORY_PROBE enabled 
> > and mem=XXX was specified in grub. we set nr_node_ids as MAX_NUMNODES + 1, because
> >  we do not know how many nodes will be hot-added through memory/probe interface. 
> >  it might be a little wasting of memory.
> > 
> 
> nr_node_ids need not be set to anything different at boot, the 
> MEM_GOING_ONLINE callback should be used for anything (like the slab 
> allocators) where a new node is introduced and needs to be dealt with 
> accordingly; this is how regular memory hotplug works, we need no 
> additional code in this regard because it's emulated.  If a subsystem 
> needs to change in response to a new node going online and doesn't as a 
> result of using your emulator, that's a bug and either needs to be fixed 
> or prohibited from use with CONFIG_MEMORY_HOTPLUG.
> 
> (See the MEM_GOING_ONLINE callback in mm/slub.c, for instance, which deals 
> only with the case of node hotplug.)

nr_node_ids is the possible node number. when we do regular memory online,
it is oline to a possible node, and it is already counted in to nr_node_ids.

if you increment nr_node_ids dynamically when node online, it causes a lot of
problems. Many data are initialized according to nr_node_ids. That is our
experience when we debug the emulator.

mm/page_alloc.c:
/*
 * Figure out the number of possible node ids.
 */
static void __init setup_nr_node_ids(void)
{
	unsigned int node;
	unsigned int highest = 0;

	for_each_node_mask(node, node_possible_map)
		highest = node;
	nr_node_ids = highest + 1;
}

There is no conflict between emulator and CONFIG_MEMORY_HOTPLUG. A real node can be
 onlined because we already set it as _possible_; if emulator is enabled, all the 
nodes were marked as _possbile_ node, the real ndoe is also included in.

-- 
Thanks & Regards,
Shaohui


WARNING: multiple messages have this Message-ID (diff)
From: Shaohui Zheng <shaohui.zheng@intel.com>
To: David Rientjes <rientjes@google.com>
Cc: Paul Mundt <lethal@linux-sh.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	haicheng.li@linux.intel.com, ak@linux.intel.com,
	shaohui.zheng@linux.intel.com, Yinghai Lu <yinghai@kernel.org>,
	Haicheng Li <haicheng.li@intel.com>
Subject: Re: [2/8,v3] NUMA Hotplug Emulator: infrastructure of NUMA hotplug emulation
Date: Fri, 19 Nov 2010 08:32:25 +0800	[thread overview]
Message-ID: <20101119003225.GB3327@shaohui> (raw)
In-Reply-To: <alpine.DEB.2.00.1011181321470.26680@chino.kir.corp.google.com>

On Thu, Nov 18, 2010 at 01:24:52PM -0800, David Rientjes wrote:
> On Thu, 18 Nov 2010, Shaohui Zheng wrote:
> 
> > in our draft patch, we re-setup nr_node_ids when CONFIG_ARCH_MEMORY_PROBE enabled 
> > and mem=XXX was specified in grub. we set nr_node_ids as MAX_NUMNODES + 1, because
> >  we do not know how many nodes will be hot-added through memory/probe interface. 
> >  it might be a little wasting of memory.
> > 
> 
> nr_node_ids need not be set to anything different at boot, the 
> MEM_GOING_ONLINE callback should be used for anything (like the slab 
> allocators) where a new node is introduced and needs to be dealt with 
> accordingly; this is how regular memory hotplug works, we need no 
> additional code in this regard because it's emulated.  If a subsystem 
> needs to change in response to a new node going online and doesn't as a 
> result of using your emulator, that's a bug and either needs to be fixed 
> or prohibited from use with CONFIG_MEMORY_HOTPLUG.
> 
> (See the MEM_GOING_ONLINE callback in mm/slub.c, for instance, which deals 
> only with the case of node hotplug.)

nr_node_ids is the possible node number. when we do regular memory online,
it is oline to a possible node, and it is already counted in to nr_node_ids.

if you increment nr_node_ids dynamically when node online, it causes a lot of
problems. Many data are initialized according to nr_node_ids. That is our
experience when we debug the emulator.

mm/page_alloc.c:
/*
 * Figure out the number of possible node ids.
 */
static void __init setup_nr_node_ids(void)
{
	unsigned int node;
	unsigned int highest = 0;

	for_each_node_mask(node, node_possible_map)
		highest = node;
	nr_node_ids = highest + 1;
}

There is no conflict between emulator and CONFIG_MEMORY_HOTPLUG. A real node can be
 onlined because we already set it as _possible_; if emulator is enabled, all the 
nodes were marked as _possbile_ node, the real ndoe is also included in.

-- 
Thanks & Regards,
Shaohui

--
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/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply	other threads:[~2010-11-19  1:53 UTC|newest]

Thread overview: 139+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-11-17  2:07 [0/8,v3] NUMA Hotplug Emulator - Introduction & Feedbacks shaohui.zheng
2010-11-17  2:07 ` shaohui.zheng
2010-11-17  2:08 ` [1/8,v3] NUMA Hotplug Emulator: add function to hide memory region via e820 table shaohui.zheng
2010-11-17  2:08   ` shaohui.zheng
2010-11-17  8:16   ` David Rientjes
2010-11-17  8:16     ` David Rientjes
2010-11-18  9:20     ` Shaohui Zheng
2010-11-18  9:20       ` Shaohui Zheng
2010-11-18 21:16       ` David Rientjes
2010-11-18 21:16         ` David Rientjes
2010-11-19  0:12         ` Shaohui Zheng
2010-11-19  0:12           ` Shaohui Zheng
2010-11-21  0:45           ` David Rientjes
2010-11-21  0:45             ` David Rientjes
2010-11-21 14:00             ` Américo Wang
2010-11-21 14:00               ` Américo Wang
2010-11-21 21:33               ` David Rientjes
2010-11-21 21:33                 ` David Rientjes
2010-11-17  2:08 ` [2/8,v3] NUMA Hotplug Emulator: infrastructure of NUMA hotplug emulation shaohui.zheng
2010-11-17  2:08   ` shaohui.zheng
2010-11-17  8:16   ` David Rientjes
2010-11-17  8:16     ` David Rientjes
2010-11-17  7:51     ` Shaohui Zheng
2010-11-17  7:51       ` Shaohui Zheng
2010-11-17 21:10       ` David Rientjes
2010-11-17 21:10         ` David Rientjes
2010-11-18  4:14         ` Shaohui Zheng
2010-11-18  4:14           ` Shaohui Zheng
2010-11-18  6:27           ` Paul Mundt
2010-11-18  6:27             ` Paul Mundt
2010-11-18  5:27             ` Shaohui Zheng
2010-11-18  5:27               ` Shaohui Zheng
2010-11-18 21:24               ` David Rientjes
2010-11-18 21:24                 ` David Rientjes
2010-11-19  0:32                 ` Shaohui Zheng [this message]
2010-11-19  0:32                   ` Shaohui Zheng
2010-11-21  0:48                   ` David Rientjes
2010-11-21  0:48                     ` David Rientjes
2010-11-21  2:28                     ` [patch 1/2] x86: add numa=possible command line option David Rientjes
2010-11-21  2:28                       ` David Rientjes
2010-11-21  2:28                       ` [patch 2/2] mm: add node hotplug emulation David Rientjes
2010-11-21  2:28                         ` David Rientjes
2010-11-21 17:34                         ` Greg KH
2010-11-21 17:34                           ` Greg KH
2010-11-21 21:48                           ` David Rientjes
2010-11-21 21:48                             ` David Rientjes
2010-11-21 23:08                             ` [patch 2/2 v2] " David Rientjes
2010-11-21 23:08                               ` David Rientjes
2010-11-22  0:56                               ` Greg KH
2010-11-22  0:56                                 ` Greg KH
2010-11-28  1:52                                 ` David Rientjes
2010-11-28  1:52                                   ` David Rientjes
2010-11-28  5:17                                   ` Greg KH
2010-11-28  5:17                                     ` Greg KH
2010-11-30  0:04                                     ` David Rientjes
2010-11-30  0:04                                       ` David Rientjes
2010-11-21 14:26                       ` [patch 1/2] x86: add numa=possible command line option Américo Wang
2010-11-21 14:26                         ` Américo Wang
2010-11-21 21:46                         ` David Rientjes
2010-11-21 21:46                           ` David Rientjes
2010-11-22 15:43                           ` Américo Wang
2010-11-22 15:43                             ` Américo Wang
2010-11-21 15:14                     ` [2/8,v3] NUMA Hotplug Emulator: infrastructure of NUMA hotplug emulation Li, Haicheng
2010-11-21 15:14                       ` Li, Haicheng
2010-11-21 21:42                       ` David Rientjes
2010-11-21 21:42                         ` David Rientjes
2010-11-18 21:19           ` David Rientjes
2010-11-18 21:19             ` David Rientjes
2010-11-17  2:08 ` [3/8,v3] NUMA Hotplug Emulator: Userland interface to hotplug-add fake offlined nodes shaohui.zheng
2010-11-17  2:08   ` shaohui.zheng
2010-11-17  8:16   ` David Rientjes
2010-11-17  8:16     ` David Rientjes
2010-11-17  2:08 ` [4/8,v3] NUMA Hotplug Emulator: Abstract cpu register functions shaohui.zheng
2010-11-17  2:08   ` shaohui.zheng
2010-11-17  2:08 ` [5/8,v3] NUMA Hotplug Emulator: support cpu probe/release in x86 shaohui.zheng
2010-11-17  2:08   ` shaohui.zheng
2010-11-21 14:45   ` Américo Wang
2010-11-21 14:45     ` Américo Wang
2010-11-22  0:01     ` Shaohui Zheng
2010-11-22  0:01       ` Shaohui Zheng
2010-11-22 15:51       ` Américo Wang
2010-11-22 15:51         ` Américo Wang
2010-11-22 23:29         ` Shaohui Zheng
2010-11-22 23:29           ` Shaohui Zheng
2010-11-17  2:08 ` [6/8,v3] NUMA Hotplug Emulator: Fake CPU socket with logical CPU on x86 shaohui.zheng
2010-11-17  2:08   ` shaohui.zheng
2010-11-17  2:08 ` [7/8,v3] NUMA Hotplug Emulator: extend memory probe interface to support NUMA shaohui.zheng
2010-11-17  2:08   ` shaohui.zheng
2010-11-17 18:50   ` Dave Hansen
2010-11-17 18:50     ` Dave Hansen
2010-11-17 21:18     ` David Rientjes
2010-11-17 21:18       ` David Rientjes
2010-11-17 21:55       ` Dave Hansen
2010-11-17 21:55         ` Dave Hansen
2010-11-17 22:44         ` David Rientjes
2010-11-17 22:44           ` David Rientjes
2010-11-17 23:00           ` Dave Hansen
2010-11-17 23:00             ` Dave Hansen
2010-11-17 23:17             ` David Rientjes
2010-11-17 23:17               ` David Rientjes
2010-11-18 16:59           ` Aaron Durbin
2010-11-18 16:59             ` Aaron Durbin
2010-11-18  4:48       ` Shaohui Zheng
2010-11-18  4:48         ` Shaohui Zheng
2010-11-18  6:24         ` Paul Mundt
2010-11-18  6:24           ` Paul Mundt
2010-11-18 21:28           ` David Rientjes
2010-11-18 21:28             ` David Rientjes
2010-11-18 21:31         ` David Rientjes
2010-11-18 21:31           ` David Rientjes
2010-11-18  4:36     ` Shaohui Zheng
2010-11-18  4:36       ` Shaohui Zheng
2010-11-19  7:51     ` Shaohui Zheng
2010-11-19 16:36       ` Dave Hansen
2010-11-19 16:36         ` Dave Hansen
2010-11-17  2:08 ` [8/8,v3] NUMA Hotplug Emulator: documentation shaohui.zheng
2010-11-17  2:08   ` shaohui.zheng
2010-11-17 23:06   ` Randy Dunlap
2010-11-17 23:06     ` Randy Dunlap
2010-11-18  2:31     ` Shaohui Zheng
2010-11-18  2:31       ` Shaohui Zheng
2010-11-21 15:03   ` Américo Wang
2010-11-21 15:03     ` Américo Wang
2010-11-21 15:16     ` Li, Haicheng
2010-11-21 15:16       ` Li, Haicheng
2010-11-21 23:33     ` Shaohui Zheng
2010-11-21 23:33       ` Shaohui Zheng
2010-11-22 16:04       ` Américo Wang
2010-11-22 16:04         ` Américo Wang
2010-11-22 23:23         ` Shaohui Zheng
2010-11-22 23:23           ` Shaohui Zheng
2010-11-17  5:22 ` [0/8,v3] NUMA Hotplug Emulator - Introduction & Feedbacks Paul Mundt
2010-11-17  5:22   ` Paul Mundt
2010-11-19  5:54   ` Shaohui Zheng
2010-11-19  5:54     ` Shaohui Zheng
2010-11-17  9:26 ` Yinghai Lu
2010-11-17  9:26   ` Yinghai Lu
2010-11-18  2:03   ` Shaohui Zheng
2010-11-18  2:03     ` Shaohui Zheng

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=20101119003225.GB3327@shaohui \
    --to=shaohui.zheng@intel.com \
    --cc=ak@linux.intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=haicheng.li@intel.com \
    --cc=haicheng.li@linux.intel.com \
    --cc=lethal@linux-sh.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=rientjes@google.com \
    --cc=shaohui.zheng@linux.intel.com \
    --cc=yinghai@kernel.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.