From: Jiang Liu <jiang.liu@linux.intel.com>
To: David Rientjes <rientjes@google.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Mel Gorman <mgorman@suse.de>,
Mike Galbraith <umgwanakikbuti@gmail.com>,
Peter Zijlstra <peterz@infradead.org>,
"Rafael J . Wysocki" <rafael.j.wysocki@intel.com>,
Tang Chen <tangchen@cn.fujitsu.com>, Tejun Heo <tj@kernel.org>,
Cliff Whickman <cpw@sgi.com>, Robin Holt <robinmholt@gmail.com>,
Tony Luck <tony.luck@intel.com>,
linux-mm@kvack.org, linux-hotplug@vger.kernel.org,
linux-kernel@vger.kernel.org, x86@kernel.org
Subject: Re: [Patch V3 3/9] sgi-xp: Replace cpu_to_node() with cpu_to_mem() to support memoryless node
Date: Fri, 9 Oct 2015 13:04:09 +0800 [thread overview]
Message-ID: <56174AC9.4090104@linux.intel.com> (raw)
In-Reply-To: <55D5755C.5060803@linux.intel.com>
On 2015/8/20 14:36, Jiang Liu wrote:
> On 2015/8/20 8:02, David Rientjes wrote:
>> On Wed, 19 Aug 2015, Jiang Liu wrote:
>>
>>>> Why not simply fix build_zonelists_node() so that the __GFP_THISNODE
>>>> zonelists are set up to reference the zones of cpu_to_mem() for memoryless
>>>> nodes?
>>>>
>>>> It seems much better than checking and maintaining every __GFP_THISNODE
>>>> user to determine if they are using a memoryless node or not. I don't
>>>> feel that this solution is maintainable in the longterm.
>>> Hi David,
>>> There are some usage cases, such as memory migration,
>>> expect the page allocator rejecting memory allocation requests
>>> if there is no memory on local node. So we have:
>>> 1) alloc_pages_node(cpu_to_node(), __GFP_THISNODE) to only allocate
>>> memory from local node.
>>> 2) alloc_pages_node(cpu_to_mem(), __GFP_THISNODE) to allocate memory
>>> from local node or from nearest node if local node is memoryless.
>>>
>>
>> Right, so do you think it would be better to make the default zonelists be
>> setup so that cpu_to_node()->zonelists == cpu_to_mem()->zonelists and then
>> individual callers that want to fail for memoryless nodes check
>> populated_zone() themselves?
> Hi David,
> Great idea:) I think that means we are going to kill the
> concept of memoryless node, and we only need to specially handle
> a few callers who really care about whether there is memory on
> local node.
> Then I need some time to audit all usages of __GFP_THISNODE
> and update you whether it's doable.
Hi David,
It seems that I'm too optimistic:(. After auditing all usages
of __GFP_THISNODE and reading Documentation/vm/numa again, I feel it
would be better to keep cpu_to_mem()/numa_mem_id(). It makes things
more clear if we follow rules:
1) cpu_to_node()/numa_node_id() for schedule domain
2) cpu_to_mem()/numa_mem_id() for memory management domain
3) alloc_pages_node(cpu_to_node(cpu), __GFP_THIS_NODE) for special
usage cases.
And it would be easier for maintenance than open-coded checking of
populated_zone() by using alloc_pages_node(cpu_to_node(cpu),
__GFP_THIS_NODE).
Thanks!
Gerry
--
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>
next prev parent reply other threads:[~2015-10-09 5:04 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-08-17 3:18 [Patch V3 0/9] Enable memoryless node support for x86 Jiang Liu
2015-08-17 3:18 ` [Patch V3 1/9] x86, NUMA, ACPI: Online node earlier when doing CPU hot-addition Jiang Liu
2015-08-17 3:18 ` [Patch V3 2/9] kernel/profile.c: Replace cpu_to_mem() with cpu_to_node() Jiang Liu
2015-08-18 0:31 ` David Rientjes
2015-08-19 7:18 ` Jiang Liu
2015-08-20 0:00 ` David Rientjes
2015-10-09 2:35 ` Jiang Liu
2015-08-17 3:19 ` [Patch V3 3/9] sgi-xp: Replace cpu_to_node() with cpu_to_mem() to support memoryless node Jiang Liu
2015-08-18 0:25 ` David Rientjes
2015-08-19 8:20 ` Jiang Liu
2015-08-20 0:02 ` David Rientjes
2015-08-20 6:36 ` Jiang Liu
2015-10-09 5:04 ` Jiang Liu [this message]
2015-08-19 11:52 ` Robin Holt
2015-08-19 12:45 ` Jiang Liu
2015-08-17 3:19 ` [Patch V3 4/9] openvswitch: " Jiang Liu
2015-08-18 0:14 ` Pravin Shelar
2015-08-17 3:19 ` [Patch V3 5/9] i40e: Use numa_mem_id() to better " Jiang Liu
2015-08-18 0:35 ` David Rientjes
2015-08-19 22:38 ` [Intel-wired-lan] " Patil, Kiran
2015-08-20 0:18 ` David Rientjes
2015-10-08 20:20 ` Andrew Morton
2015-10-09 5:52 ` Jiang Liu
2015-10-09 9:08 ` Kamezawa Hiroyuki
2015-10-09 9:25 ` Jiang Liu
2015-08-17 3:19 ` [Patch V3 6/9] i40evf: " Jiang Liu
2015-08-17 19:03 ` [Intel-wired-lan] " Patil, Kiran
2015-08-18 21:34 ` Jeff Kirsher
2015-08-17 3:19 ` [Patch V3 7/9] x86, numa: Kill useless code to improve code readability Jiang Liu
2015-08-17 3:19 ` [Patch V3 8/9] mm: Update _mem_id_[] for every possible CPU when memory configuration changes Jiang Liu
2015-08-17 3:19 ` [Patch V3 9/9] mm, x86: Enable memoryless node support to better support CPU/memory hotplug Jiang Liu
2015-08-18 6:11 ` Tang Chen
2015-08-18 6:59 ` Jiang Liu
2015-08-18 11:28 ` Tang Chen
2015-08-18 7:31 ` Ingo Molnar
2015-08-17 21:35 ` [Patch V3 0/9] Enable memoryless node support for x86 Andrew Morton
2015-08-18 10:02 ` Tang Chen
2015-08-19 8:09 ` Jiang Liu
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=56174AC9.4090104@linux.intel.com \
--to=jiang.liu@linux.intel.com \
--cc=akpm@linux-foundation.org \
--cc=cpw@sgi.com \
--cc=linux-hotplug@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=peterz@infradead.org \
--cc=rafael.j.wysocki@intel.com \
--cc=rientjes@google.com \
--cc=robinmholt@gmail.com \
--cc=tangchen@cn.fujitsu.com \
--cc=tj@kernel.org \
--cc=tony.luck@intel.com \
--cc=umgwanakikbuti@gmail.com \
--cc=x86@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 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).