From: Christoph Lameter <cl@linux-foundation.org>
To: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Badari Pulavarty <pbadari@us.ibm.com>,
Andrew Morton <akpm@linux-foundation.org>,
Mel Gorman <mel@csn.ul.ie>, linux-mm <linux-mm@kvack.org>,
Linux Kernel ML <linux-kernel@vger.kernel.org>
Subject: Re: [RFC:Patch: 000/008](memory hotplug) rough idea of pgdat removing
Date: Thu, 31 Jul 2008 09:04:26 -0500 [thread overview]
Message-ID: <4891C66A.3040302@linux-foundation.org> (raw)
In-Reply-To: <20080731203549.2A3F.E1E9C6FF@jp.fujitsu.com>
Yasunori Goto wrote:
> Current my idea is using RCU feature for waiting them.
> Because it is the least impact against reader's performance,
> and pgdat remover can wait finish of reader's access to pgdat
> which is removing by synchronize_sched().
The use of RCU disables preemption which has implications as to what can be done in a loop over nodes or zones. This would also potentially add more overhead to the page allocator hotpaths.
> If you have better idea, please let me know.
Use stop_machine()? The removal of a zone or node is a pretty rare event after all and it would avoid having to deal with rcu etc etc.
WARNING: multiple messages have this Message-ID (diff)
From: Christoph Lameter <cl@linux-foundation.org>
To: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Badari Pulavarty <pbadari@us.ibm.com>,
Andrew Morton <akpm@linux-foundation.org>,
Mel Gorman <mel@csn.ul.ie>, linux-mm <linux-mm@kvack.org>,
Linux Kernel ML <linux-kernel@vger.kernel.org>
Subject: Re: [RFC:Patch: 000/008](memory hotplug) rough idea of pgdat removing
Date: Thu, 31 Jul 2008 09:04:26 -0500 [thread overview]
Message-ID: <4891C66A.3040302@linux-foundation.org> (raw)
In-Reply-To: <20080731203549.2A3F.E1E9C6FF@jp.fujitsu.com>
Yasunori Goto wrote:
> Current my idea is using RCU feature for waiting them.
> Because it is the least impact against reader's performance,
> and pgdat remover can wait finish of reader's access to pgdat
> which is removing by synchronize_sched().
The use of RCU disables preemption which has implications as to what can be done in a loop over nodes or zones. This would also potentially add more overhead to the page allocator hotpaths.
> If you have better idea, please let me know.
Use stop_machine()? The removal of a zone or node is a pretty rare event after all and it would avoid having to deal with rcu etc etc.
--
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:[~2008-07-31 14:05 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-07-31 11:50 [RFC:Patch: 000/008](memory hotplug) rough idea of pgdat removing Yasunori Goto
2008-07-31 11:50 ` Yasunori Goto
2008-07-31 11:55 ` [RFC:Patch: 001/008](memory hotplug) change parameter from pointer of zonelist to node id Yasunori Goto
2008-07-31 11:55 ` Yasunori Goto
2008-07-31 11:56 ` [RFC:Patch: 002/008](memory hotplug) pgdat_remove_read_lock/unlock Yasunori Goto
2008-07-31 11:56 ` Yasunori Goto
2008-07-31 11:58 ` [RFC:Patch: 003/008](memory hotplug) check node online in __alloc_pages Yasunori Goto
2008-07-31 11:58 ` Yasunori Goto
2008-07-31 12:00 ` [RFC:Patch: 004/008](memory hotplug) Use lock for for_each_online_node Yasunori Goto
2008-07-31 12:00 ` Yasunori Goto
2008-07-31 12:01 ` [RFC:Patch: 005/008](memory hotplug) check node online before NODE_DATA and so on Yasunori Goto
2008-07-31 12:01 ` Yasunori Goto
2008-07-31 12:02 ` [RFC:Patch: 006/008](memory hotplug) kswapd_stop() definition Yasunori Goto
2008-07-31 12:02 ` Yasunori Goto
2008-07-31 12:03 ` [RFC:Patch: 007/008](memory hotplug) callback routine for mempolicy Yasunori Goto
2008-07-31 12:03 ` Yasunori Goto
2008-07-31 12:04 ` [RFC:Patch: 008/008](memory hotplug) remove_pgdat() function Yasunori Goto
2008-07-31 12:04 ` Yasunori Goto
2008-09-06 14:21 ` Peter Zijlstra
2008-09-06 14:21 ` Peter Zijlstra
2008-09-08 3:07 ` Yasunori Goto
2008-09-08 3:07 ` Yasunori Goto
2008-07-31 14:04 ` Christoph Lameter [this message]
2008-07-31 14:04 ` [RFC:Patch: 000/008](memory hotplug) rough idea of pgdat removing Christoph Lameter
2008-08-01 9:42 ` Yasunori Goto
2008-08-01 9:42 ` Yasunori Goto
2008-08-01 13:51 ` Christoph Lameter
2008-08-01 13:51 ` Christoph Lameter
2008-08-02 0:16 ` Yasunori Goto
2008-08-02 0:16 ` Yasunori Goto
2008-08-04 13:25 ` Christoph Lameter
2008-08-04 13:25 ` Christoph Lameter
2008-08-05 6:39 ` Yasunori Goto
2008-08-05 6:39 ` Yasunori Goto
2008-08-05 11:14 ` Mel Gorman
2008-08-05 11:14 ` Mel Gorman
2008-08-05 17:08 ` Christoph Lameter
2008-08-05 17:08 ` Christoph Lameter
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=4891C66A.3040302@linux-foundation.org \
--to=cl@linux-foundation.org \
--cc=akpm@linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mel@csn.ul.ie \
--cc=pbadari@us.ibm.com \
--cc=y-goto@jp.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 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.