From: Dave Hansen <dave.hansen@intel.com>
To: "Huang, Ying" <ying.huang@intel.com>,
Dave Hansen <dave.hansen@linux.intel.com>
Cc: linux-kernel@vger.kernel.org, oliver.sang@intel.com,
mhocko@suse.com, weixugc@google.com, osalvador@suse.de,
rientjes@google.com, dan.j.williams@intel.com, david@redhat.com,
gthelen@google.com, yang.shi@linux.alibaba.com,
akpm@linux-foundation.org
Subject: Re: [PATCH 1/2] mm/migrate: optimize hotplug-time demotion order updates
Date: Mon, 20 Sep 2021 14:37:28 -0700 [thread overview]
Message-ID: <2d7e4078-f9c0-7511-0bab-de5dab25b45d@intel.com> (raw)
In-Reply-To: <87k0jeog7r.fsf@yhuang6-desk2.ccr.corp.intel.com>
[-- Attachment #1: Type: text/plain, Size: 1572 bytes --]
On 9/17/21 5:55 PM, Huang, Ying wrote:
>> @@ -3147,6 +3177,16 @@ static void __set_migration_target_nodes
>> int node;
>>
>> /*
>> + * The "migration path" array is heavily optimized
>> + * for reads. This is the write side which incurs a
>> + * very heavy synchronize_rcu(). Avoid this overhead
>> + * when nothing of consequence has changed since the
>> + * last write.
>> + */
>> + if (!node_demotion_topo_changed())
>> + return;
>> +
>> + /*
>> * Avoid any oddities like cycles that could occur
>> * from changes in the topology. This will leave
>> * a momentary gap when migration is disabled.
> Now synchronize_rcu() is called in disable_all_migrate_targets(), which
> is called for MEM_GOING_OFFLINE. Can we remove the synchronize_rcu()
> from disable_all_migrate_targets() and call it in
> __set_migration_target_nodes() before we update the node_demotion[]?
I see what you are saying. This patch just targeted
__set_migration_target_nodes() which is called in for
MEM_ONLINE/OFFLINE. But, it missed MEM_GOING_OFFLINE's call to
disable_all_migrate_targets().
I think I found something better than what I had in this patch, or the
tweak you suggested: The 'memory_notify->status_change_nid' field is
passed to all memory hotplug notifiers and tells us whether the node is
going online/offline. Instead of trying to track the changes, I think
we can simply rely on it to tell us when a node is going online/offline.
This removes the need for the demotion code to track *any* state. I've
attached a totally untested patch to do this.
[-- Attachment #2: faster-node-order.patch --]
[-- Type: text/x-patch, Size: 815 bytes --]
diff -puN mm/migrate.c~faster-node-order mm/migrate.c
--- a/mm/migrate.c~faster-node-order 2021-09-17 14:44:58.697476940 -0700
+++ b/mm/migrate.c 2021-09-20 14:31:43.570477095 -0700
@@ -3239,8 +3239,18 @@ static int migration_offline_cpu(unsigne
* set_migration_target_nodes().
*/
static int __meminit migrate_on_reclaim_callback(struct notifier_block *self,
- unsigned long action, void *arg)
+ unsigned long action, void *_arg)
{
+ struct memory_notify *arg = _arg;
+
+ /*
+ * Only update the node migration order when a node is
+ * changing status, like online->offline. This avoids
+ * the overhead of synchronize_rcu() in most cases.
+ */
+ if (arg->status_change_nid < 0)
+ return notifier_from_errno(0);
+
switch (action) {
case MEM_GOING_OFFLINE:
/*
_
next prev parent reply other threads:[~2021-09-20 21:41 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-09-17 22:35 [PATCH 0/2] mm/migrate: 5.15 fixes for automatic demotion Dave Hansen
2021-09-17 22:35 ` [PATCH 1/2] mm/migrate: optimize hotplug-time demotion order updates Dave Hansen
2021-09-18 0:55 ` Huang, Ying
2021-09-20 21:37 ` Dave Hansen [this message]
2021-09-21 7:23 ` David Hildenbrand
2021-09-21 14:36 ` Huang, Ying
2021-09-21 17:01 ` Dave Hansen
2021-09-22 2:19 ` Huang, Ying
2021-09-23 4:44 ` Huang, Ying
2021-09-17 22:35 ` [PATCH 2/2] mm/migrate: add CPU hotplug to demotion #ifdef Dave Hansen
2021-09-17 23:04 ` Wei Xu
2021-09-24 16:12 [PATCH 0/2] [v2] mm/migrate: 5.15 fixes for automatic demotion Dave Hansen
2021-09-24 16:12 ` [PATCH 1/2] mm/migrate: optimize hotplug-time demotion order updates Dave Hansen
2021-09-24 16:45 ` David Hildenbrand
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=2d7e4078-f9c0-7511-0bab-de5dab25b45d@intel.com \
--to=dave.hansen@intel.com \
--cc=akpm@linux-foundation.org \
--cc=dan.j.williams@intel.com \
--cc=dave.hansen@linux.intel.com \
--cc=david@redhat.com \
--cc=gthelen@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mhocko@suse.com \
--cc=oliver.sang@intel.com \
--cc=osalvador@suse.de \
--cc=rientjes@google.com \
--cc=weixugc@google.com \
--cc=yang.shi@linux.alibaba.com \
--cc=ying.huang@intel.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).