From: Li Zefan <lizefan-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
To: Tejun Heo <tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
Cc: Cgroups <cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
Containers
<containers-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org>,
LKML <linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>
Subject: [PATCH v2 10/10] cpuset: fix to migrate mm correctly in a corner case
Date: Wed, 5 Jun 2013 17:17:30 +0800 [thread overview]
Message-ID: <51AF022A.8090208@huawei.com> (raw)
In-Reply-To: <51AF0183.8070602-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
Before moving tasks out of empty cpusets, update_tasks_nodemask()
is called, which calls do_migrate_pages(xx, from, to). Then those
tasks are moved to an ancestor, and do_migrate_pages() is called
again.
The first time: from = node_to_be_offlined, to = empty.
The second time: from = empty, to = ancestor's nodemask.
so looks like no pages will be migrated.
Fix this by:
- Don't call update_tasks_nodemask() on empty cpusets.
- Pass cs->old_mems_allowed to do_migrate_pages().
Signed-off-by: Li Zefan <lizefan-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
---
kernel/cpuset.c | 15 +++++++++++----
1 file changed, 11 insertions(+), 4 deletions(-)
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 9bb6a47..de7f6c1 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1574,9 +1574,16 @@ static void cpuset_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
struct cpuset *mems_oldcs = effective_nodemask_cpuset(oldcs);
mpol_rebind_mm(mm, &cpuset_attach_nodemask_to);
- if (is_memory_migrate(cs))
- cpuset_migrate_mm(mm, &mems_oldcs->mems_allowed,
+ if (is_memory_migrate(cs)) {
+ /*
+ * old_mems_allowed is the same with mems_allowed,
+ * except if this task is being moved automatically
+ * due to hotplug, and in this case mems_allowed is
+ * empty and old_mems_allowed is the offflined node.
+ */
+ cpuset_migrate_mm(mm, &mems_oldcs->old_mems_allowed,
&cpuset_attach_nodemask_to);
+ }
mmput(mm);
}
@@ -2168,7 +2175,7 @@ static void cpuset_propagate_hotplug_workfn(struct work_struct *work)
* for empty cpuset to take on ancestor's cpumask
*/
if ((sane && cpumask_empty(cs->cpus_allowed)) ||
- !cpumask_empty(&off_cpus))
+ (!cpumask_empty(&off_cpus) && !cpumask_empty(cs->cpus_allowed)))
update_tasks_cpumask(cs, NULL);
mutex_lock(&callback_mutex);
@@ -2180,7 +2187,7 @@ static void cpuset_propagate_hotplug_workfn(struct work_struct *work)
* for empty cpuset to take on ancestor's nodemask
*/
if ((sane && nodes_empty(cs->mems_allowed)) ||
- !nodes_empty(off_mems))
+ (!nodes_empty(off_mems) && !nodes_empty(cs->mems_allowed)))
update_tasks_nodemask(cs, NULL);
is_empty = cpumask_empty(cs->cpus_allowed) ||
--
1.8.0.2
WARNING: multiple messages have this Message-ID (diff)
From: Li Zefan <lizefan@huawei.com>
To: Tejun Heo <tj@kernel.org>
Cc: LKML <linux-kernel@vger.kernel.org>,
Cgroups <cgroups@vger.kernel.org>,
Containers <containers@lists.linux-foundation.org>
Subject: [PATCH v2 10/10] cpuset: fix to migrate mm correctly in a corner case
Date: Wed, 5 Jun 2013 17:17:30 +0800 [thread overview]
Message-ID: <51AF022A.8090208@huawei.com> (raw)
In-Reply-To: <51AF0183.8070602@huawei.com>
Before moving tasks out of empty cpusets, update_tasks_nodemask()
is called, which calls do_migrate_pages(xx, from, to). Then those
tasks are moved to an ancestor, and do_migrate_pages() is called
again.
The first time: from = node_to_be_offlined, to = empty.
The second time: from = empty, to = ancestor's nodemask.
so looks like no pages will be migrated.
Fix this by:
- Don't call update_tasks_nodemask() on empty cpusets.
- Pass cs->old_mems_allowed to do_migrate_pages().
Signed-off-by: Li Zefan <lizefan@huawei.com>
---
kernel/cpuset.c | 15 +++++++++++----
1 file changed, 11 insertions(+), 4 deletions(-)
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 9bb6a47..de7f6c1 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1574,9 +1574,16 @@ static void cpuset_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
struct cpuset *mems_oldcs = effective_nodemask_cpuset(oldcs);
mpol_rebind_mm(mm, &cpuset_attach_nodemask_to);
- if (is_memory_migrate(cs))
- cpuset_migrate_mm(mm, &mems_oldcs->mems_allowed,
+ if (is_memory_migrate(cs)) {
+ /*
+ * old_mems_allowed is the same with mems_allowed,
+ * except if this task is being moved automatically
+ * due to hotplug, and in this case mems_allowed is
+ * empty and old_mems_allowed is the offflined node.
+ */
+ cpuset_migrate_mm(mm, &mems_oldcs->old_mems_allowed,
&cpuset_attach_nodemask_to);
+ }
mmput(mm);
}
@@ -2168,7 +2175,7 @@ static void cpuset_propagate_hotplug_workfn(struct work_struct *work)
* for empty cpuset to take on ancestor's cpumask
*/
if ((sane && cpumask_empty(cs->cpus_allowed)) ||
- !cpumask_empty(&off_cpus))
+ (!cpumask_empty(&off_cpus) && !cpumask_empty(cs->cpus_allowed)))
update_tasks_cpumask(cs, NULL);
mutex_lock(&callback_mutex);
@@ -2180,7 +2187,7 @@ static void cpuset_propagate_hotplug_workfn(struct work_struct *work)
* for empty cpuset to take on ancestor's nodemask
*/
if ((sane && nodes_empty(cs->mems_allowed)) ||
- !nodes_empty(off_mems))
+ (!nodes_empty(off_mems) && !nodes_empty(cs->mems_allowed)))
update_tasks_nodemask(cs, NULL);
is_empty = cpumask_empty(cs->cpus_allowed) ||
--
1.8.0.2
next prev parent reply other threads:[~2013-06-05 9:17 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-06-05 9:14 [PATCH v2 00/10] cpuset: implement sane hierarchy behaviors Li Zefan
2013-06-05 9:14 ` Li Zefan
[not found] ` <51AF0183.8070602-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
2013-06-05 9:15 ` [PATCH v2 01/10] cpuset: remove redundant check in cpuset_cpus_allowed_fallback() Li Zefan
2013-06-05 9:15 ` Li Zefan
2013-06-05 9:15 ` [PATCH v2 02/10] cpuset: cleanup guarantee_online_{cpus|mems}() Li Zefan
2013-06-05 9:15 ` Li Zefan
2013-06-05 9:15 ` Li Zefan
2013-06-05 9:15 ` [PATCH v2 03/10] cpuset: remove unnecessary variable in cpuset_attach() Li Zefan
2013-06-05 9:15 ` Li Zefan
2013-06-05 9:15 ` Li Zefan
2013-06-05 9:15 ` [PATCH v2 04/10] cpuset: remove cpuset_test_cpumask() Li Zefan
2013-06-05 9:15 ` Li Zefan
2013-06-05 9:15 ` [PATCH v2 05/10] cpuset: re-structure update_cpumask() a bit Li Zefan
2013-06-05 9:15 ` Li Zefan
[not found] ` <51AF01CF.1070706-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
2013-06-05 20:57 ` Tejun Heo
2013-06-05 20:57 ` Tejun Heo
2013-06-05 9:16 ` [PATCH v2 06/10] cpuset: record old_mems_allowed in struct cpuset Li Zefan
2013-06-05 9:16 ` Li Zefan
[not found] ` <51AF01E8.8080205-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
2013-06-05 19:45 ` Tejun Heo
2013-06-05 19:45 ` Tejun Heo
[not found] ` <20130605194522.GG10693-9pTldWuhBndy/B6EtB590w@public.gmane.org>
2013-06-06 9:58 ` Li Zefan
2013-06-06 9:58 ` Li Zefan
2013-06-05 9:16 ` [PATCH v2 07/10] cpuset: introduce effective_{cpumask|nodemask}_cpuset() Li Zefan
2013-06-05 9:16 ` Li Zefan
2013-06-05 9:16 ` [PATCH v2 08/10] cpuset: allow to keep tasks in empty cpusets Li Zefan
2013-06-05 9:16 ` Li Zefan
[not found] ` <51AF020B.3030701-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
2013-06-05 20:51 ` Tejun Heo
2013-06-05 20:51 ` Tejun Heo
[not found] ` <20130605205146.GI10693-9pTldWuhBndy/B6EtB590w@public.gmane.org>
2013-06-06 10:26 ` Li Zefan
2013-06-06 10:26 ` Li Zefan
2013-06-06 10:26 ` Li Zefan
[not found] ` <51B063E6.30107-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>
2013-06-06 21:24 ` Tejun Heo
2013-06-06 21:24 ` Tejun Heo
2013-06-06 21:24 ` Tejun Heo
2013-06-05 9:17 ` [PATCH v2 09/10] cpuset: allow to move tasks to " Li Zefan
2013-06-05 9:17 ` Li Zefan
2013-06-05 9:17 ` Li Zefan [this message]
2013-06-05 9:17 ` [PATCH v2 10/10] cpuset: fix to migrate mm correctly in a corner case Li Zefan
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=51AF022A.8090208@huawei.com \
--to=lizefan-hv44wf8li93qt0dzr+alfa@public.gmane.org \
--cc=cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=containers-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org \
--cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.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.