Re: [PATCH v2] net: skip genenerating uevents for network namespaces that are exiting

[David Miller]

From: Andrei Vagin 
Date: Mon, 24 Oct 2016 19:09:53 -0700

> No one can see these events, because a network namespace can not be
> destroyed, if it has sockets.
> 
> Unlike other devices, uevent-s for network devices are generated
> only inside their network namespaces. They are filtered in
> kobj_bcast_filter()
> 
> My experiments shows that net namespaces are destroyed more 30% faster
> with this optimization.
> 
> Here is a perf output for destroying network namespaces without this
> patch.
 ...
> It's very critical to optimize the exit path for network namespaces,
> because they are destroyed under net_mutex and many namespaces can be
> destroyed for one iteration.
> 
> v2: use dev_set_uevent_suppress()
> 
> Cc: Cong Wang 
> Cc: "David S. Miller" 
> Cc: Eric W. Biederman 
> Signed-off-by: Andrei Vagin 

Applied to net-next, thanks.

[PATCH v2] net: skip genenerating uevents for network namespaces that are exiting

[Andrei Vagin]

No one can see these events, because a network namespace can not be
destroyed, if it has sockets.

Unlike other devices, uevent-s for network devices are generated
only inside their network namespaces. They are filtered in
kobj_bcast_filter()

My experiments shows that net namespaces are destroyed more 30% faster
with this optimization.

Here is a perf output for destroying network namespaces without this
patch.

-   94.76% 0.02%  kworker/u48:1  [kernel.kallsyms] [k] cleanup_net
   - 94.74% cleanup_net
  - 94.64% ops_exit_list.isra.4
 - 41.61% default_device_exit_batch
- 41.47% unregister_netdevice_many
   - rollback_registered_many
  - 40.36% netdev_unregister_kobject
 - 14.55% device_del
+ 13.71% kobject_uevent
 - 13.04% netdev_queue_update_kobjects
+ 12.96% kobject_put
 - 12.72% net_rx_queue_update_kobjects
  kobject_put
- kobject_release
   + 12.69% kobject_uevent
  + 0.80% call_netdevice_notifiers_info
 + 19.57% nfsd_exit_net
 + 11.15% tcp_net_metrics_exit
 + 8.25% rpcsec_gss_exit_net

It's very critical to optimize the exit path for network namespaces,
because they are destroyed under net_mutex and many namespaces can be
destroyed for one iteration.

v2: use dev_set_uevent_suppress()

Cc: Cong Wang 
Cc: "David S. Miller" 
Cc: Eric W. Biederman 
Signed-off-by: Andrei Vagin 
---
 net/core/net-sysfs.c | 14 +++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 6e4f347..d4fe286 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -950,10 +950,13 @@ net_rx_queue_update_kobjects(struct net_device *dev, int 
old_num, int new_num)
}
 
while (--i >= new_num) {
+   struct kobject *kobj = >_rx[i].kobj;
+
+   if (!list_empty(_net(dev)->exit_list))
+   kobj->uevent_suppress = 1;
if (dev->sysfs_rx_queue_group)
-   sysfs_remove_group(>_rx[i].kobj,
-  dev->sysfs_rx_queue_group);
-   kobject_put(>_rx[i].kobj);
+   sysfs_remove_group(kobj, dev->sysfs_rx_queue_group);
+   kobject_put(kobj);
}
 
return error;
@@ -1340,6 +1343,8 @@ netdev_queue_update_kobjects(struct net_device *dev, int 
old_num, int new_num)
while (--i >= new_num) {
struct netdev_queue *queue = dev->_tx + i;
 
+   if (!list_empty(_net(dev)->exit_list))
+   queue->kobj.uevent_suppress = 1;
 #ifdef CONFIG_BQL
sysfs_remove_group(>kobj, _group);
 #endif
@@ -1525,6 +1530,9 @@ void netdev_unregister_kobject(struct net_device *ndev)
 {
struct device *dev = &(ndev->dev);
 
+   if (!list_empty(_net(ndev)->exit_list))
+   dev_set_uevent_suppress(dev, 1);
+
kobject_get(>kobj);
 
remove_queue_kobjects(ndev);
-- 
2.7.4