On Fri, Jun 9, 2017 at 11:43 AM, Krister Johansen
wrote:
> On Fri, Jun 09, 2017 at 11:18:44AM -0700, Cong Wang wrote:
>> On Thu, Jun 8, 2017 at 1:12 PM, Krister Johansen
>> wrote:
>> > The way this works is that if there's still a reference on the dst entry
>> > at the time we try to free it, it
On Fri, Jun 09, 2017 at 11:18:44AM -0700, Cong Wang wrote:
> On Thu, Jun 8, 2017 at 1:12 PM, Krister Johansen
> wrote:
> > The way this works is that if there's still a reference on the dst entry
> > at the time we try to free it, it gets placed in the gc list by
> > __dst_free and the dst_destroy
On Thu, Jun 8, 2017 at 1:12 PM, Krister Johansen
wrote:
> After looking through the list of callbacks that the netdevice notifiers
> invoke in this path, it appears that the dst_dev_event is the most
> interesting. The dst_ifdown path places a hold on the loopback_dev as
> part of releasing the d
From: Krister Johansen
Date: Thu, 8 Jun 2017 13:12:38 -0700
> It looks like this:
>
> Message from syslogd@flamingo at Apr 26 00:45:00 ...
> kernel:unregister_netdevice: waiting for lo to become free. Usage count = 4
>
> They seem to coincide with net namespace teardown.
>
> The message is em
> Wei Wan is actually working on a patch series removing all this
> dst_garbage list stuff.
Yes. I am working on removing the dst garbage collector completely.
dst_dev_event() will be removed from the list of callbacks that the
netdevice notifiers invoke in my patch series.
On Thu, Jun 8, 2017 at
On Thu, 2017-06-08 at 13:12 -0700, Krister Johansen wrote:
...
> Looking at the gc_task intervals, they started at 663ms when we invoked
> __dst_free(). After that, they increased to 1663, 3136, 5567, 8191,
> 10751, and 14848. The release that set the refcnt to 0 on our dst entry
> occurred aft
It looks like this:
Message from syslogd@flamingo at Apr 26 00:45:00 ...
kernel:unregister_netdevice: waiting for lo to become free. Usage count = 4
They seem to coincide with net namespace teardown.
The message is emitted by netdev_wait_allrefs().
Forced a kdump in netdev_run_todo, but found
