On Fri, Jun 09, 2017 at 11:18:44AM -0700, Cong Wang wrote: > On Thu, Jun 8, 2017 at 1:12 PM, Krister Johansen > <k...@templeofstupid.com> 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() call is invoked by the gc task once the > > refcount is 0. If the gc task processes a 10th or less of its entries > > on a single pass, it inreases the amount of time it waits between gc > > intervals. > > > > 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 after the gc_task was enqueued for 14 second interval so we had > > to wait longer than the warning time in wait_allrefs in order for the > > dst entry to get free'd and the hold on 'lo' to be released. > > > > I am glad to see you don't have a dst leak here. > > But from my experience of a similar bug (refcnt wait on lo), this goes > infinitely rather than just 14sec, so it looked more like a real leak than > just a gc delay. So in your case, this annoying warning eventually > disappears, right?
That's correct. The problem occurs intermittently, and the warnings are less frequent than the interval in netdev_wait_allrefs(). At least when I observed it, it tended to conincide with our controlplane canary issuing an API call that lead to a network namespace teardown on the dataplane. Sometimes, the message would look like this: unregister_netdevice: waiting for lo to become free. Usage count = 0 The dst entries were getting released, it's just that often our dst cache gc interval was longer than the warning interval in wait_allrefs. The other concern was that because the wait_allrefs happens in the netdev_todo path, a long gc interval can cause the rtnl_lock hold times to be much longer than necessary if this bug is encountered. -K
