On Thu, Sep 27, 2018 at 4:51 AM Jason Wang <jasow...@redhat.com> wrote: > > > > On 2018年09月14日 12:46, Willem de Bruijn wrote: > >> I'm not sure I get this. If we don't enable tx napi, we tend to delay TX > >> interrupt if we found the ring is about to full to avoid interrupt > >> storm, so we're probably ok in this case. > > I'm only concerned about the transition state when converting from > > napi to no-napi when the queue is stopped and tx interrupt disabled. > > > > With napi mode the interrupt is only disabled if napi is scheduled, > > in which case it will eventually reenable the interrupt. But when > > switching to no-napi mode in this state no progress will be made. > > > > But it seems this cannot happen. When converting to no-napi > > mode, set_coalesce waits for napi to complete in napi_disable. > > So the interrupt should always start enabled when transitioning > > into no-napi mode. > > An update, I meet a hang in napi_disalbe(). But it's hard to be > reproduced. I tend to choose a easy way like V1 that only allow the > switching when device is down.
I agree. > I will post the patch after a vacation. (or you can post if it was > urgent for you). If you have time to review and add your signed-off-by, I can post it. It's a pretty small diff at this point. But no rush, we can also wait until after your vacation. I also need to look at a patch to toggle LRO using ethtool, btw.
