On 2019/5/29 16:12, Salil Mehta wrote: >> From: netdev-ow...@vger.kernel.org [mailto:netdev-ow...@vger.kernel.org] On >> Behalf Of Yunsheng Lin >> Sent: Tuesday, May 28, 2019 2:04 AM >> >> On 2019/5/27 22:58, Stephen Hemminger wrote: >>> On Mon, 27 May 2019 09:47:54 +0800 >>> Yunsheng Lin <linyunsh...@huawei.com> wrote: >>> >>>> When user has configured a large number of virtual netdev, such >>>> as 4K vlans, the carrier on/off operation of the real netdev >>>> will also cause it's virtual netdev's link state to be processed >>>> in linkwatch. Currently, the processing is done in a work queue, >>>> which may cause worker starvation problem for other work queue. > > > I think we had already discussed about this internally and using separate > workqueue with WQ_UNBOUND should solve this problem. HNS3 driver was sharing > workqueue with the system workqueue.
Yes, using WQ_UNBOUND wq in hns3 solved the cpu starvation for hns3 workqueue. But the rtnl_lock taken by linkwatch is still a problem for hns3's reset workqueue to do the down operation, which need a rtnl_lock. > > >>>> This patch releases the cpu when link watch worker has processed >>>> a fixed number of netdev' link watch event, and schedule the >>>> work queue again when there is still link watch event remaining. > > > We need proper examples/use-cases because of which we require above > kind of co-operative scheduling. Touching the common shared queue logic > which solid argument might invite for more problem to other modules. > > >>>> Signed-off-by: Yunsheng Lin <linyunsh...@huawei.com> >>> >>> Why not put link watch in its own workqueue so it is scheduled >>> separately from the system workqueue? >> >> From testing and debuging, the workqueue runs on the cpu where the >> workqueue is schedule when using normal workqueue, even using its >> own workqueue instead of system workqueue. So if the cpu is busy >> processing the linkwatch event, it is not able to process other >> workqueue' work when the workqueue is scheduled on the same cpu. >> >> Using unbound workqueue may solve the cpu starvation problem. > > [...] > >> But the __linkwatch_run_queue is called with rtnl_lock, so if it >> takes a lot time to process, other need to take the rtnl_lock may >> not be able to move forward. > > Please help me in understanding, Are you trying to pitch this patch > to solve more general system issue OR still your argument/concern > is related to the HNS3 driver problem mentioned in this patch? As about. > > Salil. > > > > > > >