On Mon, Aug 18, 2014 at 07:47:53PM +0000, Daniele Di Proietto wrote: > On 8/18/14, 11:47 AM, "Ben Pfaff" <b...@nicira.com> wrote: > > >On Mon, Aug 18, 2014 at 11:26:22AM -0700, Daniele Di Proietto wrote: > >> fat_rwlock_tryrdlock() used to call fat_rwlock_get_slot__() which could > >>block > >> in the "slow path" case. This commit adds fat_rwlock_try_get_slot__() > >>which > >> does not block, even in the "slow path" case. > >> > >> Signed-off-by: Daniele Di Proietto <ddiproie...@vmware.com> > > > >What's the visible effect of this patch? Does it make something > >faster? > > Hi Ben, > > this fixes a hang on dpif-netdev: fat_rwlock_tryrdlock() is used to detect > if there?s a registered upcall handler. If the lock is taken (because > there is no upcall handler) the pmd thread is blocked and stops processing > packets. > > The issue specifically happens when creating the datapath with dpctl > commands, so it is not a big problem. > > I will send a v2 with a more clear commit message.
Thanks for the additional details. It makes sense now. _______________________________________________ dev mailing list dev@openvswitch.org http://openvswitch.org/mailman/listinfo/dev
