On Fri, 22 Mar 2019, Waiman Long wrote: > > > >> I am looking forward to it. > > There is also alrady rcu being used in these paths. kfree_rcu() would not > > be enough? It is an estalished mechanism that is mature and well > > understood. > > > In this case, the memory objects are from kmem caches, so they can't > freed using kfree_rcu(). Oh they can. kfree() can free memory from any slab cache. > There are certainly overhead using the kfree_rcu(), or a > kfree_rcu()-like mechanism. Also I think the actual freeing is done at > SoftIRQ context which can be a problem if there are too many memory > objects to free. No there is none that I am aware of. And this has survived testing of HPC loads with gazillion of objects that have to be freed from multiple processors. We really should not rearchitect this stuff... It took us quite a long time to have this scale well under all loads. Please use rcu_free().
