From: Davidlohr Bueso <dave@xxxxxxxxxxxx> Subject: fs/epoll: drop ovflist branch prediction The ep->ovflist is a secondary ready-list to temporarily store events that might occur when doing sproc without holding the ep->wq.lock. This accounts for every time we check for ready events and also send events back to userspace; both callbacks, particularly the latter because of copy_to_user, can account for a non-trivial time. As such, the unlikely() check to see if the pointer is being used, seems both misleading and sub-optimal. In fact, we go to an awful lot of trouble to sync both lists, and populating the ovflist is far from an uncommon scenario. For example, profiling a concurrent epoll_wait(2) benchmark, with CONFIG_PROFILE_ANNOTATED_BRANCHES shows that for a two threads a 33% incorrect rate was seen; and when incrementally increasing the number of epoll instances (which is used, for example for multiple queuing load balancing models), up to a 90% incorrect rate was seen. Similarly, by deleting the prediction, 3% throughput boost was seen across incremental threads. Link: http://lkml.kernel.org/r/20181108051006.18751-4-dave@xxxxxxxxxxxx Signed-off-by: Davidlohr Bueso <dbueso@xxxxxxx> Reviewed-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx> Cc: Jason Baron <jbaron@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- fs/eventpoll.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/fs/eventpoll.c~fs-epoll-drop-ovflist-branch-prediction +++ a/fs/eventpoll.c @@ -1153,7 +1153,7 @@ static int ep_poll_callback(wait_queue_e * semantics). All the events that happen during that period of time are * chained in ep->ovflist and requeued later on. */ - if (unlikely(ep->ovflist != EP_UNACTIVE_PTR)) { + if (ep->ovflist != EP_UNACTIVE_PTR) { if (epi->next == EP_UNACTIVE_PTR) { epi->next = ep->ovflist; ep->ovflist = epi; _
