Messages in this thread | | | Date | Tue, 04 Jun 2013 11:52:45 +0300 | From | Eliezer Tamir <> | Subject | Re: [PATCH v8 net-next 5/7] net: simple poll/select low latency socket poll |
| |
On 03/06/2013 16:59, Eliezer Tamir wrote: > On 03/06/2013 16:15, Eric Dumazet wrote: >> On Mon, 2013-06-03 at 11:02 +0300, Eliezer Tamir wrote: >>> sock = file->private_data; >>> - return sock->ops->poll(file, sock, wait); >>> + >>> + poll_result = sock->ops->poll(file, sock, wait); >>> + >>> + if (!(poll_result & (POLLRDNORM | POLLERR | POLLRDHUP | >>> POLLHUP)) && >>> + sk_valid_ll(sock->sk) && sk_poll_ll(sock->sk, 1)) >>> + poll_result = sock->ops->poll(file, sock, NULL); >>> + >>> + return poll_result; >>> } >>> >>> static int sock_mmap(struct file *file, struct vm_area_struct *vma) >>> >> >> >> In fact, for TCP, POLLOUT event being ready can also be triggered by >> incoming messages, as the ACK might allow the user application to push >> more data in the write queue. >> >> And you might check wait->_key to avoid testing flags that user is not >> interested into. > > yes, comparing to _key is more correct. > In any case this needs to be completely rewritten for support for > working well with a large number of sockets. >
Is it possible for wait to be NULL? (do we need to check for that?) I see that poll_does_not_wait() checks for that, but I could not find anywhere this is actually done.
-Eliezer
| |