[nanomsg] Lock in nn_sock_send
- From: Steven Wu <stevenwu.ucd@xxxxxxxxx>
- To: nanomsg@xxxxxxxxxxxxx
- Date: Fri, 13 Sep 2013 12:49:59 -0400
Hi All,
Here is a question about where there is a possible performance penalty or a
better solution for it. The send function nn_sock_send will require a lock
through nn_ctx_enter(&self->ctx); I guess the self is the super socket
which may have many connections. I'm afraid that all of the connections of
a super socket sharing a single lock may have performance penalty
underneath.
Thanks,
Steven
Other related posts:
