queued gives what was written in the outbound queue already, and the queued + size checks that what is going to be written is not exceeding the configured limit.

Have you increased the limits with global parameters (tcp_conn_wq_max and tcp_wq_max), or just used the defaults? If you deal with large output, these values have to be adjusted.


You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub, or mute the thread.