Following up on this: Carlo and I both tried disabling Nagle on the
sockets (both ends). We still saw the same slow sending pattern.
On one end (the "ircu" process in Carlo's original mail), the send and
receive buffers (SO_SNDBUF, SO_RCVBUF) had been set to 8 KB each. If
these are increased to be larger than the loopback MTU, it makes the
problem go away. (On the other, "srvx" end, the buffer sizes were
kept at the default.)
Is this expected behavior? If so, why? (The references I've found on
the web suggest that the send and receive buffer sizes would only come
into play if Nagle were still enabled.)
-- Entrope
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Thu Nov 15 2001 - 21:00:22 EST