From: Hannes Frederic Sowa > On Fri, Apr 11, 2014 at 11:30:44AM +0900, YOSHIFUJI Hideaki wrote: > > Eric Dumazet wrote: > > > > > We must limit the IPv6 MTU to (65535 + 40) bytes in theory. > > > > > > In practice, its better to align to a multiple of 4 for optimal TCP > > > performance. > > > > It is a TCP issue. We should not limit the mtu to 65532+40. > > I am for 65535+40. Otherwise, other protocol such as UDP cannot > > use full mtu as before. > > I have not seen problems with max ipv6 mtu limit of 65535+40 and tcp. > > I agree this would be a better approach, and maybe & ~3 the mtu/mss > in tcp code? I assume people expect maximum udp packet sizes working > over loopback? The 'trick' would be to generate slightly short messages in the tcp transmit code when doing so wouldn't generate an extra packet. So (using very small numbers) if the max userdata was 63 bytes a 120 byte transmit would generate two 60 byte packets, but 121 to 126 byte transmits would still generate two packets. David ��.n��������+%������w��{.n����z����ܨ}���Ơz�j:+v�����w����ޙ��&�)ߡ�a����z�ޗ���ݢj��w�f