Throughput degradations for single packet messages (RFC0632)
Original Publication Date: 1974-May-01
Included in the Prior Art Database: 2019-Feb-12
Internet Society Requests For Comment (RFCs)
Network Working Group H. Opderbeck Request for Comments: #632 UCLA-NMC NIC # 30239 20 May 1974
Throughput Degradations for Single Packet Messages
The transmission of digitized speech over the ARPANET represents a new dimension in the use of packet switching systems. The throughput and delay requirements for this newly emerging application area are quite different from the throughput and delay requirements for interactive use or file transfers. In particular, we need to achieve a high throughput for small messages since long messages result in long source delays to fill the large buffers. Therefore we are currently studying the throughput limits for single-packet messages. We realize that up to now little attempt was made to optimize throughput for low delay traffic. It was nevertheless surprising for us to find out that the observed throughput for single-packet messages is in many cases only about one fourth of what one would expect. In what follows we are going to explain why this happens and what could be done to correct this situation.
On April 1, 1974, we sent, using the IMP message generator, single- packet messages at the highest possible rate ("RFNM-driven") from the MOFFET-IMP to the SRI-IMP. There are two three-hop paths from MOFFET to SRI, one of them involving two 230.4 kbs circuits. Since there was hardly any interfering traffic we expected an average round-trip delay of not more than 100 msec. Assuming that there are, on an average, 3 messages in transmission between MOFFET and SRI and assuming a message length of about 1000 bits this should result in a throughout of more than 30 kbs. The observed through was, however, less than 8 kbs. A repetition of the experiment showed the same result. A more detailed analysis of the collected data revealed that an average number of 3.5 messages were simultaneously in transmission between MOFFET and SRI. The throughput degradation could therefore not have been due to interfering traffic between these two sites. Also the channel utilization for all channels that were involved in the transmission was less than 40 percent. The observed mean round-trip times between MOFFET and SRI, however, were about 500 msec. Since these large round-trip times were obviously not due to physical limitations, we studied the flow control mechanism for single-packet messages and were able to come up with an explanation for this undesirable behavior.
When a single-packet message arrives at the destination IMP out of order (i.e., the logically preceding message has not yet arrived there) it is not accepted by the destination IMP. It is rather treated as a request for the allocation of one reassembly buffer. The corresponding ALLOCATE
Opderbeck [Page 1]
RFC 632 Throughput Degradations for Single Packet Messages May 1974
is then sent back to the source IMP only after the RFNM for the previous message has been processed. We therefore may have the following sequence of events:
1 MSG(i) sent from SOURCE-IMP (message i is...