SCTP supports multistreaming. It solves the head-of-line blocking problem of TCP and makes SCTP a proper transport for signaling. However, this feature can be further exploited to provide QoS scheduling among multiple streams. This is what we want to add in this patch. In the current implementation, multiple streams in an SCTP association are scheduled in a first-come-first-serve (FCFS) fashion. We would like to augment this simple algorithm with many other scheduling algorithms and let the application choose which scheduling algorithm they want to use. We provide a multistream scheduling framework in the kernel so that different scheduling algorithms can be implemented as kernel modules. We also extend the SCTP socket API to include a new socket option for applications to choose and configure the scheduling algorithm. This approach is inspired by the pluggable TCP congestion control mechanism in the Linux kernel. Note that this modification doesn't change the protocol on the wire. It only changes the internal scheduling. Therefore, it won't cause any interoperability problem. Further, this modification doesn't change the congestion control algorithm of SCTP. It only changes which data chunk should be transmitted first, under the constraints of the congestion window. Therefore, it's safe to be deployed in the Internet. -- To unsubscribe from this list: send the line "unsubscribe linux-sctp" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
