The authors distinguish between four types of service that may beprovided to real-time traffic by packet-switched networks, ranging from“need-blind” and “need-based best-effort” to“guaranteed throughput” and “bounded delayjitter” services. They evaluate a number of scheduling policiesthat offer need-based, best-effort service. They introduce hop-laxity(HL) scheduling which is based on the time remaining until the packetmust reach its destination as well as the number of hops separating itfrom the destination. HL scheduling is evaluated through simulation andhas been implemented within a BSD-based kernel and tested on the DARTnetnetwork. The results indicate that HL scheduling tends to equalizedelays between calls with large and small number of hops as compared toa FIFO discipline, reducing the 99.9% percentile of delay and thefraction of late packets. They compare HL scheduling to the FIFO+discipline suggested by Clark et al., (see SIGCOMM Symposium onCommunications Architectures and Protocols, p.14-26, 1992, and ComputerCommunication Review, vol.22, no.4) and find that their delay propertiesare similar. Other disciplines, such as minimum laxity or transitpriority, may actually do more harm than good
展开▼
