Back to results
US 12,452,185 B1Granted
Predictive management of a network buffer
AssigneeCable Television Laboratories, Inc.
InventorsGregory C. White, Joey Padden, Takashi Hayakawa
Life of this patent
Estimating the term…
Abstract
Predictive management of a network buffer is contemplated. The network buffer maybe predictively managed to control packet drop based at least in part on predicted sojourn time. The predicted sojourn time may be determined to predict time needed from an arriving packet to travel through a queue of the network buffer.
Claims11
A method, comprising:
- monitoring a per-packet queuing latency metric for the one or more packets;
- determining if a packet of the one or more packets is a latency intolerant packet or a latency tolerant packet, wherein the step of determining is based on the monitored per-packet queueing latency metric for the packet;
- marking the latency intolerant packet with a first marking such that the marked packet will be sent to a first queue, the first queue having a first size;
- not marking the latency tolerant packet such that the unmarked packet will be sent to a second queue, the second queue having a second size greater than the first size;
- outputting a drop probability for the packet based on at least one of a present monitored per-packet queuing latency metric for the packet, a recent history of the monitored per-packet queuing latency metric for the packet, a rate of change in the monitored per-packet queuing latency metric for the packet, and an amount of time that the monitored per-packet queuing latency metric for the packet has remained above a certain threshold;
- and
- adjusting the packet drop rate in response to a change in the monitored per-packet queuing latency metric.
4 more elements
A method, comprising:
- monitoring a per-packet queuing latency metric for the one or more packets;
- determining if a packet of the one or more packets is a latency intolerant packet or a latency tolerant packet, wherein the step of determining is based on the monitored per-packet queueing latency metric for the packet;
- marking the latency intolerant packet with a first marking such that the marked packet will be sent to a first queue, the first queue having a first size;
- marking the latency tolerant packet with a second marking such that the unmarked packet will be sent to a second queue, the second queue having a second size greater than the first size;
- outputting a drop probability for the packet based on at least one of a present monitored per-packet queuing latency metric for the packet, a recent history of the monitored per-packet queuing latency metric for the packet, a rate of change in the monitored per-packet queuing latency metric for the packet, and an amount of time that the monitored per-packet queuing latency metric for the packet has remained above a certain threshold;
- and
- adjusting the packet drop rate in response to a change in the monitored per-packet queuing latency metric.
4 more elements
Dependencies are inferred from the claim text.