Network latency optimization
A network may provide latency optimization by configuring respective latency values of one or more network components. A latency manager may receive a request indicative of a maximum latency value of a communications path between two devices, and may determine a particular network latency value. The latency manager may then determine respective endpoint latency values for endpoint devices based on the maximum latency value and network latency values. In addition, buffer characteristics, such as buffer depth at particular devices, may be adjusted in view of the latencies.
1. A method, comprising:
determining, by one or more computing devices and based on a service tier associated with a user, a network latency value for a first device and a network latency value for a second device;
adjusting, based on the network latency value for the first device, a queue associated with the first device; and
adjusting, based on the network latency value for the second device and a device type of the first device, a queue associated with the second device.
2. The method of claim 1 , wherein:
adjusting the queue associated with the first device comprises adjusting, based on the network latency value for the first device, a minimum packet-buffer-queue depth and a maximum packet-buffer-queue depth of the queue associated with the first device; and
adjusting the queue associated with the second device comprises adjusting, based on the network latency value for the second device, a minimum packet-buffer-queue depth and a maximum packet-buffer-queue depth of the queue associated with the second device.
3. The method of claim 2 , wherein adjusting the minimum packet-buffer-queue depth and the maximum packet-buffer-queue depth of the queue associated with the first device comprises adjusting a packet-buffer-queue depth associated with the service tier.
4. The method of claim 3 , wherein each network latency value is based on a maximum latency value for an endpoint-to-endpoint communications path.
5. The method of claim 1 , wherein determining the network latency value for the first device comprises determining, based on a device service tier associated with the first device, the network latency value for the first device.
6. The method of claim 1 , wherein determining the network latency value for the first device comprises determining, based on the device type of the first device, the network latency value for the first device.
7. The method of claim 1 , wherein determining the network latency value for the first device comprises determining, responsive to a determination that a communications link associated with the first device has failed, the network latency value for the first device.
8. The method of claim 1 , wherein determining the network latency value for the first device comprises determining, responsive to a determination that a network latency associated with a communications link associated with the first device exceeds a threshold, the network latency value for the first device.
9. A method, comprising:
adjusting, by a computing device and based on a difference between a requested maximum network latency value and a value indicative of a measured network latency of a network communications path between a computing device of a first type and a computing device of a second type, a minimum packet-buffer-queue depth and a maximum packet-buffer-queue depth of a queue associated with the computing device of the first type to depths determined based on a service tier associated with a user, the second type of computing device being different from the first type of computing device; and
adjusting, by the computing device and based on the difference, a minimum packet-buffer-queue depth and a maximum packet-buffer-queue depth of a queue associated with the computing device of the second type to depths determined based on the service tier associated with the user.
10. The method of claim 9 , further comprising determining the requested maximum network latency value based on the service tier associated with the user.
11. The method of claim 10 , wherein the requested maximum network latency value is associated with a service flow, and wherein adjusting the minimum packet-buffer-queue depth and the maximum packet-buffer-queue depth of the queue associated with the computing device of the first type comprises adjusting a queue associated with the service flow.
12. The method of claim 10 , wherein adjusting the minimum packet-buffer-queue depth and the maximum packet-buffer-queue depth of the queue associated with the computing device of the first type comprises adjusting, based on a subscription tier associated with the computing device of the first type, at least one of the minimum packet-buffer-queue depth or the maximum packet-buffer-queue depth of the queue associated with the computing device of the first type.
13. The method of claim 10 , wherein adjusting the minimum packet-buffer-queue depth and the maximum packet-buffer-queue depth of the queue associated with the computing device of the first type comprises adjusting, responsive to at least one of a determination that a communications link associated with the computing device of the first type has failed or a determination that a network latency associated with the communications link exceeds a threshold, at least one of the minimum packet-buffer-queue depth or the maximum packet-buffer-queue depth of the queue associated with the computing device of the first type.
14. An apparatus comprising:
a processor;
a memory storing computer-executable modules comprising:
an application manager configured to determine a requested network latency based at least on a service tier subscribed to by a user;
a packet queue manager configured to determine an adjusted latency value based on the requested network latency and a measured network latency of a link of a network that interfaces a communication interface of a first device and a communication interface of a second device; and
a policy manager configured to transmit instructions adjusting, based on the adjusted latency value, a queue associated with the first device and a queue associated with the second device.
15. The apparatus of claim 14 , wherein the transmitted instructions further adjust, based on a difference between a value associated with the requested network latency and a value associated with the measured network latency, the queue associated with the first device.
16. The apparatus of claim 15 , wherein the transmitted instructions further adjust, based on the difference, the queue associated with the second device.
17. The apparatus of claim 14 , wherein the policy manager is further configured to readjust the queue associated with the first device responsive to a change in the measured network latency.
18. The apparatus of claim 14 , wherein the transmitted instructions adjust responsive to at least one of a determination that a different link of the network has failed or a determination that a network latency measurement associated with the first device exceeds a threshold.
19. The apparatus of claim 14 , wherein the transmitted instructions further adjust at least one of a minimum packet-buffer-queue depth or a maximum packet-buffer-queue depth of the queue associated with the first device.
20. The apparatus of claim 14 , wherein the transmitted instructions further adjust at least one of a minimum packet-buffer-queue depth or a maximum packet-buffer-queue depth of the queue associated with the second device.