Increased packet scheduling throughput and efficiency using über batching
View Patent ↗Described embodiments improve the performance of a computer network via selectively forwarding packets to bypass quality of service (QoS) processing, avoiding processing delays during critical periods of high demand, increasing throughput and efficiency may be increased by sacrificing a small amount of QoS accuracy. QoS processing may be applied to a subset of packets of a flow or connection, referred to herein as “lazy” processing or lazy byte batching. Packets that bypass QoS processing may be immediately forwarded with the same QoS settings as packets of the flow for which QoS processing is applied, resulting in tremendous overhead savings with only minimal decline in accuracy. In case of backlog, packets may be collected together into an aggregated or ‘uber’ packet, with QoS processing applied based on a virtual size of the aggregated packet.
1. A method comprising:
transmitting, by a device while a flow of a plurality of packets is not backlogged, one or more packets of the plurality of packets received by the device;
aggregating, by the device responsive to the flow becoming backlogged, a number of the plurality of packets into a virtual packet, the virtual packet having a size based on a sum of sizes of the number of plurality of packets;
determining, by the device, that a credit of throughput for the virtual packet exceeds a threshold based on the size; and
selecting, by the device responsive to the determination, a quality of service (QoS) queue from a plurality of QoS queues for transmission of the virtual packet.
2. The method of claim 1 , further comprising transmitting, by the device, the virtual packet as part of the flow via a connection to another device.
3. The method of claim 1 , further comprising determining, by the device, the flow has become backlogged.
4. The method of claim 1 , further comprising incrementing, by the device, the credit of throughput for each packet of the number of the plurality of packets aggregated into the virtual packet.
5. The method of claim 4 , further comprising incrementing the credit based on sizes of the number of the plurality of packets.
6. The method of claim 1 , further comprising resetting, by the device, the credit of throughput responsive to applying QoS to the virtual packet.
7. The method of claim 1 , further comprising selecting, by the device, the QoS queue based at least on the size of the virtual packet.
8. A device comprising:
one or more processors, coupled to memory and configured to:
transmit, while a flow of a plurality of packets is not backlogged, one or more packets of the plurality of packets received by the device;
aggregate, responsive to the flow becoming backlogged, a number of the plurality of packets into a virtual packet, the virtual packet having a size based on a sum of sizes of the number of plurality of packets;
determine, that a credit of throughput for the virtual packet exceeds a threshold based on the size; and
select, responsive to the determination, a quality of service (QOS) queue from a plurality of QoS queues for transmission of the virtual packet.
9. The device of claim 8 , wherein the one or more processors are further configured to transmit the virtual packet as part of the flow via a connection to another device.
10. The device of claim 8 , wherein the one or more processors are further configured to determine the flow has become backlogged.
11. The device of claim 8 , wherein the one or more processors are further configured to increment the credit of throughput for each packet of the number of the plurality of packets aggregated into the virtual packet.
12. The device of claim 11 , wherein the one or more processors are further configured to increment the credit based on sizes of the number of the plurality of packets.
13. The device of claim 8 , wherein the one or more processors are further configured to reset the credit of throughput responsive to applying QoS to the virtual packet.
14. The device of claim 8 , wherein the one or more processors are further configured to select the QoS queue based at least on the size of the virtual packet.
15. A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to:
transmit, while a flow of a plurality of packets is not backlogged, one or more packets of the plurality of packets received by the device;
aggregate, responsive to the flow becoming backlogged, a number of the plurality of packets into a virtual packet, the virtual packet having a size based on a sum of sizes of the number of plurality of packets;
determine, that a credit of throughput for the virtual packet exceeds a threshold based on the size; and
select, responsive to the determination, a quality of service (QOS) queue from a plurality of QoS queues for transmission of the virtual packet.
16. The non-transitory computer-readable medium of claim 15 , wherein the one or more processors are further configured to transmit the virtual packet as part of the flow via a connection to another device.
17. The non-transitory computer-readable medium of claim 15 , wherein the one or more processors are further configured to increment the credit of throughput for each packet of the number of the plurality of packets aggregated into the virtual packet.
18. The non-transitory computer-readable medium of claim 17 , wherein the one or more processors are further configured to increment the credit based on sizes of the number of the plurality of packets.
19. The non-transitory computer-readable medium of claim 15 , wherein the one or more processors are further configured to reset the credit of throughput responsive to applying QoS to the virtual packet.
20. The non-transitory computer-readable medium of claim 15 , wherein the one or more processors are further configured to select the QoS queue based at least on the size of the virtual packet.