Apparatus to achieve quality of service (QoS) without requiring fabric speedup

Patent metadata

Field	Value
Publication number	US-9369397-B1
Application number	US-201414332564-A
Country	US
Kind code	B1
Filing date	Jul 16, 2014
Priority date	Jul 16, 2014
Publication date	Jun 14, 2016
Grant date	Jun 14, 2016

Abstract

A device may store a credit value for each of multiple output components. The device may receive packets from a network device via an input component. The device may cause the input component to queue the packets. The device may selectively dequeue a packet from the input component, to be sent to an output component, based on whether the credit value for the output component satisfies a credit threshold. The device may send the packet to the output component based on a destination of the packet when the packet is dequeued from the input component. The device may determine a size of the packet after the packet is dequeued. The device may update the credit value for the output component based on the size of the packet. The device may output the packet to another network device via the output component.

First claim

What is claimed is:

1. A device, comprising:
one or more processors to:
store a credit value for each of a plurality of output components;
receive packets from a network device via an input component;
cause the input component to queue the packets,
selectively dequeue a packet from the input component, to be sent to an output component, based on whether the credit value for the output component satisfies a credit threshold,
the packets including the packet, and
the plurality of output components including the output component;

send the packet to the output component based on a destination of the packet when the packet is dequeued from the input component;
determine a size of the packet after the packet is dequeued;
update the credit value for the output component based on the size of the packet; and
output the packet to another network device via the output component.

2. The device of claim 1 , where the one or more processors are further to:
receive a dequeue response after the packet has been sent to the output component,
the dequeue response indicating the size of the packet; and

where the one or more processors, when determining the size of the packet, are further to:
determine the size of the packet based on the dequeue response.

3. The device of claim 1 , where the one or more processors, when selectively dequeuing the packet, are further to:
dequeue the packet based on the credit value for the output component satisfying the credit threshold.

4. The device of claim 1 , where the one or more processors, when selectively dequeuing the packet, are further to:
prevent scheduling a dequeue of the packet based on the credit value for the output component failing to satisfy the credit threshold.

5. The device of claim 1 , where the one or more processors are further to:
modify the packet after dequeuing the packet;
determine a change in size of the packet due to the modification;
update the credit value for the output component based on the change in size of the packet due to the modification.

6. The device of claim 5 , where the one or more processors, when modifying the packet, are further to:
drop, add, or change a header of the packet.

7. The device of claim 5 , where the one or more processors, when updating the credit value based on the change in the size of the packet, are further to:
increase the credit value if the packet is smaller due to the modification; and
decrease the credit value if the packet is larger due to the modification.

8. A computer-readable medium storing instructions, the instructions comprising:
one or more instructions that, when executed by one or more processors, cause the one or more processors to:
store a credit value for each of a plurality of output components,
the credit value being based on weights assigned to the plurality of output components;

receive packets from a first device via an input component;
cause the input component to store the packets in one or more queues,
selectively dequeue a packet from the input component, to be sent to an output component, based on whether the credit value for the output component satisfies a credit threshold,
the packets including the packet,
the plurality of output components including the output component;

send the packet to the output component based on a destination of the packet when the packet is dequeued;
determine a size of the packet;
update the credit value for the output component based on the size of the packet; and
output the packet to a second device via the output component.

9. The computer-readable medium of claim 8 , where the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
assign the weights to the plurality of output components based on data rates of the plurality of output components.

10. The computer-readable medium of claim 8 , where the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
store a request value for each particular output component of the plurality of output components,
the request value indicating whether there any pending dequeue requests for the particular output component; and

where the one or more instructions, when selectively dequeuing the packet, further cause the one or more processors to:
selectively dequeue the packet from the input component based on whether the request value for the output component satisfies a request threshold and based on whether the credit value for the output component satisfies the credit threshold.

11. The computer-readable medium of claim 10 , where the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
decrement the request value based on dequeuing the packet.

12. The computer-readable medium of claim 10 , where the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
receive a dequeue response after the packet has been dequeued,
the dequeue response indicating whether an additional dequeue request is pending for the output component; and

update the request value based on the dequeue response.

13. The computer-readable medium of claim 10 , where the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
determine that none of the plurality of output components has the credit value that satisfies the credit threshold and the request value that satisfies the request threshold; and
replenish the credit value for each of the plurality of output components based on determining that none of the plurality of output components has the credit value that satisfies the credit threshold and the request value that satisfies the request threshold.

14. The computer-readable medium of claim 8 , where the one or more instructions, that cause the one or more processors to selectively dequeue the packet, further cause the one or more processors to:
prevent dequeuing of the packet while the credit value fails to satisfy the credit threshold.

15. A method, comprising:
storing, by a device, a credit value for each of a plurality of output components,
the credit value being based on weights assigned to the plurality of output components;

receiving, by the device, packets from a first device, via a plurality of input components, to be output to a second device;
causing, by the device, the plurality of input components to store the packets in one or more queues included in the plurality of input components,
selectively dequeuing, by the device, a packet from a particular input component, to be sent to an output component, based on whether the credit value for the output component satisfies a credit threshold,
the packets including the packet,
the plurality of output components including the output component;

sending, by the device, the packet to the output component to be output from the device when the packet is dequeued;
determining, by the device, a size of the packet after the packet has been dequeued;
updating, by the device, the credit value for the output component based on the size of the packet; and
outputting, by the device, the packet to the second device via the output component.

16. The method of claim 15 , further comprising:
determining that none of the plurality of output components has the credit value that satisfies the credit threshold; and
updating the credit value for each of the plurality of output components based on dete

Assignees

• Juniper Networks Inc

Inventors

• Pathakota Ravi
• Thomas Sarin
• Kundu Sudipta
• Vegesna Srihari R
• Irani Firdaus Mahiar
• Maji Kalpataru
• Jain Naveen K

Classifications

• H04W72/23

  in the downlink direction of a wireless link, i.e. towards a terminal · CPC title

• H04L47/527 Primary

  Quantum based scheduling, e.g. credit or deficit based scheduling or token bank · CPC title

• H04L47/36

  by determining packet size, e.g. maximum transfer unit [MTU] · CPC title

• H04L47/365

  Dynamic adaptation of the packet size · CPC title

• H04L49/3009 Primary

  Header conversion, routing tables or routing tags · CPC title