IP Library Granted Patent US 8,023,521
Granted Patent B2
US 8,023,521 · App. 12/276,098 · Granted Sep 20, 2011

Methods and apparatus for differentiated services over a packet-based network

Assignee: Enterasys Networks, Inc.
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 8,023,521
App. No.
12/276,098
Granted
Sep 20, 2011
Kind
B2
Abstract

Methods and apparatus for the provision of differentiated services in a packet-based network may be provided in a communications device such as a switch or router having input ports and output ports. Each output port is associated with a set of configurable queues that store incoming data packets from one or more input ports. A scheduling mechanism retrieves data packets from individual queues in accord with a specified configuration, providing both pure priority and proportionate de-queuing to achieve a guaranteed QoS over a connectionless network.

Claims (25)

1. A hierarchical packet-buffering system of memory structures for processing packets in a network, the network having a network bandwidth, the system comprising:

a first memory including one or more first packet buffers configured to receive data packets from the network, each of the one or more first packet buffers having a first packet-buffer bandwidth and a first packet-buffer depth, wherein a sum of first packet-buffer bandwidths is equal to or greater than the network bandwidth; and

a second memory different from the first memory and including one or more second packet buffers configured to receive packets from at least one of the one or more first packet buffers, each of the one or more second packet buffers having a second packet-buffer bandwidth and a second packet-buffer depth and being organized as a plurality of queues, each of the plurality of queues being configurable, by a configuration parameter stored in memory, to independently operate in one of a fairness-based mode and a priority based-mode, wherein a sum of the second packet-buffer depths is equal to or greater than a sum of first packet-buffer depths of the at least one of the one or more first packet buffers and a sum of the second packet-buffer bandwidths is equal to or greater than a sum of first packet-buffer bandwidths of the at least one of the one or more first packet buffers.

2. The system according to claim 1 , wherein the one or more first packet buffers comprise a packet buffer embedded in an ASIC.

3. The system according to claim 1 , wherein each of the one or more second packet buffers comprises field configurable memory elements.

4. The system according to claim 1 , wherein the first memory is composed of a first memory type and the second memory is composed of a second memory type, the second memory type having performance characteristics substantially different from that of the first memory type.

5. The system according to claim 1 , wherein the one or more first packet buffers and the one or more second packet buffers are implemented in a fully connected mesh architecture having a plurality of input ports and a plurality of output ports, each input port being continuously connected to a corresponding output port.

6. The system according to claim 1 , wherein the one or more first packet buffers and the one or more second packet buffers are implemented in a partially connected mesh architecture having a plurality of input ports and a plurality of output ports, at least one of the input ports being switchably connected to at least one of the output ports.

7. The system according to claim 1 , wherein each of the one or more second packet buffers has a priority level and the system is configured to transmit packets according to the priority level of each of the one or more second packet buffers.

8. The system according to claim 1 , further comprising a scheduler in communication with the one or more second packet buffers, the scheduler configured to donate bandwidth from one of the one or more second packet buffers with a first priority level to another of the one or more second packet buffers with a second priority level, wherein the first priority level is higher than the second priority level.

9. The system according to claim 8 , further comprising a scheduler in communication with the one or more second packet buffers, the scheduler configured to donate bandwidth from one of the one or more second packet buffers with a first priority level to another of the one or more second packet buffers with a second priority level, wherein the first priority level is lower than the second priority level.

10. The system according to claim 1 , further comprising a scheduler in communication with the one or more second packet buffers, the scheduler configured to independently schedule packets on a pure priority basis.

11. The system according to claim 1 , further comprising a scheduler in communication with the one or more second packet buffers, the scheduler configured to independently schedule packets using a weighted fair queuing technique.

12. The system according to claim 1 , further comprising a scheduler in communication with the one or more second packet buffers, the scheduler configured to independently schedule packets using a random early detection technique.

13. The system according to claim 1 , further comprising a scheduler in communication with the one or more second packet buffers, the scheduler configured to independently schedule packets using a weighted random early detection technique.

14. The system according to claim 1 , further comprising a scheduler in communication with the one or more second packet buffers, the scheduler configured to independently schedule packets using a bandwidth donation technique.

15. The system according to claim 1 , further comprising a scheduler in communication with the one or more second packet buffers, the scheduler configured to independently schedule packets by using a combination of techniques selected from pure priority, weighted fair queuing, random early detection, weighted random early detection, and bandwidth donation.

16. A hierarchical packet-buffering system of memory structures for processing packets in a network, the network having a network bandwidth, the system comprising:

a first memory including one or more first packet buffers configured to receive data packets from the network, each of the one or more first packet buffers having a first packet-buffer bandwidth and a first packet-buffer depth, wherein a sum of first packet-buffer bandwidths is equal to or greater than the network bandwidth;

a second memory different from the first memory and including one or more second packet buffers configured to receive packets from at least one of the one or more first packet buffers, each of the one or more second packet buffers having a second packet-buffer bandwidth and a second packet-buffer depth, wherein a sum of the second packet-buffer depths is equal to or greater than a sum of first packet-buffer depths of the at least one of the one or more first packet buffers and a sum of the second packet-buffer bandwidths is equal to or greater than a sum of the first packet-buffer bandwidths of the at least one of the one or more first packet buffers; and

one or more other packet buffers configured to receive packets from one or more previous packet buffers, each of the one or more other packet buffers being organized as a plurality of queues, each of the plurality of queues being configurable, by a configuration parameter stored in memory, to independently operate in one of a fairness-based mode and a priority based-mode.

17. The system according to claim 16 , wherein the first packet buffer comprises a packet buffer embedded in an ASIC.

18. The system according to claim 16 , wherein the one or more previous packet buffers include at least one of the one or more second packet buffers.

19. The system according to claim 16 , wherein the one or more previous packet buffers include one or more third packet buffers configured to receive packets from at least one of the one or more second packet buffers.

20. The system according to claim 16 , further comprising a scheduler in communication with the one or more other packet buffers, the scheduler configured to independently schedule packets by using at least one technique selected from pure priority, weighted fair queuing, random early detection, weighted random early detection, and bandwidth donation.

Assignments (12)
AMENDED SECURITY AGREEMENT Recorded Aug 18, 2023
From: EXTREME NETWORKS, INC.; AEROHIVE NETWORKS, INC.
To: BANK OF MONTREAL
Reel/Frame 064782/0971 →
RELEASE OF SECURITY INTEREST Recorded May 1, 2018
From: SILICON VALLEY BANK
To: ENTERASYS NETWORKS, INC.
Reel/Frame 046047/0223 →
SECURITY INTEREST Recorded May 1, 2018
From: EXTREME NETWORKS, INC.
To: BANK OF MONTREAL
Reel/Frame 046050/0546 →
RELEASE OF SECURITY INTEREST Recorded May 1, 2018
From: SILICON VALLEY BANK
To: EXTREME NETWORKS, INC.
Reel/Frame 046051/0775 →
THIRD AMENDED AND RESTATED PATENT AND TRADEMARK SECURITY AGREEMENT Recorded Oct 31, 2017
From: EXTREME NETWORKS, INC.
To: SILICON VALLEY BANK
Reel/Frame 044639/0300 →
SECOND AMENDED AND RESTATED PATENT AND TRADEMARK SECURITY AGREEMENT Recorded Jul 14, 2017
From: EXTREME NETWORKS, INC.
To: SILICON VALLEY BANK
Reel/Frame 043200/0614 →
AMENDED AND RESTATED PATENT AND TRADEMARK SECURITY AGREEMENT Recorded Oct 31, 2016
From: EXTREME NETWORKS, INC.
To: SILICON VALLEY BANK
Reel/Frame 040521/0762 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 3, 2015
From: ENTERASYS NETWORKS, INC.
To: EXTREME NETWORKS, INC.
Reel/Frame 036538/0011 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 26, 2015
From: ENTERASYS NETWORKS, INC.
To: EXTREME NETWORKS, INC.
Reel/Frame 036467/0566 →
SECURITY AGREEMENT Recorded Jul 27, 2015
From: ENTERASYS NETWORKS, INC.
To: SILICON VALLEY BANK
Reel/Frame 036189/0509 →
TERMINATION AND RELEASE OF SECURITY INTEREST IN PATENTS AT REEL/FRAME NO. 25339/0875 Recorded Nov 1, 2013
From: WELLS FARGO TRUST CORPORATION LIMITED
To: ENTERASYS NETWORKS INC.
Reel/Frame 031558/0677 →
GRANT OF SECURITY INTEREST IN U.S. PATENTS Recorded Nov 10, 2010
From: ENTERASYS NETWORKS INC.
To: WELLS FARGO TRUST CORPORATION LIMITED, AS SECURITY AGENT
Reel/Frame 025339/0875 →
Continuity (3)
Division 10298243 · Nov 15, 2002
Provisional Application 60339073 · Nov 16, 2001
Related Publication 20090141732A1 · Jun 4, 2009