Network data congestion management probe system

Patent metadata

Field	Value
Publication number	US-9628387-B2
Application number	US-201213729677-A
Country	US
Kind code	B2
Filing date	Dec 28, 2012
Priority date	Apr 22, 2010
Publication date	Apr 18, 2017
Grant date	Apr 18, 2017

Abstract

A method to investigate congestion in a computer network may include network devices to route data packets throughout the network. The method includes, for example, sending a probe packet to network devices from a source node to gather information about the traffic queues at each network device that is examined by the probe packet. A routing table at each network device that receives the probe packet is based on the gathered information for respective each traffic queue.

First claim

What is claimed is:

1. A method comprising:
receiving, by a source node, congestion notification messages from network devices within a virtual local area network;
filtering portions of the congestion notification messages used by the source node, wherein the filtering is performed by a low pass filter;
sending a probe packet to network devices from the source node to gather information about traffic queues at each network device that is examined by the probe packet, wherein the probe packet is sent in response to the source node receiving a threshold number of the congestion notification messages in a given time interval, wherein the probe packet includes a layer 2 flag and a sequence ID, a flow ID, and a source node ID;
basing a routing table at each network device that receives the probe packet on the gathered information for respective each traffic queue;
sending an extended queue status of at least one of the network devices to the source node in response to receiving the probe packet, wherein the extended queue status includes a number of pings from any flow ID received since a last queue change, a number of packets forwarded since the last queue change, and pointers to a complete network device core dump;
sending the extended queue status of at least one of the network devices to other network devices in response to receiving the probe packet;
updating, by the source node, the routing table at each network device to rebalance traffic loads in response to the extended queue status exceeding a threshold level; and
adjusting how frequently subsequent probe packets are sent.

2. The method of claim 1 , further comprising organizing the network devices into a virtual local area network.

3. The method of claim 1 , further comprising providing the extended queue status of a network device to other network devices in response to the network device receiving the probe packet.

4. A system comprising:
network devices to route data packets throughout a network;
a source node to:
receive congestion notification messages from network devices within a virtual local area network;
filter portions of the congestion notification messages used by the source node, wherein the filtering is performed by a low pass filter; and
send a probe packet to the network devices to gather information about traffic queues at each network device that receives the probe packet, wherein the probe packet is sent in response to the source node receiving a threshold number of the congestion notification messages in a given time interval, wherein the probe packet includes a layer 2 flag and a sequence ID, a flow ID, and a source node ID, where a frequency of sending subsequent probe packets is adjusted;

a routing table at each network device that receives the probe packet, and the routing table is based upon the gathered information for each respective traffic queue; and
an extended queue status of at least one of the network devices configured to be sent to the source node in response to receiving the probe packet, wherein the extended queue status includes a number of pings from any flow ID received since a last queue change, a number of packets forwarded since the last queue change, and pointers to a complete network device core dump, the extended queue status of at least one of the network devices is configured to be sent to other network devices in response to receiving the probe packet;
wherein the source node is configured to update the routing table at each network device to rebalance traffic loads in response to the extended queue status exceeding a threshold level.

5. The system of claim 4 , wherein the network devices are members of at least one virtual local area network.

6. The system of claim 4 , wherein each network device can ignore the probe packet if it is busy.

7. A computer program product embodied in a non-transitory tangible media comprising:
computer readable program codes coupled to the tangible media to investigate congestion in a computer network, the computer readable program codes configured to cause the program to:
receive, by a source node, congestion notification messages from network devices within a virtual local area network;
filter portions of the congestion notification messages used by the source node, wherein the filtering is performed by a low pass filter;
send a probe packet to network devices from the source node to gather information about traffic queues at each network device that is examined by the probe packet, wherein the probe packet is sent in response to the source node receiving a threshold number of the congestion notification messages in a given time interval, wherein the probe packet includes a layer 2 flag and a sequence ID, a flow ID, and a source node ID;
base a routing table at each network device that receives the probe packet on the gathered information for each respective traffic queue;
send an extended queue status of at least one of the network devices to the source node in response to receiving the probe packet, wherein the extended queue status includes a number of pings from any flow ID received since a last queue change, a number of packets forwarded since the last queue change, and pointers to a complete network device core dump;
send the extended queue status of at least one of the network devices to other network devices in response to receiving the probe packet;
update, by the source node, the routing table at each network device to rebalance traffic loads in response to the extended queue status exceeding a threshold level; and
adjust how frequently subsequent probe packets are sent.

8. The computer program product of claim 7 , wherein the network devices are members of at least one virtual local area network.

9. The computer program product of claim 7 , wherein each network device can ignore the probe packet if it is busy.

Assignees

• IBM

Inventors

• Crisan Daniel
• Decusatis Casimer M
• Gusat Mitch
• Minkenberg Cyriel J A

Classifications

• H04L45/00 Primary

  Routing or path finding of packets in data switching networks (routing or path finding in wireless networks H04W40/00) · CPC title

• H04L45/26

  Route discovery packet · CPC title

• H04L45/125 Primary

  based on throughput or bandwidth · CPC title

• H04L47/11 Primary

  Identifying congestion · CPC title

• H04L45/127

  based on intermediate node capabilities · CPC title