Deferred processing of continuous metrics

• US 7,788,365 B1
• Filed: 04/25/2003
• Issued: 08/31/2010
• Est. Priority Date: 04/25/2002
• Status: Active Grant

• Current Assignee: Viavi Solutions, Inc. (Lumentum Holdings Inc.)
• Original Assignee: Viavi Solutions, Inc. (Lumentum Holdings Inc.)
• Inventors: Foster, Craig E., Bain, Lawrence M.
• Primary Examiner(s): Lee; Philip C
• Assistant Examiner(s): BIAGINI, CHRISTOPHER D
• Application Number:
  US10/424,361
• Time in Patent Office: 2,685 Days
• Field of Search: 709/224
• US Class Current: 709/224
• CPC Class Codes: H04L 41/22 comprising specially adapted graphical user interfaces [GUI]
• CPC Class Codes: H04L 43/00 Arrangements for monitoring or testing data switching networks
• CPC Class Codes: H04L 43/026 using flow identification
• CPC Class Codes: H04L 43/0888 Throughput
• CPC Class Codes: H04L 43/12 Network monitoring probes

Abstract

Network monitoring is performed using a three-tiered distributed computing system architecture, including a data source tier, a portal tier and a client tier. The data source tier monitors the physical data on the network medium using multiple data collection sources connected to the network. The probes analyze network data and generate fundamental metrics that describe attributes of the network data. The portal tier encapsulates the fundamental metrics along with executable processor objects into data containers having a predefined format. The processor objects contain logic that operates on fundamental metrics contained in the data containers in a manner so as to generate new derived metrics or aggregates of metric data. The data containers may be requested by the client tier, which executes the processor objects and provides a user interface for displaying various types of network information derived from the contents of data containers.

Claims

1. A system for monitoring traffic on a communications network, the system comprising:

a plurality of data collection sources connected at predetermined connection points on the network, wherein each of the data collection sources generates a plurality of fundamental metrics, the fundamental metrics being representative of at least one characteristic of the network traffic traversing the corresponding connection point, the data collection sources including at least a network link circuit and a data frame circuit configured to generate the plurality of fundamental metrics;

a data portal connected to the plurality of data collection sources so as to receive the plurality of fundamental metrics, at least some of which are then included in at least one data container having a predefined format, and wherein the data portal further generates at least one processor object that is included in the at least one data container, the at least one processor object providing predefined logic capable of processing information represented by the fundamental metrics contained within the data container; and

a monitoring client operatively connected to the data portal, the client including;

a communication interface configured to selectively request and receive at least one data container from the data portal; and

a user interface capable of selectively displaying network information derived from the contents of at least one data container,

wherein the predefined logic of the processor object is defined based on a metrics request received by the data portal from the monitoring client, the metrics request requesting a type of derivation to be performed by the predefined logic on the information represented by the fundamental metrics to generate derived metrics, and

wherein at least a portion of the displayed network information is based upon the derived metrics.

2. The system as defined in claim 1, wherein the communications network is a Storage Area Network (SAN).

3. The system as defined in claim 1, wherein the communications network utilizes at least one of an electrical communications medium and an optical communications medium.

4. The system as defined in claim 1, wherein the fundamental or the derived metrics contain at least one attribute of a storage I/O transaction communicated between at least two devices connected on the communications network.

5. The system as defined in claim 4, wherein the attribute is selected from at least one of the following:

transaction latency;

response time;

block transfer size; and

transfer completion status.

6. The system as defined in claim 1, wherein the fundamental or derived metrics contain at least one attribute of an instantaneous event on the communications network.

7. The system as defined in claim 6, wherein the attribute is selected from at least one of the following:

an error condition; and

aggregate throughput.

8. The system as defined in claim 1, wherein a passive tap is interposed between a data collection source and the communications network.

9. The system as defined in claim 1, wherein the data portal is implemented on a host computing device.

10. The system as defined in claim 1, wherein the monitoring client is implemented on a host computing device.

11. The system as defined in claim 1, wherein the data portal and the monitoring client are implemented on a single host computing device.

12. The system as defined in claim 1, wherein the plurality of fundamental metrics are generated at substantially the same rate as the speed of the communications network.

13. The system as defined in claim 12, wherein the speed of the communications network is one gigabit per second or greater.

14. The system as defined in claim 1, wherein the communications network is a Fibre Channel network running a SCSI upper level protocol.

15. The system as defined in claim 1, wherein the at least one processor object in the data container is used for processing information represented by fundamental metrics contained within other data containers.

16. The system as defined in claim 1, wherein the portal tier is configured to determine if the at least one processor object is needed to obtain the derived metrics based on the fundamental metrics before the at least one processor object is generated.

17. A system for monitoring traffic on a communications network, the system comprising:

a plurality of data collection sources connected at predetermined connection points on the network, wherein each of the data collection sources generates a plurality of fundamental metrics, the fundamental metrics being representative of at least one characteristic of the network traffic traversing the corresponding connection point, the data collection sources including at least a network link circuit and a data frame circuit configured to generate the plurality of fundamental metrics;

a data portal connected to the plurality of data collection sources so as to receive the plurality of fundamental metrics, at least some of which are then included in at least one data container having a predefined format, and wherein the data portal further generates at least one processor object that is included in the at least one data container, the at least one processor object providing predefined logic capable of processing information represented by the fundamental metrics contained within the data container; and

a monitoring client operatively connected to the data portal, the client including;

a communication interface configured to selectively request and receive at least one data container from the data portal; and

a user interface capable of selectively displaying network information derived from the contents of at least one data container,

wherein the predefined logic of the processor object is defined based on a metrics request received by the data portal from the monitoring client, the metrics request requesting a type of aggregation and/or derivation to be performed by the predefined logic on the information represented by the fundamental metrics.

18. The system as defined in claim 17, wherein the type of aggregation to be performed by the predefined logic is one that combines the information represented by the fundamental metrics with information represented by metrics derived from the fundamental metrics.

19. The system as defined in claim 17, wherein the type of derivation to be performed by the predefined logic is an averaging function.

20. The system as defined in claim 17, wherein the processing to be performed by the predefined logic is to be performed without user input.