End-to end analysis of transactions in networks with traffic-altering devices
View Patent ↗In a network that includes intermediary nodes, such as WAN accelerators, that transform messages between nodes, an end-to-end path of the messages is determined. The determined end-to-end path is used in subsequent analysis of message traces, to identify timing and other factors related to the performance of the network relative to the propagation of these messages, including the propagation of the transformed messages. A variety of techniques are presented for determining the path of the messages, depending upon the characteristics of the collected trace data. Upon determining the message path, the traces are synchronized in time and correlations between the connections along the path are determined, including causal relationships. In a preferred embodiment, a user identifies an application process between or among particular nodes of a network, and the system provides a variety of formats for viewing statistics related to the performance of the application on the network.
1. A network analysis system comprising:
a processor that is configured to receive a plurality of traces that include records of messages communicated between a first and second node of interest
a topology determiner that is configured to determine an end-to-end path for communicating the messages between the first and second node of interest, the end-to-end path including one or more intermediate nodes that transform one or more first messages between the first and second nodes of interest to create corresponding transformed messages that are communicated on a portion of the end-to-end path, and
a correlator that is configured to correlate the first messages and the transformed messages that are identified in the plurality of traces based on the determined end-to-end path, wherein
the processor is further configured to display information based on the correlation of messages along the end-to-end path, including information that is specific to the one or more intermediate nodes.
2. The network analysis system of claim 1 , wherein the topology determiner is configured to:
distinguish traffic flows based on the traces, including one or more traffic flows that include the first messages and the transformed messages, and
determine a topological arrangement of the one or more intermediate nodes with respect to the first and second nodes based on the traffic flows.
3. The network analysis system of claim 2 , wherein the topology determiner is configured to distinguish the traffic flows based on one or more MAC addresses associated with the first and transformed messages.
4. The network analysis system of claim 3 , wherein the topology determiner is configured to distinguish the traffic flows based on one or more IP addresses associated with the first and transformed messages.
5. The network analysis system of claim 4 , wherein the topology determiner is configured to distinguish the traffic flows based on a distinction between source and destination MAC addresses associated with the one or more IP addresses.
6. The network analysis system of claim 2 , wherein the topology determiner is configured to distinguish the traffic flows based on one or more sequence numbers associated with the messages.
7. The network analysis system of claim 1 , wherein the topology determiner is configured to identify the one or more intermediate nodes based on the traces.
8. The network analysis system of claim 1 , wherein the topology determiner is configured to identify the one or more intermediate nodes based on one or more MAC addresses associated with the first and transformed messages.
9. The network analysis system of claim 8 , wherein the topology determiner is configured to identify the one or more intermediate nodes based on one or more IP addresses associated with the first and transformed messages.
10. The network analysis system of claim 9 , wherein the topology determiner is configured to identify the one or more intermediate nodes based on a distinction between source and destination MAC addresses associated with the one or more IP addresses.
11. The network analysis system of claim 1 , wherein the topology determiner is configured to determine the end-to-end path based on a set of times associated with propagation of a select message at the intermediate nodes.
12. The network analysis system of claim 1 , wherein at least one of the first messages and the transformed messages have distinguishing characteristics, and the topology determiner is configured to distinguish the first messages from the transformed messages based on these distinguishing characteristics.
13. The network analysis system of claim 12 , wherein the topology determiner is configured to identify the one or more intermediate nodes based on the distinguishing characteristics.
14. The network analysis system of claim 1 , wherein the correlator includes a synchronizer that is configured to adjust one or more of the time bases of the traces to establish a common time base among the traces.
15. The network analysis system of claim 1 , wherein the correlator is configured to identify causal relationships between the first messages and the transformed messages.
16. The network analysis system of claim 1 , wherein the transformed messages include a transformation of addresses of the first messages.
17. The network analysis system of claim 1 , wherein the transformed messages include a transformation of content of the first messages.
18. The network analysis system of claim 1 , wherein the transformed messages include a transformation of addresses and content of the first messages.
19. The network analysis system of claim 1 , wherein the correlator is further configured to correlate the transformed messages and second messages, the second messages being recreations of the first messages from the transformed messages.
20. The network analysis system of claim 19 , wherein the correlator is configured to identify causal relationships between the transformed messages and the second messages.
21. A method comprising:
receiving, by a network analysis system, a plurality of traces that include records of messages communicated between a first and second node of interest,
determining, by the network analysis system, an end-to-end path for communicating the messages between the first and second node of interest based on the plurality of traces, the end-to-end path including one or more intermediate nodes that transform one or more first messages between the first and second nodes of interest to create corresponding transformed messages that are communicated on a portion of the end-to-end path,
correlating, by the network analysis system, the first messages and the transformed messages that are identified in the plurality of traces, based on the determined end-to-end path, and
displaying, by the network analysis system, information based on the correlation of messages along the end-to-end path, including information that is specific to the one or more intermediate nodes.
22. The method of claim 21 , wherein determining the end-to-end path includes:
distinguishing traffic flows based on the traces, including one or more traffic flows that include the first messages and the transformed messages, and
determining a topological arrangement of the one or more intermediate nodes with respect to the first and second nodes based on the traffic flows.
23. The method of claim 22 , wherein distinguishing the traffic flows includes distinguishing between source and destination MAC addresses associated with one or more IP addresses.
24. The method of claim 22 , wherein distinguishing the traffic flows includes distinguishing the traffic flows based on one or more sequence numbers associated with the messages.
25. The method of claim 21 , wherein determining the end-to-end path includes identifying the one or more intermediate nodes based on a distinction between source and destination MAC addresses associated with one or more IP addresses.
26. The method of claim 21 , wherein determining the end-to-end path includes determining the end-to-end path based on a set of times associated with propagation of one or more select messages at the intermediate nodes.
27. The method of claim 21 , wherein at least one of the first messages and the transformed messages have distinguishing characteristics, and distinguishing the first messages from the transformed messages is based on these distinguishing characteristics.
28. The method of claim 21 , including identifying causal relationships between the first messages and the transformed messages.
29. The method of claim 21 , wherein the transformed messages include a transformation of addresses and content of the first messages.
30. The method of claim 21 , including correlating the transformed messages and second messages, the second messages being recreations of the first messages from the transformed messages.
31. A non-transitory computer-readable medium that includes a program that, when executed by a processor, causes the processor to:
receive a plurality of traces that include records of messages communicated between a first and second node of interest,
determine an end-to-end path for communicating the messages between the first and second node of interest based on the plurality of traces, the end-to-end path including one or more intermediate nodes that transform one or more first messages between the first and second nodes of interest to create corresponding transformed messages that are communicated on a portion of the end-to-end path,
correlate the first messages and the transformed messages that are identified in the plurality of traces, based on the determined end-to-end path, and
display information based on the correlation of messages along the end-to-end path, including information that is specific to the one or more intermediate nodes.
32. The medium of claim 31 , wherein the program causes the processor to:
distinguish traffic flows based on the traces, including one or more traffic flows that include the first messages and the transformed messages, and
determine a topological arrangement of the one or more intermediate nodes with respect to the first and second nodes based on the traffic flows.
33. The medium of claim 32 , wherein the program causes the processor to distinguish between source and destination MAC addresses associated with one or more IP addresses to distinguish traffic flows.
34. The medium of claim 32 , wherein the program causes the processor to distinguish the traffic flows based on one or more sequence numbers associated with the messages.
35. The medium of claim 31 , wherein the program causes the processor to identify the one or more intermediate nodes based on a distinction between source and destination MAC addresses associated with one or more IP addresses.
36. The medium of claim 31 , wherein the program causes the processor to determine the end-to-end path based on a set of times associated with propagation of one or more select messages at the intermediate nodes.
37. The medium of claim 31 , wherein at least one of the first messages and the transformed messages have distinguishing characteristics, and the program causes the processor to distinguish the first messages from the transformed messages based on these distinguishing characteristics.
38. The medium of claim 31 , wherein the program causes the processor to identify causal relationships between the first messages and the transformed messages.
39. The medium of claim 31 , wherein the transformed messages include a transformation of addresses and content of the first messages.
40. The medium of claim 31 , the program causes the processor to correlate the transformed messages and second messages, the second messages being recreations of the first messages from the transformed messages.