Detection of an unresponsive application in a high availability system

An information processing system for determining if an application has become unresponsive, the information processing system comprising:

• a memory;
• a processor communicatively coupled to the memory;
• and
• an application monitor communicatively coupled to the memory and the processor, wherein the application monitor is configured to perform a method comprising:
• monitoring network traffic at a receiver node;
• receiving, based on monitoring network traffic a receiver node, a window probe response comprising a window size, the window size indicating a number of packets a receive buffer at the receiver node is currently able to hold;
• comparing the window size of the window probe response to a predetermined window size;
• determining, based on the comparing, that the window size of the window probe response matches the predetermined window size;
• setting, based on determining that the window size of the window probe response matches the predetermined window size, at least one of a time threshold and a count threshold associated with the window size of the receiver node;
• receiving, based on setting the at least one of the time threshold and the count threshold, a set of additional window probe responses, wherein each of the set of additional window probe responses comprises a window size update indicating a current window size of the receive buffer;
• determining, based on receiving the set of additional window probe responses, at least one of
• that the window size of the receiver node has been at the predetermined window size for a time period that is one of greater than and equal to the time threshold, and
• that a number of window size updates in the set of additional window probe responses, indicating that the window size of the receiver node remains at the predetermined window size, is one of greater than and equal to the count threshold;
• and
• classifying, based on the determining, an application associated with the receiver node as unresponsive.

A tangible non-transitory computer program storage product for determining, with an information processing system, if an application has become unresponsive, the computer program storage product comprising instructions for:

• monitoring network traffic at a receiver node;
• receiving, based on monitoring network traffic a receiver node, a window probe response comprising a window size, the window size indicating a number of packets a receive buffer at the receiver node is currently able to hold;
• comparing the window size of the window probe response to a predetermined window size;
• determining, based on the comparing, that the window size of the window probe response matches the predetermined window size;
• setting, based on determining that the window size of the window probe response matches the predetermined window size, at least one of a time threshold and a count threshold associated with the window size of the receiver node;
• receiving, based on setting the at least one of the time threshold and the count threshold, a set of additional window probe responses, wherein each of the set of additional window probe responses comprises a window size update indicating a current window size of the receive buffer;
• determining, based on receiving the set of additional window probe responses, at least one of
• that the window size of the receiver node has been at the predetermined window size for a time period that is one of greater than and equal to the time threshold, and
• that a number of window size updates in the set of additional window probe response, indicating that the window size of the receiver node remains at the predetermined window size, is one of greater than and equal to the count threshold;
• and
• classifying, based on the determining, an application associated with the receiver node as unresponsive.