Methods and apparatus to determine network delay with location independence

Abstract

The techniques disclosed herein determine a location independent network delay via a network monitoring device. Such techniques particularly include determining various delays such as a zero window delay, an advertised window delay, and a congestion window delay (including slow start delays).

What is claimed is: 
     
         1 . A method for monitoring network a zero window delay in a communication network comprising:
 monitoring, via a network monitoring device, an exchange of data between at least a first network device and a second network device;   determining, via the network monitoring device, the first network device received data in excess of its capacity thereby causing its transmission control protocol (TCP) window to reduce to zero;   marking, via the network monitoring device, a zero window delay start time once the first network device receives data in excess of its capacity;   determining, via the network monitoring device, that the TCP window size for the first network device increases from zero;   marking, via the network monitoring device, a zero window delay end time once the TCP window size of the first network device increases from zero; and   determining a difference between the zero window delay end time and the zero window delay start time to yield a total zero window delay.   
     
     
         2 . The method of  claim 1 , further comprising:
 displaying, via a display of the network monitoring device, the total zero window delay.   
     
     
         3 . The method of  claim 1 ,
 wherein determining that the first network device receives data in excess of its capacity comprises receiving a window update from the first network device, and   wherein determining that the TCP window size for the first network device increases from zero comprises receiving a window update from the first network device that the TCP window size increases from zero.   
     
     
         4 . The method of  claim 1 , wherein the first network device and e second network device include at least one of a client and a server, 
     
     
         5 . A method for determining an advertised window delay in a communication network comprising:
 monitoring, via a network monitoring device, an exchange of data between at least a first network device and a second network device;   determining, via the network monitoring device, that the first network device ceased transmission of data caused by an amount of non-acknowledged data by the second network device;   marking, via the network monitoring device, an advertised window delay start time when the first network device ceases transmission of data;   determining, via the network monitoring device, that the first network device continues transmission of data once the non-acknowledged data is acknowledged by the second network device;   marking, via the network monitoring device, an advertised window delay end time when the first network device continues transmission of data; and   determining a difference between the advertised window delay start time and the advertised window delay end time to yield a total advertised window delay.   
     
     
         6 . The method of  claim 5 , further comprising:
 displaying, via a display of the network monitoring device, the total advertised window delay.   
     
     
         7 . The method of  claim 5 , wherein the first network device ceases transmission of data when the amount of non-acknowledged data by the second network device exceeds a previously advertised window of the first network device. 
     
     
         8 . The method of  claim 5 , wherein the first network device and the second network device include at least one of a client and a server. 
     
     
         9 . A method for determining a congestion window delay in a communication network comprising:
 monitoring, via a network monitoring device, an exchange of data between a first network device and a second network device;   determining, via the network monitoring device, a congestion window for at least the first network device;   maintaining, via the network monitoring device, a congestion window value for at least the first network device;   determining, via the network monitoring device, that the first network device ceased data transmission caused by a transmission of bytes greater than or equal to s congestion window value;   marking, via the network monitoring device, a congestion window start time when the first network device ceases data transmission;   determining, via the network monitoring device, that the first network device increases its congestion window causing it to continue transmitting data;   marking, via the network monitoring device, a congestion window end time when the first network device continues to transmits data; and   determining a difference between the congestion window end time and the congestion window start time to yield a total congestion window delay.   
     
     
         10 . The method of  claim 9 , wherein the first network device increases its congestion window once it receives an acknowledgement from the second network device. 
     
     
         11 . The method of  claim 9 , further comprising:
 displaying, via a display of the network monitoring device, the total congestion window delay.   
     
     
         12 . The method of  claim 9 , wherein the first network device and the second network device include at least one of a client and a server. 
     
     
         13 . A network monitoring device, comprising:
 one or more network interfaces adapted to communicate in a communication network;   a processor adapted to execute one or more processes; and   a memory configured to store a process executable by the processor, the process when executed operable to:
 monitor an exchange of data between at least a first network device and a second network device; 
 determine the first network device received data in excess of its capacity thereby causing its transmission control protocol (TCP) window to reduce to zero; 
 mark a zero window delay start time once the first network device receives data in excess of its capacity; 
 determine that the TCP window size for the first network device increases from zero; 
 mark a zero window delay end time once the TCP window size of the first network device increases from zero; and 
 determine a difference between the zero window delay end time and the zero window delay start time to yield a total zero window delay. 
   
     
     
         14 . The network monitoring device of  claim 13 , further comprising:
 a display that displays the total zero delay window.   
     
     
         15 . The network monitoring device of  claim 13 , wherein the first network device and the second network device include at least one of a server device and a client device. 
     
     
         16 . A network monitoring device, comprising:
 one or more network interfaces adapted to communicate in a communication network;   a processor adapted to execute one or more processes; and   a memory configured to store a process executable by the processor, the process when executed operable to:
 monitor an exchange of data between at least a first network device, and a second network device; 
 determine that the first network device ceased transmission of data caused by an amount of non-acknowledged data by the second network device; 
 mark an advertised window delay start time when the first network device ceases transmission of data; 
 determine that the first network device continues transmission of data once the non-acknowledged data is acknowledged by the second network device; 
 mark an advertised window delay end time when the first network device continues transmission of data; and 
 determine a difference between the advertised window delay start time and the advertised window delay end time to yield a total advertised window delay. 
   
     
     
         17 . The network monitoring device of  claim 16 , further comprising:
 a display that displays the total advertised window delay.   
     
     
         18 . The network monitoring device of  claim 16 , wherein the first network device and the second network device include at least one of a client and a server. 
     
     
         19 . A network monitoring device, comprising:
 one or more network interfaces adapted to communicate in a communication network;   a processor adapted to execute one or more processes; and   a memory configured to store a process executable by the processor, the process when executed operable to:
 monitor an exchange of data between a first network device and a second network device; 
 determine a congestion window for at least the first network device; 
 maintain a congestion window value for at least the first network device; 
 determine that the first network device ceased data transmission caused by a transmission of bytes greater than or equal to its congestion window value; 
 mark a congestion window start time when the first network device ceases data transmission; 
 determine that the first network device increases its congestion window causing it to continue transmitting data; 
 mark a congestion window end time when the first network device continues to transmits data; and 
 determine a difference between the congestion window end time and the congestion window start to yield a total congestion window delay. 
   
     
     
         20 . A tangible, non-transitory, computer-readable media having software encoded thereon, the software, when executed by a processor, operable to:
 monitor an exchange of data between at least a first network device and a second network device;   determine the first network device received data from the second network device in excess of a capacity first network device thereby causing the first network device to reduce a transmission control protocol (TCP) window zero;   mark a zero window delay start time once the first network device receives data in excess of the capacity;   determine that the TCP window size for the first network device increases from zero;   mark a zero window delay end time once the TCP window size increases from zero;   determine a difference between the zero window delay end time and the zero window delay start time to yield a zero window delay time;   determine that the first network device ceased transmission of data caused by an non-acknowledgement of data from the second network device;   mark an advertised window delay start time when the first network device ceases transmission of data;   determine that the first network device continues transmission of data once the non-acknowledged data is acknowledged by the second network device;   mark an advertised window delay end time when the amount of unacknowledged data is acknowledged;   determine a difference between the advertised window delay start time and the advertised window end time to yield the advertised window delay;   determine a congestion window for each of the network devices in the communication network;   maintain a congestion window value for each of the network devices;   determine that the first network device ceases data transmission caused by a transmission of bytes greater than or equal to its respective congestion window value;   mark a congestion window delay start time when the first network device ceases data transmission;   determine that the first network device increases its congestion window causing it to continue transmitting data;   mark a congestion window delay end time when the first network device continues to transmits data;   determine a difference between the congestion window delay end time and the congestion window delay start time to yield the congestion window delay; and   displaying at least one of the advertised window delay, the zero window delay and the congestion window delay.