System, method and computer program product to maximize server throughput while avoiding server overload by controlling the rate of establishing server-side network connections
A method for maximizing server throughput while avoiding overload of a server is presented. The method involves intercepting, via an interface unit, a client request for information from the server. Next, the interface unit determines the current server performance, where the server performance is based on the number of connections opened to the server, the response time of the server and the rate at which the response time is changing. Finally, the interface unit forwards the client request to the server if the current server performance is close to an optimal performance, whereby avoiding overload of the server.
1. A method for improving performance of a server by device intermediary to a plurality of clients and the server, the method comprising:
(a) monitoring, by a device intermediary to a plurality of a clients and a server, a mix of requests from existing clients and new clients pending at the server;
(b) determining, by the device based on the monitoring of the mix of requests, a first predetermined percentage of processing resources of the server to spend servicing existing clients for the server to perform within a predetermined performance range; and
(c) regulating, by the device, a rate at which requests received by the device from existing clients are delivered to the server to maintain performance of the server within the predetermined performance range.
2. The method of claim 1 , wherein step (a) further comprises monitoring, by the device, the mix of requests at a point in time.
3. The method of claim 1 , wherein step (b) further comprises determining, by the device responsive to monitoring, for the server to perform within the predetermined performance range, a second predetermined percentage of processing resources of the server to accept new clients.
4. The method of claim 1 , wherein step (c) further comprises regulating, by the device, the rate at which requests received by new clients are delivered to the server to maintain performance of the server within the predetermined performance range.
5. The method of claim 1 , wherein step (c) further comprises receiving, by the device, a connection request to the server from a new client.
6. The method of claim 5 , further comprising determining, by the device, whether the server would maintain performance within the predetermined performance range if the client is allowed to make a connection.
7. The method of claim 6 , further comprising determining, by the device, that the server's response time would not increase to an unacceptable level and forwarding the connection request to the server.
8. The method of claim 6 , further comprising determining, by the device, that the server's response time would increase to an unacceptable level and buffering by the device the connection request.
9. The method of claim 1 , wherein step (c) further comprising determining a number of requests queued at the server and comparing the number of requests with a maximum capacity of the server's queue.
10. The method of claim 1 , wherein step (c) further comprising determining an amount of time requests have been pending at the server.
11. A system for improving performance of a server, the system comprising:
a device intermediary to a plurality of a clients and a server comprising a processor configured for monitoring a mix of requests from existing clients and new clients pending at the server;
a controller of the device, determining, based on the monitoring of the mix of requests, a first predetermined percentage of processing resources of the server to spend servicing existing clients for the server to perform within a predetermined performance range; and
wherein the device regulates a rate at which requests received by the device from existing clients are delivered to the server to maintain performance of the server within the predetermined performance range.
12. The system of claim 11 , wherein the device monitors the mix of requests at a point in time.
13. The system of claim 11 , wherein the device determines, responsive to monitoring, for the server to perform within the predetermined performance range, a second predetermined percentage of processing resources of the server to accept new clients.
14. The system of claim 11 , wherein the device regulates the rate at which requests received by new clients are delivered to the server to maintain performance of the server within the predetermined performance range.
15. The system of claim 11 , wherein a communication interface of the device receives a connection request to the server from a new client.
16. The system of claim 15 , wherein the device determines whether the server would maintain performance within the predetermined performance range if the client is allowed to make a connection.
17. The system of claim 16 , wherein the device determines that the server's response time would not increase to an unacceptable level and forwards the connection request to the server.
18. The system of claim 16 , wherein the controller determines that the server's response time would increase to an unacceptable level and buffers the connection request.
19. The system of claim 11 , wherein the device regulates by determining a number of requests queued at the server and comparing the number of requests with a maximum capacity of the server's queue.
20. The system of claim 11 , wherein the device regulates by determining an amount of time requests have been pending at the server.