Read-throttled input/output scheduler

1. One or more computing devices configured to read and write data onto memory, the one or more computing devices comprising:

a read-throttling input/output scheduler configured to take write requests for data captured from a network, provide this data to a system that persists the captured data, and read requests from external user systems;

the read-throttling input/output scheduler further configured to determine a rate for data capture by maintaining two sliding windows over previous write requests;

the read-throttling input/output scheduler further configured such that, when write requests activity exceeds a threshold as determined over one of the two sliding windows, the read-throttling input/output scheduler ceases to service read requests; and

a data storage recording element that services the read and write request by retrieving and storing data from and onto a data storage medium.

2. The one or more computing devices of claim 1 further comprising a network communication protocol capture card configured to capture data disseminated over a network and provide this data to the read-throttling input/output scheduler.

3. The one or more computing devices of claim 2 further comprising a passive network tap configured to access data flowing across a network, and to packet and route the data to the network communication protocol capture card.

4. The one or more computing devices of claim 1 wherein the read-throttling input/output scheduler is further configured such that, when write requests activity exceeds the threshold, the read-throttling input/output scheduler ceases to service read requests.

5. The one or more computing devices of claim 4 wherein the second sliding window is longer then the first, and when read and write requests activity exceeds the threshold as determined over the first window, the read-throttling input/output scheduler ceases to service read requests.

6. The one or more computing devices of claim 1 wherein the read-throttling input/output scheduler is further configured such that, when write requests activity exceeds the threshold, the read-throttling input/output scheduler blocks existing and incoming read requests.

7. The one or more computing devices of claim 1 wherein the read-throttling input/output scheduler is further configured such that, when write requests activity drops below the threshold, the read-throttling input/output scheduler resumes servicing read requests.

8. The one or more computing devices of claim 7 wherein the second sliding window is longer then the first, and when read and write requests activity drops below the threshold as computed over the second window, the read-throttling input/output scheduler resumes servicing read requests.

9. The one or more computing devices of claim 1 wherein the read-throttling input/output scheduler is further configured such that, when write performance falls below the rate of data capture, the read-throttling input/output scheduler alters the flow of read requests.

10. The one or more computing devices of claim 1 wherein the threshold is preset.

11. The one or more computing devices of claim 1 wherein the threshold is dynamically determined.

12. The one or more computing devices of claim 1 wherein the storage medium is selected from the group consisting of magnetic disk drives, flash drives, and combinations thereof.

13. The one or more computing devices of claim 1 wherein the storage medium comprises a redundant array of independent disks.

14. A method implemented by one or more computing device configured to read and write data onto memory, the method comprising:

capturing data disseminated over a network;

providing this data to a system which persists the captured data;

determining a rate for data capture by maintaining two sliding windows over previous write requests;

creating read and write requests from the captured data;

forwarding the read and write request to a storage medium; and

when write request activity exceeds a threshold as determined over one of the two sliding windows, throttling the flow of read requests; and

forwarding the read and write request to a storage medium.

15. The method of claim 14 further comprising when the capture rate exceeds a throttling threshold, ceasing servicing read requests.

16. The method of claim 14 further comprising, when the capture rate exceeds the throttling threshold, blocking existing and incoming read requests.

17. The method of claim 14 further comprising, when the capture rate drops below the capture threshold, resuming servicing read requests.

18. The method of claim 17 further comprising the computing devices connected in a network selected from the group comprising the Internet, personal networks, local area networks, home networks, storage area networks, campus networks, backbone networks, metropolitan area networks, wide area networks, virtual private networks, and combinations thereof.

19. A method implemented by one or more computing devices configured to schedule read and write data onto memory, the method comprising:

receiving read and write requests;

taking write requests for data captured from a network;

providing this data to a system that persists the captured data;

reading requests from external user systems;

determining a rate of read and write requests by maintaining two sliding windows over previous write requests, with the second window being longer than the first;

when write requests activity exceeds the threshold as determined over the first window, throttling the flow of read requests; and

forwarding the read and write request to a storage medium.

20. The method of claim 19 further comprising, when write requests activity exceeds the threshold, ceasing servicing read requests.

21. The method of claim 19 further comprising, when write requests activity exceeds the threshold, blocking existing and incoming read requests.

22. The method of claim 19 further comprising, when requests activity drops below the threshold, resuming servicing read requests.

23. The method of claim 19 further comprising, when write performance falls below the rate of data capture, altering the flow of read requests.