User-level stack

• US 8,005,916 B2
• Filed: 04/21/2005
• Issued: 08/23/2011
• Est. Priority Date: 04/21/2004
• Status: Active Grant

• Current Assignee: Xilinx, Inc. (Advanced Micro Devices, Inc.)
• Original Assignee: SolarFlare Communications Incorporated (Advanced Micro Devices, Inc.)
• Inventors: Riddoch, David J., Pope, Steve L.
• Primary Examiner(s): Bates; Kevin
• Assistant Examiner(s): Ahmed; Mohammed
• Application Number:
  US11/111,481
• Publication Number:
  US 20050226165A1
• Time in Patent Office: 2,315 Days
• Field of Search: 709/212, 709/213
• US Class Current: 709/212
• CPC Class Codes: G06F 13/10 Program control for peripheral devices G06F13/14 - G06F13/42 take precedence

Abstract

A method for transmitting data by means of a data processing system, the system being capable of supporting an operating system and at least one application and having access to a memory and a network interface device capable of supporting a communication link over a network with another network interface device, the method comprising the steps of: forming by means of the application data to be transmitted; requesting by means of the application a non-operating-system functionality of the data processing system to send the data to be transmitted; responsive to that request: writing the data to be transmitted to an area of the memory; and initiating by means of direct communication between the non-operating-system functionality and the network interface device a transmission operation of at least some of the data over the network; and subsequently accessing the memory by means of the operating system and performing at least part of a transmission operation of at least some of the data over the network by means of the network interface device.

Claims

1. A method for transmitting data by means of a data processing system having a processor subsystem, the system being capable of supporting an operating system and at least one application and having access to a memory and a network interface device capable of supporting a communication link over a network with another network interface device, the method comprising the steps of:

forming by means of an application executing on the processor subsystem, data to be transmitted;

requesting by means of the application a non-operating-system functionality executing on the processor subsystem to send the data to be transmitted over the network;

responsive to that request;

writing the data to be transmitted to an area of the memory comprising a data buffer and corresponding connection state; and

initiating by means of direct communication between the non-operating-system functionality and the network interface device a transmission operation of at least some of the data over the network;

and after the transmission operation has been initiated over the network, determining that the application is unresponsive, and in response to such determination, the operating system accessing the said data buffer and connection state and continuing the transmission operation over the network by means of the network interface device,

wherein the processor subsystem is in communication with the memory via a bus,

and wherein the network interface device is in communication with the memory via a bus.

2. A method as claimed in claim 1, wherein the operating system is capable of direct communication with the network interface device.

3. A method as claimed in claim 2, wherein the said direct communication between the non-operating-system functionality bypasses the operating system.

4. A method as claimed in any of claims 1-3, wherein the non-operating-system functionality is a transport library.

5. A method as claimed in any of claims 1-3, wherein the said area of the memory is mapped to a second area of the memory, and the second area of the memory is accessible to the operating system but not directly accessible to the non-operating-system functionality.

6. A method as claimed in any of claims 1-3, comprising, on initiating a transmission operation of data over the network, starting a timer;

and if the timer reaches a predetermined value before an acknowledgement is received for that data transmitting a failure message from the network interface device to the data processing system.

7. A method as claimed in any of claims 1 to 3, comprising, on initiating a transmission operation of data over the network, storing a record of that operation and an indication of the application that was the source of the data;

and, on receiving data for that application starting a timer for each record associated with that application; and

if such a timer reaches a predetermined value before an acknowledgement is received for that data transmitting a failure message from the network interface device to the data processing system.

8. A method as claimed in claim 6, wherein the or each timer is run on the network interface device.

9. A method as claimed in claim 7, comprising cancelling the timer on receiving an acknowledgement for the data, and wherein the or each failure message is directed to the operating system.

10. A method as claimed in claim 9, wherein the step of cancelling the timer comprises the application signaling the entity on which the timer is run in a manner that bypasses the operating system.

11. A method as claimed in claim 6, wherein the or each failure message is directed to the application that was the source of the data.

12. A method as claimed in claim 11, wherein the operating system is responsive to failure messages that are directed to applications that are no longer in communication with the network device to continue the transmission operation in respect of data corresponding to the failure message.

36. A method as claimed in claim 7, wherein each of the timers is run on the network interface device.

13. A data processing system for transmitting data, comprising:

a processor subsystem having access to a memory and a network interface device capable of supporting a communication link over a network with another network interface device, the processor subsystem being in communication with the memory via a bus and the network interface device being in communication with the memory via a bus, the data processing system having;

an application configured to, while executing on the processor subsystem, form data to be transmitted, cause it to be written to an area of the memory comprising a data buffer and corresponding connection state and request a non-operating-system functionality of the data processing system to send the data to be transmitted over the network;

a non-operating system functionality configured to, while executing on the processor subsystem, initiate by means of direct communication between itself and the network interface device a transmission operation of at least some of the data over the network; and

an operating system configured to, while executing on the processor subsystem and in response to the application being determined to be unresponsive after the transmission operation has been initiated over the network, access the said data buffer and connection state and continue the transmission operation over the network by means of the network interface device.

37. A data processing system as claimed in claim 13, wherein the operating system is capable of direct communication with the network interface device.

38. A data processing system as claimed in claim 37, wherein the said direct communication between the non-operating-system functionality bypasses the operating system.

39. A data processing system as claimed in claim 13, wherein the non-operating-system functionality is a transport library.

40. A data processing system as claimed in claim 13, wherein the said area of the memory is mapped to a second area of the memory, and the second area of the memory is accessible to the operating system but not directly accessible to the non-operating-system functionality.

41. A data processing system as claimed in claim 13, wherein the network interface device is configured to, on a transmission operation of data being initiated over the network, start a timer;

and, if the timer reaches a predetermined value before an acknowledgement is received for that data, transmit a failure message to the data processing system.

42. A data processing system as claimed in claim 13, wherein, on a transmission operation of data over the network being initiated, a record of that operation and an indication of the application that was the source of the data is stored;

and the network interface device is configured to, on receiving data for that application, start a timer for each record associated with that application; and

, if such a timer reaches a predetermined value before an acknowledgement is received for that data, transmit a failure message to the data processing system.

43. A data processing system as claimed in claim 41, wherein the or each timer is run on the network interface device.

44. A data processing system as claimed in claim 42, wherein the application is configured to cancel the timer on receiving an acknowledgement for the data, and wherein the or each failure message is directed to the operating system.

45. A data processing system as claimed in claim 44, wherein the application is configured to cancel the timer by signaling the entity on which the timer is run in a manner that bypasses the operating system.

46. A data processing system as claimed in claim 41, wherein the failure message is directed to the application that was the source of the data.

47. A data processing system as claimed in claim 46, wherein the operating system is configured to be responsive to failure messages that are directed to applications that are no longer in communication with the network device and to continue the transmission operation in respect of data corresponding to the failure message.

14. A method for receiving data by means of a data processing system having a processor subsystem, the system being capable of supporting at least one application and having access to a memory and a network interface device capable of supporting a communication link over a network with another network interface device, the method comprising the steps of:

establishing by means of a non-operating-system functionality executing on the processor subsystem, a channel for reception of data by an application, the channel being associated with an area of the memory comprising a data buffer and corresponding connection state; and

receiving data of a data reception operation through that channel by;

the network interface device writing received data to the data buffer; and

the application, while executing on the processor subsystem, reading received data from the data buffer; and

after the reception operation has been initiated over the network, and in response to the application becoming unable to communicate with the network device the operating system, while executing on the processor subsystem, accessing the connection state and the data buffer and continuing the data reception operation, wherein the processor subsystem is in communication with the memory via a bus,

and wherein the network interface device is in communication with the memory via a bus.

15. A method as claimed in claim 14, wherein the operating system is arranged to automatically read received data from the data buffer on a determination being made that the application is unable to communicate with the network device.

16. A system for receiving data comprising:

a network interface device capable of supporting a communication link over a network with another network interface device;

a data processing system having a processor subsystem and supporting an operating system and at least one application and having access to a memory and the network interface device, the data processing system further supporting a non-operating-system functionality configured for, while executing on the processor subsystem, establishing a channel for reception of data by an application, the channel being associated with an area of the memory comprising a data buffer and corresponding connection state;

the network interface device being configured to write received data of a data reception operation to the data buffer;

the application being configured to read received data from the data buffer while the application is executing on the processor subsystem; and

the operating system being configured to, while executing on the processor subsystem and in response to the application becoming unable to communicate with the network device after the reception operation has been initiated over the network, access the connection state and the data buffer and continue the data reception operation,

the processor subsystem being in communication with the memory via a bus and the network interface device being in communication with the memory via a bus.

63. A system as claimed in claim 16, wherein the operating system is arranged to automatically read received data from the data buffer on a determination being made that the application is unable to communicate with the network device.

17. A method for transmitting data by means of a data processing system having a processing subsystem, the system being capable of supporting an application and an operating system and having access to a memory and a network interface device capable of supporting a communication link over a network with another network interface device, the method comprising the steps of:

forming by means of the application data to be transmitted;

a non-operating-system functionality, while executing on the processor subsystem, passing that data to the network interface device for transmission, the said passing of the data being performed bypassing the operating system;

transmitting the data by means of the network interface device;

on receiving an acknowledgement for the data, the network interface device writing the acknowledgement to an area of the memory accessible to the application and starting a timer at the network interface device; and

if the application accesses the acknowledgement, cancelling the timer;

or

if the timer reaches a predetermined value, the network interface device signaling the operating system to indicate that the application is unresponsive,

the processor subsystem being in communication with the memory via a bus and the network interface device being in communication with the memory via a bus.

18. A method as claimed in claim 17, wherein the non-operating-system functionality is a transport library.

19. A method as claimed in claim 17, wherein the said signaling comprises applying a failure event to an event queue of the operating system.

20. A method as claimed in claim 17, comprising:

in response to the operating system being signaled, the operating system communicating with the network interface device to advance communication with the said another network device.

21. A system for transmitting data comprising a data processing system supporting an operating system and a network interface device capable of supporting a communication link over a network with another network interface device, the data processing system having a processor subsystem with access to a memory and the network interface device, and further having:

an application configured to form data to be transmitted;

a non-operating-system functionality configured to, while executing on the processor subsystem, pass the formed data to the network interface device for transmission, the said passing of the data being performed bypassing the operating system; and

a timer at the network interface device;

wherein the network interface device is configured to transmit the data and, on receiving an acknowledgement for the data, write the acknowledgement to an area of the memory accessible to the application and start a timer corresponding to the data;

the network interface device being further configured to;

if the application accesses the acknowledgement, cancel the timer;

or

if the timer reaches a predetermined value, signal the operating system to indicate that the application is unresponsive,

wherein the processor subsystem is in communication with the memory via a bus and the network interface is in communication with the memory via a bus.

48. A system as claimed in claim 21, wherein the non-operating-system functionality is a transport library.

49. A system as claimed in claim 21, wherein the said signaling comprises applying a failure event to an event queue of the operating system.

50. A system as claimed in claim 21, the operating system being configured to, in response to being signaled, communicate with the network interface device to advance communication with the said another network device.

22. A method for transmitting or receiving data by means of a data processing system having a processor subsystem, the system supporting an operating system and an application and having access to a memory and a network interface device capable of supporting a communication link over a network with another network interface device, the method comprising:

allocating one or more areas of the memory for use as data buffers and connection state in the transfer of data between the data processing system and the network interface device; and

directly accessing at least one of the areas of the memory by means of the application, executing on the processor subsystem, for at least one of a data transmission operation by means of the network interface device and a data reception operation by means of the network interface device;

if the application is determined to be unresponsive, the network interface device signaling the operating system to access the said at least one of the areas of the memory; and

in response to the signal, the operating system, executing on the processor subsystem, directly accessing at least one of the data buffers and connection state for continuing the at least one transmission or reception operation by means of the network interface device,

wherein the processor subsystem is in communication with the memory via a bus and the network interface is in communication with the memory via a bus.

23. A method as claimed in claim 22, wherein the method comprises:

receiving data from the network by means of the network device; and

writing that data to the said at least one of the areas of the memory by means of the network device.

24. A method as claimed in claim 23, wherein the network device supports a timer and the method comprises starting the timer to count from a preset initial value when received data is written to the said at least one of the areas, and the application is determined to be unresponsive if the timer reaches a preset final value.

25. A method as claimed in claim 24, comprising the step of setting the initial value and/or the final value by means of the application.

26. A method as claimed in claim 24 or 25, comprising stopping the timer by means of the application on reading received data by means of the application from the said at least one of the areas.

27. A method as claimed in any of claim 22, 23, 24 or 25, wherein each of the said steps of directly accessing at least one of the areas of the memory for the data reception operation by means of the network interface device comprises protocol processing data received from the network by the network interface device and stored in the said at least one of the areas.

28. A method as claimed in claim 27, wherein the step of protocol processing comprises extracting traffic data from the received data.

29. A method as claimed in claim 27, wherein the step of protocol processing comprises causing the network interface device to transmit an acknowledgement and/or re-transmit message over the network in respect of at least some of the received data.

30. A method as claimed in claim 22, wherein the method comprises:

reading data from the said at least one of the areas by means of the network device; and

transmitting that data over the network by means of the network device.

31. A method as claimed in claim 30, wherein each of the said steps of directly accessing at least one of the areas of the memory comprises storing data for transmission in the said at least one of the areas.

32. A method as claimed in claim 30 or 31, wherein each of the said steps of directly accessing at least one of the areas of the memory comprises triggering the network interface device to perform the said step of reading data from the said at least one of the areas.

33. A method as claimed in claim 32, wherein the network device supports a timer and the method comprises starting the timer to count from a preset initial value when the application is signaled by the network interface device that received data has been written to the said at least one of the areas, and the application is determined to be unresponsive if the timer reaches a preset final value.

34. A method as claimed in claim 33, comprising the step of setting the initial value and/or the final value by means of the application.

35. A system for transmitting or receiving data, the system comprising:

a data processing system having a processor subsystem and supporting an operating system and an application and having access to a memory, one or more areas of which are allocated for use for data buffers and connection state in the transfer of data between the data processing system and the network interface device; and

a network interface device capable of supporting a connection over a network with another network interface device and configured to signal the operating system if the application is determined to be unresponsive;

wherein the application is configured to, while executing on the processor subsystem, directly access at least one of the data buffers and connection state for at least one of a data transmission operation by means of the network interface device and a data reception operation by means of the network interface device, and the operating system is configured to, while executing on the processor subsystem and in response to said signal from the network interface device, directly access the said at least one of the data buffers and connection state for continuing the at least one transmission or reception operation by means of the network interface device,

wherein the processor subsystem is in communication with the memory via a bus and the network interface is in communication with the memory via a bus.

51. A system as claimed in claim 35, wherein the network interface device is configured to, on receiving data from the network, write that data to the said at least one of the areas of the memory.

52. A system as claimed in claim 51, wherein the network interface device supports a timer and is configured to start the timer to count from a preset initial value when received data is written to the said at least one of the areas, and the application is determined to be unresponsive if the timer reaches a preset final value.

53. A system as claimed in claim 52, wherein the application is configured to set the initial value and/or the final value.

54. A system as claimed in claim 52, wherein the application is configured to stop the timer on reading received data from the said at least one of the areas.

55. A system as claimed in claim 35, wherein the application and operating system are configured to, on directly accessing at least one of the areas of the memory for a data reception operation by means of the network interface device, protocol process data received from the network by the network interface device and stored in the said at least one of the areas.

56. A system as claimed in claim 55, wherein the protocol processing comprises extracting traffic data from the received data.

57. A system as claimed in claim 55, wherein the protocol processing comprises causing the network interface device to transmit an acknowledgement and/or re-transmit message over the network in respect of at least some of the received data.

58. A system as claimed in claim 35, wherein the network interface device is configured to, on transmitting data over the network, read data from the said at least one of the areas.

59. A system as claimed in claim 58, wherein the application and operating system are configured to, on directly accessing at least one of the areas of the memory for a data transmission operation by means of the network interface device, store data for transmission in the said at least one of the areas.

60. A system as claimed in claim 58, wherein the application and operating system are configured to, on directly accessing at least one of the areas of the memory for a data transmission operation by means of the network interface device, trigger the network interface device to read data from the said at least one of the areas.

61. A system as claimed in claim 60, wherein the network interface device supports a timer and is configured to, when the network interface device signals the application that received data has been written to the said at least one of the areas, start the timer to count from a preset initial value;

the application being determined to be unresponsive if the timer reaches a preset final value.

62. A system as claimed in claim 61, wherein the application is configured to set the initial value and/or the final value.