System and method for handling out-of-order frames
View Patent ↗Aspects of the invention may be found in a method and system for handling out-of-order frames. In one embodiment, a method includes, for example, one or more of the following: receiving an out-of-order frame via a network interface card (NIC); placing data of the out-of-order frame in a host memory; and managing information relating to one or more holes in a receive window.
1. A method for handling out-of-order frames, comprising the steps of:
(a) receiving an out-of-order frame via a network subsystem;
(b) placing data of the out-of-order frame in a host memory;
(c) managing information relating to one or more holes resulting from the out-of-order frame in a receive window; and
(d) setting a programmable limit with respect to a number of holes allowed in the receive window.
2. The method according to claim 1 , wherein the out-of-order frame is received via a TCP offload engine (TOE) of the network subsystem or a TCP-enabled Ethernet controller (TEEC) of the network subsystem.
3. The method according to claim 1 , wherein the network subsystem does not store the out-of-order frame on an onboard memory.
4. The method according to claim 3 , wherein the network subsystem does not store one or more missing frames relating to the out-of-order frame.
5. The method according to claim 1 , wherein the network subsystem comprises a network interface card (NIC).
6. The method according to claim 1 , wherein step (b) comprises placing the data of the out-of-order frame in the host memory if the out-of-order frame is determined to be inside the receive window.
7. The method according to claim 1 , further comprising:
dropping the out-of-order frame if the out-of-order frame is determined not to be inside the receive window.
8. The method according to claim 1 , further comprising:
placing a portion of the data of the out-of-order frame in the host memory, the portion of the data being inside the receive window.
9. The method according to claim 1 , wherein step (c) comprises one or more of the following:
storing information relating to a new hole created by the placement of the data of the out-of-order frame,
updating information relating to an existing hole modified by the placement of the data of the out-of-order frame, and
deleting information relating to a plugged hole created by the placement of the data of the out-of-order frame.
10. The method according to claim 9 ,
wherein the stored information resides on the network subsystem,
wherein the updated information resides on the network subsystem, and
wherein the deleted information resided on the network subsystem.
11. The method according to claim 1 , wherein the managed information resides on the network subsystem.
12. The method according to claim 1 , further comprising:
updating the receive window based upon the placement of the data of the out-of-order frame.
13. The method according to claim 1 , wherein step (b) comprises mapping TCP space into host buffer space.
14. The method according to claim 1 , wherein the network subsystem comprises a memory whose memory usage scales with a number of holes in the receive window.
15. The method according to claim 1 , wherein the network subsystem comprises a memory whose memory usage does not scale with a number of out-of-order frames received.