US2014198799A1PendingUtilityA1
Scheduling and Traffic Management with Offload Processors
Est. expiryJan 17, 2033(~6.5 yrs left)· nominal 20-yr term from priority
H04L 49/90H04L 67/1097H04L 2101/686H04L 67/10Y02D10/00G06F 12/0875G06F 15/161G06F 13/1652H04L 47/2441G06F 13/4022G06F 9/3877H04L 47/6295H04L 47/624H04L 61/2592H04L 47/56G06F 9/4843G06F 13/362G06F 9/461H04L 49/40G06F 13/285G06F 15/17337G06F 13/4068H04L 47/193H04L 61/103G06F 12/1027G06F 12/0815G06F 13/16G06F 12/1081G06F 2212/1024
61
PatentIndex Score
0
Cited by
0
References
0
Claims
Abstract
A method for providing scheduling services for network packet processing using a memory bus connected module is disclosed. The method can include transferring network packets to the module through a memory bus connection, reordering network packets received from the memory bus connection with a scheduling circuit and placing the reordered network packets into multiple input/output queues, and modifying reordered network packets placed into multiple input/output queues using multiple offload processors connected to the memory bus.
Claims
exact text as granted — not AI-modifiedWhat is claimed is:
1 . A method for providing scheduling services for network packet processing using a memory bus connected module, comprising the steps of:
transferring network packets to the module through a memory bus connection, reordering network packets received from the memory bus connection with a scheduling circuit and placing the reordered network packets into multiple input/output queues, and modifying reordered network packets placed into multiple input/output queues using multiple offload processors connected to the memory bus.
2 . The method of claim 1 , wherein placing the reordered network packets is based on availability of the multiple offload processors.
3 . The method of claim 1 , wherein the reordering of network packets is according to session priorities of the network packets.
4 . The method of claim 1 , further including initiating a context switch of at least one of the multiple offload processors by operation of the scheduling circuit.
5 . The method of claim 1 , further including transferring network packets into a defined traffic management queue by operation of the scheduling circuit.
6 . The method of claim 1 , further including determining when packet processing for each of the multiple offload processors is complete by operation of the scheduling circuit.
7 . The method of claim 1 further including preempting a current network packet processing session by operation of the scheduling circuit.
8 . The method of claim 1 , wherein transferring network packets to the module includes transferring the network packets through a memory bus socket.
9 . The method of claim 1 , wherein transferring network packets to the module includes transferring the network packets through a dual in line memory module (DIMM) or DIMM compatible socket.Cited by (0)
No later patents cite this yet.
References (0)
No backward citations on record.