Abstract: The present invention is directed toward data packet transmission scheduling. Scheduling values, such as priority or other scheduling criteria assigned to data packets, are placed in a scheduling heap data structure. Packets percolate up through the heap by comparing their assigned values in pairs. Operations in the heap may be pipelined so as to provide for high-speed sorting. Thus, a few relatively simple operations can be performed repeatedly to quickly percolate packets up through the heap. Another aspect of the invention provides for fast traversal of the scheduling heap data structure. The hierarchical heap may include a highest level having a single position and each succeeding lower level having twice the number of positions as the preceding level. A binary number may represent each position in the heap. To traverse the heap, the relative movements necessary to move from one position to another may be determined from the binary number. This is useful to quickly and efficiently traverse the heap.

Abstract: The present invention is directed toward methods and apparatus for data packet transmission scheduling using a partitioned scheduling heap data structure. The scheduling heap data structure has a plurality of levels for storing scheduling values for data packets according to their relative priorities. A highest level in the heap has a single position and each succeeding lower level has twice the number of positions as the preceding level. The data structure may be adapted to store a plurality of logical heaps within the heap data structure by assigning a highest level of each logical heap to a level in the heap data structure that is lower than the highest level. Thus, a single physical memory may be adapted to store plural logical heaps. This is useful because a single physical memory can be adapted to prioritize packets of various different transmission protocols and speeds.

Abstract: The present invention is directed toward methods and apparatus for packet transmission scheduling in a data communication network. In one aspect, received data packets are assigned to an appropriate one of a plurality of scheduling heap data structures. Each scheduling heap data structure is percolated to identify a most eligible data packet in each heap data structure. A highest-priority one of the most-eligible data packets is identifying by prioritizing among the most-eligible data packets. This is useful because the scheduling tasks may be distributed among the hierarchy of schedulers to efficiently handle data packet scheduling. Another aspect provides a technique for combining priority schemes, such as strict priority and weighted fair queuing. This is useful because packets may have equal priorities or no priorities, such as in the case of certain legacy equipment.

Abstract: The present invention is directed toward data packet transmission scheduling. Scheduling values, such as priority or other scheduling criteria assigned to data packets, are placed in a scheduling heap data structure. Packets percolate up through the heap by comparing their assigned values in pairs. Operations in the heap may be pipelined so as to provide for high-speed sorting. Thus, a few relatively simple operations can be performed repeatedly to quickly percolate packets up through the heap. Another aspect of the invention provides for fast traversal of the scheduling heap data structure. The hierarchical heap may include a highest level having a single position and each succeeding lower level having twice the number of positions as the preceding level. A binary number may represent each position in the heap. To traverse the heap, the relative movements necessary to move from one position to another may be determined from the binary number. This is useful to quickly and efficiently traverse the heap.

Abstract: The present invention is directed toward methods and apparatus for scheduling packet transmission based on anticipated arrival times of the data packets. Arrival times for data packets may be determined relative to a system clock value. Because the system clock is expressed by a finite number of bits, the clock rolls over to all zeros after it reaches its maximum value. Thus, some of the arrival times may be anticipated to occur after the system clock recycles and a comparison of the magnitude of arrival times would not always indicate which is earlier in time. Since packets are limited in length, however, the range of arrival times is bounded. By determining whether the difference between arrival times exceeds the maximum range of arrival times, it can be determined that the result of a comparison of magnitudes yields a wrong result. By knowing that the result is wrong, it can then be reversed to correctly indicate which arrival time occurs first.

Abstract: The present invention is directed toward methods and apparatus for data packet transmission scheduling using a partitioned scheduling heap data structure. The scheduling heap data structure has a plurality of levels for storing scheduling values for data packets according to their relative priorities. A highest level in the heap has a single position and each succeeding lower level has twice the number of positions as the preceding level. The data structure may be adapted to store a plurality of logical heaps within the heap data structure by assigning a highest level of each logical heap to a level in the heap data structure that is lower than the highest level. Thus, a single physical memory may be adapted to store plural logical heaps. This is useful because a single physical memory can be adapted to prioritize packets of various different transmission protocols and speeds.