Process scheduler employing adaptive partitioning of process threads
View Patent ↗A system is set forth comprising a processor and memory storage units storing software code. The software code comprises code for a scheduling system and for generating a plurality of adaptive partitions that are each associated with one or more software threads and that each have a corresponding processor budget. The code also is executable to generate at least one sending thread and at least one receiving thread which responds to communications from the sending thread to execute one or more tasks corresponding to the communications. In operation, the scheduling system selectively allocates the processor to each sending and receiving thread based on the processor budget of the adaptive partition associated with the respective thread. The scheduling system bills the processor budget of the adaptive partition associated with the sending thread for processor allocation used by the receiving thread to respond to communications sent by the sending thread.
1. A system comprising:
a processor;
one or more memory storage units;
software code stored in the one or more memory storage units, where the software code is executable by the processor and comprises:
a plurality of adaptive partitions each having an associated guaranteed processor time budget and one or more associated process threads from a plurality of process threads;
the plurality of process threads each having a priority and each dynamically associable with any one of the plurality of adaptive partitions; and
a process scheduler executable by the processor configured to:
when the system is under a normal load, allocate the processor to a process thread, of the plurality of process threads, that is in a ready state and having the highest priority amongst process threads, of the plurality of process threads, that are in the ready state; and
when the system is in overload, allocate the processor to a process thread, of the plurality of process threads, that is in the ready state, having the highest priority amongst process threads, of the plurality of process threads, that are in the ready state and for which the adaptive partition that the process thread is associated with has available guaranteed processor time budget;
where the guaranteed processor time budget is allocated and billed over successive averaging windows; and
where a portion of the guaranteed processor time budget associated with each adaptive partition is billed whenever the processor is allocated to a process thread associated with the adaptive partition.
2. The system of claim 1 , the plurality of process threads comprising a sending thread that sends a message and a receiving thread that receives the message;
where the guaranteed processor time budget associated the adaptive partition with which the sending thread is associated is billed when the processor is allocated to the receiving thread to process the message.
3. The system of claim 2 , where the receiving thread is temporarily associated with the adaptive partition with which the sending thread is associated while the receiving thread is processing the message.
4. The system of claim 1 , where the system is in overload when all of the process threads in the ready state cannot be allocated the processor over the duration of one averaging window, of the successive averaging windows, and where the system is under normal load otherwise.
5. The system of claim 1 , where the guaranteed processor time budget associated with each of the plurality of adaptive partitions is dynamic and can be reallocated while the system executes.
6. The system of claim 1 , where the process thread to which the processor is allocated runs until the process thread is finished, is blocked, or the guaranteed processor time budget associated with adaptive partition with which the process thread is associated is exhausted.
7. The system of claim 6 , where the process thread to which the processor is allocated further runs until the process thread is preempted and the processor is allocated to another process thread, of the plurality of process threads, that is in the ready state and that has a priority higher than the priority of the process thread to which the processor is currently allocated.
8. A method of scheduling a plurality of process threads, each having a priority and each dynamically associable with an adaptive partition, for execution by a processor of a system, the method comprising:
creating a plurality of adaptive partitions each having an associated guaranteed processor time budget;
associating one or more process threads from the plurality of process threads with each of the plurality of adaptive partitions;
when the processor is under a normal load, allocating the processor to a process thread, of the plurality of process threads, that is in a ready state and having the highest priority amongst process threads, of the plurality of process threads, that are in the ready state; and
when the processor is in overload, allocating the processor to a process thread, of the plurality of process threads, that is in the ready state, having the highest priority amongst process threads, of the plurality of process threads, that are in the ready state and for which the adaptive partition that the process thread is associated with has available guaranteed processor time budget;
where the guaranteed processor time budget is allocated and billed over successive averaging windows; and where a portion of the guaranteed processor time budget associated with each adaptive partition is billed whenever the processor is allocated to a process thread associated with the adaptive partition.
9. The method of claim 8 , further comprising:
sending a message from a sending thread of the plurality of process threads;
receiving the message by a receiving thread of the plurality of process threads; and
billing the guaranteed processor time budget associated the adaptive partition with which the sending thread is associated when the processor is allocated to the receiving thread to process the message.
10. The method of claim 9 , further comprising:
temporarily associating the receiving thread with the adaptive partition with which the sending thread is associated while the receiving thread is processing the message.
11. The method of claim 8 , where the system is in overload when all of the process threads in the ready state cannot be allocated the processor over the duration of one averaging window, of the successive averaging windows, and where the system is under normal load otherwise.
12. The method of claim 8 , where the guaranteed processor time budget associated with each of the plurality of adaptive partitions is dynamic and can be reallocated while the system executes.
13. The method of claim 8 , where the process thread to which the processor is allocated runs until the process thread is finished, is blocked, or the guaranteed processor time budget associated with adaptive partition with which the process thread is associated is exhausted.
14. The method of claim 13 , where the process thread to which the processor is allocated further runs until the process thread is preempted and the processor is allocated to another process thread, of the plurality of process threads, that is in the ready state and that has a priority higher than the priority of the process thread to which the processor is currently allocated.