Apparatuses, systems, and methods for distributed workload serialization
View Patent ↗Apparatuses, systems, methods, and computer program products are provided for processing workload requests in a distributed computing system. In general, a cooperative workload serialization system is provided that includes a Message Queue that is configured to receive and hold workload requests from a number of requestors and a Request Manager that is in communication with the Message Queue and is configured to direct the processing of the workload requests. The system may include a Culler in communication with the Request Manager, where the Culler is configured to monitor the validity of the workload requests. The Request Manager, in turn, may be configured to remove an indicated workload request from the Message Queue based on information from the Culler that the indicated workload request is not valid.
1. A system for processing workload requests comprising:
a message queue configured to receive and hold workload requests from a plurality of requestors;
a request manager associated with a processor, the request manager being in communication with the message queue and configured to direct processing of the workload requests; and
a culler in communication with the request manager, wherein the culler is configured to monitor validity of workload requests,
wherein the message queue is configured to assign an order indication to each workload request based on an order in which the workload request is received by the message queue and, in an instance in which the workload request includes an indication of priority, further based on the indication of priority, such that the order indication prioritizes the workload requests within a first in-first out framework,
wherein each workload request includes a designation of a coordination point indicative of a functionality required for processing of the workload request,
wherein the culler is configured to monitor the validity of the workload requests by monitoring a network connection between the requestor of the respective workload request and at least one of the request manager or the respective designated coordination point, and
wherein the request manager is configured to direct processing of a particular workload request based at least in part on the assigned order indication of the particular workload request, an availability of the coordination point designated by the particular workload request, and information received from the culler, and
wherein each requestor is configured to establish a network connection with a network port of the system for communicating a respective workload request to the request manager and for processing of the workload requests, wherein the culler is configured to monitor a validity of the network port associated with each requestor, and wherein the request manager is configured to remove an indicated workload request from the message queue based on information from the culler that a network port associated with a requestor of the indicated workload request is not valid.
2. The system of claim 1 , wherein the request manager is configured to determine an availability of a particular coordination point based on information from the culler that a network port associated with a requestor of a workload request designating the particular coordination point is not valid.
3. The system of claim 1 , wherein the request manager is configured to receive a communication from each requestor indicating an availability of the coordination point designated in the corresponding workload request upon completion of processing of the respective workload request.
4. The system of claim 1 , wherein the request manager is configured to receive an inquiry from a requestor regarding an availability of a particular coordination point and to communicate a response to the inquiry.
5. The system of claim 1 , wherein the request manager is configured to remove a particular workload request from the message queue based on an expiration of the particular workload request.
6. The system of claim 1 , wherein the request manager is configured to determine a type of access required by each workload request and to direct concurrent processing of more than one workload request in the message queue designating the same coordination point for which shared access is determined.
7. The system of claim 1 , wherein the coordination point comprises an arbitrary value that is independent of a computer language or operating environment.
8. A method for processing workload requests in a distributed system comprising:
communicating with a message queue, wherein the message queue is configured to receive and hold workload requests, wherein the workload requests are received from a plurality of requestors, wherein each workload request includes a designation of a coordination point indicative of a functionality required for processing of the workload request, and wherein an order indication is assigned to each workload request based on an order in which the workload request is received by the message queue and, in an instance in which the workload request includes an indication of priority, further based on the indication of priority, such that the order indication prioritizes the workload requests within a first in-first out framework;
communicating with a culler configured to monitor validity of workload requests, wherein the culler is configured to monitor the validity of the workload requests by monitoring a network connection with the requestor of the respective workload request or a network connection between the requestor and the respective designated coordination point; and
directing processing of each workload request based at least in part on the assigned order indication of the particular workload request, an availability of the coordination point designated by the particular workload request, and information received from the culler; and
removing an indicated workload request from the message queue based on information received from the culler that a network port associated with a requestor of the indicated workload request is not valid.
9. The method of claim 8 further comprising determining an availability of a particular coordination point based on information received from the culler that a network port associated with a requestor of a workload request designating the particular coordination point is not valid.
10. The method of claim 8 further comprising receiving a communication from each requestor indicating an availability of the coordination point designated in the corresponding workload request upon completion of processing of the respective workload request.
11. The method of claim 8 further comprising receiving an inquiry from a requestor regarding an availability of a particular coordination point and communicating a response to the inquiry.
12. The method of claim 8 further comprising removing a particular workload request from the message queue based on an expiration of the workload request.
13. The method of claim 8 further comprising determining a type of access required by each workload request and directing concurrent processing of more than one workload request in the message queue designating the same coordination point for which shared access is determined.
14. The method of claim 8 , wherein the coordination point comprises an arbitrary value that is independent of a computer language or operating environment.