Method of Managing Workloads and Associated Distributed Processing System

Abstract

Various embodiments enable a server system to receive a request to store data, select various distributed devices to store the data, and then send the data to the selected distributed devices. In one embodiment, a method may include: receiving a request to store back-up data on a distributed processing system from a client system, the back-up data having a storage priority, searching a database to identify one or more distributed devices with excess storage capacity, and selecting one or more of the distributed devices to store the back-up data based in part on the back-up data's storage priority. Then, sending the back-up data to one or more selected distributed devices along with retention instructions indicating conditions for retaining and/or deleting the back-up data, and updating an index with addresses for the one or more selected distributed devices that received the back-up data.

1 . A method comprising:
 receiving a request to store back-up data on a distributed processing system from a client system, the back-up data having a storage priority;   searching a database to identify one or more distributed devices with excess storage capacity;   selecting one or more of the distributed devices to store the back-up data based in part on the back-up data's storage priority;   sending the back-up data to one or more selected distributed devices along with retention instructions indicating conditions for retaining and/or deleting the back-up data; and   updating an index with addresses for the one or more selected distributed devices that received the back-up data.   
     
     
         2 . A method as recited in  claim 1 , further comprising incentivizing one or more distributed devices to join the distributed processing system, wherein an incentive comprises an authorization to back-up data on the distributed processing system. 
     
     
         3 . A method as recited in  claim 1 , further comprising:
 partitioning the back-up data into N partitions based in part on the back-up data's storage priority;   identifying M distributed devices from the database to store the N partitions; and   distributing the N partitions across the M distributed devices for storage.   
     
     
         4 . A method as recited in  claim 3 , further comprising updating the index to identify the M distributed devices to which the N partitions were distributed. 
     
     
         5 . A method as recited in  claim 1 , further comprising identifying at least one workload capability for one or more distributed devices, and utilizing the at least one workload capability to schedule back-up data workloads for the one or more distributed devices. 
     
     
         6 . A method as recited in  claim 1 , wherein the storage priority is configured to enable a determination of a retention time for the back-up data, a recovery speed for recovering the back-up data, and a level of redundancy for the back-up data. 
     
     
         7 . A method as recited in  claim 6 , wherein the retention time, the recovery speed, and the level of redundancy are used to determine a number of distributed devices to store the back-up data, and which distributed devices are selected to store the back-up data. 
     
     
         8 . A method as recited in  claim 1 , wherein the back-up data includes redundant back-up data so that the back-up data is stored on at least two different distributed devices. 
     
     
         9 . A tangible computer readable medium having instructions stored thereon, the instructions comprising:
 instructions to receive a command from a user to store data;   instructions to prompt the user to select one or more options for storing the data;   instructions to generate a storage priority for the data based in part on the storage options selected by the user;   instructions to request a server system to store the data, the request including the data's storage priority; and   instructions to send the data to the server system for distribution and storage on one or more distributed devices.   
     
     
         10 . The tangible computer readable medium as recited in  claim 9 , wherein the storage priority is configured to enable a determination or a retention time for the data, a recovery speed for recovering the data, and a level of redundancy for the data. 
     
     
         11 . The tangible computer readable medium as recited in  claim 10 , wherein the retention time, the recovery speed, and the redundancy level are used to determine a number of distributed devices to store the data, and which distributed devices are selected to store the data. 
     
     
         12 . A tangible computer readable medium having instructions stored thereon, the instructions, the instructions comprising:
 instructions to incentivize one or more distributed devices to join a network and store data;   instructions to receive a request from a client system to store data on the network, the data having an associated storage priority;   instructions to search a database to identify one or more distributed devices with excess storage capacity;   instructions to select one or more distributed devices to store the data based in part on the data's storage priority;   instructions to send the data to one or more selected distributed devices along with retention instructions indicating conditions for retaining and/or deleting the data; and   instructions to update an index with addresses for the one or more selected distributed devices that received the data.   
     
     
         13 . The tangible computer readable medium as recited in  claim 12 , wherein an incentive comprises an authorization to store data on the network. 
     
     
         14 . The tangible computer readable medium as recited in  claim 12 , wherein the storage priority is configured to enable a determination of a retention time for the data, a recovery speed for recovering the data, and a level of redundancy for the data. 
     
     
         15 . The tangible computer readable medium as recited in  claim 14 , wherein the retention time, the recovery speed, and the level of redundancy are used to determine a number of distributed devices to store the data, and which distributed devices are selected to store the data. 
     
     
         16 . The tangible computer readable medium as recited in  claim 12 , wherein the data includes redundant data so that the data can be stored on at least two different distributed devices. 
     
     
         17 . The tangible computer readable medium as recited in  claim 12 , further comprising instructions to identify at least one workload capability for one or more distributed devices, and utilize the at least one workload capability to schedule data workloads for the one or more distributed devices. 
     
     
         18 . The tangible computer readable medium as recited in  claim 12 , further comprising instructions to transfer a software agent to one or more distributed devices, the software agent configured to manage data sent to the one or more distributed devices. 
     
     
         19 . The tangible computer readable medium as recited in  claim 12 , further comprising:
 instructions to partition the data into N partitions based in part on the data's storage priority;   instructions to identify M distributed devices from the database to store the N partitions; and   instructions to distribute the N partitions across the M distributed devices for storage.   
     
     
         20 . The tangible computer readable medium as recited in  claim 19 , further comprising instructions to update the index to identify the M distributed devices to which the N partitions were distributed.