Mitigating data loss in a storage network
A method for execution by a storage network starts by maintaining loading and data access rate information for a storage node and estimating a future data access rate for the storage node. The method continues by determining a probability level of potential future data loss, based on the estimated future data access rate and in response to a determination that the probability level of potential future data loss compares unfavorably to a maximum probability of data loss threshold level the method continues by facilitating migration of at least a portion of data stored on the storage node for temporary storage in another storage node of the storage network.
1. A method for execution by a storage network, the method comprises:
maintaining loading and data access rate information for a solid-state storage node of the storage network, wherein the storage network includes a plurality of solid-state storage nodes and wherein a data object stored in the storage network is dispersed error encoded in accordance with dispersed error encoding parameters to produce a plurality of encoded data slices for storage in different ones of the plurality of storage nodes, wherein the plurality of storage nodes includes the solid-state storage node;
estimating a future data access rate for the solid-state storage node;
determining a probability level of potential future data loss, based on the estimated future data access rate and a data access tasks maximum for the solid-state storage node; and
in response to a determination that the probability level of potential future data loss compares unfavorably to a predetermined maximum probability of data loss threshold level, facilitating migration of at least a portion of data stored on the solid-state storage node to another storage node of the storage network for temporary storage.
2. The method of claim 1 , further comprising:
suspending, upon the probability level of potential future data loss comparing unfavorably to a maximum probability of data loss threshold level, the execution of one or more ongoing data access tasks for the storage node.
3. The method of claim 2 , wherein the data is stored as sets of encoded data slices and the suspending includes one or more of: storing fewer slices of each set of newly stored encoded data slices, or prioritizing data access tasks.
4. The method of claim 1 , wherein the estimated future data access rate is based on write data access and maintenance tasks associated with the s storage node.
5. The method of claim 1 , wherein the estimated future data access rate is based on write data access and an elapsed time for data stored in the storage node.
6. The method of claim 1 , wherein the estimated future data access rate is generated based on one or more of: storage node loading information, interpreting a task queue, interpreting current loading rates, interpreting a schedule, or interpreting a message.
7. The method of claim 1 , wherein the determining includes at least one of: estimating a future capacity for execution of maintenance tasks or estimating a data retrieval reliability level.
8. The method of claim 1 , wherein the data is stored as sets of encoded data slices and the facilitating includes one or more of: storing additional encoded data slices of each set of newly stored encoded data slices, prioritizing maintenance tasks, or a de-prioritizing data access tasks.
9. The method of claim 8 , wherein the storing additional slices of each set of newly stored encoded data slices includes increasing a write threshold number.
10. The method of claim 8 , wherein the storing additional slices of each set of newly stored encoded data slices includes decreasing a read threshold number.
11. A computing device of a storage network, the computing device comprises:
an interface;
a local memory; and
a processing module operably coupled to the interface and the local memory, wherein the processing module functions to:
maintain loading and data access rate information for a solid-state storage node of the storage network, wherein the storage network includes a plurality of solid-state storage nodes and wherein a data object stored in the storage network is dispersed error encoded in accordance with dispersed error encoding parameters to produce a plurality of encoded data slices for storage in different ones of the plurality of storage nodes, wherein the plurality of storage nodes includes the solid-state storage node;
estimate a future data access rate for the solid-state storage node;
determine a probability level of potential future data loss, based on the estimated future data access rate and a data access tasks maximum for the solid-state storage node; and
in response to a determination that the probability level of potential future data loss compares unfavorably to a predetermined maximum probability of data loss threshold level, suspend, upon a current data access task rate being greater than a maximum task rate level, facilitate execution of a preventative data loss mitigation process.
12. The computing device of claim 11 , wherein the data is stored as sets of encoded data slices and the suspending includes one or more of: storing fewer slices of each set of newly stored encoded data slices, or prioritizing data access tasks.
13. The computing device of claim 11 , wherein the estimated future data access rate is based on write data access and maintenance tasks associated with the storage node.
14. The computing device of claim 11 , wherein the estimated future data access rate is based on write data access and an elapsed time for data stored in the storage node.
15. The computing device of claim 11 , wherein the estimated future data access rate is generated based on one or more of: storage node loading information, interpreting a task queue, interpreting current loading rates, interpreting a schedule, or interpreting a message.
16. The computing device of claim 11 , wherein the determining includes at least one of: estimating a future capacity for execution of maintenance tasks or estimating a data retrieval reliability level.
17. The computing device of claim 11 , wherein the data is stored as sets of encoded data slices and the facilitating includes one or more of: storing additional encoded data slices of each set of newly stored encoded data slices, prioritizing maintenance tasks, or a de-prioritizing data access tasks.
18. The computing device of claim 17 , wherein the processing module functions to store additional slices of each set of newly stored encoded data slices by increasing a write threshold number.
19. The computing device of claim 18 , wherein the processing module functions to store additional slices of each set of newly stored encoded data slices by decreasing a read threshold number.
20. A system comprises:
an interface;
a local memory; and
a processing module operably coupled to the interface and the local memory, wherein the processing module functions to:
maintain loading and data access rate information for a solid-state storage node of a storage network, wherein data is stored as sets of encoded data slices in the storage node;
estimate a future data access rate for the solid-state storage node;
determine a probability level of potential future data loss, based on the estimated future data access rate and a predetermined threshold number of write accesses for the solid-state storage node; and
in response to a determination that the probability level of potential future data loss compares unfavorably to a predetermined maximum probability of data loss threshold level, store additional encoded data slices of each set of any encoded data slices for which a write access task is received by the storage node.