Memory utilization balancing in a dispersed storage network
View Patent ↗A method begins by a processing module identifying a memory loading mismatch between a first memory device and a second memory device of a dispersed storage unit, wherein the first memory device is assigned a first range of slice names and the second memory device is assigned a second range of slice names. The method continues with the processing module determining an estimated impact to reduce the memory loading mismatch and when the estimated impact compares favorably to an impact threshold, modifying the first and second ranges of slices names to produce a first modified range of slice names for the first memory device and a second modified range of slice names for the second memory device based on the memory loading mismatch and transferring one or more encoded data slices between the first and second memory devices in accordance with the first and second modified ranges of slice names.
1. A method comprises:
establishing, by a processing module of a dispersed storage unit, an address based memory balancing scheme that is based on allocating a set of unique address ranges to a set of memory devices of the dispersed storage unit, wherein a respective unique address range is allocated to a respective memory device of the set of memory devices, in which the respective unique address range corresponds to a slice name range, and wherein the slice name range pertains to slice names of a plurality of data slices that are created when encoding a plurality of data segments, in which for a respective data segment, n data slices are generated in accordance with an error coding function, and in which at least a threshold number k of the n data slices are needed to reconstruct the respective data segment, where k is less than n;
storing, in a first memory device of the set of memory devices, encoded data slices having slice name range in accordance with a first unique address range;
storing, in a second memory device of the set of memory devices, encoded data slices having slice name range in accordance with a second unique address range;
identifying a memory loading mismatch between the first memory device and the second memory device, wherein the memory loading mismatch occurs when more storage space is utilized in the first memory device than utilized in the second memory device for storing the encoded data slices;
determining an estimated impact to reduce the memory loading mismatch; and
when the estimated impact compares favorably to an impact threshold, modifying the first and second sets of unique address ranges based on the memory loading mismatch, by reducing the first unique address range corresponding to the first memory device and expanding the second unique address range corresponding to the second memory device, such that storage space utilization of the first and second memory devices is approximately balanced for the first and second unique address ranges.
2. The method of claim 1 , wherein the modifying the first and second sets of unique address ranges comprises:
de-assigning the first and second sets of unique address ranges from the first and second memory devices to create an unassigned range of slice names; and
partitioning the unassigned range of slices names to obtain the approximate balance of storage space utilization for the first and second memory devices.
3. The method of claim 1 , wherein the identifying the memory loading mismatch comprises at least one of:
determining a utilized amount of storage for the first and second memory devices;
determining an unutilized amount of storage for the first and second memory devices;
determining a utilization percentage of storage capacity for the first and second memory devices;
determining an unutilized percentage of storage capacity for the first and second memory devices; and
determining a storage balancing factor for a group of encoded data slices associated with at least one of a priority indicator, a security indicator, a performance indicator, a user identifier, and a vault identifier.
4. The method of claim 1 , wherein the determining the estimated impact comprises at least one of:
determining a financial impact based on one or more of:
a cost level; and
a revenue gain or loss level;
determining a processing resource impact based on one or more of:
a memory capacity extension time period;
a balancing execution time period;
a performance level;
a wide area network bandwidth utilization level to execute load balancing; and
a local area network bandwidth utilization level to execute the load balancing;
determining an accessibility impact based on one or more of:
a wide area network bandwidth availability level;
a local area network bandwidth availability level;
a memory unavailability time period; and
balancing execution time; and
determining a user impact based on one or more of:
a security level;
a priority level;
an associated user identifier (ID); and
an associated vault ID.
5. The method of claim 1 further comprises:
transferring one or more encoded data slices from the first memory device to the second memory device in accordance with the modifying of the first and second sets of unique address ranges.
6. A computer comprises:
an interface;
a set of memory devices; and
a processing module operably coupled to the interface and the memory, wherein the processing module is operable to:
establish an address based memory balancing scheme that is based on allocating a set of unique address ranges to the set of memory devices, wherein a respective unique address range is allocated to a respective memory device of the set of memory devices, in which the respective unique address range corresponds to a slice name range, and wherein the slice name range pertains to slice names of a plurality of data slices that are created when encoding a plurality of data segments, in which for a respective data segment, n data slices are generated in accordance with an error coding function, and in which at least a threshold number k of the n data slices are needed to reconstruct the respective data segment, where k is less than n;
store, in a first memory device of the set of memory devices, encoded data slices having slice name range in accordance with a first unique address range;
store, in a second memory device of the set of memory devices, encoded data slices having slice name range in accordance with a second unique address range;
identify a memory loading mismatch between the first memory device and the second memory device, wherein the memory loading mismatch occurs when more storage space is utilized in the first memory device than utilized in the second memory device for storing the encoded data slices;
determine an estimated impact to reduce the memory loading mismatch; and
when the estimated impact compares favorably to an impact threshold, modify the first and second sets of unique address ranges based on the memory loading mismatch, by reducing the first unique address range corresponding to the first memory device and expanding the second unique address range corresponding to the second memory device, such that storage space utilization of the first and second memory devices is approximately balanced for the first and second unique address ranges.
7. The computer of claim 6 , wherein the processing module functions to modify the first and second sets of unique address ranges by:
de-assigning the first and second sets of unique address ranges from the first and second memory devices to create an unassigned range of slice names; and
partitioning the unassigned range of slices names to obtain the approximate balance of storage space utilization for the first and second memory devices.
8. The computer of claim 6 , wherein the processing module functions to identify the memory loading mismatch by at least one of:
determining a utilized amount of storage for the first and second memory devices;
determining an unutilized amount of storage for the first and second memory devices;
determining a utilization percentage of storage capacity for the first and second memory devices;
determining an unutilized percentage of storage capacity for the first and second memory devices; and
determining a storage balancing factor for a group of encoded data slices associated with at least one of a priority indicator, a security indicator, a performance indicator, a user identifier, and a vault identifier.
9. The computer of claim 6 , wherein the processing module functions to determine the estimated impact by at least one of:
determining a financial impact based on one or more of:
a cost level; and
a revenue gain or loss level;
determining a processing resource impact based on one or more of:
a memory capacity extension time period;
a balancing execution time period;
a performance level;
a wide area network bandwidth utilization level to execute load balancing; and
a local area network bandwidth utilization level to execute the load balancing;
determining an accessibility impact based on one or more of:
a wide area network bandwidth availability level;
a local area network bandwidth availability level;
a memory unavailability time period; and
balancing execution time; and
determining a user impact based on one or more of:
a security level;
a priority level;
an associated user identifier (ID); and
an associated vault ID.
10. The computer of claim 6 , wherein the processing module further functions to:
transfer one or more encoded data slices from the first memory device to the second memory device in accordance with modifying the first and second sets of unique address ranges.