Efficiently accessing an encoded data slice in a memory container utilizing a memory bin

摘要

A method begins by receiving encoded data slices for storage. At least some of the encoded data slices have different data sizes. The method continues by accessing memory container information of the storage unit that includes a listing of virtual memory containers of the storage unit and, for each virtual memory container, bin identifier information. Each virtual memory contain is divided into bins, where the bins of a virtual memory container are of a substantially similar storage size. At least some of the virtual memory containers have different bin storage sizes. The method continues by mapping encoded data slices to virtual memory containers of the plurality based on data size of the encoded data slices and bin storage sizes of the virtual memory containers. The method continues by storing the encoded data slices in the virtual memory containers based on the mapping.

主权项

1. A method for execution by a processing module of a storage unit of a dispersed storage network (DSN), the method comprises:
receiving a plurality of encoded data slices for storage, wherein at least some of the encoded data slices of the plurality of encoded data slices have different data sizes; accessing memory container information of the storage unit, wherein the memory container information includes a listing of a plurality of virtual memory containers of the storage unit and, for each virtual memory container, bin identifier information, wherein physical memory of the storage unit is virtually divided into the virtual memory containers and each virtual memory contain is divided into a plurality of bins, wherein the plurality of bins of a virtual memory container of the plurality of virtual memory containers are of a substantially similar storage size, and wherein at least some of the plurality of virtual memory containers have different bin storage sizes; and mapping encoded data slices of the plurality of encoded data slices to virtual memory containers of the plurality of virtual memory containers based on data size of the encoded data slices and bin storage sizes of the virtual memory containers; and storing the encoded data slices in the virtual memory containers based on the mapping.