Data movement from data storage clusters

Data storage equipment, comprising:

• a processor;
• and
• a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising:
• distributing data movement tasks among multiple nodes of a data storage cluster, wherein the multiple nodes share a data store that identifies the data movement tasks, and wherein distributing the data movement tasks comprises:
• splitting the data store into multiple storage segments, wherein the multiple storage segments comprise at least a first storage segment and a second storage segment;
• assigning, to a first group of nodes of the multiple nodes, a first affinity to the first storage segment, resulting in an affinity of the first group of nodes to select first data movement tasks of the first storage segment for processing over first ones of the data movement tasks that are not part of the first storage segment;
• assigning, to a second group of nodes of the multiple nodes, a second affinity to the second storage segment, resulting in an affinity of the second group of nodes to select second data movement tasks of the second storage segment for processing over second ones of the data movement tasks that are not part of the second storage segment;
• assigning, to respective first nodes of the first group of nodes, different first start positions within the first storage segment to search for first unclaimed data movement tasks in the first storage segment for processing, resulting in the respective first nodes of the first group of nodes processing the first data movement tasks of the first storage segment according to the different first start positions within the first storage segment;
• and
• assigning, to respective second nodes of the second group of nodes, different second start positions within the second storage segment to search for second unclaimed data movement tasks in the second storage segment for processing, resulting in the respective second nodes of the second group of nodes processing the second data movement tasks of the second storage segment according to the different second start positions within the second storage segment.

A non-transitory machine-readable medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising:

• distributing data movement tasks among multiple nodes of a data storage cluster, wherein the multiple nodes share a data store that identifies the data movement tasks, and wherein distributing the data movement tasks comprises:
• splitting the data store into multiple storage segments, wherein the multiple storage segments comprise at least a first storage segment and a second storage segment;
• assigning, to a first group of nodes of the multiple nodes, a first affinity to the first storage segment, resulting in an affinity of the first group of nodes to select data movement tasks of the first storage segment for processing over data movement tasks that are not part of the first storage segment;
• assigning, to a second group of nodes of the multiple nodes, a second affinity to the second storage segment, resulting in an affinity of the second group of nodes to select data movement tasks of the second storage segment for processing over data movement tasks that are not part of the second storage segment;
• assigning, to respective nodes of the first group of nodes, different start positions within the first storage segment to search for unclaimed data movement tasks in the first storage segment for processing, resulting in the respective nodes of the first group of nodes processing different data movement tasks of the first storage segment according to the different start positions within the first storage segment;
• and
• assigning, to respective nodes of the second group of nodes, different start positions within the second storage segment to search for unclaimed data movement tasks in the second storage segment for processing, resulting in the respective nodes of the second group of nodes processing different data movement tasks of the second storage segment according to the different start positions within the second storage segment.