Capacity based load balancing in distributed storage systems with deduplication and compression functionalities

A non-transitory computer readable storage medium comprising instructions that are executable in a computer system to cause the computer system to perform a method for migrating a first group of data blocks stored in a first node to a second node, comprising:

• determining, for each of a plurality of groups of data blocks stored in the first node, a corresponding first metric representing a total size for storing all data blocks in the corresponding group without deduplication, wherein each data block of the plurality of groups of data blocks is associated with a corresponding physical address;
• determining, for each of the plurality of groups of data blocks stored in the first node, a corresponding second metric representing a total size for storing all unique data blocks in the corresponding group, wherein a given data block is a unique data block if no other data block of the plurality of groups of data blocks is associated with the same physical address as the given data block;
• selecting the first group of data blocks for migration from the first node to the second node based on the corresponding first metric satisfying a first criteria and the corresponding second metric satisfying a second criteria;
• and
• migrating the first group of data blocks to the second node.

A computer system comprising:

• local storage of a first node that stores a plurality of groups of data blocks;
• and
• a processor configured to:
• determine, for each of the plurality of groups of data blocks stored in the first node, a corresponding first metric representing a total size for storing all data blocks in the corresponding group without deduplication, wherein each data block of the plurality of groups of data blocks is associated with a corresponding physical address;
• determine, for each of the plurality of groups of data blocks stored in the first node, a corresponding second metric representing a total size for storing all unique data blocks in the corresponding group, wherein a given data block is a unique data block if no other data block of the plurality of groups of data blocks is associated with the same physical address as the given data block;
• select the first group of data blocks for migration from the first node to the second node based on the corresponding first metric satisfying a first criteria and the corresponding second metric satisfying a second criteria;
• and
• migrate the first group of data blocks to the second node.