Abstract: Techniques are provided for using near-full bloom filters for efficiently identifying hash slices in which the deviation between replicas is sufficient to justify remedial measures. Techniques are also described for adjusting the size of slices and the size of the bloom filters, so that the bloom-filter-to-bloom-filter comparison serves as an accurate indicator of the degree to which the contents of the slices of a slice pair have deviated. Slice size may vary from slice pair to slice pair, so that relatively sparsely populated portions of the ring (access key ranges into which fewer chunks fall) are represented by relatively larger slices, while relatively densely populated portions of the ring (access key ranges into which more chunks fall) are represented by relatively smaller slices.

Abstract: A content addressable storage (CAS) system is provided in which each storage unit is assigned to one of a plurality of sibling groups. Each sibling group is assigned the entire hash space. Within each sibling group, the hash space is partitioned into hash segments which are assigned to the individual storage units that belong to the sibling group. Chunk retrieval requests are submitted to all sibling groups. Chunk storage requests are submitted to a single sibling group. The sibling group to which a storage request is submitted depends on whether any sibling group already stores the chunk, and which sibling groups are considered full.