Robustness in the Salus scalable block store
Proceedings of the USENIX Symposium on Networked Systems Design and Implementation (NSDI) 2013.
View
PDF or BibTeX.
areas
Distributed Systems
abstract
This paper describes Salus, a block store that seeks to
maximize simultaneously both scalability and robustness. Salus provides
strong end-to-end correctness guarantees for read operations, strict
ordering guarantees for write operations, and strong durability and
availability guarantees despite a wide range of server failures
(including memory corruptions, disk corruptions, firmware bugs, etc.).
Such increased protection does not come at the cost of scalability or
performance: indeed, Salus often actually outperforms HBase (the
codebase from which Salus descends). For example, Salus' active
replication allows it to halve network bandwidth while increasing
aggregate write throughput by a factor of 1.74 compared to HBase in a
well-provisioned system.