Toward Fast Query Serving in Key-Value Store Migration with Approximate Telemetry

Distributed key-value stores scale data analytical processing by spreading data across nodes. Frequent migration of key-value shards between online nodes is a key technique to react to dynamic workload changes for load balancing and service elasticity. During migration, the data is split between a source and a destination, making it difficult to query the exact location. Existing solutions aiming to provide real-time read and write query capabilities during migration may require querying both source and destination servers, doubling the compute/network resources. In this paper, we explore a simple yet effective measurement approach to track the key-value migration status, in order to improve the query-serving performance under migration. In our preliminary prototype, we use a Bloom filter on the destination server to keep track of individual key-value pairs that have been successfully migrated. For key-value pairs that have yet migrated, the information stored in the Bloom filter enables fast forwarding to the source server without the need to check the database. We prototype this design on a local cluster with Redis deployments. Our preliminary results show that this approximate measurement-based design minimizes query losses during migration.