Controlled Transactional Consistency for Web Caching

In-memory read-only caches are widely used in cloud in-frastructure to reduce access latency and to reduce load on backend databases. Operators view coherent caches as impractical at genuinely large scale and many client-facing caches are updated in an asynchronous manner with best-effort pipelines. Existing incoherent cache technologies do not support transactional data access, even if the backend database supports transactions. We propose T-Cache, a cache that supports read-only transactions despite asynchronous and unreliable communication with the database. We also define cache-serializability, a variant of serializabil-ity that is suitable for incoherent caches, and prove that with unbounded resources T-Cache implements it. With limited resources, T-Cache allows the system manager to choose a trade-off between performance and consistency. Our evaluation shows that T-Cache detects many in-consistencies with only nominal overhead. We use syn-thetic workloads to demonstrate the efficacy of T-Cache when data accesses are clustered and its adaptive reac-tion to workload changes. With workloads based on the real-world topologies, T-Cache detects 43 − 70 % of the inconsistencies and increases the rate of consistent trans-actions by 33−58%.