Many applications at Google are structured with data stored in a transactional database (source of truth) and same data being required by servers distributed worldwide. For efficient and fast computation servers store this data in memory. Further, the database is changing continuously and we need to update the in-memory view of these large number of servers in real-time. For example, in Google Search Ads application we have Advertisers configuration stored in a database and this data is loaded in the memory of various servers to compute Ads in a scalable and fast way. In this talk, we describe our solution to this data distribution problem and the challenges that we encountered in providing a highly reliable and low latency service.

Data in traditional "caching'' data systems resides on secondary storage, and is read into main memory only when operated on. This limits system performance. Main memory data stores with data always in main memory are much faster. But this performance comes at a cost. In this paper, we analyze the costs of both in-memory operations and secondary storage operations where data is not "in cache''. We study the performance impact of cache misses on caching system performance. The analysis considers both execution and storage costs. Based on our analysis, we derive cost/performance results for a data caching system and a main memory system to understand where each demonstrates the best cost per operation, what is driving the cost differences, and the scale of the differences. This analysis (1) provides insight into why data caching systems continue to dominate the market; (2) points to higher performance that does not rely on simply increasing main memory cache size; and (3) suggests a path to lower costs and hence better cost/performance.