Data center storage systems increasingly adopt erasure coding to reduce the storage overhead of traditional 3-way replication. However, maintaining high performance in erasure-coded data center storage systems remains challenging. In this talk, I will present new results on how to seamlessly adapt erasure codes into data-center architectures. In particular, I will present repair pipelining, a general technique that speeds up the repair performance in erasure-coded storage, such that it can reduce the repair time to approximately the same as the normal read time by slicing the repair operation via a linear chain. This creates opportunities for applying erasure coding to frequently accessed data for high storage efficiency, while preserving read performance.