Leading e-commerce providers have built large and complicated systems to provide countrywide or even worldwide services. However, there have been few substantive studies on e-commerce systems in real world. In this paper, we investigate the systems of Tmall and JD, the top-two most popular e-commerce websites in China, with a measurement approach. By analyzing traffics from campus network, we present a characterization study that covers several features, including usage patterns and shopping behaviors, of the e-commerce workload; in particular, we characterize the massive flash crowd in the Double-11 Day, which is the biggest online shopping festival in the world. We also reveal Tmall and JD's e-commerce infrastructures, including content delivery networks ( CDNs ) and clouds , and evaluate their performances under the flash crowd. We find that Tmall's CDN proactively throttles bandwidths for ensuring low but guaranteed throughputs, while JD still follows the best-effort way, leading to poor and unstable performances; both providers do not have sufficient capacities in their private clouds, resulting in extraordinarily long transaction latencies. Based on the insights obtained from measurement, we discuss the design choices of e-commerce CDNs, and investigate the potential benefits brought by incorporating client-side assistances in offloading massive flash crowd of e-commerce workloads.