-e-Commerce services have become a promising and profitable application of the Internet. In order to keep them growing, solutions must be found to deal with unreliable connections and high latencies, among other problems. The best solutions to such problems tend to depend on the distribution of the service over the network, placing servers in multiple locations, closer to customers. If placement of servers is effective it tends to reduce delays and traffic-related costs. In this paper we discuss the distribution of e-commerce services by introducing a traffic-aware cost model and evaluating it using an actual log from an e-tailer. The results show that the model yields good placement solutions, which perform better than simpler ad-hoc solutions.I INTRODUCTION e-Commerce services have become a promising and profitable application of the Internet. Nevertheless, the use of the Internet as the communication environment in this case is not without its problems. For an e-commerce site to be successful it has to reduce the negative effects of unreliable connections and high network latencies, among other problems. Such problems may compromise customer satisfaction and therefore the success of the virtual business.Techniques based on improving the quality of a centralized server do not provide a reliable solution, since the difficulties faced are inherent to the network infrastructure itself, not just the server. A better solution tends to be the distribution of the service over the network, placing servers in multiple locations closer to the final users. The existence of multiple servers tends to increase availability, and assuming the placement is well planned, it tends to reduce delays. Proxy cache servers [8] are an example of a successful service distribution strategy: they replicate static content such as HTML pages and images, and are responsible for significant traffic reduction. Content distribution networks [3] have deserved special attention lately, since they provide a more reliable and controlled solution than proxy caches, but at a cost for the information providers. On the other hand, there are several applications that generate dynamic and non-cacheable responses (at least when using traditional cache technologies).For a distributed e-commerce solution to be successful, there are several issues that must be addressed, such as resource placement and discovery, and load balancing. Resource placement policies define the number and location of servers and products. A larger number of servers allows a higher degree of parallelism, but also leads to higher complexity and context maintenance costs. Regarding product allocation in servers, it would be simpler to divide them uniformly, but a strategy that takes regional demands into account should be more cost-effective. Resource discovery is defined by strategies that determine how clients decide which server to contact. These strategies may be based on network topology or geographical affinity, and may be implemented through dynamic DNS replies, for ex...