Database servers typically offer a best-effort model of service to submitted commands, that is, they try to process every command as fast as possible. Hence, they are not prepared to provide differentiation for quality of service. In this paper we consider the distributed Grid-DWPA architecture context, which fragments and replicates data into several sites to provide an efficient grid data warehouse solution. Instead of offering best-effort service to every query, we propose the use of a performance predict model that is used in conjunction with QoS oriented scheduling to enable the establishment of Service Level Agreements (SLA).