The dramatic increase of data stored, processed and reused in all sectors leads to the evolution of modern storage systems known as NoSQL databases such as Amazon Dynamo,Cassandra, Big-Table, PNUTS, HBase. In order to boost the availability and performance of the system, these storage systems follow eventual consistency and don't o er tight consistency by default. Paxos is commonly used in this context to ensure tight consistency on demand. But it adds extra costs on messages management, mostly complexity and size. In addition, Paxos shrinks the space for other research areas such as cache memory optimization and loadbalancing. This paper gives an opportunity to propose and discuss the challenges of a new consistency protocol for modern storage systems entitled 'LibRe'. LibRe follows the Eventual Consistency model. In addition, it logs operations executed on each node in the distributed system. This additional information is used by the load balancer and ensures that requests are not forwarded to a node where the data needed to serve the request are stale. Since Eventual Consistency already o ers better Availability and Partition tolerance, the aspiration of associating LibRe with eventual consistency is to work out a better consistency management service providing also availability and partition tolerance. The simulation results for consistency and latency in LibRe are compared among traditional Pessimistic Consistency, Eventual Consistency, and Paxos. The overall results are discussed and new opportunities for research works are provided.