If you have only two locations, you probably don't need to convert the full session ID into an integer, but just a small part or it. I recently had to build a kind of hashing function for splitting my processing of a very large data chunk into 10 sub-processes. One of the mandatory IDs of my data was a telephone number. I simply used the last digit of the phone number to decide to which process to allocate a given record and obtained an excellent load balancing. The advantage is that the simpler the splitting function is, the less performance overhead you get.
Alternately, you could use the IP address of the user (assuming it is available). There's several ways in which you could use the IP address for this, the easiest of which may be to take the modulo of any combination/all/one of the octets.
You could even then ensure you get some sort of consistency in approach for users on the same network by determining the network class, and then taking the modulo of the network portion of the IP address only. Hence users on the same network (even those with DHCP addreses) would always go to the same destination.
You'll never get a perfect 50/50 spread with this approach, but you'll get a fair spread.