The ANL/IBM SP scheduling system

Approximately five years ago scientists discovered that modern UNLX workstations connected with ethernet and fiber networks could provide enough computational performance to compete with the supercomputers. As this concept became increasingly popular, the need for distributed queuing and scheduler systems became apparent. Systems such as DQS from Florida State University were developed and worked very well. Today however, supercomputers such as Argonne National Laboratory`s IBM SP system can provide more CPU and networking speed than can be obtained from these networks of workstations. Nevertheless, because modern super computers look like clusters of workstations developers felt that the scheduling systems previously used on clusters of workstations should still apply. After trying to apply some of these scheduling systems to Argonne`s SP environment it became obvious that these two computer environments have very different scheduling needs. Recognizing this need, and realizing that no one has addressed it, we at Argonne developed a new scheduling system. The approach taken in creating this system was unique in that user input and interaction were encouraged throughout the development process. Thus a scheduler was built that actually works the way the users want it to