An Infrastructure for Grid Job Monitoring

摘要

As a part of an ongoing project titled MASSIVE, we have designed and implemented the MASSIVE Monitoring System (MMS) to monitor grid jobs. MMS is able to work on multiple sites and support multiple users. In addition to grid jobs, MMS is capable of monitoring and steering file operations. The Job Register Code (JRC) is adopted to map a job to its processes, and used to decide whether a user can access the monitoring information or steer the jobs. MMS supports top-down start-up of the monitoring components, which can ensure the components at their places.