OperatingPlan - ACES Planning Wiki

1. Ongoing operational plan for ACES

Day to day operational support is provided by TechSquare as follows.
1. The ACES project currently contracts for up to 12 hours per week of operational support from Techsquare. Operational support covers items such as
  1. Monitoring system for hardware failures.
  2. Taking lead on resolving hardware failures and providing information on any hardware replacements that are needed.
  3. Providing support for correct operation of system software, queue systems, file-systems, OS.
  4. Carrying out backups according to a determined policy and restoring items from backup as needed.
  5. Maintaining e-mail list(s) for systems and user support.
  6. Adding new user accounts and providing first-line response to general user queries.
  7. Installation and/or install-level customization of application support software stack e.g. MPI, GM libraries, graphics packages.
A systems support oversight team works with Techsquare to help prioritize and schedule work. This team includes members with application expertise in the ACES application auite. This team is responsible for setting policies and practices for the ACES system. The team also provides "pro-bono" user oriented support, that includes:
1. Developing and maintaining test codes and checklists that can be used by end-users and/or Techsquare to demonstrate and verify system behavior.
2. Working with individual users to help distinguish between user application problems and system problems.
3. Following up with users to determine necessary system changes to meet application needs.
4. Maintaining the ACESwiki and https://acesgrid.org web sites.
5. Leading a weekly user open session for meeting with ACES users.