Distributed device status in a clustered system environment

Abstract

Problem ownership and status propagation in a clustered system environment must be coordinated in a way that avoids redundant and/or conflicting recovery efforts. IOP managers which overcome these problems are disclosed. A primary IOP manager is one which has problem ownership for a particular IOP. There is only one primary IOP manager for each IOP. A secondary IOP manager is one which resides upon a computer system that shares the resources of a particular IOP or IOPs, but nevertheless does not have problem ownership for that particular IOP(s). There are one or more secondary IOP managers for a given IOP. When a primary IOP manager is informed of a problem in a device attached to a shared IOP, it updates resident system management information to indicate the new status of the subject device, informs its local system management of the problem so that corrective actions may be taken, and sends the status information to the secondary IOP managers via the IOP itself. When a secondary IOP manager is informed of a problem with a device attached to a shared IOP, it updates system management information to indicate the new status of the subject device and sends the status information to the primary IOP manager and other secondary IOP managers via the IOP itself. The secondary IOP manager does not, however, inform its local system management that corrective actions are required.