Abstract: A task list can list tasks to be performed on a target host machine. Certain tasks in the task list can be revised to produce a revised task list. Tasks directed to storage devices can be revised depending on whether or not the storage devices are shared by both the target host machine and a reference host machine.

Abstract: The current document is directed to a storage stack subsystem of a computer system that transfers data between memory and various data-storage devices and subsystems and that processes I/O requests. In one implementation, the disclosed storage stack includes a latency monitor, an I/O-scheduling bypass pathway, and short-circuit switch, controlled by the latency monitor. While the latency associated with I/O-request execution remains below a threshold latency, I/O-scheduling components of the storage stack are bypassed, with I/O requests routed directly to multiple input queues associated with one or more high-throughput multi-queue I/O device controllers. When the latency for execution of I/O requests rises above the threshold latency, I/O requests are instead directed to I/O-scheduling components of the storage stack, which attempt to optimally reorganize the incoming I/O-request stream and optimally distribute I/O-requests among multiple input queues associated I/O device controllers.

Abstract: A task list can list tasks to be performed on a target host machine. Certain tasks in the task list can be revised to produce a revised task list. Tasks directed to storage devices can be revised depending on whether or not the storage devices are shared by both the target host machine and a reference host machine.

Abstract: The current document is directed to a storage stack subsystem of a computer system that transfers data between memory and various data-storage devices and subsystems and that processes I/O requests at a greater rate than conventional storage stacks. In one implementation, the disclosed storage stack includes a latency monitor, an I/O-scheduling bypass pathway, and short-circuit switch, controlled by the latency monitor. While the latency associated with I/O-request execution remains below a threshold latency, I/O-scheduling components of the storage stack are bypassed, with I/O requests routed directly to multiple input queues associated with one or more high-throughput multi-queue I/O device controllers.

Abstract: A per device state is introduced that indicates whether a storage device is shared clusterwide or not. The state may be populated by default based on detected device locality. Devices detected as local and those shared by only a subset of host machines in a cluster of machines may have the state set to “FALSE.” Devices which are shared by all the machines in a cluster may have the state set to “TRUE.” Locality of storage devices in a cluster may be modified using such state information. Operations upon other storage device state may be modified depending upon device sharing state.

Abstract: A per device state is introduced that indicates whether a storage device is shared clusterwide or not. The state may be populated by default based on detected device locality. Devices detected as local and those shared by only a subset of host machines in a cluster of machines may have the state set to “FALSE.” Devices which are shared by all the machines in a cluster may have the state set to “TRUE.” Locality of storage devices in a cluster may be modified using such state information. Operations upon other storage device state may be modified depending upon device sharing state.