Abstract:
Embodiments for managing unequal workloads between Network Shared Disks (NSD) in a networked computing environment by a processor. Additional space may be carved out from at least one of a plurality of NSDs in a cluster file system, upon detecting an unbalanced load between the plurality of NSDs, while maintaining a predetermined level of usage according to a performance profile of the plurality of NSDs.
Abstract:
According to one embodiment, a computer-implemented method includes obtaining, during a measurement period, a set of utilization metrics for a system; determining, whether the average number of outstanding system requests of the system lies between a current and an actual value of the maximum concurrency; in response to determining that the average number of outstanding system requests of the system does not lie between the current and actual values of the maximum concurrency, not adjusting the maximum concurrency value; in response to determining that the average number of outstanding system requests of the system does lie between the current and actual values of the maximum concurrency, assigning a value of the maximum concurrency to be the value of the average number of outstanding system requests; accessing a utilization function; solving the utilization function; and managing performance problems of the system indicated by solving the utilization function.
Abstract:
A computer-implemented mechanism is provided that monitors usage of one or more computing resources within a set of computing components relative to a received workload. The mechanism calculates a maximum workload for the set of computing components from the monitored use of the computing resources within the set of computing components and determines an available overhead between the calculated maximum workload for the set of computing components and a current workload being performed by the set of computing components. The mechanism selects one or more maintenance tasks for the set of computing components, the total workload of the selected maintenance tasks being less than the determined available overhead.
Abstract:
In one embodiment, a system includes a robotic accessor for transporting media between multiple storage slots and one or more data storage drives; a controller for controlling the robotic accessor; a memory in communication with and/or integrated with the controller for storing information about the media and the storage slots, the information including data corresponding to a physical distribution of the media in the storage slots; and logic integrated with and/or executable by the controller, the logic being adapted to: position the robotic accessor at a computed optimal position during an idle period of the robotic accessor, the computed optimal position being based at least in part on the physical distribution of the media in the storage slots.
Abstract:
According to one embodiment, a computer-implemented method includes obtaining, during a measurement period, a set of utilization metrics for a system; determining, whether the average number of outstanding system requests of the system lies between a current and an actual value of the maximum concurrency; in response to determining that the average number of outstanding system requests of the system does not lie between the current and actual values of the maximum concurrency, not adjusting the maximum concurrency value; in response to determining that the average number of outstanding system requests of the system does lie between the current and actual values of the maximum concurrency, assigning a value of the maximum concurrency to be the value of the average number of outstanding system requests; accessing a utilization function; solving the utilization function; and managing performance problems of the system indicated by solving the utilization function.
Abstract:
A computer-implemented method according to one embodiment includes identifying aggregated customer performance data for a system resource, creating a first system map for the system resource, utilizing the aggregated customer performance data, comparing the first system map to a second system map created for the system resource utilizing calibration data, and adjusting the second system map, based on the comparing.
Abstract:
In one embodiment, a system includes a controller for controlling a robotic accessor, and a memory in communication with and/or integrated with the controller for storing information about media and storage slots. The information includes data corresponding to a physical distribution of the media in the storage slots. Logic integrated with and/or executable by the controller is configured to position the robotic accessor at a computed optimal position during an idle period of the robotic accessor, the computed optimal position being based at least in part on at least one of: (a) the data corresponding to the physical distribution of the media in the storage slots, and (b) a center of access calculated using the data corresponding to the physical distribution of the media in the storage slots.
Abstract:
A mechanism is provided in a cache subsystem for cache prefetching based on non-sequential access. The mechanism determines frequently accessed non-sequential cache records in the cache subsystem. The mechanism collects trailing record statistics for the frequently accessed non-sequential cache records. The mechanism determines a caching strategy. The caching strategy comprises prefetching a set of trailing records responsive to a read of a given frequently accessed non-sequential cache record. The mechanism applies the caching strategy to the cache subsystem.
Abstract:
A computer-implemented method according to one embodiment includes identifying aggregated customer performance data for a system resource, creating a first system map for the system resource, utilizing the aggregated customer performance data, comparing the first system map to a second system map created for the system resource utilizing calibration data, and adjusting the second system map, based on the comparing.
Abstract:
A computer-implemented method according to one embodiment includes identifying aggregated customer performance data for a system resource, creating a first system map for the system resource, utilizing the aggregated customer performance data, comparing the first system map to a second system map created for the system resource utilizing calibration data, and adjusting the second system map, based on the comparing.