Hewlett Packard Enterprise Development LP

Matthew S Gates

Alex Veprinsky

Susan Agten

Joel E Lilienkamp

Christopher Robert Nichols

Xiali He

Monica Jane Kinney

Tessa DeMuth

William Michael McCormack

Robert Michael Lester

Systems and methods are provided for lock-free thread scheduling. Threads may be placed in a ring buffer shared by all computer processing units (CPUs), e.g., in a node. A thread assigned to a CPU may be placed in the CPU's local run queue. However, when a CPU's local run queue is cleared, that CPU checks the shared ring buffer to determine if any threads are waiting to run on that CPU, and if so, the CPU pulls a batch of threads related to that ready-to-run thread to execute. If not, an idle CPU randomly selects another CPU to steak threads from, and the idle CPU attempts to dequeue a thread batch associated with the CPU from the shared ring buffer. Polling may be handled through the use of a shared poller array to dynamically distribute polling across multiple CPUs.

Lock-free work-stealing thread scheduler

A process includes determining a first degree of throttling to apply to a polling of hardware devices by a hardware processor based on a historical total utilization of the hardware processor; and determining a second degree of throttling to apply to the polling of hardware devices by the hardware processor based on a historical polling utilization of the hardware processor. The hardware processor includes, responsive to an upcoming hardware device polling cycle for the hardware processor and based on the first degree of throttling and the second degree of throttling, regulating whether the hardware processor bypasses the hardware device polling cycle or executes the hardware device polling cycle.

Regulation of throttling of polling based on processor utilizations

In some examples, a system maintains, for a base storage structure and a collection of snapshots associated with the base storage structure, statistics relating to usage of storage space based on data of the base storage structure and the collection of snapshots. The system checks metadata of a first snapshot to determine validity of references in the metadata and a presence of any child of the first snapshot or a grandparent of the first snapshot. The system associates, based on the validity of the references in the metadata and the presence of any child or grandparent of the first snapshot, a hint with a metadata entry of a parent of the first snapshot to indicate that a metadata entry of the child or the grandparent is to be checked. The system updates, using the hint, the statistics relating to usage of storage space.

Storage space determinations for snapshots

Example implementations relate to storing data in a storage system. An example includes receiving, by a storage controller of a storage system, a data unit to be stored in persistent storage of the storage system. The storage controller determines maximum and minimum entropy values for the received data unit. The storage controller determines, based on at least the minimum entropy value and the maximum entropy value, whether the received data unit is viable for data reduction. In response to a determination that the received data unit is viable for data reduction, The storage controller performs at least one reduction operation on the received data unit.

Data reduction in a storage system

In some examples, a system dynamically adjusts a prefetching load with respect to a prefetch cache based on a measure of past utilizations of the prefetch cache, wherein the prefetching load is to prefetch data from storage into the prefetch cache.

Dynamic prefetching of data from storage

Systems and methods are provided for lock-free thread scheduling. Threads may be placed in a ring buffer shared by all computer processing units (CPUs), e.g., in a node. A thread assigned to a CPU may be placed in the CPU's local run queue. However, when a CPU's local run queue is cleared, that CPU checks the shared ring buffer to determine if any threads are waiting to run on that CPU, and if so, the CPU pulls a batch of threads related to that ready-to-run thread to execute. If not, an idle CPU randomly selects another CPU to steal threads from, and the idle CPU attempts to dequeue a thread batch associated with the CPU from the shared ring buffer. Polling may be handled through the use of a shared poller array to dynamically distribute polling across multiple CPUs.

A process includes, responsive to a first epoch of a sequence of epochs, a plurality of processors accessing first entries of a first buffer that is shared among the plurality of processors. The first entries identify a first subset of hardware devices to be polled of a plurality of hardware devices. Responsive to the accessing, the plurality of processors poll the first subset of hardware devices. Responsive to the first epoch, the process includes, responsive to results of the polling, the plurality of processors updating delay orders that are associated with the first subset of hardware devices; and the plurality of processors adding second entries identifying the first subset of hardware devices to a plurality of second buffers based on the delay orders, where each second buffer of the plurality of second buffers corresponds to a different delay order of the delay orders. The process includes, responsive to a condition that represents an end of the first epoch, preparing the first buffer for a second epoch of the sequence of epochs. The preparation includes, responsive to a position of the second epoch in the sequence of epochs, selecting a second subset of hardware devices of the plurality of hardware devices for the second epoch. The selection includes selecting, from the plurality of second buffers, third entries that identify the second subset of hardware devices and adding the third entries to the first buffer.

Growing community of inventors

Houston, TX, United States of America

Matthew S Gates