Abstract: Embodiments presented herein techniques for balancing a multidimensional set of resources of different types within a distributed resources system. Each host computer providing the resources publishes a status on current resource usage by guest clients. Upon identifying a local imbalance, the host computer determines a source workload to migrate to or from the resources container to minimize the variance in resource usage. Additionally, when placing a new resource workload, the host computer selects a resources container that minimizes the variance to further balance resource usage.

Abstract: Example methods are provided for unbalanced storage resource usage configuration for a distributed storage system in a virtualized computing environment. An example method may include obtaining usage data associated with multiple storage resources forming the distributed storage system. The multiple storage resources are supported by the multiple hosts. Based on the usage data, the method may further include determining a higher usage set and a lower usage set of one or more storage resources from the multiple storage resources and configuring the multiple hosts to use the multiple storage resources in an unbalanced manner by using the higher usage set of one or more storage resources at a higher usage level compared to the lower usage set of one or more storage resources.

Abstract: Techniques for implementing access pattern-based distribution of key-value content in a distributed key-value store comprising a plurality of nodes are provided. In one set of embodiments, a node in the plurality of nodes can receive a request to create a key-value entry. The node can further determine whether the key-value entry is associated with a first (e.g., global) scope or a second (e.g., local) scope. If the key-value entry is associated with the first scope, the node can cause the key-value entry to be replicated on every node in the plurality of nodes. On the other hand, if the key-value entry is associated with the second scope, the node cause the key-value entry to be stored solely on that node.

Abstract: The disclosure herein describes reconfiguring a data object in a data store using batch portions of components of the data object. Instructions to reconfigure the data object to a target object layout are received, the data object including a concatenation layer that references a plurality of components. The components are grouped into batch portions and the batch portions are reconfigured in a series based on the received instructions. The reconfiguring for each batch portion includes allocating free storage space according to the target object layout as target components, copying the data stored in the batch portion to the target components, redirecting references in the concatenation layer from the components of the batch portion to the target components, and releasing storage space occupied by the components of the batch portion. As a result, storage space used as transient capacity during the reconfiguring is reduced to a size of the batch portions.

Abstract: Techniques for predicting the outcome of a storage management operation on a hyper-converged infrastructure (HCI) deployment are provided. In one set of embodiments, a computer system can retrieve a current storage resource state of the HCI deployment. The computer system can then execute a simulation of the storage management operation in view of the current storage resource state, where the executing includes performing one or more simulated data movements between one or more host systems in the HCI deployment. Upon completing the simulation, the computer system can generate a report including, among other things, a predicted result status of the storage management operation based on the simulation.

Abstract: The disclosure herein describes reconfiguring a data object in a data store using batch portions of components of the data object. Instructions to reconfigure the data object to a target object layout are received, the data object including a concatenation layer that references a plurality of components. The components are grouped into batch portions and the batch portions are reconfigured in a series based on the received instructions. The reconfiguring for each batch portion includes allocating free storage space according to the target object layout as target components, copying the data stored in the batch portion to the target components, redirecting references in the concatenation layer from the components of the batch portion to the target components, and releasing storage space occupied by the components of the batch portion. As a result, storage space used as transient capacity during the reconfiguring is reduced to a size of the batch portions.

Abstract: Example methods are provided for unbalanced storage resource usage configuration for a distributed storage system in a virtualized computing environment. The method may comprise: obtaining usage data associated with multiple storage resources forming the distributed storage system; and based on the usage data, determining a higher usage set and a lower usage set from the multiple storage resources. The method also comprise configuring the multiple hosts to use the multiple storage resources in an unbalanced manner by using the higher usage set at a higher usage level compared to the lower usage set.

Abstract: The disclosure herein describes throttling resynchronization operations in a cluster of distributed data stores based on I/O bandwidth limits. Resynchronization operations are added to a queue as they are received. A cluster resource manager accesses a resynchronization operation in the queue. A transient capacity value is determined and an available capacity value is obtained. A resynchronization limit of the cluster is identified, wherein the resynchronization limit indicates a maximum percentage of I/O bandwidth of the cluster that is for use by resynchronization operations. Based on a sum of the resynchronization capacity value and the transient capacity value being less than or equal to a product of the resynchronization limit and the available capacity value, the cluster resource manager initiates the accessed resynchronization operation on the cluster, whereby free space is maintained in the cluster for use by user operations.

Abstract: Techniques are described for storing a virtual disk in an object store comprising a plurality of physical storage devices housed in a plurality of host computers. A profile is received for creation of the virtual disk wherein the profile specifies storage properties desired for an intended use of the virtual disk. A virtual disk blueprint is generated based on the profile such that that the virtual disk blueprint describes a storage organization for the virtual disk that addresses redundancy or performance requirements corresponding to the profile. A set of the physical storage devices that can store components of the virtual disk in a manner that satisfies the storage organization is then determined.

Abstract: The disclosure herein describes throttling resynchronization operations in a cluster of distributed data stores based on I/O bandwidth limits. Resynchronization operations are added to a queue as they are received. A cluster resource manager accesses a resynchronization operation in the queue. A transient capacity value is determined and an available capacity value is obtained. A resynchronization limit of the cluster is identified, wherein the resynchronization limit indicates a maximum percentage of I/O bandwidth of the cluster that is for use by resynchronization operations. Based on a sum of the resynchronization capacity value and the transient capacity value being less than or equal to a product of the resynchronization limit and the available capacity value, the cluster resource manager initiates the accessed resynchronization operation on the cluster, whereby free space is maintained in the cluster for use by user operations.

Abstract: Techniques for implementing access pattern-based distribution of key-value content in a distributed key-value store comprising a plurality of nodes are provided. In one set of embodiments, a node in the plurality of nodes can receive a request to create a key-value entry. The node can further determine whether the key-value entry is associated with a first (e.g., global) scope or a second (e.g., local) scope. If the key-value entry is associated with the first scope, the node can cause the key-value entry to be replicated on every node in the plurality of nodes. On the other hand, if the key-value entry is associated with the second scope, the node cause the key-value entry to be stored solely on that node.

Abstract: Techniques are described for storing a virtual disk in an object store comprising a plurality of physical storage devices housed in a plurality of host computers. A profile is received for creation of the virtual disk wherein the profile specifies storage properties desired for an intended use of the virtual disk. A virtual disk blueprint is generated based on the profile such that that the virtual disk blueprint describes a storage organization for the virtual disk that addresses redundancy or performance requirements corresponding to the profile. A set of the physical storage devices that can store components of the virtual disk in a manner that satisfies the storage organization is then determined.

Abstract: The embodiments described herein relate to synchronization of data in a shared pool of configurable computer resources. One or more consistency points are created in a source filesystem. A first consistency point is compared with a second consistency point to detect a directory change at the source filesystem, which includes identifying at least one difference between the first and second consistency points. A file level change associated with an established directory at a target filesystem is identified responsive to the detection of the directory change. A link is established between the source filesystem and the target filesystem, and the established directory is updated based on the file level change.

Abstract: In a storage cluster having nodes, blocks of a logical storage space of a storage object are allocated flexibly by a parent node to component nodes that are backed by physical storage. The method includes maintaining a first allocation map for the parent node, and second and third allocation maps for the first and second component nodes, respectively, executing a first write operation on the first component node and updating the second allocation map to indicate that the first block is a written block, and upon detecting that the first component node is offline, executing a second write operation that targets a second block of the logical storage space, which is allocated to the first component node, on the second component node and updating the third allocation map to indicate that the second block is a written block.

Abstract: Example methods are provided for unbalanced storage resource usage configuration for a distributed storage system in a virtualized computing environment. The method may comprise: obtaining usage data associated with multiple storage resources forming the distributed storage system; and based on the usage data, determining a higher usage set and a lower usage set from the multiple storage resources. The method also comprise configuring the multiple hosts to use the multiple storage resources in an unbalanced manner by using the higher usage set at a higher usage level compared to the lower usage set.

Abstract: In a storage cluster having nodes, blocks of a logical storage space of a storage object are allocated flexibly by a parent node to component nodes that are backed by physical storage. The method includes maintaining a first allocation map for the parent node, and second and third allocation maps for the first and second component nodes, respectively, executing a first write operation on the first component node and updating the second allocation map to indicate that the first block is a written block, selecting the second component node for executing a second write operation, and executing the second write operation on the second component node. Upon execution of the second write operation, the third allocation map is updated to indicate that the second block is a written block and the first allocation map is updated to indicate that the second block is allocated to the second component node.

Abstract: In a storage cluster having nodes, blocks of a logical storage space of a storage object are allocated flexibly by a parent node to component nodes that are backed by physical storage. The method includes maintaining a first allocation map for the parent node, and second and third allocation maps for the first and second component nodes, respectively, executing a first write operation on the first component node and updating the second allocation map to indicate that the first block is a written block, selecting the second component node for executing a second write operation, and executing the second write operation on the second component node. Upon execution of the second write operation, the third allocation map is updated to indicate that the second block is a written block and the first allocation map is updated to indicate that the second block is allocated to the second component node.

Abstract: In a storage cluster having nodes, blocks of a logical storage space of a storage object are allocated flexibly by a parent node to component nodes that are backed by physical storage. The method includes maintaining a first allocation map for the parent node, and second and third allocation maps for the first and second component nodes, respectively, executing a first write operation on the first component node and updating the second allocation map to indicate that the first block is a written block, and upon detecting that the first component node is offline, executing a second write operation that targets a second block of the logical storage space, which is allocated to the first component node, on the second component node and updating the third allocation map to indicate that the second block is a written block.

Abstract: The embodiments described herein relate to synchronization of data in a shared pool of configurable computer resources. One or more consistency points are created in a source filesystem. A first consistency point is compared with a second consistency point to detect a directory change at the source filesystem, which includes identifying at least one difference between the first and second consistency points. A file level change associated with an established directory at a target filesystem is identified responsive to the detection of the directory change. A link is established between the source filesystem and the target filesystem, and the established directory is updated based on the file level change.

Abstract: Embodiments of the invention relate to synchronization of data in a shared pool of configurable computer resources. An image of the filesystem changes, including data and metadata, is captured in the form of a consistency point. Sequential consistency points are created, with changes to data and metadata in the filesystem between sequential consistency captured and placed in a queue for communication to a target filesystem at a target site. The changes are communicated as a filesystem operation, with the communication limited to the changes captured and reflected in the consistency point.