Vmware, Inc.

Western Digital Technologies, Inc.

Virident Systems, Inc.

Vibhor Arunkumar Patale

Rupesh Bajaj

Edward Joseph Goggin

Hariharan Subramanian

Tomy Ammuthan Cheru

Ameet Pyati

Ashwin Narasimha

Sandeep Sharma

Ajith Kumar Battaje

Sanjana Aswani

Muhammad Tanweer Alam

Example object storage systems, bookkeeping engines, and methods provide quota usage monitoring for control entities, such as accounts, users, and buckets. An object data store is configured to enable control entities to access data objects associated with each control entity. Data objects are mapped to the control entities and the data objects are processed to identify object usage values corresponding to each combination of data object and control entity. Total usage values are calculated for each control entity and used to determine a data object access response for a target data object and associated control entities.

Object storage system with control entity quota usage mapping

Example distributed storage systems, replication managers, and methods provide versioning validation for data transfers between heterogeneous data stores. A first object data store includes a versioned data object with a plurality of sequential versions corresponding to the versioned data object. A versioned write request message is sent to a second object data store and a response is received. The versioning-enabled status of the second object data store is determined from the response message and, if the versioning enabled status is invalid, any residual object versions in the second object data store are deleted based on a delete request.

Versioning validation for data transfer between heterogeneous data stores

Example distributed storage systems, version control managers, and methods provide persistent version control for data transfers between heterogeneous data stores. A first object data store includes a versioned data object with a plurality of sequential versions corresponding to the versioned data object. A version control manager is configured to determine a creation timestamp for each of the plurality of sequential versions and store a persistent version field for each. The persistent version field remains associated with each of the plurality of sequential versions when transferred from the first object data store to a second object data store.

Persistent version control for data transfer between heterogeneous data stores

Example object storage systems, meta object generators, and methods provide meta objects for replication of configuration data between data object stores. A meta object may be generated that includes configuration data. A meta object identifier may be assigned to the meta object. The meta object may be stored in a first object store with related data objects and may be replicated to a second object data store with the related data objects.

Object storage system with meta object replication

A memory apparatus and methods are provided for preventing read errors on weak pages in a non-volatile memory system. In one example, a method includes identifying a weak page in a non-volatile memory device along a word line, wherein the weak page is partially written with at least some data; buffering data associated with the weak page to a weak page buffer that is coupled in communication with the non-volatile memory device; determining that an amount of data in the weak page buffer has reached a predetermined data level; and writing the data from the weak page buffer into the weak page along the word line in the non-volatile memory device.

Shutdowns and data recovery to avoid read errors weak pages in a non-volatile memory system

A method of direct access by a virtual machine (VM) running on a host machine to physical storage via a virtual function (VF) running on an input/output (IO) adapter comprising: providing by a virtualization intermediary running on the host machine an indication of an active path associated with a virtual storage device; obtaining by a guest driver running within a guest operating system of the VM the stored indication of the active path from the shared memory region; dispatching an IO request by the guest driver to the VF that includes an indication of the active path; and sending by the VF an IO request that includes the indicated active path.

Virtualization intermediary/virtual machine guest operating system collaborative SCSI path management

A method is described for coalescing input/output (IO) interrupts to a virtual machine (VM) running on a host computer. At a virtualization layer of the host computer that supports execution of the VM receives an IO interrupt in response to a completion of an IO request of the VM, wherein a transmission of the IO request by the VM to an IO device bypasses the virtualization layer. The virtualization layer then determines whether the VM has responded to a most recently delivered IO interrupt to the VM by the virtualization layer, and drops the IO interrupt if the VM has not responded to the most recently delivered IO interrupt, thereby failing to deliver the IO interrupt to the VM.

Guest/hypervisor interrupt coalescing for storage adapter virtual function in guest passthrough mode

A method is provided for use in a system that includes a host machine that includes multiple physical CPUs (PCPUs) and at least two cache nodes that are shared by different sets of the PCPUs, comprising: creating in a memory device multiple sets of lanes each lane set associated with a respective PCPU set; tracking levels of processing activity of the PCPUs of each PCPU set; using an MSIX vector value to associate lanes with PCPUs; receiving a IO request from any given PCPU from among the multiple PCPUs; and assigning the IO request to a respective lane based at least in part upon the PCPU set associated with the lane and PCPU processing activity levels.

Virtual machine access to storage via a multi-queue IO storage adapter with optimized cache affinity and PCPU load balancing

A system and method are provided that involve a host computing machine and an SR IOV storage adapter in which the host machine hosts a virtual machine having a guest operating system (guest) coupled for direct passthrough IOV data path and also hosts a virtualization intermediary; a guest operating system (guest) and a virtualization intermediary exchange information concerning IO completions through a shared memory space; the guest writes information to a shared memory space that is indicative of whether an IO completion queue has reached a fill level since the most recently dispatched interrupt at which it is unsafe to coalesce an interrupt; the virtualization intermediary writes information to the shared memory space that is indicative of the interrupt most recently delivered to the guest; the virtualization intermediary reads the information written by the guest to the shared memory space that is indicative of whether an IO completion queue has reached a fill level since the most recently dispatched interrupt at which it is unsafe to coalesce an interrupt; the guest reads the information written to the shared memory space that is indicative of the interrupt most recently delivered to the guest; virtual interrupt coalescing determinations are made based upon the information shred through the shared memory space.

Growing community of inventors

Bengaluru, India

Vibhor Arunkumar Patale