Dell Products Inc.

Emc IP Holding Company LLC

Emc Corporation

Igor Achkinazi

Lev Knopov

Sergey Kornfeld

Luis O Torres

Arieh Don

Owen Martin

Alexandr Veprinsky

Adnan Sahin

John D Hushon, Jr

Ahmet Kirac

Narasimha R Challa

Bryan Duerk

Tal Abir

Vladislav Eremeev

Jitender Sawal

A method for use by a computing device, comprising: receiving a bulk request for namespace information, the bulk request being a Non-Volatile Memory Express (NVMe) command that contains a Controller and Namespace Structure (CNS) code, the CNS code being arranged to indicate that the namespace information for multiple namespaces should be returned in response to the bulk request; identifying a plurality of namespaces, the plurality of namespaces being identified based on an offset value and a length value that are provided in the bulk request; transmitting a bulk request response that contains namespace descriptors for each of the plurality of namespaces.

NVMe over TCP connection performance optimization on high latency networks

An apparatus includes at least one processing device comprising a processor coupled to a memory. The processing device is configured to process host input-output operations received in a first storage system from at least one host device, the host input-output operations being placed in a first storage queue of the first storage system to await access to one or more backend storage devices of the first storage system, to process replication input-output operations in the first storage system for delivery to a second storage system, the replication input-output operations being placed in a second storage queue of the first storage system to await access to the one or more backend storage devices of the first storage system, and to dynamically adjust priorities of the respective first and second storage queues for access to the one or more backend storage devices in accordance with one or more priority adjustment criteria.

Storage system with dynamic fair queue scheduling of host and replication input-output operations

In a software-defined data storage system with a production node and local and remote storage nodes that replicate data generated by an application running on the production node, all filesystem metadata associated with remotely replicated devices is copied from the remote storage node to memory of the production node in response to establishment of a communication link between the production node and remote storage node. That metadata is maintained in the memory for as long as the link is active and used to generate multiple remote replication IOs. Local replication is implemented by reading only necessary metadata from the local storage node on a per-IO basis. The cached metadata is flushed from memory in response to loss of the communication link.

Efficient storage device handling in remote replication

An apparatus comprises at least one processing device that includes a processor coupled to a memory. The processing device is configured to receive in a host device, for a plurality of targets of a storage system, information characterizing particular sets of one or more logical storage volumes accessible to the host device via respective ones of the targets, to compare the received information to a working set maintained by the host device, the working set identifying one or more logical storage volumes utilized by at least one application deployed on the host device, and to control a number of input-output (IO) queues configured in the storage system for each of one or more of the targets based at least in part on a result of the comparison of the received information to the working set. The targets illustratively comprise NVMe targets, and the logical storage volumes comprise respective NVMe namespaces.

Dynamic adjustment of network resources based on logical storage volume working set

One or more aspects of the present disclosure relate to dynamically selecting a storage array and corresponding input/output (IO) paths between a host and the storage array. In embodiments, a virtual storage volume (VSV) can be established for a host entity using one or more storage device portions from a plurality of storage arrays. In addition, IO servicing metric parameters can be dynamically measured. The servicing metric parameters can define metrics corresponding to the VSV's assigned ports on each of the storage arrays or network latency between the host and each of the plurality of storage arrays. Further, a primary storage array from the plurality of storage arrays can be selected based on the IO servicing metrics.

Resiliency SLO protocol layer

Systems and methods herein save one or more parameters related to NVMe® data in one or more memory mapped files or in shared memory region(s). When a storage target experiences an interrupt event (e.g., loss of connectivity, system crash, application crash, etc.), the storage target may be restarted (e.g., a new instance formed in the case of a software-defined storage target) that uses the stored parameter data to recreate the controller context (e.g., NVMe® controller and TCP (transmission control protocol) connection), and the storage target may resend the last TCP acknowledgement, thereby causing the host to send or resend any NVMe/TCP data that follows the last successfully received NVMe/TCP data—thus, any data that the host sent during the storage target down time, which may have been lost, is re-sent. Embodiments keep a host unaware of a storage target interrupt and remove the need for TCP reestablishment.

High availability in non-volatile memory express (NVMe®) over transmission control protocol (NVMe/TCP)

An apparatus includes at least one processing device configured to identify a logical storage volume stored across multiple storage nodes of a distributed storage system, to obtain from each of one or more of the storage nodes locality information for one or more different portions of the logical storage volume, the locality information for a given one of the portions indicating whether or not the given portion of the logical storage volume is local to a particular storage node, and to utilize the obtained locality information in performing path selection for one or more input-output operations targeting the logical storage volume. Obtaining from each of one or more of the storage nodes locality information for one or more different portions of the logical storage volume illustratively comprises, for a given such storage node, obtaining the locality information from one or more log pages maintained by the storage node.

Host-based locality determination using locality log pages

First and second target controllers implemented in a storage system are associated with respective first and second storage pools having respective first and second service level objectives. Input-output (IO) operations are received from one or more host devices and processed in the storage system, with different ones of the IO operations being directed from one or more initiators of the one or more host devices to different ones of the first and second target controllers. Separate feedback information is provided from the storage system to the one or more host devices for respective ones of the first and second target controllers, so as to permit different amounts of throttling of additional IO operations in the one or more host devices based at least in part on whether those additional IO operations are to be directed to the first target controller or the second target controller.

Storage system with multiple target controllers supporting different service level objectives

An apparatus includes at least one processing device configured to identify a logical storage volume stored across multiple storage nodes of a distributed storage system, and for each of a plurality of different portions of the logical storage volume, to send one or more locality determination commands to each of one or more of the storage nodes, a given such command requesting a corresponding one of the storage nodes to respond with an indication as to whether or not the portion of the logical storage volume is local to that storage node, and to receive from the one or more storage nodes responses to the one or more locality determination commands. The processing device is further configured to store locality information for the plurality of different portions of the logical storage volume based at least in part on the responses of the storage nodes to the locality determination commands.

Host-based locality determination for logical volumes stored across multiple nodes of a distributed storage system

Providing access to a host for requested data in a data storage array includes transferring the requested data from a cache memory of the data storage array to either the host or a host adaptor if the requested data is in the cache memory, transferring the requested data from a relatively slow non-volatile memory of the data storage array to the cache memory and subsequently transferring the requested data from the cache memory to either the host or the host adaptor if the requested data is in the relatively slow non-volatile memory and transferring the requested data simultaneously to the cache and to either the host and the host adaptor if the requested data is stored in relatively fast non-volatile memory. Data may be transferred directly from the relatively fast non-volatile memory to the host. The relatively fast non-volatile memory may be controlled by the host adaptor.

Accessing fast memory in a data storage array

Transferring data to an initiator includes providing a first target that exchanges commands and status with the initiator, providing a second target that exchanges commands and data with the first target and exchanges data with the initiator, the initiator providing a transfer command to the first target, the first target providing a transfer command to the second target, and in response to the transfer command received from the first target, the second target transferring data to the initiator. Data may be transferred to the initiator using RDMA. The second target may provide a status message to the first target indicating a result of transferring data. The first target may provide the status message to the initiator. The first target may be a host adaptor of a data storage array. The second target may be a flash memory. The initiator may be a host coupled to the data storage array.

Split target data transfer

Described are techniques for partitioning processors in a system. At a first point in time, a short term workload ratio and a long term workload ratio are determined. At the first point in time, the system is in a first workload state having a first configuration including a first portion of the processors performing front end processing tasks and a second portion of the processors performing back end processing tasks. A first value is determined where the first value is an absolute value of a difference between the short term workload ratio and the long term workload ratio. First processing is performed that determines, in accordance with the first value and the short term workload ratio, whether to adjust any of the first portion of the processors and the second portion of the processors of the first configuration.

Dynamic allocation of CPU resources based on system load trends

A scalable, storage cloud enabled data center includes a cluster of enterprise storage nodes. Each storage node includes a storage grid, a computation grid, and data availability and data protection modules. The data center is scaled by adding additional storage nodes to a cluster of storage nodes which are interconnected, e.g., via a hardware interface, switches, and switch-routers.

Scalable monolithic data storage system for cloud environment

Described are techniques for processing data operations. A request is sent from an application to perform a data operation on a key-value data store. The request is in accordance with a first application-level protocol for performing the data operation on the key-value data store and includes a first key of a first key-value pair used by a data storage system to perform the data operation. The request is received at the data storage system such as by a key-value server that processes requests in accordance with the first application-level protocol for the key-value data store. In response to receiving the request at the data storage system, first processing is performed on the data storage system for the data operation and a response is returned to the application.

Growing community of inventors

Northborough, MA, United States of America

Igor Achkinazi