Dot Hill Systems Corporation

Oracle International Corporation

Kent Lee

James George Wayda

Qiang Wang

Ngoclan Thi Vu

Elizabeth Guadalupe Rodriguez

Deepak Agarwal

Travis Portz

Raghavendra Kulkarni

Haining Mo

The disclosed systems, methods and computer readable media relate to managing Non-Volatile Memory Express (NVMe) over Transmission Control Protocol (TCP) (NVMeOTCP) connections between a smart network interface card (smartNIC) and a block storage data plane (BSDP) of a cloud computing environment. A software agent ('agent') executing at the smartNIC may manage a number of network paths (active and, in some cases, passive network paths). The agent may monitor the network traffic (e.g., input/output operations (IOPS)) through the paths (e.g., using established NVMeOTCP connections corresponding to the paths). If a condition is met relating to a performance threshold associated with the monitored paths, the agent may increase or decrease the number established NVMeOTCP connections to match real time network conditions.

Load-based management for NVME over TCP connections

A smart network interface card (smartNIC) may receive first traffic for a first process configured with a first bandwidth limit. The smartNIC may receive second traffic for a second process configured with a second bandwidth limit, the second bandwidth limit corresponding to a larger value between a second transmit limit and a second receive limit associated with the second process. The smartNIC may queue the received traffic associated with the first process and the second process in a scheduler, the scheduler having a first set of queues configured to store traffic from the first process, and a second set of queues configured to store traffic from the second process. The smartNIC may forward queued traffic from the first set of queues or the second set of queues, a maximum amount of forwarded first process traffic corresponding to the first bandwidth limit minus an amount of forwarded second process traffic.

Bandwidth control inside a shared network interface card

The disclosed systems, methods, and computer readable media relate to managing persistent memory within a smart network interface card (smartNIC) of a cloud-computing environment, or at storage device of the host instance on which the smartNIC operates and to which the smartNIC has access. The smartNIC may be configured with various modes that enable passthrough of input/output operations to or from non-volatile remote storage (e.g., a block storage data plane volume) or storage of at least some of the data corresponding to the input/output operations within the persistent memory managed by the smartNIC. The smartNIC may be configured to select a storage location for data between a pool of candidate storage including the persistent storage managed by the smartNIC or the non-volatile remote storage. These techniques improve communications between the smartNIC and the non-volatile remote storage and reduce the risk of network jitters and overall network latency.

Persistent memory based caching for intelligent network interface cards

The present embodiments relate to throttling input/output (IO) processing tasks at a centralized node (e.g., a SmartNIC device) and implement multiple routing paths to prevent performance degradation in handling data patterns. For instance, the centralized node can implement a throttling system to assign portions of a number of input/output operations to be performed to a series of extent servers in a cloud infrastructure environment. The present embodiments also can implement multiple paths and/or multiple path groups to route the assigned portions of the I/O operations. For instance, the assigned portions of I/O operations can be routed to the extent servers via a first path of multiple paths. In the event of a failure of the first path, the assigned portions of I/O operations can be re-directed to a second path or another path in the path group.

Increased data processing performance of a non-volatile memory express (NVME) block store

A data storage system, device, and method are provided for replicating data between different data storage systems or appliances. More specifically, the present invention affords communications between heterogeneous data storage systems that potential employ different communication protocols. A bridging communication protocol is utilized by one or both storage systems in order to accommodate different communication protocols. Alternatively, a storage appliance connecting the data storage systems may employ the bridging communication protocol.

Pull data replication model

A method, device, and system are provided for accessing metadata in a data storage system. More specifically, a requesting application requests a cache application to allocate a cache page to retrieve metadata from a storage device. After metadata is written to the cache page, the cache page is locked by the requesting application. The cache page is maintained in a locked state by the requesting application. This allows the data stored within the cache page to be quickly accessed and updated by the requesting application without waiting for the cache page to be written back to the storage device after every update to the cache page occurs.

Method and apparatus for quickly accessing backing store metadata

A method and device for cloning snapshots is provided. A new snapshot can be created by cloning an existing snapshot. The clone snapshot may use the preserved data of the existing snapshot, thereby obviating the need to copy the preserved data. Additionally, the clone snapshot may be created with a data structure for storing write data. Since the clone snapshot initially has no write data to store, the creation of the entire clone snapshot can be accomplished without copying any preserved data or write data from the existing snapshot, thereby increasing the efficiency with which a clone snapshot can be created.

Snapshot preserved data cloning

A method, device, and system for resetting snapshots are provided. The reset of a snapshot incorporates the traditional snapshot delete and snapshot create operations into a single operation. Additionally, a snapshot created under the reset operation may receive an array partition from a snapshot being deleted under the same snapshot reset operation thereby retaining its identifying characteristics.

Snapshot reset method and apparatus

A method, device, and system are provided for determining when to re-initialize a backing store in a data storage system. More specifically, when all snapshots associated with a specified backing store are either being deleted or are marked for deletion the backing store is re-initialized rather than deleting each snapshot independently. The re-initialization of the backing store provides for a quicker way to delete all snapshots than can be achieved by deleting each snapshot independently.

Automatic triggering of backing store re-initialization

A method and device for managing snapshot data is provided. Snapshots may be created having a preserved data area and a write data area. The preserved data area is used to maintain snapshot data corresponding to the point-in-time when the snapshot was created while the write data area is used to facilitate host read/write access to the snapshot. By maintaining two separate areas, the snapshot can be written to without altering the point-in-time representation of the snapshot.

Method and apparatus for separating snapshot preserved and write data

A method, device, and system are provided for rollback of a master volume in a data storage system. More specifically, when a rollback is requested, snapshots that are involved in the rollback can be deleted during the rollback. This is accomplished by deleting the snapshot partition but not the actual snapshot data. Rather, the snapshot data is retained until the rollback is complete incase some of the snapshot data needs to be written to the master volume as part of the rollback.

Deletion of rollback snapshot partition

A method, device, and system are provided for re-initializing a backing store in a data storage system. More specifically, when all snapshots associated with a specified backing store are either being deleted or are marked for deletion the backing store is re-initialized rather than deleting each snapshot independently. The re-initialization of the backing store provides for a quicker way to delete all snapshots than could previously be achieved when each snapshot was deleted independently.

Growing community of inventors

Ladera Ranch, CA, United States of America

Kent Lee