Netapp, Inc.

Rajesh Rajaraman

Christopher Alan Busick

Sangramsinh Pandurang Pawar

James Silva

William D Dallas

Houze Xu

Per Olov Wahlstrom

Joseph Brown

Jason L Goldschmidt

John David McA'Nulty

Ahmed Shihab

Ling Zheng

Kiyoshi James Komatsu

Balaji Ramani

Vitaly Revsin

Joseph P CaraDonna

Brian Naylor

John DeGraaf

Joseph Caradonna

Stephen Winslow Schmitt

Salimah Addetia

Mohinish Vinnakota

Balaji Cherukuri

Ruitao Duan

Richard Swift

Ardalan Kangarlou

Systems and methods for flushing an operation log journal to both ephemeral storage and persistent storage during a shutdown sequence of a virtual storage system to minimize data-loss scenarios are provided. According to one embodiment, the shutdown or reboot scenarios that result in loss of data are minimized by using persistent storage as a backup to ephemeral storage when the scenario results in rehosting of virtual storage system. For example, responsive to an event indicative of an imminent shutdown or reboot of the virtual storage system, vNVRAM memory may be flushed to both ephemeral storage and persistent storage (e.g., a boot disk). In this manner, when the virtual storage system is rehosted after an unplanned shutdown or reboot resulting from an unrecoverable host error (other than an unrecoverable hardware failure), the operation log journal may be recovered from persistent storage to facilitate vNVRAM replay and avoid data loss.

Reducing potential data-loss scenarios when using ephemeral storage as backing storage for journaling by a virtual storage system

Systems and methods for making use of non-persistent storage as the journaling storage media for a virtual storage system are provided. According to one embodiment, in order to meet the needs of Extreme Low Latency Workloads while also seeking to provide predictable performance and the lowest possible latency, ephemeral storage of the virtual storage system is used to preserve state information (e.g., in the form of boot arguments and an operation log journal) across a host failure recovery scenario in which the virtual storage system is expected to be redeployed within a compute instance brought up by a cloud environment of a hyperscaler on the same host, thereby providing improved data durability (fewer host failure scenarios that result in lost data) as compared to the use of ephemeral memory of the compute instance and lower write latency than the use of persistent storage provided by the cloud environment.

Using ephemeral storage as backing storage for journaling by a virtual storage system

A method, non-transitory computer readable medium and storage server computing device that stores an identifier for a file system block evicted from a buffer cache in an entry in a table. The file system block is inserted into a victim cache hosted by an ephemeral block-level storage device by invoking a function provided by an application programming interface (API). The API exposes the ephemeral block-level storage device to a virtual storage appliance via an operating system of the storage server computing device. The entry in the table is updated to include location(s) on the ephemeral block-level storage device at which one or more portions of the file system block are stored, the location(s) returned in response to the function invocation. By this technology, performance of the virtual storage appliance is significantly improved, resulting in lower latency for client devices requesting data in a cloud storage environment.

Methods for facilitating external cache in a cloud storage environment and devices thereof

Techniques are provided for a high availability solution (e.g., a network attached storage (NAS) solution) with address preservation during switchover. A first virtual machine is deployed into a first domain and a second virtual machine is deployed into a second domain of a computing environment. The first and second virtual machines are configured as a node pair for providing clients with access to data stored within an aggregate comprising one or more storage structures within shared storage of the computing environment. A load balancer is utilized to manage logical interfaces used by clients to access the virtual machines. During switchover, the load balancer preserves an IP address used to mount and access a data share of the aggregate used by a client.

Shared storage model for high availability within cloud environments

Techniques are provided for backing up and restoring a file system or storage virtual machine located within a remote object store. A specification is parsed to identify resources associated with and including a primary resource hosted within a remote object store and to identify REST API endpoints of the resources. GET operations targeting the REST API endpoints of the resources are performed to retrieve the resources and properties of the resources. A link relationship specification is parsed to identify links corresponding to dependencies amongst the resources. A backup of the primary resource is generated to include the resources, the properties of the resources, and dependency information derived from the links. The backup can be used to restore the primary resource to the remote object store in manner that preserves the dependencies amongst the resources.

Backup and restore of resources located within a remote object store

Systems, methods, and machine-readable media for creating, deleting, and restoring volume snapshots in a remote data store are disclosed. A storage volume and a storage operating system are implemented in a software container. Through a user interface, a user may create a snapshot of the volume to a cloud storage. A user may also delete individual snapshots from the cloud storage. Further, deletion of a most recent snapshot may occur by awaiting deletion (though marking as deleted to the user) until a next snapshot is received. Snapshots in the cloud storage are manipulatable even after destruction of the source volume (by destruction of the container, for example). A controller outside the container is used by implementing the same API as the controller in the container had. Full restores of snapshots in the cloud are also possible even when the original container and volume have been destroyed.

Managing volume snapshots in the cloud

Techniques are provided for lock reservations for shared storage. A reserve command to reserve a storage structure is received by a driver from a node. The reserve command is formatted according to a storage protocol. The driver translates the reserve command into a lease acquire command formatted according to an object store protocol and targeting an object stored within an object store and corresponding to the storage structure. A lease identifier derived from a node identifier of the node is inserted into the lease acquire command. The lease acquire command is routed to the object store for obtaining a lease on the object for granting the node exclusive write access to the object.

Lock reservations for shared storage

Techniques are provided for load balancing for IP failover. A backend address of a first node is identified as a routing destination to which a request is to be routed by a load balancer based upon a load balancer rule mapping a frontend address, specified by the request as a request destination, to the backend address of the first node. The request is routed to a primary network interface of the first node using the backend address. The first node has a loopback interface with an address matching the frontend address for routing the request to a destination data structure based upon the request maintaining the frontend address as the request destination. Health probes are used by the load balancer for detecting a failure of the first node in order to failover to routing requests to a second backend address of a second node.

Load balancing for IP failover

A passive state storage controller monitors a plurality of active state storage controllers to determine when a failure of at least one of the active state storage controllers occurs. Based on a determination of a failure, the passive state storage controller remaps storage devices to the passive state storage controller from the failed storage controller. The passive state storage controller may also remap network interfaces. The passive state storage controller retrieves a transaction log of the failed storage controller from a transaction log database, and replays transactions in the retrieved transaction log. The passive state storage controller switches to operating in an active state.

Facilitating n-way high availability storage services

A method, non-transitory computer readable medium, and apparatus that monitors with a passive storage controller a plurality of active storage controllers. A determination is made with the passive storage controller when a failure of one of the active storage controllers has occurred based on the monitoring. Storage device(s) previously assigned to the one of the active storage controllers are remapped to the passive storage controller. A transaction log associated with the one of the active storage controllers is retrieved with the passive storage controller from a transaction log database. Transaction(s) in the transaction log are replayed with the passive storage controller, when the failure of the one of the active storage controllers is determined to have occurred.

Facilitating N-way high availability storage services

A context-based file system (CBFS) receives a request to perform an operation in a hierarchy of directories from a virtual host running on a node in a storage server, the hierarchy having a parent-child relationship and a root directory. An identifier is obtained for the virtual host from an operating system. A directory associated with the virtual host is selected from the hierarchy based on a type of the operation and a position of the directory in the hierarchy. A result is received as a result of performing the operation on the selected directory.

Context based file system

A distributed storage server includes a network module, data module and a management module. The management module receives a data user command for execution on the data module. The data user command is forwarded to the data module and any execution output sent back to the management module. Similarly, the data module receives a management user command for execution on the management module. The management user command is forwarded to the management module and any execution output sent back to the data module.

Growing community of inventors

Acton, MA, United States of America

Rajesh Rajaraman