Netapp, Inc.

Brian McCarthy

Joseph P CaraDonna

Donna Duffy

Tabriz Holtz

Farshid Eslami Sarab

Afshin Salek Ardakani

Joseph Caradonna

A method, non-transitory computer readable medium, and computing device that determines when a software failure associated with a virtual storage controller has occurred. At least a portion of a transaction log corresponding to the virtual storage controller is stored in a stable storage device, when the determining indicates that the software failure associated with the virtual storage controller has occurred. A determination is made when the virtual storage controller has rebooted. The at least a portion of the transaction log is retrieved from the stable storage device, when the determining indicates that the virtual storage controller has rebooted. Thereby, state can be preserved and transactions pending, but not yet committed to storage server devices, can be replayed and proceed with minimal or no impact on the client devices originating the transactions.

Methods for preserving state across a failure and devices thereof

A method, non-transitory computer readable medium, and host device that receives one or more transactions. A state is stored in a transaction log in a volatile memory wherein the state includes information associated with the one or more transactions. The transaction log is stored in a stable storage device when a failure is determined to a have occurred. The transaction log can then be retrieved and replayed subsequent to a reboot. Thereby, state can be preserved and transactions pending, but not yet committed to storage server devices, can be replayed and proceed with minimal or no impact on the client devices originating the write transactions.

A persistent random-access, byte-addressable storage device may be simulated on a persistent random-access, block-addressable storage device of a storage system configured to enable asynchronous buffered access to information persistently stored on the block-addressable device. Buffered access to the information is provided, in part, by a portion of kernel memory within the storage system allocated as a staging area for the simulated byte-addressable storage device to temporarily store the information destined for persistent storage. One or more asynchronous interfaces may be employed by a user of the simulated byte-addressable device to pass metadata describing the information to a driver of the device, which may process the metadata to copy the information to the staging area. The driver may organize the staging area as one or more regions to facilitate buffering of the information (data) prior to persistent storage on the block-addressable storage device. Each asynchronous access interface is configured to ensure that an order of changes to the data in the persistent storage is consistent with the order of arrival of the changes at the driver.

System and method for simulating a persistent byte addressable storage device on a persistent block addressable storage device

A system and method of testing, during development, the operation of a clustered storage server system and its associated storage operating system. The system includes at least one host computer having a host operating system, and at least one virtual computer having a simulated storage operating system, at least one simulated disk, a simulated NVRAM, and a simulated flashcard within a guest operating system hosted by the host operating system. The simulated storage operating system represents an actual storage operating system. Facilities of the simulated storage operating system including the simulated disk, the simulated NVRAM, and the simulated flashcard are mapped onto corresponding facilities of the host operating system via virtualization components of the virtual computer so that the simulated storage operating system operates substantially the same as the actual storage operating system on low cost host hardware platforms.

Growing community of inventors

Nashua, NH, United States of America

Brian McCarthy