Dell Products Inc.

Amit Pratap Singh

Sandeep Agarwal

Deepu Syam Sreedhar M

Raveendra Babu Madala

Santosh Hanamant Gore

Vivek Sundaresan

Stuart Allen Berke

Chandrashekar Nelogal

Anup Atluri

Ashokan Vellimalai

Vivek S

Sasikumar Subramani

Rishi Kumar

Servers at a data center having similar hardware configurations are grouped together; a leader server is determined from members of the group. A remote network management console discovers the leader without necessarily discovering each particular server and provides a firmware update to only the leader via a communication network over which the systems management console/application and the group of servers can communicate. The leader receives the firmware update and distributes the update to the other group members. In a cluster environment where servers of a group are substantially identical to one another, a leader of the cluster may use a discovery protocol to determine a catalog of current firmware versions of cluster members and their respective peripherals. Based on the catalog, the systems management console/application determines a custom firmware update that will normalize each member of the cluster to one another and forwards the custom update to the cluster leader.

Increased resource usage efficiency in providing updates to distributed computing devices

An information handling system includes a shared device, first and second compute nodes, and a chassis management controller. The first compute node includes a first management controller, which initiates a firmware update for firmware in the shared device. The first management controller detects that that the firmware update is complete. In response to the firmware update being completed, the management controller sends rollback information for the firmware to the chassis controller. The chassis controller stores the rollback information as a rollback image within a storage location of a memory. The chassis controller further sends the rollback information to the second compute node. The second compute node includes a second management controller, which in turn receives the rollback information from the chassis controller, and updates the rollback information within the second compute node.

System and method for enabling a rollback mechanism for shared devices in an information handling system

Systems and methods provide a storage controller with write-back caching capabilities that may be used during scenarios where the storage controller is required to provide write-through caching, and thus unable to utilize internal cache memory for write-back caching. The storage controller utilizes an allocation of persistent memory that is made available by the host IHS (Information Handling System), to which the storage controller is coupled. In scenarios where the storage controller is required to provide write-through caching, the storage controller may be configured to route received write data to the allocated host memory. In this manner, the data integrity provided by write-through operations is maintained, while also providing the host IHS with the speed of write-back operations. When ready to store the write data, the storage controller may request the flushing of write data from the allocated host memory.

Write-back cache for storage controller using persistent system memory

In accordance with embodiments of the present disclosure, a method may be implemented to respond to receiving data A to be stored in a storage system that includes a plurality of N spans, each including a plurality of M drives. The method may include performing data storing operations. The data storing operations may include storing the data A in N portions across the plurality of spans, generating a Za parity based on an XOR operation applied to the N portions of the data A, storing the Za parity in N&#x2212;1 portions across a subset of the plurality of spans, determining a Zap parity based on an XOR operation applied to the N&#x2212;1 portions of the Za parity, and storing the Zap parity.

Spanned RAID with nested parity

A method for copying data from a storage device that has been identified for replacement or has failed to a spare storage device. The method includes a storage controller tracking input/output statistics for several storage devices. The storage controller determines if a first storage device storing first data has been identified for replacement within the storage devices. In response to the first storage device having been identified for replacement, a first least written to data address space within the first storage device is determined based on the input/output statistics. First data contained in the first least written to data address space is copied from the first storage device to the spare storage device.

Growing community of inventors

Allahabad, India

Amit Pratap Singh