Dell Products Inc.

Ramesha He

Syama Poluri

Faizal Sn

Raveendra Babu Madala

Viswanath Ponnuru

Krishnaprasad Koladi

Michael Albert Perks

Bharath Koushik Bangalore Suryanarayana

Vaideeswaran G

Bharath Koushik

Chitrak Gupta

Santosh Hanamant Gore

Anurag Sharma

Chandrasekhar Puthillathe

Rishi Mukherjee

Rajib Saha

Nikhith Ganigarakoppal Kantharaju

Abhijit Shashikant Mirajkar

Manjunath Vishwanath

Ravishankar Kanakapura N

Ajay Shenoy

Harish Babu

Suman Lal Banik

Jo Ann Varble

Richa Kumari

Nikita Joshi

Venkataragavan Vijayakumar

Devadath Vijay

Michael Hobbs

In a clustered environment, compute nodes work together to provide high availability and reliability for applications and services. To keep the compute nodes synchronized, a cluster employs a witness service, which typically operates on a separate system. In addition to issues related to potential loss of the witness service, there are also issues of additional costs and overhead. In one or more embodiments, two or more compute nodes of a cluster include a data processing unit (DPU) system operating a witness service. For a compute node with a local DPU system that operates a local witness service, the local witness service handles data related to the local workload(s) and may synchronize with one or more remote witness services on remote DPUs in the cluster in the event of failure or other issues.

Using a data processing unit to support a witness service for a cluster

An information handling system provides configuration, monitoring, and inventory services between an application programming interface service hosted by the information handling system and a remote client. The system communicates using application program interfaces exposed by the application programming interface service with a device associated with the information handling system, and packages data received from the device via the application programming interface service before transmitting the data to the remote client.

Out-of-band support for software redundant array of independent disks

Systems and methods provide failover operations for witness sled hardware installed in a chassis. The chassis may include data storage devices and Information Handling Systems (IHSs), each storing data redundantly to the storage devices, such as in a vSAN. A primary witness sled provides witness functions, such as arbitrating discrepancies in the redundantly stored data. The chassis includes a chassis management controller (CMC) that connects with the primary witness sled via a management signaling pathway and maintains a copy of witness transactions stored by the primary witness sled based on transactions transmitted via the management signaling pathway. The CMC generates an inventory of co-located witness sleds. Upon detecting the primary witness sled is not operational, the CMC selects a failover witness sled from the inventory of co-located witness sleds and migrates witness operations of the primary witness sled to the selected failover witness sled.

Systems and methods for high-availability witness sleds

Systems and methods provide witness sled hardware that may be installed in a chassis and that is configurable using management resources of a chassis in which the witness sled is installed. The chassis may include data storage devices and Information Handling Systems (IHSs), each including one or more CPUs (Central Processing Units) that execute instructions that cause a respective IHS to store data redundantly to the plurality of data storage devices, such as part of a vSAN (Virtual Storage Area Network). The witness sled is configured to provide witness functions, such as arbitrating discrepancies in the redundantly stored data. The chassis includes a management controller that is configured to interface with the witness sled to set up high-speed network connections supported by the witness sled in order to configure the witness sled for providing witness functions within the vSAN, while accounting for the limited resources of the compute sled.

Systems and methods for configuration of witness sleds

A system claims ownership of a shared mailbox, and configures the shared mailbox as a redundant array of independent drives (RAID) controller. The system creates a RAID volume from at least one non-volatile memory express drive, and exposes the RAID volume during a boot process to a basic input/output system.

Enable boot on a non-volatile memory express software redundant array of independent drives volume

Systems and methods provide witness sled hardware installed in a chassis and supported during network failures using management resources of the chassis. A chassis may include data storage devices and Information Handling Systems (IHSs), each configured to store data redundantly to the data storage devices, such as part of a vSAN (Virtual Storage Area Network). The witness sled is configured to provide witness functions, such as to arbitrate discrepancies in the redundantly stored data. The chassis also includes a chassis management controller (CMC) configured to initiate a connection with the witness sled via a management signaling pathway in response to a notification indicating a network fault in a high-speed connection used by the IHSs in communicating with the witness sled. The CMC receives witness transactions from theses IHSs and utilizes the connection initiated via the management signaling pathway to submit the transactions for processing by the witness sled.

Systems and methods for fault-tolerant witness sleds

Technology described herein can globally perform management of security tokens of plural nodes of a multi-node system. In an embodiment, a system can comprise an interconnected group of server nodes, and an administrator node communicatively connected to the interconnected group of server nodes and comprising a processor, and a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations. The operations can comprise selecting a server node of the interconnected group of server nodes as a leader server node, resulting in a selection of the leader server node, in response, receiving, by the administrator node from the leader server node, a request for a new security token, and sending, to the leader server node, the new security token, and broadcasting, by the leader server node across a link layer discovery (LLDP) network, the new security token to additional nodes of the interconnected group of nodes.

Server node-controlled advertisement

Support is provided for remote monitoring and management of non-standard devices of an IHS (Information Handling System) that are not supported by a remote management interface, such as the Redfish management interface. The IHS may be configured for remote management of a non-standard device as part of the manufacture of the IHS. Software for management of the non-standard device is validated against a checksum stored to the IHS during its manufacture to confirm the software for managing the non-standard device has not been altered. If the software is validated, the software is used to initialize a plugin for management of the non-standard device. Data collected by the plugin from monitoring of the non-standard device is provided to a remote access controller of the IHS and the remote access controller issues commands to the non-standard device via the plugin.

Systems and methods for remote management of non-standard devices

Method and systems provide tools for evaluating the impact of component deprecations with a datacenter formed from a plurality of IHSs. Upon receiving a notification of a deprecated component, configuration files that invoke the deprecated component and are in use within the datacenter are identified. Estimates are generated for the resources that would be required to replace references to the deprecated component within the identified configuration files. Estimates may be generated based on compilation errors, test suite failures and historical error repair data. A tree is generated of the dependencies on the deprecated component within the identified configuration files. Based on characteristics of the dependency tree and also based on the resource estimates for replacing references to the deprecated component, a risk level is generated for the deprecated component. The risk level may be generated for individual IHSs, groups of IHSs, or an entire data center.

Systems and methods for evaluating and updating deprecated products

Method and systems support management of deprecated components within a system of IHSs (Information Handling Systems), such as within a datacenter. Upon receiving notification of a deprecated component, instances of the deprecated component are identified within the datacenter. Usage information is collected for the deprecated component by remote access capabilities of the IHSs and by management capabilities of chassis in which the IHSs may be housed. Based on the collected usage information, usages are determined for individual features of the deprecated component. Even though a component has been deprecated, some features of the component may still be supported. Such supported features of the deprecated components are identified. Licenses may be provided for use of features that are that are supported and that are actually utilized, as determined from the usage information.

Systems and methods for extended support of deprecated products

Growing community of inventors

Bengaluru, India

Ramesha He