Dell Products Inc.

Rishi Mukherjee

Shivendra Katiyar

Raveendra Babu Madala

Ravishankar Kanakapura Nanjundaswamy

Prasoon Kumar Sinha

Naman Goel

Ravishankar N Kanakapura

Sivakumar Swamy

Smruti Ranjan Debata

Sandeep Venkatesh Pai

Harshendra Shetty

Suman Lal Banik

Muniswamy Setty Ks

Elie Antoun Jreij

Sudhir Vittal Shetty

Michael Emery Brown

Ravishankar Kanakapura N

Ramesha He

Chandrasekhar Revuri

Rekha Poosala

Lori Lynn Matthews

Ramesha Hachagodanahally Eraiah

Prasad Yadav Da

Techniques described herein relate to a method for establishing communication sessions. The method may include sending, by a first data node, a request to establish a session to a second data node, wherein the request is encrypted using a compound certificate associated with a data cluster; obtaining, an encrypted token from the second data node; verifying the encrypted token using the compound certificate; performing steward selection to select a third data node to be a steward; generating a unique key and providing a copy of the unique key to the steward; generating an encrypted authentication token using the unique key; sending the encrypted authentication token to the steward; obtaining an authentication token from the second data node, wherein the authentication token is decrypted; verifying the authentication token using the encrypted authentication token; and performing remaining communications associated with the session using the steward.

Cross-vendor device authentication for multi-vendor infrastructure

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

An apparatus in an illustrative embodiment comprises at least one processing device including a processor coupled to a memory. The at least one processing device is configured to identify a plurality of components of a first network device, to generate at least one fingerprint based at least in part on the identified plurality of components of the first network device, to encrypt the at least one fingerprint, to generate at least one packet containing at least the encrypted at least one fingerprint, to send the at least one packet to at least a second network device, and to interact with the second network device to obtain at least one key derived at least in part from the at least one fingerprint. The at least one key is utilized in an authentication process carried out between the first network device and the second network device.

Authentication system for cloud infrastructure using keys derived from device component information

Managing computing workloads within a computing environment including identifying computing parameters of datacenter elements of each computing cluster of a computing environment; for each computing cluster of the computing environment: determining a health of the power device of the computing cluster; for each computing node of the computing cluster: determining a processing load of the computing node; determining a computing cost associated with a geo-location of the computing node; calculating, for each computing cluster, an availability of computing resources of the computing cluster based on the computing parameters of the data center elements of the computing cluster, the health of the power device of the computing cluster, the processing load of each computing node of the computing cluster, and the computing cost of each computing node of the computing cluster; generating a ranking of each computing cluster based on the availability of the computing resources of the computing cluster.

Managing computing workloads within a computing environment

Methods and systems for managing operation of a deployment comprising data processing systems are disclosed. The operation of the deployment may be managed by reducing a likelihood of failure of services to a data processing system. The likelihood of the failure of the services may be reduced by assigning a pod to a data processing system based on identifying fault zones and implementing a fault zone policy. The fault zones may be identified by determining data processing systems that are managed by an infrastructure component. The fault zone policy may be implemented by limiting the assignment of the pod to any number of data processing systems within a fault zone.

Systematic topology spread of pods to data processing systems

A datacenter includes a heterogeneous node group efficiency management system that is coupled to node devices and that, based on a power consumption and performance associated with each node device, generates node group rankings that it uses to group subsets of the node devices into respective heterogeneous node groups. The heterogeneous node group efficiency management system then identifies workload characteristic(s) and performance requirement(s) for a workload provided for deployment, identifies a first heterogeneous node group that satisfies the performance requirement for the workload, and identifies first node device(s) that are included in the first heterogeneous node group and that are configured to perform the first workload having the workload characteristic(s) with a higher power efficiency than second node device(s) that are included in the first heterogeneous node group. The heterogeneous node group efficiency management system then deploys the workload on the first node device(s) in the first heterogeneous node group.

Heterogeneous node group efficiency management system

In one or more embodiments, one or more systems, one or more methods, and/or one or more processes may determine first thermal attribute values associated with multiple information handling systems (IHSs) with respect to a period of time as the IHSs execute a first workload; determine multiple variance ranges respectively associated with the first thermal attributes; periodically determine second thermal attribute values associated with the IHSs as the IHSs execute a second workload; determine that a thermal attribute value of the second thermal attribute values exceeds a respective variance range of the variance ranges as a first information handling system (IHS) of the IHSs executes the second workload; generate an alert based at least on the thermal attribute value exceeding the respective variance range; and in response to the alert, transfer at least a portion of the second workload from the first IHS to a second IHS of the IHSs.

Managing workload execution across MultipleDiffering information handling systems UtilizingThermal profiles

An information handling system includes a console bid manager that may intercept an event from a managed node, transmit notification to eligible management consoles for bids on the event, process the bids to determine one or more interrelated actions in response to the event, and coordinate performance of the one or more interrelated actions in handling the event. The performance of the one or more interrelated actions may be delegated to the eligible management consoles to resolve the event from the managed node.

Coordinating and processing events across multiple system managers

Technology described herein relates to dynamic adjustment of power capping for one or more servers of a subset of servers. A method can comprise generating, by a system operatively coupled to a processor, for a first server subset of a server system, weighted average values comprising a first weighted average value of current workload priority at the first server subset, a second weighted average value of current performance efficiency of the first server subset, and a third weighted average value of predicted future power usage for the first server subset, ranking, by the system, the first server subset as compared to a second server subset of the server system that does not overlap servers with the first server subset, wherein the ranking is based on at least one of the weighted average values, and applying, by the system, a power cap to the first server subset based on the ranking.

Kinetic power capping using fuzzy logic-based dynamic system prioritization

An apparatus comprises a processing device configured to identify compute nodes installed in a chassis of a modular server, and to determine a health status of the compute nodes. The processing device is also configured to designate, based at least in part on the determined health status of the compute nodes, a first one of the compute nodes to act as a primary node for publishing events generated by the compute nodes to a console of the chassis and at least one other compute node to act as a secondary node responsible for acting as the primary node in response to detecting one or more designated conditions. The processing device is further configured to monitor for the designated conditions, and to re-designate a second one of the compute nodes to act as the primary node in response to detecting at least one of the designated conditions.

Event publication from compute nodes installed in a chassis of a modular server to a console of the chassis

The described technology is generally directed towards reallocating power to devices in a group, such as a rack of servers in a datacenter, when no power headroom remains available. Respective devices, which are classified into respective classes corresponding to respective priority device class levels, have power distributed thereto. Upon determining that available power headroom for power capacity distribution among the group of devices has reached an available power capacity distribution lower limit (e.g., zero), reallocation is performed by increasing power capacity allocated to a first device of a higher priority level class, and decreasing power capacity allocated to a second device of a lower priority level class. For more classes, such as high, medium and low, the power can be decreased among the lower priority level classes by a defined ratio, e.g., two-to-one between the medium and low priority classes.

Reallocation of available power among devices in a group

Managing power consumption for computing cluster, including for each IHS of the computing cluster: executing I/O computing workloads at the IHS associated with movement of block storage data, stored at a disk array in communication with the IHS, between the disk array and the IHS; during execution of the I/O computing workloads, determining an I/O power usage of the IHS; calculating an accumulated I/O power consumption of the plurality of IHS based on a summation of the I/O power usage of each of the IHS; during movement of the block storage data, calculating a power consumption of the disk array; calculating, for each IHS, a power storage consumption of the IHS based on the I/O power usage of the IHS, the accumulated I/O power consumption, and the power consumption of the disk array; allocating additional workloads among the plurality of IHS based on the power storage consumption of each IHS.

Managing power consumption for a computing cluster

A datacenter includes a datacenter efficiency management system coupled to node devices. For each of the node devices and based on a power consumption associated with that node device and a performance associated with that node device, the datacenter efficiency management system generates a node group ranking that it uses to group subsets of the node devices into respective homogenous node groups, and then deploys a respective workload on at least one node device in each of the homogenous node groups. Based on at least one of a node workload bandwidth, a node power consumption, and a node health of each node device on which a workload was deployed, the datacenter efficiency management system then generates a workload performance efficiency ranking of the node devices that it then uses to migrate at least one workload between the node devices.

Datacenter efficiency management system for migrating workload across nodes based on workload performance efficiency ranking

An information handling system may include at least one processor and a memory coupled to the at least one processor. The information handling system may be configured to: receive configuration data from a managed information handling system; receive compatibility data from a vendor of the managed information handling system; determine, based on the configuration data and the compatibility data, that the managed information handling system has drifted from a predetermined configuration; and based on the determination of drift, execute a responsive action with regard to the managed information handling system.

Hardware drift determination and remediation

A cooling-power-consumption-based workload allocation system includes a workload allocation system coupled to at least one client device and a plurality of server devices. The workload allocation system receives a first workload request that identifies a first workload from the at least one client device, and determines a first workload priority of the first workload relative to a second workload priority of each second workload being performed by the plurality of server devices. Based on the first workload priority of the first workload relative to the second workload priority of each second workload and a cooling-power-utilization-efficiency ranking of each of the plurality of server devices, the workload allocation system identifies a first server device included in the plurality of server devices for performing the first workload, and causes the first server device to perform the first workload.

Growing community of inventors

Bengaluru, India

Rishi Mukherjee