A method includes receiving a plurality of data processing requests and generating a primary processing stack indicating a queue for processing the first data. The primary processing stack comprises a plurality of layers. Each layer comprises a plurality of slices, wherein each slice represents a portion of the first data of at least one data processing request. The plurality of slices are arranged within each layer based at least on the priority indicator corresponding to the first data that each slice represents. The method further includes receiving resource information about a plurality of servers, assigning each slice of the primary processing stack to one of the servers, and sending processing instructions comprising an identification of each slice of the primary processing stack assigned to the respective server.

Container orchestration platforms, such as Kubernetes, automatically manage the execution of applications in containers on host computing systems. An application may include component applications that execute in different containers and a container orchestration platform may organize the containers for those component applications into a pod for the application. To spread the load for the application, the container orchestration platform may enable creation of more than one pod for a single application. Once created, any of the multiple pods may be selected to handle a request to the application. As such, all of the pods are considered active by the container orchestration platform.

Examples described herein relate to execution of multiple Reliability Availability Serviceability (RAS) processes on different processors of the at least two processors to provide fallback from a first RAS process to a second RAS process executing on a processor of the at least two processors based on failure or timeout of the first RAS process. In some examples, the different processors comprise independently operating processors whereby failure or inoperability of one of the different processors is independent of another of the different processors. In some examples, failure or timeout of the first RAS process comprises failure of the second RAS process to receive an operating status signal from the first RAS process.

A Peripheral Component Interconnect Express (PCIe) device includes a plurality of lanes comprising a plurality of ports, a link controller setting a link including the plurality of lanes, wherein the link is set to have a link width that includes the remaining of lanes, except for a fail lane from among the plurality of lanes, and an EQ controller performing an equalization operation for determining a transmitter or receiver setting of each of the remaining lanes, wherein the EQ controller determining a final EQ coefficient using a log information and an error information.

Techniques are described for providing managed computer networks, such as for managed virtual computer networks overlaid on one or more other underlying computer networks. In some situations, the techniques include facilitating replication of a primary computing node that is actively participating in a managed computer network, such as by maintaining one or more other computing nodes in the managed computer network as replicas, and using such replica computing nodes in various manners. For example, a particular managed virtual computer network may span multiple broadcast domains of an underlying computer network, and a particular primary computing node and a corresponding remote replica computing node of the managed virtual computer network may be implemented in distinct broadcast domains of the underlying computer network, with the replica computing node being used to transparently replace the primary computing node in the virtual computer network if the primary computing node becomes unavailable.

A storage system includes a plurality of controllers and a relay device and is configured to perform mirror transfer between the plurality of controllers, the relay device detects an abnormality in each device located between the plurality of controller and aggregates error information in a register, and a first controller module that is a source of performing the mirror transfer among the plurality of controllers reads content of the register and determines whether the mirror transfer is completed normally, after the mirror transfer is performed.

An object of the present invention is to realize a proper storage operation in accordance with the state of a storage devices which constructed remote copy pair via a network. A first storage device for providing a first volume and a second storage device for providing a second volume as a remote copy destination of the first volume, includes: a storing unit for policy sets that is a regulation group relating to the service quality of the second volume; and a policy selection unit for selecting a policy set to be used from the plurality of policy sets in accordance with the states of the first volume and the second storage device. According to such a configuration and operation, it is possible to properly operate the storage device by selecting a policy set before and after the failover or according to the presence or absence of degeneration.

Technologies for dynamic accelerator selection include a compute sled. The compute sled includes a network interface controller to communicate with a remote accelerator of an accelerator sled over a network, where the network interface controller includes a local accelerator and a compute engine. The compute engine is to obtain network telemetry data indicative of a level of bandwidth saturation of the network. The compute engine is also to determine whether to accelerate a function managed by the compute sled. The compute engine is further to determine, in response to a determination to accelerate the function, whether to offload the function to the remote accelerator of the accelerator sled based on the telemetry data. Also the compute engine is to assign, in response a determination not to offload the function to the remote accelerator, the function to the local accelerator of the network interface controller.

Techniques provide for managing data storage. The techniques involve in response to receiving a request for unmapping a logical storage unit associated with a first disk slice on a first physical disk and the first disk slice, determining information associated with the first disk slice; generating, based on the information, a first entry and a second entry corresponding to the first disk slice; adding the first entry into a queue of failed disk slices to enable data stored on the first disk slice to be cleared; and adding the second entry into a queue of free disk slices to enable the first disk slice to be mapped to a further logical storage unit. Accordingly, such techniques can remarkably improve the write I/O performance of the system and prolong the lifetime of the SSD.

A storage system caches, in volatile memory, data read from non-volatile memory. After detecting an uncorrectable error in the data cached in the volatile memory, the storage system replaces the cached data with data re-read from the non-volatile memory and updated to reflect any changes made to the data after it was stored in the non-volatile memory. The storage system can also analyze a pattern in data adjacent to the uncorrectable error and predict corrected data based on the pattern.