Abstract: Embodiments of the present disclosure provide methods, devices, and computer program products for processing a task. A method of processing a task comprises: receiving, at a network device and from a set of computing devices, a set of processing results derived from processing the task by the set of computing devices; in response to receiving the set of processing results, executing a reduction operation on the set of processing results; and transmitting a result of the reduction operation to the set of computing devices. In this way, embodiments of the present disclosure can significantly reduce an amount of data exchanged among a plurality of devices processing a task in parallel, and thus reduce network latency caused by data exchange.

Abstract: The present disclosure provides a method and apparatus for storing data. The method comprises: extracting metric information and metadata associated with the metric information from time series data, the metric information including a time value and a numerical value at the time value; and staling the metric information in an object storage device and the metadata in a database. As compared with the prior art, the present disclosure provides a flexible storage design to guarantee extensibility of storage capacity and meanwhile support fast data retrieving.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for encoding binary data are provided. One of the methods includes: obtaining a multimedia file from a storage device, extracting multiple bytes of binary data from the multimedia file, converting the binary data into 7-bit encoded data using an encoding algorithm, and sending one or more signals comprising the 7-bit encoded data to a remote computing device. The converting includes identifying multiple bits of data, each corresponding to a predetermined bit position of one of the bytes of binary data, generating one or more bytes of combined-bit data by combining the identified bits of data, generating one or more bytes of remaining-bit data, and generating the 7-bit encoded data by concatenating the one or more bytes of combined-bit data and the one or more bytes of remaining-bit data.

Abstract: A scheduler module receives a first allocation request for a given amount of a resource in a cloud computing platform that an application program currently needs. The scheduler module allocates the given amount of the resource to the application program for a first time slot. The given amount of allocated resource is received back at the scheduler module upon expiration of the first time slot for subsequent allocation. The scheduler module receives a second allocation request for a given amount of a resource that an application program currently needs. The scheduler module allocates the given amount of the resource to the application program for a second time slot. The given amount of allocated resource is received back at the scheduler module upon expiration of the second time slot for subsequent allocation.

Abstract: A method, system and computer program product for performing video analytics on content, by collecting content (video data) from a plurality of sources, wherein the content pursues a streaming protocol; and performing at least one of storing the content in a local repository for downtime recording wherein on negative determination of a network connection, wherein servers directly coupled to a plurality of sources cache content until the network connection retains normalcy or performing analytics at least one of a real-time insight or an interactive insight or a batch insights on the content, and displaying to the user a resulting insight wherein the resulting insights are in a human readable form.

Abstract: Embodiments of the present disclosure provide a method and apparatus for data processing. The apparatus comprises: a dividing unit configured to divide, based on a predetermined policy, computation workload for data in a storage node into at least one sub-workload; and a dispatching unit configured to dispatch the at least one sub-workload to at least one of the storage node and a computing node that is physically separate from the storage node for execution of the at least one sub-workload with computing resources in the at least one of the storage node and the computing node.

Abstract: Embodiments of the present disclosure provide a method and apparatus for providing data storage service. The method comprises: receiving a storage service template from an user, the storage service template specifying a storage service policy for the user and a service instance to launch; and providing a storage service according to the storage service template; wherein the storage service policy defines a storage function to be performed for data of the user. With the method and apparatus according to embodiments of the present disclosure, a unified solution for overall orchestration of storage functions can be provided to enable the user to customize the required storage function flexibly.

Abstract: At least one performance metric is monitored in an information processing system to detect a performance event substantially contemporaneous with the occurrence of the event, wherein monitoring of the performance metric is performed in a continuous manner. At least a portion of the information processing system is profiled in response to detection of a performance event, wherein the profiling step obtains a performance snapshot of the portion of the information processing system being profiled. The performance snapshot is analyzed to determine a root cause of the performance event within the information processing system.

Abstract: Embodiments of the present disclosure provide methods and apparatuses for data migration of storage devices including registering at least one executing unit for data migration, each of the at least one executing unit corresponding to description file; extracting and storing information contained in the description file corresponding to each of the at least one executing unit; receiving a data migration request from a user; in response to the data migration request from the user, selecting an executing unit for data migration of the user at least based on part of the stored information contained in the description file; and scheduling an instance of the selected executing unit to execute data migration of the user. The methods or apparatuses according to embodiments of the present disclosure can implement, in a uniform and scalable manner, data migration for various formats, various performance requirements, and application scenarios.

Abstract: An apparatus in one embodiment comprises a plurality of container host devices of at least one processing platform. The container host devices implement a plurality of containers for executing applications on behalf of one or more tenants of cloud infrastructure. One or more of the container host devices are each configured to compute distance measures between respective pairs of the containers and to assign the containers to container clusters based at least in part on the distance measures. The distance measures may be computed as respective content-based distance measures between hash identifiers of respective layers of layer structures of the corresponding containers. The apparatus may further comprise an interface configured to present a visualization of the container clusters. User feedback received via the interface is utilized to alter at least one parameter of the computation of distance measures and the assignment of clusters to container clusters.

Abstract: A time-series data cache is operatively coupled between a time-series analytics application program and a time-series data store, and configured to temporarily store portions of the time-series data. The time-series data store is configured to persistently store time-series data. The time-series data cache is further configured to be responsive to one or more data read requests received from the time-series analytics application program.

Abstract: A method for processing data includes receiving an adjustment request for adjusting a number of consumer instances from a first number to a second number, and determining a migration overhead for adjusting a first distribution of states associated with the first number of consumer instances to a second distribution of the states associated with the second number of consumer instances, wherein the states are intermediate results of processing the data and the migration overhead includes a latency and a bandwidth shortage incurred for migrating the states. Based on the determined migration overhead, the states are migrated between the first number of consumer instances and the second number of consumer instances, and thereafter the data is processed based on the second distribution of the states at the second number of consumer instances.

Abstract: Systems and methods are provided for implementing a self-adaptive batch dataset partitioning control process which is utilized in conjunction with a distributed deep learning model training process to optimize load balancing among a set of accelerator resources. An iterative batch size tuning process is configured to determine an optimal job partition ratio for partitioning mini-batch datasets into sub-batch datasets for processing by a set of hybrid accelerator resources, wherein the sub-batch datasets are partitioned into optimal batch sizes for processing by respective accelerator resources to minimize a time for completing the deep learning model training process.

Abstract: Embodiments of the present invention relates to a method and system for processing data. Specifically, there is provided a method for processing data, comprising: in response to receiving an adjustment request for adjusting the number of consumer instances from a first number to a second number, determining an adjustment policy on adjusting a first distribution of states associated with the first number of consumer instances to a second distribution of the states associated with the second number of consumer instances, the states being intermediate results of processing the data; migrating the states between the first number of the consumer instances and the second number of the consumer instances according to the adjustment policy; and processing the data based on the second distribution of the states at the second number of the consumer instances. In other embodiments, there are further provided a device and system for processing data.

Abstract: Embodiments of the present disclosure provide a method and apparatus for determining a cause of performance degradation of a storage system. The method comprises: monitoring performance of the storage system according to a predetermined policy; generating a performance degradation event from a result of the monitoring based on system performance baseline; in response to performance degradation event, obtaining information about the performance degradation; and offline analyzing the information to determine the cause of the performance degradation. Compared with the prior art, embodiments of the present disclosure can manage the system performance degradation effectively and continuously to minimize running costs and enable current performance profiling tools in the manner of insertion.

Abstract: Embodiments of the present disclosure provide a method, apparatus and computer program product for resource scheduling. The method comprises obtaining a processing requirement for a deep learning task, the processing requirement being specified by a user and at least including a requirement related to a completion time of the deep learning task. The method further comprises determining, based on the processing requirement, a resource required by the deep learning task such that processing of the deep learning task based on the resource satisfies the processing requirement. Through the embodiments of the present disclosure, the resources can be scheduled reasonably and flexibly to satisfy the user's processing requirement for a particular deep learning task without requiring the user to manually specify the requirement on the resources.

Abstract: According to an embodiment, a performance benchmark dataset is obtained, where the performance benchmark database at least includes structural data of one or more deep neural network models, time performance data and computing resource consumption data of a plurality of deep learning applications based on the one or more deep neural network models; a training dataset is extracted based on the performance benchmark database, where the training dataset has a plurality of parameter dimensions, the plurality of parameter dimensions including: structures of deep neural network models of the plurality of deep learning applications, resource configuration of the plurality of deep learning applications, and training time of the plurality of deep learning applications; and correspondence among the parameter dimensions of the training dataset is created so as to create an estimation model for estimating resources utilized by deep learning applications.

Abstract: Embodiments of the present disclosure relate to methods and an electronic device for transmitting and receiving data. The data transmission method includes: determining a hash value of original data to be transmitted; determining whether the hash value exist in a predetermined set of hash values; in response to the hash value being present in the set of hash values, transmitting the hash value, rather than the original data, to a server; and in response to the hash value being absent from the set of hash values, transmitting the original data to the server; and adding the hash value to the set of hash values. The embodiments of the present disclosure can avoid transmitting duplicated data between a client and a server, and it is not required to add extra remote procedure calling commands between the client and the server.

Abstract: A method for processing a data request in a software defined storage system, wherein the software defined storage system comprises one or more nodes configured as a set of client modules operatively coupled to a set of server modules, comprises the following steps. A data request with a data set is received at one of the set of client modules. One or more data services (e.g., deduplication and/or data compression) are performed on the data set, wherein the performance of the one or more data services on the data set is dynamically shared between one or more of the set of client modules and one or more of the set of server modules.

Abstract: A request is received for an image to be presented on a client computing device, where the image is synthesized by shared images and dedicated images dedicated to the client computing device. A first one or more source files are identified for generating the shared images that are used by the client computing device and one or more other client computing devices. The shared images are generated based on the first one or more source files. A second one or more source files are identified for generating the dedicated images. A configuration file is generated that includes instructions for the client computing device to synthesize the shared images and the second one or more source files to the requested image. The shared images, the second one or more source files, and the configuration file are sent to the client computing device.