International Business Machines Corporation

Finisar Corporation

Qin Yue Chen

Han Su

Fei Fei Li

Qi Liang

Hong Lin

Yong Xin Qi

Hongdang He

Chao Wei

Feng Liu

Zhi Hong Li

Feifei Li

Xi Xue Jia

Shu Han Weng

Peng Hui Jiang

Jian Qiao Sun

Xin Peng Liu

Yu Sun

Li Ping Wang

Nan Li

Gang Tang

Shuai Wang

Yang Liang

Li Cao

Ming Shuang Xian

Di Li Hu

Bin Xiong

Chang Xin Miao

Da Long Wang

Yang Yang Feng

Hua Pin Shen

Zu Rui Li

Ya Niu

Xue Lian Feng

VM file management includes detecting a user request to access to a virtual machine (VM) and searching a pre-defined list to determine whether the user requesting access is identified on the list. If so, a file-level snapshot is generated prior to enabling modification of a VM file by the user. The file-level snapshot includes a user attribute and is added as the top layer of a stack. The user attribute indicates a role of the user for whom the file-level snapshot is created. Each layer of the stack contains one or more other file-level snapshots. The VM file is written in the file's entirety to the snapshot in response to the user modifying the VM file. Based on the user attribute of each snapshot, a set of snapshots is selected from the stack, and the VM is modified by merging the VM files belonging to the set of snapshots selected.

Virtual machine file management using file-level snapshots

A serverless computing-based, continuous gateway watch of a data store for data change process is provided. The process includes the gateway interface of the computing environment receiving a watch request from a user system to monitor the data store for data change. Based on receiving the watch request, the gateway interface invokes a serverless setup service to establish a connection between the gateway interface and the data store of the computing environment to be monitored for data change. Based on receiving, at the gateway interface, a data change indication from the data store, the gateway interface invokes a serverless message process service to mutate the data change indication from the data store into a mutated data change message indicative of a data change at the data store for return to the user system pursuant to the watch request, with the serverless message process service terminating thereafter.

Serverless computing-based, continuous gateway watch for data change

A user requests explanation of a term. In response, a definition is provided. The user can indicate that the user does not understand a new term included in the definition. In response, explanation information is customized based on analysis of the initial term and the new term, and then the explanation information is provided to the user.

Providing customized term explanation

A method, computer program product, and a system where a processor(s), in a computing environment comprised of multiple containers comprising modules, includes a processor(s) parsing a module originating from a given container in the computing environment by copying various identifying aspects of a module file comprising the module and calculating, based on contents of the module file, a digest value as a unique identifier for the module file. The processor(s) stores the various identifying aspects of the module file and the digest value in one or more memory objects, wherein the one or more memory objects comprise a module content map to correlate the unique identifier for the module file with the contents of the module, images in the module file with the unique identifier for the module file, and layers with the unique identifier for the module file.

Performance of containers

Embodiments for locating performance hot spots include collecting sample data having instruction addresses, the sample data being for a neural network model and determining instructions in the instruction addresses that are performance hot spots. A listing file is used to map the instructions of the sample data that are performance hot spots to locations in a lower-level intermediate representation. A mapping file is used to map the locations of the lower-level intermediate representation that are performance hot spots to operations in one or more higher-level representations, one or more of the operations corresponding to the performance hot spots, the mapping file being generated from compiling the neural network model.

Locate neural network performance hot spots

Automatic application of software patches to software associated with container images based upon image relationships in a dependency tree. The computing device determines whether software associated with a base container image requires software patches. The computing device accesses dependency trees maintaining image relationships between the base container image and dependent container images. The computing device determines based upon the accessed one or more dependency trees whether the base container image has dependent container images derived from the base container image. The computing device applies software patches to the software associated with the base container image. The computing device rebuilds the base container image with the applied software patches. The computing device then rebuilds the dependent container images dependent upon the rebuilt base container image.

Automatic application of software updates to container images based on dependencies

A method for network communication across application containers in a computer server system includes executing, by a computer system, a host operating system (OS). The host OS is an instance of an OS. The host OS includes multiple application containers operatively coupled to a memory. The method further includes executing, by the host OS, a virtual network interface for each of the application containers. The method further includes implementing, by the host OS, a remote direct memory access (RDMA) transparently for communications amongst the application containers by utilizing shared memory communications.

High performance networking across docker containers

Embodiments of the present disclosure relate to a computer-implemented method for container scheduling in a container orchestration system (COS). According to the method, a new unit comprising one or more containers are detected. Available memory for each of a plurality of candidate nodes deployed in the COS is predicted based on page sharing information of each candidate node. The plurality of candidate nodes filtered to obtain a set of filtered nodes are, wherein the available memory of each of the set of filtered node meets a memory size limitation of the new unit. Priorities of the set of filtered nodes are ranked according to one or more priority functions. The new unit is deployed to one of the filtered nodes based on the priorities.

Container scheduling in a container orchestration system

A method, computer system, and computer program product for accelerating class data loading in a containers environment are provided. In response to a first container in a containers environment being created from a first image, at least one archive file containing a set of classes from the first image can be loaded. Then a respective class sharing file for each of the at least one archive file can be generated. The class sharing file is stored in a shared location. A second container in the containers environment is created from a second image. If a class sharing file from the archive is found in the shared location, that class sharing file can be used.

Class data loading acceleration

This disclosure provides methods, systems and computer program products for page sharing among a plurality of containers running on a host. The method comprises in response to a first container accessing a first file not cached by the first container, checking whether a second file equivalent to the first file is shared in a memory of the host by a second container, wherein the checking is based on a record in which related information of at least one shared file is stored. The method further comprises in response to the checking indicating there is no second file, allocating in the memory at least one page for the first file, loading the first file into the at least one page, and storing related information of the first file into the record.

Page sharing for containers

An example embodiment includes an idle state detection circuit. The idle state detection circuit includes a bias current loop, a rectifying circuit loop, a voltage translating loop, and a filter circuit. The bias current loop provides a rectifying diode a forward current such that the rectifying diode detects an alternating current (AC) signal received from a transmitter via one or more transmission nodes. The rectifying circuit loop stores differential peak to peak amplitude information representative of a peak to peak amplitude of the AC signal in a first capacitor that is electrically coupled to a cathode side of the rectifying diode. The voltage translating loop converts the differential peak to peak amplitude information stored at the first capacitor to a single-end voltage signal across a first resistor that is electrically coupled to the cathode side of the rectifying diode. The filter circuit filters an AC component of the single-end voltage signal.

Differential amplitude detector

A peripheral component interconnect-express (PCIe) link with presence of an active optical cable (AOC) that couples between an electrical PCIe (E-PCIe) transmitter and an E-PCIe receiver may include the AOC. The AOC may include an electrical-to-optical PCIe (EO-PCIe) transceiver coupled to the E-PCIe transmitter. The EO-PCIe transceiver may include a laser diode driver that includes a common mode voltage output terminal. The EO-PCIe transceiver may include a detection condition circuit that includes a decoupling capacitor. The decoupling capacitor may be referenced to a ground level and may connect to the common mode voltage output terminal of the laser diode driver. The detection condition circuit may create a receiver detection condition for a receiver detection circuit of the E-PCIe transmitter to detect presence of the AOC.

Detecting presence of active optical cables in peripheral component interconnect-express links

Processing instruction grouping information is provided that includes: reading addresses of machine instructions grouped by a processor at runtime from a buffer to form an address file; analyzing the address file to obtain grouping information of the machine instructions; converting the machine instructions in the address file into readable instructions; and obtaining grouping information of the readable instructions based on the grouping information of the machine instructions and the readable instructions resulted from conversion. Status of grouping and processing performed on instructions by a processor at runtime can be acquired dynamically, such that processing capability of the processor can be better utilized.

Growing community of inventors

Shanghai, China

Qin Yue Chen