Shanghai Jiao Tong University

Huawei Technologies Co., Limited

Haibing Guan

Ruhui Ma

Jian Li

Zhengwei Qi

Xiaokang Hu

Tao Song

Jianguo Yao

Yun Yu Wang

Xin Xu

Yan Li

Yin Wang

Qiang Gu

Miao Yu

Junsheng Tan

Yubin Chen

Weiye Chen

Jiacheng Ma

Yongbiao Chen

Xiaolong Jia

Minjun Zhu

Fanfu Zhou

Shuangshuai Jia

Zongpu Zhang

Zhuocheng Ding

Yang Hua

Wang Zhang

Zhouwang Fu

A request-response based paravirtualized I/O system and method relating to the fields of virtualization and cloud computing includes a request-response application, a front-end drive module and a back-end drive module. The front-end drive module and the back-end drive module interact by means of a transmit queue and a receive queue. The request-response application generates an I/O request, and the front-end drive module writes the I/O request into the transmit queue. The system has two operating modes: a notification mode and a polling mode. The system operates by default in the notification mode. When the request-response application issues a connection establishment or service request, the system switches to the polling mode. This system and method introduce an optimistic polling mechanism, combine the advantages of the notification mode and the polling mode, reduce the number of VM exits and decrease wasting of computing resources, thus improving data path performance.

Request-response based paravirtualized I/O system and method

The present invention discloses a hierarchical highly heterogeneous distributed system based deep learning application optimization framework and relates to the field of deep learning in the direction of computational science. The hierarchical highly heterogeneous distributed system based deep learning application optimization framework comprises a running preparation stage and a running stage. The running preparation stage is used for performing deep neural network training. The running stage performs task assignment to all kinds of devices in the distributed system and uses a data encryption module to perform privacy protection to user sensitive data. Due to heterogeneous characteristics of a system task of the present invention, on the premise that the overall performance is guaranteed, the system response time is reduced, the user experience is guaranteed, the data encryption module based on the neural network can perform privacy protection to user sensitive data at a lower computing cost and storage cost, and the user data security is guaranteed.

Hierarchical highly heterogeneous distributed system based deep learning application optimization framework

The present invention finds and defines a problem which possibly exists in an interrupt remapping mechanism under a virtual symmetric multiprocessing environment, i.e., a problem of Interruptability Holder Preemption (IHP). This problem causes the interrupt remapping mechanism to fail and reduces I/O performance of virtual machines. In order to solve the IHP problem, the present invention provides a proactive VCPU comprehensive scheduling method based on interruptability holder information. This method is based on Kernel-Based Virtual Machines (KVMs) which are widely used at present and paravirtualization network models thereof. By globally controlling and analyzing a running state of an interruptability holder and simultaneously considering global scheduling fairness of a system, a VCPU comprehensive scheduling method is established, which can effectively eliminate the IHP problem and obviously improve the I/O performance of the virtual machines.

Comprehensive scheduling method and device for problem of interruptability holder preemption

The present invention provides an adaptive computing resource allocation approach for virtual network functions, including the following two steps: Step 1: predicting VNFs' real-time computing resource requirements; Step 1.1: offline profiling different types of VNFs, to obtain a parameter relation between the required amount of computing resources and the ingress packet rate; Step 1.2: online monitoring the network traffic information of each VNF, and predicting VNFs' required amount of computing resources with combination of the parameters in Step 1.1; Step 2: reallocating computing resources based on VNFs' resource requirements. The computing resource allocation approach includes a direct allocation approach and an incremental approach. The adaptive computing resource allocation approach for virtual network functions of the present invention allocates computing resources based on VNFs' actual requirements, and remedies performance bottlenecks caused by fair allocation.

Adaptive computing resource allocation approach for virtual network functions

The method includes the following steps: step 1. obtaining NUMA topology information of a host machine, and monitoring virtual machine performance events by using a kernel PMU; step 2. implementing a greedy algorithm, and a scheduling decision is obtained; step 3. scheduling, according to the scheduling decision, a virtual CPU (VCPU) and a memory of a virtual machine; step 4. after the scheduling of the virtual machine is complete, redirecting to step 1 to continue performing performance monitoring of the virtual machine.

Apparatus and method for virtual machine scheduling in non-uniform memory access architecture

The present invention provides a multi-resource scheduling method responding to uncertain demands in a cloud scheduler, where two computation formulas for fairness and efficiency are used as cost functions in an optimization problem. For some change sets with uncertain resource demands, a robust counterpart of an original non-linear optimization problem is computationally tractable. Therefore, the present invention models features of these sets with uncertain resource demands, i.e., establishes an ellipsoidal uncertainty model. In this model, each coefficient vector is put into a hyper-ellipsoidal space and used as a metric to measure an uncertainty degree. With the ellipsoidal uncertainty model, a non-linear optimization problem is solved and a resource allocation solution that can respond to dynamically changing demands can be obtained.

Multi-resource scheduling method responding to uncertain demand in cloud scheduler

Physical Graphics Processing Unit (GPU) resource scheduling system and method between virtual machines are provided. An agent is inserted between a physical GPU instruction dispatch and a physical GPU interface through a hooking method, for delaying sending instructions and data in the physical GPU instruction dispatch to the physical GPU interface, monitoring a set of GPU conditions of a guest application executing in the virtual machine and a use condition of physical GPU hardware resources, and then providing a feedback to a GPU resource scheduling algorithm based on time or a time sequence. With the agent, it is unneeded for the method to make any modification to the guest application of the virtual machine, a host operating system, a virtual machine operating system, a GPU driver and a virtual machine manager.

Resource scheduling system and method under graphics processing unit virtualization based on instant feedback of application effect

Described herein is a method for resource aggregation (many-to-one virtualization), comprising: virtualizing CPU by QEMU in a distributed way; organizing a plurality of memories scattered over different machines as pages to providing consistent memory view for guest OS; and performing time synchronization between different machines.

GiantVM for resource aggregation

The present invention relates to Data Center Network (DCN) flow scheduling scheme. It provides a dynamic scheduling algorithm and a hybrid of centralized and decentralized scheduling system to improve the performance of DCN and data parallel application. The scheduling system uses a central controller to collect the real-time bandwidth of each node, and schedule the priority as well as transmission rate of each network flow set combined by application context (Coflow [1]). The centralized scheduling avoids a sophisticated system design and hardware (switch) modification to comparing with full decentralized solutions. The combination of centralization and decentralization decreases the average completion time of Coflows, and eventually improve the performance of data parallel applications.

Dynamic network flows scheduling scheme in data center

Described herein is a method for optimizing a scalable GPU virtualization, comprising: providing each vGPU with a private shadow graphics translation table (GTT); copying vGPU's private shadow GTT to physical GTT along with the context switch, wherein the private shadow GTT allows vGPUs to share an overlapped range of a global graphics memory space.

System, apparatus, and method for optimizing a scalable GPU virtualization

A method for mapping between a virtual central processing unit (CPU) and a physical CPU. The method includes obtaining, by a virtual machine manager, a set of to-be-mapped first virtual CPUs in a current time period and a first physical CPU that has fewest to-be-run tasks, obtaining, by the virtual machine manager, a first characteristic value of each first virtual CPU in the set of first virtual CPUs and a second characteristic value of the first physical CPU, obtaining, by the virtual machine manager from all the first characteristic values, a target characteristic value that matches the second characteristic value, and mapping a target virtual CPU corresponding to the target characteristic value to the first physical CPU for running. By means of the foregoing technical solutions, resource contention and a decrease in overall system performance are avoided when mapping a virtual CPU to a physical CPU.

Method for mapping between virtual CPU and physical CPU and electronic device

A scheduling method for virtual processors based on the affinity of NUMA high-performance network buffer resources, including: in a NUMA architecture, when a network interface card (NIC) of a virtual machine is started, getting distribution of the buffer of the NIC on each NUMA node; getting affinities of each NUMA node for the buffer of the network interface card on the basis of an affinity relationship between each NUMA node; determining a target NUMA node in combination with the distribution of the buffer of the NIC on each NUMA node and NUMA node affinities for the buffer of the NIC; scheduling the virtual processor to the CPU on the target NUMA node. The problem of affinity between the VCPU of the virtual machine and the buffer of the NIC not being optimal in the NUMA architecture is solved to reduce the speed of VCPU processing network packets.

Scheduling method for virtual processors based on the affinity of NUMA high-performance network buffer resources

The invention discloses a method for dynamic interrupt balanced mapping method based on the current scheduling states of VCPUs. When the virtual I/O APIC of an SMP virtual machine needs to map a virtual interrupt into a VCPU of the virtual machine after receiving the virtual interrupt, a part of VCPUs in the active state are analyzed according to the scheduling states of all VCPUs of the current VM in a VMM scheduler, and the virtual interrupt is mapped into the active VCPUs to obtain lower interrupt processing delay. If a plurality of VCPUs are in the active state simultaneously, the interrupt load of each active VCPU is considered further, and the interrupt is mapped into the active VCPU with the current lowest current load to further ensure balancing of interrupt processing loads of all VCPUs, and therefore, the loads of VCPUs in the SPMP structure are more symmetrical to promote balancing of the overall performance of all VCPUs in the SMP structure.

Method for dynamic interrupt balanced mapping based on current scheduling states of VCPUs

The present invention discloses a method for allocating processor resources precisely by means of predictive scheduling based on current credits, wherein the run queue of the Credit scheduler comprises virtual central processing units (VCPUs) with UNDER priority located at the head of the queue, VCPUs with OVER priority, VCPUs with IDLE priority located at the end of the queue and a wait queue for saving all VCPUs with overdrawn credits. Based on credit values of VCPUs, the method predicts the time of the credit overdrawing, and sets a timer which is triggered after the time to notify the Credit scheduler to stop scheduling corresponding VCPU. Thus the method effectively controls credit consumption and achieves the object of precise allocation of processor resources. The method is suitable to multi-core environment, and is also capable of reserving the advantages of the existing Credit scheduler, which are quick response for small task loads and load balancing.

Growing community of inventors

Shanghai, China

Haibing Guan