CN101561769A - Process migration tracking method based on multi-core platform virtual machine - Google Patents
Process migration tracking method based on multi-core platform virtual machine Download PDFInfo
- Publication number
- CN101561769A CN101561769A CN 200910084822 CN200910084822A CN101561769A CN 101561769 A CN101561769 A CN 101561769A CN 200910084822 CN200910084822 CN 200910084822 CN 200910084822 A CN200910084822 A CN 200910084822A CN 101561769 A CN101561769 A CN 101561769A
- Authority
- CN
- China
- Prior art keywords
- operating system
- processor
- client operating
- virtual machine
- machine monitor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Abstract
The invention relates to a process migration tracking method, in particular to a process migration tracking method in a client operating system of a virtual machine based on a multi-core platform. By tracking process migration as a target, through twice mapping, the method spans a monitor of the virtual machine to monitor a relation between a process and a physical processor inner core in the client operating system. The method comprises the following steps: firstly, finding out a running environment of each process in the client operating system, and extracting information associated with the processor from the running environment; secondly, starting from the inner core of the client operating system, transmitting the relation between each process and a virtual processor number to the monitor of the virtual machine through a communication mechanism; and finally, in the monitor of the virtual machine, acquiring a mapping relation between the virtual processor number and the number of the physical processor inner core so as to map the process in the client operating system to the physical processor inner core, and repeating the process, continuously acquiring the corresponding information of each moment, namely spanning the monitor of the virtual machine to associate the client operating system and the physical processor inner core so as to achieve the aim of tracking the migration process of the client operating system between the physical processor inner cores.
Description
Technical field
The present invention relates to a kind of tracking of the process migration based on virtual machine, particularly relate to a kind of tracking based on process migration in the virtual machine client operation system of multi-core platform.
Background technology
Along with the progress of hardware technology, polycaryon processor becomes more and more popular now, and price is also more and more cheap.As topmost two big processor manufacturers in the world, Intel and AMD have issued 4 core processors towards domestic consumer respectively.Simultaneously, virtual as a generalized concept, a kind of abstract for computer resource described, it can be understood as a kind of framework or theory is partitioned into a plurality of computing environment that can independently carry out with computer resource, and they are divided and create by virtual machine monitor (Virtual Machines Monitor-VMM) or virtual environment (Virtual Environments-VEs) on a physical server hardware.But polycaryon processor and Intel Virtualization Technology all have their born weakness, the present theme that the research concern is seldom arranged the two combination, and in fact this method can be good at bringing into play their advantages separately and counteracting defective separately.With the two in conjunction with and create a kind of brand-new virtual machine structure based on multinuclear, and some specific functions of virtual machine monitor are assigned to specific kernel, this structure is also considered to operate in the process classification in the client operating system and they is bundled on the corresponding physical kernel, with these methods with the higher performance of expectation acquisition.In order to verify the such expectation and the validity of binding mechanism, we need a kind of method to obtain and monitor the process in the client operating system and the mapping relations of processor physics kernel, reflect the transition process of process on processor cores of client operating system with these information.We have proposed a kind of like this method, and its realization is to finish by the cooperation of the kernel of client operating system and virtual machine monitor.
Some relevant work are arranged at present, and they all are used for the state of supervisory system.Simultaneously in (SuSE) Linux OS, root directory under / real-time information that the proc file also can provide a lot of useful files to come the reflection system to move.The instrument Torsmo of the common exploitation of Hannu and Lauri can the video-stream processor operation and situation and its similar instrument of dormancy also have conky.Sysstat (http://pagesperso-orange.fr) can obtain the comprehensive information of processor, for example global information, the information of each kernel and virtual support technology.The team develops of Hisham Muhammad instrument htop, be similar to the order top of Linux, it is a kind of interactively process scan tool.But, these instruments all can not be concerned about the relation of the processor cores that how to reflect process and its operation place, the transition process of monitoring process on processor cores said nothing of and crossed over this level of virtual machine monitor and removed to reflect process in the client operating system and mapping relations between the processor physics kernel and transition process.These aspects are but more paid close attention in our work, in the hope of intactly reacting and monitor the process of crossing over virtual machine manager and the corresponding relation of processor.
Summary of the invention
The present invention is a target with the trace daemon migration, by twice mapping, cross over this level of virtual machine monitor and reach process in the monitoring client operating system and the relation between the concurrent physical processor kernel, follow the tracks of the process that the process of client operating system is moved on the concurrent physical processor kernel.Specifically comprise:
1. in client operating system, find control table, therefrom obtain the inlet of plan.Travel through this plan, find the process image of the runtime environment of each process of expression also therefrom to extract the information relevant with the process scheduling result with processor.
2. from client operating system nucleus, be delivered in the virtual machine monitor by the information with the virtual processor number corresponding relation of communication mechanism with each process.
3. in virtual machine monitor, obtain the mapping relations of virtual processor number and concurrent physical processor kernel numbering, and the process of client operating system and the corresponding relation of virtual processor be connected, promptly the process in the client operating system can be corresponded on the concurrent physical processor kernel.
4. repeat this process, obtain the relation of each moment client operating system process and concurrent physical processor kernel correspondence, promptly can reach the purpose of process transition process on the concurrent physical processor kernel of following the tracks of client operating system.
Compared with prior art, innovation part of the present invention is: cross over this one deck of virtual machine monitor, the process in the client operating system is mapped on the concurrent physical processor kernel.Be embodied in:
1. not only pay close attention to the corresponding relation and the transition process of client operating system and virtual processor or virtual processor and concurrent physical processor kernel, but the process and the concurrent physical processor kernel of the client operating system of communication virtual machine monitor both sides, find their corresponding relation, cross over this level trace daemon migration between the concurrent physical processor kernel of virtual machine monitor.
2. by this method, the process of the evaluation virtual machine monitor scheduling client operating system that can quantize and the result of virtual processor, show the situation of virtual machine monitor, from the performance and the performance of a side checking virtual machine monitor to the utilization factor of physical hardware resources.
Description of drawings
The system architecture of Fig. 1 processor mapping
Fig. 2 process image
The general structure of control table and plan in Fig. 3 operating system
Mutual between Fig. 4 client operating system and the virtual machine monitor
Structure cpu_info among Fig. 5 Xen Hypervisor
Embodiment
Of the present inventionly be implemented in (SuSE) Linux OS and increase income and carry out among the virtual machine monitor Xen Hypervisor, the client operating system among the Xen Hypervisor is similarly Linux.Consult Fig. 1, finish three steps of process need of whole trace daemon migration, at first, from (SuSE) Linux OS, obtain the information of corresponding relation between process and the virtual processor as client operating system, then, between client operating system Linux and virtual machine monitor Xen Hypervisor, set up an event channel, the information of process and virtual processor corresponding relation is sent to virtual machine monitor Xen Hypervisor from client operating system Linux, at last, in virtual machine monitor Xen Hypervisor, obtain the corresponding relation of virtual processor vCPU and concurrent physical processor kernel CPU, corresponding relation with process among the client operating system Linux and virtual processor vCPU is connected mapping with it again, obtain process among the client operating system Linux and the corresponding relation of concurrent physical processor kernel CPU, repeat this process, each corresponding informance constantly will be obtained continuously, promptly crossed over this level of virtual machine monitor Xen Hypervisor, make and internuclearly in client operating system and the concurrent physical processor carried out relatedly, reach the purpose of process transition process between the concurrent physical processor kernel of following the tracks of client operating system.
The process of process and virtual processor vCPU corresponding relation of obtaining is carried out in client operating system Linux.In any operating system, process is the example of program, and it comprises sequence of program instructions.On forming, process can be regarded the inlet of some element sets as.These elements comprise process number, process status, process priority, programmable counter, main memory pointer, context environmental and I/O information or the like.Process of these information unique identifications provides the foundation of differentiation for operating system control process.Operating system needs to be grasped the situation of process and the distribution condition of system resource.The data that process must comprise a series of executable programs at least and be associated, process also needs some necessary storage space to preserve these programs and data.Simultaneously, process also needs a block storage space to come calling of tracing process as stack, and is last, and it is that operating system control is used that process also has a series of information.In realization, operating system is included in these control informations in the data structure, is called process control block (PCB) (Process Control Block-PCB), and it is along with the establishment of process is created.The integral body of program, data, stack and PCB is called process image (Process Image), and the structure of process image is consulted Fig. 2.For the managing process reflection, operating system is placed on them in the plan of a queue structure usually.Process image is the runtime environment of process, and along with the operation and the scheduling of process, its attribute can change, and new runtime environment has also just produced.
Method in common is that main memory, equipment, file and progress information are deposited in control table of maintenance in the modern operating system.Inlet from control table begins, and operating system just can obtain the position of plan in storer.Information and when from the kernel of client operating system, obtaining the operation of process from wherein extracting information about process scheduling and processor distribution, need find control table in the operating system, therefrom obtain the inlet of plan, travel through this table, find the runtime environment of each process and extract the information that wherein is associated with processor.In most of operating systems, process control block (PCB) has comprised a lot of important information, can be divided three classes 1 basically) process identity information; 2) processor state information; 3) process control information.By analysis, the information of the processor cores numbering at a process operation place can find in two category informations of back.In the kernel source code of (SuSE) Linux OS, such information leaves in the cpu field among the structure thread_info.In other operating systems, these information may exist with other forms, and the specific implementation of this and this operating system is relevant.The general structure of control table and plan is consulted Fig. 3 in the modern operating system.
In order to realize this purpose, need in client operating system Linux, write a kernel module, the function of this module is to find and process list that Ergodic Theory is current and the processor cores numbering at place when extracting each process operation.After the compiling module loading is arrived system kernel, this module can be registered a file task_cpu and the information that obtains is write in this file in (SuSE) Linux OS/proc file.
The Ergodic Theory current process list can obtain by grand for_each_process (p), and the parameter p that type of these grand needs is task_struct, grand process are replaced becomes a for circulation,
for(p＝&init_task；(p＝next_task(p))！＝&init_task；)
， ﹠amp wherein; Init_task is the address of No. 0 process init, obtain the task_struct structure pointer p of each process successively by traversal process chained list, information when each task_struct structure has been preserved the current operation of process, the pointer stack of one of them thread_info type, what preserve among the stack is the thread_info structure of this task_struct correspondence, stack obtains thread_info and visit field cpu wherein by coercion of type conversion visit, just can obtain the numbering of the place processor cores of the current operation of process.
((struct?thread_info*)(p)-＞stack)-＞cpu
Simultaneously in client operating system, write a program with Python, read file/proc/task_cpu, and the content of reading sent to the domain0 at virtual machine monitor place, domain0 has promptly obtained the task_vcpu that concerns of the process of domainU and virtual processor vCPU correspondence.
Virtual machine monitor can be defined as the virtual coprocessor number that each client operating system distributes in initialized process, consider the problem of performance, the virtual coprocessor number of generally distributing to client operating system should be less than the quantity of concurrent physical processor kernel.In operational process, client operating system can be dispatched virtual processor, and course allocation is moved to virtual processor.In virtual machine monitor inside, it can change the corresponding relation of virtual processor and concurrent physical processor kernel dynamically by current situation, this corresponding relation is set up in virtual machine monitor, each is associated the corresponding relation of such relation and process that obtains and virtual processor constantly with the corresponding relation of virtual processor and concurrent physical processor kernel, obtain the corresponding relation of process in the client operating system and concurrent physical processor kernel numbering.
Obtain the corresponding relation of virtual processor vCPU and concurrent physical processor kernel CPU, the process that again corresponding relation of process among the client operating system Linux and virtual processor vCPU is connected mapping with it is carried out in virtual machine monitor Xen Hypervisor.In Xen Hypervisor, structure cpu_info has embodied the corresponding relation about virtual processor and concurrent physical processor kernel.Consult Fig. 5, cpu_info has comprised the numbering and the virtual processor minor structure of current concurrent physical processor kernel as can be seen, and the numbering of virtual processor is present in the vcpu_struct minor structure.We just can capture the corresponding relation between them by this data structure.In virtual machine monitor Xen Hypervisor, can use xend interface and hypervisor to engage in the dialogue and obtain this corresponding relation.Xend provides the interface of most of Xen management functions, and it receives the request of user's space, directly communicates by letter with the hypervisor kernel.The virtual processor vCPU numbering that shows among Fig. 5 and the corresponding relation of concurrent physical processor kernel CPU numbering can obtain by interface server.xend.domain.getVCPUInfo, as long as specify the client operating system domainU that needs inquiry, import it into server.xend.domain.getVCPUInfo as parameter, perhaps pass through the method map (func of Python, target), server.xend.domain.getVCPUInfo and domainU are passed to map () method as the value of parameter f unc and target, just can obtain all information about the virtual processor of this domainU, these information are represented by the mode of Python tabulation, form tissue with [key, value].Be the numbering that the value value of key correspondence is virtual processor and the concurrent physical processor kernel of this domainU wherein with number and CPU.The interface that provides by Python promptly can obtain corresponding information from tabulation, obtain between each virtual processor vCPU of current domainU and the concurrent physical processor kernel CPU corresponding lists vcpu_list.
The process that the information of client operating system Linux process and virtual processor vCPU corresponding relation is sent to virtual machine monitor Xen Hypervisor from client operating system Linux is cooperated to finish by client operating system Linux and virtual machine monitor Xen Hypervisor.Virtual machine monitor Xen Hypervisor sets up an event channel and client operating system Linux is connected, and beginning virtual machine monitor XenHypervisor and client operating system Linux are in listening state.Virtual machine monitor Xen Hypervisor transfers active state to then, and after this request that sends goes back to listening state to client operating system Linux.Client operating system Linux receives request, transfers active state to, by obtaining process and the corresponding relation between the virtual processor vCPU the client operating system Linux from kernel module and preserving.Its information that needs of client operating system Linux response virtual machine monitor Xen Hypervisor obtains after finishing, and goes back to listening state.Virtual machine monitor Xen Hypervisor receives the echo message of client operating system Linux, transfers active state to, obtains process and the corresponding relation task_vcpu between the virtual processor vCPU of client operating system Linux and goes back to listening state.Complete communication process is consulted Fig. 4.
In realization, the communication between Xen Hypervisor and the client operating system Linux is connected by a socket to be finished.In XenHypervisor, the request of all high levels all is translated into the incident of bottom and transmits by event channel, so these socket communications are also finished by case mechanism at bottom.When Xen Hypervisor at first sends request to client operating system, read the tabulation of process and virtual processor corresponding relation after client operating system obtains asking and be connected information is sent to Xen Hypervisor by socket, Xen Hypervisor receive these message subsequently and obtain virtual processor and the concurrent physical processor kernel between corresponding relation, shine upon at last, obtain the process in the client operating system and the corresponding relation of concurrent physical processor kernel, it is inferior to reach the leap virtual machine monitor layer, the purpose that the process of tracking client operating system is moved between the concurrent physical processor kernel.
Claims (9)
1, a kind of process migration tracking method of the virtual machine based on multi-core platform may further comprise the steps:
Information and from wherein extracting information when (1) from the kernel of client operating system, obtaining the operation of process about process scheduling and processor distribution;
(2) will from the kernel of client operating system, be delivered in the virtual machine monitor about the information of process scheduling and processor distribution;
(3), obtain in the client operating system corresponding relation of processor cores numbering on the virtual processor and physical hardware by virtual machine monitor;
(4) in virtual machine monitor, the information of processor cores corresponding relation on the information of process scheduling and processor distribution and virtual processor and the physical hardware is associated, obtain the corresponding relation of process in the client operating system and concurrent physical processor kernel numbering, the process in the client operating system of monitoring internuclear migration in concurrent physical processor;
It is characterized in that:
Information and comprise during the described operation that from the kernel of client operating system, obtains process: 1) find control table the operating system, therefrom obtain the inlet of plan from the step of wherein extracting about the information of process scheduling and processor distribution; 2) travel through this table, find the runtime environment of each process and extract the information that wherein is associated with processor;
The described step that will be delivered in the virtual machine monitor from the kernel of client operating system about the information of process scheduling and processor distribution comprises:
1) virtual machine monitor is at first set up an event channel, sends a request to client operating system then; 2) client operating system receives this request, obtains the relation between process and the virtual processor, and they are kept in main memory or the file; 3) client operating system is set up an event channel and is responded virtual machine monitor, informs that its information obtains; 4) virtual machine monitor meets with a response, and obtains the information from client operating system;
Described by virtual machine monitor, obtain in the client operating system that the step of the corresponding relation of processor cores numbering comprises on the virtual processor and physical hardware: 1) the process storehouse in client space corresponds to kernel process with client process; 2) client operating system nucleus corresponds to virtual processor with kernel process; 3) virtual machine monitor is assigned to the concurrent physical processor kernel with virtual processor.
Described in virtual machine monitor, the information of processor cores corresponding relation on the information of process scheduling and processor distribution and virtual processor and the physical hardware is associated, obtain the relation of process in the client operating system and concurrent physical processor kernel numbering, monitor that the process step of internuclear migration in concurrent physical processor in the client operating system comprises: virtual machine monitor is associated the relation of process in the client operating system that obtains and virtual processor kernel with the corresponding relation of virtual processor that obtains and concurrent physical processor kernel, obtain the relation of process in the client operating system and concurrent physical processor kernel numbering, the process in the client operating system of monitoring internuclear migration in concurrent physical processor.
2, method according to claim 1, it is characterized in that: information and from wherein extract step 1) when from the kernel of client operating system, obtaining the operation of process about the information step of process scheduling and processor distribution, process is regarded the inlet of some element sets as, these elements comprise process number, process status, process priority, programmable counter, main memory pointer, context environmental and I/O information, process of these information unique identifications.
3, according to claim 1 and 2 described methods, it is characterized in that: will from the kernel of client operating system, be delivered in the step 1) of step in the virtual machine monitor about the information of process scheduling and processor distribution, virtual machine monitor is set up an event channel, be connected with client operating system, this moment, virtual machine monitor was in listening state, virtual machine monitor transfers active state to and sends request to client operating system, after this goes back to listening state.
4, according to the described method of claim 1-3, it is characterized in that: will from the kernel of client operating system, be delivered to the step 2 of step in the virtual machine monitor about the information of process scheduling and processor distribution) in, client operating system receives request at listening state, transfer active state to, obtain the relation between process and the virtual processor, they are kept in main memory or the file.
5, according to the described method of claim 1-4, it is characterized in that: will from the kernel of client operating system, be delivered in the step 3) of step in the virtual machine monitor about the information of process scheduling and processor distribution, client operating system transfers active state to, respond virtual machine monitor, after virtual machine monitor was received response, client operating system went back to listening state.
6, method according to claim 1, it is characterized in that: will from the kernel of client operating system, be delivered in the step 4) of step in the virtual machine monitor about the information of process scheduling and processor distribution, virtual machine monitor is received the echo message of client operating system, transfer active state to, acceptance also obtains the process of client operating system and the corresponding relation between the virtual processor, after this transfers listening state to.
7, method according to claim 1, it is characterized in that: pass through virtual machine monitor, obtain in the client operating system on the virtual processor and physical hardware in the step 1) of the relationship step of processor cores numbering, virtual machine monitor is defined as the virtual coprocessor number that each client operating system distributes in initialized process, distribute to the quantity of the virtual coprocessor number of client operating system less than the concurrent physical processor kernel.
8, method according to claim 1, it is characterized in that: pass through virtual machine monitor, obtain in the client operating system step 2 of the relationship step of processor cores numbering on the virtual processor and physical hardware) in, client operating system scheduling virtual processor moves course allocation to virtual processor.
9, method according to claim 1, it is characterized in that: pass through virtual machine monitor, obtain in the client operating system on the virtual processor and physical hardware in the step 3) of the relationship step of processor cores numbering, virtual machine monitor changes the corresponding relation of virtual processor and concurrent physical processor kernel dynamically by current situation, and this corresponding relation is set up in virtual machine monitor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200910084822 CN101561769B (en) | 2009-05-25 | 2009-05-25 | Process migration tracking method based on multi-core platform virtual machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200910084822 CN101561769B (en) | 2009-05-25 | 2009-05-25 | Process migration tracking method based on multi-core platform virtual machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101561769A true CN101561769A (en) | 2009-10-21 |
| CN101561769B CN101561769B (en) | 2013-02-13 |
Family
ID=41220581
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 200910084822 Expired - Fee Related CN101561769B (en) | 2009-05-25 | 2009-05-25 | Process migration tracking method based on multi-core platform virtual machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101561769B (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101859263A (en) * | 2010-06-12 | 2010-10-13 | 中国人民解放军国防科学技术大学 | Quick communication method between virtual machines supporting online migration |
| CN102411510A (en) * | 2011-09-16 | 2012-04-11 | 华为技术有限公司 | Method and device for mapping service data streams on virtual machines of multi-core processor |
| CN103139167A (en) * | 2011-11-30 | 2013-06-05 | 中兴通讯股份有限公司 | Virtual site associating method and device during virtual site migration |
| CN103491118A (en) * | 2012-06-12 | 2014-01-01 | 中国移动通信集团公司 | Method and system for service node distribution in communication network |
| CN103514076A (en) * | 2013-09-11 | 2014-01-15 | 深圳市共进电子股份有限公司 | Application layer process monitoring method |
| CN103620558A (en) * | 2013-05-21 | 2014-03-05 | 华为技术有限公司 | A method for achieving correspondence of physical resource and virtual resource and a basic input output system |
| CN104050030A (en) * | 2014-05-30 | 2014-09-17 | 汉柏科技有限公司 | Operating system process scheduling method |
| CN104216758A (en) * | 2014-08-22 | 2014-12-17 | 华为技术有限公司 | Read and write operation performance optimization method and device |
| CN104331322A (en) * | 2014-10-24 | 2015-02-04 | 华为技术有限公司 | Process migration method and device |
| CN104714846A (en) * | 2013-12-17 | 2015-06-17 | 华为技术有限公司 | Resource processing method, operating system and equipment |
| WO2015188649A1 (en) * | 2014-06-12 | 2015-12-17 | 华为技术有限公司 | Method of mapping between virtual cpu and physical cpu, and electronic device |
| CN105653361A (en) * | 2014-12-01 | 2016-06-08 | 联发科技股份有限公司 | Execution environment and multicore processor system |
| CN105653347A (en) * | 2014-11-28 | 2016-06-08 | 杭州华为数字技术有限公司 | Server, resource management method and virtual machine manager |
| CN105940375A (en) * | 2014-03-06 | 2016-09-14 | 英特尔公司 | Dynamic reassignment for multi-operating system devices |
| CN107818054A (en) * | 2016-09-12 | 2018-03-20 | 联发科技股份有限公司 | Distribute method and system of the continuous physical memory space to equipment |
| CN108897598A (en) * | 2018-06-13 | 2018-11-27 | 南京享达汉辰网络科技有限公司 | A kind of virtual machine Autonomic Migration Framework system and method for optimization |
| CN109101318A (en) * | 2014-03-12 | 2018-12-28 | 华为技术有限公司 | A kind of virtual machine (vm) migration control method and device |
| CN109739612A (en) * | 2018-11-22 | 2019-05-10 | 海光信息技术有限公司 | Dispatching method, device, equipment and the storage medium of virtual machine process |
| CN110362405A (en) * | 2019-07-02 | 2019-10-22 | Oppo广东移动通信有限公司 | Thread distribution method, device, equipment and the readable storage medium storing program for executing of application program |
| CN110888771A (en) * | 2018-12-26 | 2020-03-17 | 北京安天网络安全技术有限公司 | Method and device for monitoring and analyzing process, electronic equipment and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100472452C (en) * | 2006-06-23 | 2009-03-25 | 联想(北京)有限公司 | Method for switching a system of virtual machine and hardware devices |
| CN101403983B (en) * | 2008-11-25 | 2010-10-13 | 北京航空航天大学 | Resource monitoring method and system for multi-core processor based on virtual machine |
-
2009
- 2009-05-25 CN CN 200910084822 patent/CN101561769B/en not_active Expired - Fee Related
Cited By (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101859263A (en) * | 2010-06-12 | 2010-10-13 | 中国人民解放军国防科学技术大学 | Quick communication method between virtual machines supporting online migration |
| CN101859263B (en) * | 2010-06-12 | 2012-07-25 | 中国人民解放军国防科学技术大学 | Quick communication method between virtual machines supporting online migration |
| CN102411510A (en) * | 2011-09-16 | 2012-04-11 | 华为技术有限公司 | Method and device for mapping service data streams on virtual machines of multi-core processor |
| CN103139167A (en) * | 2011-11-30 | 2013-06-05 | 中兴通讯股份有限公司 | Virtual site associating method and device during virtual site migration |
| CN103139167B (en) * | 2011-11-30 | 2017-12-12 | 温州大学 | A kind of method and apparatus for associating virtual site during virtual site migration |
| CN103491118A (en) * | 2012-06-12 | 2014-01-01 | 中国移动通信集团公司 | Method and system for service node distribution in communication network |
| CN103620558A (en) * | 2013-05-21 | 2014-03-05 | 华为技术有限公司 | A method for achieving correspondence of physical resource and virtual resource and a basic input output system |
| CN103514076A (en) * | 2013-09-11 | 2014-01-15 | 深圳市共进电子股份有限公司 | Application layer process monitoring method |
| US10180843B2 (en) | 2013-12-17 | 2019-01-15 | Huawei Technologies Co., Ltd. | Resource processing method and device for a multi-core operating system |
| CN104714846A (en) * | 2013-12-17 | 2015-06-17 | 华为技术有限公司 | Resource processing method, operating system and equipment |
| WO2015090197A1 (en) * | 2013-12-17 | 2015-06-25 | 华为技术有限公司 | Resource processing method, operating system, and device |
| CN104714846B (en) * | 2013-12-17 | 2018-06-05 | 华为技术有限公司 | Method for processing resource, operating system and equipment |
| RU2639693C1 (en) * | 2013-12-17 | 2017-12-21 | Хуавэй Текнолоджиз Ко., Лтд. | Method for resource processing, operating system and device |
| CN105940375B (en) * | 2014-03-06 | 2020-12-01 | 英特尔公司 | Dynamic reassignment for multiple operating system devices |
| CN105940375A (en) * | 2014-03-06 | 2016-09-14 | 英特尔公司 | Dynamic reassignment for multi-operating system devices |
| CN109101318A (en) * | 2014-03-12 | 2018-12-28 | 华为技术有限公司 | A kind of virtual machine (vm) migration control method and device |
| CN104050030A (en) * | 2014-05-30 | 2014-09-17 | 汉柏科技有限公司 | Operating system process scheduling method |
| CN105242954A (en) * | 2014-06-12 | 2016-01-13 | 华为技术有限公司 | Mapping method between virtual CPUs (Central Processing Unit) and physical CPUs, and electronic equipment |
| US10216530B2 (en) | 2014-06-12 | 2019-02-26 | Huawei Technologies Co., Ltd. | Method for mapping between virtual CPU and physical CPU and electronic device |
| WO2015188649A1 (en) * | 2014-06-12 | 2015-12-17 | 华为技术有限公司 | Method of mapping between virtual cpu and physical cpu, and electronic device |
| CN104216758B (en) * | 2014-08-22 | 2018-05-04 | 华为技术有限公司 | A kind of read-write operation performance optimization method and device |
| CN104216758A (en) * | 2014-08-22 | 2014-12-17 | 华为技术有限公司 | Read and write operation performance optimization method and device |
| CN104331322A (en) * | 2014-10-24 | 2015-02-04 | 华为技术有限公司 | Process migration method and device |
| CN104331322B (en) * | 2014-10-24 | 2018-03-13 | 华为技术有限公司 | A kind of process migration method and apparatus |
| CN105653347B (en) * | 2014-11-28 | 2019-06-07 | 杭州华为数字技术有限公司 | A kind of server, method for managing resource and virtual machine manager |
| CN105653347A (en) * | 2014-11-28 | 2016-06-08 | 杭州华为数字技术有限公司 | Server, resource management method and virtual machine manager |
| CN105653361A (en) * | 2014-12-01 | 2016-06-08 | 联发科技股份有限公司 | Execution environment and multicore processor system |
| CN107818054A (en) * | 2016-09-12 | 2018-03-20 | 联发科技股份有限公司 | Distribute method and system of the continuous physical memory space to equipment |
| CN108897598A (en) * | 2018-06-13 | 2018-11-27 | 南京享达汉辰网络科技有限公司 | A kind of virtual machine Autonomic Migration Framework system and method for optimization |
| CN109739612A (en) * | 2018-11-22 | 2019-05-10 | 海光信息技术有限公司 | Dispatching method, device, equipment and the storage medium of virtual machine process |
| CN109739612B (en) * | 2018-11-22 | 2021-10-26 | 海光信息技术股份有限公司 | Scheduling method, device, equipment and storage medium of virtual machine process |
| CN110888771A (en) * | 2018-12-26 | 2020-03-17 | 北京安天网络安全技术有限公司 | Method and device for monitoring and analyzing process, electronic equipment and storage medium |
| CN110362405A (en) * | 2019-07-02 | 2019-10-22 | Oppo广东移动通信有限公司 | Thread distribution method, device, equipment and the readable storage medium storing program for executing of application program |
| CN110362405B (en) * | 2019-07-02 | 2023-06-20 | Oppo广东移动通信有限公司 | Thread allocation method, device and equipment of application program and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101561769B (en) | 2013-02-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101561769B (en) | Process migration tracking method based on multi-core platform virtual machine | |
| CN104854563B (en) | What resource used automatically analyzes | |
| CN100533387C (en) | System and method for executing job step | |
| CN102902512B (en) | A kind of multi-threading parallel process method based on multi-thread programming and message queue | |
| Raicu et al. | Middleware support for many-task computing | |
| US9250886B2 (en) | Optimizing provisioning workflows in cloud computing | |
| Cheng et al. | Heterogeneity-aware workload placement and migration in distributed sustainable datacenters | |
| US20080244611A1 (en) | Product, method and system for improved computer data processing capacity planning using dependency relationships from a configuration management database | |
| CN105653372B (en) | The method for realizing multiple virtualization mixed management and scheduling based on cloud platform | |
| US20170255890A1 (en) | Methods and systems to optimize operating system license costs in a virtual data center | |
| CN102073535B (en) | Hardware counter virtualization-based performance analysis method for multiple virtual machines | |
| CN102521052B (en) | Resource allocation method of virtualized data center and virtual machine monitor | |
| CN109144710A (en) | Resource regulating method, device and computer readable storage medium | |
| US9501313B2 (en) | Resource management and allocation using history information stored in application's commit signature log | |
| US20160203424A1 (en) | Information technology cost calculation in a software defined data center | |
| CN104243617A (en) | Task scheduling method and system facing mixed load in heterogeneous cluster | |
| CN102567077A (en) | Virtualized resource distribution method based on game theory | |
| Pongsakorn et al. | Container rebalancing: Towards proactive linux containers placement optimization in a data center | |
| Han et al. | Refining microservices placement employing workload profiling over multiple kubernetes clusters | |
| US11886898B2 (en) | GPU-remoting latency aware virtual machine migration | |
| Lee et al. | Shard manager: A generic shard management framework for geo-distributed applications | |
| CN108268546A (en) | A kind of method and device for optimizing database | |
| Liu et al. | High-responsive scheduling with MapReduce performance prediction on hadoop YARN | |
| Bansal et al. | A framework for performance analysis and tuning in hadoop based clusters | |
| Gehr et al. | Measuring fragmentation of two-dimensional resources applied to advance reservation grid scheduling |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20130213 Termination date: 20140525 |