CN107967168B - Virtual machine integration method based on shared memory page in cloud data center - Google Patents
Virtual machine integration method based on shared memory page in cloud data center Download PDFInfo
- Publication number
- CN107967168B CN107967168B CN201711293781.8A CN201711293781A CN107967168B CN 107967168 B CN107967168 B CN 107967168B CN 201711293781 A CN201711293781 A CN 201711293781A CN 107967168 B CN107967168 B CN 107967168B
- Authority
- CN
- China
- Prior art keywords
- virtual machines
- virtual
- machines
- physical
- virtual machine
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
- G06F9/5033—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering data affinity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/4557—Distribution of virtual machine instances; Migration and load balancing
Abstract
The invention discloses a virtual machine integration method based on shared memory pages in a cloud data center. The method utilizes the similarity between the memory contents of the virtual machines when the virtual machines are integrated into the physical machines, and greatly reduces the memory data volume required to be transmitted when the virtual machines are thermally migrated while using a small number of physical machines, thereby improving the utilization rate of physical resources in the cloud data center.
Description
Technical Field
The invention relates to a method for integrating virtual machines in a cloud data center, in particular to a virtual machine integration method based on a shared memory page in the cloud data center.
Background
At present, cloud computing gradually goes out of a stage of emerging technology, and more users are in the arms of cloud computing services. With the large-scale increase of the number of users, the size of each cloud data center is also expanded by adding servers. How to effectively utilize a large-scale physical server is a big problem faced by a cloud data center. Through the virtual machine live migration, the cloud data center can transfer the virtual machine from the physical machine with the physical resources being excessively used to the physical machine with the physical resources not being fully used without interrupting the service. Through the migration of the virtual machines, the load of the cloud data center is balanced, and physical resources can be more effectively utilized.
In the process of virtual machine live migration, a great challenge is faced, namely, a virtual machine integration problem is that how to select a proper physical machine for each virtual machine to be placed can only install a batch of virtual machines by using a minimum number of physical machines, given a group of virtual machines to be migrated. The smaller the number of physical machines used, the higher the physical resource utilization in the cloud data center.
On the other hand, when the virtual machine is migrated, a large amount of memory data needs to be transmitted between different physical machines through the network, which causes problems of long migration time and high network pressure. Such a situation may further lead to a problem of a substantial degradation of the cloud service user experience.
In order to integrate the above two aspects, a virtual machine integration algorithm capable of reducing data transmission amount in the migration process needs to be researched.
Research finds that great similarity exists between the memory contents of the virtual machines. The memory of the virtual machine is stored by taking a memory page as a basic unit. From the perspective of the memory pages, it is observed that many memory pages are identical or similar between virtual machines using the same or similar operating systems and the same application software. By utilizing the property, the memory amount of the virtual machine, which needs to be transmitted in the process of virtual machine live migration, can be greatly reduced: when a plurality of virtual machines are migrated to one physical machine, the same memory page is only required to be transmitted once.
There have been several achievements on the problem of virtual machine placement during migration using similarities between the memory contents of virtual machines, such as Greedy-Flow algorithm, SAVMP algorithm, G-msapm algorithm, but they all have some drawbacks. When a target physical machine is selected for one virtual machine to be migrated, the Greedy-Flow algorithm selects the physical machine with the largest memory content similarity with the target physical machine, but the virtual machine integration problem is ignored by the method. The SAVMP algorithm takes into account the similarity of the contents in the memory of the virtual machine while integrating the virtual machine, but does not take into account other resource constraints, such as CPU resources. The G-MSAMMS algorithm considers how one physical machine can be loaded with as many virtual machines as possible, and simultaneously utilizes the similarity of the memory contents of the virtual machines, but does not consider the situation that a plurality of target physical machines exist.
Therefore, it is still necessary to design a virtual machine integration method that can solve the above-mentioned deficiencies of the existing methods.
Disclosure of Invention
The invention solves the technical problem that aiming at the defects of the prior art, the invention provides a virtual machine integration method based on a shared memory page in a cloud data center, which utilizes the similarity between the memory contents of virtual machines when integrating the virtual machines to physical machines, can optimize the number of occupied physical machines in the process of live migration of the virtual machines in the cloud data center, and simultaneously greatly reduces the memory data volume required to be transmitted in the process of live migration of the virtual machines, thereby reducing the network pressure, shortening the migration time and improving the utilization rate of physical resources in the cloud data center.
The technical scheme provided by the invention for solving the technical problems is as follows:
a virtual machine integration method based on a shared memory page in a cloud data center comprises the following steps:
the method comprises the following steps: inputting a set P of n physical machines, a set V of m virtual machines to be migrated, wherein the total amount of available CPU resources and the total amount of storable virtual machine memory pages when the n physical machines are in no-load are respectively PC and PM; the available CPU resource amount of the first physical machine PM _ l is PC (PM _ l), the number of the storable memory pages is PM (PM _ l), the memory page set of the virtual machine stored on the first physical machine PM _ l is PM _ M (PM _ l), and l is 1,2, …, n; the CPU resource amount required by the kth virtual machine VM _ k is VC (VM _ k), the included memory page set is VM (VM _ k), and k is 1,2, …, m;
step two: arranging the physical machines in a descending order according to the available resource quantity to form a physical machine List PM _ List;
step three: recording a first physical machine in the PM _ List as PM1, recording a set of virtual machines to be migrated to the PM1 as T1, and initializing T1 as an empty set;
step four: judging whether the V is an empty set, if so, terminating the algorithm; if the V is not an empty set, entering a fifth step;
step five: correcting a memory page set VM (VM _ k) contained in each virtual machine in V into VM (VM _ k) \ PM _ M (PM1), namely, making VM (VM _ k) \ PM _ M (PM1), wherein a symbol \ represents a difference set of two sets, PM _ M (PM1) represents a virtual machine memory page set stored on a physical machine PM1, VM (VM _ k) \ PM _ M (PM1) represents a difference set of VM (VM _ k) and PM _ M (PM1), namely a memory page set contained by VM _ k relative to PM 1;
step six: setting the number i of newly added virtual machines which need to be migrated to the PM1, where i is set to 3 in this embodiment;
step seven: selecting a subset V' containing i virtual machines from V, so that the number of memory pages contained in the i virtual machines is minimum while PM1 has enough resources to run the i virtual machines; if the i virtual machines meeting the conditions cannot be found, enabling the V' to be an empty set;
step eight: judging whether V 'is an empty set, if not, merging V' into T1, then deleting V, and jumping to the fourth step; if V' is an empty set, entering the ninth step;
step nine: judging whether i is equal to 1, if not, making i equal to i-1 and jumping to the step seven; if i is equal to 1, entering a step ten;
step ten: migrating the virtual machine in T1 to PM 1; and deleting the PM1 from the PM _ List, and jumping to step three.
In the second step, the available resource amount calculating method is as follows:
wherein pm _ l represents the l-th physical machine pm _ l in the set P.
In the sixth step, setting i to 3 can ensure result accuracy and avoid larger time complexity of the algorithm.
In the seventh step, the method for judging whether the PM1 has enough resources to run the i virtual machines includes: PM1 has sufficient resources when the following two inequalities hold simultaneously:
wherein vc (vm) is the amount of CPU resources required by the virtual machine vm, vm (vm) is the memory page set included in the virtual machine vm, PC (PM1) is the amount of available CPU resources of the physical machine PM1, PM (PM1) is the number of memory pages storable by the physical machine PM1, and | | represents the number of pages in the set.
In the seventh step, the method for searching the i virtual machines with the minimum number of memory pages includes: solve so that
The minimum subset V ' is determined to be the i virtual machines with the minimum number of memory pages, where VM (V ') is a set of memory pages included in all virtual machines in the set V ', TM ═ VM (T1) $ PM _ M (PM1), VM (T1) is a set of virtual machine memory pages included in all virtual machines in T1, PM _ M (PM1) is a set of virtual machine memory pages stored on PM1, and | represents the number of pages in the set.
The invention greatly reduces the memory amount of the virtual machine required to be transmitted and the number of occupied physical machines during the thermal migration based on the following principles:
the memory of the virtual machine is stored in the memory of the physical machine by taking the memory page as a basic unit. There is a great similarity between the memory contents of different virtual machines, so many memory pages are the same between them. When the virtual machines are migrated in a live mode, if multiple virtual machines are migrated to one physical machine, the same memory page of the virtual machine only needs to be transmitted once. In addition, the target physical machines are arranged in descending order according to the available resource amount and are sequentially filled with the virtual machines, and the method can effectively reduce the number of the physical machines which are finally used.
Has the advantages that:
when the virtual machines are migrated in batch by the cloud data center, the available physical machines are firstly arranged in a descending order according to the available computing resource amount, and then a group of virtual machines with the least number of pages of the transmission memory are selected by computing the similarity among the memory contents to sequentially fill each physical machine under the condition of meeting the resource constraint until all the virtual machines are migrated. According to the invention, the similarity between the memory contents of the virtual machines is utilized when the virtual machines are integrated to the physical machines, so that the number of the occupied physical machines in the process of thermal migration of the virtual machines in the cloud data center can be optimized, and meanwhile, the memory data amount required to be transmitted in batch thermal migration of the virtual machines is greatly reduced, thereby improving the utilization rate of physical resources in the cloud data center. Experimental results show that the usage amount of the physical machine and the memory data amount required to be transmitted in the process of live migration of the virtual machine are less than those of the existing First-First virtual machine packing algorithm and green-Flow algorithm.
Drawings
FIG. 1 is a flow chart of the present invention.
FIG. 2 is a comparison of the number of physical machines used for each algorithm; fig. 2(a) - (d) are comparison of the number of physical machines used in the four cloud data centers for each algorithm, respectively.
FIG. 3 is a comparison of the number of pages of the virtual machine memory to be transmitted by each algorithm; fig. 3(a) - (d) are comparison of the number of virtual machine memory pages required to be transmitted in four cloud data centers for each algorithm, respectively.
In fig. 2-3, the algorithm proposed by the present invention is Greedy _ Hybrid, and compared with the algorithms greeny _ Flow and First _ Fit.
Detailed Description
The invention will be further described with reference to the accompanying drawings.
Referring to fig. 1, fig. 1 is a flow chart of the present invention. The process is as follows:
a virtual machine integration method based on a shared memory page in a cloud data center is characterized by comprising the following steps:
the method comprises the following steps: inputting a set P of n physical machines, a set V of m virtual machines to be migrated, wherein the total amount of available CPU resources and the total amount of storable virtual machine memory pages when the n physical machines are in no-load are respectively PC and PM; the available CPU resource amount of the first physical machine PM _ l is PC (PM _ l), the number of the storable memory pages is PM (PM _ l), the memory page set of the virtual machine stored on the first physical machine PM _ l is PM _ M (PM _ l), and l is 1,2, …, n; the CPU resource amount required by the kth virtual machine VM _ k is VC (VM _ k), the included memory page set is VM (VM _ k), and k is 1,2, …, m;
step two: arranging the physical machines in a descending order according to the available resource quantity to form a physical machine List PM _ List; the available resource amount calculation method of the ith physical machine pm _ l in P is as follows:
step three: recording a first physical machine in the PM _ List as PM1, recording a set of virtual machines to be migrated to the PM1 as T1, and initializing T1 as an empty set;
step four: judging whether the V is an empty set, if so, terminating the algorithm; if the V is not an empty set, entering a fifth step;
step five: correcting a memory page set VM (VM _ k) contained in each virtual machine in the V into a memory page set VM (VM _ k) \ PM _ M (PM1), namely, making the memory page set VM (VM _ k) \ PM _ M (PM1), wherein a symbol \ represents a difference set of the two sets, and the PM _ M (PM1) represents a virtual machine memory page set stored on a physical machine PM 1;
step six: setting the number i of newly added virtual machines needing to be migrated to PM1, wherein i is more than or equal to 1;
step seven: a subset V' of i virtual machines is selected from V, so that while PM1 has sufficient resources to run the i virtual machines,
minimum; if the i virtual machines meeting the conditions cannot be found, enabling the V' to be an empty set;
step eight: judging whether V 'is an empty set, if not, merging V' into T1, then deleting V, and jumping to the fourth step; if V' is an empty set, entering the ninth step;
step nine: judging whether i is equal to 1, if not, making i equal to i-1 and jumping to the step seven; if i is equal to 1, entering a step ten;
step ten: migrating the virtual machine in T1 to PM 1; remove PM1 from the PM List and go to step three.
In order to verify the effectiveness of the present invention, the present invention is implemented by a Matlab simulation platform and a performance test is performed.
In the performance test, 4 cloud data centers are simulated, and each cloud data center comprises 400 physical machines and 1000 virtual machines to be migrated. On each data center's physical machine, 500 virtual machines have been run randomly. 5 workloads were tested in the performance test: 1) randomly extracting 200 virtual machines from 1000 virtual machines for migration; 2) randomly extracting 400 virtual machines from 1000 virtual machines for migration; 3) randomly extracting 600 virtual machines from 1000 virtual machines for migration; 4) randomly extracting 800 virtual machines from 1000 virtual machines for migration; 5) all 1000 of the stations were removed at once. In which the workload in the first 4 is randomly drawn 10 times to run various algorithms for comparison.
As can be seen from fig. 2, greeny _ Hybrid uses a minimum number of physical machines to load virtual machines of various workloads in four cloud data centers, compared to the other two algorithms. As can be seen from fig. 3, in the four cloud data centers, compared with the other two algorithms, Greedy _ Hybrid can always transmit the least number of virtual machine memory pages, and the advantage of Greedy _ Hybrid gradually becomes more obvious as the size of the workload increases.
Claims (4)
1. A virtual machine integration method based on a shared memory page in a cloud data center is characterized by comprising the following steps:
the method comprises the following steps: inputting a set P of n physical machines, a set V of m virtual machines to be migrated, wherein the total amount of available CPU resources and the total amount of storable virtual machine memory pages when the n physical machines are in no-load are respectively PC and PM; the available CPU resource amount of the first physical machine PM _ l is PC (PM _ l), the number of the storable memory pages is PM (PM _ l), the memory page set of the virtual machine stored on the first physical machine PM _ l is PM _ M (PM _ l), and l is 1,2, …, n; the CPU resource amount required by the kth virtual machine VM _ k is VC (VM _ k), the included memory page set is VM (VM _ k), and k is 1,2, …, m;
step two: arranging the physical machines in a descending order according to the available resource quantity to form a physical machine List PM _ List;
step three: recording a first physical machine in the PM _ List as PM1, recording a set of virtual machines to be migrated to the PM1 as T1, and initializing T1 as an empty set;
step four: judging whether the V is an empty set, if so, terminating the algorithm; if the V is not an empty set, entering a fifth step;
step five: correcting a memory page set VM (VM _ k) contained in each virtual machine in the V into a memory page set VM (VM _ k) \ PM _ M (PM1), namely, making the memory page set VM (VM _ k) \ PM _ M (PM1), wherein a symbol \ represents a difference set of the two sets, and the PM _ M (PM1) represents a virtual machine memory page set stored on a physical machine PM 1;
step six: setting the number i of newly added virtual machines needing to be migrated to PM1, wherein i is more than or equal to 1;
step seven: selecting a subset V' containing i virtual machines from V, so that the number of memory pages contained in the i virtual machines is minimum while PM1 has enough resources to run the i virtual machines; if the i virtual machines meeting the conditions cannot be found, enabling the V' to be an empty set;
in the seventh step, the method for searching the i virtual machines with the minimum number of memory pages includes: solve so that
The minimum subset V ' is determined, i virtual machines contained in the subset V ' are i virtual machines with the minimum number of contained memory pages, wherein VM (V ') is a setIntegrating memory page sets contained in all virtual machines in V', TM ═ VM (T1) ═ PM _ M (PM1), VM (T1) is a set of virtual machine memory pages contained in all virtual machines in T1, PM _ M (PM1) is a set of virtual machine memory pages stored on PM1, and | represents the number of pages in the set;
step eight: judging whether V 'is an empty set, if not, merging V' into T1, then deleting V, and jumping to the fourth step; if V' is an empty set, entering the ninth step;
step nine: judging whether i is equal to 1, if not, making i equal to i-1 and jumping to the step seven; if i is equal to 1, entering a step ten;
step ten: migrating the virtual machine in T1 to PM 1; remove PM1 from the PM List and go to step three.
2. The method for integrating virtual machines based on shared memory pages in the cloud data center according to claim 1, wherein the method for calculating the available resource amount of the ith physical machine pm _ l in P comprises:
3. the method for integrating virtual machines based on shared memory pages in a cloud data center according to claim 1, wherein in the sixth step, i-3 is set.
4. The method according to claim 1, wherein in the seventh step, the method for determining whether the PM1 has enough resources to run the i virtual machines comprises: PM1 has sufficient resources when the following two inequalities hold simultaneously:
wherein vc (vm) is the amount of CPU resources required by the virtual machine vm, vm (vm) is the memory page set included in the virtual machine vm, PC (PM1) is the amount of available CPU resources of the physical machine PM1, PM (PM1) is the number of memory pages storable by the physical machine PM1, and | | represents the number of pages in the set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711293781.8A CN107967168B (en) | 2017-12-08 | 2017-12-08 | Virtual machine integration method based on shared memory page in cloud data center |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711293781.8A CN107967168B (en) | 2017-12-08 | 2017-12-08 | Virtual machine integration method based on shared memory page in cloud data center |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107967168A CN107967168A (en) | 2018-04-27 |
| CN107967168B true CN107967168B (en) | 2021-11-12 |
Family
ID=61998454
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711293781.8A Active CN107967168B (en) | 2017-12-08 | 2017-12-08 | Virtual machine integration method based on shared memory page in cloud data center |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107967168B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102103524A (en) * | 2010-12-23 | 2011-06-22 | 北京航空航天大学 | Memory redundancy oriented virtual machine migration device and method |
| CN102866915A (en) * | 2012-08-21 | 2013-01-09 | 华为技术有限公司 | Virtualization cluster integration method and device, and virtualization cluster system |
| CN106155933A (en) * | 2016-07-06 | 2016-11-23 | 乾云众创（北京）信息科技研究院有限公司 | A kind of virutal machine memory sharing method combined based on KSM and Pass through |
| CN106502765A (en) * | 2016-11-07 | 2017-03-15 | 中南大学 | A kind of virtual machine placement method suitable for cloud data center |
| CN106648829A (en) * | 2016-10-28 | 2017-05-10 | 广州市泰富信通科技有限公司 | Virtual machine transferring method for efficient utilization of cloud resource |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8650563B2 (en) * | 2010-02-26 | 2014-02-11 | Red Hat Israel, Ltd. | Identification and placement of new virtual machines to reduce memory consumption based on shared images with hosted virtual machines |
| US8631405B2 (en) * | 2010-02-26 | 2014-01-14 | Red Hat Israel, Ltd. | Identification and placement of new virtual machines based on similarity of software configurations with hosted virtual machines |
| US9280385B2 (en) * | 2013-12-19 | 2016-03-08 | International Business Machines Corporation | Optimally provisioning and merging shared resources to maximize resource availability |
| US9823842B2 (en) * | 2014-05-12 | 2017-11-21 | The Research Foundation For The State University Of New York | Gang migration of virtual machines using cluster-wide deduplication |
| DE112015007188T5 (en) * | 2015-12-18 | 2018-09-13 | Intel Corporation | Batch migration of virtual machines during active operation |
| CN106909462A (en) * | 2017-02-27 | 2017-06-30 | 郑州云海信息技术有限公司 | A kind of cloud resource regulating method and device |
-
2017
- 2017-12-08 CN CN201711293781.8A patent/CN107967168B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102103524A (en) * | 2010-12-23 | 2011-06-22 | 北京航空航天大学 | Memory redundancy oriented virtual machine migration device and method |
| CN102866915A (en) * | 2012-08-21 | 2013-01-09 | 华为技术有限公司 | Virtualization cluster integration method and device, and virtualization cluster system |
| CN106155933A (en) * | 2016-07-06 | 2016-11-23 | 乾云众创（北京）信息科技研究院有限公司 | A kind of virutal machine memory sharing method combined based on KSM and Pass through |
| CN106648829A (en) * | 2016-10-28 | 2017-05-10 | 广州市泰富信通科技有限公司 | Virtual machine transferring method for efficient utilization of cloud resource |
| CN106502765A (en) * | 2016-11-07 | 2017-03-15 | 中南大学 | A kind of virtual machine placement method suitable for cloud data center |
Non-Patent Citations (5)
| Title |
|---|
| An Empirical Study on Memory Sharing of Virtual Machines for Server Consolidation;Chao-Rui Chang 等;《2011 IEEE Ninth International Symposium on Parallel and Distributed Processing with Applications》;20110714;244-249 * |
| Distributed Shared Memory Based Live VM Migration;Tariq Daradkeh等;《2016 IEEE 9th International Conference on Cloud Computing (CLOUD)》;20170119;826-830 * |
| Memory Buddies:Exploiting Page Sharing for Smart Colocation in Virtualized Data Centers;Timothy Wood 等;《Proceedings of the 2009 ACM SIGPLAN/SIGOPS International Conference on Virtual Execution Environments》;20090313;第3-4节 * |
| 云环境下基于内存共享的服务器整合算法研究;陈静怡;《中国优秀硕士学位论文全文数据库 信息科技辑》;20130315(第3期);I137-129 * |
| 面向CPU资源超售环境的虚拟化平台管理方法研究;刘瑛;《中国博士学位论文全文数据库 信息科技辑》;20170815(第8期);I137-2 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107967168A (en) | 2018-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8893131B2 (en) | System and/or method for bulk loading of records into an ordered distributed database | |
| US20020065870A1 (en) | Method and apparatus for heterogeneous distributed computation | |
| CN108196935B (en) | Cloud computing-oriented virtual machine energy-saving migration method | |
| CN106502765B (en) | A kind of virtual machine placement method suitable for cloud data center | |
| CN104219318A (en) | Distributed file storage system and method thereof | |
| CN109101320B (en) | Heterogeneous processor platform fusion management system | |
| CN103164253A (en) | Virtual machine deployment system and virtual machine deployment method | |
| CN106161633A (en) | A kind of based on the transmission method of packaging file under cloud computing environment and system | |
| CN106775470B (en) | Data storage method and system | |
| CN106648832A (en) | Virtual machine resource utilization improving device and method thereof | |
| Zhou et al. | Cost-aware partitioning for efficient large graph processing in geo-distributed datacenters | |
| CN106909462A (en) | A kind of cloud resource regulating method and device | |
| CN107644081A (en) | Data duplicate removal method and device | |
| CN112087332A (en) | Virtual network performance optimization system under cloud edge cooperation | |
| CN102420850B (en) | Resource scheduling method and system thereof | |
| CN107967168B (en) | Virtual machine integration method based on shared memory page in cloud data center | |
| Zhang et al. | Optimizing execution for pipelined‐based distributed deep learning in a heterogeneously networked GPU cluster | |
| CN104050189B (en) | The page shares processing method and processing device | |
| CN104778088A (en) | Method and system for optimizing parallel I/O (input/output) by reducing inter-progress communication expense | |
| CN112130927A (en) | Reliability-enhanced mobile edge computing task unloading method | |
| CN104268146A (en) | Static B+-tree index method suitable for analytic applications | |
| US10387578B1 (en) | Utilization limiting for nested object queries | |
| CN107491689A (en) | A kind of password cracking method and apparatus | |
| WO2014071580A1 (en) | Compute node migration method and device | |
| CN105120008A (en) | Layering-based distributed cloud computing centre load balancing method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |