CN102594861A - Cloud storage system with balanced multi-server load - Google Patents
Cloud storage system with balanced multi-server load Download PDFInfo
- Publication number
- CN102594861A CN102594861A CN2011104202719A CN201110420271A CN102594861A CN 102594861 A CN102594861 A CN 102594861A CN 2011104202719 A CN2011104202719 A CN 2011104202719A CN 201110420271 A CN201110420271 A CN 201110420271A CN 102594861 A CN102594861 A CN 102594861A
- Authority
- CN
- China
- Prior art keywords
- server
- logical volume
- volume management
- management server
- load
- 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.)
- Pending
Links
Images
Abstract
The invention relates to a cloud storage system with a balanced multi-server load. A conventional cloud storage system, in part, has defects that firstly, since the cloud storage system is tightly coupled with an own platform system, intersystem integration and secondary development are not facilitated; and secondly, logical volume management server bottleneck seriously affects the whole performance and the reliability of the system. According to the invention, multiple logical volume management server bottleneck manages a background storage device via logic volume management technology based on a colony; an intermediate control service coordinates and controls modules of the system to operate, and distributes storage resources for a user virtual machine; and besides, the reliability and the performances of the system are ensured via a fault management mechanism and a dynamic load equalization mechanism. The system provided by the invention achieves the reliable storage device management of a cloud storage server is achieved; on performance, the storage device reading/writing throughput capacity of the system is affectively improved, and averaged reading/writing response time is shortened.
Description
Technical field
The present invention relates to the cloud technical field of memory, relate to a kind of cloud storage system of multiserver load balancing.
Background technology
Domestic cloud memory technology is according to providing the aspect difference of storage can be divided into file-level memory technology and piece rank memory technology.
The cloud memory technology of file-level mainly refers to distributed file system; It manages a series of storage resources that are distributed on the network; And, all use distributed file system the backstage storage to be provided as user virtual machine like Amazon Simple storage service (S3), Eucalyptus S3, OpenStack, Hadoop Distribute File System (HDFS) for the user provides a whole set of file operation interface.Distributed file system has higher fail safe, extensibility and read-write efficiency, but the storage of file-level can not provide original block equipment for the user.
The storage of piece rank cloud provides original block rank storage resources through the remote storage technology for the user; Make the user can be on its block device that provides custom file system and database; This series products such as Amazon Elastic Block Store (AmazonEBS); Eucalyptus EBS, the Virtual Block Store (VBS) and the improved project VBS-Lustre thereof of Indiana University.Yet there is following deficiency in above piece rank cloud storage system all part.(1) with self plateform system close-coupled, is unfavorable for integrated and secondary development between system.The user who is respectively Amazon EC2, Eucalyptus EC2 like Amazon EBS and Eucalyptus EBS provides lasting storage, but can't storage be provided for other cloud computing system, is not suitable for the scientific research field.(2) there is bottleneck in the system.Method for designing like separate unit logical volume management server among the VBS influences the entire system performance, and possibly cause Single Point of Faliure.Though VBS-Lustre utilizes the thought of distributed file system to improve the framework of VBS; Eliminated the design defect of single logical volume management server; But VBS-Lustre logical volume with the stored in form of file in the Lustre file system; And the write-protect mechanism of Lustre file system makes logical volume can't support a plurality of users to write data simultaneously, has therefore limited the function of cloud storage system to a certain extent, can't satisfy the User Part demand.
Summary of the invention
The objective of the invention is to avoid storage server single-point bottleneck problem in the existing piece rank storage system, and propose a kind of cloud storage system of multiserver load balancing.This system uses Clustering and technological based on the logical volume management of cluster; Realized the managed together of many logical volume management servers to the backstage memory device; Can storage resources be distributed to the user virtual machine on the virtual machine server with the form of logical volume through system's central control server control logic volume management server again; Realized the dynamic assignment of user virtual machine memory space; Eliminate the storage administration single-point bottleneck problem of conventional block rank storage system, thereby improved the reliability and the memory property of system.
In order to reach above purpose, the basic ideas of native system are to intercept program in each logical volume management server deploy load and running status, regularly send load and state information to central control server.Central control server uses the database of these information updatings oneself, to obtain to carry out the necessary data of fault management and load-balancing decision.In native system, central control server need have following three kinds according to the problem that these type of data are made a strategic decision: when receiving certain user virtual machine to the memory space request, decision-making is carried out the volume allocating task through which platform logical volume management server; When in detecting system, having fault logic volume management server, decision-making is moved to the iSCSI link of having set up on the failed server on which platform logical volume management server; When in detecting system, having the load imbalance, make a strategic decision and carry out load balancing between any two-server, and how to carry out load balancing.
The technical scheme that technical solution problem of the present invention is taked is:
A kind of cloud storage system of multiserver load balancing comprises the storage pool that the backstage heterogeneous storage devices is formed, many volume server cluster, virtual machine server, central control server and the clients that the logical volume management server is formed.Volume server cluster and backstage storage pool carry out exchanges data through optical fiber; The logical volume management server is that virtual machine server provides storage resources through the iSCSI mode; Central control server is accepted the request from client through web service interface; Regularly detect each volume management server operating load and running status; Give many logical volume managements server-assignment volume management task according to operating load, the logical volume management server to detected operation troubles carries out data migration and Fault Isolation simultaneously; When middle Control Server detects between the multireel management server behind the load imbalance; Performance according to the real-time load data of system and each logical volume management server; Adopt genetic algorithm to find out rational load allocating mode, with the migration cost of minimum system load is heavily distributed at last.
Beneficial effect of the present invention: the cloud storage system of many logical volume managements server load balancing proposed by the invention can dynamically be carried allocation block rank storage resources for user virtual machine by user's request, has higher reliabilty and availability.On performance, improve simultaneously the storage read-write throughput of system effectively, shortened the average read-write response time, had higher read-write efficiency.
Description of drawings
Fig. 1 is the Organization Chart of many logical volume managements server cloud storage system;
Fig. 2 creates/checks logical volume workflow sketch map;
Fig. 3 creates/checks snapshot workflow sketch map;
Fig. 4 is a deletion volume/snapshot workflow sketch map;
Fig. 5 is a carry logical volume workflow sketch map;
Fig. 6 is a unloading logical volume workflow sketch map;
Fig. 7 is a server failure manage workflow sketch map.
Embodiment
Below in conjunction with accompanying drawing and practical implementation application process native system is further specified.
As shown in Figure 1; Whole system is made up of seven functional modules; Be respectively that logical volume trustship module, snoop logic volume management server load monitoring module, snoop logic volume management server state monitoring module, virtual machine monitor trustship module, system's central control module, snoop logic volume management server state are intercepted administration module and client modules, these modules are deployed in respectively on the different node of logical volume management server, virtual machine server, system's central control server and four types of functions of system client.Each module supplies other module invokes through the function of Web Service interface issue oneself, accomplishes each item work of system jointly through the coordination of system's central control module.
Many logical volume management servers adopt the linux Clustering to form a cluster, and major function is the memory device that management is shared, and is deployed with logical volume trustship module, load monitoring module and logical volume management server state monitoring module.The functional interface that logical volume trustship module provides through the Linux logical volume management (CLVM) that calls based on cluster; Be implemented in establishment/deletion volume on the logical volume management server, establishment/deletion snapshot, SNAPSHOT INFO copied to function such as new volume, CLVM guaranteed volume information on each logical volume management server synchronously; In addition, the functional interface that provides through iSCSI Enterprise Target of logical volume trustship module becomes iscsi target device (iSCSI target) with logical volume and supplies that iSCSI starter (iSCSI initiator) calls on the virtual machine server.The load monitoring module can be obtained the load size of every iSCSI connection and the total load of logical volume management server from the tcp port of logical volume management server.Whether logical volume management server state monitoring module is in normal operating conditions through the decision logic volume management server that calls to the CLVM functional interface.
Virtual machine server uses Xen to come the managing virtual machines instance.Virtual machine monitor trustship module is deployed on the virtual machine server, logins the iSCSI object machine of logical volume management server through the functional interface that calls the iSCSI starter and provide, with obtain with the logical volume management server on the long-range of logical volume be connected.The module of virtual machine monitor trustship afterwards can be mounted to block device on the virtual machine Domain U from Domain 0 through Virtual Block Device (VBD) technology, makes user virtual machine can utilize remote storage resource.
System's central control module is on system's central control server; According to request type and parameter from system client; Send the corresponding command and accept feedback information to logical volume management server and VMM node; And preserve volume, snapshot and carry information, make it orderly work to coordinate whole system.Also be deployed with the logical volume management server state on system's central control server and intercept administration module, regularly send logical volume management operation condition of server request and load state request to the logical volume management server.Intercept submodule when state and receive logical volume management server operation exception feedback, will call troubleshooting submodule actuating logic volume management server switch operating; When load is intercepted the load information judgement system of submodule through each logical volume management server feedback and is got into the load imbalance, will call the load balancing submodule, carry out the load of load balancing process balance sysmte.
The establishment deletion that logical volume management work in the system mainly comprises volume with check, the establishment deletion of snapshot with check and carry/unloading operation of rolling up.
When central Control Server is received from the request of the establishment of client volume, can send to a logical volume management server immediately and create volume order and relevant parameter.The logical volume management server that receives orders has enough memory spaces in confirming storage pool after, this volume is created in " lvcreate " order that calling CLVM provides.System's central control server returns the information of this volume to client, and wherein volume state is " pending ".If this volume is through a snapshot creation; Then new thread of system creation orders the content replication that will formulate in the snapshot in volume through dd in later time; After duplicating completion, the state of rolling up in the database on system's central control server is updated to " available "; Otherwise, directly volume state is updated to " available ".When needs check the volume created the time, system's central control server returns to client with the Query Result of volume information in the database, creates and checks that the flow process of volume is as shown in Figure 2.When needs were deleted the volume of having created, system's central control server sent the order of deletion volume to the logical volume management server, and logical volume management server calls lvremove orders the deletion specified volume, and flow process is shown in figure four.Because all logical volume management servers are formed a cluster; The operating result of volume and snapshot can obtain on each logical volume management server synchronously in the storage pool for sharing for logical volume management server, and therefore above operation all need be carried out on a logical volume management server.
The management work of snapshot is flowed with similar to the management work stream of rolling up, and only is the parameter difference of in constructive process, calling " lvcreate " order, flow process such as Fig. 3, shown in Figure 4.
It is as shown in Figure 5 that carry licks journey.Carry volume request from client can be specified an available volume, the user virtual machine that need be mounted to, and the VMM server at this virtual machine place.According to these information, system's central control server is at first selected a logical volume management server, on this logical volume management server, target volume is become the iSCSI object machine and issues.Then the VMM server is logined the iSCSI object machine through the iSCSI starter, and a virtual iscsi device can occur on the VMM server this moment.Through " xm block-attach " order virtual iscsi device is mounted on the virtual machine at last, has just successfully added a long-range memory device on the virtual machine.
The work of unloading volume is the inverse process of carry volume, and flow process is as shown in Figure 6.
Fig. 7 is a server failure manage workflow sketch map.The fault management workflow by intercept-the fault detect flow process with intercept-troubleshooting process forms.At first; The logical volume management server state that is deployed on system's central control server node is intercepted each logical volume management server of program timing poll, obtains the state information of logical volume management server through the condition monitoring program on the calling logic volume management server.When a logical volume management server has returned logical volume management server failure message, the logical volume management server state hypervisor that is deployed on system's central control server node is launched.The iSCSI that has set up on the fault logic volume management server connects and will be reset: client virtual machine breaks off the iSCSI that sets up with fault logic volume management server and is connected; Select other normal logical volume management servers to carry out iSCSI again and reconnect, regain the right to use target volume.
The key step of many logical volume managements server failure management is following:
A. each logical volume management server of central control server automatic regular polling, the server state on the calling logic volume management server are intercepted the real-time running state that program obtains the logical volume management server.
B. when having fault logic volume management server in the discovery system, call the fault migrator, the iSCSI link of having set up on this server is migrated on other logical volume management servers one by one.
C. when all iSCSI link on the failed server after all migration finishes, call fault isolation routine, fault logic volume management server is isolated the logical volume management server cluster.
Fig. 8 is load balancing strategic process figure.The logical volume management server state is intercepted per interval of program
calling logic volume management server load monitoring program and is obtained the load state that each bar iSCSI connects, and the logical volume management Server Manager Daemon calculates the performance weighting load value of every volume server then.The difference that in system, has two-server performance weighting load value is greater than threshold value
ωThe time, the minimum and maximum volume server of load is carried out iSCSI link load balancing process in the extraction system.The fitness function of definition genetic algorithm is the load balancing degrees of two-server, draws the highest iSCSI link migration pattern of fitness through N for heredity.The migration strategy that obtains according to the genetic algorithm simulation at last carries out iSCSI link migration.
The concrete operating procedure of dynamic load leveling is following between many logical volume managements server:
A. before each logical volume management server adds system cluster, adopt black-box approach, according to request number of waiting in its formation and the relation of IO response time, to its performance modeling.
B. each logical volume management server of central control server automatic regular polling; The real-time load information that program obtains the logical volume management server is intercepted in server load on the calling logic volume management server, and obtains server performance weighting load state after the weighting of server performance model.
C. when central Control Server detects system and is in the load imbalance, the two-server that performance weighting load in the system is minimum and maximum is carried out the load balancing process: obtain taking all factors into consideration best iSCSI link migration strategy after portfolio effect and the migration cost through the genetic algorithm simulation.
D. the best migration strategy that obtains according to simulation carries out iSCSI link migration between two-server.
The cloud storage system of many logical volume managements server load balancing that the present invention proposes has solved the problem of storage managing server Single Point of Faliure and performance bottleneck in the conventional block rank cloud storage system.It has improved the reliabilty and availability of system; Improved the readwrite performance of system.
Claims (6)
1. the cloud storage system of a multiserver load balancing; Comprise the storage pool that the backstage heterogeneous storage devices is formed; Many the volume server clusters that the logical volume management server is formed; Virtual machine server, central control server and client is characterized in that: volume server cluster and backstage storage pool carry out exchanges data through optical fiber; The logical volume management server is that virtual machine server provides storage resources through the iSCSI mode, and central control server is accepted the work from the request of client and coordination logic volume management server, virtual machine server through web service interface.
2. according to the cloud storage system of the said a kind of multiserver load balancing of claim 1; It is characterized in that: many logical volume managements server is through the logic volume management management backstage memory device based on cluster, and each logical volume management server is to the modification information of backstage memory device synchronously.
3. according to the cloud storage system of the said a kind of multiserver load balancing of claim 1, it is characterized in that: system has failure handling mechanisms, and avoiding influences system works because of certain logical volume management server failure;
Described failure handling mechanisms realizes through following method: central control server regularly detects the running status of each logical volume management server, find certain server exception after, it is carried out data migrations and failed server isolation.
4. according to the cloud storage system of the said a kind of multiserver load balancing of claim 1; It is characterized in that: central control server is accepted the system client request, and many logical volume management servers of dynamic management are user virtual machine memory allocated space on many virtual machine server.
5. according to the cloud storage system of the said a kind of multiserver load balancing of claim 1, it is characterized in that: the logical volume management server that performance differs can carry out dynamic load leveling in system.
6. according to the cloud storage system of the said a kind of multiserver load balancing of claim 5, it is characterized in that: it is specific as follows to utilize genetic algorithm that many logical volume managements server is carried out load balancing:
Utilize black-box approach to the modeling of logical volume management server performance; To each logical volume management server load modeling, obtain each logical volume management server performance weighting load module through total iSCSI packet size of capturing at the iSCSI port according to the ratio of preceding two models;
Central control server regularly detects each logical volume management server performance weighting load state, when detecting when having the server load imbalance, the minimum and maximum server of performance weighting load in the system is carried out load balancing;
According to the load state of each iSCSI link on the two-server, use genetic algorithm to simulate the minimum load-balancing method of migration cost;
D. the best migration strategy that obtains according to simulation carries out iSCSI link migration between two-server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011104202719A CN102594861A (en) | 2011-12-15 | 2011-12-15 | Cloud storage system with balanced multi-server load |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011104202719A CN102594861A (en) | 2011-12-15 | 2011-12-15 | Cloud storage system with balanced multi-server load |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102594861A true CN102594861A (en) | 2012-07-18 |
Family
ID=46483059
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011104202719A Pending CN102594861A (en) | 2011-12-15 | 2011-12-15 | Cloud storage system with balanced multi-server load |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102594861A (en) |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102857577A (en) * | 2012-09-24 | 2013-01-02 | 北京联创信安科技有限公司 | System and method for automatic load balancing of cluster storage |
| CN102968720A (en) * | 2012-11-07 | 2013-03-13 | 东莞宇龙通信科技有限公司 | Payment server, terminal and payment channel partition method |
| CN103118073A (en) * | 2013-01-08 | 2013-05-22 | 华中科技大学 | Virtual machine data persistence storage system and method in cloud environment |
| CN103440158A (en) * | 2013-07-29 | 2013-12-11 | 西北工业大学 | Hotspot migration method for cloud resource scheduling |
| CN103458055A (en) * | 2013-09-22 | 2013-12-18 | 广州中国科学院软件应用技术研究所 | Clout competing platform |
| CN103530317A (en) * | 2013-09-12 | 2014-01-22 | 杭州电子科技大学 | Energy consumption adaptive type replication managing method used in cloud storage system |
| CN105530313A (en) * | 2015-12-21 | 2016-04-27 | 中国石油大学(华东) | Context sensing service migrating method based on OSGi pervasive cloud environment |
| CN106060876A (en) * | 2016-07-28 | 2016-10-26 | 中国科学院计算技术研究所 | Load balancing method for heterogeneous wireless network |
| WO2017028696A1 (en) * | 2015-08-17 | 2017-02-23 | 阿里巴巴集团控股有限公司 | Method and device for monitoring load of distributed storage system |
| CN106528265A (en) * | 2016-10-24 | 2017-03-22 | 郑州云海信息技术有限公司 | Virtual machine management method and system based on distributed SAN (Storage Area Network) storage architecture |
| CN106603632A (en) * | 2016-11-25 | 2017-04-26 | 国云科技股份有限公司 | Virtual machine management method for reducing boot storm of cloud platform |
| CN106886374A (en) * | 2017-03-10 | 2017-06-23 | 济南浪潮高新科技投资发展有限公司 | A kind of virtual disk dispatching method based on openstack |
| CN107018163A (en) * | 2016-01-28 | 2017-08-04 | 中国移动通信集团河北有限公司 | A kind of resource allocation method and device |
| CN107423301A (en) * | 2016-05-24 | 2017-12-01 | 华为技术有限公司 | A kind of method of data processing, relevant device and storage system |
| CN107453888A (en) * | 2016-05-31 | 2017-12-08 | 深圳市深信服电子科技有限公司 | The management method and device of the cluster virtual machine of high availability |
| CN107645421A (en) * | 2017-11-09 | 2018-01-30 | 郑州云海信息技术有限公司 | A kind of ISCSI protocol implementing methods of distributed storage |
| CN107707393A (en) * | 2017-09-26 | 2018-02-16 | 赛尔网络有限公司 | More live systems based on Openstack O version characteristics |
| CN108874305A (en) * | 2017-05-10 | 2018-11-23 | 斯特拉托斯卡莱有限公司 | For storage area network（SAN）The object of equipment covers |
| CN109618002A (en) * | 2019-01-11 | 2019-04-12 | 武汉斗鱼鱼乐网络科技有限公司 | A kind of micro services gateway optimization method, device and storage medium |
| CN109672714A (en) * | 2017-10-17 | 2019-04-23 | 中移(苏州)软件技术有限公司 | A kind of data processing method and distributed memory system of distributed memory system |
| CN111209108A (en) * | 2019-12-26 | 2020-05-29 | 天津中科曙光存储科技有限公司 | Load balancing method and device for storage device end of iSCSI (Internet small computer system interface) |
| CN111367467A (en) * | 2018-12-26 | 2020-07-03 | 浙江宇视科技有限公司 | Storage resource mounting method and device, server and distributed system |
| CN112333143A (en) * | 2017-02-10 | 2021-02-05 | 瞻博网络公司 | Granular offload of proxy secure sessions |
| CN113411369A (en) * | 2020-03-26 | 2021-09-17 | 山东管理学院 | Cloud service resource collaborative optimization scheduling method, system, medium and equipment |
| CN113806125A (en) * | 2021-09-07 | 2021-12-17 | 济南浪潮数据技术有限公司 | Processing method, device and equipment for unloading volume exception and readable medium |
| CN113900774A (en) * | 2021-12-06 | 2022-01-07 | 浙江云针信息科技有限公司 | Virtual machine control method and device of cloud operating system and storage medium |
| CN114661247A (en) * | 2022-05-23 | 2022-06-24 | 武汉四通信息服务有限公司 | Automatic capacity expansion method and device, electronic equipment and storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101753617A (en) * | 2009-12-11 | 2010-06-23 | 中兴通讯股份有限公司 | Cloud storage system and method |
-
2011
- 2011-12-15 CN CN2011104202719A patent/CN102594861A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101753617A (en) * | 2009-12-11 | 2010-06-23 | 中兴通讯股份有限公司 | Cloud storage system and method |
Non-Patent Citations (2)
| Title |
|---|
| XIAOMING GAO, YU MA, MARLON PIERCE, MIKE LOWE, AND GEOFFREY FOX: "Building a Distributed Block Storage System for Cloud Infrastructure", 《CLOUD COMPUTING TECHNOLOGY AND SCIENCE (CLOUDCOM)》 * |
| 倪云竹,吕光宏,黄彦辉: "用遗传算法解决基于分条技术的磁盘负载均衡问题", 《计算机学报》 * |
Cited By (42)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102857577B (en) * | 2012-09-24 | 2015-10-28 | 北京联创信安科技有限公司 | A kind of system and method for cluster-based storage automatic load balancing |
| CN102857577A (en) * | 2012-09-24 | 2013-01-02 | 北京联创信安科技有限公司 | System and method for automatic load balancing of cluster storage |
| CN102968720B (en) * | 2012-11-07 | 2016-08-03 | 东莞宇龙通信科技有限公司 | Paying server, terminal and payment channel partition method |
| CN102968720A (en) * | 2012-11-07 | 2013-03-13 | 东莞宇龙通信科技有限公司 | Payment server, terminal and payment channel partition method |
| CN103118073A (en) * | 2013-01-08 | 2013-05-22 | 华中科技大学 | Virtual machine data persistence storage system and method in cloud environment |
| CN103118073B (en) * | 2013-01-08 | 2015-07-22 | 华中科技大学 | Virtual machine data persistence storage system and method in cloud environment |
| CN103440158A (en) * | 2013-07-29 | 2013-12-11 | 西北工业大学 | Hotspot migration method for cloud resource scheduling |
| CN103440158B (en) * | 2013-07-29 | 2016-03-30 | 西北工业大学 | The hotspot migration method of facing cloud scheduling of resource |
| CN103530317B (en) * | 2013-09-12 | 2017-07-07 | 杭州电子科技大学 | A kind of copy management method of energy consumption self adaptation in cloud storage system |
| CN103530317A (en) * | 2013-09-12 | 2014-01-22 | 杭州电子科技大学 | Energy consumption adaptive type replication managing method used in cloud storage system |
| CN103458055A (en) * | 2013-09-22 | 2013-12-18 | 广州中国科学院软件应用技术研究所 | Clout competing platform |
| WO2017028696A1 (en) * | 2015-08-17 | 2017-02-23 | 阿里巴巴集团控股有限公司 | Method and device for monitoring load of distributed storage system |
| CN106469018A (en) * | 2015-08-17 | 2017-03-01 | 阿里巴巴集团控股有限公司 | The load monitoring method and apparatus of distributed memory system |
| CN106469018B (en) * | 2015-08-17 | 2019-12-27 | 阿里巴巴集团控股有限公司 | Load monitoring method and device for distributed storage system |
| CN105530313A (en) * | 2015-12-21 | 2016-04-27 | 中国石油大学(华东) | Context sensing service migrating method based on OSGi pervasive cloud environment |
| CN107018163B (en) * | 2016-01-28 | 2020-02-11 | 中国移动通信集团河北有限公司 | Resource allocation method and device |
| CN107018163A (en) * | 2016-01-28 | 2017-08-04 | 中国移动通信集团河北有限公司 | A kind of resource allocation method and device |
| CN107423301A (en) * | 2016-05-24 | 2017-12-01 | 华为技术有限公司 | A kind of method of data processing, relevant device and storage system |
| CN107453888A (en) * | 2016-05-31 | 2017-12-08 | 深圳市深信服电子科技有限公司 | The management method and device of the cluster virtual machine of high availability |
| CN107453888B (en) * | 2016-05-31 | 2020-11-20 | 深信服科技股份有限公司 | High-availability virtual machine cluster management method and device |
| CN106060876B (en) * | 2016-07-28 | 2019-11-29 | 中国科学院计算技术研究所 | A kind of method of heterogeneous wireless network equally loaded |
| CN106060876A (en) * | 2016-07-28 | 2016-10-26 | 中国科学院计算技术研究所 | Load balancing method for heterogeneous wireless network |
| CN106528265A (en) * | 2016-10-24 | 2017-03-22 | 郑州云海信息技术有限公司 | Virtual machine management method and system based on distributed SAN (Storage Area Network) storage architecture |
| CN106603632A (en) * | 2016-11-25 | 2017-04-26 | 国云科技股份有限公司 | Virtual machine management method for reducing boot storm of cloud platform |
| CN112333143A (en) * | 2017-02-10 | 2021-02-05 | 瞻博网络公司 | Granular offload of proxy secure sessions |
| CN106886374A (en) * | 2017-03-10 | 2017-06-23 | 济南浪潮高新科技投资发展有限公司 | A kind of virtual disk dispatching method based on openstack |
| CN108874305A (en) * | 2017-05-10 | 2018-11-23 | 斯特拉托斯卡莱有限公司 | For storage area network（SAN）The object of equipment covers |
| CN108874305B (en) * | 2017-05-10 | 2023-10-20 | 迈络思科技有限公司 | Object overlay for storage area network (SAN) devices |
| CN107707393A (en) * | 2017-09-26 | 2018-02-16 | 赛尔网络有限公司 | More live systems based on Openstack O version characteristics |
| CN107707393B (en) * | 2017-09-26 | 2021-07-16 | 赛尔网络有限公司 | Multi-active system based on Openstack O version characteristics |
| CN109672714A (en) * | 2017-10-17 | 2019-04-23 | 中移(苏州)软件技术有限公司 | A kind of data processing method and distributed memory system of distributed memory system |
| CN107645421A (en) * | 2017-11-09 | 2018-01-30 | 郑州云海信息技术有限公司 | A kind of ISCSI protocol implementing methods of distributed storage |
| CN111367467A (en) * | 2018-12-26 | 2020-07-03 | 浙江宇视科技有限公司 | Storage resource mounting method and device, server and distributed system |
| CN111367467B (en) * | 2018-12-26 | 2022-11-04 | 浙江宇视科技有限公司 | Storage resource mounting method and device, server and distributed system |
| CN109618002B (en) * | 2019-01-11 | 2022-07-05 | 武汉斗鱼鱼乐网络科技有限公司 | Micro-service gateway optimization method, device and storage medium |
| CN109618002A (en) * | 2019-01-11 | 2019-04-12 | 武汉斗鱼鱼乐网络科技有限公司 | A kind of micro services gateway optimization method, device and storage medium |
| CN111209108A (en) * | 2019-12-26 | 2020-05-29 | 天津中科曙光存储科技有限公司 | Load balancing method and device for storage device end of iSCSI (Internet small computer system interface) |
| CN113411369A (en) * | 2020-03-26 | 2021-09-17 | 山东管理学院 | Cloud service resource collaborative optimization scheduling method, system, medium and equipment |
| CN113806125A (en) * | 2021-09-07 | 2021-12-17 | 济南浪潮数据技术有限公司 | Processing method, device and equipment for unloading volume exception and readable medium |
| CN113806125B (en) * | 2021-09-07 | 2023-12-22 | 济南浪潮数据技术有限公司 | Method, device, equipment and readable medium for processing unloaded volume exception |
| CN113900774A (en) * | 2021-12-06 | 2022-01-07 | 浙江云针信息科技有限公司 | Virtual machine control method and device of cloud operating system and storage medium |
| CN114661247A (en) * | 2022-05-23 | 2022-06-24 | 武汉四通信息服务有限公司 | Automatic capacity expansion method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102594861A (en) | Cloud storage system with balanced multi-server load | |
| US10601917B2 (en) | Containerized high-performance network storage | |
| US8468548B2 (en) | Multi-tenant, high-density container service for hosting stateful and stateless middleware components | |
| CA3000161C (en) | Distributed stream-based database triggers | |
| CN105245523B (en) | Storage service platform and its implementation applied to desktop virtualization scene | |
| CN102355369B (en) | Virtual clustered system as well as processing method and processing device thereof | |
| US9733989B1 (en) | Non-disruptive load-balancing of virtual machines between data centers | |
| CN105743995A (en) | Transplantable high-available container cluster deploying and managing system and method | |
| CN113504954B (en) | Method, system and medium for calling CSI LVM plug in and dynamic persistent volume supply | |
| US10942759B2 (en) | Seamless virtual standard switch to virtual distributed switch migration for hyper-converged infrastructure | |
| WO2014036717A1 (en) | Virtual resource object component | |
| CN103124299A (en) | Distributed block-level storage system in heterogeneous environment | |
| US20170315883A1 (en) | Data storage with virtual appliances | |
| US11740921B2 (en) | Coordinated container scheduling for improved resource allocation in virtual computing environment | |
| US10761869B2 (en) | Cloud platform construction method and cloud platform storing image files in storage backend cluster according to image file type | |
| US10880367B2 (en) | Load balancing stretched clusters in a distributed network | |
| US20220091874A1 (en) | Method for optimizing the load balance in the cluster and framework thereof | |
| CN110661865A (en) | Network communication method and network communication architecture | |
| CN110798362A (en) | Multi-data center online management system and management method based on Internet of things | |
| US9495257B2 (en) | Networking support for zone clusters based on virtualization of servers | |
| CN109284169A (en) | Big data platform process management method and computer equipment based on process virtual | |
| KR101673882B1 (en) | Storage system with virtualization using embedded disk and method of operation thereof | |
| CN114416301A (en) | Data collection service container management method | |
| CN112988335A (en) | High-availability virtualization management system, method and related equipment | |
| CN104683363B (en) | The migration of binary implementation under cloud computing environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C05 | Deemed withdrawal (patent law before 1993) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20120718 |