CN108055338A - A kind of ISCSI accesses load-balancing method - Google Patents
A kind of ISCSI accesses load-balancing method Download PDFInfo
- Publication number
- CN108055338A CN108055338A CN201711402414.7A CN201711402414A CN108055338A CN 108055338 A CN108055338 A CN 108055338A CN 201711402414 A CN201711402414 A CN 201711402414A CN 108055338 A CN108055338 A CN 108055338A
- Authority
- CN
- China
- Prior art keywords
- node
- load
- network interface
- interface card
- storage device
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1029—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers using data related to the state of servers by a load balancer
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer And Data Communications (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
This application discloses a kind of ISCSI to access load-balancing method, including：Each node is monitored the load of each network interface card in this node, and when receiving the access request of client, connection is established using ISCSI redirection functions and the client using minimum network interface card is loaded in this node；When the network interface card load that node is monitored in this node is more than threshold value, a connection for meeting balanced adjustment condition is selected from the connection on the network interface card, disconnects the connection；Balanced adjustment condition is less than threshold value to connect the sum of the load of corresponding load with loading minimum network interface card in this node；If the selection failure, a node is then selected from system as resource migration destination node, and a storage device is selected from the storage device of this node, the connection for accessing the storage device is disconnected, selected storage device is migrated to resource migration destination node.The present invention can improve resource utilization while system load balancing is realized, it is easy to accomplish.
Description
Technical field
The present invention relates to distributed storage technology, more particularly to a kind of Internet small computer system interfaces
(ISCSI) load-balancing method is accessed.
Background technology
The load of network interface card is maintained at by hardware device itself affect in a fixed range, by more in distributed memory system
A node composition, each node generally configures polylith network interface card (different network interface card rates may be different), if every piece of network interface card load is not
Together or even there is part network interface card and load that very high while part network interface card is more idle, then distribution will be become by loading high network interface card
Network bottleneck in formula storage system influences systematic entirety energy.
For the above problem of distributed memory system, current solution is using hardware load balancer or makes
It is bound with polylith network interface card.The scheme of load balancing is carried out using hardware load balancer, it is necessary to buy professional equipment, such
Equipment can increase more expenses again generally costly and there are Single Point of Faliure, using two-shipper is mutually standby, therefore, can there are costs
High limitation.The scheme of load balancing is realized using more network card bindings, can only realize load balancing in node, it is impossible to realize section
There are cannot making full use of Internet resources between node in load balancing between point, therefore, the program.
It can be seen that there are of high cost or cannot make full use of and be for the load balancing scheme of existing distributed memory system
The problem of resource of uniting.
The content of the invention
It in view of this, can be effective real it is a primary object of the present invention to provide a kind of ISCSI to access load-balancing method
While the load balancing of existing distributed memory system, utilization ratio of storage resources is improved, and is easily achieved.
In order to achieve the above object, technical solution proposed by the present invention is：
A kind of ISCSI accesses load-balancing method, including：
Each node of distributed memory system, is monitored the load of each network interface card in this node, when receiving client
During the access request at end, established using minimum network interface card is loaded in this node using ISCSI redirection functions and the client
Connection；
When the network interface card load that the node is monitored in this node is more than predetermined threshold value, selected from the connection on the network interface card
A connection for meeting default balanced adjustment condition is selected, selected connection is disconnected；The balanced adjustment condition includes connection
Corresponding load is less than the threshold value with loading the sum of minimum load of network interface card in this node；
If the selection failure, the node select one according to the loading condition of each node in system from system
Node selects a storage device as resource migration destination node from the storage device of this node, and disconnecting access, this is deposited
The connection of equipment is stored up, selected storage device is migrated to the resource migration destination node.
In conclusion ISCSI proposed by the present invention accesses load-balancing method, the network between node in node is realized
Load balancing, so as to improve ISCSI storage performances in distributed system to greatest extent, while there is no single for the program
Point failure realizes High Availabitity, and therefore, the present invention improves while the load balancing of distributed memory system is effectively realized
Utilization ratio of storage resources, and be easily achieved.
Description of the drawings
Fig. 1 is the method flow schematic diagram of the embodiment of the present invention；
The dynamic schematic diagram of load balancing is realized under a concrete application scene for the present invention in Fig. 2~7.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, it is right below in conjunction with the accompanying drawings and the specific embodiments
The present invention is described in further detail.
The present invention core concept be：The network interface card that each node selects load minimum is established for the client that request accesses to be connected
It connects, when monitoring the load too high of network interface card, then idle network interface card is preferentially selected from this node, realized using it in node
Dynamic load leveling, if the selection fails, the relatively low node of one load of selection, is moved by storage device in consideration system
The mode of shifting realizes the dynamic load leveling between node using the network interface card resource on selected node.It is in this way it can be ensured that each
Node is all load balancing node, without the utilization rate and storage performance of Single Point of Faliure, to the greatest extent raising system resource.
Fig. 1 accesses load-balancing method flow diagram for ISCSI provided in an embodiment of the present invention, as shown in Figure 1, the reality
Applying example mainly includes：
Each node of step 101, distributed memory system, is monitored the load of each network interface card in this node, when connecing
When receiving the access request of client, ISCSI redirection functions and the visitor are used using minimum network interface card is loaded in this node
Connection is established at family end.
This step is used to implement real time load equilibrium, (is somebody's turn to do when client is connected to server-side i.e. in distributed memory system
Node where the resource of client access request, that is, the node of service is provided in system for the client) after, server-side
It can unconditionally select to load minimum network interface card in this node, no matter the network interface card is either with or without overload.In this way, server-side pass through it is preferential
Connection is established using client of the minimum network interface card for request service is loaded in node, can realize that the real time load in node is equal
Weighing apparatus.
In practical applications, for each network interface card, the load of the network interface card can be connected to the network interface card by calculating
The summation of the access speed of all clients obtains.It is preferred that it is considered that non-traffic network present in practical application is opened
Pin, the load of network interface card can be more somewhat larger than the summation of the access speed of all clients thereon, such as can according to Z=a ×
S calculates the load of network interface card, wherein, a is default regulation coefficient, and value range can be 1≤a ＜ 2, and S is all on network interface card
The summation of the access speed of client, Z are the load of network interface card.
Distinguishingly, if the load of each network interface card in node is identical (during such as initial launch), can select any
A network interface card is attached.
Step 102, when the node monitor in this node network interface card load be more than predetermined threshold value when, from the network interface card
A connection for meeting default balanced adjustment condition is selected in connection, selected connection is disconnected；The balanced adjustment condition
It is less than the threshold value with loading the sum of minimum load of network interface card in this node including connecting corresponding load；If the selection
Failure, then the node selects a node as resource migration target according to the loading condition of each node in system from system
Node, and a storage device is selected from the storage device of this node, the connection for accessing the storage device is disconnected, by selected by
Storage device migrate to the resource migration destination node.
This step, is used to implement dynamic load leveling, i.e., to the actual loading situation of each network interface card of each node in system into
Row monitoring at the overload of some network interface card (i.e. load is more than predetermined threshold value), first triggers the adjustment of load in node, in node
When adjusting unsuccessful, then trigger the adjustment of load between system node.Wherein, for the adjustment of load in node, disconnection will be passed through
Some connection to overload on network interface card, connects access system, so as to utilize to trigger the corresponding client re-request of the connection
The execution of step 101 is avoided as much as on individual node load centralization on some network interface card；And between system node
Adjustment of load then needs the migration of some storage resource by node where triggering overload network interface card to realize, is to make full use of
Node resource in system realizes the load balancing between whole system node.
Here, from, it is necessary to meet balanced adjustment condition, i.e., should when selection one needs the connection disconnected on overload network interface card
It connects corresponding load and is less than the threshold value with loading the sum of minimum load of network interface card in this node, in this way, after connection disconnects,
Corresponding client is when re-request accesses again, according to the technical characteristic in step 101, it will be connected in node load it is minimum
Network interface card on, and by the satisfaction of above-mentioned balanced adjustment condition, then can cause to save to avoid due to the connection re-established
Minimum network interface card overload is loaded in point, so as to ensure the validity of load balancing operation in node.
When the connection disconnection for meeting the balanced adjustment condition can not be selected from overload network interface card, then need consideration will
The storage resource of node is moved on other nodes lighter than this node load where the overload network interface card, to reduce the overload network interface card
The load of place node, hereafter to realize the load balance of the node by the adjustment of load in node.
It is preferred that following methods may be employed in this step selects a node as current resource migration from system
Destination node：
The node current load data of each node in acquisition system from the management node of system, and according to described negative
Data are carried, from other nodes in system, the node for selecting load minimum is as current resource migration destination node.
In the selection method of above-mentioned resource migration destination node, current overload network interface card place node its will be removed from system
He selects the node of present load minimum as resource migration destination node in node, in this way, loaded between node can be reduced
Gap preferably realizes the load balancing between whole system node, farthest the available storage resource in increase system, into
And improve utilization ratio of storage resources.
Further, in practical applications, each node in system can be when the load of this node changes, will
The load information of this node is reported to the management node of system, so as to system management node can exactly in grasp system it is each
The loading condition of node carries out real-time servicing to the load data of each node.So, it can be ensured that each node in system exists
When needing to carry out resource migration, the real time load data of each node are obtained from management node, are suitable for select exactly
Carry out the destination node of resource migration.
Specifically, the management node can be some node in system in itself, which can preassign.
Can be according to the load data of each node in system for the ease of node where overload network interface card, filtering out exactly can
To carry out the node of resource migration, acquired load information will be including at least the load of node and negative from management node
Carry surplus.
It is preferred that in the storage device from this node a storage device is selected to include：
Calculate the load value of each storage device in this node；
Determine the storage device for meeting transition condition in the storage device of this node；The transition condition is storage device
Load value is less than the load surplus of the resource migration destination node, and the load surplus is on the resource migration destination node
The sum of remaining load of all network interface cards, the remaining load of each network interface card are the difference of the load of the threshold value and network interface card；
The storage device of quantity minimum will be connected in the storage device determined as selected storage device.
The threshold value, for judging whether the load of network interface card overloads, load is more than the threshold value, then illustrates that network interface card overloads, tool
Suitable value can be configured according to actual needs by those skilled in the art body.
By above-described embodiment it can be seen that the load balancing of the invention by realizing distributed system following aspects：
1. real time load is balanced in node, the minimum network interface card of selection load is realized using ISCSI redirection functions to client
It is balanced that end connection carries out real time load in node.
2. dynamic load leveling in node, if overload occurs in a certain network interface card, node is interior simultaneously and has phase in the process of running
A suitable connection (another network interface card load too high will not be made after reconnect) is then selected idle network interface card, which is broken
It opens, ISCSI clients can automatically initiate reconnect, and net can be connected according to real time load equilibrium client in above-mentioned 1 node
The minimum network interface card of network load realizes dynamic load leveling adjustment in node.
3. dynamic load leveling between node can not find node Intranet card in above-mentioned 2 and carry out searching institute during load balancing
There is the network load of node, find a duty factor relatively low node and storage device is moved into above-mentioned 1,2 step of node repetition
Rapid dynamic load between realizing node.
4. each node in the invention is all load balancing node, without Single Point of Faliure, High Availabitity is realized.
The Network Load Balance in node, between node is realized by the foregoing description present invention to improve to greatest extent point
ISCSI storage performances in cloth system, while the program, there is no Single Point of Faliure, there is no two-shipper, mutually the increased expense of standby institute is opened
Pin, it is achieved thereby that High Availabitity.In short, the present invention can be divided by real time load equilibrium and dynamic load leveling in effective realize
While the load balancing of cloth storage system, utilization ratio of storage resources is improved, and is easily achieved.Specifically should below by one
The realization of the present invention is further elaborated with scene.
Assuming that having storage resource Target1, Target2, Target3, given birth to respectively by book 1, book 2, book 3
Into.VIP is the empty IP in distributed system, can be drifted about between node, but is only existed on one node always.Client
End speed when being initially connected to Target ends is always 0, and all network interface cards are that (actual speed rate hypothesis can only achieve Gigabit Ethernet
The 95% of ideal rate, then actual speed rate is the ≈ 118MB/s of 1000Mbit/s*95%/8).This example uses simplest situation
To illustrate workflow, it is assumed that current VIP is on node 1.
Assuming that it is configured now there are two node as follows
Node 1：Network interface card 1, network interface card 2 are configured, while there are Target1, Target2 for the node.
Node 2：Network interface card 3, network interface card 4 are configured, there are Target3 for the node.
All network card configurations are all identical.
Network interface card loads calculation formula：(network interface card transmission rate+network interface card receiving velocity) * 100/ network interface card ideal rate, rate list
Position is KB/s.
As shown in Fig. 2, real time load in 1 node, client 1 will access Target1, and all network interface cards are all idle shapes at this time
State then randomly chooses the network interface card 1 of node 1 or network interface card 2, it is assumed that selection network interface card 1, as shown in Figure 3.
Dynamic load in 2 nodes, client 2 will access Target1, and network interface card 2 is in idle condition at this time, then selects network interface card
2, as shown in Figure 4.
Client 3 will access Target2, load-balancing algorithm final choice network interface card 2 according to the present invention, as shown in Figure 5.
At this time 2 load too high of network interface card and network interface card 1 is also available free, then by calculate client 2 is moved to network interface card 1 after can be
Load is more balanced, disconnects client 2 and connects, the meeting Auto-reconnect of client 2, balanced according to the real time load in above-mentioned 1 node,
It redirects in network interface card 1.As shown in Figure 6.
Load balancing between 3 nodes, 2 read or write speed of client increase to 50MB/s, and 1 all network interface cards of node load at this time is all compared
It is higher, the connection of client on Target2 3 can be disconnected by calculating and Target2 is moved into node 2, at this time client
3 meeting Auto-reconnect Target2 of end, node 2 can repeat real time load isostatic hypothesis in 1 node and select network interface card 3, while node 1
Load balancing in node can be carried out, final result is as shown in Figure 7.
In conclusion the foregoing is merely a prefered embodiment of the invention, it is not intended to limit the scope of the present invention.
Within the spirit and principles of the invention, any modifications, equivalent replacements and improvements are made should be included in the present invention's
Within protection domain.
Claims (5)
1. a kind of ISCSI accesses load-balancing method, which is characterized in that including：
Each node of distributed memory system, is monitored the load of each network interface card in this node, when receiving client
During access request, connection is established using ISCSI redirection functions and the client using minimum network interface card is loaded in this node；
When the network interface card load that the node is monitored in this node is more than predetermined threshold value, one is selected from the connection on the network interface card
A connection for meeting default balanced adjustment condition, selected connection is disconnected；The balanced adjustment condition includes connection and corresponds to
Load be less than the threshold value with loading the sum of minimum load of network interface card in this node；
If the selection failure, the node select a node according to the loading condition of each node in system from system
As resource migration destination node, and a storage device is selected from the storage device of this node, disconnection accesses the storage and sets
Standby connection migrates selected storage device to the resource migration destination node.
2. according to the method described in claim 1, it is characterized in that, the node selects a node as current from system
Resource migration destination node include：
The node current load data of each node in acquisition system from the management node of system, and according to the load number
According to from other nodes in system, the node for selecting load minimum is as current resource migration destination node.
3. according to the method described in claim 2, it is characterized in that, the method is further included：
The load information of this node is reported to the pipe of system by each node in system when the load of this node changes
Node is managed, the management node is a node in system, and the load information includes at least the load of node and bears
Carry surplus.
4. according to the method described in claim 1, it is characterized in that, a storage is selected in the storage device from this node
Equipment includes：
Calculate the load value of each storage device in this node；
Determine the storage device for meeting transition condition in the storage device of this node；The transition condition is the load of storage device
For value less than the load surplus of the resource migration destination node, the load surplus is all on the resource migration destination node
The sum of remaining load of network interface card, the remaining load of each network interface card are the difference of the load of the threshold value and network interface card；
The storage device of quantity minimum will be connected in the storage device determined as selected storage device.
5. according to the method described in claim 1, it is characterized in that, the method is further included：
For each network interface card, the load of the network interface card is the sum of access speed of all clients for connecting the network interface card.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711402414.7A CN108055338B (en) | 2017-12-22 | 2017-12-22 | ISCSI access load balancing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711402414.7A CN108055338B (en) | 2017-12-22 | 2017-12-22 | ISCSI access load balancing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108055338A true CN108055338A (en) | 2018-05-18 |
| CN108055338B CN108055338B (en) | 2021-04-09 |
Family
ID=62131508
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711402414.7A Active CN108055338B (en) | 2017-12-22 | 2017-12-22 | ISCSI access load balancing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108055338B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108762924A (en) * | 2018-05-28 | 2018-11-06 | 郑州云海信息技术有限公司 | A kind of method, apparatus and computer readable storage medium of load balancing |
| CN109474700A (en) * | 2018-12-18 | 2019-03-15 | 创新科存储技术有限公司 | Cut-in method, storage medium, client and the memory node of iSCSI client |
| CN110611622A (en) * | 2018-06-15 | 2019-12-24 | 伊姆西Ip控股有限责任公司 | Method for load balancing, network interface card and computer program product |
| 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) |
| CN111752624A (en) * | 2020-05-18 | 2020-10-09 | 深圳市东微智能科技股份有限公司 | Centralized control method and system for multiple devices and readable storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1852502A (en) * | 2006-05-29 | 2006-10-25 | 杭州华为三康技术有限公司 | Method for realizing load uniform in clustering system, system and storage controller |
| US20090103432A1 (en) * | 2007-05-11 | 2009-04-23 | Incipient, Inc. | Non-disruptive data path upgrade using target mobility |
| CN101488918A (en) * | 2009-01-09 | 2009-07-22 | 杭州华三通信技术有限公司 | Multi-network card server access method and system |
| EP2302837A1 (en) * | 2009-09-23 | 2011-03-30 | Ixia | Network testing using control plane and data plane convergence |
| CN102123179A (en) * | 2011-03-28 | 2011-07-13 | 中国人民解放军国防科学技术大学 | Load balancing method and system applied to distributed application system |
| EP2510455A1 (en) * | 2009-12-09 | 2012-10-17 | Scality, SA | Probabilistic offload engine for distributed hierarchical object storage devices |
| CN103220354A (en) * | 2013-04-18 | 2013-07-24 | 广东宜通世纪科技股份有限公司 | Method for achieving load balancing of server cluster |
| CN103596290A (en) * | 2013-10-24 | 2014-02-19 | 西南交通大学 | Wireless multi-network integration method |
| US8874459B1 (en) * | 2008-07-31 | 2014-10-28 | American Airlines, Inc. | System and method for providing flight data services |
| CN107592370A (en) * | 2017-10-31 | 2018-01-16 | 郑州云海信息技术有限公司 | A kind of network load balancing method and device |
-
2017
- 2017-12-22 CN CN201711402414.7A patent/CN108055338B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1852502A (en) * | 2006-05-29 | 2006-10-25 | 杭州华为三康技术有限公司 | Method for realizing load uniform in clustering system, system and storage controller |
| US20090103432A1 (en) * | 2007-05-11 | 2009-04-23 | Incipient, Inc. | Non-disruptive data path upgrade using target mobility |
| US8874459B1 (en) * | 2008-07-31 | 2014-10-28 | American Airlines, Inc. | System and method for providing flight data services |
| CN101488918A (en) * | 2009-01-09 | 2009-07-22 | 杭州华三通信技术有限公司 | Multi-network card server access method and system |
| EP2302837A1 (en) * | 2009-09-23 | 2011-03-30 | Ixia | Network testing using control plane and data plane convergence |
| EP2510455A1 (en) * | 2009-12-09 | 2012-10-17 | Scality, SA | Probabilistic offload engine for distributed hierarchical object storage devices |
| CN102123179A (en) * | 2011-03-28 | 2011-07-13 | 中国人民解放军国防科学技术大学 | Load balancing method and system applied to distributed application system |
| CN103220354A (en) * | 2013-04-18 | 2013-07-24 | 广东宜通世纪科技股份有限公司 | Method for achieving load balancing of server cluster |
| CN103596290A (en) * | 2013-10-24 | 2014-02-19 | 西南交通大学 | Wireless multi-network integration method |
| CN107592370A (en) * | 2017-10-31 | 2018-01-16 | 郑州云海信息技术有限公司 | A kind of network load balancing method and device |
Non-Patent Citations (2)
| Title |
|---|
| GUANG YANG: "Dynamic Load-Balancing in iSCSI Systems Based on a Feedback Control Mechanism", < 2011 FIFTH INTERNATIONAL CONFERENCE ON MANAGEMENT OF E-COMMERCE AND E-GOVERNMENT> * |
| 张燕鹏: "基于Web服务器集群负载均衡技术的研究与应用", <信息科技辑> * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108762924A (en) * | 2018-05-28 | 2018-11-06 | 郑州云海信息技术有限公司 | A kind of method, apparatus and computer readable storage medium of load balancing |
| CN110611622A (en) * | 2018-06-15 | 2019-12-24 | 伊姆西Ip控股有限责任公司 | Method for load balancing, network interface card and computer program product |
| CN109474700A (en) * | 2018-12-18 | 2019-03-15 | 创新科存储技术有限公司 | Cut-in method, storage medium, client and the memory node of iSCSI client |
| CN109474700B (en) * | 2018-12-18 | 2021-09-24 | 创新科技术有限公司 | Access method of iSCSI client, storage medium, client and storage node |
| 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) |
| CN111752624A (en) * | 2020-05-18 | 2020-10-09 | 深圳市东微智能科技股份有限公司 | Centralized control method and system for multiple devices and readable storage medium |
| CN111752624B (en) * | 2020-05-18 | 2023-09-05 | 深圳市东微智能科技股份有限公司 | Centralized control method and system for multiple devices and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108055338B (en) | 2021-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108055338A (en) | A kind of ISCSI accesses load-balancing method | |
| CN102469023B (en) | Based on the dispatching method of cloud computing, unit and system | |
| CN104283948B (en) | Server cluster system and its implementation of load balancing | |
| CN103369601B (en) | For cell-phone customer terminal provides the method for large concurrent processing and flow control | |
| CN1146186C (en) | Virtual enclosed cluster capable of recovery | |
| CN108206852A (en) | A kind of dialogue-based Service Instance management method and equipment under micro services frame | |
| EP2515504B1 (en) | Content delivery method, system and schedule server | |
| CN101873224A (en) | Cloud computing load balancing method and equipment | |
| CN103067293A (en) | Method and system for multiplex and connection management of a load balancer | |
| CN108200218B (en) | Method and device for realizing load balance and electronic equipment | |
| JP2018518736A (en) | Receive buffer credits over multiple channels of one or more host computing devices to transmit data to the control unit | |
| CN103227754A (en) | Dynamic load balancing method of high-availability cluster system, and node equipment | |
| CN102281190A (en) | Networking method for load balancing apparatus, server and client access method | |
| CN102970379A (en) | Method for realizing load balance among multiple servers | |
| CN104980494B (en) | A kind of cloud storage download shared platform and method with local cache | |
| CN106375395A (en) | Load balancing method and system for node servers | |
| US20150312343A1 (en) | Parallel i/o read processing for use in clustered file systems having cache storage | |
| CN108270818A (en) | A kind of micro services architecture system and its access method | |
| CN109474700B (en) | Access method of iSCSI client, storage medium, client and storage node | |
| CN104852859B (en) | A kind of aggregation interface method for processing business and equipment | |
| CN109358971A (en) | Quick and load balancing service function chain dispositions method in dynamic network environment | |
| CN108228393A (en) | A kind of implementation method of expansible big data High Availabitity | |
| CN105207947A (en) | rogressive flow scheduling method and system capable of filtering vibration | |
| CN108737573A (en) | A kind of distributed storage cluster and its service response control method, device and equipment | |
| CN108055314A (en) | The management method and group system of a kind of group system |
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 | ||
| CB02 | Change of applicant information |
Address after: Room 505, Taixing Building, 11 Garden East Road, Haidian District, Beijing, 100191 Applicant after: Innovation Technology Co., Ltd. Address before: Room 0801-0805, 51 College Road, Haidian District, Beijing, 100191 Applicant before: Innovation and Technology Storage Technology Co., Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |