CN103118124A - Cloud computing load balancing method based on layering multiple agents - Google Patents
Cloud computing load balancing method based on layering multiple agents Download PDFInfo
- Publication number
- CN103118124A CN103118124A CN2013100565252A CN201310056525A CN103118124A CN 103118124 A CN103118124 A CN 103118124A CN 2013100565252 A CN2013100565252 A CN 2013100565252A CN 201310056525 A CN201310056525 A CN 201310056525A CN 103118124 A CN103118124 A CN 103118124A
- Authority
- CN
- China
- Prior art keywords
- task
- resource
- virtual machine
- node
- sub agent
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Multi Processors (AREA)
Abstract
The invention relates to a cloud computing load balancing method based on layering multiple agents. Two of a plurality of nodes which are connected with a cloud computing platform through the network are used as a task monitoring agent and a resource monitoring agent, 1-n nodes of a task agent layer in the task monitoring agent are task subagents, 1-m nodes of a resource agent layer in the resource monitoring agent are resource subagent, agents are jointly management nodes of the cloud computing platform, each management node performs task allocation according load conditions, different management nodes respectively take charge of task monitoring, resource monitoring, resource allocating and the like, the management nodes at different layers have different functions, and the upper layer management nodes and the lower layer management nodes mutually report task information and resource information and cooperation with each other, so that a plurality of cloud computing tasks can be concurrently and effectively processed, load balancing of the cloud computing platform is achieved, and task processing capacity of the cloud computing platform is improved.
Description
Technical field
The present invention relates to a kind of cloud computing method for scheduling task, relate in particular to a kind of cloud computing load balancing method based on the many agencies of layering.
Background technology
Along with the explosive increase of network size and speed, traditional data are processed and method of service is difficult to resist, so cloud computing is arisen at the historic moment.Cloud computing is transferred to data handling procedure the cloud computing cluster that on the Internet, a plurality of nodes consist of from personal computer or server, cluster is by a certain central server unified management, this is the centre management node, respectively forms cloud computing platform from node in centre management node and network.The centre management node distributes the resource of cloud computing platform by the task of client's proposition, finally can reach the effect identical with supercomputer, effectively solves the problems such as mass data processing.
The key problem of cloud computing technology is exactly the resource management of platform, and its target is exactly the rational management by resource, makes cloud computing platform Processing tasks efficiently.
In cloud computing environment, when facing the mission requirements of magnanimity, the situation of resource unreasonable distribution can appear.What have is idle for a long time from the resource of node, have from node because its resource frequently is used, load is overweight, each is from the unbalanced task disposal ability that has had a strong impact on cloud computing platform of node load.Therefore rational load balancing must be arranged, make resource divide timing each load balancing from node, could improve the operational efficiency of cloud computing platform.
the method that multiple cloud computing platform task is processed has now appearred, it is 201210236332 Chinese invention patent application " cloud computing resources distribution method " as the patent No., the patent No. is 201210472862.5 Chinese invention patent application " resource allocation methods in cloud computing system ", the patent No. is 201010199455.2 Chinese invention patent application " a kind of cloud computing load balancing method and equipment ", the patent No. is 201110051656.2 Chinese invention patent application " based on the network load balancing method of cloud computing ", the patent No. is 201210116060.0 Chinese invention patent application " implementation of load balancing under a kind of cloud computing environment " etc.Above method can be summarized as: calculate from the current loading condition of node by obtaining respectively the performance parameter from node (1), and by certain selection strategy, and selecting suitable provides the Energy Resources Service should front task from node; (2) by Intel Virtualization Technology, virtual resource is dispatched, by increase and decrease and the dynamic migration of virtual machine, guaranteed that each is from the load balancing of node; (3) based on the SLA(service-level agreement) load balancing, to guarantee SLA as purpose, each load from node is evaluated and optimized.
In the cloud computing platform framework, carry out the management of platform in the centre management set of node, be namely a kind of way to manage of master slave mode.The centre management node is as host node, and other node of platform is as from node, by the unification of centre management node to managing from node.Under this way to manage, the centre management node need to constantly be monitored implementation status from node load state, task, resource is carried out dispatching distribution etc., the computing cost that these tasks are brought is very large, causes in cloud computing platform, and the load pressure of centre management node is very heavy.The method of above-mentioned solution load balancing is all only to have considered respectively from the problem of load balancing between node, and has ignored the loading condition of centre management node.The centre management node will be disposed and complete above-mentioned load balancing, and its burden can further increase the weight of, and causes its operational efficiency step-down, even paralysis.
Therefore, need at present can the balance cloud computing platform each from the load between node, can effectively share again the load of centre management node, adapt to the cloud computing load balancing method of the lifting task disposal ability of actual demand.
Summary of the invention
the objective of the invention is for the deficiencies in the prior art, a kind of cloud computing load balancing method based on the many agencies of layering is provided, a plurality of agencies of layering are set bear the centre management monitoring nodes of present cloud computing platform from the node load state, the implementation status of task, resource is carried out the work of dispatching distribution, by mutually exchanging between many agencies, collaborative work, walk abreast and process efficiently a plurality of cloud computing tasks, each layer proxy carries out the distribution of task according to loading condition, effective load sharing, realize each node load balancing of cloud computing platform, promote the task disposal ability of cloud computing platform.
to achieve these goals, a kind of cloud computing load balancing method based on the many agencies of layering of the present invention's design, cloud computing platform contains a plurality of nodes that connect through network, wherein 2 nodes are respectively task monitoring control agency and monitoring resource agency, under task monitoring control agency, the task agent layer is set, it is the task sub agent that the task agent layer has 1～n node, under the monitoring resource agency, the Resource Broker layer is set, it is the resource sub agent that the Resource Broker layer has 1～m node, the monitoring resource agency, 1～n task sub agent of task monitoring control agency and lower floor thereof, 1～m resource sub agent is the management node of cloud computing platform jointly, the physical resource layer have 1～M possess computational resource from node, 1～N the waiting task that has the client to submit in task pool, the present invention includes following steps:
The current task information of S1, Mission Monitor agents monitor task pool, the present load information of each task sub agent, the current virtual resource information in virtual resource pond are regularly to the current virtual resource information of all task sub agent circulars;
S2, Mission Monitor agency give respectively priority with each waiting task current in task pool, and certain waiting task are distributed to certain task sub agent;
The task sub agent of S3, reception task creates virtual machine according to mission requirements, the operation of monitoring virtual machine, and the tasks carrying information reporting is acted on behalf of to Mission Monitor;
S4, monitoring resource agency collect respectively from node present load information, regularly circulate a notice of respectively from node present load information to all resource sub agents, simultaneously the present load information of each resource sub agent of monitoring resource agents monitor;
S5, monitoring resource agency will be virtualized into virtual resource information from node resource, send to the virtual resource pond of virtual resource layer, and according to the virtual machine information that the task sub agent is sent, divide virtual resource;
S6, monitoring resource are acted on behalf of according to the agent selection strategy, select certain resource sub agent to dispose virtual machine;
Described agent selection strategy is specially: all resource sub agent load M of monitoring resource agents monitor
1, M
2M
m, comparing its load, the virtual machine information that certain task sub agent is sent sends to the minimum resource sub agent of load;
S7, disposed virtual machine by the resource sub agent of monitoring resource agent selection, and monitor this virtual machine operation, simultaneously to the task sub agent feedback tasks carrying information that creates this virtual machine.
In described step S1, the current mission bit stream of Mission Monitor agents monitor task pool comprises deadline, task length, the internal memory of task needs, hard disk, the network bandwidth of task; The present load information of task sub agent comprises the current CPU usage of task sub agent, memory usage, task queue length, response time; Virtual resource information comprises cpu frequency, memory size, hard disk size, the network bandwidth after virtual.
Described step S2 specifically comprises following substep:
S21, Mission Monitor agents monitor task pool read current waiting task in task pool, obtain each waiting task T deadline
1
S22, Mission Monitor agency be T deadline of certain waiting task x relatively
1xWith current time T
2Determine this task priority G
x, x is the Arbitrary Digit in 1～N, the priority specific formula for calculation of waiting task x is: G
x=T
1x-T
2, priority G is less shows that this priority of task rank is higher;
S23, Mission Monitor agency read the priority G of waiting task in task pool
1, G
2G
N, compare its priority, the task that the priority treatment priority level is high;
S24, all task sub agent load L of Mission Monitor agents monitor
1, L
2L
n, relatively its load, be distributed to the minimum task sub agent of load with task;
S25, Mission Monitor agency collect the tasks carrying information of each task sub agent report;
In described substep S24, the specific formula for calculation of certain task sub agent i load is: L
iThe response time of the task queue length of the memory usage of the CPU usage of=a1* task sub agent i+a2* task sub agent i+a3* task sub agent i+a4* task sub agent i, wherein i is the Arbitrary Digit in 1～n, a1, a2, a3, a4 are the load calculation weights, more than or equal to 0 and satisfy a1+a2+a3+a4=1.
Described step S3 specifically comprises following substep:
S31, task sub agent calculate required virtual machine information according to receiving of task, create virtual machine;
S32, task sub agent be according to the virtual resource information of receiving from the Mission Monitor agency, and whether judge in the virtual resource pond has enough virtual resources to satisfy this virtual machine; If have, this virtual machine information is sent to the monitoring resource agency, if do not have, after waiting for the virtual resource information updating, again judge;
If S33 task sub agent is received virtual resource and is divided successful information, execution in step S34; If the task sub agent is received virtual resource and is divided failure information, execution in step S32;
S34, task sub agent monitor the running status of the virtual machine of its establishment;
After S35, task sub agent monitor the virtual machine activation of its establishment, task is sent on this virtual machine carry out;
S36, task sub agent are collected tasks carrying information from corresponding resource sub agent, report to the Mission Monitor agency;
S37, task sub agent are cancelled its establishment when task is finished virtual machine.
In described substep S31, virtual machine information comprises virtual machine cpu frequency, memory size, hard disk size, the network bandwidth; The specific formula for calculation of virtual machine information is: virtual machine cpu frequency=task length/task priority G, virutal machine memory=required by task internal memory, virtual hard disk=required by task hard disk, virtual machine network bandwidth=required by task network bandwidth.Resources of virtual machine demand Q=(virtual machine cpu frequency, virutal machine memory, virtual hard disk, virtual machine network bandwidth).
In described step S4, certain comprises cpu frequency, memory size, hard disk size, the network bandwidth, CPU usage, memory usage, hard disk utilization rate, network usage from node load information; The load information of resource sub agent comprises CPU usage, memory usage, virtual machine queue length, the response time of resource sub agent.
Described step S5 specifically comprises following substep:
S51, monitoring resource agency will respectively be virtualized into virtual resource information from node load information, send to the virtual resource pond of virtual resource layer;
S52, monitoring resource agency receive the virtual machine information that certain task sub agent sends, and check virtual resource information, for this virtual machine is divided virtual resource; As divide successfully execution in step S53; As divide failure, execution in step S54;
S53, monitoring resource agency adds the virtual resource pond with this virtual machine, upgrades virtual resource information, and virtual resource is divided successful information sends to and create described virtual machine task sub agent;
S54, monitoring resource agency send virtual resource and divide failure information to the task sub agent that creates described virtual machine;
After S55, monitoring resource agency receives certain virtual machine revocation information, this virtual machine is deleted from the virtual resource pond, and upgraded virtual resource information.
In described step S6, the specific formula for calculation of certain resource sub agent j load is: M
jThe response time of the virtual machine queue length of the memory usage of the CPU usage of=b1* resource sub agent j+b2* resource sub agent j+b3* resource sub agent j+b4* resource sub agent j, wherein j is the Arbitrary Digit of 1～m, b1, b2, b3, b4 are the load calculation weights, more than or equal to 0 and satisfy b1+b2+b3+b4=1.
Described step S7 specifically comprises following substep:
S71, received by the resource sub agent of monitoring resource agent selection current from node load information and virtual machine information that the monitoring resource agency sends;
S72, described resource sub agent are according to calculating each from node present load O from node load information
1, O
2O
MWith available resources P
1, P
2P
M
S73, described resource sub agent be available resources P relatively
1, P
2P
MSize with resources of virtual machine demand Q satisfies P
kThe feasible from node of virtual machine disposed in being called from node of 〉=Q condition;
S74, described resource sub agent be all feasible present loads from node relatively, select the feasible from node of least-loaded, dispose current virtual machine;
S75, described resource sub agent start current virtual machine, monitor this virtual machine running status;
S76, described resource sub agent are collected current task from this virtual machine and are carried out information, feed back to the task sub agent that creates this virtual machine;
S77, described resource sub agent monitor this virtual machine cancel after, discharge that this virtual machine disposes from node resource, and this virtual machine revocation information is sent to the monitoring resource agency.
In described substep S72, certain specific formula for calculation from node k present load is: O
kThe network usage of the memory usage+r3* of=r1* from CPU usage+r2* of node k from node k from hard disk utilization rate+r4* of node k from node k, wherein, k is the Arbitrary Digit of 1～M, and r1, r2, r3, r4 are the load calculation weights, more than or equal to 0 and satisfy r1+r2+r3+r4=1; Certain specific formula for calculation from node k current available resource is: P
k={ from the cpu frequency * (1-is from the CPU usage of node k) of node k, memory size * (1-is from the memory usage of node k) from node k, from the hard disk size * (1-is from the hard disk utilization rate of node k) of node k, from the network bandwidth * (1-is from the network usage of node k) of node k }.
Compared with prior art, a kind of advantage based on the layering cloud computing load balancing methods of acting on behalf of of the present invention is more: 1, adopt layering to act on behalf of more, the management work of existing cloud computing platform centre management node is shared jointly by a plurality of management nodes, the management node of different levels has different functions, mutually circulate a notice of mission bit stream and resource information between the levels management node, coordinate between a plurality of management nodes, concurrent and process efficiently a plurality of cloud computing tasks, promote the task disposal ability of cloud computing platform; 2, each management node carries out task according to loading condition and distributes, and is responsible for respectively Mission Monitor, monitoring resource, resource distribution etc. by different management nodes, and effective load sharing is realized the load balancing of cloud computing platform.
Description of drawings
Fig. 1 is that this is based on the many agencies' of layering cloud computing load balancing method embodiment cloud computing platform general structure block diagram;
Fig. 2 is Mission Monitor factorage flow chart in Fig. 1;
Fig. 3 is the task sub agent workflow diagram in Fig. 1;
Fig. 4 is the monitoring resource factorage flow chart in Fig. 1;
Fig. 5 is the resource sub agent workflow diagram in Fig. 1;
The load balancing degrees comparative graph of Fig. 6 node when to be this use on identical cloud computing platform with the static load balancing method based on cloud computing load balancing method embodiment of the many agencies of layering.
Embodiment
Below in conjunction with accompanying drawing, provide specific embodiments of the invention, the present invention is described in further detail.Need to prove: the present invention is not limited to the following examples.
this is based on the many agencies' of layering cloud computing load balancing method embodiment, the cloud computing platform general structure as shown in Figure 1, contain a plurality of nodes that connect through network, wherein 2 nodes are respectively task monitoring control agency and monitoring resource agency, under task monitoring control agency, the task agent layer is set, it is the task sub agent that the task agent layer has 1～n node, under the monitoring resource agency, the Resource Broker layer is set, it is the resource sub agent that the Resource Broker layer has 1～m node, the monitoring resource agency, 1～n task sub agent of task monitoring control agency and lower floor thereof, 1～m resource sub agent is the management node of cloud computing platform jointly, the physical resource layer have 1～M possess computational resource from node, 1～N the waiting task that has the client to submit in task pool.
In order to illustrate that more clearly this is based on cloud computing load balancing methods of the many agencies of layering, by cloud computing emulation platform CloudSim simulated experimental environments.N=4 in this example, m=4, the CPU of task agent monitoring, Resource Broker monitoring, task sub agent, resource sub agent, internal memory, hard disk, network bandwidth parameter generate within the specific limits at random.M=30, its CPU, internal memory, hard disk, network bandwidth parameter generate within the specific limits at random.N=100, its task length, required memory, hard disk, bandwidth parameter generate within the specific limits at random, the time t1 that appointed task arrives task pool generates between scope [0:00-0:15] at random, task t2 deadline generates between time range [0:05-0:20] at random, in order to guarantee between t1 and t2 to have the time interval of executing the task, generate t1 at random and t2 satisfies condition: t1+5＜=t2.
This example comprises the steps:
The current task information of S1, Mission Monitor agents monitor task pool, the present load information of each task sub agent, the current virtual resource information in virtual resource pond are regularly to the current virtual resource information of all task sub agent circulars;
Wherein the current mission bit stream of Mission Monitor agents monitor task pool comprises deadline, task length, the internal memory of task needs, hard disk, the network bandwidth of task; The present load information of task sub agent comprises the current CPU usage of task sub agent, memory usage, task queue length, response time; Virtual resource information comprises cpu frequency, memory size, hard disk size, the network bandwidth after virtual.
S2, Mission Monitor agency give respectively priority with each waiting task current in task pool, and certain waiting task are distributed to certain task sub agent;
Specifically comprise following substep, its workflow as shown in Figure 2,
S21, Mission Monitor agents monitor task pool read current waiting task in task pool, obtain each waiting task T deadline
1
S22, Mission Monitor agency be T deadline of certain waiting task x relatively
1xWith current time T
2Determine the priority Gx of this task, x is the Arbitrary Digit in 1～N, and the priority specific formula for calculation of waiting task x is: G
x=T
1x-T
2, priority G is less shows that this priority of task rank is higher;
Suppose current time T
2Be 0:00, two task A and B are arranged, T deadline of task A
1ABe 0:05, T deadline of task B
1BBe 0:10.Can calculate so the priority G of task A
A=5min, the priority G of task B
B=10min is due to G
A＜G
B, so the priority of task A is high.
S23, Mission Monitor agency read the priority G of waiting task in task pool
1, G
2G
N, compare its priority, the task that the priority treatment priority level is high;
S24, all task sub agent load L of Mission Monitor agents monitor
1, L
2L
n, relatively its load, be distributed to the minimum task sub agent of load with task;
S25, Mission Monitor agency collect the tasks carrying information of each task sub agent report;
In described substep S24, the specific formula for calculation of certain task sub agent i load is: L
iThe response time of the task queue length of the memory usage of the CPU usage of=a1* task sub agent i+a2* task sub agent i+a3* task sub agent i+a4* task sub agent i, wherein i is the Arbitrary Digit in 1～n, a1, a2, a3, a4 are the load calculation weights, more than or equal to 0 and satisfy a1+a2+a3+a4=1.Weights a1=0.3 for example, a2=0.3, a3=0.2, a4=0.2.
The task sub agent of S3, reception task creates virtual machine according to mission requirements, the operation of monitoring virtual machine, and the tasks carrying information reporting is acted on behalf of to Mission Monitor;
Described step S3 specifically comprises following substep, its workflow as shown in Figure 3,
S31, task sub agent calculate required virtual machine information according to receiving of task, create virtual machine;
Described virtual machine information comprises virtual machine cpu frequency, memory size, hard disk size, the network bandwidth; The specific formula for calculation of virtual machine information is: virtual machine cpu frequency=task length/task priority G, virutal machine memory=required by task internal memory, virtual hard disk=required by task hard disk, virtual machine network bandwidth=required by task network bandwidth.Resources of virtual machine demand Q=(virtual machine cpu frequency, virutal machine memory, virtual hard disk, virtual machine network bandwidth).
Suppose that the task sub agent learns from the mission bit stream of task A, task length is 30,000 hundred ten thousand instructions, and required memory, hard disk, the network bandwidth are respectively 512MB, 4GB, 10Mbit/s, and its priority provides G by the Mission Monitor agency
A=5min.The required by task virtual machine information can draw by calculating: 1,000,000 instruction/5min=100MIPS(million instructions per seconds of virtual machine cpu frequency=30000), virutal machine memory=512MB, virtual hard disk=4GB, virtual machine network bandwidth=10Mbit/s, resources of virtual machine demand Q=(100MIPS, 512MB, 4GB, 10Mbit/s)
S32, task sub agent be according to the virtual resource information of receiving from the Mission Monitor agency, and whether judge in the virtual resource pond has enough virtual resources to satisfy this virtual machine; If have, this virtual machine information is sent to the monitoring resource agency, if do not have, after waiting for the virtual resource information updating, again judge;
If S33 task sub agent is received virtual resource and is divided successful information, execution in step S34; If the task sub agent is received virtual resource and is divided failure information, execution in step S32;
S34, task sub agent monitor the running status of the virtual machine of its establishment;
After S35, task sub agent monitor the virtual machine activation of its establishment, task is sent on this virtual machine carry out;
S36, task sub agent are collected tasks carrying information from corresponding resource sub agent, report to the Mission Monitor agency;
S37, task sub agent are cancelled its establishment when task is finished virtual machine.
S4, monitoring resource agency collect respectively from node present load information, regularly circulate a notice of respectively from node present load information to all resource sub agents, simultaneously the present load information of each resource sub agent of monitoring resource agents monitor;
Certain comprises cpu frequency, memory size, hard disk size, the network bandwidth, CPU usage, memory usage, hard disk utilization rate, network usage from node load information; The load information of resource sub agent comprises CPU usage, memory usage, virtual machine queue length, the response time of resource sub agent.
S5, monitoring resource agency will be virtualized into virtual resource information from node resource, send to the virtual resource pond of virtual resource layer, and according to the virtual machine information that the task sub agent is sent, divide virtual resource;
Specifically comprise following substep, its workflow as shown in Figure 4,
S51, monitoring resource agency will respectively be virtualized into virtual resource information from node load information, send to the virtual resource pond of virtual resource layer;
S52, monitoring resource agency receive the virtual machine information that certain task sub agent sends, and check virtual resource information, for this virtual machine is divided virtual resource; As divide successfully execution in step S53; As divide failure, execution in step S54;
S53, monitoring resource agency adds the virtual resource pond with this virtual machine, upgrades virtual resource information, and virtual resource is divided successful information sends to and create described virtual machine task sub agent;
S54, monitoring resource agency send virtual resource and divide failure information to the task sub agent that creates described virtual machine;
After S55, monitoring resource agency receives certain virtual machine revocation information, this virtual machine is deleted from the virtual resource pond, and upgraded virtual resource information.
S6, monitoring resource are acted on behalf of according to the agent selection strategy, select certain resource sub agent to dispose virtual machine;
The agent selection strategy is specially: all resource sub agent load M of monitoring resource agents monitor
1, M
2M
m, comparing its load, the virtual machine information that certain task sub agent is sent sends to the minimum resource sub agent of load; The specific formula for calculation of certain resource sub agent j load is: M
jThe response time of the virtual machine queue length of the memory usage of the CPU usage of=b1* resource sub agent j+b2* resource sub agent j+b3* resource sub agent j+b4* resource sub agent j, wherein j is the Arbitrary Digit of 1～m, b1, b2, b3, b4 are the load calculation weights, more than or equal to 0 and satisfy b1+b2+b3+b4=1.
S7, disposed virtual machine by the resource sub agent of monitoring resource agent selection, and monitor this virtual machine operation, simultaneously to the task sub agent feedback tasks carrying information that creates this virtual machine.
Specifically comprise following substep, its workflow as shown in Figure 5,
S71, received by the resource sub agent of monitoring resource agent selection current from node load information and virtual machine information that the monitoring resource agency sends;
S72, described resource sub agent are according to calculating each from node present load O from node load information
1, O
2O
MWith available resources P
1, P
2P
M
Certain specific formula for calculation from node k present load is: O
kThe network usage of the memory usage+r3* of=r1* from CPU usage+r2* of node k from node k from hard disk utilization rate+r4* of node k from node k, wherein, k is the Arbitrary Digit of 1～M, and r1, r2, r3, r4 are the load calculation weights, more than or equal to 0 and satisfy r1+r2+r3+r4=1; Certain specific formula for calculation from node k current available resource is: P
k={ from the cpu frequency * (1-is from the CPU usage of node k) of node k, memory size * (1-is from the memory usage of node k) from node k, from the hard disk size * (1-is from the hard disk utilization rate of node k) of node k, from the network bandwidth * (1-is from the network usage of node k) of node k }.
Suppose from node Y, cpu frequency be 300MIPS, CPU usage 50%, in to save as 2GB, memory usage 60%, hard disk 100GB, hard disk utilization rate 30%, the network bandwidth be 100Mbit/s, utilization rate 20%.Can be calculated from nodal information by above, from node Y present load O
Y=0.3*50+0.3*60+0.2*30+0.2*20=43 is from node Y current available resource P
Y={ 150MIPS, 800MB, 70GB, 80Mbit/s}.
S73, described resource sub agent be available resources P relatively
1, P
2P
MSize with resources of virtual machine demand Q satisfies P
kThe feasible from node of virtual machine disposed in being called from node k of 〉=Q condition;
For example compare substep 72 gained P
Y={ 150MIPS, 800MB, 70GB, 80Mbit/s} and substep 37 gained virtual machine demand resource Q={100MIPS, 512MB, 4GB, 10Mbit/s}, P
YFor disposing the feasible from node of virtual machine.
S74, described resource sub agent be all feasible present loads from node relatively, select the feasible from node of least-loaded, dispose current virtual machine;
Feasible from the current load of node, feasible from node P by comparing each
YPresent load O
YBe minimum, so the resource sub agent just with deploying virtual machine at P
YUpper operation
S75, described resource sub agent start current virtual machine, monitor this virtual machine running status;
S76, described resource sub agent are collected current task from this virtual machine and are carried out information, feed back to the task sub agent that creates this virtual machine;
S77, described resource sub agent monitor this virtual machine cancel after, discharge that this virtual machine disposes from node resource, and this virtual machine revocation information is sent to the monitoring resource agency.
In order to assess the validity of load-balancing method of the present invention, introduce load balancing degrees as evaluation index, it is defined as the variance of the load of each node of t constantly, and its computing formula is as follows:
In following formula, m is number of nodes, Load
iBe the load of node i, Load
avgBe all node average loads, load balancing degrees is less, and the load between the expression node is more balanced.
For the ease of comparing, experimental situation by cloud computing emulation platform CloudSim simulation Comparative Examples static load balancing method (Static), its physical layer node number is also 30, the CPU of centre management node, internal memory, hard disk, network bandwidth parameter generate within the specific limits at random, the task queue number is 100, and its task length, required memory, hard disk, bandwidth parameter are identical with the present embodiment.
In 20 minutes of time range [0:00-0:20], when the many agencies' of layering load-balancing method (Multi_Agent) and static load balancing method (Static) are used on cloud computing platform, the load balancing degrees curve of node as shown in Figure 6, in figure, abscissa is the time, unit is a minute m, ordinate is load balancing degrees LB, " zero " line is the load balancing degrees curve of static load balancing method node, and " rice " line is the load balancing degrees curve of the many agencies' of this layering load-balancing method node.
As seen from Figure 6, load-balancing method based on the many agencies of layering is compared with the static load balancing method, its load balancing degrees is lower, not only effectively shared computational load from node, and effectively shared the load management of centre management node due to each management nodes of many agencies, make the load of whole cloud computing platform more balanced.Lower load balancing degrees also shows, can make cloud computing platform can also accept and process more task at one time based on the many agencies' of layering load-balancing methods, promoted the disposal ability of cloud computing platform.
Above-described embodiment is only the specific case that purpose of the present invention, technical scheme and beneficial effect are further described, and the present invention is defined in this.All any modifications of making, be equal to replacement, improvement etc., within all being included in protection scope of the present invention within scope of disclosure of the present invention.
Claims (11)
1. cloud computing load balancing methods based on the many agencies of layering, cloud computing platform contains a plurality of nodes that connect through network, it is characterized in that:
in described cloud computing platform, 2 nodes are respectively task monitoring control agency and monitoring resource agency, under task monitoring control agency, the task agent layer is set, it is the task sub agent that the task agent layer has 1～n node, under the monitoring resource agency, the Resource Broker layer is set, it is the resource sub agent that the Resource Broker layer has 1～m node, the monitoring resource agency, 1～n task sub agent of task monitoring control agency and lower floor thereof, 1～m resource sub agent is the management node of cloud computing platform jointly, the physical resource layer have 1～M possess computational resource from node, 1～N the waiting task that has the client to submit in task pool, cloud computing load balancing method based on the many agencies of layering comprises the steps:
The current task information of S1, Mission Monitor agents monitor task pool, the present load information of each task sub agent, the current virtual resource information in virtual resource pond are regularly to the current virtual resource information of all task sub agent circulars;
S2, Mission Monitor agency give respectively priority with each waiting task current in task pool, and certain waiting task are distributed to certain task sub agent;
The task sub agent of S3, reception task creates virtual machine according to mission requirements, the operation of monitoring virtual machine, and the tasks carrying information reporting is acted on behalf of to Mission Monitor;
S4, monitoring resource agency collect respectively from node present load information, regularly circulate a notice of respectively from node present load information to all resource sub agents, simultaneously the present load information of each resource sub agent of monitoring resource agents monitor;
S5, monitoring resource agency will be virtualized into virtual resource information from node resource, send to the virtual resource pond of virtual resource layer, and according to the virtual machine information that the task sub agent is sent, divide virtual resource;
S6, monitoring resource are acted on behalf of according to the agent selection strategy, select certain resource sub agent to dispose virtual machine;
Described agent selection strategy is specially: all resource sub agent load M of monitoring resource agents monitor
1, M
2M
m, comparing its load, the virtual machine information that certain task sub agent is sent sends to the minimum resource sub agent of load;
S7, disposed virtual machine by the resource sub agent of monitoring resource agent selection, and monitor this virtual machine operation, simultaneously to the task sub agent feedback tasks carrying information that creates this virtual machine.
2. according to claim 1 based on the layering cloud computing load balancing methods of acting on behalf of more, it is characterized in that:
In described step S1, the current mission bit stream of Mission Monitor agents monitor task pool comprises deadline, task length, the internal memory of task needs, hard disk, the network bandwidth of task; The present load information of task sub agent comprises the current CPU usage of task sub agent, memory usage, task queue length, response time; Virtual resource information comprises cpu frequency, memory size, hard disk size, the network bandwidth after virtual.
3. according to claim 1 based on the layering cloud computing load balancing methods of acting on behalf of more, it is characterized in that:
Described step S2 specifically comprises following substep:
S21, Mission Monitor agents monitor task pool read waiting task in task pool, obtain each waiting task T deadline
1
S22, Mission Monitor agency be T deadline of certain waiting task x relatively
1xWith current time T
2Determine this task priority Gx, x is the Arbitrary Digit in 1～N, and the priority specific formula for calculation of waiting task x is: G
x=T
1x-T
2, priority G is less shows that this priority of task rank is higher;
S23, Mission Monitor agency read the priority G of waiting task in task pool
1, G
2G
N, compare its priority, the task that the priority treatment priority level is high;
S24, all task sub agent load L of Mission Monitor agents monitor
1, L
2L
n, relatively its load, be distributed to the minimum task sub agent of load with task;
The tasks carrying information of S25, the report of collection task sub agent.
4. according to claim 3 based on the layering cloud computing load balancing methods of acting on behalf of more, it is characterized in that:
In described substep S24, the specific formula for calculation of certain task sub agent i load is: L
iThe response time of the task queue length of the memory usage of the CPU usage of=a1* task sub agent i+a2* task sub agent i+a3* task sub agent i+a4* task sub agent i, wherein i is the Arbitrary Digit in 1～n, a1, a2, a3, a4 are the load calculation weights, more than or equal to 0 and satisfy a1+a2+a3+a4=1.
5. according to claim 1 based on the layering cloud computing load balancing methods of acting on behalf of more, it is characterized in that:
Described step S3 specifically comprises following substep:
S31, task sub agent calculate required virtual machine information according to receiving of task, create virtual machine;
S32, task sub agent be according to the virtual resource information of receiving from the Mission Monitor agency, and whether judge in the virtual resource pond has enough virtual resources to satisfy this virtual machine; If have, this virtual machine information is sent to the monitoring resource agency, if do not have, after waiting for the virtual resource information updating, again judge;
If S33 task sub agent is received virtual resource and is divided successful information, execution in step S34; If the task sub agent is received virtual resource and is divided failure information, execution in step S32;
S34, task sub agent monitor the running status of the virtual machine of its establishment;
After S35, task sub agent monitor the virtual machine activation of its establishment, task is sent on this virtual machine carry out;
S36, task sub agent are collected tasks carrying information from corresponding resource sub agent, report to the Mission Monitor agency;
S37, task sub agent are cancelled its establishment when task is finished virtual machine.
6. according to claim 5 based on the layering cloud computing load balancing methods of acting on behalf of more, it is characterized in that:
In described substep S31, virtual machine information comprises virtual machine cpu frequency, memory size, hard disk size, the network bandwidth; The specific formula for calculation of virtual machine information is: virtual machine cpu frequency=task length/task priority G, virutal machine memory=required by task internal memory, virtual hard disk=required by task hard disk, virtual machine network bandwidth=required by task network bandwidth; Resources of virtual machine demand Q=(virtual machine cpu frequency, virutal machine memory, virtual hard disk, virtual machine network bandwidth).
7. according to claim 1 based on the layering cloud computing load balancing methods of acting on behalf of more, it is characterized in that:
In described step S4, certain comprises cpu frequency, memory size, hard disk size, the network bandwidth, CPU usage, memory usage, hard disk utilization rate, network usage from node load information; The load information of resource sub agent comprises CPU usage, memory usage, virtual machine queue length, the response time of resource sub agent.
8. according to claim 1 based on the layering cloud computing load balancing methods of acting on behalf of more, it is characterized in that:
Described step S5 specifically comprises following substep:
S51, monitoring resource agency will respectively be virtualized into virtual resource information from node load information, send to the virtual resource pond of virtual resource layer;
S52, monitoring resource agency receive the virtual machine information that certain task sub agent sends, and check virtual resource information, for this virtual machine is divided virtual resource; As divide successfully execution in step S53; As divide failure, execution in step S54;
S53, monitoring resource agency adds the virtual resource pond with this virtual machine, upgrades virtual resource information, and virtual resource is divided successful information sends to and create described virtual machine task sub agent;
S54, monitoring resource agency send virtual resource and divide failure information to the task sub agent that creates described virtual machine;
After S55, monitoring resource agency receives certain virtual machine revocation information, this virtual machine is deleted from the virtual resource pond, and upgraded virtual resource information.
9. according to claim 1 based on the layering cloud computing load balancing methods of acting on behalf of more, it is characterized in that:
In described step S6, the specific formula for calculation of certain resource sub agent j load is: M
jThe response time of the virtual machine queue length of the memory usage of the CPU usage of=b1* resource sub agent j+b2* resource sub agent j+b3* resource sub agent j+b4* resource sub agent j, wherein j is the Arbitrary Digit of 1～m, b1, b2, b3, b4 are the load calculation weights, more than or equal to 0 and satisfy b1+b2+b3+b4=1.
10. according to claim 1 based on the layering cloud computing load balancing methods of acting on behalf of more, it is characterized in that:
Described step S7 specifically comprises following substep:
S71, received by the resource sub agent of monitoring resource agent selection current from node load information and virtual machine information that the monitoring resource agency sends;
S72, described resource sub agent are according to calculating each from node present load O from node load information
1, O
2O
MWith available resources P
1, P
2P
M
S73, described resource sub agent be available resources P relatively
1, P
2P
MSize with resources of virtual machine demand Q satisfies P
kThe feasible from node of virtual machine disposed in being called from node k of 〉=Q condition;
S74, described resource sub agent be all feasible present loads from node relatively, select the feasible from node of least-loaded, dispose current virtual machine;
S75, described resource sub agent start current virtual machine, monitor this virtual machine running status;
S76, described resource sub agent are collected current task from this virtual machine and are carried out information, feed back to the task sub agent that creates this virtual machine;
S77, described resource sub agent monitor this virtual machine cancel after, discharge that this virtual machine disposes from node resource, and this virtual machine revocation information is sent to the monitoring resource agency.
11. the cloud computing load balancing method based on the many agencies of layering according to claim 10 is characterized in that:
In described substep S72, certain specific formula for calculation from node k present load is: O
kThe network usage of the memory usage+r3* of=r1* from CPU usage+r2* of node k from node k from hard disk utilization rate+r4* of node k from node k, wherein, k is the Arbitrary Digit of 1～M, and r1, r2, r3, r4 are the load calculation weights, more than or equal to 0 and satisfy r1+r2+r3+r4=1; Certain specific formula for calculation from node k current available resource is: P
k={ from the cpu frequency * (1-is from the CPU usage of node k) of node k, memory size * (1-is from the memory usage of node k) from node k, from the hard disk size * (1-is from the hard disk utilization rate of node k) of node k, from the network bandwidth * (1-is from the network usage of node k) of node k }.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310056525.2A CN103118124B (en) | 2013-02-22 | 2013-02-22 | A kind of cloud computing load balancing method based on the many agencies of layering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310056525.2A CN103118124B (en) | 2013-02-22 | 2013-02-22 | A kind of cloud computing load balancing method based on the many agencies of layering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103118124A true CN103118124A (en) | 2013-05-22 |
| CN103118124B CN103118124B (en) | 2015-08-05 |
Family
ID=48416394
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310056525.2A Active CN103118124B (en) | 2013-02-22 | 2013-02-22 | A kind of cloud computing load balancing method based on the many agencies of layering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103118124B (en) |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103309738A (en) * | 2013-05-31 | 2013-09-18 | 中国联合网络通信集团有限公司 | User job scheduling method and device |
| CN103533086A (en) * | 2013-10-31 | 2014-01-22 | 中国科学院计算机网络信息中心 | Uniform resource scheduling method in cloud computing system |
| CN103873293A (en) * | 2014-03-05 | 2014-06-18 | 杭州华三通信技术有限公司 | Health detection device and method |
| CN104219285A (en) * | 2014-08-12 | 2014-12-17 | 重庆大学 | Method for determining mapping relation of communication agent nodes and virtual machines in cloud platform |
| CN104239117A (en) * | 2013-06-13 | 2014-12-24 | 鸿富锦精密工业（深圳）有限公司 | Virtual machine control system and method |
| CN104301241A (en) * | 2014-06-05 | 2015-01-21 | 中国人民解放军信息工程大学 | SOA dynamic load distribution method and system |
| CN104731635A (en) * | 2014-12-17 | 2015-06-24 | 华为技术有限公司 | Virtual machine access control method and virtual machine access control system |
| CN104899092A (en) * | 2014-03-03 | 2015-09-09 | 携程计算机技术（上海）有限公司 | JOB assignment system and method |
| CN105120008A (en) * | 2015-09-14 | 2015-12-02 | 南京邮电大学 | Layering-based distributed cloud computing centre load balancing method |
| CN105389196A (en) * | 2014-09-04 | 2016-03-09 | 中国石油化工股份有限公司 | Method for processing seismic data by utilizing virtualization technology |
| CN105740054A (en) * | 2016-02-01 | 2016-07-06 | 浪潮软件股份有限公司 | Virtual machine management method and device |
| CN106161629A (en) * | 2016-07-13 | 2016-11-23 | 广州新博庭网络信息科技股份有限公司 | The method of a kind of business object synchronization, client and server |
| WO2016206441A1 (en) * | 2015-06-26 | 2016-12-29 | 中兴通讯股份有限公司 | Method and device for allocating virtual resource, and computer storage medium |
| CN107193706A (en) * | 2017-03-31 | 2017-09-22 | 深圳市浩远智能科技有限公司 | A kind of method and apparatus for determining target computer room information technology information technoloy equipment |
| CN107807853A (en) * | 2017-10-16 | 2018-03-16 | 北京航空航天大学 | A kind of node screening technique and device based on machine real time load and task state machine |
| CN109284275A (en) * | 2018-09-28 | 2019-01-29 | 郑州云海信息技术有限公司 | A kind of cloud platform virtual machine file system monitoring method and apparatus |
| CN109412876A (en) * | 2018-12-27 | 2019-03-01 | 杭州数梦工场科技有限公司 | A kind of cloud management platform, cloud management method and a kind of cloud management system |
| CN110062032A (en) * | 2019-04-01 | 2019-07-26 | 北京航天发射技术研究所 | A kind of computer network clustered control platform application reconfiguration system |
| CN110543315A (en) * | 2019-09-06 | 2019-12-06 | 程延辉 | distributed operating system of kbroker, storage medium and electronic equipment |
| CN112055068A (en) * | 2020-08-28 | 2020-12-08 | 合肥工业大学 | Distribution method, device, terminal and storage medium of multi-agent system master control node |
| US10873541B2 (en) | 2017-04-17 | 2020-12-22 | Microsoft Technology Licensing, Llc | Systems and methods for proactively and reactively allocating resources in cloud-based networks |
| CN115277781A (en) * | 2022-07-29 | 2022-11-01 | 京东方科技集团股份有限公司 | Proxy connection method and related equipment |
| CN115460106A (en) * | 2022-08-30 | 2022-12-09 | 南京赛宁信息技术有限公司 | Virtual machine monitoring method and system for improving resource utilization rate in network target range |
| CN116467068A (en) * | 2023-03-14 | 2023-07-21 | 浙江大学 | Resource scheduling method, equipment and storage medium |
| US11824784B2 (en) | 2019-12-20 | 2023-11-21 | Intel Corporation | Automated platform resource management in edge computing environments |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102170474A (en) * | 2011-04-22 | 2011-08-31 | 广州杰赛科技股份有限公司 | Method and system for dynamic scheduling of virtual resources in cloud computing network |
| US20110252137A1 (en) * | 2008-12-31 | 2011-10-13 | Sap Ag | Systems and Methods for Dynamically Provisioning Cloud Computing Resources |
| CN102427475A (en) * | 2011-12-08 | 2012-04-25 | 曙光信息产业(北京)有限公司 | Load balance scheduling system in cloud computing environment |
| CN102479099A (en) * | 2010-11-22 | 2012-05-30 | 中兴通讯股份有限公司 | Virtual machine management system and use method thereof |
| CN102508714A (en) * | 2011-11-03 | 2012-06-20 | 南京邮电大学 | Green-computer-based virtual machine scheduling method for cloud computing |
-
2013
- 2013-02-22 CN CN201310056525.2A patent/CN103118124B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110252137A1 (en) * | 2008-12-31 | 2011-10-13 | Sap Ag | Systems and Methods for Dynamically Provisioning Cloud Computing Resources |
| CN102479099A (en) * | 2010-11-22 | 2012-05-30 | 中兴通讯股份有限公司 | Virtual machine management system and use method thereof |
| CN102170474A (en) * | 2011-04-22 | 2011-08-31 | 广州杰赛科技股份有限公司 | Method and system for dynamic scheduling of virtual resources in cloud computing network |
| CN102508714A (en) * | 2011-11-03 | 2012-06-20 | 南京邮电大学 | Green-computer-based virtual machine scheduling method for cloud computing |
| CN102427475A (en) * | 2011-12-08 | 2012-04-25 | 曙光信息产业(北京)有限公司 | Load balance scheduling system in cloud computing environment |
Cited By (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103309738B (en) * | 2013-05-31 | 2016-12-28 | 中国联合网络通信集团有限公司 | User job dispatching method and device |
| CN103309738A (en) * | 2013-05-31 | 2013-09-18 | 中国联合网络通信集团有限公司 | User job scheduling method and device |
| CN104239117A (en) * | 2013-06-13 | 2014-12-24 | 鸿富锦精密工业（深圳）有限公司 | Virtual machine control system and method |
| CN103533086A (en) * | 2013-10-31 | 2014-01-22 | 中国科学院计算机网络信息中心 | Uniform resource scheduling method in cloud computing system |
| CN103533086B (en) * | 2013-10-31 | 2017-02-01 | 中国科学院计算机网络信息中心 | Uniform resource scheduling method in cloud computing system |
| CN104899092A (en) * | 2014-03-03 | 2015-09-09 | 携程计算机技术（上海）有限公司 | JOB assignment system and method |
| CN103873293B (en) * | 2014-03-05 | 2018-06-12 | 新华三技术有限公司 | A kind of healthprobe device and method |
| CN103873293A (en) * | 2014-03-05 | 2014-06-18 | 杭州华三通信技术有限公司 | Health detection device and method |
| CN104301241A (en) * | 2014-06-05 | 2015-01-21 | 中国人民解放军信息工程大学 | SOA dynamic load distribution method and system |
| CN104219285B (en) * | 2014-08-12 | 2018-05-29 | 重庆大学 | The method for determining the mapping relations of communication agent node and virtual machine in cloud platform |
| CN104219285A (en) * | 2014-08-12 | 2014-12-17 | 重庆大学 | Method for determining mapping relation of communication agent nodes and virtual machines in cloud platform |
| CN105389196A (en) * | 2014-09-04 | 2016-03-09 | 中国石油化工股份有限公司 | Method for processing seismic data by utilizing virtualization technology |
| WO2016095762A1 (en) * | 2014-12-17 | 2016-06-23 | 华为技术有限公司 | Virtual machine access control method and virtual machine access control system |
| CN104731635B (en) * | 2014-12-17 | 2018-10-19 | 华为技术有限公司 | A kind of virtual machine access control method and virtual machine access control system |
| CN104731635A (en) * | 2014-12-17 | 2015-06-24 | 华为技术有限公司 | Virtual machine access control method and virtual machine access control system |
| WO2016206441A1 (en) * | 2015-06-26 | 2016-12-29 | 中兴通讯股份有限公司 | Method and device for allocating virtual resource, and computer storage medium |
| CN105120008B (en) * | 2015-09-14 | 2018-05-04 | 南京邮电大学 | A kind of distributed cloud computing center balancing method of loads based on layering |
| CN105120008A (en) * | 2015-09-14 | 2015-12-02 | 南京邮电大学 | Layering-based distributed cloud computing centre load balancing method |
| CN105740054A (en) * | 2016-02-01 | 2016-07-06 | 浪潮软件股份有限公司 | Virtual machine management method and device |
| CN106161629A (en) * | 2016-07-13 | 2016-11-23 | 广州新博庭网络信息科技股份有限公司 | The method of a kind of business object synchronization, client and server |
| CN107193706A (en) * | 2017-03-31 | 2017-09-22 | 深圳市浩远智能科技有限公司 | A kind of method and apparatus for determining target computer room information technology information technoloy equipment |
| US10873541B2 (en) | 2017-04-17 | 2020-12-22 | Microsoft Technology Licensing, Llc | Systems and methods for proactively and reactively allocating resources in cloud-based networks |
| CN107807853A (en) * | 2017-10-16 | 2018-03-16 | 北京航空航天大学 | A kind of node screening technique and device based on machine real time load and task state machine |
| CN107807853B (en) * | 2017-10-16 | 2021-07-02 | 北京航空航天大学 | Node screening method and device based on machine real-time load and task state machine |
| CN109284275A (en) * | 2018-09-28 | 2019-01-29 | 郑州云海信息技术有限公司 | A kind of cloud platform virtual machine file system monitoring method and apparatus |
| CN109412876A (en) * | 2018-12-27 | 2019-03-01 | 杭州数梦工场科技有限公司 | A kind of cloud management platform, cloud management method and a kind of cloud management system |
| CN109412876B (en) * | 2018-12-27 | 2022-02-08 | 杭州数梦工场科技有限公司 | Cloud management platform, cloud management method and cloud management system |
| CN110062032A (en) * | 2019-04-01 | 2019-07-26 | 北京航天发射技术研究所 | A kind of computer network clustered control platform application reconfiguration system |
| CN110543315A (en) * | 2019-09-06 | 2019-12-06 | 程延辉 | distributed operating system of kbroker, storage medium and electronic equipment |
| CN110543315B (en) * | 2019-09-06 | 2021-08-31 | 程延辉 | Distributed operating system of kbroker, storage medium and electronic equipment |
| US11824784B2 (en) | 2019-12-20 | 2023-11-21 | Intel Corporation | Automated platform resource management in edge computing environments |
| CN112055068A (en) * | 2020-08-28 | 2020-12-08 | 合肥工业大学 | Distribution method, device, terminal and storage medium of multi-agent system master control node |
| CN112055068B (en) * | 2020-08-28 | 2022-09-16 | 合肥工业大学 | Distribution method, device, terminal and storage medium of multi-agent system master control node |
| CN115277781A (en) * | 2022-07-29 | 2022-11-01 | 京东方科技集团股份有限公司 | Proxy connection method and related equipment |
| CN115460106A (en) * | 2022-08-30 | 2022-12-09 | 南京赛宁信息技术有限公司 | Virtual machine monitoring method and system for improving resource utilization rate in network target range |
| CN115460106B (en) * | 2022-08-30 | 2023-06-30 | 南京赛宁信息技术有限公司 | Virtual machine monitoring method and system for improving resource utilization rate in network target range |
| CN116467068A (en) * | 2023-03-14 | 2023-07-21 | 浙江大学 | Resource scheduling method, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103118124B (en) | 2015-08-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103118124B (en) | A kind of cloud computing load balancing method based on the many agencies of layering | |
| CN112783649B (en) | Cloud computing-oriented interaction-aware containerized micro-service resource scheduling method | |
| Kaur et al. | Container-as-a-service at the edge: Trade-off between energy efficiency and service availability at fog nano data centers | |
| CN103617086B (en) | Parallel computation method and system | |
| CN102932422B (en) | Cloud environment task scheduling method based on improved ant colony algorithm | |
| Sotiriadis et al. | SimIC: Designing a new inter-cloud simulation platform for integrating large-scale resource management | |
| Xhafa et al. | Computational models and heuristic methods for Grid scheduling problems | |
| Balasangameshwara et al. | A hybrid policy for fault tolerant load balancing in grid computing environments | |
| CN106790726A (en) | A kind of priority query's dynamic feedback of load equilibrium resource regulating method based on Docker cloud platforms | |
| CN105550323A (en) | Load balancing prediction method of distributed database, and predictive analyzer | |
| CN108845878A (en) | The big data processing method and processing device calculated based on serverless backup | |
| CN104902001B (en) | Web request load-balancing method based on operating system virtualization | |
| CN102223419A (en) | Virtual resource dynamic feedback balanced allocation mechanism for network operation system | |
| CN102012891B (en) | Computer cluster management method, device and system | |
| CN110109756A (en) | A kind of network target range construction method, system and storage medium | |
| CN103164287A (en) | Distributed-type parallel computing platform system based on Web dynamic participation | |
| CN104239555A (en) | MPP (massively parallel processing)-based parallel data mining framework and MPP-based parallel data mining method | |
| Patni et al. | Load balancing strategies for grid computing | |
| CN103605578A (en) | Load balance scheduling method based on virtual machine migration | |
| Wu et al. | Meccas: Collaborative storage algorithm based on alternating direction method of multipliers on mobile edge cloud | |
| CN101937359A (en) | Simulation application-orientated universal extensible computing system | |
| Zhang et al. | A PSO-based hierarchical resource scheduling strategy on cloud computing | |
| CN102339233A (en) | Cloud computing centralized management platform | |
| Zhou et al. | Scheduling workflow in cloud computing based on ant colony optimization algorithm | |
| Zhang et al. | An energy-aware host resource management framework for two-tier virtualized cloud data centers |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20130522 Assignee: Guangxi Jun'an Network Security Technology Co.,Ltd. Assignor: GUILIN University OF ELECTRONIC TECHNOLOGY Contract record no.: X2022450000459 Denomination of invention: A Load Balancing Method for Cloud Computing Based on Hierarchical Multi Agent Granted publication date: 20150805 License type: Common License Record date: 20221228 |
|
| EE01 | Entry into force of recordation of patent licensing contract |