CN110677274A - Event-based cloud network service scheduling method and device - Google Patents
Event-based cloud network service scheduling method and device Download PDFInfo
- Publication number
- CN110677274A CN110677274A CN201910789151.2A CN201910789151A CN110677274A CN 110677274 A CN110677274 A CN 110677274A CN 201910789151 A CN201910789151 A CN 201910789151A CN 110677274 A CN110677274 A CN 110677274A
- Authority
- CN
- China
- Prior art keywords
- alarm
- strategy
- threshold
- cluster
- end server
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
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
- H04L67/1004—Server selection for load balancing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
- G06F9/5088—Techniques for rebalancing the load in a distributed system involving task migration
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0893—Assignment of logical groups to network elements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/04—Processing captured monitoring data, e.g. for logfile generation
- H04L43/045—Processing captured monitoring data, e.g. for logfile generation for graphical visualisation of monitoring data
-
- 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
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
- H04L67/025—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP] for remote control or remote monitoring of applications
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention provides a cloud network service scheduling method and device based on events, which are used for distributing a request to a corresponding back-end server according to a preset load balancing strategy to realize the distribution of the request based on the events; compared with the traditional manually configured load balancing tool, the load balancing strategy of the invention can be predefined and then dynamically adjusted according to the real-time resource consumption condition of the back-end server; meanwhile, the invention can modify and adjust the load balancing strategy in time according to the resource consumption condition of the back-end server, thereby better improving the resource utilization rate.
Description
Technical Field
The invention relates to a cloud computing technology, in particular to the field of cloud computing network service, and more particularly to a cloud network service scheduling method and device based on events.
Background
With the development of the internet, internet applications for large-scale computing tasks are becoming mainstream to replace applications installed locally on the device. Since 1980, client-server (C/S) architectures became the mainstream for internet applications, after which the computing resource requirements for different tasks became more flexible as computer performance increased. In 2006, 3, amazon first introduced elastic computing cloud services, and with the popularization of cloud computing, more and more application services are migrated from physical servers to the cloud. The cloud computing quantifies the computing capacity as a commodity, has the advantages of super-large scale, virtualization, high reliability, universality, high expandability and the like compared with the traditional physical server, and provides cheap computing resources serving as required for users. However, deployment of computing tasks on the cloud necessarily involves resource allocation problems, particularly for internet applications that require both network resources and computing resources, which are mainly reflected in load balancing. The existing load balancing is realized through a router, a haproxy, a nginx and the like, but the schemes use simple configuration files for load balancing, lack of monitoring and interaction on a cloud platform and cannot dynamically sense the change of the cloud platform, so that the dynamic adjustment of resource allocation is realized.
Disclosure of Invention
Therefore, an object of the present invention is to overcome the defects in the prior art, and provide a new event-based cloud network service scheduling method and apparatus, so as to implement dynamic allocation of resources, improve resource utilization rate, and ensure service quality.
According to a first aspect of the present invention, the present invention provides an event-based cloud network service scheduling method, including the following steps:
s1, receiving a service request event, and distributing the request to a corresponding back-end server according to the current load balancing strategy;
s2, real-time monitoring the resource use condition of the back-end server, executing the operation behavior corresponding to the preset alarm strategy and/or adjusting the load balancing strategy;
and S3, dynamically adjusting the scale of the back-end server cluster according to the resource use condition.
The load balancing strategy is pre-configurable through the web and is adjusted in real time according to the resource use condition. Configuring a load balancing strategy for each back-end server cluster, and configuring the load balancing strategy as a balancing strategy or a combination of a plurality of balancing strategies comprising a back-end server bearing proportion, a priority of the back-end server, an upper limit of a concurrent connection number of the back-end server, timeout time of the back-end server and other related resources in a back-end server list in the corresponding cluster.
Configuring an alarm threshold and a cluster scale control threshold for a back-end server cluster in advance, setting an alarm mode corresponding to the alarm threshold, an alarm strategy and an operation behavior corresponding to the alarm strategy, and setting a cluster scale adjustment strategy corresponding to the cluster scale control threshold.
The alarm threshold is set to be one or more of a CPU utilization rate threshold, a memory utilization rate threshold, a hard disk utilization rate threshold, a network utilization rate threshold, a concurrent connection number threshold, a data throughput threshold and an average delay time threshold; the alarm mode is set to be one or any combination of short message alarm, mail alarm and command line alarm; different alarm strategies correspond to different operation behaviors, and the operation behaviors are one or more of modifying the load balancing strategy, sending out an alarm and adjusting the cluster scale.
The cluster scale control threshold comprises a cluster scale reduction threshold and a cluster scale expansion threshold, and respectively corresponds to a cluster scale reduction strategy and a cluster scale expansion strategy; the cluster scale control threshold is set to be a threshold corresponding to one or more combined resources including the number of concurrent connections, the CPU utilization rate, the memory utilization rate, the disk utilization rate and the network utilization rate, or set to be a threshold corresponding to other resources according to the requirements of an actual application scene; when the consumption result of the cluster resources of the back-end server is lower than the cluster scale reduction threshold, executing a cluster scale reduction strategy; and when the consumption result of the cluster resources of the back-end server is higher than the cluster scale enlargement threshold value, executing a cluster scale enlargement strategy.
According to another aspect of the present invention, the present invention provides an event-based cloud network service scheduling apparatus, configured between a cloud platform providing cloud services and a user, where the cloud platform includes a backend server providing cloud services, and the apparatus includes the following modules:
the user authentication module is used for defining the user role, configuring the role authority level and verifying the user identity;
the policy configuration module is used for providing configuration and query of a web-form load balancing policy; and configured to dynamically adjust a load balancing policy;
the alarm configuration module is used for configuring an alarm threshold and a cluster scale control threshold, setting an alarm mode and an alarm strategy corresponding to the alarm threshold, setting an operation behavior corresponding to the alarm strategy, and setting a cluster scale adjustment strategy corresponding to the control threshold;
the resource monitoring module is used for monitoring the resource consumption condition of the server in real time and providing a resource consumption monitoring result for the scheduling device;
the distribution module is used for carrying out load balancing on the request sent by the client according to the current load balancing strategy and distributing the request to the corresponding back-end server;
the intelligent sensing module is used for analyzing and judging the resource consumption monitoring result according to the resource consumption monitoring result provided by the resource monitoring module and referring to the alarm strategy to obtain a judgment result, and adjusting the load balancing strategy or executing a corresponding alarm strategy and a cluster scale adjustment strategy according to the judgment result;
and the cloud platform scheduling module is used for outputting a control signal matched with the cluster adjustment strategy corresponding to the judgment result according to the judgment result of the intelligent sensing module to control the cluster scale adjustment of the back-end server.
The alarm module is used for giving an alarm and/or executing corresponding operation behaviors according to the judgment result of the intelligent sensing module and an alarm strategy set by the alarm configuration module;
and the cloud platform resource interaction module is used for receiving the control signal of the cloud platform scheduling module and carrying out resource interaction with the cloud service providing platform.
According to the invention, through the scheduling of the cloud network service based on the event, the reasonable distribution and utilization of the cloud computing resources can be realized. According to the cloud computing service management method and the cloud computing service management system, the current service demand and the server resource consumption are dynamically monitored, the expandability of the cloud computing service is utilized, the service is dynamically controlled, and the resource utilization rate is improved. The service supply is dynamically adjusted according to the demand, the unavailability of the service caused by the conditions that the service is unavailable due to network blockage, the exhaustion of server resources, the downtime of part of servers and the like can be effectively avoided, the highly available electronic invoice service is provided for users, further, the network delay can be reduced as much as possible, and better use experience is brought for the users. In addition, the resource allocation and the use state are displayed through a graphical interface, the operation and maintenance difficulty is reduced, the operation and maintenance personnel can directly configure the scheduler through a web page, complicated command line configuration and maintenance operation are avoided, and the operation and maintenance experience of a system administrator is optimized.
Drawings
Embodiments of the invention are further described below with reference to the accompanying drawings, in which:
fig. 1 is a schematic main flow chart of a cloud network service scheduling method based on events according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a framework of a cloud network service scheduling apparatus based on events according to an embodiment of the present invention;
fig. 3 is a schematic flowchart of a cloud network service scheduling apparatus based on an event according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail by embodiments with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
According to the method, a load balancing strategy is configured for each back-end server cluster of the cloud platform, and the load balancing strategy is configured to be a balancing strategy or a combination of a plurality of balancing strategies comprising a back-end server bearing proportion, the priority of the back-end server, the upper limit of the number of concurrent connections of the back-end server, the timeout time of the back-end server and other related resources in a back-end server list in the corresponding cluster; for example, according to one embodiment of the present invention, the load balancing policy may be set to preferentially distribute requests to servers with a smaller number of connections; for example, if a back-end server cluster includes server A and server B; the current number of connections for server B is small, and the load balancing policy may be set to distribute requests preferentially to server B.
On the other hand, in the invention, an alarm threshold and a cluster scale control threshold are configured for the back-end server cluster in advance, an alarm mode, an alarm strategy and an operation behavior corresponding to the alarm threshold are set, and a cluster scale adjustment strategy corresponding to the cluster scale control threshold is set.
According to an embodiment of the present invention, the alarm threshold is set as one or more of a CPU utilization threshold, a memory utilization threshold, a hard disk utilization threshold, a network utilization threshold, a concurrent connection number threshold, a data throughput threshold, and an average delay time threshold, or set as a threshold corresponding to other resources according to actual application requirements.
According to one embodiment of the invention, different alarm strategies correspond to different operation behaviors, and the operation behaviors are one or more of modifying a load balancing strategy, sending an alarm and adjusting the cluster scale; when the class of resources exceeds the corresponding threshold value, executing corresponding operation behaviors; according to an embodiment of the invention, the alarm mode can be set to be one of short message alarm, mail alarm and command line alarm or any combination thereof.
According to one embodiment of the present invention, the cluster size control threshold includes a cluster size reduction threshold and a cluster size enlargement threshold, and respectively corresponds to the cluster size reduction policy and the cluster size enlargement policy; when the consumption result of the cluster resources of the back-end server is lower than the cluster scale reduction threshold, executing a cluster scale reduction strategy; and when the consumption result of the cluster resources of the back-end server is higher than the cluster scale enlargement threshold value, executing a cluster scale enlargement strategy. According to another embodiment of the present invention, the cluster size control threshold is set as a threshold corresponding to one or more combined resources including the number of concurrent connections, CPU utilization, memory utilization, disk utilization, and network utilization.
According to an embodiment of the invention, the alarm threshold is set to a combination of a server connection number threshold of 1000000 and a traffic threshold of 100M, the alarm policy is that when the number of server connections exceeds 1000000 and the traffic is less than 100M within 10 minutes (in this case, a DDoS attack may be received), the alarm is executed in a mail alarm manner.
According to an embodiment of the present invention, the cluster size reduction threshold is set to be 10000, which is the threshold of the number of server connections, and the cluster size reduction policy is that the average number of server connections per server is less than 10000 in 10 minutes, and a proper number of servers are reduced.
According to an embodiment of the present invention, the cluster size expansion threshold sets the server connection number threshold of 100000, and the cluster size expansion policy is to add an appropriate number of servers when the average number of connections per server is greater than 100000 in 10 minutes.
According to an embodiment of the present invention, there is provided an event-based cloud network service scheduling method, including the steps of:
step 1, receiving a service request, and distributing the request to a corresponding server according to a current load balancing strategy;
step 2, monitoring the resource consumption condition of the back-end server cluster in real time to obtain a server resource consumption result;
for example, in one embodiment of the present invention, if the number of connections monitored to server a is 20000, the number of connections monitored to server B is 30000, and the number of connections monitored to server a is small, the load balancing policy is adjusted to preferentially distribute the request to server a; according to the alarm strategy setting of the embodiment, if the load connection number does not reach the alarm threshold value and does not reach the cluster scale control threshold value, no alarm and no cluster scale adjustment are performed;
according to another embodiment of the invention, when the number of connections of the servers a and B within 10 minutes is 5000 and is lower than a set cluster size reduction threshold 10000, a request is made to the cloud platform to close one server and release the resource of the server.
According to another embodiment of the invention, when the number of connections of the servers a and B within 10 minutes is 150000 and is larger than the set cluster scale-up threshold 100000, the resources of one server are requested to be reallocated to the cloud platform.
According to another embodiment of the invention, when the number of connections of the servers A and B is 1500000 in 10 minutes and exceeds the alarm threshold of 1000000, a mail alarm is sent to the operation and maintenance personnel.
According to another embodiment of the invention, the alarm threshold is set to be 99% of the CPU utilization rate threshold, and the alarm strategy is to remove the server from the back-end server list of the load balancing strategy and send out the mail alarm when the CPU utilization rate of the server exceeds 99%; the cluster scale reduction threshold is set to be 10% of the CPU utilization rate threshold of the server, and when the cluster scale reduction strategy is that the average CPU utilization rate of each server is lower than 10% in 10 minutes, a proper amount of servers are reduced; setting a server CPU utilization rate threshold value to be 50% by using a cluster scale enlargement threshold value, and increasing a proper amount of servers when the average CPU utilization rate of each server is higher than 50% in 10 minutes by using a cluster scale enlargement strategy; in the embodiment, when the CPU utilization rate of the server A is monitored to be 100%, a mail alarm is sent out according to the setting of an alarm threshold value, a load balancing strategy is modified, the server corresponding to the load balancing strategy is set to be in a failure state, and a subsequent request cannot be distributed to the server; and adding a proper amount of servers according to the cluster size expansion threshold.
According to other embodiments of the invention, corresponding load balancing strategies, alarm strategies and cluster control strategies can be set according to actual application scenes and requirements.
For better understanding of the present invention, the present invention is further described in detail with reference to the accompanying drawings, and according to an embodiment of the present invention, as shown in fig. 1, there is provided an event-based cloud network service scheduling method including the following steps:
p1, the user carries out identity authentication through web, and logs in the system after the authentication is passed;
p2, the user inquires and configures the current load balancing strategy and the alarm strategy through the web;
p3, the system receives the access request and distributes the request to the corresponding server according to the load balancing strategy; meanwhile, the resource consumption condition of a back-end server cluster of the system is monitored in real time, and the system alarms or changes the cluster scale by comparing the resource consumption condition with an alarm strategy;
p4, when the server cluster size needs to be changed, the system changes the cluster size through the API of the cloud computing resource providing platform and/or gives an alarm to the operation and maintenance personnel through an email or a command line;
p5, continue accepting new access request, go to step P2.
According to an embodiment of the present invention, as shown in fig. 2, there is provided an event-based cloud network service scheduling apparatus configured between a cloud platform providing cloud services and a user, where the cloud platform includes a backend server providing cloud services, including:
the user authentication module is used for defining user roles and configuring role authority levels, different roles have different authority levels, and the user identity is verified through a user name and password login mode, so that the safety of the system is ensured, irrelevant personnel are prevented from operating the system, and a request can be sent after the user passes the verification;
the policy configuration module is used for providing configuration and query of the load balancing policy in a web form so that operation and maintenance personnel can query and configure the load balancing policy through a web page; the content of the strategy configurable comprises the load bearing proportion of each back-end server corresponding to the back-end server list, the priority of the load bearing of each back-end server, the upper limit of the number of concurrent connections, the overtime time and the like; the strategy configuration module is configured to dynamically adjust a load balancing strategy according to the judgment result of the intelligent sensing module;
the alarm configuration module is used for configuring an alarm threshold and a cluster scale control threshold, setting an alarm mode corresponding to the alarm threshold, an alarm strategy and an operation behavior corresponding to the alarm strategy, and setting a cluster scale adjustment strategy corresponding to the control threshold; configuring an alarm threshold or a cluster scale control threshold through a web page; the operation behavior corresponding to the alarm strategy comprises the steps of modifying the load balancing strategy of the distribution module, adjusting the scale of the back-end server cluster, giving an alarm to operation and maintenance personnel, notifying the distribution module of temporary service rejection and the like; the cluster scale adjustment strategy comprises the steps of enlarging the cluster scale of the back-end server and reducing the cluster scale of the back-end server;
the resource monitoring module is used for monitoring the resource consumption condition of the server in real time and providing a resource consumption monitoring result for the scheduling device; the CPU, the memory, the storage and the network utilization rate are queried in real time through the api provided by the system, the resource consumption condition of the server is monitored in real time, and a resource consumption monitoring result is provided for the intelligent sensing module; the usable resource monitoring types comprise CPU utilization rate, memory utilization rate, hard disk utilization rate, concurrent connection number, data throughput, average delay time and the like, and resource monitoring objects can be added according to actual application requirements;
the distribution module is used for carrying out load balancing on the request sent by the client according to the current load balancing strategy and distributing the request to the corresponding back-end server;
the intelligent sensing module is used for analyzing and judging the resource consumption monitoring result according to the resource consumption monitoring result provided by the resource monitoring module and referring to the alarm strategy to obtain a judgment result, and modifying the load balancing strategy and/or executing a corresponding alarm strategy and cluster scale adjustment strategy according to the judgment result;
the cloud platform scheduling module is used for outputting a control signal matched with the cluster adjustment strategy corresponding to the judgment result according to the judgment result of the intelligent sensing module to control the cluster scale adjustment of the back-end server; if the resource utilization rate is too low, the server cluster scale is properly reduced, otherwise, more resources are requested, the resources can be requested in a variety manner, and the types which can be requested comprise computing resources, storage resources, network bandwidth resources and the like;
the alarm module is used for giving an alarm according to the judgment result of the intelligent sensing module and an alarm strategy set by the alarm configuration module; when the judgment result of the intelligent sensing module exceeds the alarm threshold value, alarming is carried out according to the alarm strategy set by the alarm configuration module, and alarm information can be sent to operation and maintenance personnel in the modes of short messages, mails, console information and the like;
the cloud platform resource interaction module is used for receiving a control signal of the cloud platform scheduling module and performing resource interaction with the cloud service providing platform; the api of the platform is provided through the cloud service, and is controlled by the cloud platform scheduling module, so that computing, storage and network resources are increased or reduced.
As shown in fig. 3, according to an embodiment of the present invention, the service scheduling using the event-based cloud network service scheduling apparatus includes the following steps:
t1, an administrator logs in a scheduling device management page through a web interface, and the display content of the management page comprises a current load balancing strategy, a current alarm strategy and the resource consumption condition of a back-end server;
t2, analyzing the resource consumption condition of the current front-end and back-end servers, modifying the load balancing strategy and the alarm strategy through the web page by an administrator according to the analysis result, and reading and configuring the distribution module and the intelligent sensing module again after modification to obtain the current load balancing strategy and the alarm strategy;
t3, when a new request comes, the intelligent sensing module analyzes the resource consumption monitoring result of the back-end server cluster, modifies a detailed load balancing strategy according to the analysis result, and assigns a distribution module to distribute the request to a corresponding back-end server;
t4, the intelligent sensing module judges whether the cluster needs to be reduced, enlarged or alarmed, if so, the cloud platform scheduling module is assigned to perform corresponding operation; if the resource consumption is lower than the cluster shrinking threshold value, the cloud platform scheduling module applies for the shrinking cluster to the cloud platform; if the resource consumption exceeds the cluster expansion threshold, the cloud platform scheduling module applies for cluster expansion to the cloud platform; and if a certain monitoring value exceeds an alarm threshold value, alarming according to the current alarm strategy.
The cloud network service scheduling device can realize the following functions:
based on the request distribution of the event, when receiving the service request event, the distribution module distributes the request to a corresponding back-end server according to a load balancing strategy; compared with the traditional load balancing tool configured manually, the load balancing configuration can be predefined, and then specific request distribution is carried out according to the real-time resource consumption condition of the back-end server; meanwhile, the load balancing strategy can be adjusted in time according to the resource consumption condition of the back-end server, so that the resource utilization rate is improved better;
the method comprises the steps that a threshold value warning function is integrated into a resource scheduler based on intelligent sensing of a cloud platform of an event, when a request event arrives, the request event is distributed, the resource use condition of each rear-end server is monitored in real time, and a predefined strategy is automatically used for corresponding according to the resource use condition;
the intelligent control of the cloud platform based on the distribution analysis realizes the intelligent control of cloud computing resources by integrating a threshold alarm function into a resource scheduler, reduces the cluster scale when the resources are abundant, otherwise enlarges the cluster scale, and avoids the waste of the cloud resources and the reduction of the service quality.
The invention uses the cloud network service scheduling device based on the event to carry out overall control, and realizes high availability by a double-main hot standby mode; meanwhile, alarm thresholds of various monitoring indexes are predefined, and the monitoring result is compared with the alarm thresholds, so that the cloud platform abnormity can be found in real time and an alarm or cluster scale can be alarmed, and the problems that the resource utilization rate is low or the service quality cannot be guaranteed because the existing responsible balancing tool cannot dynamically allocate calculation, storage and network resources are solved.
The cloud network service scheduling device based on the events can reasonably distribute and utilize cloud computing resources. The device dynamically monitors the current service demand and the resource consumption of the server, and dynamically controls the service in a closed loop mode by utilizing the expandability of the cloud computing service, so that the resource utilization rate is improved. The service supply is dynamically adjusted according to the demand, the unavailability of the service caused by the conditions that the service is unavailable due to network blockage, the exhaustion of server resources, the downtime of part of servers and the like can be effectively avoided, the highly available cloud service is provided for users, further, the network delay can be reduced as much as possible, and better use experience is brought for the users. In addition, the resource allocation and the use state are displayed through a graphical interface, the operation and maintenance difficulty is reduced, the operation and maintenance personnel can directly configure the scheduler through a web page, complicated command line configuration and maintenance operation are avoided, and the operation and maintenance experience of a system administrator is optimized.
According to the cloud service load balancing method and device, the computing resource utilization rate and the network resource utilization rate of the server group providing the cloud service are monitored in real time through the system resource interface, the network connection condition counting interface and the network flow counting interface, and the load is led to the corresponding service providing server by combining the configured load balancing strategy, so that high-performance request distribution is achieved, and the problem that the existing load balancing tool can only carry out load balancing according to static configuration and cannot carry out closed-loop control is solved.
It should be noted that, although the steps are described in a specific order, the steps are not necessarily performed in the specific order, and in fact, some of the steps may be performed concurrently or even in a changed order as long as the required functions are achieved.
The present invention may be a system, method and/or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied therewith for causing a processor to implement various aspects of the present invention.
The computer readable storage medium may be a tangible device that retains and stores instructions for use by an instruction execution device. The computer readable storage medium may include, for example, but is not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing.
Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (12)
1. A cloud network service scheduling method based on events is characterized by comprising the following steps:
s1, receiving a service request event, and distributing the request to a corresponding back-end server according to the current load balancing strategy;
and S2, monitoring the resource use condition of the back-end server in real time, and executing the operation behavior corresponding to the preset alarm strategy and/or adjusting the load balancing strategy.
2. The event-based cloud network service scheduling method according to claim 1, further comprising:
and S3, dynamically adjusting the scale of the back-end server cluster according to the resource use condition.
3. The event-based cloud network service scheduling method of claim 1,
the load balancing strategy is pre-configurable through the web and is adjusted in real time according to the resource use condition.
4. The event-based cloud network service scheduling method of claim 3,
configuring a load balancing strategy for each back-end server cluster, and configuring the load balancing strategy as a balancing strategy or a combination of a plurality of balancing strategies comprising a back-end server bearing proportion, a priority of the back-end server, an upper limit of a concurrent connection number of the back-end server, timeout time of the back-end server and other related resources in a back-end server list in the corresponding cluster.
5. The event-based cloud network service scheduling method according to claim 2,
configuring an alarm threshold and a cluster scale control threshold for a back-end server cluster in advance, setting an alarm mode corresponding to the alarm threshold, an alarm strategy and an operation behavior corresponding to the alarm strategy, and setting a cluster scale adjustment strategy corresponding to the cluster scale control threshold.
6. The event-based cloud network service scheduling method of claim 5,
the alarm threshold is set to be one or more of a CPU utilization rate threshold, a memory utilization rate threshold, a hard disk utilization rate threshold, a network utilization rate threshold, a concurrent connection number threshold, a data throughput threshold and an average delay time threshold;
different alarm strategies correspond to different operation behaviors, and the operation behaviors are one or more of modifying the load balancing strategy, sending out an alarm and adjusting the cluster scale.
7. The event-based cloud network service scheduling method of claim 5,
the alarm mode is set to be one or any combination of short message alarm, mail alarm and command line alarm.
8. The event-based cloud network service scheduling method of claim 5,
the cluster scale control threshold comprises a cluster scale reduction threshold and a cluster scale expansion threshold, and respectively corresponds to a cluster scale reduction strategy and a cluster scale expansion strategy;
when the consumption result of the cluster resources of the back-end server is lower than the cluster scale reduction threshold, executing a cluster scale reduction strategy;
and when the consumption result of the cluster resources of the back-end server is higher than the cluster scale enlargement threshold value, executing a cluster scale enlargement strategy.
9. The event-based cloud network service scheduling method of claim 8,
the cluster scale control threshold is set to be a threshold corresponding to one or more combined resources including the number of concurrent connections, the CPU utilization rate, the memory utilization rate, the disk utilization rate and the network utilization rate, or set to be a threshold corresponding to other resources according to the requirements of an actual application scene.
10. A cloud network service scheduling apparatus for use in the method according to any one of claims 1 to 9, configured between a cloud platform providing cloud services and a user, the cloud platform including a backend server providing cloud services, the apparatus comprising:
the user authentication module is used for defining the user role, configuring the role authority level and verifying the user identity;
the policy configuration module is used for providing configuration and query of a web-form load balancing policy; and configured to dynamically adjust a load balancing policy;
the alarm configuration module is used for configuring an alarm threshold and a cluster scale control threshold, setting an alarm mode and an alarm strategy corresponding to the alarm threshold, setting an operation behavior corresponding to the alarm strategy, and setting a cluster scale adjustment strategy corresponding to the control threshold;
the resource monitoring module is used for monitoring the resource consumption condition of the server in real time and providing a resource consumption monitoring result for the scheduling device;
the distribution module is used for carrying out load balancing on the request sent by the client according to the current load balancing strategy and distributing the request to the corresponding back-end server;
the intelligent sensing module is used for analyzing and judging the resource consumption monitoring result according to the resource consumption monitoring result provided by the resource monitoring module and referring to the alarm strategy to obtain a judgment result, and adjusting the load balancing strategy or executing a corresponding alarm strategy and a cluster scale adjustment strategy according to the judgment result;
and the cloud platform scheduling module is used for outputting a control signal matched with the cluster adjustment strategy corresponding to the judgment result according to the judgment result of the intelligent sensing module to control the cluster scale adjustment of the back-end server.
The alarm module is used for giving an alarm and/or executing corresponding operation behaviors according to the judgment result of the intelligent sensing module and an alarm strategy set by the alarm configuration module;
and the cloud platform resource interaction module is used for receiving the control signal of the cloud platform scheduling module and carrying out resource interaction with the cloud service providing platform.
11. A computer device for cloud network service scheduling, comprising a memory and a processor, on which a computer program is stored which is executable on the processor, characterized in that the processor realizes the steps of the method of any one of claims 1 to 9 when executing the program.
12. A computer-readable storage medium having stored thereon program code for implementing the method of any one of claims 1 to 9 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910789151.2A CN110677274A (en) | 2019-08-26 | 2019-08-26 | Event-based cloud network service scheduling method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910789151.2A CN110677274A (en) | 2019-08-26 | 2019-08-26 | Event-based cloud network service scheduling method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110677274A true CN110677274A (en) | 2020-01-10 |
Family
ID=69076456
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910789151.2A Pending CN110677274A (en) | 2019-08-26 | 2019-08-26 | Event-based cloud network service scheduling method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110677274A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111682971A (en) * | 2020-07-23 | 2020-09-18 | 拉货宝网络科技有限责任公司 | Logistics system resource automatic management method |
| CN111831454A (en) * | 2020-09-17 | 2020-10-27 | 北京汇智恒安科技有限责任公司 | Cloud computing server cluster resource allocation control system and method |
| CN113055126A (en) * | 2021-03-09 | 2021-06-29 | 华夏云融航空科技有限公司 | Flight data decoding method and device and terminal equipment |
| CN113067850A (en) * | 2021-02-20 | 2021-07-02 | 麒麟软件有限公司 | Cluster arrangement system under multi-cloud scene |
| CN113765966A (en) * | 2020-09-01 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Load balancing method and device |
| CN115334136A (en) * | 2022-07-05 | 2022-11-11 | 北京天融信网络安全技术有限公司 | Connection aging control method, system, equipment and storage medium |
| CN117112239A (en) * | 2023-10-23 | 2023-11-24 | 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) | Extensible load balancing method and system on heterogeneous reasoning back end |
| CN117407248A (en) * | 2023-12-08 | 2024-01-16 | 南京云玑信息科技有限公司 | Method and system for realizing accurate green energy conservation of cloud computer |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102646062A (en) * | 2012-03-20 | 2012-08-22 | 广东电子工业研究院有限公司 | Flexible capacity enlargement method for cloud computing platform based application clusters |
| CN104202388A (en) * | 2014-08-27 | 2014-12-10 | 福建富士通信息软件有限公司 | Automatic load balancing system based on cloud platform |
| CN105426254A (en) * | 2015-12-24 | 2016-03-23 | 北京轻元科技有限公司 | Graded cloud computing resource customizing method and system |
| CN106375420A (en) * | 2016-08-31 | 2017-02-01 | 武汉钢信软件有限公司 | System and method for intelligently monitoring server cluster based on load balancing |
| CN107135250A (en) * | 2017-04-13 | 2017-09-05 | 华北水利水电大学 | A kind of SiteServer LBS and mechanism towards cloud computing |
| CN107404523A (en) * | 2017-07-21 | 2017-11-28 | 中国石油大学(华东) | Cloud platform adaptive resource dispatches system and method |
-
2019
- 2019-08-26 CN CN201910789151.2A patent/CN110677274A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102646062A (en) * | 2012-03-20 | 2012-08-22 | 广东电子工业研究院有限公司 | Flexible capacity enlargement method for cloud computing platform based application clusters |
| CN104202388A (en) * | 2014-08-27 | 2014-12-10 | 福建富士通信息软件有限公司 | Automatic load balancing system based on cloud platform |
| CN105426254A (en) * | 2015-12-24 | 2016-03-23 | 北京轻元科技有限公司 | Graded cloud computing resource customizing method and system |
| CN106375420A (en) * | 2016-08-31 | 2017-02-01 | 武汉钢信软件有限公司 | System and method for intelligently monitoring server cluster based on load balancing |
| CN107135250A (en) * | 2017-04-13 | 2017-09-05 | 华北水利水电大学 | A kind of SiteServer LBS and mechanism towards cloud computing |
| CN107404523A (en) * | 2017-07-21 | 2017-11-28 | 中国石油大学(华东) | Cloud platform adaptive resource dispatches system and method |
Non-Patent Citations (2)
| Title |
|---|
| 伍银波，岑健: "《智慧建筑集成技术》", 30 July 2019 * |
| 周曙东: "《电子商务概论》", 31 January 2019 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111682971A (en) * | 2020-07-23 | 2020-09-18 | 拉货宝网络科技有限责任公司 | Logistics system resource automatic management method |
| CN113765966A (en) * | 2020-09-01 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Load balancing method and device |
| CN111831454A (en) * | 2020-09-17 | 2020-10-27 | 北京汇智恒安科技有限责任公司 | Cloud computing server cluster resource allocation control system and method |
| CN111831454B (en) * | 2020-09-17 | 2021-02-19 | 北京汇智恒安科技有限责任公司 | Cloud computing server cluster resource allocation control system and method |
| CN113067850B (en) * | 2021-02-20 | 2023-04-07 | 麒麟软件有限公司 | Cluster arrangement system under multi-cloud scene |
| CN113067850A (en) * | 2021-02-20 | 2021-07-02 | 麒麟软件有限公司 | Cluster arrangement system under multi-cloud scene |
| CN113055126A (en) * | 2021-03-09 | 2021-06-29 | 华夏云融航空科技有限公司 | Flight data decoding method and device and terminal equipment |
| CN115334136A (en) * | 2022-07-05 | 2022-11-11 | 北京天融信网络安全技术有限公司 | Connection aging control method, system, equipment and storage medium |
| CN115334136B (en) * | 2022-07-05 | 2024-02-02 | 北京天融信网络安全技术有限公司 | Connection aging control method, system, equipment and storage medium |
| CN117112239A (en) * | 2023-10-23 | 2023-11-24 | 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) | Extensible load balancing method and system on heterogeneous reasoning back end |
| CN117112239B (en) * | 2023-10-23 | 2024-02-09 | 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) | Extensible load balancing method and system on heterogeneous reasoning back end |
| CN117407248A (en) * | 2023-12-08 | 2024-01-16 | 南京云玑信息科技有限公司 | Method and system for realizing accurate green energy conservation of cloud computer |
| CN117407248B (en) * | 2023-12-08 | 2024-03-12 | 南京云玑信息科技有限公司 | Method and system for realizing accurate green energy conservation of cloud computer |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110677274A (en) | Event-based cloud network service scheduling method and device | |
| US11252220B2 (en) | Distributed code execution involving a serverless computing infrastructure | |
| US6857020B1 (en) | Apparatus, system, and method for managing quality-of-service-assured e-business service systems | |
| US7644161B1 (en) | Topology for a hierarchy of control plug-ins used in a control system | |
| CN108712464A (en) | A kind of implementation method towards cluster micro services High Availabitity | |
| JP2017126975A (en) | Network traffic scheduling method and device of data center | |
| US9596189B1 (en) | Virtual machine management | |
| CN110351366B (en) | Service scheduling system and method for internet application and storage medium | |
| EP2883342B1 (en) | Virtual desktop policy control | |
| US20070094343A1 (en) | System and method of implementing selective session replication utilizing request-based service level agreements | |
| US20150058844A1 (en) | Virtual computing resource orchestration | |
| WO2013104217A1 (en) | Cloud infrastructure based management system and method for performing maintenance and deployment for application system | |
| US9110745B2 (en) | System and method for flow control in a messaging subsystem based on message-in/out rates | |
| CN110245031B (en) | AI service opening middle platform and method | |
| US20220006879A1 (en) | Intelligent scheduling apparatus and method | |
| KR20110083084A (en) | Apparatus and method for operating server by using virtualization technology | |
| CN109800261B (en) | Dynamic control method and device for double-database connection pool and related equipment | |
| CN111988234A (en) | Overload protection method, device, server and storage medium | |
| CN110727508A (en) | Task scheduling system and scheduling method | |
| US11966273B2 (en) | Throughput-optimized, quality-of-service aware power capping system | |
| WO2022057001A1 (en) | Device management method and system, and management cluster | |
| US9607275B2 (en) | Method and system for integration of systems management with project and portfolio management | |
| US10348814B1 (en) | Efficient storage reclamation for system components managing storage | |
| CN107426012B (en) | Fault recovery method and device based on super-fusion architecture | |
| Mookdarsanit et al. | Light-weight operation of a failover system for Cloud computing |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200110 |