CN111683109B - Micro-service system - Google Patents
Micro-service system Download PDFInfo
- Publication number
- CN111683109B CN111683109B CN202010824722.4A CN202010824722A CN111683109B CN 111683109 B CN111683109 B CN 111683109B CN 202010824722 A CN202010824722 A CN 202010824722A CN 111683109 B CN111683109 B CN 111683109B
- Authority
- CN
- China
- Prior art keywords
- kernel
- mode
- service
- microservice
- micro
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/16—Implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP]
-
- 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
- H04L67/50—Network services
- H04L67/56—Provisioning of proxy services
- H04L67/562—Brokering proxy services
-
- 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
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
- H04L67/63—Routing a service request depending on the request content or context
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/16—Implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP]
- H04L69/161—Implementation details of TCP/IP or UDP/IP stack architecture; Specification of modified or new header fields
- H04L69/162—Implementation details of TCP/IP or UDP/IP stack architecture; Specification of modified or new header fields involving adaptations of sockets based mechanisms
Abstract
The invention discloses a micro-service system, which comprises a control plane and a data plane; the service agents in the data plane comprise a user mode agent and a kernel mode agent; the user mode agent is configured to receive the traffic rules sent by the control plane and synchronize the traffic rules to the kernel mode agent through a cache; the kernel mode agent is configured to acquire a data packet sent by an upstream micro service and forward the data packet to a downstream micro service according to the flow rule; the invention uses the user mode agent and the kernel mode agent to forward and process the network flow between the micro-services, greatly shortens the network processing flow, reduces the network delay between the micro-services, and improves the network performance of the physical machine, the container or the virtual machine to the performance level in the process.
Description
Technical Field
The invention belongs to the technical field of micro services, and particularly relates to a high-performance micro service system.
Background
Microservice is a software architecture model that calls for a single application to be divided into a set of small services that are coordinated and coordinated to provide ultimate value to the user. Each service runs in an independent process, the micro-services are loosely coupled, and the services communicate with each other by adopting a lightweight communication mechanism (usually, a RESTful API based on an HTTP protocol). The micro-service framework is a software platform supporting micro-service operation management, the micro-service application is a business application unit based on a micro-service mode and capable of being independently deployed and developed, and each micro-service application represents a small business capability.
For accessing a micro service platform by a micro service application, there are generally two types of invasive and non-invasive methods. Intrusive is the development of microservices based on SDKs provided by microservice frameworks, which themselves rely on the development environment of the microservice framework. The non-intrusive mode is a mode of utilizing a network layer service agent to provide transaction flow forwarding among micro services, and the non-intrusive micro service architecture can be used for non-transformation access of a legacy system and also can be accessed to the micro services developed by a heterogeneous technology and a framework.
The services grid is an infrastructure layer that functions to handle inter-service communications and the responsibility is to effect reliable delivery of requests. In practice, the service grid is typically implemented as a lightweight network proxy, typically deployed with the application, but transparent to the application. The service grid is generally divided into a control plane and a data plane, and the control plane performs rule control, and the data plane processes traffic forwarding and the like. The upstream service refers to a service in the micro service, which exposes an interface for other services to call, and the downstream service refers to a service in the micro service, which calls other services.
Fig. 1 is a network traffic forwarding flow of a current service grid framework, as shown in fig. 1, in the current service grid framework, a proxy and a micro-service communicate with each other through a local loopback interface, network traffic is sent from the micro-service to the proxy through a complete network 7-layer structure, and is controlled and forwarded by using iptables, the proxy sends the network traffic to a downstream micro-service and also needs to pass through the 7-layer network structure, a communication network between two micro-services is lengthy, the network process may generate a 10 ms or longer delay, and for some industrial production environments or other environments with high requirements for delay, the lengthy network flow affects network performance.
Disclosure of Invention
In view of at least one defect or improvement requirement in the prior art, the present invention provides a micro service system, which aims to solve the problem that network processing flow in the current micro service system is long, which results in long network delay between micro services and affects network performance.
To achieve the above object, according to one aspect of the present invention, there is provided a microservice system including a control plane and a data plane; the service agents in the data plane comprise a user mode agent and a kernel mode agent;
the user mode agent is configured to receive the traffic rules sent by the control plane and synchronize the traffic rules to the kernel mode agent through a cache;
the kernel mode agent is configured to forward a data packet sent by an upstream micro service to a downstream micro service according to the traffic rule;
the service agent switches from the user-mode agent to the kernel-mode agent upon detecting a communication event between the microservices to perform traffic forwarding between the upstream microservices and the downstream microservices.
Preferably, in the microservice system, when the upstream microservice and the downstream microservice are located in the same physical host, container or virtual machine, the kernel-mode proxy obtains the data packet from the kernel-mode socket created by the upstream microservice and directly forwards the data packet to the kernel-mode socket of the downstream microservice, and the kernel-mode socket of the downstream microservice synchronizes the data packet to the user mode of the downstream microservice.
Preferably, in the microservice system, when the upstream microservice and the downstream microservice are located in different physical hosts, containers or virtual machines, the kernel-mode proxy acquires the data packet from the kernel-mode socket created by the upstream microservice and sends the data packet to the kernel-mode socket of the downstream microservice through network communication, and the kernel-mode socket of the downstream microservice synchronizes the data packet to the user mode of the downstream microservice.
Preferably, in the micro service system, the user mode agent is further configured to receive a shielding rule sent by the control plane and import the shielding rule into the kernel mode agent through a cache;
when the forwarding object of the data packet received by the kernel mode agent is abnormal service, the kernel mode agent directly returns a preset result according to the shielding rule without forwarding the data packet to the abnormal service.
Preferably, in the micro service system, the user mode agent is further configured to receive a traffic balancing rule sent by the control plane and import the traffic balancing rule into the kernel mode agent through a cache;
the kernel-state agent calculates load distribution by counting the request processing number of each micro-service providing the same service, and uniformly distributes the flow to each micro-service for processing according to the load distribution and the flow balancing rule.
Preferably, in the micro service system, the user mode agent is further configured to receive a traffic routing rule sent by the control plane and import the traffic routing rule into the kernel mode agent through the cache; the flow routing rule comprises a mapping relation between a data packet and one or more downstream micro-services which are used as receiving objects of the data packet;
and the kernel mode agent sends the data packet sent by the upstream micro-service to the corresponding downstream micro-service for processing according to the mapping relation.
Preferably, the microservice system further includes a cache unit, where the cache unit is created by a user mode agent or a kernel mode agent, and is used to store the traffic rule sent by the control plane.
Preferably, in the micro service system, the user mode agent and the kernel mode agent are implemented based on eBPF provided by the linux kernel, and the kernel mode agent operates in the kernel mode of the linux operating system.
Preferably, the microservice system further comprises a plurality of microservices, and the microservices may be containerized microservices or independently-processed microservices.
Preferably, in the microservice system, the control plane is configured to perform automatic discovery and registration of microservices, and generate traffic rules for use by the kernel-mode proxy according to the service state and the traffic access rules of each microservice.
In general, compared with the prior art, the above technical solution contemplated by the present invention can achieve the following beneficial effects:
the micro-service system provided by the invention abandons the traditional iptables, directly forwards and processes the network flow between micro-services through the user mode agent and the kernel mode agent, greatly shortens the network processing flow, reduces the network delay between micro-services, and improves the network performance of the same physical machine, container or virtual machine to the performance level in the process.
Drawings
FIG. 1 is a schematic diagram of a network traffic forwarding flow of a current service grid framework;
FIG. 2 is a schematic structural diagram of a microservice system provided in an embodiment of the present invention;
FIG. 3 is a schematic structural component diagram of a service agent provided by an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating the flow processing between the microservices with physical hosts according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of inter-microservice traffic processing across physical hosts, provided by an embodiment of the present invention;
fig. 6 is a schematic structural diagram of another microservice system 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 described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Fig. 2 is a schematic structural diagram of a micro service system provided in this embodiment, referring to fig. 2, the micro service system includes a control plane and a data plane;
when a new micro service is running, the control plane can automatically or manually discover the new micro service and generate a flow rule for a service agent in the data plane according to the service state and the flow access rule of each micro service.
The data plane includes a service agent and a plurality of microservices, which may be containerized microservices, i.e., microservices running in containers, or independently processed microservices, i.e., microservices running in independent processes.
The service agent is a bridge connecting the control plane and the data plane, and the control plane and the service agent interact through network connection. For a physical host, container or virtual machine, only one service agent needs to be deployed, so that all the microservices on the same physical host, container or virtual machine can be managed. As shown in fig. 2, each dashed box represents a data plane running on a physical host, container, or virtual machine, and only one service agent is deployed on the same physical host, container, or virtual machine.
In the scheme, the service agent comprises a user mode agent and a kernel mode agent; the user mode agent interacts with the control plane and the kernel mode agent respectively, and is configured to receive the traffic rule sent by the control plane and synchronize the traffic rule to the kernel mode agent through a cache; the kernel-mode agent is configured to obtain data packets sent by the upstream microservice and forward the data packets to the downstream microservice according to the traffic rules.
Fig. 3 is a schematic structural diagram of a service agent provided in this embodiment, and referring to fig. 3, a user mode agent works in a kernel mode, and a kernel mode agent works in the kernel mode, and first, code logic of the kernel mode agent is loaded into a system kernel mode for execution after passing verification and compilation from the user mode, so as to form the kernel mode agent; the method comprises the steps that a map cache is created by a kernel mode agent or a user mode agent, the user mode agent generates specific flow rules used by the kernel mode agent according to the state of each micro service of a data plane and flow access rules acquired by a control plane and stores the flow rules into the map cache, the kernel mode agent reads the flow rules in the map cache in flow processing, and then the data packet is processed according to the flow rules.
According to the method, the traditional iptables is abandoned, network flow forwarding and processing between the micro services are executed through the user mode agent and the kernel mode agent, the network processing flow is greatly shortened, and the network performance of the same physical machine, container or virtual machine is improved to the performance level in the process.
Because the kernel-mode agent operates in system kernel mode, the container run isolation is based on cgroup, which is under the same operating system. Thus, the data plane has the same structure for containerized microservices and for independently-processed microservices.
FIG. 4 is a schematic diagram illustrating the processing of traffic between the microservices of the physical host according to the embodiment; the flow processing flow provided by the scheme is arranged in a dotted line frame, and the flow processing flow provided by the traditional micro service frame is arranged outside the dotted line frame; as shown in fig. 4, when an upstream microservice located in the same physical host, container, or virtual machine sends a data packet to a downstream microservice, the kernel-mode proxy obtains the data packet from the kernel-mode socket created by the upstream microservice and directly forwards the data packet to the kernel-mode socket of the downstream microservice, and the kernel-mode socket of the downstream microservice synchronizes the data packet to the user mode of the downstream microservice. Specifically, the upstream microservice may first create a socket to establish a connection with the downstream microservice. When sending a data packet, the data packet will first enter the system kernel state and be converted into a kernel socket. And at the moment, the kernel mode agent in the kernel mode of the system intervenes to intercept the data packet, and directly forwards the data packet to the kernel mode socket of the downstream micro-service according to the flow rule in the map cache, the kernel mode socket transfers the data packet to the user mode, and the downstream micro-service formally receives the data packet. Compared with a traditional multi-layer network structure of a micro service frame based on iptables, the scheme effectively shortens the network processing flow and reduces the network delay between micro services, thereby improving the network performance.
FIG. 5 is a schematic diagram of the traffic processing between the microservices across the physical hosts according to the embodiment; as shown in fig. 5, when an upstream microservice located in a different physical host, container or virtual machine sends a packet to a downstream microservice, for example: when the upstream microservice and the downstream microservice are respectively positioned on two independent physical hosts which need to be connected and communicated by a network cable, the kernel-state agent also acquires a data packet from a kernel-state socket created by the upstream microservice, and the difference is that the kernel-state agent needs to send the data packet to a kernel-state socket of the downstream microservice on another physical host through network communication, and finally the kernel-state socket of the downstream microservice synchronizes the data packet to a user state of the downstream microservice, and the downstream microservice formally receives the data packet.
As can be seen by comparing fig. 4 and 5, communication between two microservices on the same physical host will be much faster than communication between two microservices on different physical hosts and much faster than network communication between two separate programs on the same physical host as provided by the conventional microservice architecture. Therefore, in actual deployment, the micro-services with high network performance requirements among the micro-services are deployed on the same physical host, and the network performance is greatly improved.
As a more preferable example, fig. 6 is a schematic structural diagram of another micro service system provided in this embodiment, and referring to fig. 6, a control plane in the micro service system includes a service administration unit and a flow control unit; wherein the content of the first and second substances,
the service management unit is mainly used for executing automatic discovery and registration of the micro-service, and when a new micro-service runs, the service management unit can automatically or manually discover the new micro-service; the microservice may be registered with the service administration unit after being started in a variety of ways, including but not limited to the following:
a) under K8S, the service discovery mechanism of K8S is used for automatic discovery and registration of the service;
b) under docker, acquiring a docker container list according to configuration to automatically discover and register services;
c) when the micro-service is an independent running program, automatic discovery is carried out through set rules, or the micro-service actively registers the micro-service into the framework.
The service management unit is also used for monitoring the service state of each micro service, and eliminating abnormal micro services outside the service list to realize the isolation of the abnormal services.
Specifically, the service management unit detects each micro service in the data plane, and when a certain micro service is found to be abnormal, a corresponding shielding rule is generated and sent to a user mode agent in the data plane;
the user mode agent receives the shielding rule and leads the shielding rule into the kernel mode agent through a cache; when the forwarding object of the data packet received by the kernel mode agent is abnormal service, the kernel mode agent directly returns a preset result according to the shielding rule without forwarding the data packet to the abnormal service, so that long delay or other unknown problems are avoided; in addition to traffic forwarding, when an access request for an exception service is received, the kernel-state agent also directly returns a preset result according to the shielding rule without calling the exception service.
In addition, when the service management unit detects that the downstream micro-service is unavailable or the response reaches the threshold value of the unavailable or abnormal state, the service management unit directly generates a fusing instruction and sends the fusing instruction to a user mode agent in the data plane;
similarly, the user mode agent receives the fusing instruction and leads the fusing instruction into the kernel mode agent through the cache; when the forwarding object of the data packet received by the kernel mode agent is the unavailable service, the kernel mode agent directly returns the preset result according to the fusing instruction without forwarding the data packet to the unavailable service, so that the quick response is realized, and the phenomenon that the operation of the whole system is slowed down due to a certain unavailable micro service is prevented. In addition, when receiving an access request aiming at the unavailable service, the kernel-state agent directly returns a preset result according to the fusing instruction.
The flow control unit is mainly used for controlling and managing the flow processing process among the micro-services, and specifically comprises the aspects of load balancing, flow routing and the like;
regarding load balancing, specifically, for a group of micro services providing the same service, a flow balancing rule is formulated according to the flow size of a data packet and sent to a user mode agent;
the user mode agent receives the flow balancing rule and leads the flow balancing rule into the kernel mode agent through the cache; the kernel-state agent calculates load distribution by counting the request processing number of each micro-service providing the same service, and uniformly distributes the flow to each micro-service for processing according to the load distribution and the flow balancing rule, thereby reducing the work load of each micro-service.
With regard to traffic routing, traffic is specifically forwarded or proportionally forwarded to a certain microservice or services according to rules. For example, for each microservice, there are multiple versions, and the traffic is gradually transferred from the microservice of the low version to the microservice of the high version, so that the traffic is smoothly transited.
According to actual service requirements, the flow control unit configures a flow routing rule for a group of micro services implementing the same function, where the flow routing rule may be configured by using micro services of different versions for different users, or configured according to a region or other rules, and this embodiment is not particularly limited; taking a flow routing rule configured by using micro services of different versions for different users as an example, the flow routing rule needs to contain a mapping relation between an identification label of a data packet and the version numbers of one or more downstream micro services; the flow control unit sends the generated flow routing rule to the user mode agent;
the user mode agent receives the flow routing rule and leads the flow routing rule into the kernel mode agent through the cache; and the kernel mode agent sends the data packet to one or more downstream micro services with corresponding version numbers for processing according to the identification label of the data packet sent by the upstream micro service and the mapping relation.
Further, the control plane further includes an ingress gateway and/or an egress gateway, and when the ingress gateway or the egress gateway is deployed, the micro service in the external service access data plane or the micro service access external service both need to pass through a gateway proxy and cannot be directly accessed.
a) And the entrance gateway is accessed by the micro-service in the external service access data plane, and the entrance gateway hands the access to the corresponding micro-service for processing according to the configured rule.
b) And the outlet gateway is required to be accessed when the micro service in the data plane accesses the external service, and the outlet gateway proxies the external service according to the configuration rule and returns the result to the micro service.
c) Ingress and egress gateways are essentially micro-services configured with special rules. And the kernel-state agent controls the data connection and access inside and outside the micro-service system according to the rule, so as to realize isolation and access security. As shown in fig. 1, if an ingress gateway and an egress gateway equivalent to independent micro services are configured in a conventional micro service system, the processing flow of network traffic will be further increased, and the delay will become 2 times that of the micro service network. In the scheme, the forwarding is realized by using the kernel mode agent, and the incoming and outgoing flow is doubled compared with the time delay of the micro service network. On the basis of reducing the micro-service time delay, the network time delay of external access micro-service and micro-service access outside is further reduced.
As a specific application scenario, the user mode agent and the kernel mode agent provided in this embodiment are implemented based on eBPF provided by the linux kernel, and the kernel mode agent operates in the kernel mode of the linux operating system. The Linux 3.15 starts to introduce the eBPF and expands the functions of the BPF, the instruction set is enriched, the kernel provides a virtual machine, the user mode agent transmits the filtering rules to the kernel in the form of virtual machine instructions, and the kernel agent filters network data packets according to the instructions.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A micro-service system comprises a control plane and a data plane; wherein the service agents in the data plane include a user mode agent and a kernel mode agent;
the user mode agent is configured to receive the traffic rules sent by the control plane and synchronize the traffic rules to the kernel mode agent through a cache;
the kernel mode agent is configured to obtain the data packet sent by the upstream micro service and forward the data packet to the downstream micro service according to the flow rule.
2. The microservice system of claim 1, wherein when the upstream microservice is located on the same physical host, container, or virtual machine as the downstream microservice, the kernel-mode proxy obtains the data packet from the kernel-mode socket created by the upstream microservice and forwards it directly to the kernel-mode socket of the downstream microservice, and the kernel-mode socket of the downstream microservice synchronizes the data packet to the user mode of the downstream microservice.
3. The microservice system of claim 1, wherein when the upstream microservice is located on a different physical host, container, or virtual machine than the downstream microservice, the kernel-mode proxy obtains the packet from the kernel-mode socket created by the upstream microservice and sends it to the kernel-mode socket of the downstream microservice via network communication, and the kernel-mode socket of the downstream microservice synchronizes the packet to the user-mode of the downstream microservice.
4. The microservice system of claim 1, wherein the user-mode proxy is further configured to receive a masking rule sent by the control plane and to import the masking rule to the kernel-mode proxy via a cache;
when the forwarding object of the data packet received by the kernel mode agent is abnormal service, the kernel mode agent directly returns a preset result according to the shielding rule without forwarding the data packet to the abnormal service.
5. The microservice system of claim 1, wherein the user-mode proxy is further configured to receive traffic balancing rules sent by the control plane and to import the traffic balancing rules into the kernel-mode proxy via a cache;
the kernel-state agent calculates load distribution by counting the request processing number of each micro-service providing the same service, and uniformly distributes the flow to each micro-service for processing according to the load distribution and the flow balancing rule.
6. The microservice system of claim 1, wherein the user-mode proxy is further configured to receive traffic routing rules sent by the control plane and to import the traffic routing rules into the kernel-mode proxy via a cache; the flow routing rule comprises a mapping relation between a data packet and one or more downstream micro-services which are used as receiving objects of the data packet;
and the kernel mode agent sends the data packet sent by the upstream micro-service to the corresponding downstream micro-service for processing according to the mapping relation.
7. The microservice system of claim 1, further comprising a caching unit created by a user-mode proxy or a kernel-mode proxy to store traffic rules sent by the control plane.
8. The microservice system of claim 1, wherein the user-mode agent and kernel-mode agent are implemented based on eBPF provided by the linux kernel, the kernel-mode agent operating in the kernel-mode of the linux operating system.
9. The microservice system of claim 1, further comprising a plurality of microservices in the data plane, the microservices being containerized microservices or independently-processed microservices.
10. The microservice system of claim 9, wherein the control plane is configured to perform automatic discovery and registration of microservices, and to generate traffic rules for use by kernel-mode agents based on service state and traffic access rules for each microservice.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010824722.4A CN111683109B (en) | 2020-08-17 | 2020-08-17 | Micro-service system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010824722.4A CN111683109B (en) | 2020-08-17 | 2020-08-17 | Micro-service system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111683109A CN111683109A (en) | 2020-09-18 |
| CN111683109B true CN111683109B (en) | 2020-11-13 |
Family
ID=72438790
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010824722.4A Active CN111683109B (en) | 2020-08-17 | 2020-08-17 | Micro-service system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111683109B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112887756B (en) * | 2021-01-11 | 2023-02-07 | 上海七牛信息技术有限公司 | Multi-input multi-output communication system and method for multimedia micro-service |
| CN112910692B (en) * | 2021-01-19 | 2022-08-02 | 中原银行股份有限公司 | Method, system and medium for controlling service grid flow based on micro service gateway |
| CN114915602B (en) * | 2021-01-29 | 2024-01-26 | 中移(苏州)软件技术有限公司 | Processing method, processing device and terminal for flow table in virtual switch |
| CN113568711B (en) * | 2021-08-04 | 2024-02-02 | 上海仪电（集团）有限公司中央研究院 | EBPF architecture-based load balancing method and device used in K8S |
| CN114244898A (en) * | 2021-11-16 | 2022-03-25 | 阿里巴巴（中国）有限公司 | Service grid-based workload preheating method and device |
| CN114338763B (en) * | 2021-12-20 | 2024-01-19 | 深圳Tcl新技术有限公司 | Micro-service calling method, micro-service calling device, server and computer readable storage medium |
| CN114363378B (en) * | 2022-01-14 | 2022-10-11 | 上海交通大学 | Micro-service system architecture and management method for industrial heterogeneous network management |
| CN115190178B (en) * | 2022-08-10 | 2024-03-08 | 苏州创意云网络科技有限公司 | Micro-service distribution method, device and equipment |
| CN115766858A (en) * | 2022-11-11 | 2023-03-07 | 中国工商银行股份有限公司 | Traffic processing method and device, computer readable storage medium and electronic equipment |
| CN116233135B (en) * | 2023-05-06 | 2023-07-11 | 华控清交信息科技(北京)有限公司 | Data transmission method, system, device and readable storage medium |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104123194A (en) * | 2014-07-16 | 2014-10-29 | 上海斐讯数据通信技术有限公司 | Communication structure and method for kernel mode and user mode |
| CN107026767B (en) * | 2017-03-30 | 2019-10-18 | 上海七牛信息技术有限公司 | Service protocol achievement data collection method and system |
| US11792307B2 (en) * | 2018-03-28 | 2023-10-17 | Apple Inc. | Methods and apparatus for single entity buffer pool management |
| CN108650295A (en) * | 2018-03-30 | 2018-10-12 | 深圳市风云实业有限公司 | Protocol massages cross-layer communication method device and electronic equipment |
| CN111131198B (en) * | 2019-12-11 | 2022-04-26 | 杭州迪普科技股份有限公司 | Updating method and device for network security policy configuration |
| CN111143072B (en) * | 2019-12-29 | 2023-09-08 | 浪潮(北京)电子信息产业有限公司 | User mode program memory allocation method, system and related components |
| CN111556136B (en) * | 2020-04-26 | 2022-08-30 | 全球能源互联网研究院有限公司 | Data interaction method between internal containers of power edge Internet of things agent |
-
2020
- 2020-08-17 CN CN202010824722.4A patent/CN111683109B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111683109A (en) | 2020-09-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111683109B (en) | Micro-service system | |
| US11824962B2 (en) | Methods and apparatus for sharing and arbitration of host stack information with user space communication stacks | |
| US11502950B2 (en) | Universal customer premise equipment | |
| RU2643451C2 (en) | System and method for virtualisation of mobile network function | |
| EP3669532B1 (en) | Managing network connectivity between cloud computing service endpoints and virtual machines | |
| US8634437B2 (en) | Extended network protocols for communicating metadata with virtual machines | |
| US8954957B2 (en) | Network traffic processing according to network traffic rule criteria and transferring network traffic metadata in a network device that includes hosted virtual machines | |
| US8990433B2 (en) | Defining network traffic processing flows between virtual machines | |
| US20110004877A1 (en) | Maintaining Virtual Machines in a Network Device | |
| JP2006262193A (en) | Controller, packet transferring method, and packet processor | |
| US8886838B2 (en) | Method and system for transferring packets to a guest operating system | |
| CN114301868B (en) | Method for quickly generating virtual container floating IP and method and device for network direct connection | |
| CN112738184A (en) | Plug-in dynamic registration distributed micro-service gateway system | |
| EP3788772A1 (en) | On-node dhcp implementation for virtual machines | |
| CN114143258B (en) | Service agent method based on Open vSwitch under Kubernetes environment | |
| CN115022408A (en) | Data transmission method and device based on service grid and electronic equipment | |
| CN111405076A (en) | IPv4/IPv6 protocol conversion method based on OpenFlow SDN | |
| Kawashima et al. | A generic and efficient local service function chaining framework for user VM-dedicated micro-VNFs | |
| EP4184873A1 (en) | Communication method, cp device, and nat device | |
| CN112073503A (en) | High-performance load balancing method based on flow control mechanism | |
| CN113489684A (en) | Communication device, method for calling service between cloud and intranet | |
| CN116980480B (en) | Method and system for processing fusing information based on micro-service network model | |
| US20230370938A1 (en) | Traffic sending method, apparatus, and system, and storage medium | |
| US20240098021A1 (en) | Systems and methods for route mismatch identification | |
| Zeng et al. | CONTC: A Traffic Control System for Container Overlay Networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |