CN113259503A - Method and system for realizing cross-network communication among different containers based on Infiniband - Google Patents
Method and system for realizing cross-network communication among different containers based on Infiniband Download PDFInfo
- Publication number
- CN113259503A CN113259503A CN202110702022.2A CN202110702022A CN113259503A CN 113259503 A CN113259503 A CN 113259503A CN 202110702022 A CN202110702022 A CN 202110702022A CN 113259503 A CN113259503 A CN 113259503A
- Authority
- CN
- China
- Prior art keywords
- container
- network
- address
- host
- host machine
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L61/00—Network arrangements, protocols or services for addressing or naming
- H04L61/50—Address allocation
- H04L61/5046—Resolving address allocation conflicts; Testing of addresses
Abstract
The invention discloses a method and a system for realizing cross-network communication among different containers based on Infiniband, wherein the method comprises the following steps: ensuring the network configuration of the host machine to be correct, and defining the IP network segment of the container; acquiring the environment number of a host in a cluster, and dividing a container IP network segment; the IP address of the container is distributed through an IP distributor on the host machine, if the container is deleted, the IP address of the current container is recycled through the IP distributor, and the distributed state of the IP address of the container is eliminated; configuring a container network interface device to complete network communication between a host machine based on the infinite bandwidth technology device and a container; and configuring iptables rules of the host and route rules of the container to complete network access control and data packet forwarding. Has the advantages that: the cross-network segment communication between the container and the host machine, between the container and between the container and the non-host machine is realized.
Description
Technical Field
The invention relates to the field of network communication, in particular to a method and a system for realizing cross-network communication among different containers based on Infiniband.
Background
1. Cross-host communication of containers:
the IP address of host1 is: 192.168.0.101, the IP address of container1 is: 10.0.101.2.
the IP address of host2 is: 192.168.0.102, the IP address of container1 is: 10.0.102.2.
two routing rules are defined: all packets with destination address 10.0.101.0/24 are forwarded to host1, and all packets with destination address 10.0.102.0/24 are forwarded to host 2.
As shown in fig. 2, the packet is transferred between two containers: the data packet sent from container1 to container2 is first sent to "gateway" Docker0 (Docker is an open source application container engine) of container1, then it is known that the data packet needs to be sent to host2 by searching the route of host1, and the data packet reaches host2 and then is forwarded to Docker0 of host2, and finally the data packet is transferred to container 2. The same principle applies to packets sent from container2 to container 1.
2. IP address management (IPAM):
IPAM provides the ability to efficiently manage, control, monitor, and allocate IP address space. By using the IPAM tool, the storage library capable of distributing the IP addresses can be kept up to date, the management of a plurality of tasks related to the IP addresses is simplified and automated, and the orderly distribution and recovery management of the IP addresses is ensured.
IPAM can provide global IP address space and allocate IP address resources, playing an important role in overall network security. The commonly used IPAM scheme thinking at present is: based on local IP address management and global unified IP address management of a host machine, the related solutions are as follows: host-local (a solution based on the host itself for IP address management), infoblob (a solution based on globally uniform IP address management), etc.
The interconnection communication between containers of different hosts is very complex, and the networking is usually performed directly by using the network of the hosts. To implement inter-network-segment container communication, 2 major problems need to be solved: the data packet can not be forwarded due to the lack of effective routing; there may be IP collisions with multiple containers.
An effective solution to the problems in the related art has not been proposed yet.
Disclosure of Invention
Aiming at the problems in the related art, the invention provides a method and a system for realizing cross-network communication between different containers based on Infiniband, so as to overcome the technical problems in the prior related art.
Therefore, the invention adopts the following specific technical scheme:
according to one aspect of the invention, a method for realizing cross-network communication among different containers based on Infiniband is provided, which comprises the following steps:
s1, ensuring the correct network configuration of the host machine, and defining the container IP network segment through the container IP network segment definition rule;
s2, acquiring the environment number of the host in the cluster, and dividing the container IP network segment based on the host environment number;
s3, allocating the IP address of the container through the IP distributor on the host machine, if the container is deleted, recycling the IP address of the current container through the IP distributor, and eliminating the allocated state of the IP address of the container;
s4, configuring the container network interface device, and completing the network communication between the host machine based on the infiniband technology device and the container;
and S5, configuring an iptables (IP information packet filtering system) rule of the host and a route (routing) rule of the container to complete network access control and data packet forwarding.
Further, when the container IP network segment is divided based on the host environment number in S2, the IP address intervals divided by each host are not repeated in a crossing manner.
Further, the step of assigning the container IP address by the IP assigner on the host in S3 further includes the following steps:
when a container is created, an IP distributor on a host machine acquires container IP planning information of the host machine and eliminates an IP address which is distributed;
and obtaining an allocable IP address by adopting a polling scheduling algorithm, allocating the IP address to the container, and marking the IP address as an allocated state.
Further, the formula for allocating the IP address of the container in S3 is as follows:
wherein: last _ Assigned _ IP represents the newly allocated IP address, IP _ Range represents the IP address Range of the container on the host, and Unallocated _ Status represents the assignable state.
Further, the step of configuring the container network interface device in S4 to complete network connectivity between the host and the container based on the infiniband technology device further includes the following steps:
s41, create an ipoib (IP protocol over Infiniband network) type network device on the Infiniband technology device ib0, and bind the network device to the network namespace of the container and rename it to eth 0;
s42, the IP address assigned by the IP distributor is configured to the container network device eth 0.
Further, the step S4 of configuring the container network interface device, where the specific command for completing the network connection between the host based on the infiniband technology device and the container is:
creating an ipoib-type network device;
adding a network device to a network namespace of a container;
rename the network device to eth 0;
configuring an IP address of eth0 of the container;
open eth0 network card of container.
Further, configuring iptables rules of the host and route rules of the container in S5, and completing network access control and packet forwarding further includes the following steps:
s51, configuring iptables rules of the host machine and allowing the IP data packet of the container network segment to pass through;
s52, configuring the route rule of the container, and setting the IP address of the ib0 network card of the host machine as a default route.
Further, the command for configuring the container route rule is as follows:
According to another aspect of the present invention, there is provided an Infiniband-based system for implementing cross-network communication between different containers, the system comprising: the system comprises a preparation environment module, a container IP address global planning module, a container IP address allocation and recovery module, a configuration container network interface equipment module and a network access control and data packet forwarding module;
the system comprises a preparation environment module, a container IP network segment definition module and a host machine, wherein the preparation environment module is used for ensuring that the network configuration of the host machine is correct and defining the container IP network segment through a container IP network segment definition rule;
the container IP address global planning module is used for acquiring the environment number of the host in the cluster and dividing the container IP network segment based on the host environment number;
the distribution and recovery module of the container IP address is used for distributing the container IP address through an IP distributor on the host machine, if the container is deleted, the IP distributor recovers the IP address of the current container and eliminates the distributed state of the IP address of the container;
the system comprises a configuration container network interface device module, a container network interface device module and a host machine, wherein the configuration container network interface device module is used for configuring container network interface devices and completing network communication between the host machine based on the infinite bandwidth technology device and a container;
and the network access control and data packet forwarding module is used for configuring iptables rules of the host and route rules of the container to complete network access control and data packet forwarding.
Further, when the container IP network segment is divided based on the host machine environment number, the IP address intervals divided by each host machine are not crossed and repeated.
The invention has the beneficial effects that:
(1) the invention adopts the container IP address global planning strategy and the container IP address allocation and recovery management strategy, can effectively manage the IP addresses of the containers, and perfectly solves the conflict problem of a plurality of container IP addresses on different hosts in a cluster environment.
(2) The configuration method of the container network interface equipment provided by the invention greatly plays the characteristics of high throughput and low delay of Infiniband on the basis of providing the communication connection between the container and the host, and meets the requirement of high-performance service of the container.
(3) The network access control and data packet forwarding strategy adopted by the invention effectively solves the problem of cross-network-segment communication of the container, realizes the cross-network-segment communication between the container and the host, between the container and between the container and the non-host, and realizes the network interconnection and intercommunication of the whole cluster environment.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a diagram of a host and a network architecture of its container implementing a cross-network communication method between different containers based on Infiniband according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a packet transfer process between two containers;
fig. 3 is a schematic diagram of the process of iptables transmitting data packets.
Detailed Description
For further explanation of the various embodiments, the drawings which form a part of the disclosure and which are incorporated in and constitute a part of this specification, illustrate embodiments and, together with the description, serve to explain the principles of operation of the embodiments, and to enable others of ordinary skill in the art to understand the various embodiments and advantages of the invention, and, by reference to these figures, reference is made to the accompanying drawings, which are not to scale and wherein like reference numerals generally refer to like elements.
According to the embodiment of the invention, a method and a system for realizing cross-network communication among different containers based on Infiniband are provided, which mainly relate to the field of network configuration management, comprise a container IP address global planning strategy, a container IP address allocation and recovery management strategy, a container network interface equipment configuration method, a network access control and data packet forwarding strategy and the like, and aim to solve the cross-network communication problem among different containers. And planning distributable IP network segments of the hosts based on the serial numbers of the hosts in the whole environment, and uniformly distributing and recycling the IP of the containers by the IP distributor of each host so as to ensure that different containers have globally unique IP addresses. By configuring the iptables (IP information packet filtering system) rule of the host and the route (routing) rule of the container, the host can forward the data packet of the container network segment to the container for processing, and the container can forward the data packet of the non-container network segment to the host for processing, thereby realizing the cross-network communication between the container and the host and between the container and the container. The Kubernets CNI plug-in (Kubernets is an open source and is used for managing containerized application on a plurality of hosts in a cloud platform, and CNI is called a Container Network Interface, namely an API (application programming Interface) Interface of a Container Network), which is developed and realized by taking the Kubernets CNI plug-in as a key technology, not only can perfectly solve the IP management and Network communication problems of Pod (the minimum deployable unit capable of creating and managing Kubernets calculation), but also can greatly play the advantages of high throughput and low delay of Infiniband, and is one of the first choices of the Kubernets Network plug-in a high-performance service scene.
The present invention will be further described with reference to the accompanying drawings and specific embodiments, and as shown in fig. 1, a method for implementing cross-network communication between different containers based on Infiniband according to an embodiment of the present invention includes the following steps:
step S1: an environment is prepared. Firstly, the network configuration of the host machine is ensured to be correct, and the IP network segment of the container is defined. Host environment and container IP network segment definitions are shown in table 1 below.
Step S2: container IP address global planning. The method comprises the steps of obtaining an environment number of a host machine in a cluster, dividing a container IP network segment based on the host machine environment number, dividing each host machine into IP address intervals which are not crossed and repeated, representing all IP addresses which can be allocated to a container on the host machine, and laying a foundation for allocation and recovery management of subsequent container IP addresses. The planning information is shown in table 2 below, and is stored on the host in the form of a file.
Step S3: and allocating and recycling the IP address of the container. When creating a container, the IP distributor on the host first obtains the container IP planning information of the host (step S2), then excludes the IP addresses that have been distributed, adopts round-robin policy to obtain a distributable IP address, distributes it to the container, and marks the IP address as a distributed state. When the container is deleted, the IP distributor can recycle the IP address of the current container to eliminate the distributed state. Because the container IP of different hosts is planned in different IP address intervals, the container IP address conflict condition in the whole cluster environment can be effectively avoided only by ensuring that the container IP address on a single host is properly managed.
The formula for assigning the container IP address is as follows:
wherein: last _ Assigned _ IP represents the newly allocated IP address, IP _ Range represents the IP address Range of the container on the host, and Unallocated _ Status represents the assignable state.
Step S4: configuring a container network interface device. An ipoib (IP protocol over Infiniband network) type network device is created on the Infiniband device ib0, bound to the network namespace of the container and renamed as eth0, and then the IP address assigned by the IP distributor is configured to the container network device eth0, thus realizing network connectivity of the hosts of the Infiniband device with the container. The specific commands are as follows:
creating a network device of the ipoib type:
network device joining to container's network namespace:
the network device is renamed eth 0:
IP address of eth0 of the configuration container:
eth0 network card to open container:
wherein the meaning of the variables:is a random name of the network device,is the name of the network namespace of container C1,is the IP address assigned to the container C1 (step S3).
Step S5: network access control and packet forwarding. Configuring an iptables rule of a host machine, and allowing an IP data packet of a container network segment to pass through; and configuring a route rule of the container, and setting the IP address of the ib0 network card of the host machine as a default route.
The iptables rule for a host is as follows in table 3:
the command to configure the container route rule is as follows:
Through configuration, when the host machine receives the data packet of the container network segment, the data packet is forwarded to the container for processing; when the container sends the data packet of the non-container network segment, the data packet is also routed to the host machine for processing, so that cross-network-segment communication between the container and the host machine, communication between the container and high-performance communication rate based on Infiniband are realized.
According to another aspect of the present invention, there is provided an Infiniband-based system for implementing cross-network communication between different containers, the system comprising: the system comprises a preparation environment module, a container IP address global planning module, a container IP address allocation and recovery module, a configuration container network interface equipment module and a network access control and data packet forwarding module;
the system comprises a preparation environment module, a container IP network segment definition module and a host machine, wherein the preparation environment module is used for ensuring that the network configuration of the host machine is correct and defining the container IP network segment through a container IP network segment definition rule;
the container IP address global planning module is used for acquiring the environment number of the host in the cluster and dividing the container IP network segment based on the host environment number;
the distribution and recovery module of the container IP address is used for distributing the container IP address through an IP distributor on the host machine, if the container is deleted, the IP distributor recovers the IP address of the current container and eliminates the distributed state of the IP address of the container;
the system comprises a configuration container network interface device module, a container network interface device module and a host machine, wherein the configuration container network interface device module is used for configuring container network interface devices and completing network communication between the host machine based on the infinite bandwidth technology device and a container;
and the network access control and data packet forwarding module is used for configuring iptables rules of the host and route rules of the container to complete network access control and data packet forwarding.
In one embodiment, when the container IP network segment is divided based on the host environment number, the IP address intervals divided by each host are not repeated in a crossing manner.
Fig. 1 is a network architecture diagram of hosts and their containers, describing the network (eth 0, ib 0) configuration scenario at host1 and host2, and 2 containers created on each of these 2 hosts, and the IPoIB-based container network configuration scenario.
Table 4-table 7, the routing information for the container is described.
Table 4 container1 routing information
Table 5 container2 routing information
Table 6 container3 routing information
Table 7 container4 routing information
iptable rule:
iptables is application software running in user space, and manages the processing and forwarding of network packets by controlling a Linux (a UNIX-like operating system which is free to use and propagate freely) kernel module. The iptables is internally provided with 4 tables, namely a filter table, a nat table, a mangle table and a raw table, and is used for realizing packet filtering, network address conversion, packet reconstruction and data tracking processing. Where the filter table is the default table, this table is used if no table is specified, which is typically used to filter packets. The nat table is used for address translation operations. The mangle table is used to process packets, and the main difference from the nat table is that the nat table is heavily connected and the mangle table is heavily tied to each packet. The raw table is used to handle exceptions.
Chains (chains) are the paths along which packets travel, and each chain is a checklist of rules, with each chain containing one or more rules. When a packet arrives in a chain, iptables will check from the first rule in the chain to determine if the packet satisfies the conditions defined by the rule. If so, the system processes the data packet according to the method defined by the rule; otherwise, the iptables will continue to check the next rule, and if the packet does not meet any rule in the chain, the iptables will process the packet according to a default policy predefined by the chain.
The process of iptables transmitting data packets is as follows in fig. 3:
firstly, when a data packet enters the network card, the data packet firstly enters a PREROUTING chain (pre-routing), and the kernel judges whether the data packet needs to be forwarded according to the destination IP of the data packet. ② if the data packet is local, it will move down the graph to INPUT chain (INPUT). After the packet arrives in the INPUT chain, any process receives it. A program running locally may send packets that go through the OUTPUT link and then to the post OUTPUT link (routed) for OUTPUT. And if the data packet is to be forwarded and the kernel allows forwarding, the data packet moves to the right as shown in fig. 3, passes through the FORWARD chain (forwarding), and then reaches the post output chain (after routing) for output.
route rule:
routing refers to the process in which a router receives a data packet from one interface, directs the data packet according to the destination address of the data packet, and forwards the data packet to another interface.
The routing method of the next node, i.e. to which "next node" the router sends the data packet, is indicated by configuring the routing rule. Routing rules may be configured via an ip route add command.
In summary, the container IP address global planning policy and the container IP address allocation and recovery management policy adopted in the present invention can effectively manage the IP addresses of the containers, and perfectly solve the problem of conflict of multiple container IP addresses on different hosts in a cluster environment. The configuration method of the container network interface equipment provided by the invention greatly plays the characteristics of high throughput and low delay of Infiniband on the basis of providing the communication connection between the container and the host, and meets the requirement of high-performance service of the container. The network access control and data packet forwarding strategy adopted by the invention effectively solves the problem of cross-network-segment communication of the container, realizes the cross-network-segment communication between the container and the host, between the container and between the container and the non-host, and realizes the network interconnection and intercommunication of the whole cluster environment.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A method for realizing cross-network communication among different containers based on Infiniband is characterized by comprising the following steps:
s1, ensuring the correct network configuration of the host machine, and defining the container IP network segment through the container IP network segment definition rule;
s2, acquiring the environment number of the host in the cluster, and dividing the container IP network segment based on the host environment number;
s3, allocating the IP address of the container through the IP distributor on the host machine, if the container is deleted, recycling the IP address of the current container through the IP distributor, and eliminating the allocated state of the IP address of the container;
s4, configuring the container network interface device, and completing the network communication between the host machine based on the infiniband technology device and the container;
and S5, configuring iptables rules of the host and route rules of the container to complete network access control and data packet forwarding.
2. The method according to claim 1, wherein when the container IP segment is divided based on the host environment number in S2, the IP address intervals of each host division are not repeated across each other.
3. The method of claim 1, wherein the step of assigning the container IP address by an IP assigner on a host in S3 further comprises the steps of:
when a container is created, an IP distributor on a host machine acquires container IP planning information of the host machine and eliminates an IP address which is distributed;
and obtaining an allocable IP address by adopting a polling scheduling algorithm, allocating the IP address to the container, and marking the IP address as an allocated state.
4. The method for implementing cross-network communication between different containers based on Infiniband according to claim 1, wherein the formula for allocating the IP address of the container in S3 is as follows:
5. The method according to claim 1, wherein the step of configuring the container network interface device in S4, and the step of completing the network connection between the host and the container based on the Infiniband technology device further comprises the following steps:
s41, create an ipoib-type network device on infiniband technology device ib0, and bind the network device to the container' S network namespace and rename it eth 0;
s42, the IP address assigned by the IP distributor is configured to the container network device eth 0.
6. The method according to claim 1, wherein the step of configuring the container network interface device in S4 includes:
creating an ipoib-type network device;
adding a network device to a network namespace of a container;
rename the network device to eth 0;
configuring an IP address of eth0 of the container;
open eth0 network card of container.
7. The method according to claim 1, wherein the step of configuring iptables rules of the host and route rules of the container in S5, and the step of performing network access control and packet forwarding further comprises the steps of:
s51, configuring iptables rules of the host machine and allowing the IP data packet of the container network segment to pass through;
s52, configuring the route rule of the container, and setting the IP address of the ib0 network card of the host machine as a default route.
9. An Infiniband-based system for realizing cross-network communication between different containers, for realizing the method of any one of claims 1 to 8, wherein the system comprises: the system comprises a preparation environment module, a container IP address global planning module, a container IP address allocation and recovery module, a configuration container network interface equipment module and a network access control and data packet forwarding module;
the system comprises a preparation environment module, a container IP network segment definition module and a host machine, wherein the preparation environment module is used for ensuring that the network configuration of the host machine is correct and defining the container IP network segment through a container IP network segment definition rule;
the container IP address global planning module is used for acquiring the environment number of the host in the cluster and dividing the container IP network segment based on the host environment number;
the distribution and recovery module of the container IP address is used for distributing the container IP address through an IP distributor on the host machine, if the container is deleted, the IP distributor recovers the IP address of the current container and eliminates the distributed state of the IP address of the container;
the system comprises a configuration container network interface device module, a container network interface device module and a host machine, wherein the configuration container network interface device module is used for configuring container network interface devices and completing network communication between the host machine based on the infinite bandwidth technology device and a container;
and the network access control and data packet forwarding module is used for configuring iptables rules of the host and route rules of the container to complete network access control and data packet forwarding.
10. The system of claim 9, wherein the IP address intervals for each host partition are not repeated across partitions when partitioning container IP segments based on host environment numbers.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110702022.2A CN113259503B (en) | 2021-06-24 | 2021-06-24 | Method and system for realizing cross-network communication among different containers based on Infiniband |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110702022.2A CN113259503B (en) | 2021-06-24 | 2021-06-24 | Method and system for realizing cross-network communication among different containers based on Infiniband |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113259503A true CN113259503A (en) | 2021-08-13 |
CN113259503B CN113259503B (en) | 2021-10-08 |
Family
ID=77189444
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110702022.2A Active CN113259503B (en) | 2021-06-24 | 2021-06-24 | Method and system for realizing cross-network communication among different containers based on Infiniband |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113259503B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114070822A (en) * | 2021-11-17 | 2022-02-18 | 苏州博纳讯动软件有限公司 | Kubernetes Overlay IP address management method |
CN114143316A (en) * | 2021-11-30 | 2022-03-04 | 招商局金融科技有限公司 | Multi-tenant network communication method and device, container node and storage medium |
CN114157455A (en) * | 2021-11-16 | 2022-03-08 | 北京达佳互联信息技术有限公司 | Data transmission method, device, equipment and storage medium |
CN114172802A (en) * | 2021-12-01 | 2022-03-11 | 百果园技术(新加坡)有限公司 | Container network configuration method and device, computing node, main node and storage medium |
CN114401214A (en) * | 2021-12-28 | 2022-04-26 | 航天科工网络信息发展有限公司 | Network and method for realizing container multicast communication |
CN114866510A (en) * | 2022-05-25 | 2022-08-05 | 山东省计算中心(国家超级计算济南中心) | Cross-network and remote interconnection communication method and system based on InfiniBand network |
CN114979076A (en) * | 2022-05-23 | 2022-08-30 | 杭州仟金顶信息科技有限公司 | Flat communication network oriented to cross-host container |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106844000A (en) * | 2016-12-21 | 2017-06-13 | 北京大学 | Using the method and apparatus of browser access linux container cluster under a kind of multi-user environment |
CN107332775A (en) * | 2017-08-14 | 2017-11-07 | 上海新炬网络信息技术股份有限公司 | Across host exchanging visit system and its control method based on docker containers |
CN107395781A (en) * | 2017-06-29 | 2017-11-24 | 北京小度信息科技有限公司 | Network communication method and device |
CN107566541A (en) * | 2017-08-03 | 2018-01-09 | 携程旅游信息技术(上海)有限公司 | Capacitor network resource allocation methods, system, storage medium and electronic equipment |
CN108737584A (en) * | 2017-04-19 | 2018-11-02 | 中国移动通信集团山西有限公司 | The access method of container service, the analytic method of network address, device and system |
US20200067876A1 (en) * | 2018-08-22 | 2020-02-27 | International Business Machines Corporation | Configuring virtual machine instances using one-to-one mappings |
CN111491040A (en) * | 2020-04-09 | 2020-08-04 | 北京城市网邻信息技术有限公司 | IP distribution method and IP distribution device |
CN111654559A (en) * | 2020-05-29 | 2020-09-11 | 深圳前海微众银行股份有限公司 | Container data transmission method and device |
CN112565047A (en) * | 2020-11-19 | 2021-03-26 | 浪潮思科网络科技有限公司 | Method, device, equipment and medium for constructing network by using VPP in docker |
-
2021
- 2021-06-24 CN CN202110702022.2A patent/CN113259503B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106844000A (en) * | 2016-12-21 | 2017-06-13 | 北京大学 | Using the method and apparatus of browser access linux container cluster under a kind of multi-user environment |
CN108737584A (en) * | 2017-04-19 | 2018-11-02 | 中国移动通信集团山西有限公司 | The access method of container service, the analytic method of network address, device and system |
CN107395781A (en) * | 2017-06-29 | 2017-11-24 | 北京小度信息科技有限公司 | Network communication method and device |
CN107566541A (en) * | 2017-08-03 | 2018-01-09 | 携程旅游信息技术(上海)有限公司 | Capacitor network resource allocation methods, system, storage medium and electronic equipment |
CN107332775A (en) * | 2017-08-14 | 2017-11-07 | 上海新炬网络信息技术股份有限公司 | Across host exchanging visit system and its control method based on docker containers |
US20200067876A1 (en) * | 2018-08-22 | 2020-02-27 | International Business Machines Corporation | Configuring virtual machine instances using one-to-one mappings |
CN111491040A (en) * | 2020-04-09 | 2020-08-04 | 北京城市网邻信息技术有限公司 | IP distribution method and IP distribution device |
CN111654559A (en) * | 2020-05-29 | 2020-09-11 | 深圳前海微众银行股份有限公司 | Container data transmission method and device |
CN112565047A (en) * | 2020-11-19 | 2021-03-26 | 浪潮思科网络科技有限公司 | Method, device, equipment and medium for constructing network by using VPP in docker |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114157455A (en) * | 2021-11-16 | 2022-03-08 | 北京达佳互联信息技术有限公司 | Data transmission method, device, equipment and storage medium |
CN114070822A (en) * | 2021-11-17 | 2022-02-18 | 苏州博纳讯动软件有限公司 | Kubernetes Overlay IP address management method |
CN114070822B (en) * | 2021-11-17 | 2022-10-14 | 江苏博云科技股份有限公司 | Kubernetes Overlay IP address management method |
CN114143316A (en) * | 2021-11-30 | 2022-03-04 | 招商局金融科技有限公司 | Multi-tenant network communication method and device, container node and storage medium |
CN114143316B (en) * | 2021-11-30 | 2024-03-19 | 招商局金融科技有限公司 | Multi-tenant network communication method, device, container node and storage medium |
CN114172802A (en) * | 2021-12-01 | 2022-03-11 | 百果园技术(新加坡)有限公司 | Container network configuration method and device, computing node, main node and storage medium |
CN114172802B (en) * | 2021-12-01 | 2024-04-26 | 百果园技术(新加坡)有限公司 | Container network configuration method, device, computing node, master node and storage medium |
CN114401214A (en) * | 2021-12-28 | 2022-04-26 | 航天科工网络信息发展有限公司 | Network and method for realizing container multicast communication |
CN114401214B (en) * | 2021-12-28 | 2024-03-29 | 航天科工网络信息发展有限公司 | Network and method for realizing multicast communication of containers |
CN114979076A (en) * | 2022-05-23 | 2022-08-30 | 杭州仟金顶信息科技有限公司 | Flat communication network oriented to cross-host container |
CN114979076B (en) * | 2022-05-23 | 2024-03-29 | 杭州仟金顶信息科技有限公司 | Flattened communication method oriented to cross-host container |
CN114866510A (en) * | 2022-05-25 | 2022-08-05 | 山东省计算中心(国家超级计算济南中心) | Cross-network and remote interconnection communication method and system based on InfiniBand network |
Also Published As
Publication number | Publication date |
---|---|
CN113259503B (en) | 2021-10-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113259503B (en) | Method and system for realizing cross-network communication among different containers based on Infiniband | |
US10230661B2 (en) | Distributed virtual network embedding | |
US10389620B2 (en) | System and apparatus of a software-service-defined-network (SSDN) | |
JP6733486B2 (en) | Vertex-centric service function chain formation in multi-domain networks | |
CN114172802B (en) | Container network configuration method, device, computing node, master node and storage medium | |
CN108111383B (en) | SDN-based cross-domain container virtual network construction method | |
JP6950327B2 (en) | Cross-domain orchestration of switch and service functions | |
US9264375B2 (en) | Software-defined networking interface between multiple platform managers | |
CN102577277B (en) | Providing a logical aggregated point-to-point data link incorporating a multi-point link | |
CN107947961A (en) | Kubernetes Network Management System and method based on SDN | |
CN111510515B (en) | Method and device for distinguishing containers of mixed application environment | |
US20150229565A1 (en) | Techniques for Managing Ternary Content-Addressable Memory (TCAM) Resources in Heterogeneous Systems | |
CN102546384B (en) | Dynamic resource management method | |
CN103917967A (en) | Network control system for configuring middleboxes | |
CN105407140A (en) | Calculation resource virtualization system of networked test system and method thereof | |
CN103346981A (en) | Virtual exchange method, related device and computer system | |
CN107003860B (en) | Software defined network controller and creating method thereof | |
CN105052113A (en) | Common agent framework for network devices | |
EP3682597B1 (en) | Modeling access networks as trees in software-defined network controllers | |
WO2014183531A1 (en) | Method and device for allocating remote memory | |
CN114500523B (en) | Fixed IP application publishing method based on container cloud platform | |
CN107609061A (en) | A kind of method and apparatus of data syn-chronization | |
CN105791402A (en) | Network virtualization realization method of cloud computing platform and corresponding plug-in and agent | |
Moro et al. | A framework for network function decomposition and deployment | |
KR101794719B1 (en) | Method and system for ip address virtualization in sdn-based network virthalization platform |
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 |