WO2024104168A1 - 跨区域的虚拟私有云之间通信的配置方法及相关装置 - Google Patents

跨区域的虚拟私有云之间通信的配置方法及相关装置 Download PDF

Info

Publication number
WO2024104168A1
WO2024104168A1 PCT/CN2023/129012 CN2023129012W WO2024104168A1 WO 2024104168 A1 WO2024104168 A1 WO 2024104168A1 CN 2023129012 W CN2023129012 W CN 2023129012W WO 2024104168 A1 WO2024104168 A1 WO 2024104168A1
Authority
WO
WIPO (PCT)
Prior art keywords
cloud
vpc
network status
communication channel
management platform
Prior art date
Application number
PCT/CN2023/129012
Other languages
English (en)
French (fr)
Inventor
杨国东
高峰
Original Assignee
华为云计算技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Priority claimed from CN202211532345.2A external-priority patent/CN118101649A/zh
Application filed by 华为云计算技术有限公司 filed Critical 华为云计算技术有限公司
Publication of WO2024104168A1 publication Critical patent/WO2024104168A1/zh

Links

Classifications

    • 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
    • H04L41/0803—Configuration setting

Definitions

  • the present application relates to the field of cloud technology, and in particular to a configuration method and related device for communication between cross-region virtual private clouds (VPCs).
  • VPCs virtual private clouds
  • the existing cross-region communication technology of virtual private clouds mainly sends data packets through a fixed sending window, and indirectly obtains the network status between cross-VPC channels based on the feedback time of the response packet, and then adjusts the sending window based on the indirectly obtained network status.
  • This method requires using a fixed sending window to send data packets at a fixed packet sending speed, and gradually increases the sending window for slow start based on the feedback network status, which will lead to slow start, network congestion, and difficulty in rapid recovery when microbursts occur, resulting in low efficiency of communication between cross-region virtual private clouds at this stage.
  • the present application provides a configuration method and related devices for communication between cross-region virtual private clouds (VPCs), which can improve the communication efficiency between cross-region private clouds (VPCs).
  • VPCs virtual private clouds
  • the present application provides a configuration method for communication between cross-regional virtual private clouds (VPCs), the method being used for a cloud management platform, wherein the cloud management platform is used to manage a network infrastructure that provides public cloud services, the network infrastructure comprising a first VPC set in a first region and a second VPC set in a second region, the method comprising: the cloud management platform provides a bandwidth package configuration interface, the bandwidth package configuration interface being used to obtain first configuration information of a bandwidth package for a tenant input by a tenant, wherein the first configuration information is used to determine a cloud connection service bound to the bandwidth package and whether the cloud connection service has a traffic optimization requirement, the cloud connection service is used to establish a communication channel between the first VPC and the second VPC, the bandwidth package is used to limit the traffic of a first communication channel between the first VPC and the second VPC, the cloud management platform detects first network status information of the first communication channel based on the configuration information, and feeds back the first network status information to a cloud instance in the first VPC
  • the cloud management platform can detect the network status information of the first communication channel based on the tenant's request and feed it back to the cloud instance in the first VPC as the sender, the cloud instance in the first VPC adjusts the packet sending rate to match the network status of the first communication channel according to the network status information. Therefore, when the cloud instance in the first VPC sends a data packet to the second VPC, it does not need to perform any trial about the packet sending rate, and can directly set the packet sending rate to match the network status, thereby improving the packet sending efficiency.
  • the first network status information includes information indicating that the network status of the first communication channel is normal. Then, the first network status information is used to indicate that after the cloud instance in the first VPC successfully shakes hands with the cloud instance in the second VPC, the TCP packet sending window is adjusted to the maximum value without slow start.
  • the cloud instance in the first VPC does not need to tentatively adjust the packet sending rate, such as slowly increasing the size of the message sending window from 1 (i.e., slow start), which wastes bandwidth. Instead, the cloud instance directly adjusts the message sending window to the maximum value based on the information that the network status is normal, thereby avoiding slow start and improving communication efficiency.
  • the first network status information includes information indicating that the network status of the first communication channel has deteriorated, and the first network status information is used to instruct the cloud instance in the first VPC to adjust the TCP message sending window to be smaller.
  • the information indicating that the network status of the first communication channel has deteriorated includes one or any combination of information indicating that the network delay of the first communication channel has increased, information indicating that the transmission bandwidth of the first communication channel has decreased, and information indicating that the packet loss rate of the first communication channel has increased.
  • the cloud instance in the first VPC does not need to test the network status by sending and receiving packets after the network degradation occurs. Instead, it can directly know and reduce the sending window when the degradation occurs, thereby avoiding the worse impact of packet loss.
  • the first network status information includes information indicating that the network status of the first communication channel is normal. Then, the network status information of the first communication channel is used to indicate that the cloud instance in the first VPC still maintains the TCP message sending window unchanged when packet loss occurs.
  • the cloud instance in the first VPC does not need to be Instead of generating an aggressive congestion control response when packets are received, rapidly reducing the packet sending rate and causing bandwidth waste, the network can be informed that there is no real congestion, thus keeping the message sending window unchanged.
  • the bandwidth package is also used to provide bandwidth for a second communication channel between the second VPC and the first VPC
  • the cloud management platform detects the network status of the second communication channel based on the first configuration information, and feeds back second network status information carrying the network status of the second communication channel to the cloud instance in the second VPC
  • the second network status information is used to instruct the cloud instance in the second VPC to adjust the packet rate of the traffic sent to the first VPC via the second communication channel according to the network status of the second communication channel to match the network status of the second communication channel, thereby achieving traffic optimization and traffic acceleration.
  • the cloud management platform can further detect the second network status of the second communication channel between the second VPC and the first VPC, and feed back the second network status information to the cloud instance in the second VPC, thereby simultaneously achieving upstream and downstream traffic optimization between the second VPC and the first VPC.
  • the cloud instance in the first VPC is any one of a virtual machine, a container, a bare metal server BMS, and a dedicated host set in the first VPC. Therefore, any cloud instance in the VPC managed by a cloud management platform can achieve traffic optimization.
  • the cloud management platform also provides a bandwidth package purchase interface, which is used to obtain the tenant's payment information for the bandwidth package; the cloud management platform provides the bandwidth package to the tenant based on the payment information.
  • the cloud management platform can obtain the tenant's payment information and provide the tenant with the corresponding bandwidth package.
  • the tenant can apply the bandwidth package to the cloud connection service based on the needs on the cloud management platform.
  • the cloud management platform also provides a cloud connection service configuration interface, which is used to obtain second configuration information of the cloud connection service input by the tenant, the second configuration information including an identifier of the first VPC, an identifier of the second VPC, and an identifier of the bandwidth package; the cloud management platform binds the bandwidth package to the cloud connection service according to the second configuration information.
  • the cloud management platform can obtain the identifiers of the first VPC, the second VPC and the bandwidth package, and bind the bandwidth package to the corresponding cloud connection service, so that the first VPC and the second VPC connected to the cloud connection service can achieve cross-region communication through the bandwidth provided by the bandwidth package.
  • the present application provides a cloud management platform for communication between cross-regional virtual private clouds (VPCs), wherein the cloud management platform is used to manage a network infrastructure that provides public cloud services, the network infrastructure includes a first VPC set in a first region and a second VPC set in a second region, and the cloud management platform includes: a bandwidth package configuration module, which is used to provide a bandwidth package configuration interface, and the bandwidth package configuration interface is used to obtain first configuration information of a bandwidth package for a tenant input by a tenant, wherein the first configuration information is used to determine a cloud connection service bound to the bandwidth package and that the cloud connection service has a traffic acceleration requirement, the cloud connection service is used to connect the first VPC and the second VPC, and the bandwidth package is used to provide bandwidth for a first communication channel between the first VPC and the second VPC; a network status information detection module, which is used to detect the network status of the first communication channel based on the configuration information, and feed back the first network status information carrying the network status of the first communication channel to
  • VPCs
  • the second aspect or any implementation of the second aspect is an implementation of the device corresponding to the first aspect or any implementation of the first aspect.
  • the description in the first aspect or any implementation of the first aspect is applicable to the second aspect or any implementation of the second aspect and will not be repeated here.
  • the present application provides a computing device cluster, which includes at least one computing device, each computing device including a processor and a memory; the processor of at least one computing device is used to execute instructions stored in the memory of at least one computing device, so that the computing device cluster executes any possible method such as the first aspect.
  • the present application provides a computer program product comprising instructions, wherein when the instructions are executed by a computing device cluster, the computing device cluster is caused to execute any possible method of the first aspect.
  • a computer-readable storage medium which includes computer program instructions.
  • the computing device cluster executes any possible method of the first aspect.
  • FIG1 is a schematic diagram of a structure of a cloud service provided in an embodiment of the present application that is deployed across regions on a cloud backbone network.
  • FIG2 is a curve diagram of the congestion window change of the TCP algorithm during slow start and congestion avoidance.
  • FIG3 is a schematic diagram of an acceleration process provided in an embodiment of the present application.
  • FIG. 4 is a schematic diagram of a configuration interface provided in an embodiment of the present application.
  • FIG. 5 is another schematic diagram of an acceleration process provided in an embodiment of the present application.
  • FIG6 is another schematic diagram of an acceleration process provided in an embodiment of the present application, in which the message sending direction is opposite to that of FIG5 .
  • FIG. 7 is a schematic diagram of a process for avoiding slow start provided in an embodiment of the present application.
  • FIG8 is a schematic diagram of a process of avoiding packet loss by perceiving degradation provided in an embodiment of the present application.
  • FIG. 9 is a schematic diagram of a process for avoiding microbursts provided in an embodiment of the present application.
  • FIG10 is a schematic diagram of the structure of a cloud management platform provided in an embodiment of the present application.
  • FIG. 11 is a schematic diagram of a computing device cluster structure of a cloud management platform provided in an embodiment of the present application.
  • FIG. 12 is a schematic diagram of a computing device cluster structure of another cloud management platform provided in an embodiment of the present application.
  • FIG. 13 is a schematic diagram of a computing device cluster structure of another cloud management platform provided in an embodiment of the present application.
  • VPC Virtual Private Cloud
  • VPC A dynamically configured pool of public cloud computing resources that requires the use of encryption protocols, tunneling protocols, and other security programs to transmit data between enterprises and cloud service providers.
  • VPC builds an isolated, user-configured, and managed virtual network environment for elastic cloud servers, improves the security of user cloud resources, and simplifies user network deployment.
  • Security groups, virtual private networks (VPN), IP address segments, bandwidth, and other network features can be defined in VPC.
  • Tenants can use VPC to conveniently manage and configure internal networks and make safe and fast network changes.
  • Cloud Connect (CC) service It can quickly build a high-speed, high-quality, and stable network between cross-region VPCs and multiple VPCs on the cloud and multiple data centers under the cloud, helping users build a global cloud network with enterprise-level scale and communication capabilities.
  • the Cloud Connect service can load network instances in different regions that need to be interconnected, and finally provide global network interconnection services by configuring the inter-domain bandwidth between network instances that need to be interconnected.
  • the Cloud Connect service is generally charged in a tiered pricing manner based on the bandwidth package that supports regional interconnection.
  • Cloud Backbone Network A high-speed network that connects cloud vendors’ data centers in different regions, allowing users to build a multi-region global network in minutes and integrate it with the hybrid cloud.
  • Cloud management platform The cloud management platform is used to manage multiple cloud data centers set up by cloud vendors in different regions.
  • the cloud management platform can provide interfaces related to public cloud services, such as configuration pages or application program interfaces (APIs) for tenants to remotely access public cloud services.
  • Tenants can log in to the cloud management platform with a pre-registered account and password, and after a successful login, they can select and purchase public cloud services provided by the cloud data center in the predetermined area, such as object storage services, virtual machine services, container services or other known public cloud services.
  • Region Divided based on geographic location and network latency, multiple data centers in the same region share public services such as elastic computing, block storage, object storage, VPC network, elastic public IP, and mirroring.
  • Tenant A top-level object used to manage cloud service virtual machines, identified by tenant name and tenant ID. Cloud contracts, fund accounts, orders, and cloud resources are all managed by the corresponding tenant.
  • Round-Trip Time In computer networks, it refers to the delay from the start of data transmission at the sender to the receipt of confirmation from the receiver. It is determined by three parts: the link propagation time, the end system processing time, and the queuing and processing time in the router's cache. Among them, the values of the first two parts are relatively fixed as a TCP connection, and the queuing and processing time in the router's cache will change with the change of the congestion level of the entire network. Therefore, the change of RTT reflects the change of network congestion level to a certain extent.
  • Slow start When a host starts to send datagrams, if a large amount of data is immediately injected into the network, network congestion may occur.
  • the slow start algorithm is to detect the network status when the host starts to send datagrams. If the network status is good, the sender can correctly receive the confirmation segment every time it sends a segment. Then increase the size of the congestion window from small to large, that is, increase the size of the sending window.
  • Microburst A port receives a lot of burst data in a short period of time at the millisecond level.
  • the duration of a typical microburst is usually 1 to 100 In milliseconds, the instantaneous burst rate reaches tens or hundreds of times the average rate, or even exceeds the port bandwidth.
  • TCP Transmission Control Protocol
  • the TCP sliding window is halved and the rate drops rapidly, resulting in a jagged and bursty session traffic.
  • TCP always hopes to send the data in the sending window as soon as possible, so it will continue to send data through the sliding window mechanism after waiting for the TCP packet arrival confirmation (ACK). This cycle makes the packet sending rate uneven and highly bursty.
  • a cloud instance is an instance in a cloud service.
  • a cloud instance is any one of a virtual machine, a container, a bare metal server BMS, and a dedicated host set in a VPC.
  • FIG. 1 is a schematic diagram of the structure of a public cloud system involving VPC cross-region communication.
  • the public cloud system includes a cloud management platform 10 and a cloud data center cluster.
  • the cloud data center cluster includes multiple subclusters, each subcluster includes multiple cloud data centers, and each subcluster is set in a different region.
  • VPCs can be set in the cloud data center.
  • VPC1 and VPC2 are set in cloud data center 1.
  • Tenant 40 can access the cloud management platform 10 through the Internet 20 through client 30, and manage the VPCs in the cloud data center through the cloud management platform 10, for example, manage VPC1 in cloud data center 1 and/or VPC4 in cloud data center 3.
  • Tenant 40 can purchase cloud connection services for cross-region communication for virtual private clouds deployed in different regions on the cloud management platform 10.
  • tenant 40 can also configure bandwidth packages required for cloud connection services in the cloud management platform 10.
  • the system further includes at least two regions, namely, region 1, region 2, region 3 and region 4.
  • Each region includes at least one VPC, and some VPCs include at least one cloud instance.
  • VPCs located in different regions need to communicate across regions, a communication channel is established on the cloud backbone network through a cloud connection gateway.
  • VPC1 is connected to edge access point 1 on the cloud backbone network through a gateway
  • VPC4 is connected to edge access point 2 on the cloud backbone network through a gateway, thereby establishing a connection between VPC1 and VPC4 on the cloud backbone network.
  • the figure shows that VPC1 located in region 1 and VPC4 located in region 2 establish an uplink communication channel 1 for transmitting messages from VPC1 to VPC4 and a downlink communication channel 2 for transmitting messages from VPC4 to VPC1.
  • Figure 2 is a curve diagram of the congestion window change of the TCP algorithm during slow start and congestion avoidance.
  • the cloud instance needs to perceive the network status through the TCP congestion control algorithm to adjust the message sending and receiving rate.
  • the TCP algorithm cannot directly know the real state of the network, but requires the cloud instance to send and receive packets to test the network status.
  • the TCP algorithm cannot determine whether there is network congestion.
  • the congestion window will only increase slowly when the sender receives a new ACK.
  • the sender's congestion window will first double from 1, showing an exponential growth until it reaches a certain level.
  • the exponential growth changes to linear growth, and finally reaches the optimal message receiving and sending window.
  • packet loss occurs at nodes 1 and 3
  • the TCP protocol will consider that network congestion has occurred, and thus enter phase 3 to reduce the congestion window.
  • the congestion window will even be reset to 0, and the slow start phase will be re-entered.
  • TCP uses a slow start strategy when the sender and receiver establish a connection in order to avoid packet loss caused by a large number of messages being sent and received when the network is congested, thereby ensuring the reliability of communication.
  • network congestion is not a very common phenomenon. When the network status is normal, if the slow start method is still used, the communication efficiency will be reduced. The same negative effect also occurs in the TCP protocol's misjudgment of the congestion status caused by microbursts.
  • an embodiment of the present invention provides a configuration method and related device for communication between cross-region virtual private clouds (VPCs). Based on the public cloud system shown in FIG1 , the method and device detect the network status of the communication channel between cross-region cloud instances through a cloud management platform and feed it back to the cloud instance, thereby instructing the cloud instance to adjust the message sending and receiving rate, realize traffic acceleration, and improve the communication efficiency between cross-region private clouds (VPCs).
  • VPCs virtual private clouds
  • FIG. 3 is a schematic diagram of a cross-region communication acceleration process provided by an embodiment of the present invention.
  • the process includes but is not limited to the following steps:
  • Step S101 The tenant configures a bandwidth package.
  • the tenant purchases and configures a bandwidth package on the cloud management platform through the client
  • the tenant pays through the bandwidth package purchase interface provided by the cloud management platform, and configures through the bandwidth package configuration interface provided by the cloud management platform.
  • Step S102 The cloud management platform creates a cloud connection.
  • the cloud management platform creates a cloud connection.
  • cloud instance 1 in region 1 is connected to cloud instance 3 in region 2 through a gateway, edge access point 1, and edge access point 2.
  • Figure 4 is a schematic diagram of a configuration interface provided by an embodiment of the present invention.
  • the configuration information includes but is not limited to billing mode, interconnection area, bandwidth, acceleration service, instance, etc.
  • Step S103 The cloud management platform allocates bandwidth packages for the communication channels between VPCs and configures cloud instance acceleration services.
  • the cloud management platform determines the communication between the virtual private clouds to be configured with cloud connection services based on the purchase and configuration information provided by the tenant.
  • the communication channel and cloud instance are then allocated bandwidth packages for the communication channel and acceleration services are configured for the cloud instance in the virtual private cloud.
  • the cloud management platform sets up a user-mode acceleration service agent in the cloud instance.
  • Step S104 Register for acceleration service.
  • the cloud instance corresponding to the aforementioned steps enables the acceleration service and registers with the cloud management platform through the user-mode acceleration service agent set in the cloud instance.
  • Step S105 Acquire and notify the network status of the communication channel.
  • the cloud management platform After the cloud management platform accepts the registration of the cloud instance, it starts to obtain the network status of the cross-region communication channel 1 and notifies the cloud instance 1 in VPC 1.
  • the network status can be reflected by one or any combination of network latency, transmission bandwidth and packet loss rate.
  • Step S106 adjusting the message sending window according to the network status.
  • cloud instance 1 adjusts the TCP message sending window according to the network status information provided by the cloud management platform.
  • Step S107 Send a message.
  • cloud instance 1 located in VPC1 sends a message to cloud instance 3 located in VPC4 through a cross-region communication channel.
  • Figures 5 and 6 are schematic diagrams of a cross-region communication acceleration process provided by an embodiment of the present invention, respectively showing the process of accelerating communication from cloud instance 1 to cloud instance 3 and accelerating communication from cloud instance 3 to cloud instance 1.
  • the operation of the cross-region communication acceleration service includes but is not limited to the following steps:
  • Step S201 The cloud management platform 10 detects the network status information 10 of the communication channel 1 through which the cloud instance 1 sends a message to the cloud instance 3.
  • Step S202 the cloud management platform feeds back network status information 10 to cloud instance 1.
  • Step S203 Cloud instance 1 adjusts the TCP packet sending rate sent by it to cloud instance 3 through communication channel 1. Specifically, when the network status information 10 shows that the network status is normal, the packet sending rate is adjusted to the maximum, and when the network status information 10 shows that the network status is deteriorated, the packet sending rate is reduced.
  • FIG6 reverses the communication direction of FIG5, and converts the message sent from cloud instance 1 in region 1 to cloud instance 3 in region 2 to cloud instance 3 in region 2 to cloud instance 1 in region 1, that is, FIG5 shows the scenario where VPC1 in region 1 transmits a message to VPC4 in region 2 through uplink communication channel 1, and FIG6 shows the scenario where VPC4 in region 2 transmits a message to VPC1 in region 1 through downlink communication channel 2.
  • FIG5 shows the scenario where VPC1 in region 1 transmits a message to VPC4 in region 2 through uplink communication channel 1
  • FIG6 shows the scenario where VPC4 in region 2 transmits a message to VPC1 in region 1 through downlink communication channel 2.
  • S201-S203 which will not be repeated here.
  • the cloud management platform 10 includes a network status information detection module 11 and an acceleration service management module 12, and the cloud instance 1 includes an acceleration service proxy module 51 and a message acceleration module 52.
  • the cloud instance can start the acceleration service proxy 51 and the message acceleration module 52.
  • the acceleration service proxy 51 can be set in the user state
  • the message acceleration module 52 can be set in the kernel state.
  • FIG 7 is a flow chart of avoiding slow start in an embodiment of the present invention. It is specifically applied in the scenario of cross-region VPC connection.
  • the acceleration service agent 51 in cloud instance 1 registers the acceleration service with the acceleration service management 12 in the cloud management platform to obtain network status information.
  • the acceleration service agent 51 feeds back the network status information to the message acceleration module 52, and the message acceleration module 52 adjusts the message sending rate based on the network status information.
  • the acceleration service management 12 in the cloud management platform obtains the information registered by the acceleration service agent 51 and notifies the network status information.
  • the network status information is detected by the network status information detection module.
  • the message acceleration module 52 in cloud instance 1 sends a connection start notification to the acceleration service agent 51, and the acceleration service agent 51 sends a connection start notification to the acceleration service management 12 in the cloud management platform.
  • the acceleration service management 12 sends an information request to the network status information detection module 11 to obtain the network status information.
  • the network status information detection module 11 detects the network status, obtains the network status information, and finally sends it to the message acceleration module 52 via the acceleration service management 12 and the acceleration service agent 51.
  • the message acceleration module 52 adjusts its message sending window to the optimum according to the information, thereby avoiding the slow start effect caused by slowly expanding the congestion window according to the TCP protocol when the connection is started.
  • FIG8 is a flow chart of sensing network state degradation and avoiding packet loss in an embodiment of the present invention, which is specifically applied to the scenario where network state degradation occurs during cross-region private cloud communication.
  • the network state degradation here includes one or more of increased network delay, reduced transmission bandwidth, and increased packet loss rate.
  • the acceleration service management module 12 requests to obtain network state information from the network state information detection module 11.
  • the network state information detection module 11 detects that the network state is degraded and sends the information to the acceleration service management module 12.
  • the acceleration service management module 12 then sends it to the acceleration service agent 51 in the cloud instance.
  • the message acceleration module 52 After the message acceleration module 52 receives the network state degradation information, it knows that the network has degraded, and reduces the message sending window according to the information, thereby avoiding the TCP message sending window from being adjusted in time when the network is degraded, resulting in packet loss and causing a worse impact.
  • FIG9 is a flow chart of avoiding microbursts in an embodiment of the present invention, which is specifically applied to the scenario where microbursts occur during cross-region private cloud communication.
  • the message acceleration module 52 in the cloud instance sends a packet loss notification to the acceleration service proxy module 51, and the acceleration service proxy module 51 reports the packet loss notification to the acceleration service management module 12 in the cloud management platform.
  • a request for obtaining network status information is sent to the network status information detection module 11.
  • the communication channel is not actually congested, and the network status information detection module 11 detects that the network status is normal, and sends the information that the network status is normal to the acceleration service management module 12.
  • the acceleration service management module 12 sends the information that the network status is normal to the acceleration service proxy module 51 in the cloud instance.
  • the message acceleration module 52 in the cloud instance obtains the information that the network status is normal, it knows that the network status is normal and no congestion has occurred, and keeps the congestion window unchanged based on the information, thereby avoiding the TCP protocol from overreacting to a small amount of packet loss when a micro-burst occurs, excessively reducing the message sending window, causing network bandwidth waste, and reducing transmission efficiency.
  • the above-mentioned embodiments disclose a method and apparatus for accelerating cross-region private cloud traffic by controlling the sending window of TCP messages. It is worth noting that in other embodiments of the present invention, the cloud instance can also achieve the above-mentioned function by controlling the sending window of Stream Control Transmission Protocol (SCTP) messages or other messages that adjust the packet sending rate in a trial manner.
  • SCTP Stream Control Transmission Protocol
  • the embodiments of the present invention do not limit the type of messages. Those skilled in the art can apply the ideas of the present invention to different types of messages according to their own needs, thereby achieving message acceleration.
  • Figure 10 shows a schematic diagram of the functional modules of the cloud management platform based on an embodiment of the present invention, including a network status information detection module 11, an acceleration service management module 12, a service binding module 13, a bandwidth package purchasing module 14, a bandwidth package configuration module 15, a bandwidth package providing module 16, and a cloud connection service configuration module 17.
  • the network status information detection module 11 is used to execute the step of obtaining the communication channel status in S105
  • the service binding module 13 is used to execute the step of creating a cloud connection in S102
  • the acceleration service management module 12 is used to execute the step of configuring the acceleration service for the cloud instance in S103
  • the bandwidth package purchasing module 14 is used to execute the step of purchasing the bandwidth package for the tenant in S101
  • the bandwidth package configuration module 15 is used to execute the step of configuring the bandwidth package for the tenant in S101
  • the bandwidth package providing module 16 is used to execute the step of allocating bandwidth packages for the communication channel between VPCs in S103
  • the cloud connection service configuration module 17 is used to execute the step of allocating bandwidth packages for the communication channel between VPCs in S103 and configuring the cloud instance acceleration service.
  • the cloud management platform can be implemented by software or hardware. As an example, the implementation of the cloud management platform is described below.
  • a cloud management platform may include code running on a computing instance.
  • the computing instance may be at least one of a physical host (computing device), a virtual machine, a container, and other computing devices.
  • the computing device may be one or more.
  • the cloud management platform may include code running on multiple hosts/virtual machines/containers.
  • the multiple hosts/virtual machines/containers used to run the application may be distributed in the same region or in different regions.
  • the multiple hosts/virtual machines/containers used to run the code may be distributed in the same AZ or in different AZs, each AZ including one data center or multiple data centers with close geographical locations.
  • a region may include multiple AZs.
  • multiple hosts/virtual machines/containers used to run the code can be distributed in the same VPC or in multiple VPCs.
  • a VPC is set up in a region.
  • a communication gateway must be set up in each VPC to achieve interconnection between VPCs through the communication gateway.
  • the cloud management platform may include at least one computing device, such as a server, etc.
  • the cloud management platform may also be a device implemented using ASIC or PLD, etc.
  • the PLD may be implemented using CPLD, FPGA, GAL or any combination thereof.
  • the multiple computing devices included in the cloud management platform can be distributed in the same region or in different regions.
  • the multiple computing devices included in the cloud management platform can be distributed in the same AZ or in different AZs.
  • the multiple computing devices included in the cloud management platform can be distributed in the same VPC or in multiple VPCs.
  • the multiple computing devices can be any combination of computing devices such as servers, ASICs, PLDs, CPLDs, FPGAs, and GALs.
  • the present application also provides a computing device 600.
  • the computing device 600 includes: a bus 602, a processor 604, a memory 606, and a communication interface 608.
  • the processor 604, the memory 606, and the communication interface 608 communicate with each other via the bus 602.
  • the computing device 600 may be a server or a terminal device. It should be understood that the present application does not limit the number of processors and memories in the computing device 600.
  • the bus 602 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc.
  • the bus may be divided into an address bus, a data bus, a control bus, etc.
  • FIG. 11 is represented by only one line, but does not mean that there is only one bus or one type of bus.
  • the bus 602 may include a path for transmitting information between various components of the computing device 600 (e.g., the memory 606, the processor 604, and the communication interface 608).
  • Processor 604 may include any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).
  • CPU central processing unit
  • GPU graphics processing unit
  • MP microprocessor
  • DSP digital signal processor
  • the memory 606 may include a volatile memory, such as a random access memory (RAM).
  • the processor 604 may also include a non-volatile memory, such as a read-only memory (READ-ONLY MEMORY). ROM), flash memory, hard disk drive (HDD) or solid state drive (SSD).
  • ROM read-only memory
  • HDD hard disk drive
  • SSD solid state drive
  • the memory 606 stores executable program codes, and the processor 604 executes the executable program codes to respectively implement the functions of the aforementioned network status information detection module 11, the acceleration service management module 12, the service binding module 13, the bandwidth package purchase module 14, the bandwidth package configuration module 15, and the bandwidth package providing module 16, thereby implementing any one of the methods of claims 1 to 9. That is, the memory 606 stores instructions for executing any one of the methods of claims 1 to 9.
  • the memory 606 stores executable codes
  • the processor 604 executes the executable codes to implement the functions of the aforementioned cloud management platform, thereby implementing any method of claims 1 to 9. That is, the memory 606 stores instructions for executing any method of claims 1 to 9.
  • the communication interface 608 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computing device 600 and other devices or communication networks.
  • a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computing device 600 and other devices or communication networks.
  • the embodiment of the present application also provides a computing device cluster.
  • the computing device cluster includes at least one computing device.
  • the computing device can be a server, such as a central server, an edge server, or a local server in a local data center.
  • the computing device can also be a terminal device such as a desktop computer, a laptop computer, or a smart phone.
  • the computing device cluster includes at least one computing device 600.
  • the memory 606 in one or more computing devices 600 in the computing device cluster may store the same instructions for executing any one of the methods of claims 1 to 9.
  • the memory 606 of one or more computing devices 600 in the computing device cluster may also respectively store partial instructions for executing any one of the methods of claims 1 to 9.
  • a combination of one or more computing devices 600 may jointly execute instructions for executing any one of the methods of claims 1 to 9.
  • the memory 606 in different computing devices 600 in the computing device cluster can store different instructions, which are respectively used to execute part of the functions of the cloud management platform. That is, the instructions stored in the memory 606 in different computing devices 600 can implement the functions of one or more modules of the network status information detection module 11, the acceleration service management module 12, the service binding module 13, the bandwidth package purchase module 14, the bandwidth package configuration module 15, and the bandwidth package provision module 16.
  • one or more computing devices in a computing device cluster may be connected via a network.
  • the network may be a wide area network or a local area network, etc.
  • FIG. 13 shows a possible implementation. As shown in FIG. 13 , two computing devices 600A and 600B are connected via a network. Specifically, the network is connected via a communication interface in each computing device.
  • the memory 606 in the computing device 600A stores instructions for executing the functions of the bandwidth package purchase module 14, the bandwidth package configuration module 15, the bandwidth package provision module 16, and the cloud connection service configuration module 17.
  • the memory 606 in the computing device 600B stores instructions for executing the functions of the network status information detection module 11, the acceleration service management module 12, and the service binding module 13.
  • connection method between the computing device clusters shown in Figure 13 can be considered to be that any method of claims 1 to 9 provided in the present application needs to support communication between cross-regional virtual private clouds, so it is considered to entrust the functions implemented by the network status information detection module 11, the acceleration service management module 12, the service binding module 13 and the bandwidth package purchase module 14, the bandwidth package configuration module 15, the bandwidth package provision module 16, and the cloud connection service configuration module 17 to the computing device 600B for execution.
  • the functions of the computing device 600A shown in FIG13 may also be completed by multiple computing devices 600.
  • the functions of the computing device 600B may also be completed by multiple computing devices 600.
  • the embodiment of the present application also provides another computing device cluster.
  • the connection relationship between the computing devices in the computing device cluster can be similar to the connection mode of the computing device cluster described in Figures 12 and 13.
  • the difference is that the memory 606 in one or more computing devices 600 in the computing device cluster can store the same instructions for executing any one of the methods of claims 1 to 9.
  • the memory 606 of one or more computing devices 600 in the computing device cluster may also respectively store partial instructions for executing any one of the methods of claims 1 to 9.
  • a combination of one or more computing devices 600 may jointly execute instructions for executing any one of the methods of claims 1 to 9.
  • the memory 606 in different computing devices 600 in the computing device cluster may store different instructions for executing the functions of the cloud management platform. That is, the instructions stored in the memory 606 in different computing devices 600 may implement the functions of the cloud management platform.
  • the embodiment of the present application also provides a computer program product including instructions.
  • the computer program product may be a software or program product including instructions that can be run on a computing device or stored in any available medium.
  • the at least one computing device executes any one of the methods of claims 1 to 9.
  • the embodiment of the present application also provides a computer-readable storage medium.
  • the computer-readable storage medium can be any available medium that can be stored by a computing device or a data storage device such as a data center containing one or more available media.
  • the available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk).
  • the computer-readable storage medium includes instructions that instruct the computing device to execute any one of the methods of claims 1 to 9.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

本发明实施例提供一种实现跨区域的虚拟私有云之间通信的配置方法及相关装置，该配置方法包括：云管理平台提供带宽包配置接口，获取租户带宽包的第一配置信息，该信息用于确定与带宽包绑定的云连接服务及其流量加速需求；云管理平台基于第一配置信息检测第一通信通道的网络状态，并将携带有第一通信通道的网络状态的第一网络状态信息反馈至第一VPC中的云实例，该第一网络状态信息用于指示第一VPC中的云实例根据第一通信通道的网络状态调整经第一通信通道发送至第二VPC的流量的发包速率至与第一通信通道的网络状态匹配从而实现流量加速。通过以上方案，能够解决跨区域虚拟私有云之间因无法感知真实网络状态导致的通信效率较低的问题。

Description

跨区域的虚拟私有云之间通信的配置方法及相关装置 技术领域
本申请涉及云技术领域，特别涉及一种跨区域的虚拟私有云VPC之间通信的配置方法及相关装置。
背景技术
云计算作为近年来新兴的产业，获得了科研界和产业界的广泛关注。云计算在全世界范围的兴起，以其灵活、高效、低成本、节能的运作方式成为推动产业绿色发展的重要引擎和21世纪新的商业平台。随着云技术的发展，越来越多的应用在跨区域(Region)虚拟私有云(Virtual Private Cloud，VPC)上部署，存在提高跨区域虚拟私有云之间通信效率的诉求。
现有虚拟私有云跨区域通信技术主要通过固定的发送窗口发送数据包，并根据响应包的反馈时间间接获知跨VPC通道之间网络状态，进而根据间接获知的网络状态来调整发送窗口。这种方式需要使用固定的发送窗口以固定的发包速度发送数据包，并根据反馈的网络状态逐渐地增大发送窗口进行慢启动，从而会出现慢启动、网络拥塞，以及微突发出现时难以快速恢复等问题，导致现阶段跨区域虚拟私有云之间通信的效率较低。
发明内容
为解决现有技术的问题，本申请提供一种跨区域的虚拟私有云VPC之间通信的配置方法及相关装置，能够提高跨区域私有云VPC之间通信效率。
第一方面，本申请提供一种跨区域的虚拟私有云VPC之间通信的配置方法，该方法用于云管理平台，其中，云管理平台用于管理提供公有云服务的网络基础设施，网络基础设施包括设置在第一区域的第一VPC和设置在第二区域的第二VPC，该方法包括：云管理平台提供带宽包配置接口，带宽包配置接口用于获取租户输入的针对租户的带宽包的第一配置信息，其中第一配置信息用于确定与带宽包绑定的云连接服务以及云连接服务有流量优化需求，云连接服务用于在第一VPC和第二VPC建立通信通道，带宽包用于对第一VPC至第二VPC之间的第一通信通道的流量进行限速，云管理平台基于配置信息检测第一通信通道的第一网络状态信息，并将第一网络状态信息反馈至第一VPC中的云实例，以使得第一VPC中的云实例根据第一网络状态信息调整经第一通信通道发送至第二VPC的流量的发包速率至与网络状态匹配。
由于云管理平台可以基于租户的请求检测第一通信通道的网络状态信息并反馈至作为发送方的第一VPC中的云实例，第一VPC中的云实例根据该网络状态信息调整发包速率至与第一通信通道的网络状态匹配，因此第一VPC中的云实例在向第二VPC发送数据包时，无需进行任何关于发包速率的试探，可以直接将发包速率设置成与网络状态匹配，从而提高发包效率。根据第一方面的一种可能的实现方式，第一网络状态信息包括指示第一通信通道的网络状态正常的信息，则，第一网络状态信息用于指示第一VPC中的云实例与第二VPC中的云实例握手成功后，在不进行慢启动的前提下调整TCP报文发送窗口至最大值。
通过获取指示第一通信通道的网络状态正常的信息，第一VPC中的云实例无需试探性地调整发包速率，例如从1开始缓慢增加报文发送窗口的大小(即慢启动)，而浪费带宽，而是根据网络状态正常的信息直接调整报文发送窗口至最大值，因此可以避免慢启动，提高通信效率。
根据第一方面的一种可能的实现方式，第一网络状态信息包括指示第一通信通道的网络状态劣化的信息，则，第一网络状态信息用于指示第一VPC中的云实例调整TCP报文发送窗口变小。其中，指示第一通信通道的网络状态劣化的信息包括指示第一通信通道的网络时延增大的信息、指示第一通信通道的传输带宽减小的信息以及指示第一通信通道的丢包率增大的信息中的一者或任意组合。
通过获取指示第一通信通道网络状态劣化的信息，第一VPC中的云实例无需在网络劣化发生后仍通过收发包试探网络状态，而是能够在劣化发生时直接知悉并减小发送窗口，从而避免丢包带来更坏的影响。
根据第一方面的一种可能的实现方式，第一网络状态信息包括指示第一通信通道的网络状态正常的信息，则，第一通信通道的网络状态信息用于指示第一VPC中的云实例在发生丢包的情况下仍然保持TCP报文发送窗口不变。
通过获取指示第一通信通道网络状态正常的信息，第一VPC中的云实例无需在业务波动导致少量丢 包时产生过激的拥塞控制反应，迅速降低发包速率，造成带宽浪费，而是能够知悉网络没有发生真正的拥塞，从而保持报文发送窗口不变。
根据第一方面的一种可能的实现方式，带宽包还用于为第二VPC至第一VPC之间的第二通信通道提供带宽，其中，云管理平台基于第一配置信息检测第二通信通道的网络状态，并将携带有第二通信通道的网络状态的第二网络状态信息反馈至第二VPC中的云实例，其中，第二网络状态信息用于指示第二VPC中的云实例根据第二通信通道的网络状态调整经第二通信通道发送至第一VPC的流量的发包速率至与第二通信通道的网络状态匹配从而实现流量优化流量加速。
因此，云管理平台可进一步检测第二VPC至第一VPC之间的第二通信通道的第二网络状态，将第二网络状态信息反馈给第二VPC中的云实例，从而同时实现第二VPC至第一VPC之间的上行和下行的流量优化。
根据第一方面的一种可能的实现方式，第一VPC中的云实例为设置在第一VPC中的虚拟机、容器、裸金属服务器BMS以及专属主机中的任意一者。因此，VPC中的任何基于云管理平台管理的云实例均可以实现流量优化。
根据第一方面的一种可能的实现方式，云管理平台还提供带宽包购买接口，带宽包购买接口用于获取租户针对带宽包的支付信息；云管理平台根据支付信息向租户提供带宽包。
通过带宽包购买接口，云管理平台能够获取租户的支付信息从而向租户提供对应的带宽包，租户可在云管理平台基于需要将带宽包应用在云连接服务中。
根据第一方面的一种可能的实现方式，云管理平台还提供云连接服务配置接口，云连接服务配置接口用于获取租户输入的云连接服务的第二配置信息，第二配置信息包括第一VPC的标识、第二VPC的标识以及带宽包的标识；云管理平台根据第二配置信息将带宽包与云连接服务绑定。
通过云连接服务配置接口，云管理平台能够获取第一VPC、第二VPC和带宽包的标识，将带宽包与相应的云连接服务绑定，使得云连接服务连接的第一VPC和第二VPC可通过带宽包提供的带宽实现跨区域通信。
第二方面，本申请提供一种跨区域的虚拟私有云VPC之间通信的云管理平台，其中，云管理平台用于管理提供公有云服务的网络基础设施，网络基础设施包括设置在第一区域的第一VPC和设置在第二区域的第二VPC，云管理平台包括：带宽包配置模块，用于提供带宽包配置接口，带宽包配置接口用于获取租户输入的针对租户的带宽包的第一配置信息，其中第一配置信息用于确定与带宽包绑定的云连接服务以及云连接服务有流量加速需求，云连接服务用于连接第一VPC和第二VPC，带宽包用于为第一VPC至第二VPC之间的第一通信通道提供带宽；网络状态信息检测模块，用于基于配置信息检测第一通信通道的网络状态，并将携带有第一通信通道的网络状态的第一网络状态信息反馈至第一VPC中的云实例，其中，第一网络状态信息用于指示第一VPC中的云实例根据第一通信通道的网络状态调整经第一通信通道发送至第二VPC的流量的发包速率至与第一通信通道的网络状态匹配从而实现流量加速。
第二方面或第二方面任意一种实现方式是第一方面或第一方面任意一种实现方式对应的装置实现，第一方面或第一方面任意一种实现方式中的描述适用于第二方面或第二方面任意一种实现方式，在此不再赘述。
第三方面，本申请提供了一种计算设备集群，其中，包括至少一个计算设备，每个计算设备包括处理器和存储器；至少一个计算设备的处理器用于执行至少一个计算设备的存储器中存储的指令，以使得计算设备集群执行如第一方面的任意一种可能的方法。
第四方面，本申请提供了一种包含指令的计算机程序产品，其中，当指令被计算设备集群运行时，使得计算设备集群执行如第一方面的任意一种可能的方法。
第五方面，本身请提供了一种计算机可读存储介质，其中，包括计算机程序指令，当计算机程序指令由计算设备集群执行时，计算设备集群执行如第一方面的任意一种可能的方法。
附图说明
为了更清楚地说明本发明实施例技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本申请实施例提供的一种云服务在云骨干网上跨区域部署的结构示意图。
图2是TCP算法在慢启动、拥塞避免时的拥塞窗口变化曲线图。
图3是本申请实施例提供的一种加速流程示意图。
图4是本申请实施例提供的一种配置界面示意图。
图5是本申请实施例提供的又一种加速流程示意图。
图6是本申请实施例提供的又一种加速流程示意图，其报文发送方向与图5相反。
图7是本申请实施例提供的一种避免慢启动的流程示意图。
图8是本申请实施例提供的一种感知劣化避免丢包的流程示意图。
图9是本申请实施例提供的一种避免微突发的流程示意图。
图10是本申请实施例提供的一种云管理平台的结构示意图。
图11是本申请实施例提供的一种云管理平台的计算设备集群结构示意图。
图12是本申请实施例提供的另一种云管理平台的计算设备集群结构示意图。
图13是本申请实施例提供的另一种云管理平台的计算设备集群结构示意图。
具体实施方式
下面结合附图对本发明实施例中的技术方案进行清楚、完整的描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
在本文中提及“实施例”意味着，结合实施例描述的特定特征、结构或特性可以包含在本申请的至少一个实施例中。在说明书中的各个位置出现该短语并不一定均是指相同的实施例，也不是与其它实施例互斥的独立的或备选的实施例。本领域技术人员显式地和隐式地理解的是，本文所描述的实施例可以与其它实施例相结合。
首先，结合附图对本申请中所涉及的部分用语和相关技术进行解释说明，以便于本领域技术人员理解。
虚拟私有云(Virtual Private Cloud，VPC)：一个公共云计算资源的动态配置池，需要使用加密协议、隧道协议和其它安全程序，在企业和云服务提供商之间传输数据。VPC为弹性云服务器构建隔离的、用户自主配置和管理的虚拟网络环境，提升用户云中资源的安全性，简化用户的网络部署，可以在VPC中定义安全组、虚拟专用网(virtual private network，VPN)、IP地址段、带宽等网络特性，租户可以通过VPC方便的管理、配置内部网络，进行安全快捷的网络变更。
云连接(Cloud Connect，CC)服务：能够提供快速构建跨区域VPC及云上多VPC与云下多数据中心之间的高速、优质、稳定的网络，帮助用户打造一张具有企业级规模和通信能力的全球云上网络。云连接服务可以加载需要实现互通的不同区域的网络实例，最后通过配置需要互通的网络实例之间的域间带宽，就可以提供全球网络互通服务。云连接服务一般基于支撑区域互通的带宽包采取阶梯定价方式进行收费。
云骨干网(Cloud Backbone Network)：连接云厂商的分布在不同区域的数据中心的高速网络，让用户分钟级构建多地域全球网络，并和混合云连成一体。
云管理平台：云管理平台用于管理云厂商设置在不同区域的多个云数据中心，云管理平台可提供与公有云服务相关的接口，例如配置页面或应用程序接口(Application Program Interface，API)以供租户远程访问公有云服务，租户可通过预先注册的账号密码登录云管理平台，并在登录成功之后，选择并购买在预定区域的云数据中心提供的公有云服务，公有云服务例如对象存储服务、虚拟机服务、容器服务或其他已知的公有云服务。
区域(Region)：从地理位置和网络时延维度划分，同一个Region的多个数据中心内共享弹性计算、块存储、对象存储、VPC网络、弹性公网IP、镜像等公共服务。
租户：用于管理云服务虚拟机的顶层对象，通过租户名和租户ID进行标识。云上合同、资金账户、订单、云资源都归对应租户管理。
往返时延(Round-Trip Time，RTT)：在计算机网络中，表示从发送端发送数据开始，到发送端收到来自接收端的确认这个过程中经历的时延。它由三个部分决定：即链路的传播时间、末端系统的处理时间以及路由器的缓存中的排队和处理时间。其中，前面两个部分的值作为一个TCP连接相对固定，路由器的缓存中的排队和处理时间会随着整个网络拥塞程度的变化而变化。所以RTT的变化在一定程度上反映了网络拥塞程度的变化。
慢启动：主机开发发送数据报时，如果立即将大量的数据注入到网络中，可能会出现网络的拥塞。慢启动算法就是在主机刚开始发送数据报的时候先探测一下网络的状况，如果网络状况良好，发送方每发送一次文段都能正确的接受确认报文段。那么就从小到大的增加拥塞窗口的大小，即增加发送窗口的大小。
微突发：端口在毫秒级别的短时间内收到非常多的突发数据，典型的微突发的持续时间通常在1～100 毫秒之间，以至于瞬时突发速率达到平均速率的数十倍、数百倍，甚至超过端口带宽的现象。传统的传输控制协议(Transmission Control Protocol，TCP)中，当吞吐量达到上限后，TCP滑动窗口减半，速率迅速下降，导致会话流量呈锯齿状，具有突发性。TCP总是期望把发送窗口中的数据尽快发送完，所以会在等待TCP的报文到达确认(ACK)到来后，通过滑动窗口机制再继续发送数据，如此循环，使得发包速率不平缓，突发性强。
云实例：云实例即云服务中的实例。在本发明实施例中，云实例为设置在VPC中的虚拟机、容器、裸金属服务器BMS以及专属主机中的任意一者。
请参见图1，图1是一种涉及VPC跨区域通信的公有云系统结构示意图。如图1所示，公有云系统包括云管理平台10和云数据中心集群，云数据中心集群包括多个子集群，每个子集群包括多个云数据中心，每个子集群设置在不同的区域，云数据中心中可设置有VPC，例如，如图1所示，云数据中心1中设置有VPC1和VPC2，租户40可以通过客户端30经由互联网20访问云管理平台10，并通过云管理平台10管理云数据中心中的VPC，例如，管理云数据中心1中的VPC1和/或云数据中心3中的VPC4，租户40可在云管理平台10为部署在不同区域的虚拟私有云购买用于实现跨区域通信的云连接服务，同时，租户40还可在云管理平台10中配置云连接服务所需带宽包。
如图1所示，该系统还包括至少两个区域，图中示出了区域1、区域2、区域3和区域4，每个区域包括至少一个VPC，某些VPC中包括至少一个云实例，位于不同区域的VPC需要进行跨区域通信时，便通过云连接网关在云骨干网上建立通信通道，例如，在图1中，VPC1通过网关连接云骨干网上的边缘接入点1，VPC4通过网关连接云骨干网上的边缘接入点2，由此VPC1与VPC4在云骨干网上建立连接，图中示出了位于区域1上的VPC1与位于区域2上的VPC4建立了由VPC1向VPC4传送报文的上行通信通道1和由VPC4向VPC1传送报文的下行通信通道2。
图2是TCP算法在慢启动、拥塞避免时的拥塞窗口变化曲线图。在跨区域私有云通信的现有场景中，需要云实例通过TCP拥塞控制算法感知网络状态以调整报文收发速率，简而言之，TCP算法无法直接得知网络真实状态，而是需要云实例进行收发包试探网络状态。
如图2所示，两个虚拟私有云建立连接时，TCP算法无法确定网络是否存在拥塞，为避免网络存在拥塞导致报文大量堆积，拥塞窗口只有在发送方收到新的ACK时才会缓慢增加。在阶段1，发送方的拥塞窗口首先会从1开始倍增，呈现指数增长，直到大到一定程度时，在阶段2，由指数增长变为线性增长，最终达到最佳报文收发窗口。在节点1和节点3发生丢包时，TCP协议会认为发生了网络拥塞，从而进入阶段3把拥塞窗口调小，在超时重传时甚至会将拥塞窗口重置为0，重新进入慢启动阶段。
可以看出，在图2所示的利用TCP协议控制报文收发的场景中，云实例并不能直接及时得知网络状态，从而在调整拥塞窗口时必然存在延迟甚至误判。具体来说，TCP在发送接收双方建立连接时采用慢启动策略是为了避免在网络拥塞时仍然大量收发报文造成丢包，从而保证通信的可靠性。但是网络拥塞并非常有现象，在网络状态正常时，若仍采用慢启动的方式，会使得通信效率降低。同样的负面效果也发生在微突发导致的TCP协议对拥塞状况的误判中。
为了解决上述问题，本发明实施例提供一种跨区域的虚拟私有云VPC之间通信的配置方法及相关装置。该方法与装置在图1所示的公有云系统的基础上通过云管理平台检测跨区域云实例之间通信通道的网络状态并反馈给云实例，从而指示云实例调整报文收发速率，实现流量加速，提高跨区域私有云VPC之间通信效率。
首先请参见图3，图3为本发明实施例提供的一种跨区域通信加速流程示意图，该流程包括但不限于以下步骤：
步骤S101：租户配置带宽包。
具体地，租户通过客户端在云管理平台购买并配置带宽包时，通过云管理平台提供的带宽包购买接口进行支付，同时，通过云管理平台提供的带宽包配置接口进行配置。
步骤S102：云管理平台创建云连接。
云管理平台创建云连接。示例性地，区域1中的云实例1与区域2中的云实例3通过网关、边缘接入点1和边缘接入点2建立连接。
具体可结合图4，图4是本发明实施例提供的一种配置界面示意图，如图4所示，该配置信息包括但不限于计费模式、互通区域、带宽、加速服务、实例等。
步骤S103：云管理平台为VPC之间的通信通道分配带宽包，配置云实例加速服务。
具体地，云管理平台根据租户提供的购买与配置信息，确定要配置云连接服务的虚拟私有云之间的通 信通道和云实例，之后为该通信通道分配带宽包，并向虚拟私有云中的云实例配置加速服务。
举例而言，云管理平台在云实例中设置用户态的加速服务代理。
步骤S104：注册加速服务。
具体地，前述步骤对应的云实例启用加速服务，并通过云实例中设置好的用户态的加速服务代理向云管理平台注册。
步骤S105：获取并通知通信通道的网络状态。
具体地，云管理平台接受云实例的注册后，开始获取该跨区域通信通道1的网络状态，并通知给VPC1中的云实例1。网络状态可由网络时延、传输带宽和丢包率中的一者或任意组合反映。
步骤S106：依据网络状态调整报文发送窗口。
具体地，云实例1根据云管理平台提供的网络状态信息调整TCP报文发送窗口。
步骤S107：发送报文。
具体地，位于VPC1的云实例1通过跨区域通信通道向位于VPC4的云实例3发送报文。
上述流程可结合图5、图6，图5、图6为本发明实施例提供的一种跨区域通信加速流程示意图，分别示出了由云实例1向云实例3通信加速和由云实例3向云实例1通信加速的流程。如图5所示，该跨区域通信加速服务的运行包括但不限于以下步骤：
步骤S201：云管理平台10检测云实例1向云实例3发送报文所经的通信通道1的网络状态信息10。
步骤S202：云管理平台向云实例1反馈网络状态信息10。
步骤S203：云实例1调整由其经过通信通道1发往云实例3的TCP报文发包速率。具体地，在网络状态信息10显示网络状态正常时，调整报文发包速率至最大，在网络状态信息10显示网络状态劣化时，减小报文发包速率。
图6调转了图5的通信方向，由区域1的云实例1向区域2的云实例3发送报文转换为由区域2的云实例3向区域1的云实例1发送报文，即，图5示出了位于区域1上的VPC1向位于区域2上的VPC4通过上行通信通道1传送报文的场景，图6示出了由位于区域2上的VPC4向位于区域1上的VPC1通过下行通信通道2传送报文的场景。具体可以参阅S201-S203中的描述，此处不再赘述。
以下请参见图7至图9，图7至图9对上述报文加速服务做出具体说明，示出了云管理平台和云实例运行加速服务时所需的具体模块以及具体加速过程，以描述报文加速服务在不同场景下的实现方式。
如图7至图9所示，在加速服务开启后的加速功能模块上，云管理平台10包括网络状态信息检测模块11和加速服务管理模块12，云实例1包括加速服务代理模块51和报文加速模块52。租户在配置好跨区域加速带宽包后，云实例可启动加速服务代理51和报文加速模块52，具体地，加速服务代理51可设置在用户态，报文加速模块52可设置在内核态。
首先请参见图7，图7是本发明实施例中避免慢启动的流程示意图。具体应用在跨区域VPC连接的场景。云实例1中的加速服务代理51向云管理平台中的加速服务管理12注册加速服务，获取网络状态信息。加速服务代理51将网络状态信息反馈给报文加速模块52，报文加速模块52根据基于网络状态信息，调整报文发送速率。云管理平台中的加速服务管理12获取加速服务代理51注册的信息，并通告网络状态信息。网络状态信息由网络状态信息检测模块检测。云实例1中的报文加速模块52向加速服务代理51发送连接启动通知，加速服务代理51向云管理平台中的加速服务管理12发送连接启动通知，加速服务管理12向网络状态信息检测模块11发送信息请求获取网络状态信息，网络状态信息检测模块11检测网络状态，得到网络状态信息，并经由加速服务管理12、加速服务代理51，最终发送给报文加速模块52。报文加速模块52获得网络状态信息后，根据该信息将其报文发送窗口调至最优，从而避免在连接启动时，根据TCP协议收发报文缓慢扩大拥塞窗口带来的慢启动效果。
图8是本发明实施例中感知网络状态劣化避免丢包的流程示意图，具体应用在跨区域私有云通信时出现网络状态劣化的场景。这里的网络状态劣化包括网络时延增大、传输带宽减小、丢包率增大中的一种或几种。加速服务管理模块12从网络状态信息检测模块11处要求获取网络状态信息，网络状态信息检测模块11检测到网络状态劣化，并将该信息发送给加速服务管理模块12，加速服务管理模块12再发送给云实例中的加速服务代理51，报文加速模块52接收到网络状态劣化信息后，得知网络发生劣化，便根据该信息减小报文发送窗口，从而避免在网络发生劣化时，TCP报文发送窗口调整不及时而丢包带来更坏影响。
图9是本发明实施例中避免微突发的流程示意图，具体应用在跨区域私有云通信时出现微突发的场景。在租户的跨区域私有云通信发生丢包后，云实例中的报文加速模块52向加速服务代理模块51发送丢包通知，加速服务代理模块51将丢包通知上报给云管理平台中的加速服务管理模块12。加速服务管理模块12 得知云实例在跨区域加速通信发生丢包时，向网络状态信息检测模块11发送要求获取网络状态信息的请求。在微突发的场景下，通信通道并没有真正发生拥塞，网络状态信息检测模块11检测到网络状态正常，并将网络状态正常的信息发送给加速服务管理模块12。加速服务管理模块12将网络状态正常的信息发送给云实例中的加速服务代理模块51。云实例中的报文加速模块52获取网络状态正常的信息后，得知网络状态正常，并没有发生拥塞，便根据该信息保持拥塞窗口不变，从而避免在微突发发生时，TCP协议根据少量丢包产生过激反应，过度减小报文发送窗口，造成网络带宽浪费，传输效率降低。
上述实施例揭示了通过控制TCP报文的发送窗口来实现跨区域私有云流量加速的方法和装置，值得注意的是，本发明其他实施例中，云实例也可以通过控制流控制传输协议(Stream Control Transmission Protocol，SCTP)报文或其他通过试探方式调整发包速率的报文的发送窗口来实现上述功能,本发明实施例对报文的类型不作限定，本领域技术人员可根据自身需要将本发明思想应用在不同类型的报文中，从而实现报文加速。
请参见图10，图10示出基于本发明实施例的云管理平台功能模块示意图，包括网络状态信息检测模块11、加速服务管理模块12、服务绑定模块13、带宽包购买模块14、带宽包配置模块15、带宽包提供模块16、云连接服务配置模块17，具体可结合图3，网络状态信息检测模块11用于执行S105获取通信通道状态的步骤，服务绑定模块13用于执行S102创建云连接的步骤，加速服务管理模块12用于执行S103为云实例配置加速服务的步骤，带宽包购买模块14用于执行S101租户购买带宽包的步骤，带宽包配置模块15用于执行S101租户配置带宽包的步骤，带宽包提供模块16用于执行S103为VPC之间的通信通道分配带宽包的步骤，云连接服务配置模块17用于执行S103为VPC之间的通信通道分配带宽包，配置云实例加速服务的步骤。
云管理平台可以通过软件实现，或者可以通过硬件实现。示例性的，接下来介绍云管理平台的实现方式。
模块作为软件功能单元的一种举例，云管理平台可以包括运行在计算实例上的代码。其中，计算实例可以是物理主机(计算设备)、虚拟机、容器等计算设备中的至少一种。进一步地，上述计算设备可以是一台或者多台。例如，云管理平台可以包括运行在多个主机/虚拟机/容器上的代码。需要说明的是，用于运行该应用程序的多个主机/虚拟机/容器可以分布在相同的region中，也可以分布在不同的region中。用于运行该代码的多个主机/虚拟机/容器可以分布在相同的AZ中，也可以分布在不同的AZ中，每个AZ包括一个数据中心或多个地理位置相近的数据中心。其中，通常一个region可以包括多个AZ。
同样，用于运行该代码的多个主机/虚拟机/容器可以分布在同一个VPC中，也可以分布在多个VPC中。其中，通常一个VPC设置在一个region内。同一region内两个VPC之间，以及不同region的VPC之间跨区通信需在每个VPC内设置通信网关，经通信网关实现VPC之间的互连。
模块作为硬件功能单元的一种举例，云管理平台可以包括至少一个计算设备，如服务器等。或者，云管理平台也可以是利用ASIC实现、或PLD实现的设备等。其中，上述PLD可以是CPLD、FPGA、GAL或其任意组合实现。
云管理平台包括的多个计算设备可以分布在相同的region中，也可以分布在不同的region中。云管理平台包括的多个计算设备可以分布在相同的AZ中，也可以分布在不同的AZ中。同样，云管理平台包括的多个计算设备可以分布在同一个VPC中，也可以分布在多个VPC中。其中，所述多个计算设备可以是服务器、ASIC、PLD、CPLD、FPGA和GAL等计算设备的任意组合。
本申请还提供一种计算设备600。如图11所示，计算设备600包括：总线602、处理器604、存储器606和通信接口608。处理器604、存储器606和通信接口608之间通过总线602通信。计算设备600可以是服务器或终端设备。应理解，本申请不限定计算设备600中的处理器、存储器的个数。
总线602可以是外设部件互连标准(peripheral component interconnect，PCI)总线或扩展工业标准结构(extended industry standard architecture，EISA)总线等。总线可以分为地址总线、数据总线、控制总线等。为便于表示，图11中仅用一条线表示，但并不表示仅有一根总线或一种类型的总线。总线602可包括在计算设备600各个部件(例如，存储器606、处理器604、通信接口608)之间传送信息的通路。
处理器604可以包括中央处理器(central processing unit，CPU)、图形处理器(graphics processing unit，GPU)、微处理器(micro processor，MP)或者数字信号处理器(digital signal processor，DSP)等处理器中的任意一种或多种。
存储器606可以包括易失性存储器(volatile memory)，例如随机存取存储器(random access memory，RAM)。处理器604还可以包括非易失性存储器(non-volatile memory)，例如只读存储器(read-only memory， ROM)，快闪存储器，机械硬盘(hard disk drive，HDD)或固态硬盘(solid state drive，SSD)。
存储器606中存储有可执行的程序代码，处理器604执行该可执行的程序代码以分别实现前述网络状态信息检测模块11、加速服务管理模块12、服务绑定模块13、带宽包购买模块14、带宽包配置模块15、带宽包提供模块16的功能，从而实现权利要求1至9的任一项方法。也即，存储器606上存有用于执行权利要求1至9的任一项方法的指令。
或者，存储器606中存储有可执行的代码，处理器604执行该可执行的代码以实现前述云管理平台的功能，从而实现权利要求1至9的任一项方法。也即，存储器606上存有用于执行权利要求1至9任一项方法的指令。
通信接口608使用例如但不限于网络接口卡、收发器一类的收发模块，来实现计算设备600与其他设备或通信网络之间的通信。
本申请实施例还提供了一种计算设备集群。该计算设备集群包括至少一台计算设备。该计算设备可以是服务器，例如是中心服务器、边缘服务器，或者是本地数据中心中的本地服务器。在一些实施例中，计算设备也可以是台式机、笔记本电脑或者智能手机等终端设备。
如图12所示，所述计算设备集群包括至少一个计算设备600。计算设备集群中的一个或多个计算设备600中的存储器606中可以存有相同的用于执行权利要求1至9任一项方法的指令。
在一些可能的实现方式中，该计算设备集群中的一个或多个计算设备600的存储器606中也可以分别存有用于执行权利要求1至9任一项方法的部分指令。换言之，一个或多个计算设备600的组合可以共同执行用于执行权利要求1至9任一项方法的指令。
需要说明的是，计算设备集群中的不同的计算设备600中的存储器606可以存储不同的指令，分别用于执行云管理平台的部分功能。也即，不同的计算设备600中的存储器606存储的指令可以实现网络状态信息检测模块11、加速服务管理模块12、服务绑定模块13、带宽包购买模块14、带宽包配置模块15、带宽包提供模块16中的一个或多个模块的功能。
在一些可能的实现方式中，计算设备集群中的一个或多个计算设备可以通过网络连接。其中，所述网络可以是广域网或局域网等等。图13示出了一种可能的实现方式。如图13所示，两个计算设备600A和600B之间通过网络进行连接。具体地，通过各个计算设备中的通信接口与所述网络进行连接。在这一类可能的实现方式中，计算设备600A中的存储器606中存有执行带宽包购买模块14、带宽包配置模块15、带宽包提供模块16、云连接服务配置模块17的功能的指令。同时，计算设备600B中的存储器606中存有执行网络状态信息检测模块11、加速服务管理模块12、服务绑定模块13的功能的指令。
图13所示的计算设备集群之间的连接方式可以是考虑到本申请提供的权利要求1至9任一项方法需要支持跨区域虚拟私有云之间的通信，因此考虑将网络状态信息检测模块11、加速服务管理模块12、服务绑定模块13和带宽包购买模块14、带宽包配置模块15、带宽包提供模块16、云连接服务配置模块17实现的功能交由计算设备600B执行。
应理解，图13中示出的计算设备600A的功能也可以由多个计算设备600完成。同样，计算设备600B的功能也可以由多个计算设备600完成。
本申请实施例还提供了另一种计算设备集群。该计算设备集群中各计算设备之间的连接关系可以类似的参考图12和图13所述计算设备集群的连接方式。不同的是，该计算设备集群中的一个或多个计算设备600中的存储器606中可以存有相同的用于执行权利要求1至9任一项方法的指令。
在一些可能的实现方式中，该计算设备集群中的一个或多个计算设备600的存储器606中也可以分别存有用于执行权利要求1至9任一项方法的部分指令。换言之，一个或多个计算设备600的组合可以共同执行用于执行权利要求1至9任一项方法的指令。
需要说明的是，计算设备集群中的不同的计算设备600中的存储器606可以存储不同的指令，用于执行云管理平台的功能。也即，不同的计算设备600中的存储器606存储的指令可以实现云管理平台的功能。
本申请实施例还提供了一种包含指令的计算机程序产品。所述计算机程序产品可以是包含指令的，能够运行在计算设备上或被储存在任何可用介质中的软件或程序产品。当所述计算机程序产品在至少一个计算设备上运行时，使得至少一个计算设备执行权利要求1至9任一项方法。
本申请实施例还提供了一种计算机可读存储介质。所述计算机可读存储介质可以是计算设备能够存储的任何可用介质或者是包含一个或多个可用介质的数据中心等数据存储设备。所述可用介质可以是磁性介质，(例如，软盘、硬盘、磁带)、光介质(例如，DVD)、或者半导体介质(例如固态硬盘)等。该计算机可读存储介质包括指令，所述指令指示计算设备执行权利要求1至9任一项方法。
最后应说明的是：以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的保护范围。

Claims (21)

  1. 一种实现跨区域的虚拟私有云VPC之间通信的配置方法，其特征在于，所述方法用于云管理平台，所述云管理平台用于管理提供公有云服务的网络基础设施，所述网络基础设施包括设置在第一区域的第一VPC和设置在第二区域的第二VPC，所述方法包括：
    所述云管理平台从带宽包配置接口获取租户输入的针对所述租户的带宽包的第一配置信息，其中所述第一配置信息用于确定与所述带宽包绑定的云连接服务以及所述云连接服务有流量加速的需求，所述云连接服务用于连接所述第一VPC和所述第二VPC，所述带宽包用于为所述第一VPC至所述第二VPC之间的第一通信通道提供带宽，所述带宽包配置接口设置于所述云管理平台；
    所述云管理平台基于所述第一配置信息检测所述第一通信通道的网络状态，并将携带有所述第一通信通道的网络状态的第一网络状态信息反馈至所述第一VPC中的云实例，其中，第一网络状态信息用于指示所述第一VPC中的云实例根据所述第一通信通道的网络状态调整经所述第一通信通道发送至所述第二VPC的流量的发包速率至与所述第一通信通道的网络状态匹配从而实现流量加速。
  2. 根据权利要求1所述的方法，其特征在于，所述第一网络状态信息包括指示所述第一通信通道的网络状态正常的信息，则，所述第一网络状态信息用于指示所述第一VPC中的云实例与所述第二VPC中的云实例握手成功后，在不进行慢启动的前提下调整TCP报文发送窗口至最大值。
  3. 根据权利要求1所述的方法，其特征在于，所述第一网络状态信息包括指示所述第一通信通道的网络状态劣化的信息，则，所述第一网络状态信息用于指示所述第一VPC中的云实例调整TCP报文发送窗口变小。
  4. 根据权利要求3所述的方法，其特征在于，所述指示所述第一通信通道的网络状态劣化的信息包括指示所述第一通信通道的网络时延增大的信息、指示所述第一通信通道的传输带宽减小的信息以及指示所述第一通信通道的丢包率增大的信息中的一者或任意组合。
  5. 根据权利要求1所述的方法，其特征在于，所述第一网络状态信息包括指示所述第一通信通道的网络状态正常的信息，则，所述第一通信通道的网络状态信息用于指示所述第一VPC中的云实例在发生丢包的情况下仍然保持TCP报文发送窗口不变。
  6. 根据权利要求1至5任一项所述的方法，其特征在于，所述带宽包还用于为所述第二VPC至所述第一VPC之间的第二通信通道提供带宽，所述方法还包括：
    所述云管理平台基于所述第一配置信息检测所述第二通信通道的网络状态，并将携带有所述第二通信通道的网络状态的第二网络状态信息反馈至所述第二VPC中的云实例，其中，第二网络状态信息用于指示所述第二VPC中的云实例根据所述第二通信通道的网络状态调整经所述第二通信通道发送至所述第一VPC的流量的发包速率至与所述第二通信通道的网络状态匹配从而实现流量加速。
  7. 根据权利要求1至6任一项所述的方法，其特征在于，所述第一VPC中的云实例为设置在所述第一VPC中的虚拟机、容器、裸金属服务器BMS以及专属主机中的任意一者。
  8. 根据权利要求1至7任一项所述的方法，其特征在于，所述方法还包括：
    所述云管理平台还提供带宽包购买接口，所述带宽包购买接口用于获取所述租户针对所述带宽包的支付信息；
    所述云管理平台根据所述支付信息向所述租户提供所述带宽包。
  9. 根据权利要求8所述的方法，其特征在于，所述方法还包括：
    所述云管理平台还提供云连接服务配置接口，所述云连接服务配置接口用于获取所述租户输入的所述云连接服务的第二配置信息，所述第二配置信息包括所述第一VPC的标识、所述第二VPC的标识以及所述带宽包的标识；
    所述云管理平台根据所述第二配置信息将所述带宽包与所述云连接服务绑定。
  10. 一种云管理平台，其特征在于，所述云管理平台用于管理提供公有云服务的网络基础设施，所述网络基础设施包括设置在第一区域的第一VPC和设置在第二区域的第二VPC，所述云管理平台包括：
    带宽包配置模块，从带宽包配置接口获取租户输入的针对所述租户的带宽包的第一配置信息，其中所述第一配置信息用于确定与所述带宽包绑定的云连接服务以及所述云连接服务有流量加速需求，所述云连接服务用于连接所述第一VPC和所述第二VPC，所述带宽包用于为所述第一VPC至所述第二VPC之间的第一通信通道提供带宽；
    网络状态信息检测模块，用于基于所述配置信息检测所述第一通信通道的网络状态，并将携带有所述 第一通信通道的网络状态的所述第一网络状态信息反馈至所述第一VPC中的云实例，其中，第一网络状态信息用于指示所述第一VPC中的云实例根据所述第一通信通道的网络状态调整经所述第一通信通道发送至所述第二VPC的流量的发包速率至与所述第一通信通道的网络状态匹配从而实现流量加速。
  11. 根据权利要求10所述的云管理平台，其特征在于，所述第一网络状态信息包括指示所述第一通信通道的网络状态正常的信息，则，所述第一网络状态信息用于指示所述第一VPC中的云实例与所述第二VPC中的云实例握手成功后，在不进行慢启动的前提下调整TCP报文发送窗口至最大值。
  12. 根据权利要求10所述的云管理平台，其特征在于，所述第一网络状态信息包括指示所述第一通信通道的网络状态劣化的信息，则，所述第一网络状态信息用于指示所述第一VPC中的云实例调整TCP报文发送窗口变小。
  13. 根据权利要求12所述的云管理平台，其特征在于，所述指示所述第一通信通道的网络状态劣化的信息包括指示所述第一通信通道的网络时延增大的信息、指示所述第一通信通道的传输带宽减小的信息以及指示所述第一通信通道的丢包率增大的信息中的一者或任意组合。
  14. 根据权利要求10所述的云管理平台，其特征在于，所述第一网络状态信息包括指示所述第一通信通道的网络状态正常的信息，则，所述第一网络状态信息用于指示所述第一VPC中的云实例在发生丢包的情况下仍然保持TCP报文发送窗口不变。
  15. 根据权利要求10至14任一项所述的云管理平台，其特征在于，所述带宽包还用于为所述第二VPC至所述第一VPC之间的第二通信通道提供带宽，其中：
    所述网络状态信息检测模块，还用于基于所述第一配置信息检测所述第二通信通道的网络状态，并将携带有所述第二通信通道的网络状态的第二网络状态信息反馈至所述第二VPC中的云实例，其中，第二网络状态信息用于指示所述第二VPC中的云实例根据所述第二通信通道的网络状态调整经所述第二通信通道发送至所述第一VPC的流量的发包速率至与所述第二通信通道的网络状态匹配从而实现流量加速。
  16. 根据权利要求10至15任一项所述的云管理平台，其特征在于，所述第一VPC中的云实例为设置在所述第一VPC中的虚拟机、容器、裸金属服务器BMS以及专属主机中的任意一者。
  17. 根据权利要求10至16任一项所述的云管理平台，其特征在于，所述云管理平台还包括：
    带宽包购买模块，用于提供带宽包购买接口，所述带宽包购买接口用于获取所述租户输入的针对所述带宽包的支付信息；
    带宽包提供模块，用于根据所述支付信息向所述租户提供所述带宽包。
  18. 根据权利要求17所述的云管理平台，其特征在于，所述云管理平台还包括：
    云连接服务配置模块，用于提供云连接服务配置接口，所述云连接服务配置接口用于获取所述租户输入的所述云连接服务的第二配置信息，所述第二配置信息包括所述第一VPC的标识、所述第二VPC的标识、以及所述带宽包的标识；
    服务绑定模块，用于根据所述第二配置信息将所述带宽包与所述云连接服务绑定。
  19. 一种计算设备集群，其特征在于，包括至少一个计算设备，每个计算设备包括处理器和存储器；
    所述至少一个计算设备的处理器用于执行所述至少一个计算设备的存储器中存储的指令，以使得所述计算设备集群执行如权利要求1至9任一项所述的方法。
  20. 一种包含指令的计算机程序产品，其特征在于，当所述指令被计算设备集群运行时，使得所述计算设备集群执行如权利要求的1至9任一项所述的方法。
  21. 一种计算机可读存储介质，其特征在于，包括计算机程序指令，当所述计算机程序指令由计算设备集群执行时，所述计算设备集群执行如1至9任一项所述的方法。
PCT/CN2023/129012 2022-11-16 2023-11-01 跨区域的虚拟私有云之间通信的配置方法及相关装置 WO2024104168A1 (zh)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
CN202211431982.0 2022-11-16
CN202211431982 2022-11-16
CN202211532345.2 2022-12-01
CN202211532345.2A CN118101649A (zh) 2022-11-16 2022-12-01 跨区域的虚拟私有云之间通信的配置方法及相关装置

Publications (1)

Publication Number Publication Date
WO2024104168A1 true WO2024104168A1 (zh) 2024-05-23

Family

ID=91083767

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/129012 WO2024104168A1 (zh) 2022-11-16 2023-11-01 跨区域的虚拟私有云之间通信的配置方法及相关装置

Country Status (1)

Country Link
WO (1) WO2024104168A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110242974A1 (en) * 2010-04-02 2011-10-06 Cortina Systems, Inc. Network transport system with hybrid dynamic bandwidth allocation mechanism and method of operation thereof
CN111030912A (zh) * 2018-10-09 2020-04-17 华为技术有限公司 虚拟私有云vpc之间互通的方法
CN112688847A (zh) * 2020-08-17 2021-04-20 紫光云技术有限公司 一种云网络环境下vpc对等连接的实现方法
CN114402574A (zh) * 2019-09-27 2022-04-26 甲骨文国际公司 用于提供多租户软件定义的广域网(sd-wan)节点的方法、系统和计算机可读介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110242974A1 (en) * 2010-04-02 2011-10-06 Cortina Systems, Inc. Network transport system with hybrid dynamic bandwidth allocation mechanism and method of operation thereof
CN111030912A (zh) * 2018-10-09 2020-04-17 华为技术有限公司 虚拟私有云vpc之间互通的方法
CN114402574A (zh) * 2019-09-27 2022-04-26 甲骨文国际公司 用于提供多租户软件定义的广域网(sd-wan)节点的方法、系统和计算机可读介质
CN112688847A (zh) * 2020-08-17 2021-04-20 紫光云技术有限公司 一种云网络环境下vpc对等连接的实现方法

Similar Documents

Publication Publication Date Title
US8014312B2 (en) Method and system for handling connection setup in a network
US10116574B2 (en) System and method for improving TCP performance in virtualized environments
CN110313163B (zh) 分布式计算系统中的负载平衡
CN108199925B (zh) 一种数据发送方法、接收方法及装置
US9584418B2 (en) Quantized congestion notification for computing environments
US8699343B2 (en) Adaptive rate control based on overload signals
EP1859594B1 (en) Server side tftp flow control
US10461986B2 (en) Data transmission method, apparatus, and system
EP3694160A1 (en) Date transmission method, apparatus and device
US9749354B1 (en) Establishing and transferring connections
WO2015106453A1 (zh) 处理业务的方法和网络设备
WO2015149486A1 (zh) 页面推送方法、装置、服务器和集中式网络管理控制器
CN107995233B (zh) 建立连接的方法及相应的设备
KR20200021417A (ko) 네트워크 서비스 교환 시스템 및 그를 이용하는 방법
WO2024104168A1 (zh) 跨区域的虚拟私有云之间通信的配置方法及相关装置
US20130060960A1 (en) Optimizing software applications in a network
US7966401B2 (en) Method and apparatus for containing a denial of service attack using hardware resources on a network interface card
CN118101649A (zh) 跨区域的虚拟私有云之间通信的配置方法及相关装置
CN117813595A (zh) 用于远程直接存储器访问的设备和方法
US20200287966A1 (en) Connecting an initiator and a target based on the target including an identity key value pair and a target characteristic key value pair
CN111769910A (zh) 一种数据传输方法及装置
KR101609922B1 (ko) 피어-투-피어 기반 데이터 전송 장치 및 방법
WO2024078050A1 (zh) 进行数据传输的方法和装置
WO2024027160A1 (zh) 一种应用部署方法、系统及设备
CN111049754B (zh) 数据通信方法、装置、设备和计算机可读存储介质