技术领域technical field
本发明涉及时延确定技术，尤其涉及一种虚机迁移时的邻节点时延检测方法及系统。The invention relates to a time delay determination technology, in particular to a method and a system for detecting time delay of adjacent nodes during migration of a virtual machine.
背景技术Background technique
随着通信技术的发展，云计算无线接入网(C-RAN，CloudRadioAccessNetwork)协作化平台成为未来通信系统需要的支撑平台。云计算虚拟化是目前正在飞速发展的最前沿的IT技术。通过引入服务器虚拟化，基站资源池中的基带处理资源运行在虚拟服务器(虚拟机)上，可以实现服务器整合，能够以更加细腻的粒度更加方便地进行资源的弹性分配和统一调度。通过虚拟机在线迁移(LiveMigration，热迁移)技术，可以将承担基带处理的载波从一台物理服务器(物理机)迁移到另一台服务器，当服务器上的载波虚拟机全部迁移到其他服务器后，可以方便地对其进行检修或升级等维护操作，或者将其关电以达到节能减排的效果。With the development of communication technology, a cloud computing radio access network (C-RAN, CloudRadioAccessNetwork) collaborative platform becomes a supporting platform required by future communication systems. Cloud computing virtualization is the most cutting-edge IT technology that is currently developing rapidly. Through the introduction of server virtualization, the baseband processing resources in the base station resource pool run on virtual servers (virtual machines), which can realize server integration, and enable flexible allocation and unified scheduling of resources at a finer granularity and more conveniently. Through virtual machine online migration (LiveMigration, hot migration) technology, the carrier that undertakes baseband processing can be migrated from one physical server (physical machine) to another server. When all the carrier virtual machines on the server are migrated to other servers, Maintenance operations such as overhaul or upgrade can be conveniently performed on it, or it can be turned off to achieve the effect of energy saving and emission reduction.
发明内容Contents of the invention
为解决上述技术问题，本发明实施例提供一种虚机迁移时的邻节点时延检测方法及系统，能为物理机下的虚机确定出时延满足业务倒换要求的目的物理机。In order to solve the above-mentioned technical problems, the embodiments of the present invention provide a neighbor node delay detection method and system during virtual machine migration, which can determine the destination physical machine whose delay meets the service switching requirements for the virtual machine under the physical machine.
本发明实施例的技术方案是这样实现的：The technical scheme of the embodiment of the present invention is realized like this:
一种虚机迁移时的邻节点时延检测方法，包括：A neighbor node delay detection method during virtual machine migration, comprising:
物理机确定自身的虚机需迁移时，生成时间检测请求，并向所述物理机的邻物理机发送所述时间检测请求；所述时间检测请求中包含所述时间检测请求的生成的时间点T1；When the physical machine determines that its own virtual machine needs to be migrated, it generates a time detection request, and sends the time detection request to the adjacent physical machine of the physical machine; the time detection request includes the generation time point of the time detection request T1;
所述邻物理机接收到所述时间检测请求后，生成时间检测响应，并向所述物理机发送所述时间检测响应；其中，所述时间检测响应中包含所述T1、所述时间检测请求的接收时间点T2及所述时间检测响应的生成时间点T3；After the adjacent physical machine receives the time detection request, it generates a time detection response, and sends the time detection response to the physical machine; wherein, the time detection response includes the T1, the time detection request The receiving time point T2 of and the generation time point T3 of the time detection response;
所述物理机接收到所述时间检测响应后，记录所述时间检测响应的接收时间点T4，并根据所述T1、T2、T3及T4计算所述物理机与所述邻物理机之间的时延；After the physical machine receives the time detection response, record the receiving time point T4 of the time detection response, and calculate the distance between the physical machine and the adjacent physical machine according to T1, T2, T3, and T4 delay;
所述物理机根据所计算的时延在所述邻物理机中选择最小时延的物理机作为虚机待迁移的目的物理机。The physical machine selects the physical machine with the smallest delay among the adjacent physical machines according to the calculated delay as the target physical machine for the virtual machine to be migrated.
优选地，所述物理机根据所计算的时延在所述邻物理机中选择最小时延的物理机作为虚机待迁移的目的物理机之前，所述方法还包括：Preferably, before the physical machine selects the physical machine with the smallest delay among the adjacent physical machines according to the calculated delay as the target physical machine for the virtual machine to be migrated, the method further includes:
所述物理机在设定时间段内持续计算所述物理机与所述邻物理机之间的时延并达到设定次数N，计算N次计算的时延的平均值；The physical machine continues to calculate the time delay between the physical machine and the adjacent physical machine within a set period of time and reaches the set number N, and calculates the average value of the time delay calculated for N times;
对应地，所述物理机根据所计算的时延在所述邻物理机中选择最小时延的物理机作为虚机待迁移的目的物理机，包括：Correspondingly, the physical machine selects the physical machine with the smallest delay among the adjacent physical machines according to the calculated delay as the target physical machine for the virtual machine to be migrated, including:
所述物理机根据所计算的时延的平均值在所述邻物理机中选择最小时延的物理机作为虚机待迁移的目的物理机。The physical machine selects the physical machine with the smallest delay among the adjacent physical machines according to the calculated average delay as the target physical machine for the virtual machine to be migrated.
优选地，所述物理机根据所计算的时延在所述邻物理机中选择最小时延的物理机作为虚机待迁移的目的物理机，包括：Preferably, the physical machine selects the physical machine with the smallest delay among the adjacent physical machines according to the calculated delay as the target physical machine for the virtual machine to be migrated, including:
所述物理机将时延的平均值小于设定阈值的邻物理机确定为所述物理机的虚机备选的待迁移的目的物理机。The physical machine determines an adjacent physical machine whose average delay is less than a set threshold as a target physical machine to be migrated as a virtual machine candidate of the physical machine.
优选地，所述计算N次计算的时延的平均值，包括：Preferably, the calculation of the average value of the time delay calculated for N times includes:
根据以下算式计算N次计算的时延的平均值：Calculate the average value of the time delay calculated for N times according to the following formula:
ΔT＝[Σ(T2-T1)+Σ(T4-T3)]/N＝[Σ(Δt1)+Σ(Δt2)]/N。ΔT=[Σ(T2-T1)+Σ(T4-T3)]/N=[Σ(Δt1)+Σ(Δt2)]/N.
优选地，所述T1、T2、T3及T4在所述时间检测请求及所述时间检测响应中由不低于32位的数据表征；所述T1、T2、T3及T4的时间精度至少达到微秒级。Preferably, the T1, T2, T3 and T4 are characterized by no less than 32 bits of data in the time detection request and the time detection response; the time precision of the T1, T2, T3 and T4 is at least micro second level.
一种虚机迁移时的邻节点时延检测系统，包括物理机和所述物理机的邻物理机，其中：A neighbor node delay detection system during virtual machine migration, including a physical machine and an adjacent physical machine of the physical machine, wherein:
物理机，用于确定自身的虚机需迁移时，生成时间检测请求，并向所述物理机的邻物理机发送所述时间检测请求；所述时间检测请求中包含所述时间检测请求的生成的时间点T1；The physical machine is configured to generate a time detection request when determining that its own virtual machine needs to be migrated, and send the time detection request to an adjacent physical machine of the physical machine; the time detection request includes generation of the time detection request time point T1;
所述邻物理机，用于接收到所述时间检测请求后，生成时间检测响应，并向所述物理机发送所述时间检测响应；其中，所述时间检测响应中包含所述T1、所述时间检测请求的接收时间点T2及所述时间检测响应的生成时间点T3；The adjacent physical machine is configured to generate a time detection response after receiving the time detection request, and send the time detection response to the physical machine; wherein, the time detection response includes the T1, the The time point T2 of receiving the time detection request and the generation time point T3 of the time detection response;
所述物理机，还用于接收到所述时间检测响应后，记录所述时间检测响应的接收时间点T4，并根据所述T1、T2、T3及T4计算所述物理机与所述邻物理机之间的时延；根据所计算的时延在所述邻物理机中选择最小时延的物理机作为虚机待迁移的目的物理机。The physical machine is further configured to record the receiving time point T4 of the time detection response after receiving the time detection response, and calculate the relationship between the physical machine and the adjacent physical machine according to T1, T2, T3, and T4. The delay between the machines; according to the calculated delay, select the physical machine with the smallest delay among the adjacent physical machines as the target physical machine for the virtual machine to be migrated.
优选地，所述物理机，在根据所计算的时延在所述邻物理机中选择最小时延的物理机作为虚机待迁移的目的物理机之前，还用于在设定时间段内持续计算所述物理机与所述邻物理机之间的时延并达到设定次数N，计算N次计算的时延的平均值；Preferably, before the physical machine selects the physical machine with the smallest delay among the adjacent physical machines according to the calculated time delay as the target physical machine for the virtual machine to be migrated, it is also used to last for a set period of time Calculate the time delay between the physical machine and the adjacent physical machine and reach the set number N, and calculate the average value of the time delay calculated for N times;
对应地，所述物理机，还用于根据所计算的时延的平均值在所述邻物理机中选择最小时延的物理机作为虚机待迁移的目的物理机。Correspondingly, the physical machine is further configured to select the physical machine with the smallest delay among the adjacent physical machines as the target physical machine for the virtual machine to be migrated according to the calculated average value of the delay.
优选地，所述物理机，还用于将时延的平均值小于设定阈值的邻物理机确定为所述物理机的虚机备选的待迁移的目的物理机。Preferably, the physical machine is further configured to determine an adjacent physical machine whose average delay is less than a set threshold as a target physical machine to be migrated as a virtual machine candidate of the physical machine.
优选地，所述物理机，还用于根据以下算式计算N次计算的时延的平均值：Preferably, the physical machine is also used to calculate the average value of the time delay calculated for N times according to the following formula:
ΔT＝[Σ(T2-T1)+Σ(T4-T3)]/N＝[Σ(Δt1)+Σ(Δt2)]/N。ΔT=[Σ(T2-T1)+Σ(T4-T3)]/N=[Σ(Δt1)+Σ(Δt2)]/N.
优选地，所述T1、T2、T3及T4在所述时间检测请求及所述时间检测响应中由不低于32位的数据表征；所述T1、T2、T3及T4的时间精度至少达到微秒级。Preferably, the T1, T2, T3 and T4 are characterized by no less than 32 bits of data in the time detection request and the time detection response; the time precision of the T1, T2, T3 and T4 is at least micro second level.
本发明实施例中，物理机确定自身的虚机需迁移时，生成时间检测请求，并向物理机的邻物理机发送时间检测请求；时间检测请求中包含时间检测请求的生成的时间点T1；邻物理机接收到时间检测请求后，生成时间检测响应，并向物理机发送时间检测响应；其中，时间检测响应中包含T1、时间检测请求的接收时间点T2及时间检测响应的生成时间点T3；物理机接收到时间检测响应后，记录时间检测响应的接收时间点T4，并根据T1、T2、T3及T4计算物理机与邻物理机之间的时延；物理机根据所计算的时延在邻物理机中为物理机的虚机确定待迁移的目的物理机。In the embodiment of the present invention, when the physical machine determines that its own virtual machine needs to be migrated, it generates a time detection request, and sends the time detection request to the adjacent physical machine of the physical machine; the time detection request includes the time point T1 when the time detection request is generated; After receiving the time detection request, the adjacent physical machine generates a time detection response and sends a time detection response to the physical machine; wherein, the time detection response includes T1, the time point T2 of receiving the time detection request, and the generation time point T3 of the time detection response ; After the physical machine receives the time detection response, record the receiving time point T4 of the time detection response, and calculate the time delay between the physical machine and the adjacent physical machine according to T1, T2, T3 and T4; the physical machine according to the calculated time delay A target physical machine to be migrated is determined for the virtual machine of the physical machine among adjacent physical machines.
与现有技术相比，本发明实施例的技术方案至少有以下有益效果：Compared with the prior art, the technical solutions of the embodiments of the present invention have at least the following beneficial effects:
能够准确地检测出物理机与邻物理机之间的传输时延；Can accurately detect the transmission delay between the physical machine and the adjacent physical machine;
兼容性较好，尤其适合于C-RAN中的虚机迁移过程；Good compatibility, especially suitable for virtual machine migration process in C-RAN;
仅增加交互的消息流程，不需要对架构作改动。Only the interactive message flow is added, and no changes to the architecture are required.
附图说明Description of drawings
图1为本发明实施例的虚机迁移时的邻节点时延检测方法的流程图；FIG. 1 is a flowchart of a method for detecting delays of adjacent nodes during virtual machine migration according to an embodiment of the present invention;
图2为本发明实施例的虚机迁移时的邻节点时延检测系统的结构示意图；2 is a schematic structural diagram of an adjacent node delay detection system during virtual machine migration according to an embodiment of the present invention;
图3为本发明实施例的认证鉴权方法的一示例的流程图；FIG. 3 is a flowchart of an example of an authentication and authentication method according to an embodiment of the present invention;
图4为本发明实施例的认证鉴权方法的另一示例的流程图。Fig. 4 is a flow chart of another example of the authentication authentication method according to the embodiment of the present invention.
具体实施方式detailed description
为使本发明的目的、技术方案和优点更加清楚明白，以下举实施例并参照附图，对本发明进一步详细说明。In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail by citing the following embodiments and referring to the accompanying drawings.
图1为本发明实施例的虚机迁移时的邻节点时延检测方法的流程图，如图1所示，本发明实施例的虚机迁移时的邻节点时延检测方法包括以下步骤：Fig. 1 is a flow chart of the neighbor node delay detection method when the virtual machine is migrated according to the embodiment of the present invention. As shown in Fig. 1, the neighbor node delay detection method during the virtual machine migration according to the embodiment of the present invention includes the following steps:
步骤101，物理机确定自身的虚机需迁移时，生成时间检测请求，并向所述物理机的邻物理机发送所述时间检测请求；Step 101, when the physical machine determines that its own virtual machine needs to be migrated, it generates a time detection request, and sends the time detection request to the adjacent physical machine of the physical machine;
本发明实施例中，所述时间检测请求中包含所述时间检测请求的生成的时间点T1；In the embodiment of the present invention, the time detection request includes the generation time point T1 of the time detection request;
步骤102，所述邻物理机接收到所述时间检测请求后，生成时间检测响应，并向所述物理机发送所述时间检测响应；Step 102, after receiving the time detection request, the adjacent physical machine generates a time detection response, and sends the time detection response to the physical machine;
本发明实施例中，所述时间检测响应中包含所述T1、所述时间检测请求的接收时间点T2及所述时间检测响应的生成时间点T3；In the embodiment of the present invention, the time detection response includes the T1, the time point T2 of receiving the time detection request, and the generation time point T3 of the time detection response;
步骤103，所述物理机接收到所述时间检测响应后，记录所述时间检测响应的接收时间点T4，并根据所述T1、T2、T3及T4计算所述物理机与所述邻物理机之间的时延；Step 103, after the physical machine receives the time detection response, record the time point T4 of receiving the time detection response, and calculate the physical machine and the adjacent physical machine according to the T1, T2, T3 and T4 time delay between
本发明实施例中，所述T1、T2、T3及T4在所述时间检测请求及所述时间检测响应中由不低于32位的数据表征；所述T1、T2、T3及T4的时间精度至少达到微秒级。In the embodiment of the present invention, the T1, T2, T3, and T4 are characterized by no less than 32 bits of data in the time detection request and the time detection response; the time accuracy of the T1, T2, T3, and T4 At least to the microsecond level.
具体地，物理机与邻物理机之间的时延为：(T2-T1)+(T4-T3)。Specifically, the time delay between a physical machine and an adjacent physical machine is: (T2-T1)+(T4-T3).
步骤104，所述物理机根据所计算的时延在所述邻物理机中选择最小时延的物理机作为虚机待迁移的目的物理机。Step 104, the physical machine selects the physical machine with the smallest delay among the adjacent physical machines according to the calculated delay as the target physical machine for the virtual machine to be migrated.
本发明实施例中，具体是将时延满足物理机的虚机的业务迁移时延要求且时延最小的邻物理机选为物理机的虚机待迁移的目的物理机。In the embodiment of the present invention, specifically, the adjacent physical machine whose delay meets the service migration delay requirement of the virtual machine of the physical machine and has the smallest delay is selected as the target physical machine to be migrated from the virtual machine of the physical machine.
本发明实施例中，如果仅通过单次的物理机与邻物理机之间的时延即确定物理机的虚机待迁移的目的物理机，并不能保证所选的目的物理机每次都满足时延要求，本发明实施例通过多次检测物理机与邻物理机之间的时延，并计算时延的平均值，以平均时延作为待迁移的目的物理机选择的标准。具体地，所述物理机根据所计算的时延在所述邻物理机中为所述物理机的虚机确定待迁移的目的物理机之前，还包括：In the embodiment of the present invention, if the destination physical machine to be migrated of the virtual machine of the physical machine is determined only through a single time delay between the physical machine and the adjacent physical machine, it cannot be guaranteed that the selected destination physical machine meets the requirements of the physical machine every time. Delay requirement, the embodiment of the present invention detects the time delay between the physical machine and the adjacent physical machine multiple times, and calculates the average time delay, and uses the average time delay as the standard for selecting the target physical machine to be migrated. Specifically, the physical machine further includes:
所述物理机在设定时间段内持续计算所述物理机与所述邻物理机之间的时延并达到设定次数N，计算N次计算的时延的平均值；The physical machine continues to calculate the time delay between the physical machine and the adjacent physical machine within a set period of time and reaches the set number N, and calculates the average value of the time delay calculated for N times;
对应地，所述物理机根据所计算的时延在所述邻物理机中选择最小时延的物理机作为虚机待迁移的目的物理机，包括：Correspondingly, the physical machine selects the physical machine with the smallest delay among the adjacent physical machines according to the calculated delay as the target physical machine for the virtual machine to be migrated, including:
所述物理机根据所计算的时延的平均值在所述邻物理机中选择最小时延的物理机作为虚机待迁移的目的物理机。The physical machine selects the physical machine with the smallest delay among the adjacent physical machines according to the calculated average delay as the target physical machine for the virtual machine to be migrated.
具体地，计算N次计算的时延的平均值，包括：Specifically, the average value of the time delay calculated for N times is calculated, including:
根据以下算式计算N次计算的时延的平均值：Calculate the average value of the time delay calculated for N times according to the following formula:
ΔT＝[Σ(T2-T1)+Σ(T4-T3)]/N＝[Σ(Δt1)+Σ(Δt2)]/N。ΔT=[Σ(T2-T1)+Σ(T4-T3)]/N=[Σ(Δt1)+Σ(Δt2)]/N.
需要说明的是，也可以以时延的加权平均值作为确定待迁移的目的物理机的标准。由于加权平均值的确定方式是容易实现的，这里不再赘述其计算公式。It should be noted that, the weighted average value of time delay may also be used as a criterion for determining the destination physical machine to be migrated. Since the method of determining the weighted average value is easy to implement, its calculation formula will not be repeated here.
本发明实施例中，所述物理机将时延的平均值小于设定阈值的邻物理机确定为所述物理机的虚机备选的待迁移的目的物理机。In the embodiment of the present invention, the physical machine determines an adjacent physical machine whose average delay is less than a set threshold as a target physical machine to be migrated as a virtual machine candidate of the physical machine.
本发明实施例还记载了一种虚机迁移时的邻节点时延检测系统，包括物理机和所述物理机的邻物理机，其中：The embodiment of the present invention also records a neighbor node delay detection system when a virtual machine migrates, including a physical machine and an adjacent physical machine of the physical machine, wherein:
物理机，用于确定自身的虚机需迁移时，生成时间检测请求，并向所述物理机的邻物理机发送所述时间检测请求；所述时间检测请求中包含所述时间检测请求的生成的时间点T1；The physical machine is configured to generate a time detection request when determining that its own virtual machine needs to be migrated, and send the time detection request to an adjacent physical machine of the physical machine; the time detection request includes generation of the time detection request time point T1;
所述邻物理机，用于接收到所述时间检测请求后，生成时间检测响应，并向所述物理机发送所述时间检测响应；其中，所述时间检测响应中包含所述T1、所述时间检测请求的接收时间点T2及所述时间检测响应的生成时间点T3；The adjacent physical machine is configured to generate a time detection response after receiving the time detection request, and send the time detection response to the physical machine; wherein, the time detection response includes the T1, the The time point T2 of receiving the time detection request and the generation time point T3 of the time detection response;
所述物理机，还用于接收到所述时间检测响应后，记录所述时间检测响应的接收时间点T4，并根据所述T1、T2、T3及T4计算所述物理机与所述邻物理机之间的时延；根据所计算的时延在所述邻物理机中选择最小时延的物理机作为虚机待迁移的目的物理机。The physical machine is further configured to record the receiving time point T4 of the time detection response after receiving the time detection response, and calculate the relationship between the physical machine and the adjacent physical machine according to T1, T2, T3, and T4. The delay between the machines; according to the calculated delay, select the physical machine with the smallest delay among the adjacent physical machines as the target physical machine for the virtual machine to be migrated.
上述物理机，在根据所计算的时延在所述邻物理机中选择最小时延的物理机作为虚机待迁移的目的物理机之前，还用于在设定时间段内持续计算所述物理机与所述邻物理机之间的时延并达到设定次数N，计算N次计算的时延的平均值；The above physical machine is also used to continuously calculate the physical machine within a set period of time before selecting the physical machine with the smallest delay among the adjacent physical machines as the target physical machine for the virtual machine to be migrated according to the calculated time delay. The time delay between the computer and the adjacent physical machine reaches the set number of times N, and calculates the average value of the time delay calculated for N times;
对应地，所述物理机，还用于根据所计算的时延的平均值在所述邻物理机中选择最小时延的物理机作为虚机待迁移的目的物理机。Correspondingly, the physical machine is further configured to select the physical machine with the smallest delay among the adjacent physical machines as the target physical machine for the virtual machine to be migrated according to the calculated average value of the delay.
上述物理机，还用于将时延的平均值小于设定阈值的邻物理机确定为所述物理机的虚机备选的待迁移的目的物理机。The aforementioned physical machine is further configured to determine an adjacent physical machine whose average delay is less than a set threshold as a target physical machine to be migrated as a virtual machine candidate of the physical machine.
上述物理机，还用于根据以下算式计算N次计算的时延的平均值：The above-mentioned physical machine is also used to calculate the average value of the delay of N calculations according to the following formula:
ΔT＝[Σ(T2-T1)+Σ(T4-T3)]/N＝[Σ(Δt1)+Σ(Δt2)]/N。ΔT=[Σ(T2-T1)+Σ(T4-T3)]/N=[Σ(Δt1)+Σ(Δt2)]/N.
其中，所述T1、T2、T3及T4在所述时间检测请求及所述时间检测响应中由不低于32位的数据表征；所述T1、T2、T3及T4的时间精度至少达到微秒级。Wherein, the T1, T2, T3, and T4 are characterized by no less than 32 bits of data in the time detection request and the time detection response; the time precision of the T1, T2, T3, and T4 reaches at least microseconds class.
以下通过具体示例，进一步阐明本发明技术方案的实质。The essence of the technical solution of the present invention is further clarified through specific examples below.
图2为本发明实施例的虚机迁移时的邻节点时延检测系统的结构示意图，如图2所示，物理机B和C是物理机A待迁移的目标物理机，当A迁移到B上后，如图中黑粗线所表示的连接方式，A上的RRU需要直接跟B进行信息和数据交换。B到A的RRU的时延越接近A到其RRU的时延越合理，故选择到本地天面系统时延小的目的物理机是虚机迁移要考虑的必要条件。FIG. 2 is a schematic structural diagram of a neighbor node delay detection system when a virtual machine is migrated according to an embodiment of the present invention. As shown in FIG. 2 , physical machines B and C are target physical machines for physical machine A to be migrated. After connecting, the RRU on A needs to directly exchange information and data with B in the connection mode indicated by the thick black line in the figure. The closer the delay from B to A's RRU is to the delay from A to its RRU, the more reasonable it is. Therefore, choosing a destination physical machine with a small delay to the local antenna system is a necessary condition for virtual machine migration.
当源物理机上的虚机迁移时，首先要选择迁移的目的物理机，目的物理机与源物理机的天面需要保持持续的数据和信息交换，并且这些数据都是高实时性的空口数据，如何选择一个时延传输小的目的物理机是十分必要的。When the virtual machine on the source physical machine is migrated, the target physical machine for migration must be selected first. The sky between the target physical machine and the source physical machine needs to maintain continuous data and information exchange, and these data are air interface data with high real-time performance. How to choose a destination physical machine with a small transmission delay is very necessary.
以下通过具体示例，并结合图2所示的虚机迁移时的邻节点时延检测系统，进一步阐明本发明技术方案的实质。The essence of the technical solution of the present invention is further clarified below through specific examples and in combination with the neighbor node delay detection system during virtual machine migration shown in FIG. 2 .
本发明实施例通过该检测方案，可以获得待迁移虚机到其所有相邻物理机的传输时延，选择时延最小者且满足时延门限的物理机作为迁移的目的物理机。In the embodiment of the present invention, through the detection scheme, the transmission delays from the virtual machine to be migrated to all its adjacent physical machines can be obtained, and the physical machine with the smallest delay and meeting the delay threshold is selected as the target physical machine for migration.
启动流程的条件：Conditions to start the process:
当虚机管理模块获得相邻物理机节点的路由表后，启动检测流程，连续检测N次，N>1。或者，After the virtual machine management module obtains the routing table of the adjacent physical machine node, it starts the detection process and continuously detects N times, where N>1. or,
虚机迁移前的一段时间内。比如分钟级如3分钟内，连续检测N次，N>1。A period of time before virtual machine migration. For example, at the minute level, such as within 3 minutes, N times of continuous detection, N>1.
具体的检测流程包括以下步骤：The specific detection process includes the following steps:
1、源物理机组建时间检测请求帧，包含时间点T1，T1的物理意义为：生成时间检测请求帧的时间点；T1的精度为至少达到微秒(百万分之一秒)级。T1采用不低于32bits的数据类型存储，T1取值范围：0～1024×106微秒。1. The source physical machine constructs a time detection request frame, including a time point T1. The physical meaning of T1 is: the time point at which the time detection request frame is generated; the precision of T1 is at least microsecond (one millionth of a second) level. T1 is stored in a data type not lower than 32 bits, and the value range of T1 is: 0 to 1024×106 microseconds.
2、将时间检测请求帧向源物理机的邻物理机发送。2. Send the time detection request frame to an adjacent physical machine of the source physical machine.
3、邻物理机接收到该时间检测请求帧后，记录收到该时间检测请求帧的时间点T2。T2的物理意义为：接收到时间检测请求帧的时间点。T2的精度为至少微秒(百万分之一秒)级。T2采用不低于32bits的数据类型存储，T2取值范围：0～1024×106微秒。3. After receiving the time detection request frame, the adjacent physical machine records the time point T2 when the time detection request frame is received. The physical meaning of T2 is: the time point when the time detection request frame is received. The accuracy of T2 is at least microsecond (one millionth of a second) level. T2 is stored in a data type not lower than 32 bits, and the value range of T2 is: 0 to 1024×106 microseconds.
4、邻物理机生成时间检测响应帧，包含时间点T3，T3的物理意义为：生成时间检测响应帧的时间点。精度为至少达到微秒(百万分之一秒)级。T3采用不低于32bits的数据类型存储，T3取值范围：0～1024×106微秒。4. The adjacent physical machine generates the time detection response frame, including the time point T3, and the physical meaning of T3 is: the time point at which the time detection response frame is generated. The precision is at least microsecond (one millionth of a second) level. T3 is stored in a data type not lower than 32 bits, and the value range of T3 is: 0 to 1024×106 microseconds.
5、邻物理机将时间检测响应帧向源物理机发送。5. The adjacent physical machine sends the time detection response frame to the source physical machine.
6、源物理机接收到时间检测响应帧后，记录收到该时间检测响应帧的时间点T4，T4的物理意义为：源物理机接收到时间检测响应帧的时间点。精度为至少微秒(百万分之一秒)级。T4采用不低于32bits的数据类型存储，T4取值范围：0～1024×106微秒。6. After the source physical machine receives the time detection response frame, it records the time point T4 when the time detection response frame is received. The physical meaning of T4 is: the time point when the source physical machine receives the time detection response frame. The precision is at least microsecond (one millionth of a second) level. T4 is stored in a data type not lower than 32 bits, and the value range of T4 is: 0 to 1024×106 microseconds.
本发明实施例中，时间检测请求帧结构如图3所示，图3中，T1在时间检测请求帧占用4字节。S_PC_ID为源物理机ID，表示发送时延控制请求帧的物理机的标识符，可以是IP地址，也可以是统一分配的ID标识符。长度可以根据实际情况确定。In the embodiment of the present invention, the structure of the time detection request frame is shown in FIG. 3 . In FIG. 3 , the T1 time detection request frame occupies 4 bytes. S_PC_ID is the ID of the source physical machine, indicating the identifier of the physical machine that sends the delay control request frame, and may be an IP address or a uniformly allocated ID. The length can be determined according to the actual situation.
本发明实施例中，时间检测响应帧结构如图4所示，图4中，T1、T2及T3均占用4字节。S_PC_ID为邻物理机的ID，表示发送时延控制响应帧的邻物理机的标识符，可以是IP地址，也可以是统一分配的ID标识符。长度可以根据实际情况确定。In the embodiment of the present invention, the structure of the time detection response frame is shown in FIG. 4 . In FIG. 4 , T1, T2 and T3 all occupy 4 bytes. S_PC_ID is the ID of the neighboring physical machine, and represents the identifier of the neighboring physical machine that sends the delay control response frame, and may be an IP address or a uniformly allocated ID. The length can be determined according to the actual situation.
需要说明的是，本发明实施例中，时间检测请求帧及时间检测响应帧中还可以包含其他的相关信息，但只要包含上述的时间点信息，即可实施本发明实施例的技术方案。It should be noted that, in the embodiment of the present invention, the time detection request frame and the time detection response frame may also contain other relevant information, but as long as the above-mentioned time point information is included, the technical solution of the embodiment of the present invention can be implemented.
本发明实施例中，启动物理机与邻物理机之间的检测流程，连续检测N次，N>1。物理机与邻物理机之间的时延ΔT的均值计算公式如下：In the embodiment of the present invention, a detection process between a physical machine and an adjacent physical machine is started, and N times of continuous detection are performed, where N>1. The formula for calculating the mean value of the time delay ΔT between a physical machine and an adjacent physical machine is as follows:
ΔT＝[Σ(T2-T1)+Σ(T4-T3)]/N＝[Σ(Δt1)+Σ(Δt2)]/N；ΔT＝[Σ(T2-T1)+Σ(T4-T3)]/N＝[Σ(Δt1)+Σ(Δt2)]/N;
连续检测N，求N次的Δt1和Δt2的值，累加求和，然后求平均值。Continuously detect N, calculate the values of Δt1 and Δt2 for N times, accumulate and sum, and then calculate the average value.
本发明实施例中，还要设置最大时延容忍门限：Threshold_Delay。In the embodiment of the present invention, a maximum delay tolerance threshold: Threshold_Delay is also set.
Threshold_Delay的含义为：从通用处理器平台到天面系统最大的容易时延。根据空口的时序关系和物理机中运行长期演进(LTE，LongTermEvolution)系统协议栈的时间确定，为通用处理器平台能够连续、正常运行LTE协议栈的条件下，从通用处理平台上发送空口数据到RRU的最大时延。当时延高于该门限值，将导致系统无法连续、正常的运行LTE协议栈。The meaning of Threshold_Delay is: the maximum easy delay from the general processor platform to the sky system. According to the timing relationship of the air interface and the time for running the Long Term Evolution (LTE, LongTermEvolution) system protocol stack in the physical machine, it is determined that the air interface data is sent from the general processing platform to the The maximum delay of RRU. When the delay is higher than the threshold value, the system cannot continuously and normally run the LTE protocol stack.
这样，如果物理机与某邻物理机之间的ΔT>Threshold_Delay，则该邻物理机不能作为虚机迁移的目的物理机；In this way, if the ΔT between the physical machine and a neighboring physical machine>Threshold_Delay, the neighboring physical machine cannot be used as the destination physical machine for virtual machine migration;
如果物理机与某邻物理机之间的ΔT小于或等于Threshold_Delay，则该邻物理机是备选目的物理机。If the ΔT between the physical machine and a neighboring physical machine is less than or equal to Threshold_Delay, then the neighboring physical machine is a candidate destination physical machine.
这样，可以得到备选物理机集合：In this way, the set of alternative physical machines can be obtained:
S＝{ΔT1，ΔT2，…，ΔTn}S={ΔT1, ΔT2, ..., ΔTn}
将集合S中ΔT按照大小进行排序，从小到大，得到集合M。Sort the ΔT in the set S according to the size, from small to large, and get the set M.
则集合M中的物理机按照ΔT的顺序从下到大，选用优先级依次降低。Then the physical machines in the set M are selected from bottom to top in the order of ΔT, and the selection priority decreases in turn.
本发明实施例所记载的技术方案之间，在不冲突的情况下，可以任意组合。The technical solutions described in the embodiments of the present invention may be combined arbitrarily if there is no conflict.
在本发明所提供的几个实施例中，应该理解到，所揭露的方法、装置和电子设备，可以通过其它的方式实现。以上所描述的设备实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，如：多个单元或组件可以结合，或可以集成到另一个系统，或一些特征可以忽略，或不执行。另外，所显示或讨论的各组成部分相互之间的耦合、或直接耦合、或通信连接可以是通过一些接口，设备或单元的间接耦合或通信连接，可以是电性的、机械的或其它形式的。In the several embodiments provided by the present invention, it should be understood that the disclosed methods, devices and electronic equipment can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or May be integrated into another system, or some features may be ignored, or not implemented. In addition, the coupling, or direct coupling, or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be electrical, mechanical or other forms of.
上述作为分离部件说明的单元可以是、或也可以不是物理上分开的，作为单元显示的部件可以是、或也可以不是物理单元，即可以位于一个地方，也可以分布到多个网络单元上；可以根据实际的需要选择其中的部分或全部单元来实现本实施例方案的目的。The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units; Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
另外，在本发明各实施例中的各功能单元可以全部集成在一个处理单元中，也可以是各单元分别单独作为一个单元，也可以两个或两个以上单元集成在一个单元中；上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加应用功能单元的形式实现。In addition, each functional unit in each embodiment of the present invention can be integrated into one processing unit, or each unit can be used as a single unit, or two or more units can be integrated into one unit; the above-mentioned integration The unit can be implemented in the form of hardware, or in the form of hardware plus application function unit.
本领域普通技术人员可以理解：实现上述方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成，前述的程序可以存储于一计算机可读取存储介质中，该程序在执行时，执行包括上述方法实施例的步骤；而前述的存储介质包括：移动存储设备、只读存储器(ROM，Read-OnlyMemory)、随机存取存储器(RAM，RandomAccessMemory)、磁碟或者光盘等各种可以存储程序代码的介质。Those of ordinary skill in the art can understand that all or part of the steps for realizing the above-mentioned method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the Including the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: various storage programs such as removable storage devices, read-only memory (ROM, Read-OnlyMemory), random access memory (RAM, RandomAccessMemory), magnetic disk or optical disk, etc. The medium of the code.
或者，本发明实施例上述集成的单元如果以应用功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明实施例的技术方案本质上或者说对现有技术做出贡献的部分可以以应用产品的形式体现出来，该计算机应用产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机、服务器、或者网络设备等)执行本发明各个实施例所述方法的全部或部分。而前述的存储介质包括：移动存储设备、只读存储器(ROM，Read-OnlyMemory)、随机存取存储器(RAM，RandomAccessMemory)、磁碟或者光盘等各种可以存储程序代码的介质。Alternatively, if the above-mentioned integrated units in the embodiments of the present invention are implemented in the form of application function modules and sold or used as independent products, they may also be stored in a computer-readable storage medium. Based on this understanding, the essence of the technical solution of the embodiment of the present invention or the part that contributes to the prior art can be embodied in the form of an application product. The computer application product is stored in a storage medium and includes several instructions for Make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media capable of storing program codes such as removable storage devices, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk.
本发明的保护范围并不局限于此，熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本发明的保护范围之内。The protection scope of the present invention is not limited thereto. Those skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present invention, and all should be covered within the protection scope of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410234574.5ACN105306285B (en) | 2014-05-29 | 2014-05-29 | Neighbors time delay detecting method and system when empty machine migrates |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410234574.5ACN105306285B (en) | 2014-05-29 | 2014-05-29 | Neighbors time delay detecting method and system when empty machine migrates |
| Publication Number | Publication Date |
|---|---|
| CN105306285Atrue CN105306285A (en) | 2016-02-03 |
| CN105306285B CN105306285B (en) | 2018-12-18 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410234574.5AActiveCN105306285B (en) | 2014-05-29 | 2014-05-29 | Neighbors time delay detecting method and system when empty machine migrates |
| Country | Link |
|---|---|
| CN (1) | CN105306285B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8311032B2 (en)* | 2009-12-03 | 2012-11-13 | International Business Machines Corporation | Dynamically provisioning virtual machines |
| US20130054813A1 (en)* | 2011-08-24 | 2013-02-28 | Radware, Ltd. | Method for live migration of virtual machines |
| CN103176845A (en)* | 2011-12-22 | 2013-06-26 | 中国移动通信集团公司 | A virtual machine deployment method, system and device |
| US20130297769A1 (en)* | 2012-05-02 | 2013-11-07 | Cisco Technology, Inc. | System and method for simulating virtual machine migration in a network environment |
| CN103595762A (en)* | 2013-10-15 | 2014-02-19 | 北京航空航天大学 | Software remote execution system oriented towards mobile terminals in cloud environment |
| CN103631633A (en)* | 2012-08-20 | 2014-03-12 | 中国电信股份有限公司 | Virtual machine total-system online migration method, device and system |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8311032B2 (en)* | 2009-12-03 | 2012-11-13 | International Business Machines Corporation | Dynamically provisioning virtual machines |
| US20130054813A1 (en)* | 2011-08-24 | 2013-02-28 | Radware, Ltd. | Method for live migration of virtual machines |
| CN103176845A (en)* | 2011-12-22 | 2013-06-26 | 中国移动通信集团公司 | A virtual machine deployment method, system and device |
| US20130297769A1 (en)* | 2012-05-02 | 2013-11-07 | Cisco Technology, Inc. | System and method for simulating virtual machine migration in a network environment |
| CN103631633A (en)* | 2012-08-20 | 2014-03-12 | 中国电信股份有限公司 | Virtual machine total-system online migration method, device and system |
| CN103595762A (en)* | 2013-10-15 | 2014-02-19 | 北京航空航天大学 | Software remote execution system oriented towards mobile terminals in cloud environment |
| Publication number | Publication date |
|---|---|
| CN105306285B (en) | 2018-12-18 |
| Publication | Publication Date | Title |
|---|---|---|
| US11704144B2 (en) | Creating virtual machine groups based on request | |
| US11429449B2 (en) | Method for fast scheduling for balanced resource allocation in distributed and collaborative container platform environment | |
| US10764132B2 (en) | Scale-out association method and apparatus, and system | |
| EP3291499B1 (en) | Method and apparatus for network service capacity expansion | |
| CN102857370B (en) | A method and device for allocating resources | |
| WO2015143983A1 (en) | Method and apparatus for implementing acceleration processing on vnf | |
| US10541862B2 (en) | VNF processing policy determining method, apparatus, and system | |
| CN111212134A (en) | Request message processing method and device, edge computing system and electronic equipment | |
| KR102022441B1 (en) | Hardware Acceleration Methods and Related Devices | |
| CN110221918A (en) | A kind of correlating method, the apparatus and system of NS and VNF | |
| CN104156255B (en) | A kind of virtual machine migration method, virtual machine (vm) migration device and source physical host | |
| EP3893437B1 (en) | Method and device for deploying virtual network function | |
| WO2023020432A1 (en) | Computing power request method, computing power allocation method, computing power execution method, and terminal and network-side device | |
| CN106101171B (en) | Server connection method and device | |
| WO2016155291A1 (en) | Method and apparatus for managing virtualized network function scaling | |
| CN101778050A (en) | Load balancing method, device and system | |
| CN105677441A (en) | Migration method of virtual machines, manager of virtual facility and coordinator | |
| CN103503413B (en) | Method and device for transmitting network information | |
| BR112013027974A2 (en) | method and apparatus for baseband resource group implementation in lte base station | |
| CN103580923A (en) | Software deploying method and device | |
| CN108881506A (en) | A kind of domain name analytic method and device based on more available partition AZ | |
| CN102098343A (en) | Method and system for saving and acquiring resource information in cloud-computing operating system | |
| CN108228272B (en) | WEB container generation processing method, device and server | |
| CN112769829A (en) | Deployment method of cloud physical machine, related equipment and readable storage medium | |
| CN105306285B (en) | Neighbors time delay detecting method and system when empty machine migrates |
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |