Virtual-network-interface-card detection method, electronic device, storage medium, and computer program product

Abstract

Provided in the embodiments of the present disclosure are a virtual-network-interface-card detection method, an electronic device, a storage medium, and a computer program product. In the embodiments of the present disclosure, by means of information interaction between a detection tool and a virtual switch, a virtual-network-interface-card detection mechanism at a queue granularity is provided, such that whether a receive queue of a virtual network interface card is abnormal can be accurately and efficiently detected, thereby ensuring the stability of a virtual machine, enhancing the stability and operation and maintenance capability of a cloud service, and thus improving the user experience of the cloud service.

Description

[0001] The present disclosure relates to the technical field of cloud computing, and particularly relates to a virtual network card detection method, an electronic device, a storage medium and a computer program product. Background art The development of cloud computing is inseparable from virtualization technology. Cloud service providers use virtualization technology to build large-scale cloud computing platforms to provide cloud services for users. In the cloud computing platform, a virtual machine (VM) plays a core role, and its stability is directly related to the stability of cloud services and user experience. The virtual machine communicates with a virtual switch (Virtual Switch) through a virtual network interface card (vNIC). A virtual network card is usually configured with multiple queues such as multiple transmit queues (Tx Queues) and multiple receive queues (Rx Queues). Each queue can independently process data packets, multiple queues can be processed in parallel, thereby improving network throughput, reducing network delay, and improving network input / output (I / O) processing efficiency. In actual application, when the receive queue of the virtual network card is abnormal, the data packet cannot be normally received by the virtual machine, the network is not connected, the stability of the virtual machine is affected, and finally the stability of the cloud service and the user experience are adversely affected. Content of the invention The present disclosure provides a virtual network card detection method, an electronic device, a storage medium and a computer program product, which provide a queue granularity virtual network card detection mechanism to solve the problem that when the receive queue of the virtual network card is abnormal, the data packet cannot be normally received by the virtual machine, and the network is not connected. The present disclosure provides a virtual network card detection method, which is applied to a virtual switch. The method comprises the following steps: in response to a detection instruction of a detection tool, obtaining an enabled state of multiple receive queues of a virtual network card, the enabled state comprising enabled and disabled; setting a round-trip time of a disabled receive queue as a first default value, the first default value indicating that the receive queue is disabled; for any enabled receive queue, sending a detection packet to a virtual machine through the enabled receive queue, and determining the round-trip time of the enabled receive queue according to whether response information sent by the virtual machine in response to the detection packet is received; and returning a detection result of this time to the detection tool, so that the detection tool determines an abnormal receive queue in the multiple receive queues according to the round-trip time of the multiple receive queues in the detection result of this time.The present disclosure provides a virtual network card detection method, which is applied to a detection tool. The method comprises: sending a current detection instruction to a virtual switch; receiving a current detection result returned by the virtual switch; and determining an abnormal receiving queue from a plurality of receiving queues according to a round trip time of the plurality of receiving queues in the current detection result. The present disclosure provides a cloud computing platform, which comprises: a detection tool, a virtual switch and a virtual machine. A virtual network card of the virtual machine comprises a plurality of receiving queues. The detection tool is configured to: send a current detection instruction to the virtual switch; receive a current detection result returned by the virtual switch; and determine an abnormal receiving queue from a plurality of receiving queues according to a round trip time of the plurality of receiving queues in the current detection result. The virtual switch is configured to: in response to the current detection instruction, acquire an enabling state of a plurality of receiving queues of the virtual network card, wherein the enabling state comprises enabled and disabled; set a round trip time of a disabled receiving queue as a first default value, wherein the first default value indicates that the receiving queue is disabled; for any enabled receiving queue, send a detection packet to the virtual machine through the enabled receiving queue, and determine a round trip time of the enabled receiving queue according to whether response information sent by the virtual machine in response to the detection packet is received; and return the current detection result to the detection tool. The present disclosure provides an electronic device, which comprises: a memory and a processor. The memory is configured to store a computer program. The processor is coupled to the memory and is configured to execute the computer program to perform steps in a virtual network card detection method. The present disclosure provides a computer readable storage medium storing a computer program. When the computer program is executed by a processor, the processor can implement steps in a virtual network card detection method. The present disclosure provides a computer program product comprising computer programs / instructions. When the computer programs / instructions are executed by a processor, the processor can implement steps in a virtual network card detection method. In the present disclosure, the detection tool sends a current detection instruction to the virtual switch. In response to the current detection instruction, the virtual switch sets a round trip time of a disabled receiving queue of the virtual network card as a first default value, and the first default value indicates that the receiving queue is disabled. For any enabled receiving queue, the virtual switch sends a detection packet to the virtual machine through the enabled receiving queue, and determines a round trip time of the enabled receiving queue according to whether response information sent by the virtual machine in response to the detection packet is received. Thus, the round trip times of the receiving queues of the virtual network card can be detected. The virtual switch returns a current detection result to the detection tool. The detection tool determines an abnormal receiving queue from a plurality of receiving queues according to a round trip time of the plurality of receiving queues in the current detection result.Therefore, by information interaction between the detection tool and the virtual switch, a queue granularity virtual network card detection mechanism is provided, which can accurately and efficiently detect whether the receiving queue of the virtual network card is abnormal, ensures the stability of the virtual machine, enhances the stability and operation and maintenance capability of the cloud service, and improves the user experience of the cloud service. The accompanying drawings described herein are used to provide further understanding of the present disclosure, constitute a part of the present disclosure, and the illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure, and do not constitute improper limitations on the present disclosure. In the drawings: Fig. 1 is a schematic diagram of an application scenario of a virtual network card detection method provided by an embodiment of the present disclosure; Fig. 2 is a signaling interaction diagram of a virtual network card detection method provided by an embodiment of the present disclosure; Fig. 3 is a structural schematic diagram of a virtual network card detection device provided by an embodiment of the present disclosure; Fig. 4 is a structural schematic diagram of a detection tool provided by an embodiment of the present disclosure; Fig. 5 is a structural schematic diagram of an electronic device provided by an embodiment of the present disclosure. In order to make the purpose, technical scheme and advantages of the present disclosure clearer, the technical scheme of the present disclosure will be described clearly and completely in combination with specific embodiments of the present disclosure and corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present disclosure. In the embodiments of the present disclosure, "at least one" means one or more, and "multiple" means two or more. "And / or" describes the access relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the following three cases: A exists alone, A and B exist together, and B exists alone, wherein A and B can be singular or plural. No other special meaning. The following explains the related terms involved in the embodiments of the present disclosure: Virtual Switch: is one of the core components in cloud computing and virtualization technology, which runs in the host operating system and is responsible for network communication between virtual machines, and also responsible for data exchange between virtual machines and external physical networks. Virtual network card: refers to the network card virtualized for virtual machines through virtualization technology, which allows virtual machines to communicate through the network like physical machines, whether it is communication with other virtual machines on the same host or communication with external network devices. The design purpose of virtual network card is to provide virtual machines with similar network functions as physical network interfaces without actual hardware network cards. Virtual network cards are usually configured with multiple sending queues and multiple receiving queues, which allow parallel processing of data packets, thereby improving network throughput and reducing latency. Through the queues of multiple virtual network cards, virtual machines can more efficiently send and receive data, especially in a multi-core CPU environment, which can effectively utilize CPU resources. Virtual Machine Monitor (VMM): is a system software that provides an abstraction layer between physical host hardware and guest operating systems (Guest OS), its main responsibility is to create, run and manage virtual machines, so that each virtual machine can execute its own operating system and application program as if it is running on independent hardware. Probing Tools: is a series of software and tools used in the fields of network, system, application or security, which help users collect information, monitor status, detect vulnerabilities or performance problems. Round-Trip Time (RTT) refers to the total time taken from the sending end of a data packet or data segment to the receiving end, sending an acknowledgment after receiving, and finally the sending end receiving the acknowledgment in network communication. The embodiments of the present disclosure provide a virtual network card probing method, electronic equipment, storage medium and computer program product. In the embodiments of the present disclosure, through the information interaction between the probing tool and the virtual switch, a queue granularity virtual network card probing mechanism is provided, which can accurately and efficiently probe whether the receiving queue of the virtual network card is abnormal, ensuring the stability of the virtual machine, enhancing the stability and operation and maintenance capability of the cloud service, and improving the user experience of the cloud service. The technical solutions of the present disclosure and how the technical solutions of the present disclosure solve the above technical problems are described in detail in the following specific embodiments. The following specific embodiments can be combined with each other, and for the same or similar concepts or processes, some embodiments may not be described again. The technical solutions provided by the embodiments of the present disclosure are described in detail with reference to the accompanying drawings.FIG. 1 is a schematic diagram of an application scenario of a virtual network card detection method provided by an embodiment of the present disclosure. Referring to FIG. 1, a cloud computing platform constructed based on a virtualization technology can include a virtual machine, a virtual switch, a virtual machine monitor, and the like, but is not limited thereto. In actual application, various virtualization components such as the virtual switch and the virtual machine monitor can be hot upgraded, and the hot upgrade of the virtualization components can cause the receiving queue of the virtual network card to be abnormal, thereby causing the virtual machine to be unable to receive a data packet through the abnormal receiving queue and affecting the stability of the virtual machine. Therefore, it is necessary to detect the receiving queue of the virtual network card before and after the hot upgrade of the virtualization component, to discover the abnormal receiving queue caused by the hot upgrade of the virtualization component in a timely manner, to timely notify manual intervention to solve the fault problem, to quickly restore the abnormal receiving queue to normal, and to ensure the stability of the virtual machine. In actual application, the detection of the receiving queue can be completed through information interaction between a detection tool and the virtual switch. The detection tool can be deployed outside the virtual switch, thereby reducing the intrusion to the virtual switch and not affecting the normal function of the virtual switch. In actual application, the detection tool can be triggered to initiate the detection task of the receiving queue as needed, and no limitation is made in this regard. Here, taking the hot upgrade scenario of the virtualization component as an example, the detection tool needs to be triggered to initiate the detection task of the receiving queue before the hot upgrade of the virtualization component, to obtain a hot-upgrade detection result; the detection tool also needs to be triggered to initiate the detection task of the receiving queue after the hot upgrade of the virtualization component, to obtain a post-hot-upgrade detection result; and the abnormal receiving queue caused by the hot upgrade of the virtualization component is discovered according to the comparison result of the hot-upgrade detection result and the post-hot-upgrade detection result. For each detection task, referring to ① shown in FIG. 1, the detection tool sends a current detection instruction to the virtual switch, and the current detection instruction is used to instruct the virtual switch to detect whether the receiving queue of the virtual network card is normal. The normal receiving queue can enable the virtual machine to receive the data packet, and the abnormal receiving queue cannot enable the virtual machine to receive the data packet. After receiving the current detection instruction initiated by the detection tool, the virtual switch obtains the enabled state of each receiving queue of the virtual network card, and the enabled state includes enabled and not enabled. The enabled receiving queue is allowed to perform data packet transmission, but whether the enabled receiving queue can successfully transmit the data packet is not confirmed, and the detection of whether the enabled receiving queue is normal can be confirmed only by sending a detection packet. If the detection result is that the enabled receiving queue can successfully transmit the data packet, the enabled receiving queue is a normal receiving queue; and if the detection result is that the enabled receiving queue cannot successfully transmit the data packet, the enabled receiving queue is an abnormal receiving queue.The unenabled receiving queue is not allowed to transmit data packets, and the unenabled receiving queue can also be regarded as an abnormal receiving queue. In actual application, the virtual switch can set the round trip time of the unenabled receiving queue as a default value, for example, 0, which represents that the enabled state of the receiving queue is unenabled. For the enabled receiving queue, the virtual switch needs to send a probe packet to the virtual machine through the enabled receiving queue, and determine the round trip time of the enabled receiving queue according to whether the virtual machine returns response information of the probe packet. For example, referring to FIG. 1, the virtual network card has n receiving queues and n sending queues, n is a positive integer, the n receiving queues are receiving queue 1, receiving queue 2,..., and receiving queue n, and the n sending queues are sending queue 1, sending queue 2,..., and sending queue n. Among the n receiving queues, the enabled states of receiving queue 1, receiving queue 2, and other receiving queues are enabled. Referring to ② and ③ shown in FIG. 1, the virtual switch sends a probe packet to the virtual machine through receiving queue 1, and the virtual machine returns response information of the probe packet to the virtual switch through sending queue 1, so receiving queue 1 is a normal enabled receiving queue, and at this time, the virtual switch can calculate the round trip time of receiving queue 1 according to the sending time of the probe packet and the receiving time of the response information. The virtual switch sends a probe packet to the virtual machine through receiving queue 2 (not shown in FIG. 1), but the virtual switch does not receive the response information of the probe packet returned by the virtual machine through sending queue 2, so receiving queue 2 is an abnormal enabled receiving queue, and at this time, the round trip time of receiving queue 2 is set as a default value, for example, -1, which represents that the enabled receiving queue is abnormal. In actual application, the virtual switch generates this time detection result generated by the response detection tool according to the round trip times of a plurality of receiving queues. The virtual switch can actively or passively send the this time detection result to the detection tool, and no limitation is made to this. Optionally, after the virtual switch sends the probe packet to all the enabled receiving queues, referring to ④ shown in FIG. 1, the virtual switch can also send probe packet sending completion information to the detection tool, and after the detection tool obtains the probe packet sending completion information, referring to ⑤ shown in FIG. 1, the detection tool waits for a period of time, and the waiting time is set as needed, and the waiting time can ensure that the probe packets sent by the virtual switch are all responded.Referring to ⑥ and ⑦ shown in FIG. 1, the detection tool waits for a period of time, and then sends a detection result acquisition instruction to the virtual switch. The virtual switch returns the detection result to the detection tool. The detection tool finds out the abnormal receiving queue from the multiple receiving queues based on the detection result. Thus, the detection task is completed through the information exchange between the detection tool and the virtual switch. It should be noted that the application scenario shown in FIG. 1 is only an exemplary application scenario, and the embodiments of the present disclosure are not limited to the application scenario. The embodiments of the present disclosure do not limit the devices included in FIG. 1, nor the positional relationship between the devices in FIG. 1. FIG. 2 is a signaling interaction diagram of a virtual network card detection method provided by the embodiments of the present disclosure. Referring to FIG. 2, the method can include the following steps.

[0002] 201. The detection tool sends a detection instruction to the virtual switch. Specifically, when it is necessary to detect whether the receiving queue of the virtual network card is normal, the detection tool can be triggered to send a detection instruction to the virtual switch. In actual application, the detection tool can interact with the virtual switch through various communication mechanisms, for example, but not limited to, Socket (socket) communication, shared memory mode, event notification mode, etc.

[0003] 202. The virtual switch acquires the enabled state of the multiple receiving queues of the virtual network card in response to the detection instruction of the detection tool. The enabled state includes enabled and not enabled.

[0004] 203. The virtual switch sets the round-trip time of the not enabled receiving queue as a first default value. The first default value indicates that the receiving queue is not enabled. In actual application, the first default value is flexibly set as needed, for example, 0.

[0005] 204、The virtual switch sends a probe packet to the virtual machine through the enabled receive queue for any one enabled receive queue, and determines the round trip time of the enabled receive queue according to whether response information sent by the virtual machine in response to the probe packet is received. In actual application, after the virtual switch determines the enabled receive queue from the plurality of receive queues, a corresponding probe packet needs to be constructed for each enabled receive queue. In actual application, the value of the message field in the probe packet is not limited. Optionally, the value of the destination IP address field in the probe packet is the primary IP address of the virtual network card. Specifically, in the virtualized network, one or more IP addresses can be configured for each virtual network card, and the primary IP usually refers to the address used for external communication. The value of the destination IP address field in the probe packet as the primary IP address of the virtual network card can ensure that the probe packet is responded by the Guest OS of the virtual machine, and ensure the reliability of the probe. Optionally, the value of the source IP address field in the probe packet is the private network gateway IP address of the virtual network card. Specifically, in the virtualized network, the private network gateway IP usually refers to the gateway address of the internal network, which is used for communication between virtual machines or as a gateway to the external network. Usually, the private network gateway IP address of the virtual network card is a reserved IP address that does not carry any user service, and the value of the source IP address field in the probe packet as the private network gateway IP address of the virtual network card can reduce the invasion influence on the user service. It is worth noting that the private network gateway IP address of the virtual network card is usually an IP address preset by the cloud service provider in the virtual network configuration, which serves as a bridge for internal private network communication with the external network. This IP address is not allocated to any actual business instance, and its main function is to serve as an exit point for routing to help the internal private IP address traffic to be forwarded to the public network or between different subnets. Therefore, it can be considered that the private network gateway IP address of the virtual network card is a reserved IP address that does not carry any service. Because the private network gateway IP address is not directly associated with any user service, using it as the source IP address of the probe packet will not interfere with the normal data transmission or application logic of the user service, thereby reducing the influence on the user service. In actual application, the protocol type of the probe packet is not limited. The protocol type of the probe packet is, for example, Transmission Control Protocol (TCP), User Datagram Protocol (UDP), protocol type with sequence number, or protocol type without sequence number.The protocol type with a sequence number may include, but is not limited to, an Internet Control Message Protocol (ICMP). The protocol type without a sequence number may include, but is not limited to, an Address Resolution Protocol (ARP). It is worth noting that the protocol type of the detection packet may be various common network protocols, and the Guest OS of the virtual machine does not need to be modified, and the user does not need to cooperate. From the perspective of the user, the detection can be implemented without user awareness. Optionally, the value of the protocol type field in the detection packet is the protocol type with a sequence number or the protocol type without a sequence number; for the protocol type with a sequence number, the value of the sequence number field in the detection packet is the queue identifier of the enabled receiving queue; for the protocol type without a sequence number, the value of the source Media Access Control (MAC) address field in the detection packet is the queue identifier of the enabled receiving queue. It is worth noting that by carrying the queue identifier of the enabled receiving queue in the detection packet, it can be distinguished which enabled receiving queue the detection packet is sent to, and the accuracy of the detection is ensured. Further optionally, in order to accurately send the detection packet to the virtual machine through the enabled receiving queue, the Receive Side Scaling (RSS) value of the detection packet can also be configured as the queue identifier of the enabled receiving queue in the detection packet; and the detection packet is sent to the virtual machine through the corresponding enabled receiving queue according to the RSS value. It can be understood that the virtual switch decides which enabled receiving queue the detection packet needs to be sent through according to the RSS value. Specifically, according to the queue identifier of the enabled receiving queue pointed to by the RSS value, the enabled receiving queue pointed to by the RSS value is selected from at least one enabled receiving queue, and the detection packet is sent to the virtual machine through the selected enabled receiving queue. In actual application, when determining the round-trip time of the enabled receiving queue according to whether the response information sent by the virtual machine in response to the detection packet is received, if the response information sent by the virtual machine is received, the round-trip time of the enabled receiving queue is determined according to the sending time of the detection packet and the receiving time of the response information; if the response information sent by the virtual machine is not received, the round-trip time of the enabled receiving queue is set as a second default value, and the second default value indicates that the enabled receiving queue is abnormal. The second default value is flexibly set as needed, for example, -1. In actual application, the difference between the sending time of the detection packet and the receiving time of the response information can be used as the round-trip time of the enabled receiving queue.Of course, the difference between the sending time of the probe packet and the receiving time of the response information can also be corrected, and the corrected difference can be used as the round-trip time of the enabled receiving queue. Optionally, to efficiently determine the normal receiving queue, the round-trip time of the normal receiving queue can be set to a third default value, which is flexibly set as needed, for example, 1. In actual application, the number of enabled receiving queues confirmed by the virtual switch can be one or more. If the number of enabled receiving queues is multiple, the virtual switch can send respective corresponding probe packets to multiple enabled receiving queues in parallel. Further optionally, to reduce the probability of network congestion of the virtual machine caused by the instantaneous sending of a large number of probe packets, if the number of enabled receiving queues is multiple, the probe packets are sent to the virtual machine through each of the multiple enabled receiving queues in turn at a set time interval. The set time interval is flexibly set as needed, for example, 0.1 milliseconds. It can be understood that sending the probe packets at the set time interval reduces the probability of network congestion of the virtual machine caused by the instantaneous sending of a large number of probe packets, and sending the probe packets through each receiving queue in turn enables smooth detection of whether each receiving queue is abnormal. Specifically, the probe packets are sent to the virtual machine through each of the multiple enabled receiving queues in turn at a set time interval, that is, the probe packets are sent to the virtual machine through each of the multiple enabled receiving queues in turn, and after sending the probe packets to the previous enabled receiving queue, the probe packets are sent to the next enabled receiving queue at the set time interval. For example, there are a total of 3 enabled receiving queues, first, the virtual switch sends the probe packets to the first enabled receiving queue, waits for 0.1 milliseconds; then, the virtual switch sends the probe packets to the second enabled receiving queue, waits for 0.1 milliseconds; finally, the virtual switch sends the probe packets to the third enabled receiving queue.205、The virtual switch returns the detection result of this time to the detection tool. In actual application, after the virtual switch obtains the round-trip times of the multiple receiving queues in response to the detection instruction of this time sent by the detection tool, the virtual switch generates the detection result of this time according to the round-trip times of the multiple receiving queues. The virtual switch can actively or passively send the detection result of this time to the detection tool, and there is no limitation. Further optionally, in response to the detection result obtaining instruction sent by the detection tool, the detection result of this time is returned to the detection tool, wherein the detection result obtaining instruction is sent by the detection tool after receiving the probe packet sending completion information returned by the virtual switch, and all the probe packets sent through all the enabled receiving queues within the set time have been responded by the virtual machine.It can be understood that the time length is set to ensure that the virtual switch sends the corresponding probe packets to the virtual machines through all the enabled receiving queues respectively, and also to ensure that the virtual machines have responded to the received probe packets. Specifically, the time length is set flexibly as needed, and generally, the time length is much greater than the average round trip time, which is obtained by counting the round trip times of a large number of receiving queues. It can be understood that the probe packet sending completion information can indicate that the virtual switch has sent the probe packets, and also can inform the detection tool to obtain the detection result in time, thereby improving the detection efficiency. Further, the responses to the respective probe packets sent through all the enabled receiving queues within the set time length are completed, so that the detection tool obtains the probe packet sending completion information and waits for the set time length, the detection tool sends a detection result obtaining instruction to the virtual switch, and by restricting the sending time interval between the detection instruction and the detection result obtaining instruction of the detection tool this time, the round trip time of each enabled receiving queue can be ensured to be obtained, and the reliability of the detection result obtaining is improved. In some optional embodiments, the virtual switch can also determine at least one normal receiving queue from the plurality of enabled receiving queues according to the detection result this time; configure the RSS value of the service data packet according to the respective round trip times of the at least one normal receiving queue; and send the service data packet to the virtual machine through the normal receiving queue pointed to by the RSS value of the service data packet, so as to control the load balancing of the at least one normal receiving queue. Specifically, the virtual switch determines the receiving queue corresponding to the round trip time of the other value except the first default value and the second default value as the normal receiving queue. The round trip time can represent the load state of the normal receiving queue to some extent; the longer the round trip time, the heavier the load of the normal receiving queue, and the more data packets transmitted by the normal receiving queue; the shorter the round trip time, the lighter the load of the normal receiving queue, and the fewer data packets transmitted by the normal receiving queue. In order to improve the working performance of the virtual machine, the load balancing control can be performed on each normal receiving queue. Unlike the probe packet, the service data packet refers to the data packet carrying service data. In addition to sending the probe packet to the virtual machine, the virtual switch also sends the service data packet to the virtual machine. In actual application, the RSS function used for the service data packet is not limited. The input parameter is input into the RSS function to obtain the RSS value. The input parameter can include the parameter value of the variable parameter and a plurality of field values in the service data packet, and the plurality of field values in the service data packet include but are not limited to, for example: the source MAC address, the destination MAC address, the source IP address, the destination IP address, the protocol type, and the port number in the service data packet. The variable parameter refers to a parameter whose parameter value can be flexibly configured, and by adjusting the parameter value of the variable parameter, different RSS values can be configured.In actual application, the RSS value of the service data packet can be taken modulo with the total number of the normal receiving queues to obtain a modulo result, and the modulo result can be taken as the queue identifier of the normal receiving queue pointed by the RSS value of the service data packet. For example, there are 10 normal receiving queues, and the RSS value of the service data packet is 1, and the modulo result is 1. It is worth noting that when setting the queue identifier of each receiving queue in the multiple receiving queues of the virtual network card, each receiving queue is sequentially labeled in an increasing manner, and the label of the next receiving queue is 1 greater than the label of the previous receiving queue, and the label of each receiving queue is taken as the queue identifier of each receiving queue. For example, the virtual network card has 5 receiving queues, which are receiving queue 1, receiving queue 2, receiving queue 3, receiving queue 4, and receiving queue 5. In actual application, the implementation manner of controlling the RSS value of the service data packet according to the round-trip time of at least one normal receiving queue is not limited. As an example, when the RSS value of the service data packet is controlled according to the round-trip time of at least one normal receiving queue, for multiple service data packets to be transmitted in a unit time, the RSS value of the service data packet is controlled to allocate the service data packet to the normal receiving queue pointed by the RSS value, with the number of data packets allocated to the normal receiving queue being inversely proportional to the round-trip time of the normal receiving queue. It can be understood that for multiple service data packets to be transmitted in a unit time, the longer the round-trip time of the normal receiving queue, the fewer the number of service data packets to be transmitted allocated to the normal receiving queue; the shorter the round-trip time of the normal receiving queue, the more the number of service data packets to be transmitted allocated to the normal receiving queue. As another example, when the RSS value of the service data packet is configured according to the round-trip time of at least one normal receiving queue, the maximum allowed number of data packets transmitted in a unit time of each normal receiving queue is determined according to the round-trip time of at least one normal receiving queue; for multiple service data packets to be transmitted in a unit time, the RSS value of the service data packet is configured to allocate the service data packet to the normal receiving queue pointed by the corresponding RSS value, with the number of data packets allocated to the normal receiving queue not exceeding the maximum allowed number of data packets transmitted in a unit time of the normal receiving queue. The unit time may include, but is not limited to, every millisecond, every second, or every minute, etc. It can be understood that by controlling the maximum allowed number of data packets transmitted in a unit time of each normal receiving queue, the load state of the normal receiving queue can be better controlled, and better load balancing control can be achieved.It can be understood that the longer the round trip time of the normal receiving queue, the fewer the maximum number of data packets allowed to be transmitted per unit time by the normal receiving queue; the shorter the round trip time of the normal receiving queue, the more the maximum number of data packets allowed to be transmitted per unit time by the normal receiving queue. As another example, when controlling the RSS value of the service data packet according to the respective round trip times of the at least one normal receiving queue, at least one target normal receiving queue with a round trip time less than a preset round trip time is screened out from the at least one normal receiving queue; the maximum number of data packets allowed to be transmitted per unit time by each target normal receiving queue is determined according to the respective round trip times of the at least one target normal receiving queue; for a plurality of service data packets to be transmitted per unit time, the RSS value of the service data packet is configured to allocate the service data packet to the target normal receiving queue pointed to by the corresponding RSS value, with the number of data packets allocated to the target normal receiving queue not exceeding the maximum number of data packets allowed to be transmitted by the target normal receiving queue as the target. Specifically, the preset round trip time is flexibly set as needed, the load of the target normal receiving queue with a round trip time less than the preset round trip time is relatively light, and the load of the normal receiving queue with a round trip time greater than or equal to the preset round trip time is relatively heavy. For the normal receiving queue with a round trip time greater than or equal to the preset round trip time, use can be suspended, that is, the normal receiving queue is temporarily not used to send service data packets to the virtual machine, so as to avoid increasing the load of these normal receiving queues. For the target normal receiving queue with a round trip time less than the preset round trip time, by controlling the maximum number of data packets allowed to be transmitted per unit time by each target normal receiving queue, the load state of the target normal receiving queue can be better controlled, and better load balancing control can be achieved.

[0006] 206、The detection tool determines an abnormal receiving queue from the multiple receiving queues according to the round trip time of the multiple receiving queues in the current detection result. Specifically, after receiving the current detection result returned by the virtual switch, the detection tool can determine the receiving queue with the round trip time as the second default value as the abnormal receiving queue, can determine the receiving queue with the round trip time as the first default value as the abnormal receiving queue, and can determine the receiving queue with the round trip time as a value other than the first default value and the second default value as the normal receiving queue. For the hot upgrade of the virtualization component, the detection tool can also determine the abnormal receiving queue that is caused by the hot upgrade according to the detection result before the hot upgrade of the virtualization component and the detection result after the hot upgrade of the virtualization component. For example, the value of the round trip time of the receiving queue before the hot upgrade is not the second default value, but the value of the round trip time of the receiving queue after the hot upgrade is the second default value, and the receiving queue is the abnormal receiving queue caused by the hot upgrade. The technical solution provided by the public embodiment provides a queue granularity virtual network card detection mechanism through the information interaction between the detection tool and the virtual switch, can accurately and efficiently detect whether the receiving queue of the virtual network card is abnormal, ensures the stability of the virtual machine, enhances the stability and operation and maintenance capability of the cloud service, and improves the user experience of the cloud service. The public embodiment also provides a cloud computing platform, which includes a detection tool, a virtual switch and a virtual machine, the virtual network card of the virtual machine includes multiple receiving queues, the detection tool is configured to send a current detection instruction to the virtual switch, receive a current detection result returned by the virtual switch, and determine an abnormal receiving queue from the multiple receiving queues according to the round trip time of the multiple receiving queues in the current detection result, the virtual switch is configured to respond to the current detection instruction, acquire the enabled state of the multiple receiving queues of the virtual network card, the enabled state includes enabled and not enabled, set the round trip time of the receiving queue that is not enabled as a first default value, the first default value indicates that the receiving queue is not enabled, for any enabled receiving queue, send a detection packet to the virtual machine through the enabled receiving queue, and determine the round trip time of the enabled receiving queue according to whether the response information sent by the virtual machine in response to the detection packet is received, and return the current detection result to the detection tool. More information about the detection task completed by the interaction between the detection tool and the virtual switch can be found in the foregoing embodiments, which will not be described here. FIG. 3 is a structural schematic diagram of a virtual network card detection device provided by the embodiment of the disclosure.The device is applied to a virtual switch, the device can be composed of software and / or hardware, referring to FIG. 3, the device can comprise: an acquisition module 31, configured to acquire the enabled state of a plurality of receiving queues of a virtual network card in response to a current detection instruction of a detection tool, the enabled state comprising enabled and disabled; a processing module 32, configured to set the round trip time of a disabled receiving queue as a first default value, the first default value indicating that the receiving queue is disabled; for any enabled receiving queue, sending a detection packet to a virtual machine through the enabled receiving queue, and determining the round trip time of the enabled receiving queue according to whether response information sent by the virtual machine in response to the detection packet is received; a sending module 33, configured to return the current detection result to the detection tool, so that the detection tool determines an abnormal receiving queue among the plurality of receiving queues according to the round trip times of the plurality of receiving queues in the current detection result. Optionally, when the processing module 32 determines the round trip time of the enabled receiving queue, it is specifically configured to: if the response information sent by the virtual machine is received, then determining the round trip time of the enabled receiving queue according to the sending time of the detection packet and the receiving time of the response information; if the response information sent by the virtual machine is not received, then setting the round trip time of the enabled receiving queue as a second default value, the second default value indicating that the enabled receiving queue is abnormal. Optionally, the processing module 32 is further configured to: constructing the detection packet, wherein the value of the destination IP address field in the detection packet is the main IP address of the virtual network card; the value of the source IP address field in the detection packet is the private network gateway IP address of the virtual network card. Optionally, when the processing module 32 sends the detection packet to the virtual machine through the enabled receiving queue, it is specifically configured to: configuring the receiving end of the detection packet to scale the RSS value as the queue identifier of the enabled receiving queue in the detection packet; sending the detection packet to the virtual machine through the corresponding enabled receiving queue according to the RSS value. Optionally, the value of the protocol type field in the detection packet is a protocol type with a sequence number or a protocol type without a sequence number; for the protocol type with a sequence number, the value of the sequence number field in the detection packet is the queue identifier of the enabled receiving queue; for the protocol type without a sequence number, the value of the source MAC address field in the detection packet is the queue identifier of the enabled receiving queue. Optionally, the sending module 33 is specifically configured to: in response to a detection result acquisition instruction sent by the detection tool, returning the current detection result to the detection tool, wherein the detection result acquisition instruction is sent by the detection tool after receiving the detection packet sending completion information returned by the virtual switch, and each detection packet sent through all the enabled receiving queues within the set time length has been responded by the virtual machine.Optionally, if the number of enabled receiving queues is multiple, when the processing module 32 sends the probe packet to the virtual machine through the enabled receiving queues, it is specifically configured to: send the probe packet to the virtual machine through each of the multiple enabled receiving queues in turn, wherein after sending the probe packet to the previous enabled receiving queue, the probe packet is sent to the next enabled receiving queue after an interval of a set time interval. Optionally, the processing module 32 is further configured to: determine at least one normal receiving queue from the multiple enabled receiving queues according to the current detection result; configure the RSS value of the service data packet according to the round-trip time of each of the at least one normal receiving queue; and send the service data packet to the virtual machine through the normal receiving queue pointed to by the RSS value of the service data packet, so as to perform load balancing control on the at least one normal receiving queue. Optionally, when the processing module 32 configures the RSS value of the service data packet according to the round-trip time of each of the at least one normal receiving queue, it is specifically configured to: determine the maximum number of data packets allowed to be transmitted by each of the normal receiving queues in a unit of time according to the round-trip time of each of the at least one normal receiving queue; and for multiple service data packets to be transmitted in a unit of time, configure the RSS value of the service data packet so as to allocate the service data packet to the normal receiving queue pointed to by the corresponding RSS value, with the number of data packets allocated to the normal receiving queue not exceeding the maximum number of data packets allowed to be transmitted by the normal receiving queue as the target. Optionally, when the processing module 32 configures the RSS value of the service data packet according to the round-trip time of each of the at least one normal receiving queue, it is specifically configured to: select at least one target normal receiving queue with a round-trip time less than a preset round-trip time from the at least one normal receiving queue; determine the maximum number of data packets allowed to be transmitted by each of the target normal receiving queues in a unit of time according to the round-trip time of each of the at least one target normal receiving queue; and for multiple service data packets to be transmitted in a unit of time, configure the RSS value of the service data packet so as to allocate the service data packet to the target normal receiving queue pointed to by the corresponding RSS value, with the number of data packets allocated to the target normal receiving queue not exceeding the maximum number of data packets allowed to be transmitted by the target normal receiving queue as the target. The apparatus shown in FIG. 3 can perform the method performed by the virtual switch shown in the embodiment shown in FIG. 2, and the implementation principle and technical effects will not be repeated. FIG. 4 is a structural schematic diagram of a detection tool provided by an embodiment of the present disclosure.The detection tool can be composed of software and / or hardware, and can include a sending module 41 configured to send the current detection instruction to the virtual switch, a receiving module 42 configured to receive the current detection result returned by the virtual switch, and a processing module 43 configured to determine the abnormal receiving queue from the multiple receiving queues according to the round-trip time of the multiple receiving queues in the current detection result. Optionally, the processing module 43 is further configured to determine the abnormal receiving queue that is caused by the hot upgrade according to the detection result before the hot upgrade of the virtualization component and the detection result after the hot upgrade of the virtualization component. The detection tool shown in FIG. 4 can perform the method performed by the detection tool shown in the embodiment shown in FIG. 2, and the implementation principle and technical effects will not be repeated. In some processes described in the above embodiments and the accompanying drawings, a plurality of operations appearing in a certain order are included, but it should be clear that these operations can be executed in the order appearing in the present text or in parallel, and the serial numbers of the operations such as 203, 204, etc. are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes can include more or fewer operations, and the operations can be executed in sequence or in parallel. It should be noted that the "first", "second", etc. in the present text are used to distinguish different messages, devices, modules, etc., and do not represent the order, nor do "first" and "second" represent different types. It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present disclosure are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant national and regional laws, regulations and standards, and provide corresponding operation entrances for users to choose authorization or refusal. FIG. 5 is a structural schematic diagram of an electronic device provided by an embodiment of the present disclosure. As shown in FIG. 5, the electronic device includes a memory 51 and a processor 52; the memory 51 is configured to store a computer program and can be configured to store various other data to support operations on the computing platform. Examples of these data include instructions for any application or method operating on the computing platform, contact data, phonebook data, messages, images, videos, etc.The storage 51 can be implemented by any type of volatile or nonvolatile storage devices or a combination thereof, such as Static Random-Access Memory (SRAM), Electrically Erasable Programmable read only memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable read-only memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic or optical disk. The processor 52 is coupled to the storage 51 and used to execute computer programs in the storage 51, so as to perform the steps in the virtual network card detection method. Optionally, as shown in FIG. 5, the electronic device further includes a communication component 53, a display 54, a power supply component 55, an audio component 56 and other components. Only some components are shown in FIG. 5, which does not mean that the electronic device only includes the components shown in FIG. 5. In addition, the components in the dashed box in FIG. 5 are optional components, not mandatory components, which can be determined according to the product form of the electronic device. The electronic device of the embodiment can be implemented as a terminal device such as a desktop computer, a notebook computer, a smart phone or an IOT (Internet of things) device, or a server device such as a general server, a cloud server or a server array. If the electronic device of the embodiment is implemented as a terminal device such as a desktop computer, a notebook computer or a smart phone, it can include the components in the dashed box in FIG. 5; if the electronic device of the embodiment is implemented as a server device such as a general server, a cloud server or a server array, it can not include the components in the dashed box in FIG. 5. The detailed implementation process of the processor performing each action can be referred to the foregoing description of the method embodiment or the device embodiment, which will not be described here. Accordingly, the embodiment of the disclosure further provides a computer readable storage medium storing a computer program, which can implement each step performed by the electronic device in the foregoing method embodiment when the computer program is executed. Accordingly, the embodiment of the disclosure further provides a computer program product including computer programs / instructions, which can enable the processor to implement each step performed by the electronic device in the foregoing method embodiment when the computer programs / instructions are executed by the processor.The communication component is configured to facilitate wired or wireless communication between the device where the communication component is located and other devices. The device where the communication component is located can access a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G / LTE, 5G, or a combination thereof. In an example embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an example embodiment, the communication component further includes a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on Radio Frequency Identification (RFID) technology, The Infrared Data Association (IrDA) technology, Ultra Wide Band (UWB) technology, Bluetooth (BT) technology, and other technologies. The display includes a screen, which can include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense a touch, a slide, and a gesture on the touch panel. The touch sensor can not only sense a boundary of a touching or a sliding action, but also detect duration and intensity of the touching or sliding action. The power component provides power to various components of the device where the power component is located. The power component can include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power to the device where the power component is located. The audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC) that is configured to receive an external audio signal when the device where the audio component is located is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal can be further stored in the memory or transmitted via the communication component.In some embodiments, the audio component also includes a speaker for outputting audio signals. Those skilled in the art will appreciate that embodiments of the present disclosure can be provided as a method, a system, or a computer program product. Accordingly, the present disclosure can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure can take the form of a computer program product on one or more computer-readable storage media (including, but not limited to, disk memory, CD-ROMs, optical storage devices, etc.) embodying computer readable code. The disclosure is described in reference to the flow diagrams and / or block diagrams of the methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flow diagrams and / or block diagrams, and combinations of blocks in the flow diagrams and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flow diagrams and / or block diagrams. These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the functions specified in the flow diagrams and / or block diagrams. The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flow diagrams and / or block diagrams. In one typical configuration, a computing device includes one or more processors (Central Processing Unit, CPU), input / output interfaces, network interfaces, and memory. The memory can include non-persistent memory, random access memory (RAM), and / or non-volatile memory, such as read only memory (ROM) or flash memory, among others. The memory is an example of computer readable media.Computer-readable media includes permanent and non-permanent, movable and non-movable media that can realize information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition in this paper, computer-readable media does not include transitory media such as modulated data signals and carriers. It should also be noted that the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, product or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, product or device. Without more limitations, the element limited by the statement "including a...... " does not exclude the existence of other same elements in the process, method, product or device including the element. The above is only an embodiment of the present disclosure and is not intended to limit the present disclosure. The present disclosure can have various changes and variations for those skilled in the art. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present disclosure shall be included in the scope of claims of the present disclosure.

Claims

Claims 1. A method for detecting virtual network interface cards (NICs), applied to a virtual switch, the method comprising: In response to the current probe command from the probe tool, the activation status of multiple receive queues of the virtual network card is obtained, including enabled and disabled; Set the round-trip time of the disabled receive queue to a first default value, which indicates that the receive queue is disabled; For any enabled receive queue, a probe packet is sent to the virtual machine through the enabled receive queue, and the round-trip time of the enabled receive queue is determined based on whether the virtual machine responds to the probe packet. The detection results are returned to the detection tool so that the detection tool can identify the abnormal receiving queue among the multiple receiving queues based on the round-trip time of the multiple receiving queues in the detection results.

2. The method according to claim 1, wherein, The round-trip time of the enabled receive queue is determined based on whether or not the virtual machine responds to the response information sent by the probe packet. This includes: if the response information sent by the virtual machine is received, the round-trip time of the enabled receive queue is determined based on the sending time of the probe packet and the receiving time of the response information; if the response information sent by the virtual machine is not received, the round-trip time of the enabled receive queue is set to a second default value, the second default value indicating that the enabled receive queue is abnormal.

3. The method according to claim 2, wherein, Before sending the probe packet to the virtual machine through the enabled receive queue, the method further includes: constructing the probe packet, wherein the value of the destination IP address field in the probe packet is the main IP address of the virtual network interface card; and the value of the source IP address field in the probe packet is the private network gateway IP address of the virtual network interface card.

4. The method according to claim 2, wherein, Sending probe packets to the virtual machine through the enabled receive queue includes: configuring the receiver scaling RSS value of the probe packet as the queue identifier of the enabled receive queue in the probe packet; and sending the probe packet to the virtual machine through the corresponding enabled receive queue according to the RSS value.

5. The method according to claim 1, wherein, Returning the detection result to the detection tool includes: responding to the detection result acquisition instruction sent by the detection tool and returning the detection result to the detection tool, wherein the detection result acquisition instruction is sent by the detection tool after receiving the detection packet sending completion information returned by the virtual switch and waiting for a set time, and within the set time, all detection packets sent through all enabled receive queues have been responded to by the virtual machine.

6. The method according to claim 1, wherein, If there are multiple enabled receive queues, then probe packets are sent to the virtual machine through the enabled receive queues, including: sequentially sending probe packets to the virtual machine through each of the multiple enabled receive queues, wherein, after sending a probe packet to the previous enabled receive queue, a set time interval is used to send a probe packet to the next enabled receive queue. The receive queue sends probe packets.

7. The method according to claim 1, wherein, Also includes: Based on the results of this detection, at least one normal receiving queue was identified among the multiple enabled receiving queues; Configure the RSS value of the service data packet according to the round-trip time of each of at least one normal receiving queue; send the service data packet to the virtual machine through the normal receiving queue pointed to by the RSS value of the service data packet, so as to perform load balancing control on at least one normal receiving queue.

8. The method according to claim 7, wherein, Controlling the RSS value of service data packets according to the round-trip time of each of at least one normal receiving queue includes: determining the maximum number of data packets allowed to be transmitted by each of the at least one normal receiving queue within a unit time, based on the round-trip time of each of the at least one normal receiving queue; and configuring the RSS value of the service data packets for multiple service data packets to be transmitted within a unit time, with the objective that the number of data packets allocated to the normal receiving queue does not exceed the maximum number of data packets allowed to be transmitted corresponding to the normal receiving queue, so as to allocate the service data packets to the normal receiving queue pointed to by the corresponding RSS value.

9. The method according to claim 7, wherein, Controlling the RSS value of service data packets according to the round-trip time of each of at least one normal receiving queue includes: selecting at least one target normal receiving queue from the at least one normal receiving queue whose round-trip time is less than a preset round-trip time; determining the maximum number of data packets allowed to be transmitted per unit time for each target normal receiving queue according to the round-trip time of each of the at least one target normal receiving queue; and configuring the RSS value of the service data packets for multiple service data packets to be transmitted per unit time, with the goal that the number of data packets allocated to the target normal receiving queue does not exceed the maximum number of data packets allowed to be transmitted corresponding to the target normal receiving queue, so as to allocate the service data packets to the target normal receiving queue pointed to by the corresponding RSS value.

10. A method for detecting virtual network interface cards (NICs), applied to a detection tool, the method comprising: Send this probe command to the virtual switch; Receive the probe results returned by the virtual switch; Based on the round-trip time of multiple receiving queues in the results of this detection, the abnormal receiving queue is identified from the multiple receiving queues.

11. The method according to claim 10, wherein, Also includes: Based on the detection results before and after the hot upgrade of the virtualization component, the abnormal receiving queue caused by the hot upgrade is determined.

12. A cloud computing platform, comprising: The detection tool, virtual switch, and virtual machine, wherein the virtual network interface card of the virtual machine includes multiple receive queues; The detection tool is used to send the detection command to the virtual switch. Receive the current probe results returned by the virtual switch; Based on the round-trip time of multiple receiving queues in the current probe results, determine the abnormal receiving queue from the multiple receiving queues; 17 The virtual switch is configured to, in response to the current probe command, obtain the activation status of multiple receive queues of the virtual network card, wherein the activation status includes enabled and disabled; Set the round-trip time of the disabled receive queue to a first default value, which indicates that the receive queue is disabled; For any enabled receive queue, a probe packet is sent to the virtual machine through the enabled receive queue, and the round-trip time of the enabled receive queue is determined based on whether the virtual machine responds to the probe packet. Return the detection results to the detection tool.

13. An electronic device, comprising: Memory and processor; The memory is used to store computer programs; The processor is coupled to the memory for executing the computer program to perform the steps of the method according to any one of claims 1-9 or 10-11.

14. A computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the steps of the method according to any one of claims 1-9 or 10-11.

15. A computer program product comprising a computer program / instructions that, when executed by a processor, cause the processor to perform the steps of the method according to any one of claims 1-9 or 10-11.

Images