Processing method and device for network card in server, equipment and medium

Abstract

The embodiment of the invention provides a processing method and device for a network card in a server, equipment and a medium, and relates to the technical field of servers, and the method comprises the steps: obtaining an in-place signal of an interface riser card in a second computing node through a first computing node in response to a power-on signal of the server; if the in-place signal is the low-level signal, acquiring a first control signal of a first logic device in the first computing node and a second control signal of a first high-speed connector in the first computing node through the first computing node; performing priority ranking on the first control signal and the second control signal to obtain a control signal sequence for a shared interface network card in the first computing node; the first computing node obtains the second computing nodes from the computing nodes according to the control signal sequence, connection between the second computing nodes and the shared interface network card is sequentially established according to the generated computing node sequence, the purpose that the computing nodes share the same shared network card is achieved, and the cost of server components is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of servers, and in particular to a method, device, equipment and medium for processing a network card in a server. Background Art

[0002] With the development of information technology, servers are increasingly used. In industries such as government, finance, healthcare, and energy, there is an increasing demand for large core databases, virtualization integration, in-memory computing, and high-performance computing. Many services in modern society rely on high-performance computing (HPC), such as weather forecasting, DNA sequencing in biology, complex model deduction in physics, aerospace simulation in the industrial field, and artificial intelligence. These application scenarios require a large amount of computing power to simulate and deduce data through scientific computing models.

[0003] High-performance computing is often achieved through a computing cluster composed of a large number of high-performance computing hardware stacks. Among them, a multi-node server can support multiple computing nodes on a single server, and each computing node can support multiple CPUs. Therefore, multi-node servers are widely used in HPC scenarios and are usually equipped with high-bandwidth network cards to support big data throughput. Among them, OCP3.0 network cards are commonly used high-bandwidth network cards. At present, each computing node of a multi-node server needs to be equipped with an independent OCP3.0 network card for data communication between nodes and node servers, and it is impossible to realize the function of different computing nodes sharing Multi Host OCP3.0 network cards, which leads to high application component costs of multi-node servers, fixed server structures, and lack of structural flexibility and scalability. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a method, device, equipment and medium for processing a network card in a server, based on the in-place signal of the interface adapter card, to enable multiple computing nodes to share the same shared network card for communication, effectively reduce the component cost of the server, and improve the flexibility of the server structure. The specific technical solution is as follows:

[0005] In a first aspect of the present invention, a method for processing a network card in a server is provided. The server includes a plurality of computing nodes and a network card. Each computing node includes at least an interface connector, a high-speed connector, and a logic device. The network card includes a shared interface network card and an interface adapter card. Each network card is connected to a computing node via the interface connector. The method includes:

[0006] In response to a power-on signal of the server, acquiring, through the first computing node, a presence signal corresponding to an interface adapter card in a second computing node;

[0007] If the in-position signal is a low level signal, obtaining a first control signal of a first logic device in the first computing node and a second control signal of a first high-speed connector in the first computing node through the first computing node;

[0008] Prioritizing the first control signal and the second control signal by the first computing node to obtain a control signal sequence for a shared interface network card in the first computing node;

[0009] Acquire a plurality of second computing nodes from the computing node according to the control signal sequence through the first computing node, and generate a computing node sequence;

[0010] A connection between the second computing node and the shared interface network card is established in sequence according to the computing node sequence.

[0011] Optionally, the prioritizing the first control signal and the second control signal by the first computing node to obtain a control signal sequence for a shared interface network card in the first computing node includes:

[0012] Acquire a first priority of the first control signal and a second priority of the second control signal;

[0013] According to a preset sorting strategy, the first control signal and the second control signal are prioritized to obtain a control signal sequence for the shared interface network card in the first computing node.

[0014] Optionally, the second computing node is connected to a first high-speed connector of the first computing node through a high-speed cable, and the acquiring, through the first computing node, a presence signal corresponding to an interface adapter card in the second computing node in response to a power-on signal of the server includes:

[0015] In response to a power-on signal of the server, acquiring, through the first computing node, a cable connection signal of the first high-speed connector;

[0016] If the cable connection signal indicates that the first high-speed connector is connected to the high-speed cable, confirming that the presence signal is a low-level signal;

[0017] If the cable connection signal indicates that the first high-speed connector is not connected to the high-speed cable, it is confirmed that the presence signal is a high-level signal.

[0018] Optionally, after acquiring, through the first computing node, a presence signal corresponding to the interface adapter card in the second computing node, the method further includes:

[0019] If the presence signal is a low level signal, it is confirmed that the network card connection mode of the server is a shared connection mode;

[0020] If the presence signal is a high level signal, it is confirmed that the network card connection mode of the server is an independent connection mode;

[0021] Based on the network card connection mode, controlling the first logic device through the first computing node to send an adjustment signal corresponding to the network card connection mode to the shared connection network card;

[0022] If the adjustment signal is a shared connection signal, adjusting the working mode of the shared interface network card to a shared connection mode through the first computing node;

[0023] If the adjustment signal is an independent connection signal, the working mode of the shared interface network card is adjusted to an independent connection mode through the first computing node.

[0024] Optionally, after the first computing node controls the first logic device to send an adjustment signal corresponding to the network card connection mode to the shared connection network card based on the network card connection mode, the method further includes:

[0025] If the adjustment signal is an independent connection signal, obtaining a first control signal of a first logic device in the first computing node through the first computing node;

[0026] According to the first control signal, a connection is established between the first computing node and the shared connection network card.

[0027] Optionally, acquiring a plurality of second computing nodes from the computing node according to the control signal sequence through the first computing node and generating a computing node sequence includes:

[0028] Acquire, from the computing node through the first computing node, a plurality of second computing nodes corresponding to a second control signal in the control signal sequence;

[0029] extracting a first order of the first control signal and a second order of the second control signal from the control signal sequence through the first computing node;

[0030] Based on the first rank and the second rank, a computing node sequence is generated by the first computing node.

[0031] Optionally, the network card further includes an independent interface network card, and the method further includes:

[0032] In response to a power-on signal of the server, obtaining, through the second computing node, a gold finger signal of an interface connector on the second computing node, the gold finger signal being an insertion signal of an interface adapter card in the second computing node;

[0033] If the golden finger signal indicates that the interface connection card is inserted into the second computing node, the presence signal is controlled to be a low level signal, and the presence signal is sent to the first computing node through the second computing node;

[0034] If the golden finger signal indicates that the interface connection card is not inserted into the second computing node, the in-place signal is controlled to be a high-level signal, and a third control signal of the second logic device in the second computing node is obtained through the second computing node;

[0035] According to the third control signal, a connection is established between the second computing node and an independent connection network card on the second computing node.

[0036] In a second aspect of the present invention, a processing device for a network card in a server is provided. The server includes a plurality of computing nodes and a network card. Each computing node includes at least an interface connector, a high-speed connector, and a logic device. The network card includes a shared interface network card and an interface adapter card. Each network card is connected to a computing node via the interface connector. The device includes:

[0037] An in-place acquisition module, configured to obtain, in response to a power-on signal of the server, an in-place signal corresponding to an interface adapter card in a second computing node through a first computing node;

[0038] a signal acquisition module, configured to acquire, through the first computing node, a first control signal of a first logic device in the first computing node and a second control signal of a first high-speed connector in the first computing node if the in-position signal is a low-level signal;

[0039] a priority sorting module, configured to prioritize the first control signal and the second control signal through the first computing node to obtain a control signal sequence for a shared interface network card in the first computing node;

[0040] A sequence generation module, configured to obtain a plurality of second computing nodes from the computing node according to the control signal sequence through the first computing node, and generate a computing node sequence;

[0041] The first connection module is used to sequentially establish a connection between the second computing node and the shared interface network card according to the computing node sequence.

[0042] In the third aspect of the implementation of the present invention, there is also provided an electronic device, comprising: one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute any of the above-mentioned methods for processing a network card in a server.

[0043] In the fourth aspect of the implementation of the present invention, a non-volatile readable storage medium is also provided. When the instructions in the non-volatile readable storage medium are executed by the processor of an electronic device, the electronic device can execute any of the above-mentioned methods for processing a network card in a server.

[0044] The method for processing a network card in a server provided by an embodiment of the present invention obtains, through a first computing node, an in-place signal corresponding to an interface adapter card in a second computing node in response to a power-on signal of the server; if the in-place signal is a low-level signal, obtains, through the first computing node, a first control signal of a first logic device in the first computing node and a second control signal of a first high-speed connector in the first computing node; prioritizes the first control signal and the second control signal through the first computing node to obtain a control signal sequence for a shared interface network card in the first computing node; obtains, through the first computing node, a number of second computing nodes from the computing node according to the control signal sequence, and generates a computing node sequence; and establishes connections between the second computing nodes and the shared interface network card in sequence according to the computing node sequence. The embodiment of the present invention selects any computing node from the computing nodes of the server to insert a shared interface network card, and inserts interface adapter cards into the remaining computing nodes, judges the network card connection mode of the current server based on the in-place signal of the interface adapter card, receives control signals of the remaining computing nodes through the high-speed connector in the computing node, arbitrates the control signals of different computing nodes through the arbitration unit, realizes the access connection of different nodes to the shared interface network card, effectively reduces the hardware burden of the server, supports connection modes with different requirements through the same connection structure, and takes into account both data processing efficiency and hardware layout cost.

[0045] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0047] Figure 1It is a flowchart of a method for processing a network card in a server provided by an embodiment of the present invention;

[0048] Figure 2 It is a schematic diagram of an independent connection mode in a method for processing a network card in a server provided by an embodiment of the present invention;

[0049] Figure 3 It is a schematic diagram of an exemplary shared connection mode in a method for processing a network card in a server provided by an embodiment of the present invention;

[0050] Figure 4 It is a schematic diagram of an exemplary interface adapter card in a method for processing a network card in a server provided by an embodiment of the present invention;

[0051] Figure 5 It is a schematic diagram of an exemplary signal transmission on a computing node in a method for processing a network card in a server provided by an embodiment of the present invention;

[0052] Figure 6 It is a structural block diagram of a processing device of a network card in a server provided by an embodiment of the present invention;

[0053] Figure 7 It is a block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, some technical features involved in the embodiments of the present invention are explained and illustrated below:

[0056] High Performance Computing (HPC) refers to the use of supercomputers or computer clusters to solve complex scientific, engineering and business problems. HPC systems are usually composed of a large number of processors, memory and storage resources, capable of large-scale parallel computing to process massive data and perform complex simulations.

[0057] OCP (Open Compute Project) is an open source hardware project initiated by Facebook in 2011 to design more efficient and economical data center hardware. OCP's goal is to promote innovation and cost-effectiveness of data center hardware through open standards and shared designs.

[0058] OCP3.0 card refers to a network interface card (NIC) that complies with the OCP3.0 specification. As part of the OCP project, the OCP3.0 card is designed to provide high-bandwidth, low-latency data communications and is suitable for high-performance computing (HPC) and data center environments.

[0059] Multi Host OCP3.0 network card (shared interface network card) is a network card designed for multi-node servers. It supports multiple computing nodes to share the same network card for data communication. This design aims to improve resource utilization, reduce hardware costs, and simplify system architecture.

[0060] High-speed connectors are electronic connectors used for high-speed data transmission. They are usually used in computers, communication equipment, data centers, servers and other occasions that require high-bandwidth data transmission. These connectors need to meet specific electrical performance standards, such as signal integrity, impedance matching, crosstalk control and electromagnetic compatibility.

[0061] BMC (Board Management Controller) is an embedded microcontroller that is specially designed to monitor and manage the hardware components of a server. BMC can run independently of other parts of the server and communicate with external management systems through specific interfaces (such as IPMI, Redfish, etc.), providing functions such as system status monitoring, fault diagnosis, and firmware updates.

[0062] As an example, in order to achieve the high-performance computing required by various service areas, computing clusters composed of a large number of high-performance computing hardware are often used. In these clusters, different computing hardware usually use high-bandwidth network cards for data communication. At present, multi-node servers are equipped with OPC network cards to provide high computing power. However, since each computing node needs to be equipped with an independent OCP3.0 network card to achieve data communication between computing nodes and node servers, the component cost of the multi-node server is relatively high, and the connection structure between different nodes and network cards cannot be adjusted according to actual needs. The board structure equipped with computing nodes has low flexibility and scalability.

[0063] In this regard, in an embodiment of the present invention, any computing node is selected from the computing nodes of the server to insert a shared interface network card, and interface adapter cards are inserted into the remaining computing nodes. Based on the in-place signal of the interface adapter card, the network card connection mode of the current server is judged, and the control signals of the remaining computing nodes are received through the high-speed connector in the computing node. The control signals of different computing nodes are arbitrated through the arbitration unit to realize access connection of different nodes to the shared interface network card.

[0064] Reference Figure 1 , shows a flowchart of a method for processing a network card in a server provided in an embodiment of the present invention, wherein the server may include a plurality of computing nodes and network cards, the computing nodes correspond to the network cards one by one, and each computing node has the same hardware structure. Exemplarily, the computing node includes at least an interface connector, a high-speed connector, and a logic device, each network card is connected to the computing node via an interface connector on the computing node, and the network card includes a shared interface network card and an interface adapter card, and specifically may include the following steps:

[0065] S101 , in response to a power-on signal of a server, obtaining, through a first computing node, a presence signal corresponding to an interface adapter card in a second computing node.

[0066] In the embodiment of the present invention, based on the in-place signal of the interface adapter card in the second computing node, the network card connection mode of the current server can be determined, and the network card connection mode corresponding to the network card connection mode can be further executed, wherein the network card connection mode includes a shared connection mode and an independent connection mode. When the server is in the independent connection mode, refer to Figure 2 The computing node 1 in the server is equipped with independent connection network card 1, and the computing node N is equipped with independent connection network card N. Each computing node is independently equipped with an independent connection network card, resulting in a higher component cost for the multi-node server.

[0067] When the server system receives the power-on signal, it initializes various components in the server, which may include a baseboard management controller and several computing nodes in the server. In the embodiment of the present invention, when it is necessary to enter the shared connection mode, refer to Figure 3The present invention uses two computing nodes to realize shared network card connection as an example for explanation. Any computing node is selected from several computing nodes of the server as the first computing node, and a shared interface network card is inserted into the OCP connector of the first computing node. Preferably, the shared interface network card can select a Multi Host OCP3.0 network card that supports multi-node sharing. Accordingly, to realize the shared connection mode, an interface adapter card is inserted into the remaining computing nodes other than the first computing node, and the remaining computing nodes are connected to the first computing node through a high-speed cable to establish a transmission channel between the remaining computing nodes and the first computing node. For the convenience of distinction, in the embodiment of the present invention, the computing node inserted with the shared interface network card is called the first computing node, and the computing node inserted with the interface adapter card is called the second computing node. Before the network card is inserted, the first computing node and the second computing node are the same computing nodes. In each computing node, the interface connector (OCP connector) exchanges data with the central processing unit, and the interface connector also exchanges signals with the high-speed connector to obtain control signals for the network card. The network card is connected to the computing node through the interface connector.

[0068] Among them, the in-place signal is a logic level signal, which can be used to indicate whether the interface adapter card in the second computing node has been inserted into the corresponding slot or connector. The in-place signal includes a high level signal and a low level signal. Based on the reading of the in-place signal, it can be determined whether the interface adapter card is inserted in the second computing node, that is, whether the shared connection mode is currently entered.

[0069] In one example, the first computing node can also receive the in-place signal by obtaining the connection status of the high-speed cable on the first computing node. When entering the shared connection mode, while inserting the interface adapter card into the second computing node, the second computing node also needs to be connected to the first computing node through a high-speed cable, wherein one end of the high-speed cable is connected to the interface adapter card of the second computing node, and the other end is connected to the first high-speed connector of the first computing node. When receiving the power-on signal of the server, the first computing node can obtain the cable connection signal in the first high-speed connector to confirm whether there is a connected high-speed cable on the current first high-speed connector.

[0070] If the cable connection signal indicates that the first high-speed connector is connected to the high-speed cable, it indicates that there is currently a second computing node connected to the first computing node via a high-speed cable, and the first computing node will be connected to the second computing node only in the shared connection mode, that is, it can be confirmed that the in-place signal is a low-level signal, wherein the low-level signal is used to indicate that the current interface adapter card is in place, and accordingly, if the cable connection signal indicates that the first high-speed connector is not connected to the high-speed cable, it indicates that there is currently no second computing node connected to the first computing node via a high-speed cable, and at this time, the first computing node and the shared interface network card are in an independent connection state, that is, it can be confirmed that the in-place signal is a high-level signal, wherein the high-level signal is used to indicate that the current interface adapter card is not in place. Preferably, in the embodiment of the present invention, the high-speed connector on the computing node can select an MCIO high-speed connector to support high-speed data transmission.

[0071] S102: If the in-place signal is a low level signal, obtaining a first control signal of a first logic device in the first computing node and a second control signal of a first high-speed connector in the first computing node through the first computing node.

[0072] S103: Prioritize the first control signal and the second control signal through the first computing node to obtain a control signal sequence for the shared interface network card in the first computing node.

[0073] When the first computing node receives a low-level signal for the in-place signal, it indicates that an interface adapter card has been inserted into the current second computing node, i.e., the shared connection mode is entered; when the in-place signal is a high-level signal, it indicates that an interface adapter card has not been inserted into the current second computing node, and the server is in an independent connection mode. Since the first computing node and the second computing node are connected via a high-speed cable, and one end of the high-speed cable is connected to the first high-speed connector of the first computing node, the second control signal sent by the second computing node can be obtained by reading the transmission signal of the first high-speed connector, and at the same time, the first control signal of the first computing node is read from the baseboard management controller (BMC).

[0074] The first control signal and the second control signal are transmitted to the arbitration unit to perform signal arbitration. Exemplarily, the first control signal and the second control signal can be prioritized by the I2C arbitration unit in the first computing node to obtain a control signal sequence for the shared interface network card in the first computing node, and the control signal sequence is sent to the interface connector to perform access control on the shared interface network card in the interface connector.

[0075] In one example, the first high-speed connector of the first computing node can also receive the second reset signal of the second computing node, and at the same time, receive the first reset signal of the first computing node itself through the programmable logic device (CPLD), and the reset signal is used to control the reset operation of the shared interface network card in the first computing node, referring to Figure 4 The second computing node sets a high-speed connector in the interface adapter card, and the interface adapter card is connected to the interface connector through the gold finger of the interface connector. The second computing node sends the second control signal, the data interaction signal, and the second reset signal to the high-speed connector in the interface adapter card through the gold finger of the interface connector, and further transmits them to the high-speed cable through the interface adapter card and sends them to the first computing node. Based on the first reset signal and the second reset signal, the corresponding reset operation of the shared interface network card can be implemented.

[0076] Specifically, the control signal sequence can be obtained through the following steps:

[0077] Obtaining a first priority of the first control signal and a second priority of the second control signal;

[0078] According to a preset sorting strategy, the first control signal and the second control signal are prioritized to obtain a control signal sequence for the shared interface network card in the first computing node.

[0079] In an embodiment of the present invention, a priority can be set for the control signal of each computing node, or relevant parameters of the calculation priority can be calculated as needed. For example, the first control signal of the first computing node can be set to the first priority, and the priority of the second control signal can be set in turn according to the order of arrival of the control signals. The corresponding priority can also be set according to the urgency of the control signal, and the present invention is not limited here.

[0080] When multiple computing nodes request to access the shared interface network card at the same time, the I2C arbitration unit will prioritize these requests according to a preset sorting strategy, such as sorting the first control signal and the second control signal in order from high to low priority. The result of the sorting is a control signal sequence, which determines which computing node's BMC will first obtain access to the shared interface network card.

[0081] In one example, the first computing node can control the programmable logic device to send an adjustment signal corresponding to the network card connection mode based on the current network card connection mode, and adjust the working mode of the shared connection network card accordingly. Specifically, the adjustment signal corresponding to the shared connection mode is a shared connection signal, and the adjustment signal corresponding to the independent connection mode is an independent connection signal. When the adjustment signal sent by the logic device is a shared connection signal, it indicates that the server is in the shared connection mode, and the working mode of the shared interface network card can be adjusted to the shared connection mode through the first computing node; when the adjustment signal sent by the logic device is an independent connection signal, it indicates that the server is in the independent connection mode, and the working mode of the shared interface network card can be adjusted to the independent connection mode through the first computing node.

[0082] When a shared interface network card is inserted into the first computing node but is not connected to the other computing nodes through a high-speed cable, that is, the server is in an independent connection mode, the first control signal of the first logic device can also be obtained through the first computing node, and an independent connection between the first computing node and the shared connection network card can be established according to the first control signal.

[0083] S104, obtaining a plurality of second computing nodes from the computing nodes according to the control signal sequence through the first computing node, and generating a computing node sequence.

[0084] S105 , establishing a connection between the second computing node and the shared interface network card in sequence according to the computing node sequence.

[0085] The control signal sequence is a list of control signals obtained after sorting the first control signal and the second control signal according to priority, which can be used to guide the server how to process these control signals. The first computing node determines the second computing node that needs to be connected from the computing nodes of the server according to the generated control signal sequence, and prepares to establish a connection. Among them, the computing node sequence is a list of computing nodes obtained after sorting the computing nodes corresponding to the control signal sequence, which can be used to guide the server to establish connections between each computing node and the shared interface network card in the correct order.

[0086] Specifically, the first computing node can extract the second control signal from the control signal sequence, and obtain several second computing nodes corresponding to the second control signal in the control signal sequence from the computing node of the server, and the first computing node extracts the first order of the first control signal and the second order of the second control signal from the control signal sequence, sorts the control signals corresponding to the first order and the second order, and generates a computing node sequence, which effectively solves the power-on timing problem of the network card when multiple computing nodes share one shared interface network card, and realizes the management problem of the shared interface network card by the baseboard management controller in each computing node.

[0087] Exemplarily, the network card on the computing node may also include an independent connection network card. When the second computing node receives the power-on signal of the server, it can obtain the gold finger signal of the interface connector on the second computing node, wherein the interface connector is in contact with the interface connection card through the gold finger, and the gold finger signal can represent the insertion signal of the interface adapter card in the second computing node; when the gold finger signal indicates that the interface connection card is inserted into the second computing node, it can be determined that the shared connection mode is currently entered, and the in-place signal is controlled to be a low-level signal, and the second computing node sends the in-place signal to the first computing node through a high-speed cable; when the gold finger signal indicates that the interface connection card is not inserted into the second computing node, it can be determined that the independent connection mode is currently entered, and the in-place signal is controlled to be a high-level signal, and the second computing node sends the in-place signal to the first computing node through a high-speed cable. At the same time, in the independent connection mode, the second computing node is inserted with an independent interface network card, and the second computing node can directly obtain the third control signal of the second logic device in the second computing node, and establish a connection between the second computing node and the independent connection network card on the second computing node according to the third control signal.

[0088] In a possible embodiment, the network card connection method provided in the embodiment of the present invention can be implemented based on a specific connection structure in the server, referring to Figure 5 , shows a schematic diagram of signal transmission on an exemplary computing node in a processing method of a network card in a server provided by an embodiment of the present invention, the data channels of the interface connector can be numbered to obtain channels 0-15, wherein channels 0-7 of the interface connector are connected to the central processing unit of the computing node to realize data interaction, and channels 0-7 of the interface connector are connected to the PCIE with a bandwidth of x8 defined on the high-speed connector to receive control signals transmitted by other computing nodes; when the second computing node confirms the insertion of the interface adapter card, a presence signal is sent to the first high-speed connector of the first computing node through a high-speed cable, which is transmitted to the first logic device by the first high-speed connector, and the first logic device sends an adjustment signal to the interface connector according to the presence signal to adjust the working mode of the shared interface network card; based on the same transmission mode, the second computing node can also send a second reset signal to the first high-speed connector of the first computing node through a high-speed cable, and the first high-speed connector transmits the second reset signal to the interface connector, exemplarily, the first reset signal can be transmitted to the A11pin of the interface connector, and the first reset signal of the first computing node itself can be obtained from the first logic device, and the shared interface network card is reset and controlled based on the first reset signal and the second reset signal;

[0089] Among them, when the first computing node detects that the first high-speed connector is connected to the interface adapter cards in the remaining computing nodes through a high-speed cable, the in-place signal changes from a high-level signal to a low-level signal, indicating that it is in a shared connection mode, that is, the first computing node currently supports a shared interface network card. When the in-place signal is high, the control signal sequence output by the I2C arbitration unit after arbitration can be output to the A7 / A8 Pin of the interface connector. Through this design, the management configuration of the independent interface network card in the second computing node is realized. When the in-place signal is low, the second control signal of the second computing node can be connected to the reserved PIN of the interface connector, such as B68 / B69, and the second control signal is transmitted to the first computing node through the interface connector, so as to realize the management configuration of the shared interface network card in the first computing node by the second computing node.

[0090] The method for processing a network card in a server provided by an embodiment of the present invention obtains, through a first computing node, an in-place signal corresponding to an interface adapter card in a second computing node in response to a power-on signal of the server; if the in-place signal is a low-level signal, obtains, through the first computing node, a first control signal of a first logic device in the first computing node and a second control signal of a first high-speed connector in the first computing node; prioritizes the first control signal and the second control signal through the first computing node to obtain a control signal sequence for a shared interface network card in the first computing node; obtains, through the first computing node, a number of second computing nodes from the computing node according to the control signal sequence, and generates a computing node sequence; and establishes connections between the second computing nodes and the shared interface network card in sequence according to the computing node sequence. The embodiment of the present invention selects any computing node from the computing nodes of the server to insert a shared interface network card, and inserts interface adapter cards into the remaining computing nodes, judges the network card connection mode of the current server based on the in-place signal of the interface adapter card, receives control signals of the remaining computing nodes through the high-speed connector in the computing node, arbitrates the control signals of different computing nodes through the arbitration unit, realizes the access connection of different nodes to the shared interface network card, effectively reduces the hardware burden of the server, and realizes the connection mode supporting different requirements in the same board card through the design of the connection structure, thereby taking into account both the data processing efficiency and the hardware layout cost.

[0091] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0092] Reference Figure 6, shows a structural block diagram of a processing device of a network card in a server provided by an embodiment of the present invention, wherein the server includes a plurality of computing nodes and network cards, each of the computing nodes includes at least an interface connector, a high-speed connector and a logic device, the network card includes a shared interface network card and an interface adapter card, each of the network cards is connected to a computing node via the interface connector, and specifically may include the following modules:

[0093] A presence acquisition module 601, configured to acquire, in response to a power-on signal of the server, a presence signal corresponding to an interface adapter card in a second computing node through a first computing node;

[0094] A signal acquisition module 602, configured to acquire, through the first computing node, a first control signal of a first logic device in the first computing node and a second control signal of a first high-speed connector in the first computing node if the in-position signal is a low-level signal;

[0095] A priority sorting module 603, configured to perform priority sorting on the first control signal and the second control signal through the first computing node to obtain a control signal sequence for a shared interface network card in the first computing node;

[0096] A sequence generation module 604, configured to obtain a plurality of second computing nodes from the computing node according to the control signal sequence through the first computing node, and generate a computing node sequence;

[0097] The network card connection module 605 is used to establish the connection between the second computing node and the shared interface network card in sequence according to the computing node sequence.

[0098] Furthermore, the priority sorting module 603 includes:

[0099] A priority acquisition module, used to acquire a first priority of the first control signal and a second priority of the second control signal;

[0100] The signal sequence acquisition module is used to prioritize the first control signal and the second control signal according to a preset sorting strategy to obtain a control signal sequence for the shared interface network card in the first computing node.

[0101] Further, the second computing node is connected to the first high-speed connector of the first computing node through a high-speed cable, and the in-place acquisition module 601 includes:

[0102] a cable connection confirmation module, configured to obtain a cable connection signal of the first high-speed connector through the first computing node in response to a power-on signal of the server;

[0103] a low-level acquisition module, configured to confirm that the presence signal is a low-level signal if the cable connection signal indicates that the first high-speed connector is connected to the high-speed cable;

[0104] The high-level acquisition module is configured to confirm that the presence signal is a high-level signal if the cable connection signal indicates that the first high-speed connector is not connected to the high-speed cable.

[0105] Furthermore, the device also includes:

[0106] A sharing mode confirmation module, used for confirming that the network card connection mode of the server is a sharing connection mode if the presence signal is a low level signal;

[0107] An independent mode confirmation module, used for confirming that the network card connection mode of the server is an independent connection mode if the presence signal is a high level signal;

[0108] an adjustment signal sending module, configured to control the first logic device to send an adjustment signal corresponding to the network card connection mode to the shared connection network card through the first computing node based on the network card connection mode;

[0109] a sharing adjustment module, configured to adjust the working mode of the shared interface network card to a shared connection mode through the first computing node if the adjustment signal is a shared connection signal;

[0110] The independent adjustment module is used to adjust the working mode of the shared interface network card to an independent connection mode through the first computing node if the adjustment signal is an independent connection signal.

[0111] Furthermore, the device also includes:

[0112] a first independent signal acquisition module, configured to acquire, through the first computing node, a first control signal of a first logic device in the first computing node if the adjustment signal is an independent connection signal;

[0113] The first independent connection module is used to establish a connection between the first computing node and the shared connection network card according to the first control signal.

[0114] Further, the sequence generation module 604 includes:

[0115] A second node acquisition module, configured to acquire, from the computing node through the first computing node, a plurality of second computing nodes corresponding to the second control signal in the control signal sequence;

[0116] A rank extraction module, configured to extract a first rank of the first control signal and a second rank of the second control signal from the control signal sequence through the first computing node;

[0117] A node sequence generation module is used to generate a computing node sequence through the first computing node based on the first ranking and the second ranking.

[0118] Furthermore, the network card further includes an independent interface network card, and the device further includes:

[0119] A golden finger signal acquisition module, configured to respond to a power-on signal of the server and acquire a golden finger signal of an interface connector on the second computing node through the second computing node, wherein the golden finger signal is an insertion signal of an interface adapter card in the second computing node;

[0120] An in-place sending module, configured to control the in-place signal to be a low-level signal if the golden finger signal indicates that the interface connection card is inserted into the second computing node, and send the in-place signal to the first computing node through the second computing node;

[0121] A second independent signal acquisition module, configured to control the in-place signal to be a high-level signal if the golden finger signal indicates that the interface connection card is not inserted into the second computing node, and acquire a third control signal of the second logic device in the second computing node through the second computing node;

[0122] The second independent connection module is used to establish a connection between the second computing node and the independent connection network card on the second computing node according to the third control signal.

[0123] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0124] refer to Figure 7 The embodiment of the present invention further provides an electronic device, including a processor 701, a communication interface 702, a memory 703 and a communication bus 704, wherein the processor 701, the communication interface 702 and the memory 703 communicate with each other via the communication bus 704.

[0125] Memory 703, used for storing computer programs;

[0126] The processor 701 is used to execute the program stored in the memory 703 to implement the following steps:

[0127] In response to a power-on signal of the server, acquiring, through the first computing node, a presence signal corresponding to the interface adapter card in the second computing node;

[0128] If the in-position signal is a low level signal, obtaining a first control signal of a first logic device in the first computing node and a second control signal of a first high-speed connector in the first computing node through the first computing node;

[0129] Prioritizing the first control signal and the second control signal by the first computing node to obtain a control signal sequence for the shared interface network card in the first computing node;

[0130] Acquire a plurality of second computing nodes from the computing nodes according to the control signal sequence through the first computing node, and generate a computing node sequence;

[0131] The connection between the second computing node and the shared interface network card is established in sequence according to the computing node sequence.

[0132] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0133] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0134] The embodiment of the present invention further provides a non-volatile readable storage medium. When the instructions in the non-volatile readable storage medium are executed by the processor of the electronic device, the electronic device can perform the various processes of the above-mentioned routing path determination method embodiment and achieve the same technical effect. To avoid repetition, it is not repeated here. The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0135] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0136] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0137] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0138] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the embodiments of the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0139] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for processing a network card in a server, characterized in that: The server includes a plurality of computing nodes and a network card, each of the computing nodes includes at least an interface connector, a high-speed connector, and a logic device, the network card includes a shared interface network card and an interface adapter card, each of the network cards is connected to a computing node via the interface connector, and the method includes: In response to a power-on signal of the server, acquiring, through the first computing node, a presence signal corresponding to an interface adapter card in a second computing node; If the in-position signal is a low level signal, obtaining a first control signal of a first logic device in the first computing node and a second control signal of a first high-speed connector in the first computing node through the first computing node; Prioritizing the first control signal and the second control signal by the first computing node to obtain a control signal sequence for a shared interface network card in the first computing node; Acquire a plurality of second computing nodes from the computing node according to the control signal sequence through the first computing node, and generate a computing node sequence; A connection between the second computing node and the shared interface network card is established in sequence according to the computing node sequence.

2. The method according to claim 1, characterized in that The step of prioritizing the first control signal and the second control signal by the first computing node to obtain a control signal sequence for a shared interface network card in the first computing node includes: Acquire a first priority of the first control signal and a second priority of the second control signal; According to a preset sorting strategy, the first control signal and the second control signal are prioritized to obtain a control signal sequence for the shared interface network card in the first computing node.

3. The method according to claim 1, characterized in that The second computing node is connected to a first high-speed connector of the first computing node through a high-speed cable, and the obtaining, through the first computing node, a presence signal corresponding to an interface adapter card in the second computing node in response to a power-on signal of the server includes: In response to a power-on signal of the server, acquiring, through the first computing node, a cable connection signal of the first high-speed connector; If the cable connection signal indicates that the first high-speed connector is connected to the high-speed cable, confirming that the presence signal is a low-level signal; If the cable connection signal indicates that the first high-speed connector is not connected to the high-speed cable, it is confirmed that the presence signal is a high-level signal.

4. The method according to claim 3, characterized in that After acquiring the presence signal corresponding to the interface adapter card in the second computing node through the first computing node, the method further includes: If the presence signal is a low level signal, it is confirmed that the network card connection mode of the server is a shared connection mode; If the in-place signal is a high-level signal, it is confirmed that the network card connection mode of the server is an independent connection mode; Based on the network card connection mode, controlling the first logic device through the first computing node to send an adjustment signal corresponding to the network card connection mode to the shared connection network card; If the adjustment signal is a shared connection signal, adjusting the working mode of the shared interface network card to a shared connection mode through the first computing node; If the adjustment signal is an independent connection signal, the working mode of the shared interface network card is adjusted to an independent connection mode through the first computing node.

5. The method according to claim 4, characterized in that After the first computing node controls the first logic device to send an adjustment signal corresponding to the network card connection mode to the shared connection network card based on the network card connection mode, the method further includes: If the adjustment signal is an independent connection signal, obtaining a first control signal of a first logic device in the first computing node through the first computing node; According to the first control signal, a connection is established between the first computing node and the shared connection network card.

6. The method according to claim 1, characterized in that The acquiring a plurality of second computing nodes from the computing node according to the control signal sequence through the first computing node and generating a computing node sequence includes: acquiring, from the computing node through the first computing node, a plurality of second computing nodes corresponding to a second control signal in the control signal sequence; extracting a first order of the first control signal and a second order of the second control signal from the control signal sequence through the first computing node; Based on the first rank and the second rank, a computing node sequence is generated by the first computing node.

7. The method according to claim 1, characterized in that The network card further includes an independent interface network card, and the method further includes: In response to a power-on signal of the server, obtaining, through the second computing node, a gold finger signal of an interface connector on the second computing node, the gold finger signal being an insertion signal of an interface adapter card in the second computing node; If the golden finger signal indicates that the interface connection card is inserted into the second computing node, the presence signal is controlled to be a low level signal, and the presence signal is sent to the first computing node through the second computing node; If the golden finger signal indicates that the interface connection card is not inserted into the second computing node, the in-place signal is controlled to be a high-level signal, and a third control signal of the second logic device in the second computing node is obtained through the second computing node; According to the third control signal, a connection is established between the second computing node and an independent connection network card on the second computing node.

8. A processing device for a network card in a server, characterized in that: The server includes a plurality of computing nodes and network cards, each of the computing nodes includes at least an interface connector, a high-speed connector and a logic device, the network card includes a shared interface network card and an interface adapter card, each of the network cards is connected to a computing node via the interface connector, and the device includes: An in-place acquisition module, configured to obtain, in response to a power-on signal of the server, an in-place signal corresponding to an interface adapter card in a second computing node through a first computing node; a signal acquisition module, configured to acquire, through the first computing node, a first control signal of a first logic device in the first computing node and a second control signal of a first high-speed connector in the first computing node if the in-position signal is a low-level signal; a priority sorting module, configured to prioritize the first control signal and the second control signal through the first computing node to obtain a control signal sequence for a shared interface network card in the first computing node; A sequence generation module, configured to obtain a plurality of second computing nodes from the computing node according to the control signal sequence through the first computing node, and generate a computing node sequence; The first connection module is used to sequentially establish a connection between the second computing node and the shared interface network card according to the computing node sequence.

9. An electronic device, comprising: one or more processors; Memory; One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured to execute the processing method of the network card in the server as described in any one of claims 1 to 7.

10. A non-volatile readable storage medium, when instructions in the non-volatile readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method for processing a network card in a server according to any one of claims 1 to 7.

Images