Computing power resource management method and device, equipment, medium and product

Abstract

The application relates to the computer field and provides a computing power resource management method, device, equipment, medium and product. The method is applied to a computing power resource management gateway, and the method comprises the following steps: translating a target resource parameter into a target resource parameter prefix based on a preset parameter translation strategy; sending a data packet carrying the target resource parameter prefix to a computing node comprising the target resource parameter prefix in a resource pool; and determining that the computing node is available in the case that the resource state of the computing node meets a preset state. According to the application, the target resource parameter is translated into the target resource parameter prefix through the parameter translation strategy, and it is determined whether the resource state of the computing node meets the preset state, so that the computing node meeting the current resource parameter demand and capable of being used can be quickly located, the search efficiency is improved, and the management efficiency of the computing power resource is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a computing power resource management method and device, equipment, medium and product. BACKGROUND

[0002] In the existing computing power resource management method, the computing power nodes in the resource pool are manually or randomly assigned an Internet Protocol version 6 (IPv6) address, and the address and resource parameters of the computing power nodes are registered in a database. When searching for resources, the corresponding IP address is found by searching the database according to the target resource parameters. The search process involves many links, and the positioning efficiency of the computing nodes is low. In addition, when the resource parameters of the computing nodes are updated, the management personnel need to manually configure and request the statistical database to update the related parameters of the computing nodes. The updating efficiency is low.

[0003] Therefore, how to quickly locate the computing nodes that meet the target resource parameters and improve the parameter updating efficiency has become a technical problem to be solved in the industry. SUMMARY

[0004] The present application provides a computing power resource management method, device, equipment, medium and product to solve the technical problem of how to quickly locate the computing nodes that meet the target resource parameters and improve the parameter updating efficiency in the prior art.

[0005] In a first aspect, the present application provides a computing power resource management method applied to a computing power resource management gateway, the method comprising:

[0006] translating a target resource parameter into a target resource parameter prefix based on a preset parameter translation strategy;

[0007] sending a data packet carrying the target resource parameter prefix to a computing node in a resource pool that includes the target resource parameter prefix;

[0008] determining that the computing node is available if the resource state of the computing node meets a preset state.

[0009] In some embodiments, the sending of the data packet carrying the target resource parameter prefix to the computing node in the resource pool that includes the target resource parameter prefix comprises:

[0010] obtaining a resource pool prefix of the resource pool and initializing a conflict prevention prefix;

[0011] searching the computing node in the resource pool based on the resource pool prefix and the target resource parameter prefix;

[0012] sending the data packet to the computing node and assigning the anti-collision prefix to the computing node; the anti-collision prefix is used to prevent the address of the computing node from colliding with an existing address in the resource pool.

[0013] In some embodiments, the computing power resource management gateway is communicatively connected with a computing node agent of a computing node in the resource pool and a routing node agent of a routing node in the resource pool; the method further comprises:

[0014] In the case where the computing node agent of any computing node monitors that the resource parameter of the any computing node has changed, receiving the anti-collision prefix before the parameter change of the any computing node sent by the routing node agent;

[0015] marking the anti-collision space of the anti-collision prefix before the parameter change of the any computing node as free;

[0016] In the case where the resource parameter of any computing node is monitored to have changed, the node prefix of the any computing node is updated based on the first computing node agent of the any computing node, the routing node and the parameter forwarding function; the node prefix includes the resource pool prefix, the resource parameter prefix and the anti-collision prefix of the any computing node.

[0017] In some embodiments, the change protocol of the node prefix is configured based on the routing node executing the parameter forwarding function and the latest anti-collision prefix and the latest resource parameter prefix of the any computing node;

[0018] The parameter forwarding function is used to forward the latest resource parameter prefix in the node data packet sent by the first computing node agent to the change port of the change protocol;

[0019] The node data packet includes a type-length-value field and a segment list; the type-length-value field carries the protocol encoding of the change protocol and the latest resource parameter prefix; the segment list includes the segment identifier of the routing node;

[0020] The latest anti-collision prefix is obtained based on the minimum value in the free part of the anti-collision space.

[0021] In a second aspect, the present application provides a computing power resource management method, applied to a computing power resource management device, the computing power resource management device including a computing node agent arranged in a computing node of a resource pool, a routing node agent arranged in a routing node of the resource pool and a computing power resource management gateway arranged in the resource pool, the method comprising:

[0022] receive, based on the computing node agent, a data packet carrying a target resource parameter prefix sent by the computing power resource management gateway;

[0023] determine that the computing node corresponding to the computing node agent is available in a case where a resource state of the computing node corresponding to the computing node agent meets a preset state;

[0024] The resource parameter prefix of the computing node corresponding to the computing node agent matches the target resource parameter prefix. The target resource parameter prefix is obtained by translating a target resource parameter based on a preset parameter translation strategy.

[0025] The computing power resource management gateway is the computing power resource management gateway described above.

[0026] In some embodiments, the method further includes:

[0027] In a case where a change in a resource parameter of any computing node is monitored, translate, based on a computing node agent corresponding to the any computing node, a latest resource parameter of the any computing node to obtain a latest resource parameter prefix of the any computing node;

[0028] encapsulate, based on the computing node agent, a node data packet of the computing node and send the node data packet to a routing node; the node data packet includes a type-length-value field and a segment list; the type-length-value field carries a protocol encoding of a change protocol and the latest resource parameter prefix; the segment list includes a segment identifier of the routing node;

[0029] execute, based on a routing node agent of the routing node, a parameter forwarding function and configure the change protocol based on a latest anti-collision prefix and a latest resource parameter prefix of the any computing node to update a node prefix of the any computing node; the latest anti-collision prefix is obtained based on a minimum value in a free part of an anti-collision space.

[0030] In a third aspect, the present application provides a computing power resource management device applied to a computing power resource management gateway, the device including:

[0031] a translation module configured to translate a target resource parameter to a target resource parameter prefix based on a preset parameter translation strategy;

[0032] a sending module configured to send a data packet carrying the target resource parameter prefix to a computing node including the target resource parameter prefix in a resource pool;

[0033] a positioning module configured to determine that the computing node is available in a case where a resource state of the computing node meets a preset state.

[0034] In a fourth aspect, an electronic device is provided, which includes a memory and a processor, the memory storing a computer program, and the processor being configured to implement the above method by executing the computer program.

[0035] In a fifth aspect, a non-transitory computer-readable storage medium is provided, which stores a computer program, and the computer program, when executed by a processor, implements the above method.

[0036] In a sixth aspect, a computer program product is provided, which includes a computer program, and the computer program, when executed by a processor, implements the above method.

[0037] The computing power resource management method, device, equipment, medium and product provided by the embodiments of the present application can convert the target resource parameter into a target resource parameter prefix through the set parameter conversion strategy, and can identify the computing node matched with the target resource parameter prefix. By judging whether the resource state of the computing node meets the preset state, the computing node meeting the current resource parameter demand and available can be quickly located, the search efficiency is improved, and the management efficiency of the computing power resource is improved. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0039] Figure 1 One of the flowcharts of the computing power resource management method provided by the embodiments of the present application;

[0040] Figure 2 The structural diagram of the resource pool topology structure provided by the embodiments of the present application;

[0041] Figure 3 The structural diagram of the computing power resource management device provided by the embodiments of the present application;

[0042] Figure 4 The schematic diagram of the resource parameter conversion provided by the embodiments of the present application;

[0043] Figure 5 One of the structural diagrams of the computing node locator provided by the embodiments of the present application;

[0044] Figure 6 The second structural diagram of the computing node locator provided by the embodiments of the present application;

[0045] Figure 7 Structure diagram of the type length value field provided for an embodiment of the present application;

[0046] Figure 8 Structure diagram of the type length value field provided for an embodiment of the present application;

[0047] Figure 9 Flowchart of the computing resource management method provided for an embodiment of the present application;

[0048] Figure 10 Structure diagram of the computing resource management device provided for an embodiment of the present application;

[0049] Figure 11 Structure diagram of the computing resource management device provided for an embodiment of the present application;

[0050] Figure 12 Structure diagram of the electronic device provided for an embodiment of the present application. DETAILED DESCRIPTION

[0051] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0052] It should be noted that the terms "first", "second", and the like in the present application are used to distinguish similar objects, and do not necessarily indicate specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or modules does not necessarily limit to those steps or modules clearly listed, but can include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices.

[0053] Figure 1 Structure diagram of the computing resource management method provided for an embodiment of the present application, as shown in Figure 1 The method includes steps 110, 120 and 130. The method flow steps are only one possible implementation of the present application.

[0054] In step 110, the target resource parameter is translated into a target resource parameter prefix based on a preset parameter translation strategy.

[0055] Specifically, the computing resource management method provided by the embodiments of the present application is applicable to a computing resource management device. The execution subject of the computing resource management method provided by the embodiments of the present application is a computing resource management gateway, which can be a component running in the computing resource management device.

[0056] Figure 2 The structural diagram of the resource pool topology structure provided by the embodiments of the present application is shown in FIG. 1. Figure 2 As shown in FIG. 1, the resource pool is a resource cluster formed according to a certain business background, which provides computing resources. Each resource pool includes a plurality of routing nodes and computing nodes.

[0057] The computing node of the embodiments of the present application is a node providing computing capability, which supports Segment Routing IPv6 (SRv6) based on an IPv6 forwarding plane. The routing node of the embodiments of the present application provides routing capability, which can route to and communicate with one or more computing nodes, and supports SRv6.

[0058] The resource pool is a separate SRv6 domain for networking and computing resource management, which contains a plurality of routing nodes and computing nodes. The locator in the Segment Identifier (SID) of each node has uniqueness, which can ensure that a specific node can be uniquely located when selecting computing resources and routing, and no conflict will occur. In the resource pool, the routing node Rm and the plurality of computing nodes Ck have a communication relationship, and the communication content includes but is not limited to the change of the locator. The locator refers to the locator part in the SID in the SRv6 domain.

[0059] Figure 3 The structural diagram of the computing resource management device provided by the embodiments of the present application is shown in FIG. 2. Figure 3 As shown in FIG. 2, the computing resource management device includes a computing resource management gateway deployed in the resource pool, a computing node agent deployed in the computing node, and a routing node agent deployed in the routing node.

[0060] The computing resource management gateway includes a parameter translation strategy management module, a computing resource search module, and a conflict prevention management module.

[0061] The parameter translation strategy management module is configured to deploy a parameter translation strategy, store a translation relationship table of resource parameters, and distribute the translation relationship table to a parameter translation module of a computing node agent; the computing resource searching module is configured to search for a computing node according to a target resource parameter; and the conflict prevention management module is configured to record an idle conflict prevention space in a resource pool, and allocate a conflict prevention prefix to a conflict prevention module of a routing node agent according to a principle from low to high.

[0062] The parameter translation strategy is a strategy for encoding data of a resource parameter to form a resource parameter prefix in an SRv6 locator. The resource parameter is a parameter for describing a resource condition of a computing node, such as memory, disk space, an operating system type, and a number of cores. The resource parameter prefix can be content of a specific segment in an IPv6 address formed by combining the resource parameter through translation and space compression.

[0063] The computing node agent includes a resource update detection module, a parameter translation module, and a data transceiver module.

[0064] The resource update detection module is configured to monitor a resource update condition of the computing node, and notify the parameter translation module of a new resource parameter, while grasping a resource parameter and a resource state of the computing node. The parameter translation module is configured to translate the resource parameter to form a resource parameter prefix. The data transceiver module is configured to cooperate with a computing resource management to perform data packet encapsulation and data transceiving.

[0065] The resource update refers to a process in which a resource parameter of the computing node changes (for example, disk space changes or memory space changes), and a new IPv6 address needs to be applied for and notified to a routing node.

[0066] The routing node agent includes a conflict prevention module, an instruction execution module, a data transceiver module, and a change management module.

[0067] The conflict prevention module is configured to allocate a conflict prevention prefix for a computing node that applies for a locator change. The instruction execution module is configured to execute a parameter forwarding function instruction, such as forwarding a resource parameter prefix to a locator change protocol. The data transceiver module is configured to perform data transceiving and parsing. The change management module is configured to manage a working process of the locator change protocol, and configure a resource pool prefix for the locator change protocol and a conflict prevention prefix provided by the conflict prevention module.

[0068] The parameter forwarding function is a type of Function in a SID under an SRv6 protocol, and is used to instruct a current node to forward a parameter to another protocol or port.

[0069] The aforementioned modules can be combined into a single module, or any one of these modules can be split into multiple modules. Alternatively, at least some functionality of one or more of these modules can be combined with at least some functionality of other modules and implemented in a single module.

[0070] Figure 4 This is a schematic diagram illustrating the translation of resource parameters provided in the embodiments of this application, such as... Figure 4 As shown, the parameter translation strategy in this embodiment can be to convert a set of resource parameters into a set of numbers in hexadecimal form according to a set resource parameter translation relationship table. The strategy encodes a limited number of operating system types, discretizes continuous disk space and memory space, and encodes the data according to the discrete interval in which it resides.

[0071] The parameter translation strategy can transform resource parameters into part of the SID, giving the SID semantic meaning and enabling the rapid location of computing nodes with a specified combination of parameters during the search for computing nodes with specific resource parameters.

[0072] The computing resource search module in the computing resource management gateway can determine the target resource parameters based on resource requirements and start the search process to find computing nodes that meet the current resource requirements. The parameter translation strategy management module converts the target resource parameters into target resource parameter prefixes through parameter translation strategies and generates data packets carrying the target resource parameter prefixes.

[0073] Step 120: Send the data packet carrying the target resource parameter prefix to the computing node in the resource pool that includes the target resource parameter prefix.

[0074] Specifically, Figure 5 This is one of the structural diagrams of the computing node locator provided in the embodiments of this application, such as... Figure 5 As shown, the locator can include a resource pool prefix, a resource parameter prefix, and an anti-collision prefix. Nodes within the same resource pool have the same resource pool prefix, which has a consistent and fixed length of pre_len_1. Resource parameters are converted into a part of the locator in the SID through a resource translation strategy to form the resource parameter prefix, which also has a consistent and fixed length of pre_len_2. The locator length for calculating a node's SID can be 64 bits.

[0075] The resource pool prefix is ​​used to identify the resource pool, and the anti-collision prefix is ​​used to avoid address conflicts.

[0076] During the search for compute nodes, data packets are sent to the node corresponding to the locator. That is, the search is conducted for compute nodes that match the prefix of the target resource parameters, and the generated data packets are sent to that compute node.

[0077] Step 130, in the case that the resource state of the computing node meets the preset state, determining that the computing node is available.

[0078] Specifically, the computing resource searching module can set a group of threshold values for each resource parameter in the translation relationship table, and when each resource parameter of the computing node is greater than or equal to the threshold value, it indicates that the computing node is available.

[0079] The computing node currently receiving the data packet can be inquired, and the resource update detection module of the computing node agent feeds back the availability of each resource of the computing node, and compares the availability of each resource with the set threshold value. If each resource parameter of the computing node is greater than or equal to the threshold value, it indicates that the resource state of the computing node meets the preset state, and the search can be stopped and a signal of search success is fed back.

[0080] The computing resource management method provided by the embodiment of the application can convert the target resource parameter into a target resource parameter prefix through the set parameter translation strategy, can identify the computing node matched with the target resource parameter prefix, and can quickly locate the computing node meeting the current resource parameter demand and available by judging whether the resource state of the computing node meets the preset state, thereby improving the search efficiency and improving the management efficiency of the computing resource.

[0081] It should be noted that each embodiment of the application can be freely combined, the order can be changed or the embodiments can be executed independently, and the fixed execution order is not required.

[0082] In some embodiments, step 120 comprises:

[0083] Obtaining the resource pool prefix of the resource pool and initializing the anti-collision prefix;

[0084] Searching the computing node in the resource pool based on the resource pool prefix and the target resource parameter prefix;

[0085] Sending the data packet to the computing node and allocating the anti-collision prefix to the computing node; the anti-collision prefix is used to prevent the address of the computing node from conflicting with the existing address in the resource pool.

[0086] Specifically, the computing resource searching module can determine the resource pool prefix and the target resource parameter prefix, initialize the anti-collision prefix, search the computing node from low to high, and allocate the anti-collision prefix to the computing node.

[0087] Figure 6 The structure diagram two of the computing node locator provided by the embodiment of the application is as follows: Figure 6As shown, the resource pool prefix length pre_len_1 in the locator of the computing node is 40 bits, which is at the beginning of the locator. The resource parameter prefix length pre_len_2 is 16 bits, which is second, and each 4-bit bit represents the encoding space of one resource parameter type. The 16-bit space can include all resource parameter types, and the total resource parameter combination space that can be represented is 16 4 . The anti-collision prefix pre_len_3 is 8 bits, which is at the end, and can satisfy 16 2 The same resource parameter prefix computing nodes exist at the same time, and the anti-collision prefix starts from “00” and is sequentially from low to high [‘00’, ‘01’...,’0E’, ‘10’,...].

[0088] The anti-collision prefix is used to prevent the locators of the computing nodes with the same resource parameter prefix from being the same and causing conflicts, so it occupies a part of the locator with a length of pre_len_3. The same resource parameter prefix computing nodes are assigned from low to high (for example, when pre_len_3 is 8 bits, it is represented as a 2-bit hexadecimal number, and from low, ‘00’ is assigned first), and the uniqueness of different locators is maintained (the anti-collision prefix can accommodate 16 pre _ len _ 3 / 4 The number of computing nodes with the same resource parameter prefix in the default resource pool will not exceed this value).

[0089] The relative positions of the above three in the locator are not limited, and the following conditions are met at the same time:

[0090] pre_len_1+pre_len_2+pre_len_3=64bit;

[0091] If the anti-collision space is exhausted, the search is stopped, and the search result is fed back. Exhausting the anti-collision space means that all available addresses have been allocated or used, and there is no extra address available for allocation or use.

[0092] For example, the computing resource search module in the computing power resource management gateway determines the target resource parameters “8G memory, 100G disk, Windows 10 system, and 4-core processor”, converts them into the target resource parameter prefix “1243” through the parameter translation strategy, and starts the search process;

[0093] The computing resource search module sets a set of thresholds for each parameter in the translation relationship table “80% memory availability, 90% disk space remaining”, and when each parameter of the computing node is not less than the value, it means that the computing node is available.

[0094] The known resource pool prefix "FCBB:BB00:AC" and the calculated resource parameter prefix "1243".

[0095] The initialization anti-collision prefix is set to the minimum value to obtain the anti-collision prefix "FCBB:BB00:AC12:4300", and the computing node is searched.

[0096] During the search process, a data packet is sent to the computing node corresponding to the locator, and the resource state of the computing node is inquired, and the resource update detection module feeds back the availability of each resource of the computing node.

[0097] If an available computing node is found, the search is stopped, and a success signal is fed back; if the anti-collision space is exhausted, the search is stopped, and a search result is fed back.

[0098] The computing power resource management method provided by the embodiment of the application can effectively avoid address conflicts of computing nodes by setting an anti-collision prefix, ensure that the nodes in the resource pool can normally communicate, and improve the management efficiency of computing power resources.

[0099] In some embodiments, the computing power resource management gateway is in communication connection with a computing node agent of a computing node in the resource pool and a routing node agent of a routing node in the resource pool. The computing power resource management method provided by the embodiment of the application further includes:

[0100] In the case where the computing node agent of any computing node detects that the resource parameter of any computing node has changed, the anti-collision prefix before the change of the parameter of any computing node is received, which is sent by the routing node agent.

[0101] The anti-collision space of the anti-collision prefix before the change of the parameter of any computing node is marked as an idle state.

[0102] In the case where the computing node agent of any computing node detects that the resource parameter of any computing node has changed, the node prefix of any computing node is updated based on the first computing node agent of any computing node, the routing node and the parameter forwarding function; the node prefix includes the resource pool prefix, the resource parameter prefix and the anti-collision prefix of any computing node.

[0103] The change protocol of the node prefix is configured based on the routing node executing the parameter forwarding function and the latest anti-collision prefix and the latest resource parameter prefix of any computing node.

[0104] The parameter forwarding function is used to forward the latest resource parameter prefix in the node data packet sent by the first computing node agent to the change port of the change protocol.

[0105] The node data packet includes a type length value field and a segment list; the type length value field carries a protocol code of a changed protocol and a latest resource parameter prefix; and the segment list includes a segment identifier of a routing node.

[0106] The latest anti-collision prefix is obtained based on the minimum value in the free part of the anti-collision space.

[0107] Specifically, the embodiment of the present application provides a type of Function in SRv6, which is a parameter forwarding function. The parameter forwarding function is used to serve other protocols or mechanisms and help them forward parameters. Each protocol / mechanism has a unique protocol code. When the function is enabled, the type length value (TLV) field needs to include two parts, the protocol code and the parameter to be forwarded. For other spaces, zero is filled by default or other content is filled. The relative positions of the protocol code and the parameter to be forwarded are not restricted, and the relative positions are agreed within the SRv6 domain. Figure 7 One of the structure diagrams of the type length value field provided by the embodiment of the present application. Figure 7 The TLV field is shown in one structure form.

[0108] Figure 8 The structure diagram of the type length value field provided by the embodiment of the present application is shown in another structure form. Figure 8 As shown, the DHCPv6 protocol is used to send a request to the routing node to apply for changing the locator. In the TLV field, the protocol code has a length of 8 bits and is located at the head position. The parameter to be forwarded has a length of 16 bits and is located second. The remaining 8 bits are filled with zeros.

[0109] The instruction action corresponding to the parameter forwarding function is that the node finds the content of the TLV field in the data packet, finds the corresponding protocol / mechanism type according to the protocol code therein, and then forwards the parameter to be forwarded to the specified protocol or interface.

[0110] In the embodiment of the present application, the parameter forwarding function serves the locator changing protocol, including but not limited to the DHCPv6 protocol. The parameter to be forwarded is the content in the latest resource parameter prefix, which has a consistent and fixed length, pre_len_2.

[0111] In the embodiment of the present application, all routing nodes in the resource pool SRv6 domain support the parameter forwarding function function, and the SID of this type is added to the local SID list. The structure can be "locator+ parameter forwarding function function code" (wherein, the parameter forwarding function function code refers to the code for marking different functions in this SRv6 domain, which is not required here, and is agreed in the SRv6 domain).

[0112] The resource of the computing node can be configured, the resource parameter can be changed, when the resource parameter of the computing node is changed, the node prefix of the computing node needs to be changed, the node prefix is locator. The resource parameter prefix in the locator needs to be changed. The specific process of updating the resource parameter of the computing node is described below:

[0113] When the resource parameter of the computing node is changed, the resource update detection module of the computing node agent detects the change and starts the resource parameter change process.

[0114] The parameter translation module of the computing node agent translates the current latest resource parameter to obtain the latest resource parameter prefix.

[0115] The data transceiver module of the computing node agent encapsulates the SRv6 node data packet, injects the latest resource parameter prefix and the protocol encoding of the locator change protocol (including but not limited to DHCPv6 protocol) into the TLV field of the node data packet, adds the SID of the routing node at the end of the SID list (the list is a segment list, recording the forwarding path of SRV6d) of the node data packet, and sends the parameter change application to the routing node through the locator change protocol.

[0116] The data transceiver module of the routing node agent receives the node data packet, finds the local SID table, and finds the hit function.

[0117] The instruction execution module of the routing node agent executes the parameter forwarding function, reads the protocol encoding in the TLV of the node data packet, sends the to-be-forwarded parameter to the change port of the locator change protocol, and changes the locator of the computing node according to the forwarding parameter.

[0118] The conflict prevention module provides the minimum value in the free part of the conflict prevention space as the latest conflict prevention prefix.

[0119] The change management module configures the locator change protocol according to the latest conflict prevention prefix and the latest resource parameter prefix, and modifies the locator of the computing node according to the latest configured locator change protocol;

[0120] The data transceiver module of the routing node agent feeds back the change result to the computing node agent of the computing node of the resource parameter change.

[0121] The conflict prevention module of the routing node agent reports the conflict prevention prefix before the change to the conflict prevention management module to inform that the conflict prevention space is free.

[0122] For example, when the disk space of a certain computing node is upgraded from 100G to 500G, the resource update detection module detects the change, and then starts the resource parameter change process.

[0123] The parameter translation module of the computing node agent translates the latest resource parameter "memory 8G, disk 500G, system Windows 10, processor 4 cores" to obtain the latest resource parameter prefix "1743".

[0124] The computing node agent encapsulates an SRv6 data packet, injects the latest resource parameter prefix "1743" and the protocol code "01" of DHCPv6 into the TLV field, fills in zeros, adds the SID of the routing node at the end of the SID list, and sends a change application through the locator change protocol.

[0125] The data transceiver module of the routing node agent finds the local SID list and finds that the function is hit.

[0126] The instruction execution module of the routing node agent executes the parameter forwarding function, reads the protocol code in the TLV, and sends the to-be-forwarded parameter to the locator change protocol.

[0127] The conflict prevention module provides the minimum value in the free part of the conflict prevention space as the latest conflict prevention prefix.

[0128] The change management module configures the locator change protocol according to the latest conflict prevention prefix and the latest resource parameter prefix, and the locator change protocol modifies the locator of the computing node in combination with the obtained to-be-forwarded parameter, that is, the latest resource parameter prefix.

[0129] The data transceiver module of the routing node agent feeds back the change result to the computing node.

[0130] The conflict prevention module of the routing node agent reports the conflict prevention prefix before the change to the conflict prevention management module.

[0131] The computing resource management method provided by the embodiment of the application realizes the convenience and autonomy of computing node resource parameter updating under the networking mode and topology structure of the computing resource pool network domain through the parameter forwarding function, and the updating of the computing node resource is highly automated and does not need to manually update the computing node management database. Autonomous resource parameter discovery can be performed at the level of the computing node and the routing node, and address updating can be performed. In combination with the parameter forwarding function, the semanticity and utilization rate of the locator in SRv6 can be enhanced, and when the network is reorganized or part of the data resource is lost, the computing resource can be quickly networked and formed to call, thereby improving the management efficiency of the computing resource.

[0132] The execution subject of the computing resource management method provided in the above embodiments is a computing resource management gateway. The computing resource management method provided in the embodiments of the present application and having an execution subject of a computing resource management device is described below. The computing resource management method described below can be referred to in correspondence with the computing resource management method described above.

[0133] Figure 9 A flowchart of a second example of the computing resource management method provided in the embodiments of the present application is shown in FIG. 9. The method includes steps 910 and 920. The method flowchart steps are merely one possible implementation of the present application. Figure 9

[0134] Step 910: receiving, by the computing node agent, the data packet carrying the target resource parameter prefix sent by the computing resource management gateway.

[0135] Step 920: determining that the computing node corresponding to the computing node agent is available in a case where the resource state of the computing node corresponding to the computing node agent meets a preset state.

[0136] The resource parameter prefix of the computing node corresponding to the computing node agent matches the target resource parameter prefix. The target resource parameter prefix is obtained by translating the target resource parameter based on a preset parameter translation strategy.

[0137] The computing resource management gateway is the computing resource management gateway described above.

[0138] Specifically, the execution subject of the computing resource management method provided in the embodiments of the present application is a computing resource management device. The computing resource management device includes a computing node agent arranged in a computing node of a resource pool, a routing node agent arranged in a routing node of the resource pool, and a computing resource management gateway arranged in the resource pool.

[0139] The computing resource management method provided in the embodiments of the present application translates the target resource parameter into a target resource parameter prefix through a preset parameter translation strategy, so that the computing node matching the target resource parameter prefix can be identified. The computing node meeting the current resource parameter requirement and available can be quickly located by judging whether the resource state of the computing node meets a preset state, thereby improving the search efficiency and the management efficiency of the computing resource.

[0140] In some embodiments, the computing resource management method provided in the embodiments of the present application further includes:

[0141] In a case where it is monitored that the resource parameter of any computing node is changed, the latest resource parameter of any computing node is translated by the computing node agent corresponding to any computing node to obtain the latest resource parameter prefix of any computing node. ​

[0142] The computing node agent encapsulates the node data packet of the computing node based on the computing node, and sends the node data packet to the routing node; the node data packet comprises a type length value field and a segment list; the type length value field carries a protocol code of a change protocol and a latest resource parameter prefix; the segment list comprises a segment identifier of the routing node;

[0143] The routing node agent based on the routing node executes a parameter forwarding function, and configures the change protocol based on the latest anti-collision prefix and the latest resource parameter prefix of any computing node to update the node prefix of any computing node; the latest anti-collision prefix is obtained based on a minimum value in an anti-collision space free part.

[0144] The computing node resource parameter updating method provided by the embodiment of the application realizes the convenience and autonomy of computing node resource parameter updating under the computing resource pool network domain networking mode and the topology structure through the parameter forwarding function, and the updating of the computing node resource is highly automatic, without the need for manual updating of the computing node management database, thereby improving the management efficiency of the computing resource.

[0145] It should be noted that the computing resource management method provided by the embodiment of the application, which is executed by the computing resource management device, corresponds to all the method steps realized by the computing resource management method embodiment executed by the computing resource management gateway, and can achieve the same technical effects. Therefore, the same parts and beneficial effects of the embodiment and the above-mentioned embodiment will not be described in detail.

[0146] The computing resource management device provided by the embodiment of the application will be described below. The computing resource management device described below can be referred to in conjunction with the computing resource management method described above.

[0147] Figure 10 As shown in FIG. 1, the computing resource management device provided by the embodiment of the application comprises a translation module 1010, a sending module 1020 and a positioning module 1030. Figure 10 The translation module is configured to translate the target resource parameter into a target resource parameter prefix based on a preset parameter translation strategy.

[0148] The sending module is configured to send a data packet carrying the target resource parameter prefix to a computing node comprising the target resource parameter prefix in the resource pool.

[0149] The positioning module is configured to determine that the computing node is available in a case where the resource state of the computing node meets a preset state.

[0150] The positioning module is configured to determine that the computing node is available in a case where the resource state of the computing node meets a preset state.

[0151] Specifically, according to the embodiments of the present application, any multiple modules of the translation module, the sending module and the positioning module can be combined in one module for implementation, or any one of the modules can be split into multiple modules.

[0152] Alternatively, at least part of the functions of one or more of the modules can be combined with at least part of the functions of other modules and implemented in one module.

[0153] According to the embodiments of the present application, at least one of the translation module, the sending module and the positioning module can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on substrate, a system on package, an application specific integrated circuit (ASIC), or any other reasonable way of integrating or packaging a circuit, etc. hardware or firmware, or any one of software, hardware and firmware or a suitable combination of any of them.

[0154] Alternatively, at least one of the translation module, the sending module and the positioning module can be at least partially implemented as a computer program module that can perform corresponding functions when the computer program module is run.

[0155] The computing power resource management device provided by the embodiments of the present application can convert the target resource parameter into a target resource parameter prefix through the set parameter translation strategy, and can identify the computing node matched with the target resource parameter prefix. By judging whether the resource state of the computing node meets the preset state, the computing node meeting the current resource parameter demand and available can be quickly located, the search efficiency is improved, and the management efficiency of the computing power resource is improved.

[0156] In some embodiments, the sending module is specifically configured to:

[0157] Obtain a resource pool prefix of the resource pool and initialize a conflict prevention prefix;

[0158] Search the computing node in the resource pool based on the resource pool prefix and the target resource parameter prefix;

[0159] Send the data packet to the computing node and allocate the conflict prevention prefix to the computing node; the conflict prevention prefix is used to prevent the address of the computing node from conflicting with the existing address in the resource pool.

[0160] In some embodiments, the computing power resource management gateway is in communication connection with a computing node agent of the computing node in the resource pool and a routing node agent of a routing node in the resource pool. The computing power resource management device further includes an updating module, and the updating module is specifically configured to:

[0161] In the case that the computing node agent of any computing node monitors that the resource parameter of any computing node changes, the anti-collision prefix before the parameter change of any computing node is received by the receiving routing node agent;

[0162] The anti-collision space of the anti-collision prefix before the parameter change of any computing node is marked as an idle state;

[0163] In the case that the computing node agent of any computing node monitors that the resource parameter of any computing node changes, the anti-collision prefix before the parameter change of any computing node is received by the receiving routing node agent;

[0164] In some embodiments, the change protocol of the node prefix is configured based on the routing node executing the parameter forwarding function and the latest anti-collision prefix and the latest resource parameter prefix of any computing node;

[0165] The parameter forwarding function is used to forward the latest resource parameter prefix in the node data packet sent by the first computing node agent to the change port of the change protocol;

[0166] The node data packet includes a type-length-value field and a segment list; the type-length-value field carries the protocol encoding of the change protocol and the latest resource parameter prefix; and the segment list includes the segment identifier of the routing node;

[0167] The latest anti-collision prefix is obtained based on the minimum value in the idle part of the anti-collision space.

[0168] It should be noted that the computing resource management device provided by the embodiments of the present application can realize all the method steps realized by the computing resource management method embodiments, and can achieve the same technical effects. Therefore, the same parts and beneficial effects of the method embodiments in the embodiments will not be described in detail.

[0169] Figure 11 As shown in FIG. 2, the computing resource management device provided by the embodiments of the present application includes a computing node agent, a routing node agent and a computing resource management gateway. Figure 11 The device can be a component running in the computing resource management device. The computing resource management device includes a computing node agent arranged in a computing node of a resource pool, a routing node agent arranged in a routing node of the resource pool, and a computing resource management gateway arranged in the resource pool. The device includes a receiving module 1110 and a determining module 1120.

[0170] The receiving module is configured to receive, based on the computing node agent, a data packet carrying a target resource parameter prefix sent by the computing resource management gateway;

[0171] determining that the computing node corresponding to the computing node agent is available when the resource state of the computing node corresponding to the computing node agent meets a preset state;

[0172] The resource parameter prefix of the computing node corresponding to the computing node agent matches the target resource parameter prefix, and the target resource parameter prefix is obtained by translating the target resource parameter based on a preset parameter translation strategy.

[0173] The computing resource management gateway is the computing resource management gateway described above.

[0174] Specifically, according to embodiments of the present application, any of the receiving module and the determining module can be combined in one module to be implemented, or any of the modules can be split into multiple modules.

[0175] Alternatively, at least part of the function of one or more of the modules can be combined with at least part of the function of other modules, and implemented in one module.

[0176] According to embodiments of the present application, at least one of the receiving module and the determining module can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on substrate, a system on package, an application specific integrated circuit (ASIC), or any other reasonable way of integrating or packaging a circuit, etc. hardware or firmware, or any one of software, hardware and firmware or a proper combination of any of them.

[0177] Alternatively, at least one of the receiving module and the determining module can be at least partially implemented as a computer program module, which can perform corresponding functions when the computer program module is run.

[0178] In some embodiments, the computing resource management device further comprises a changing module, which is specifically configured to:

[0179] In the case where it is monitored that the resource parameter of any computing node is changed, the latest resource parameter of any computing node is translated based on the computing node agent corresponding to any computing node, to obtain the latest resource parameter prefix of any computing node.

[0180] The node data packet of the computing node is encapsulated by the computing node agent, and the node data packet is sent to the routing node; the node data packet includes a type length value field and a segment list; the protocol encoding of the changing protocol and the latest resource parameter prefix are carried in the type length value field; the segment identifier of the routing node is included in the segment list.

[0181] The routing node agent based on the routing node executes a parameter forwarding function and configures a change protocol based on a latest anti-collision prefix and a latest resource parameter prefix of any computing node to update a node prefix of the any computing node; the latest anti-collision prefix is obtained based on a minimum value in an anti-collision space free part.

[0182] It should be noted that the computing resource management device provided by the embodiments of the present application can implement all the method steps implemented by the computing resource management method embodiments and achieve the same technical effects. Therefore, the same parts and beneficial effects of the method embodiments in the embodiments will not be described in detail.

[0183] Figure 12 The structural schematic diagram of the electronic device provided by the embodiments of the present application is shown in Figure 12 The electronic device can include a processor 1210, a communication interface 1220, a memory 1230 and a communication bus 1240, wherein the processor 1210, the communication interface 1220 and the memory 1230 can communicate with each other through the communication bus 1240. The processor 1210 can invoke the computer program in the memory 1230 to execute the above-mentioned method, for example, including:

[0184] Based on the preset parameter translation strategy, the target resource parameter is translated into a target resource parameter prefix;

[0185] The data packet carrying the target resource parameter prefix is sent to the computing node including the target resource parameter prefix in the resource pool;

[0186] In the case that the resource state of the computing node meets the preset state, it is determined that the computing node is available.

[0187] Or,

[0188] Based on the computing node agent receiving the data packet carrying the target resource parameter prefix sent by the computing resource management gateway;

[0189] In the case that the resource state of the computing node corresponding to the computing node agent meets the preset state, it is determined that the computing node corresponding to the computing node agent is available;

[0190] The resource parameter prefix of the computing node corresponding to the computing node agent matches the target resource parameter prefix; the target resource parameter prefix is obtained by translating the target resource parameter based on the preset parameter translation strategy;

[0191] The computing resource management gateway is the above-mentioned computing resource management gateway.

[0192] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of a software function module and sold or used as an independent product, which can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0193] In another aspect, the embodiments of the present application also provide a computer program product, which comprises a computer program. The computer program can be stored on a non-transitory computer readable storage medium. When the computer program is executed by a processor, the computer can execute the method provided by the above-mentioned embodiments.

[0194] In another aspect, the embodiments of the present application also provide a processor readable storage medium, which stores a computer program. The computer program is used to make the processor execute the method provided by the above-mentioned embodiments.

[0195] The processor readable storage medium can be any available medium or data storage device that the processor can access, including but not limited to a magnetic storage (such as a floppy disk, a hard disk, a magnetic tape, a magneto-optical disk (MO) and the like), an optical storage (such as a CD, a DVD, a BD, a HVD and the like), and a semiconductor storage (such as a ROM, an EPROM, an EEPROM, a non-volatile memory (NAND FLASH), a solid state disk (SSD)) and the like.

[0196] The above-mentioned device embodiments are only schematic, wherein the modules illustrated as separate components can or can not be physically separated, and the components illustrated as modules can or can not be physical modules, i.e. they can be located in one place or distributed on multiple network modules. Part or all of the modules can be selected to achieve the purpose of the present embodiment according to actual needs. Those skilled in the art can understand and implement it without creative labor.

[0197] Those skilled in the art can clearly understand the implementation of the various embodiments by means of software and necessary general hardware platforms through the description of the above embodiments, and of course, the implementation can also be through hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part of the prior art that makes a contribution, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in the various embodiments or some parts of the embodiments.

[0198] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing examples, or make equivalent replacement for some technical features thereof; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present application.

Claims

1. A method for managing computing resources, characterized in that, The method, applied to a computing resource management gateway, includes: Based on a preset parameter translation strategy, the target resource parameters are translated into a target resource parameter prefix; the target resource parameter prefix is ​​the content of a specific segment in the IPv6 address formed by combining resource parameters through translation and spatial compression; The data packet carrying the target resource parameter prefix is ​​sent to the computing node in the resource pool that includes the target resource parameter prefix; If the resource status of the computing node meets the preset status, the computing node is determined to be available; The step of sending the data packet carrying the target resource parameter prefix to the computing node in the resource pool that includes the target resource parameter prefix includes: Obtain the resource pool prefix of the resource pool and initialize the anti-collision prefix; the resource pool prefix is ​​used to identify the resource pool; The computing node is searched in the resource pool based on the resource pool prefix and the target resource parameter prefix; The data packet is sent to the computing node, and the anti-collision prefix is ​​assigned to the computing node; the anti-collision prefix is ​​used to prevent the address of the computing node from conflicting with the existing address in the resource pool; the locator of the segment identifier of the computing node includes the resource pool prefix, the target resource parameter prefix and the anti-collision prefix.

2. The computing resource management method according to claim 1, characterized in that, The computing resource management gateway is communicatively connected to the computing node agent of the computing node in the resource pool and the routing node agent of the routing node in the resource pool. The method further includes: If the compute node agent of any compute node detects a change in the resource parameters of any compute node, it receives the anti-collision prefix before the parameter change of any compute node sent by the routing node agent. Mark the anti-collision space of the anti-collision prefix before the parameter change of any of the computing nodes as an idle state; Specifically, if a change in the resource parameters of any computing node is detected, the node prefix of the computing node is updated based on the first computing node agent of the computing node, the routing node, and the parameter forwarding function; the node prefix includes the resource pool prefix, resource parameter prefix, and anti-collision prefix of the computing node.

3. The computing resource management method according to claim 2, characterized in that, The node prefix change protocol is configured based on the parameter forwarding function executed by the routing node, and based on the latest anti-collision prefix and the latest resource parameter prefix of any computing node; The parameter forwarding function is used to forward the latest resource parameter prefix in the node data packet sent by the first computing node agent to the change port of the change protocol; The node data packet includes a type length value field and a segment list; the type length value field carries the protocol encoding of the change protocol and the latest resource parameter prefix; The segment list includes the segment identifier of the routing node; The latest anti-collision prefix is ​​obtained based on the minimum value in the free portion of the anti-collision space.

4. A method for managing computing resources, characterized in that, An application is made to a computing resource management device, the computing resource management device including a computing node agent set in the computing nodes of the resource pool, a routing node agent set in the routing nodes of the resource pool, and a computing resource management gateway set in the resource pool, the method comprising: The computing node agent receives data packets carrying target resource parameter prefixes sent by the computing resource management gateway. If the resource status of the computing node corresponding to the computing node agent meets the preset status, it is determined that the computing node corresponding to the computing node agent is available. Wherein, the resource parameter prefix of the computing node corresponding to the computing node proxy matches the target resource parameter prefix; the target resource parameter prefix is ​​obtained by translating the target resource parameters based on a preset parameter translation strategy; The computing resource management gateway is the computing resource management gateway as described in any one of claims 1 to 3.

5. The computing resource management method according to claim 4, characterized in that, The method further includes: If a change in the resource parameters of any computing node is detected, the latest resource parameters of the computing node are translated based on the computing node agent corresponding to the computing node to obtain the latest resource parameter prefix of the computing node. The computing node proxy encapsulates the node data packets of the computing node and sends the node data packets to the routing node; the node data packets include a type length value field and a segment list; the type length value field carries the protocol encoding of the changed protocol and the latest resource parameter prefix; the segment list includes the segment identifier of the routing node; The routing node agent executes the parameter forwarding function based on the routing node, and configures the change protocol based on the latest anti-collision prefix and the latest resource parameter prefix of any computing node to update the node prefix of any computing node; the latest anti-collision prefix is ​​obtained based on the minimum value in the free part of the anti-collision space.

6. A computing resource management device, characterized in that, The device is applied to a computing resource management gateway and includes: The translation module is used to translate target resource parameters into target resource parameter prefixes based on a preset parameter translation strategy; the target resource parameter prefix is ​​the content of a specific segment in the IPv6 address formed by combining resource parameters through translation and spatial compression; The sending module is used to send data packets carrying the target resource parameter prefix to computing nodes in the resource pool that include the target resource parameter prefix; The positioning module is used to determine that the computing node is available when the resource status of the computing node meets the preset status. Specifically, the sending module is used to: obtain the resource pool prefix of the resource pool and initialize the anti-collision prefix; the resource pool prefix is ​​used to identify the resource pool; The computing node is searched in the resource pool based on the resource pool prefix and the target resource parameter prefix; The data packet is sent to the computing node, and the anti-collision prefix is ​​assigned to the computing node; the anti-collision prefix is ​​used to prevent the address of the computing node from conflicting with the existing address in the resource pool; the locator of the segment identifier of the computing node includes the resource pool prefix, the target resource parameter prefix and the anti-collision prefix.

7. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the computing resource management method according to any one of claims 1 to 3 or the computing resource management method according to claim 4 or 5 through the computer program.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the computing resource management method as described in any one of claims 1 to 3 or the computing resource management method as described in claim 4 or 5.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the computing resource management method as described in any one of claims 1 to 3 or the computing resource management method as described in claim 4 or 5.

Images