Location system for faulty resource equipment
By introducing a fault resource equipment positioning system in the pooled product, the coordinated work of the main equipment and the management module are used to automatically identify the fault resource equipment, the problem of low fault positioning efficiency in the existing technology is solved and the positioning efficiency of the fault resource equipment is improved And reduce the risk of human failure.
Patent Information
- Application Number
- CN202411024991.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-29
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2044-07-29
AI Technical Summary
The existing pooled products have low efficiency in positioning faulty resource equipment, making it difficult for maintenance personnel to accurately determine the fault location of multiple resource equipment, resulting in inefficient maintenance and potential human failure risks.
Design a fault resource device positioning system, detects the fault through the first processor in the main device and sends information to the management module. The management module automatically recognizes the main port and the connection mapping relationship between the preset resource port and the device and the automatic identification of the main port and The connection mapping relationship between resource ports determines the failed target resource device.
The automatic positioning of fault resource equipment is realized, the fault positioning efficiency is improved, the maintenance personnel need to sort out cable connections, and the risk of human failure is reduced.
Smart Images

Figure CN118555194B_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the computer field, and in particular, to a system for locating a faulty resource device. Background Art
[0002] With the popularization of cloud computing, pooling technology has emerged to ensure business continuity and stability. Pooling technology centrally manages resources, allowing multiple servers to share and use them, thereby improving resource utilization efficiency. However, existing pooling products have some problems in maintenance and troubleshooting.
[0003] In the prior art, pooled products usually do not implement the design of port ID, resulting in unclear correspondence between resource devices and external ports. In order to solve this problem, indicator lights are usually used to assist maintenance personnel in identifying resource devices that need maintenance or replacement. However, this method has obvious disadvantages. When multiple resource devices fail at the same time, multiple indicator lights light up at the same time, which not only increases the difficulty of identification for maintenance personnel, but also may cause maintenance personnel to be unable to accurately determine the specific location of the faulty resource device that caused the abnormality of a specific server, thereby affecting maintenance efficiency and system stability.
[0004] In addition, if the resource equipment in the pooled product is not equipped with a fault indicator light, maintenance personnel need to sort out the cable connection method and communicate with the back-end R&D personnel to determine the specific location of the faulty resource equipment. This method is not only inefficient, but also has certain risks. For example, maintenance personnel may dismantle normally operating resource equipment due to misjudgment, causing unnecessary human failures.
[0005] In view of the problems in related technologies such as low efficiency in locating faulty resource equipment, no effective solution has yet been proposed. Summary of the invention
[0006] The embodiment of the present application provides a system for locating a faulty resource device, so as to at least solve the problem of low efficiency in locating a faulty resource device in the related art.
[0007] According to an embodiment of the present application, a system for locating a faulty resource device is provided, comprising: a resource providing device, the resource providing device comprising a plurality of resource ports and a plurality of resource devices; a main device, the main device comprising: a first processor, a management module and a main port, the main device is connected to the resource port through the main port to obtain a running resource on the corresponding resource device, the management module is connected to the first processor and the main port respectively;
[0008] The first processor is configured to send fault information to the management module when a fault is detected in the resource device;
[0009] The management module is configured to determine the target resource device where the fault occurs according to a preset first connection mapping relationship between resource ports and resource devices and a second connection mapping relationship between automatically identified primary ports and resource ports when receiving the fault information.
[0010] As an optional implementation manner, an identification element for providing a unique port identification for the corresponding port is deployed on the master port and each of the resource ports, and the management module is configured to:
[0011] Collecting the port identification of the identification element deployed on the resource port connected to the primary port to obtain the target port identification;
[0012] A connection relationship between the primary port and a target resource port having the target port identifier among the multiple resource ports is established and recorded to obtain the second connection mapping relationship.
[0013] As an optional implementation manner, the management module is further configured to:
[0014] Collecting power parameters of the identification element deployed on the resource port connected to the main port to obtain target power parameters;
[0015] The target power parameter is converted into the target port identifier.
[0016] As an optional implementation manner, the identification element deployed on each of the resource ports is deployed with P element pins having a preset order, where P is an integer greater than 2, and the management module is further configured to:
[0017] The current pin levels of the P element pins of the identification element deployed on the resource port connected to the master port are collected in sequence according to the preset order to obtain a first pin level sequence, wherein the first pin level sequence includes the P pin levels, and the i-th pin level among the P pin levels is the pin level of the i-th element pin among the P element pins;
[0018] The first pin level sequence is determined as the target power parameter.
[0019] As an optional implementation manner, the management module is further configured to:
[0020] In a case where the target power parameter is the first pin level sequence, detecting whether each pin level in the first pin level sequence is greater than a first level threshold, and detecting whether each pin level in the first pin level sequence is less than a second level threshold;
[0021] The pin levels in the first pin level sequence that are higher than the first level threshold are converted into a first value, and the pin levels in the first pin level sequence that are lower than the second level threshold are converted into a second value, to obtain the target port identifier.
[0022] As an optional implementation manner, the management module is further configured to:
[0023] Obtaining a primary port identifier of the primary port;
[0024] Establishing a correspondence between the primary port identifier and the target port identifier;
[0025] A connection relationship between the primary port and the target resource port is established and recorded according to the corresponding relationship to obtain the first connection mapping relationship.
[0026] As an optional implementation manner, the identification element deployed on the primary port is deployed with P element pins having a preset order, where P is an integer greater than 2, and the management module is further configured to:
[0027] The current pin levels of the P element pins of the identification element deployed on the main port are collected in sequence according to the preset order to obtain a second pin level sequence, wherein the second pin level sequence includes the P pin levels, and the jth pin level of the P pin levels is the pin level of the jth element pin of the P element pins;
[0028] The second pin level sequence is converted into the master port identification.
[0029] As an optional implementation manner, the management module is further configured to:
[0030] Detecting whether the level of each pin in the second pin level sequence is greater than a first level threshold, and detecting whether the level of each pin in the second pin level sequence is less than a second level threshold;
[0031] The pin levels in the second pin level sequence that are higher than the first level threshold are converted into a first value, and the pin levels in the second pin level sequence that are lower than the second level threshold are converted into a second value, to obtain the master port identifier.
[0032] As an optional implementation manner, the first processor is configured to:
[0033] When it is detected that the service operation status of the target service on the master device is abnormal, and a reference resource device having an abnormal device operation status appears among the multiple resource devices, it is determined that a failure of the resource device is detected.
[0034] As an optional implementation manner, the first processor is configured to:
[0035] Before determining that the resource device has failed, detecting the execution state of the service thread of the target service during operation;
[0036] The service running state of the target service is determined according to the execution state of the service thread.
[0037] As an optional implementation manner, a second processor is further deployed on the main device, the first processor, the second processor and the main port are connected to each other, the target service runs on the second processor, and the first processor is configured as follows:
[0038] Detecting whether the target service is currently running on the second processor;
[0039] In the case where it is detected that the target service is running, detecting an execution result of the service thread of the target service;
[0040] In a case where it is detected that the execution result indicates that the service thread is executed abnormally, determining that the execution state of the service thread is an execution abnormal state;
[0041] When it is detected that the execution result indicates that the service thread is executed normally, it is determined that the execution state of the service thread is a normal execution state.
[0042] As an optional implementation manner, the first processor is configured to:
[0043] In a case where it is detected that the target service has the service thread whose execution status is the execution abnormality status during operation, determining that the service operation status of the target service is the service operation abnormality;
[0044] When it is detected that there is no service thread whose execution status is the abnormal execution status during the operation of the target service, it is determined that the service operation status of the target service is normal operation.
[0045] As an optional implementation manner, each of the multiple resource devices is connected to a status indicator light, and the first processor is configured to:
[0046] Before determining that a fault has occurred in the resource device, detecting a light parameter of the status indicator light corresponding to each of the plurality of resource devices to obtain a plurality of light parameters;
[0047] In the case where the presence of a first lighting parameter is detected among the multiple lighting parameters, it is determined that the reference resource device whose device operating status is the device operation abnormality appears among the multiple resource devices, wherein the status indicator light of the first lighting parameter is used to indicate that the device operating status of the corresponding resource device is the device operation abnormality.
[0048] As an optional implementation manner, the first processor is configured to:
[0049] Before the determining that the resource device has failed, detecting a control instruction currently received by the master device;
[0050] When a target control instruction is detected, it is determined that the reference resource device whose device operating status is the device operation abnormality appears among the multiple resource devices, wherein the target control instruction is sent by the target account to the master device when the reference resource device whose device operating status is the device operation abnormality appears among the multiple resource devices.
[0051] As an optional implementation manner, the management module is configured to:
[0052] Sending a first request instruction to the resource providing device, wherein the first request instruction is used to request the first connection mapping relationship in the resource providing device;
[0053] Receiving the first connection mapping relationship;
[0054] Extracting a candidate resource device connected to the target resource port from the resource devices of the resource providing apparatus according to the first connection mapping relationship;
[0055] A target resource device whose device operation status is abnormal is located from the candidate resource devices.
[0056] As an optional implementation manner, the management module is configured to:
[0057] After locating the target resource device whose device operation status is abnormal from the candidate resource devices, acquiring the device identification of the target resource device to obtain the target device identification;
[0058] Generate first prompt information carrying the target device identifier, wherein the first prompt information is used to prompt that the operation status of the target service is abnormal due to the failure of the resource device identified by the target device;
[0059] The first prompt information is sent to the target account.
[0060] As an optional implementation manner, the management module is configured to:
[0061] After locating the target resource device whose device operation status is abnormal from the candidate resource devices, obtaining a target installation slot for deploying the target resource device in the resource providing apparatus;
[0062] Generate a second prompt message carrying the target installation slot, wherein the second prompt message is used to prompt that the operation status of the target service is abnormal due to a failure of the resource device installed in the target installation slot;
[0063] The second prompt information is sent to the target account.
[0064] As an optional implementation manner, the management module is configured to:
[0065] Sending a second request instruction to the resource providing apparatus, wherein the second request instruction is used to request obtaining a correspondence between M installation slots in the resource providing apparatus and the M resource devices, each of the M installation slots being used to install one of the M resource devices;
[0066] Receiving M installation slots and M resource devices having a corresponding relationship;
[0067] The target installation slot corresponding to the target resource device is located from the M installation slots and the M resource devices.
[0068] In an embodiment of the present application, the proposed positioning system for faulty resource equipment includes a resource providing device and a main device. The first processor in the main device can send fault information to the management module when detecting that a fault occurs in the resource equipment in the resource providing device. The management module can determine the target resource equipment that has failed based on the fault information according to the first connection mapping relationship between the preset resource port and the resource equipment and the second connection mapping relationship between the automatically identified main port and the resource port, thereby realizing the automatic positioning of the faulty equipment. The above system can directly interact with the first processor on the main device and the management module. When the first processor finds that it is necessary to locate the resource equipment that causes the abnormality of the main device, the management module locates the faulty target resource equipment through the first connection mapping relationship between the preset resource port and the resource equipment and the second connection mapping relationship between the automatically identified main port and the resource port. There is no need for maintenance personnel to sort out the cable connection mode to troubleshoot the fault, which greatly improves the positioning efficiency of the faulty resource equipment. The above technical solution solves the problems of low positioning efficiency of faulty resource equipment in the related technology, and realizes the technical effect of improving the positioning efficiency of faulty resource equipment. BRIEF DESCRIPTION OF THE DRAWINGS
[0069] Figure 1 This is a hardware structure block diagram of a positioning system for a fault resource device according to an embodiment of the present application;
[0070] Figure 2 is a flow chart of a method for locating a faulty resource device according to an embodiment of the present application;
[0071] Figure 3 is a schematic diagram of a resource providing device according to an embodiment of the present application;
[0072] Figure 4 is a schematic diagram of an identification element according to an embodiment of the present application;
[0073] Figure 5 is a schematic diagram of a target controller according to an embodiment of the present application. DETAILED DESCRIPTION
[0074] The embodiments of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.
[0075] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.
[0076] The present application proposes a system for locating a faulty resource device. Before describing the optional embodiments of the present application, in order to better understand the inventive concept of the present application and the creativity of the solution, the related technologies are first described:
[0077] At present, the pooled products in the related art do not implement the design of port ID, resulting in unclear correspondence between resource devices and external ports. When multiple resource devices fail at the same time, multiple indicator lights light up at the same time. Since the correspondence between resource devices and external ports is unclear, maintenance personnel cannot accurately determine the specific location of the faulty resource device that caused the abnormality of a specific server. When multiple servers are connected to the same pooled product at the same time, the devices accessing the pooled product are different for different servers. For example, in a memory pooled product, server 1 and server 2 use 4 memory sticks in the memory pooled product: memory sticks 1-4. Assuming that the business on server 1 runs abnormally and the indicator lights of memory sticks 1-3 light up at the same time, the operation and maintenance personnel cannot know which memory sticks of memory sticks 1-3 are used by server 1, and they cannot directly replace all memory sticks 1-3 at this time, because memory stick 3 may be used by server 2. At this time, the business of server 2 is normal, and replacing memory stick 3 will affect the business of server 2. In this scenario, the operation and maintenance personnel need to locate which memory bars 1-3 are used by server 1, and only replace the located memory bars. However, the current maintenance personnel on site do not know the specific location of the memory accessed by the first server, which brings great trouble to maintenance and replacement. At the same time, a pooled product usually provides resources for multiple servers. The server is connected to the external port through a cable. The operation and maintenance personnel need to go to the site to sort out the cable connection method for the external port corresponding to the specific server to determine the external port corresponding to the specific server, and then communicate with the back-end R&D personnel to determine the specific location of the faulty resource equipment.
[0078] In this embodiment, a system for locating a faulty resource device is provided. Figure 1 is a hardware structure block diagram of a positioning system for a fault resource device in an embodiment of the present application, such as Figure 1 As shown, a positioning system for a faulty resource device includes: a resource providing device, the resource providing device includes a plurality of resource ports and a plurality of resource devices; a main device, the main device includes: a first processor, a management module and a main port, the main device connects to the resource port through the main port to obtain the running resources on the corresponding resource device, and the management module is connected to the first processor and the main port respectively;
[0079] The first processor is configured to send fault information to the management module when a fault is detected in the resource device;
[0080] The management module is configured to determine the target resource device where the fault occurs according to a preset first connection mapping relationship between resource ports and resource devices and a second connection mapping relationship between automatically identified primary ports and resource ports when receiving the fault information.
[0081] As an optional solution, an identification element for providing a unique port identification for the corresponding port is deployed on the master port and each of the resource ports, and the management module is configured to:
[0082] Collecting the port identification of the identification element deployed on the resource port connected to the primary port to obtain the target port identification;
[0083] A connection relationship between the primary port and a target resource port having the target port identifier among the multiple resource ports is established and recorded to obtain the second connection mapping relationship.
[0084] Figure 2 is a flowchart of a method for locating a faulty resource device according to an embodiment of the present application. The above-mentioned faulty resource device locating system is configured to execute Figure 2 A method for locating a faulty resource device is shown, such as Figure 2 As shown, N resource ports and M resource devices with a connection relationship are deployed on the resource providing device, and the resource providing device is used to provide the target server (equivalent to the above-mentioned main device) with the running resources on the M resource devices. The target server and the resource providing device are connected to the resource port on the resource providing device through the server port master port deployed on the target server, and N and M are both integers greater than 1. The method is applied to the target controller in the target server, and the target controller includes the above-mentioned first processor and the above-mentioned management module. The master port and each of the resource ports are deployed with an identification element, and each of the identification elements is used to provide a unique port identification for the corresponding port. The process includes the following steps:
[0085] Step S11, collecting the port identification of the identification element deployed on the resource port connected to the primary port to obtain the target port identification;
[0086] Step S12, establishing and recording a connection relationship between the primary port and a target resource port having the target port identifier among the N resource ports;
[0087] Step S13, when it is detected that the business operation status of the target business on the target server is business operation abnormality, and a reference resource device with a device operation status of device operation abnormality appears among the M resource devices, a target resource device connected to the target resource port and with the device operation status of the device operation abnormality is extracted from the M resource devices.
[0088] Optionally, in this embodiment, the resource providing device may be, but is not limited to, a pooled BOX, i.e., a pooled product as described above. The core advantage of a pooled product is that it can centrally manage resources for sharing by multiple identical or different servers. For example, in a memory pooled product, different servers can access different memory resources to achieve dynamic allocation and optimization of resources.
[0089] Figure 3 is a schematic diagram of a resource providing device according to an embodiment of the present application, such as Figure 3 As shown, taking the resource providing device including 2 resource ports and 4 resource devices as an example, 2 resource ports (port 1, port 2) and 4 resource devices (D1-1, D1-2, D2-1, D2-2) with connection relationship are deployed on the resource providing device pooling BOX, the resource providing device is used to provide the target server (equivalent to the above-mentioned main device) with the running resources on the 4 resource devices, the target server and the resource providing device are connected to the resource port (port 1 or port 2) on the resource providing device through the main port (port 3) deployed on the target server, the target controller in the target server includes the above-mentioned first processor and the above-mentioned management module, and the main port of the target server and each of the resource ports are deployed with an identification element (9555 chip), and each of the identification elements is used to provide a unique port identification for the corresponding port. The above steps S11 to S13 are executed by the target controller.
[0090] Optionally, in this embodiment, the resource devices in the resource providing apparatus may be of various types, but are not limited to: Figure 3As shown, resource devices D1-1 and D1-2 can be but are not limited to memory resource devices, which provide memory resources to the connected server through port 1, and resource devices D2-1 and D2-2 can be but are not limited to computing power resource devices, which provide computing power resources to the connected server through port 2. The target server runs the target business, and the operation of the target business requires the execution of different business threads. Different business threads rely on different types of resources. For example, the business thread that performs storage read and write functions depends on memory resources and needs to obtain the memory resources in resource devices D1-1 and D1-2 from port 1. The business thread that performs the calculation function depends on memory resources and needs to obtain the computing power resources in resource devices D2-1 and D2-2 from port 2. In this case, The target controller can detect the execution status of each service thread of the target service on the target server during operation; when it is detected that the target service thread of the target service is in an abnormal execution state, P alternative resource ports that are connected to the main port are identified from the N resource ports, wherein P is an integer greater than or equal to 1 and less than N; a target resource port for providing target operating resources is located from the P alternative resource ports, wherein the target operating resources are operating resources required to execute the target service thread; and then a target installation slot where a faulty resource device is located is located from the Q installation slots connected to the target resource port, wherein Q is an integer greater than or equal to 1 and less than M.
[0091] As an optional solution, the management module is further configured to perform the following steps:
[0092] S21, collecting power parameters of the identification element deployed on the resource port connected to the main port to obtain target power parameters;
[0093] S22: Convert the target power parameter into the target port identifier.
[0094] Optionally, in this embodiment, identification elements are deployed on the master port and each of the resource ports, and each of the identification elements is used to provide a unique port identification for the corresponding port. The target port identification can be obtained by converting the target power parameter, which is the power parameter of the identification element deployed on the resource port to which the master port is connected.
[0095] Optionally, in this embodiment, the master device (such as Figure 3 Multiple ports (master ports) can be deployed on the target server in the example. Each master port (such as port 3) is designed with an I2C channel. Pooled products (such as Figure 3I2C channels are also designed on each port (such as port 1 and 2) of the pooled BOX in the main device. When the ports of the main device and the pooled product are interconnected through a cable, there is also an I2C channel in the cable, and the ports at both ends of the cable are connected together with the same I2C channel. The I2C channel is connected to the management module in the main device and is read uniformly by the management module. Each port in the main device is designed with an independent ID number (i.e., a unique port identifier), and each port in the pooled product is designed with an independent ID number (i.e., a unique port identifier).
[0096] Optionally, in this embodiment, Figure 4 is a schematic diagram of an identification element according to an embodiment of the present application, such as Figure 4As shown, there are 3 (P takes the value of 3) component pins on each identification component 9555 chip. Here, we take the interconnection of a main device and a pooled Box as an example. The main device has an interconnected port (port 3) and the pooled Box has two interconnected ports (ports 1 and 2). The port is designed with an I2C line. The I2C line in the main device is connected to the I2C line in the pooled Box. The I2C lines in the main device and the pooled Box are respectively connected to an IO expansion chip such as 9555, and different ID numbers can be set through the IO expansion chip. Here, we take the three IO expansion pins (component pins) of 9555 as an example for explanation. Among them, pin 1 can be used to distinguish between main device products and pooled Box products. By connecting pin 1 to power / ground, the distinction is made. When connected to power, the signal is high. When connected to ground, the signal is low. The management module reads pin 1 in the 9555 chip through I2C. When pin 1 is read as a high level, it is confirmed that this is the chip used by the port of the master device. When pin 1 is read as a low level, it is confirmed that this is the chip used by the port of the pooled Box. Pins 2 and 3 of the 9555 expansion chip are used as distinguishing addresses in the master device and the pooled Box. Pin 2 of the 9555 expansion chip connected to port 1 is connected to the power supply and defined as a high level, and pin 3 is connected to the ground and defined as a low level. Pin 2 of the 9555 expansion chip connected to port 2 is connected to the ground and defined as a low level, and pin 3 is connected to the ground and defined as a low level. High level is defined as 1, low level is defined as 0, the pin number in front is defined as a low position, and the pin number in the back is defined as a high position. So the address of port 1 is 01, and the address of port 2 is 00. When the BMC (i.e., management module) reads through I2C that pin 1 in the 9555 expansion chip is low, it is confirmed that the chip used by the port of the pooled Box is read. When pins 2 and 3 in the 9555 expansion chip are read as 01 respectively, it is confirmed that it is connected to port 1 of the pooled Box. When pins 2 and 3 in the 9555 expansion chip are read as 00 respectively, it is confirmed that it is connected to port 2 of the pooled Box. By analogy, when there are multiple ports, more address bits can be set for distinction. The target port identification corresponding to ports 1-3 can be obtained by the above method. As shown in Table 1 below, the target port identification of the main device port (port 3) is 100, the target port identification of port 1 of the pooled Box is 010, and the target port identification of port 2 of the pooled Box is 000. At this point, when the interconnection between the main device port and the port in the pooled Box is determined, the management module can read the interconnection relationship between the main device port and the port in the pooled Box through I2C. In this way, after the cable is plugged in, the port is automatically matched and confirmed.
[0097] Table 1
[0098] Port Definition Pin 1 Pin 2 Pin 3 Master port 1 0 0 Pooling Box Port 1 0 1 0 Pooling Box Port 2 0 0 0
[0099] As an optional solution, the identification element deployed on each resource port is deployed with P element pins having a preset order, where P is an integer greater than 2, and the management module is further configured to perform the following steps:
[0100] S31, sequentially collecting the current pin levels of the P element pins of the identification element deployed on the resource port connected to the master port in accordance with the preset order, to obtain a first pin level sequence, wherein the first pin level sequence includes the P pin levels, and the i-th pin level among the P pin levels is the pin level of the i-th element pin among the P element pins;
[0101] S32: Determine the first pin level sequence as the target power parameter.
[0102] Optionally, in this embodiment, the first pin level sequence may be but is not limited to: Figure 4 The levels on the three extended pins (component pins) are in a sequence formed according to the pin order.
[0103] As an optional solution, the management module is further configured to perform the following steps:
[0104] S41, when the target power parameter is the first pin level sequence, detecting whether the level of each pin in the first pin level sequence is greater than a first level threshold, and detecting whether the level of each pin in the first pin level sequence is less than a second level threshold;
[0105] S42: Convert the pin levels in the first pin level sequence that are higher than the first level threshold into a first value, and convert the pin levels in the first pin level sequence that are lower than the second level threshold into a second value, to obtain the target port identifier.
[0106] Optionally, in this embodiment, the pin level higher than the first level threshold is a high level, and the pin level lower than the second level threshold is a low level. The high level is defined as 1 (first value), and the low level is defined as 0 (second value).
[0107] Optionally, in this embodiment, each port in the master device mentioned above is designed with an independent ID number (i.e., a unique port identifier), and each port in the pooled product is designed with an independent ID number (i.e., a unique port identifier). The ID number in the master device is different from the ID number in the pooled product. A few digits can be reserved in the ID number to represent the product type, indicating whether it is an ID in the master device or the pooled product (for example, pin 1 can be used to distinguish between master device products and pooled Box products, and the distinction is made by connecting pin 1 to power / ground. When connected to power, the signal is high. When connected to ground, the signal is low. The management module reads pin 1 in the 9555 chip through I2C. When pin 1 is read as a high level, it is confirmed that this is the chip used for the port of the master device. When pin 1 is read as a low level, it is confirmed that this is the chip used for the port of the pooled Box). At the same time, the back end of each port in the pooled product corresponds to a resource device at a specific location. Each resource device has a corresponding slot number (installation slot), so that the slot number of each resource device is matched with the ID number of the port. When a port of the main device is connected to any port in the pooled product through a cable, the management module accesses the ID number in the main device through I2C, and accesses the ID number in the pooled product at the same time, so that the port of the main device can be matched with the port of the pooled product, and then the port of the main device can be matched with the specific slot number of the resource device in the pooled product. When the main device product recognizes that a resource device is abnormal, the main device can find the corresponding resource device slot number through its own port, and display it in the fault reporting system as a resource device slot number. This is conducive to quickly finding resource devices in pooled products.
[0108] Optional, Figure 5 is a schematic diagram of a target controller according to an embodiment of the present application, such as Figure 5 As shown, the target controller includes a first processor CPU1 (equivalent to the first processor in the main device) and a baseboard management controller BMC (equivalent to the management module in the main device). The port identifier of the identification element deployed on the resource port connected to the main port can be, but is not limited to, obtained by the BMC. CPU1 directly extracts the port identifier from the BMC and determines the port identifier as the target port identifier.
[0109] At the same time, in the pooled Box, for resource devices with high bandwidth requirements, such as memory pooled products or NVME disk pooled products, the external port and the internal resource device are interconnected through a high-speed link, and the internal resource device position can correspond to the external port, that is, the port serial number and the resource device slot number are matched. When the BMC reads port 1 in the pooled Box through the I2C channel, it also records resource device 1 (D1-1) and resource device 2 (D1-2) at this location. When the BMC reads port 2 in the pooled Box, it also records resource device 3 (D2-1) and resource device 4 (D2-1) at this location. When developing BMC, you need to know the interconnection relationship between the ports and resource devices in the pooled Box in advance and define the connection relationship in the software.
[0110] As an optional solution, the management module is further configured to perform the following steps:
[0111] S61, obtaining a primary port identifier of the primary port;
[0112] S62, constructing a correspondence between the primary port identifier and the target port identifier;
[0113] S63: Establish and record a connection relationship between the primary port and the target resource port according to the corresponding relationship to obtain the first connection mapping relationship.
[0114] Optionally, in this embodiment, if Figure 5 As shown in the figure, after the main device is connected to the pooled Box, the target server is powered on and the service starts running. During the operation, the system accesses the resource device at the end through a high-speed link. When a fault occurs in the terminal resource device accessed through the high-speed link, the system will notify the BMC which port in the main device is connected to the resource device that has a fault. The BMC will call the port-to-port correspondence in the software, thereby extending to the port-to-resource device correspondence. And report the specific fault slot number to the operating system. The operating system directly reports the faulty resource device slot number. The maintenance personnel can directly find the specific slot in the pooled Box through the slot number of the fault reporting system and repair and replace the resource device.
[0115] As an optional solution, the identification element deployed on the primary port is deployed with P element pins having a preset order, where P is an integer greater than 2, and the management module is further configured to perform the following steps:
[0116] S71, collecting the current pin levels of the P element pins of the identification element deployed on the main port in sequence according to the preset order to obtain a second pin level sequence, wherein the second pin level sequence includes the P pin levels, and the j-th pin level of the P pin levels is the pin level of the j-th element pin of the P element pins;
[0117] S72: Convert the second pin level sequence into the master port identifier.
[0118] Optionally, in this embodiment, if Figure 4 As shown, the main port is also deployed with the identification element 9555 chip, and the 9555 chip is also deployed with 3 (P is 3) element pins. Similar to the process of acquiring the port identification of the identification element deployed on the resource port connected to the main port to obtain the target port identification, the main port identification can be acquired in a similar manner.
[0119] As an optional solution, the management module is further configured to perform the following steps:
[0120] S81, detecting whether the level of each pin in the second pin level sequence is greater than a first level threshold, and detecting whether the level of each pin in the second pin level sequence is less than a second level threshold;
[0121] S82, convert the pin levels in the second pin level sequence that are higher than the first level threshold into a first value, and convert the pin levels in the second pin level sequence that are lower than the second level threshold into a second value, to obtain the master port identifier.
[0122] Optionally, in this embodiment, the conversion method of the primary port identifier and the target port identifier is similar and will not be described in detail here.
[0123] As an optional solution, the management module is further configured to:
[0124] When it is detected that the service operation status of the target service on the master device is abnormal, and a reference resource device having an abnormal device operation status appears among the multiple resource devices, it is determined that a failure of the resource device is detected.
[0125] Optional, such as Figure 5As shown, the establishment and recording of the connection relationship between the master port and the target resource port with the target port identifier among the N resource ports can be performed, but not limited to, by the baseboard management controller BMC in the target server. After establishing and recording the connection relationship, the BMC sends the connection relationship to the first processor CPU1. After the server is connected to the pooled Box, it is powered on and the service starts to run. During the operation, the system accesses the resource device at the end through a high-speed link. When a fault occurs in the terminal resource device accessed through the high-speed link, the system will notify the BMC which port in the master device is connected downstream and has a fault. The BMC will call the port-to-port correspondence in the software, thereby extending to the port-to-resource device correspondence. And report the specific fault slot number to the operating system. The operating system directly reports the faulty resource device slot number (installation slot), and the maintenance personnel directly find the specific slot in the pooled Box through the slot number of the fault reporting system, and repair and replace the resource device.
[0126] As an optional solution, the first processor is configured to perform the following steps:
[0127] S101, before determining that a failure of the resource device is detected, detecting an execution state of a service thread of the target service during operation;
[0128] S102: Determine the service running state of the target service according to the execution state of the service thread.
[0129] Optionally, in this embodiment, the target business mentioned above is running on the target server, and the operation of the target business depends on the execution of the business thread. The detection of the business operation status of the target business can be converted into the detection of the execution status of the business thread of the target business.
[0130] As an optional solution, a second processor is further deployed on the main device, the first processor, the second processor and the main port are connected to each other, the target service runs on the second processor, and the first processor is configured to perform the following steps:
[0131] S111, detecting whether the target service is currently running on the second processor;
[0132] S112, in the case where it is detected that the target service is running, detecting the execution result of the service thread of the target service;
[0133] S113, when it is detected that the execution result indicates that the service thread is executed abnormally, determining that the execution state of the service thread is an execution abnormal state;
[0134] S114: When it is detected that the execution result indicates that the service thread is executing normally, determine that the execution state of the service thread is a normal execution state.
[0135] Optionally, in this embodiment, the above-mentioned detection of the business operation status of the target business can be converted into detection of the execution status of the business thread of the target business, specifically in the following manner: when it is detected that the execution result of the business thread of the target business is abnormal execution, the execution status of the business thread is determined to be an abnormal execution state. The abnormal execution result may be, but is not limited to, execution timeout or execution failure.
[0136] Optionally, in this embodiment, the target service may run on a second processor, the second processor may be hardware independent of the first processor, and the first processor and the second processor may be two independent processor cores.
[0137] As an optional solution, the first processor is configured to perform the following steps:
[0138] S121, when it is detected that there is a service thread whose execution status is the execution abnormality status during the operation of the target service, determining that the service operation status of the target service is the service operation abnormality;
[0139] S122: When it is detected that there is no service thread whose execution status is the abnormal execution status during the operation of the target service, determine that the service operation status of the target service is normal operation.
[0140] Optionally, in this embodiment, the above-mentioned detection of the business operation status of the target business can be converted into a detection of the execution status of the business thread of the target business. When it is detected that the business thread with the execution status of the execution abnormality exists during the operation of the target business, it indicates that the target business cannot be executed or the execution of the target business fails. At this time, it can be determined that the business operation status of the target business is the business operation abnormality.
[0141] As an optional solution, each of the multiple resource devices is connected to a status indicator light, and the first processor is configured to perform the following steps:
[0142] S131, before determining that a fault has occurred in the resource device, detecting a light parameter of the status indicator light corresponding to each of the plurality of resource devices to obtain a plurality of light parameters;
[0143] S132, when it is detected that there is a first lighting parameter among the multiple lighting parameters, it is determined that the reference resource device whose device operating status is the device operation abnormality appears among the multiple resource devices, wherein the status indicator light of the first lighting parameter is used to indicate that the device operating status of the corresponding resource device is the device operation abnormality.
[0144] Optionally, in this embodiment, regarding the method of detecting the device operation status of multiple resource devices, a status indicator light may be connected to each resource device, and a light parameter of the status indicator light may be used to indicate whether the device operation status is abnormal operation of the device. For example, if the status indicator light of the first light parameter is a red light, the status indicator light indicates that the device operation status of the corresponding resource device is abnormal operation of the device.
[0145] As an optional solution, the first processor is configured to perform the following steps:
[0146] S141, before determining that the resource device has failed, detecting a control instruction currently received by the master device;
[0147] S142, when a target control instruction is detected, determining that a reference resource device whose device operating status is the device operation abnormality appears among the multiple resource devices, wherein the target control instruction is sent by the target account to the master device when the reference resource device whose device operating status is the device operation abnormality appears among the multiple resource devices.
[0148] Optionally, in the present embodiment, another method for detecting the device operating status of the plurality of resource devices may be triggered by a target account. When the target account finds that a reference resource device whose device operating status is the device operation abnormality appears among the plurality of resource devices, the target account sends a target control instruction to the main device. At this time, the first processor and the management module may determine that a reference resource device whose device operating status is the device operation abnormality appears among the plurality of resource devices.
[0149] As an optional solution, the management module is configured to perform the following steps:
[0150] S151, sending a first request instruction to the resource providing device, wherein the first request instruction is used to request the first connection mapping relationship in the resource providing device;
[0151] S152, receiving the first connection mapping relationship;
[0152] S153, extracting candidate resource devices connected to the target resource port from the resource devices of the resource providing apparatus according to the first connection mapping relationship;
[0153] A target resource device whose device operation status is abnormal is located from the candidate resource devices.
[0154] Optionally, in this embodiment, candidate resource devices connected to the target resource port are extracted from the resource devices of the resource providing apparatus. Depending on the pre-acquisition of the connection relationship between the multiple resource ports and the multiple resource devices, the management module can pre-acquire the connection relationship between the multiple resource ports and the multiple resource devices and then extract the candidate resource devices connected to the target resource port.
[0155] As an optional solution, the management module is configured to perform the following steps:
[0156] S161, after locating the target resource device whose device operation status is abnormal from the candidate resource devices, acquiring the device identifier of the target resource device to obtain the target device identifier;
[0157] S162, generating first prompt information carrying the target device identifier, wherein the first prompt information is used to prompt that the operation status of the target service is abnormal due to the failure of the resource device identified by the target device;
[0158] S163: Send the first prompt information to the target account.
[0159] Optionally, in this embodiment, after obtaining the faulty target resource device, the management module can obtain the target device identifier of the target resource device, and then send the first prompt information carrying the target device identifier to the target account. The target account replaces or maintains the resource device with the target device identifier.
[0160] As an optional solution, the management module is configured to perform the following steps:
[0161] S171, after locating the target resource device whose device operation status is abnormal from the candidate resource devices, obtaining a target installation slot for deploying the target resource device in the resource providing apparatus;
[0162] S172, generating a second prompt message carrying the target installation slot, wherein the second prompt message is used to prompt that the operation status of the target service is abnormal due to a failure of the resource device installed in the target installation slot;
[0163] S173: Send the second prompt information to the target account.
[0164] Optionally, in this embodiment, in addition to sending the first prompt information carrying the target device identifier to the target account, and the target account replacing or maintaining the resource device identified by the target device, the target installation slot of the target resource device can be further sent to the target account through a second prompt information. The operation and maintenance personnel can quickly determine the location of the target resource device according to the target installation slot in the second prompt information of the target account, and replace and maintain the target resource device.
[0165] As an optional solution, the management module is configured to perform the following steps:
[0166] S181, sending a second request instruction to the resource providing apparatus, wherein the second request instruction is used to request to obtain a correspondence between M installation slots in the resource providing apparatus and the M resource devices, each of the M installation slots being used to install one of the M resource devices;
[0167] S182, receiving M installation slots and M resource devices having a corresponding relationship;
[0168] S183: Locate the target installation slot corresponding to the target resource device from the M installation slots and the M resource devices.
[0169] Optionally, in this embodiment, the method for obtaining the target installation slot for deploying the target resource device in the resource providing device may be obtained by the management module sending a second request instruction request to the resource providing device. After receiving the M installation slots and the M resource devices having a corresponding relationship, the target controller locates the target installation slot corresponding to the target resource device from the M installation slots and the M resource devices.
[0170] The method for locating faulty resource equipment proposed in this application has been improved in terms of hardware. A 9555 expansion chip is added to the ports on the master device and the pooled BOX to define an independent address for each port. The address information of the port is defined by connecting the expansion pins to the power supply and ground. The pins of the expansion chip of each port in the pooled product are connected to the power supply and ground in different ways, and different address information is defined. This method is used to distinguish the ports. The ports in the master device and the ports in the pooled product are read simultaneously through the same I2C of the management module to match the ports of the master device and the ports of the pooled product.
[0171] In addition, improvements have been made to the software. The management module defines the correspondence between the resource ports and resource devices in the pooled product (pooled BOX) in advance, and corresponds the ID number (port identifier of the resource port) to the device slot number. The target service on the target server can run on the target server's operating system, and the operating system can be installed on the second processor. When a device failure is detected during the operation of the target service, the main device port (main port) where the failure is located needs to be sent to the management module. The management module finds the specific slot number (target installation slot) of the faulty device through the obtained fault port and reports it to the operating system. The faulty slot number is directly displayed in the operating system.
[0172] Through this method, when the main device and the pooled product are connected through cables, once the connection relationship is determined, the main device system can confirm the connection relationship through the ID serial numbers of the ports at both ends. The resource ports in the pooled product have a corresponding relationship with the resource devices, thereby confirming that the main port of the main device is connected to the slot number of the device. The slot number of the specific error reporting device can be directly displayed in the fault system, which is convenient for maintenance personnel to directly find the location of the faulty device and perform repairs and replacements directly. It avoids maintenance personnel operating the wrong device and causing man-made accidents. This design greatly increases the maintainability of the product.
[0173] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment 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 this understanding, the technical solution of the present application, 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, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.
[0174] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.
[0175] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.
Claims
1. A system for locating faulty resource equipment, It is characterized in that The method comprises: a resource providing device, the resource providing device comprises a plurality of resource ports and a plurality of resource devices; a main device, the main device comprises: a first processor, a management module and a main port, the main device obtains the running resources on the corresponding resource device by connecting with the resource port through the main port, and the management module is connected with the first processor and the main port respectively; The first processor is configured to send fault information to the management module when a fault is detected in the resource device; The management module is configured to determine the target resource device where the fault occurs according to a preset first connection mapping relationship between resource ports and resource devices and a second connection mapping relationship between automatically identified primary ports and resource ports when receiving the fault information.
2. The system according to claim 1, characterized in that The main port and each of the resource ports are each provided with an identification element for providing a unique port identification for the corresponding port, and the management module is configured as follows: Collecting the port identification of the identification element deployed on the resource port connected to the primary port to obtain the target port identification; A connection relationship between the primary port and a target resource port having the target port identifier among the multiple resource ports is established and recorded to obtain the second connection mapping relationship.
3. The system according to claim 2, characterized in that The management module is also configured to: Collecting power parameters of the identification element deployed on the resource port connected to the main port to obtain target power parameters; The target power parameter is converted into the target port identifier.
4. The system according to claim 3, characterized in that The identification element deployed on each resource port is deployed with P element pins in a preset order, where P is an integer greater than 2, and the management module is further configured to: The current pin levels of the P element pins of the identification element deployed on the resource port connected to the master port are collected in sequence according to the preset order to obtain a first pin level sequence, wherein the first pin level sequence includes the P pin levels, and the i-th pin level among the P pin levels is the pin level of the i-th element pin among the P element pins; The first pin level sequence is determined as the target power parameter.
5. The system according to claim 4, characterized in that The management module is also configured to: In a case where the target power parameter is the first pin level sequence, detecting whether each pin level in the first pin level sequence is greater than a first level threshold, and detecting whether each pin level in the first pin level sequence is less than a second level threshold; The pin levels in the first pin level sequence that are higher than the first level threshold are converted into a first value, and the pin levels in the first pin level sequence that are lower than the second level threshold are converted into a second value, to obtain the target port identifier.
6. The system according to claim 2, characterized in that The management module is also configured to: Obtaining a primary port identifier of the primary port; Establishing a correspondence between the primary port identifier and the target port identifier; A connection relationship between the primary port and the target resource port is established and recorded according to the corresponding relationship to obtain the first connection mapping relationship.
7. The system according to claim 6, characterized in that The identification element deployed on the primary port is deployed with P element pins in a preset order, where P is an integer greater than 2, and the management module is further configured to: The current pin levels of the P element pins of the identification element deployed on the main port are collected in sequence according to the preset order to obtain a second pin level sequence, wherein the second pin level sequence includes the P pin levels, and the jth pin level of the P pin levels is the pin level of the jth element pin of the P element pins; The second pin level sequence is converted into the master port identification.
8. The system according to claim 7, characterized in that The management module is also configured to: Detecting whether the level of each pin in the second pin level sequence is greater than a first level threshold, and detecting whether the level of each pin in the second pin level sequence is less than a second level threshold; The pin levels in the second pin level sequence that are higher than the first level threshold are converted into a first value, and the pin levels in the second pin level sequence that are lower than the second level threshold are converted into a second value, to obtain the master port identifier.
9. The system according to claim 2, characterized in that The first processor is configured to: When it is detected that the service operation status of the target service on the master device is abnormal, and a reference resource device having an abnormal device operation status appears among the multiple resource devices, it is determined that a failure of the resource device is detected.
10. The system according to claim 9, characterized in that The first processor is configured to: Before determining that the resource device has failed, detecting the execution state of the service thread of the target service during operation; The service running state of the target service is determined according to the execution state of the service thread.
11. The system according to claim 10, characterized in that A second processor is also deployed on the master device. The first processor, the second processor and the master port are connected to each other. The target service runs on the second processor. The first processor is configured as follows: Detecting whether the target service is currently running on the second processor; In the case where it is detected that the target service is running, detecting an execution result of the service thread of the target service; In a case where it is detected that the execution result indicates that the service thread is executed abnormally, determining that the execution state of the service thread is an execution abnormal state; When it is detected that the execution result indicates that the service thread is executed normally, it is determined that the execution state of the service thread is a normal execution state.
12. The system according to claim 11, characterized in that The first processor is configured to: In a case where it is detected that the target service has the service thread whose execution status is the execution abnormality status during operation, determining that the service operation status of the target service is the service operation abnormality; When it is detected that there is no service thread whose execution status is the abnormal execution status during the operation of the target service, it is determined that the service operation status of the target service is normal operation.
13. The system according to claim 9, characterized in that Each of the plurality of resource devices is connected to a status indicator light, and the first processor is configured to: Before determining that a fault has occurred in the resource device, detecting a light parameter of the status indicator light corresponding to each of the plurality of resource devices to obtain a plurality of light parameters; In the case where the presence of a first lighting parameter is detected among the multiple lighting parameters, it is determined that the reference resource device whose device operating status is the device operation abnormality appears among the multiple resource devices, wherein the status indicator light of the first lighting parameter is used to indicate that the device operating status of the corresponding resource device is the device operation abnormality.
14. The system according to claim 9, characterized in that The first processor is configured to: Before the determining that the resource device has failed, detecting a control instruction currently received by the master device; When a target control instruction is detected, it is determined that the reference resource device whose device operating status is the device operation abnormality appears among the multiple resource devices, wherein the target control instruction is sent by the target account to the master device when the reference resource device whose device operating status is the device operation abnormality appears among the multiple resource devices.
15. The system according to claim 9, characterized in that The management module is configured to: Sending a first request instruction to the resource providing device, wherein the first request instruction is used to request the first connection mapping relationship in the resource providing device; Receiving the first connection mapping relationship; Extracting a candidate resource device connected to the target resource port from the resource devices of the resource providing apparatus according to the first connection mapping relationship; A target resource device whose device operation status is abnormal is located from the candidate resource devices.
16. The system according to claim 15, characterized in that The management module is configured to: After locating the target resource device whose device operation status is abnormal from the candidate resource devices, acquiring the device identification of the target resource device to obtain the target device identification; Generate first prompt information carrying the target device identifier, wherein the first prompt information is used to prompt that the operation status of the target service is abnormal due to the failure of the resource device identified by the target device; The first prompt information is sent to the target account.
17. The system according to claim 15, characterized in that The management module is configured to: After locating the target resource device whose device operation status is abnormal from the candidate resource devices, obtaining a target installation slot for deploying the target resource device in the resource providing apparatus; Generate a second prompt message carrying the target installation slot, wherein the second prompt message is used to prompt that the operation status of the target service is abnormal due to a failure of the resource device installed in the target installation slot; The second prompt information is sent to the target account.
18. The system according to claim 17, characterized in that The management module is configured to: Sending a second request instruction to the resource providing apparatus, wherein the second request instruction is used to request obtaining a correspondence between M installation slots in the resource providing apparatus and the M resource devices, each of the M installation slots being used to install one of the M resource devices; Receiving the M installation slots and the M resource devices having a corresponding relationship; The target installation slot corresponding to the target resource device is located from the M installation slots and the M resource devices.
Citation Information
Patent Citations
Fault positioning method, device, server, storage medium and system
CN113596891A
Fault detection method, master equipment, slave equipment and computer readable storage medium
CN114077857A
