Slow disk identification method and computing device

Abstract

A slow disk identification method and a computing device, which are applied to a server. The server comprises a BMC, a RAID card and a hard disk to be identified, the BMC being in communication connection with the RAID card, and the RAID card being in communication connection with said hard disk. The method comprises: the BMC sends a delay information statistical instruction to the RAID card (S510); on the basis of the delay information statistical instruction, the RAID card performs multiple read / write operations on said hard disk to obtain delay information (S520); and the BMC acquires the delay information from the RAID card and, on the basis of the delay information, determines whether to identify said hard disk as a slow disk or, on the basis of the delay information, the RAID card determines whether to identify said hard disk as a slow disk (S530).

Description

Slow disk identification method and computing device

[0001] This application claims priority to Chinese Patent Application No. 202411252743.8, filed on September 6, 2024, the entire contents of which are incorporated herein by reference. TECHNICAL FIELD

[0002] The present application relates to the field of storage technology, and in particular to a slow disk identification method and a computing device. BACKGROUND

[0003] In the field of storage technology, it is crucial to identify slow disks from one or more hard disks for stable business operation. For mechanical hard disks, there are hardware and environmental problems such as head aging, magnetic degradation, bad tracks, fragmentation, vibration, and energy-saving design; for solid state disks, there are problems such as flash media failure, frequent erasing and writing, hard disk overheating, and charge leakage; these problems can easily cause the read / write performance of the hard disk to deteriorate, the input / output (IO) response time to become longer, and form so-called slow disks. Therefore, a slow disk identification technology is needed to identify slow disks from one or more hard disks.

[0004] In existing slow disk identification methods, the hard disk is identified based on the IOPS (input / output operations per second) information of the operating system; or the hard disk is identified based on the drive program response log; or the operating system identifies the hard disk by reading and writing the hard disk. In these methods, software needs to be deployed under the operating system to identify slow disks, and the use scenarios have certain limitations. SUMMARY

[0005] Embodiments of the present application provide a slow disk identification method and a computing device, which are based on BMC (Baseboard Management Controller) and achieve slow disk detection and identification for one or more hard disks, without the need for slow disk identification under the operating system, and the use scenarios are more extensive.

[0006] In a first aspect, the embodiments of the present application provide a slow disk identification method, applied to a server, the server comprising a BMC, a RAID card and a to-be-identified hard disk, the BMC being in communication connection with the RAID card, and the RAID card being in communication connection with the to-be-identified hard disk, the method comprising: the BMC sending a time delay information statistical instruction to the RAID card; based on the time delay information statistical instruction, the RAID card performing multiple read-write operations on the to-be-identified hard disk to obtain time delay information, the time delay information being used to indicate read-write time consumption of the multiple read-write operations; the BMC obtaining the time delay information from the RAID card, and determining whether to identify the to-be-identified hard disk as a slow disk based on the time delay information, or the RAID card determining whether to identify the to-be-identified hard disk as a slow disk based on the time delay information.

[0007] In the technical scheme of the embodiments of the present application, the out-of-band management software BMC sends a time delay information statistical instruction to the RAID card, the RAID card performs multiple read-write operations on the to-be-identified hard disk, and the BMC or the RAID card identifies whether the to-be-identified hard disk has a slow disk phenomenon according to the time delay information fed back by the multiple read-write operations. That is, the technical scheme of the embodiments of the present application realizes slow disk detection and identification of one or more hard disks based on the BMC and the RAID card, without the need for slow disk identification work under an operating system, and is more widely used and can be applied to scenarios where the operating system does not support slow disk identification work or does not exist.

[0008] In a possible implementation, the BMC obtains the time delay information from the RAID card, and determines whether to identify the to-be-identified hard disk as a slow disk based on the time delay information, comprising: the BMC obtaining the time delay information from the RAID card; based on the time delay information, the BMC determines a proportion of a timeout number in a total number of the multiple read-write operations, the timeout number representing a number of read-write operations whose time consumption exceeds a time delay threshold; and when the proportion is higher than a preset proportion, the BMC identifies the to-be-identified hard disk as a slow disk. Alternatively, the RAID card determines whether to identify the to-be-identified hard disk as a slow disk based on the time delay information, comprising: based on the time delay information, the RAID card determines a proportion of a timeout number in a total number of the multiple read-write operations, the timeout number representing a number of read-write operations whose time consumption exceeds a time delay threshold; and when the proportion is higher than a preset proportion, the RAID card identifies the to-be-identified hard disk as a slow disk.

[0009] In this implementation, by the relationship between the proportion of the timeout number and the preset proportion, the BMC or the RAID card can determine whether the to-be-identified hard disk has a slow disk phenomenon. The preset number proportion can be obtained by user presetting, so that the setting of the slow disk judgment standard is more flexible, and the user experience is improved.

[0010] In a possible implementation, the slow disk includes a general slow disk and a serious slow disk. The BMC obtains the latency information from the RAID card, and determines whether to identify the to-be-identified hard disk as a slow disk based on the latency information, including: the BMC obtains the latency information from the RAID card; based on the latency information, the BMC determines a first proportion of a first number of times in a number of times of the plurality of read-write operations, the first number of times representing a number of read-write operations whose read-write time exceeds a first threshold; when the first proportion of the number of times is higher than a first preset proportion of the number of times, the BMC identifies the to-be-identified hard disk as a general slow disk; based on the latency information, the BMC determines a second proportion of a second number of times in the number of times of the plurality of read-write operations, the second number of times representing a number of read-write operations whose write time exceeds a second threshold, the second threshold being greater than the first threshold; when the second proportion of the number of times is higher than a second preset proportion of the number of times, the BMC identifies the to-be-identified hard disk as a serious slow disk. Alternatively, the RAID card determines whether to identify the to-be-identified hard disk as a slow disk based on the latency information, including: based on the latency information, the RAID card determines a first proportion of a first number of times in a number of times of the plurality of read-write operations, the first number of times representing a number of read-write operations whose read-write time exceeds a first threshold; when the first proportion of the number of times is higher than a first preset proportion of the number of times, the RAID card identifies the to-be-identified hard disk as a general slow disk; based on the latency information, the RAID card determines a second proportion of a second number of times in the number of times of the plurality of read-write operations, the second number of times representing a number of read-write operations whose write time exceeds a second threshold, the second threshold being greater than the first threshold; when the second proportion of the number of times is higher than a second preset proportion of the number of times, the RAID card identifies the to-be-identified hard disk as a serious slow disk.

[0011] In the implementation mode, by setting different second threshold and first threshold, the determination criteria of two kinds of time delay information are determined; for the first timeout times exceeding the first threshold and the second timeout times exceeding the second threshold, the first preset number of times and the second preset number of times are set respectively, so as to realize the determination of the general slow disk phenomenon and the serious slow disk phenomenon of the to-be-identified hard disk. For example, by using the sliding window method, the time delay information of the read-write operation in a period (such as x seconds*m times) is counted, if the count proportion of y1 milliseconds exceeds the threshold value of 80%, it is considered that the slow disk phenomenon occurs; if the count proportion of y2 (y2>y1) milliseconds exceeds the threshold value of 70%, it is considered that the serious slow disk phenomenon occurs. For example, it is assumed that the statistical data is that the number of times greater than the first threshold value (such as 5 ms) and less than or equal to the second threshold value (such as 10 ms) is a; the number of times greater than the second threshold value is b, so as to avoid repeated counting. By using the sliding window method, the first timeout times are (a+b); the second timeout times are b. For example, it is assumed that the statistical data is that the number of times greater than the first threshold value (such as 5 ms) is c; the number of times greater than the second threshold value (such as 10 ms) is d, so as to exist repeated counting, that is, the number of times c includes the number of times d greater than the second threshold value.

[0012] In a possible implementation mode, the read-write operation includes: the RAID card writes target data to a preset area of the to-be-identified hard disk; and the RAID card reads the target data from the preset area.

[0013] In the implementation mode, by reading and writing data to the preset area of the to-be-identified hard disk through the RAID card, the read-write operation of the to-be-identified hard disk by the RAID card is realized. In other implementation modes, the normal read-write operation occurring on the business side can also be used as the read-write operation of the to-be-identified hard disk in the embodiment of the application.

[0014] In a possible implementation mode, the BMC obtains the time delay information from the RAID card, and determines whether to identify the to-be-identified hard disk as a slow disk based on the time delay information, including: the BMC obtains the time delay information from the RAID card; based on the time delay information, the BMC determines whether the to-be-identified hard disk appears a slow disk phenomenon; when the to-be-identified hard disk appears the slow disk phenomenon, the BMC determines whether the communication link from the RAID card to the to-be-identified hard disk appears a communication fault; when the communication link from the RAID card to the to-be-identified hard disk does not appear the communication fault, the BMC identifies the to-be-identified hard disk as a slow disk. Alternatively, the RAID card determines whether to identify the to-be-identified hard disk as a slow disk based on the time delay information, including: based on the time delay information, the RAID card determines whether the to-be-identified hard disk appears a slow disk phenomenon; when the to-be-identified hard disk appears the slow disk phenomenon, the RAID card determines whether the communication link from the RAID card to the to-be-identified hard disk appears a communication fault; when the communication link from the RAID card to the to-be-identified hard disk does not appear the communication fault, the RAID card identifies the to-be-identified hard disk as a slow disk.

[0015] In this implementation, a fault location troubleshooting method of slow disk phenomenon is provided. The fault location of slow disk phenomenon can be any location of the link from the RAID card to the to-be-identified hard disk, so the fault of the link from the RAID card to the to-be-identified hard disk needs to be handled. For example, the troubleshooting method of the fault in the link can be: judging the location of the fault by checking the RAID card log and the operating system log; or troubleshooting by replacing components, such as replacing the RAID card and replacing the cable.

[0016] In a possible implementation, the BMC obtains the time delay information from the RAID card, and determines whether to identify the to-be-identified hard disk as a slow disk based on the time delay information, including: the BMC obtains the time delay information from the RAID card; the BMC processes the time delay information by a sliding window method to obtain a sliding window statistical result; and the BMC determines whether to identify the to-be-identified hard disk as a slow disk according to the sliding window statistical result. Alternatively, the RAID card determines whether to identify the to-be-identified hard disk as a slow disk based on the time delay information, including: the RAID card processes the time delay information by a sliding window method to obtain a sliding window statistical result; and the RAID card determines whether to identify the to-be-identified hard disk as a slow disk according to the sliding window statistical result.

[0017] In this implementation, the sliding window method is a common method and has high calculation efficiency.

[0018] In a possible implementation, the RAID card performs multiple read-write operations on the to-be-identified hard disk to obtain the time delay information, including: the RAID card periodically performs multiple read-write operations on the to-be-identified hard disk according to a first preset period to obtain the time delay information.

[0019] In this implementation, the RAID card periodically performs multiple read-write operations on the to-be-identified hard disk, so that the BMC or the RAID card periodically performs a slow disk identification task on the to-be-identified hard disk, and a hard disk with slow disk phenomenon is found and handled in time, so as to reduce the business impact and cost loss caused by the slow disk phenomenon.

[0020] In a possible implementation, the time delay information is a statistical result of read-write time consumption of each read-write operation in the multiple read-write operations, and is a distribution of read-write time consumption corresponding to the multiple read-write operations.

[0021] In this implementation, the read-write time consumption information of the multiple read-write operations itself can be complex and large amount of data, and the time delay information is a statistical result of the read-write time consumption data, and has the characteristics of small amount of data, full information, and easy analysis.

[0022] In a possible implementation, the BMC obtains the time delay information from the RAID card, including: the BMC periodically obtains the time delay information from the RAID card according to a second preset period.

[0023] In this implementation, the BMC periodically obtains the time delay information from the RAID card, so that the BMC can periodically perform the slow disk identification task on the to-be-identified hard disk, thereby discovering and processing the hard disk with the slow disk phenomenon in time, to reduce the business impact and cost loss caused by the slow disk phenomenon.

[0024] In a second aspect, the embodiments of the present application provide a slow disk identification method, applied to a server, the server including a BMC and a to-be-identified hard disk, the method mainly including: the BMC performs multiple read-write operations on the to-be-identified hard disk to obtain time delay information, the time delay information being used to indicate read-write time consumption of the multiple read-write operations; and the BMC determines whether to identify the to-be-identified hard disk as a slow disk based on the time delay information.

[0025] In a third aspect, the embodiments of the present application provide a slow disk identification method, applied to a server, the server including a BMC, a CPU, a volume management device (VMD) and a to-be-identified hard disk, the BMC being in communication connection with the CPU, the CPU being in communication connection with the volume management device (VMD), and the volume management device (VMD) being in communication connection with the to-be-identified hard disk, the method including: the BMC sends a time delay information statistical instruction to the volume management device (VMD) via the CPU; based on the time delay information statistical instruction, the volume management device (VMD) performs multiple read-write operations on the to-be-identified hard disk to obtain time delay information, the time delay information being used to indicate read-write time consumption of the multiple read-write operations; the BMC obtains the time delay information from the volume management device (VMD) via the CPU, and determines whether to identify the to-be-identified hard disk as a slow disk based on the time delay information.

[0026] In a possible implementation, the method further includes: when the to-be-identified hard disk is identified as a slow disk, the BMC judges whether a communication link from the volume management device (VMD) to the to-be-identified hard disk has a communication failure, to process the communication failure.

[0027] In a fourth aspect, the embodiments of the present application provide a slow disk identification method, applied to a server, the server comprising a BMC, a CPU, a volume management device (VMD) and a to-be-identified hard disk, the BMC being in communication connection with the CPU; the CPU being in communication connection with the volume management device (VMD), and the volume management device (VMD) being in communication connection with the to-be-identified hard disk, the method comprising: the BMC sending a time delay information statistical instruction to the volume management device (VMD) via the CPU; based on the time delay information statistical instruction, the volume management device (VMD) performing multiple read-write operations on the to-be-identified hard disk to obtain time delay information, the time delay information being used to indicate read-write time consumption of the multiple read-write operations; and based on the time delay information, the volume management device (VMD) determining whether to identify the to-be-identified hard disk as a slow disk.

[0028] In a fifth aspect, the embodiments of the present application provide a slow disk identification method, applied to a server, the server comprising a BMC and a to-be-identified hard disk, the method comprising: the BMC sending a time delay information statistical instruction to the to-be-identified hard disk; based on the time delay information statistical instruction, the to-be-identified hard disk performing multiple read-write operations to obtain time delay information, the time delay information being used to indicate read-write time consumption of the multiple read-write operations; the BMC acquiring the time delay information from the to-be-identified hard disk, and based on the time delay information, determining whether to identify the to-be-identified hard disk as a slow disk.

[0029] In a sixth aspect, the embodiments of the present application provide a computing device, comprising: a processor and a memory. The memory has stored therein instruction operations or codes. The processor is configured to communicate with the memory and execute the instruction operations or codes in the memory to perform the method of any one of the first aspect, the second aspect, the third aspect and the implementation manners thereof.

[0030] In a seventh aspect, the embodiments of the present application provide a computer readable storage medium, comprising instructions, which, when executed on a computer, cause the computer to perform the method of any one of the first aspect, the second aspect, the third aspect and the implementation manners thereof.

[0031] In an eighth aspect, the embodiments of the present application provide a computer program product comprising instructions, which, when executed by a computing device, cause the computing device to perform the method of any one of the first aspect, the second aspect, the third aspect and the implementation manners thereof. BRIEF DESCRIPTION OF DRAWINGS

[0032] The drawings needed to be used in the following embodiment or technical description are briefly introduced as follows.

[0033] FIG. 1a is a schematic diagram of a computing device according to an embodiment of the present application;

[0034] FIG. 1b is a schematic diagram of a communication link between a BMC and a hard disk according to an embodiment of the present application;

[0035] FIG. 2a is a schematic diagram of a first communication link according to an embodiment of the present application;

[0036] FIG. 2b is a schematic diagram of a second communication link according to an embodiment of the present application;

[0037] FIG. 2c is a schematic diagram of a third communication link according to an embodiment of the present application;

[0038] FIG. 2d is a schematic diagram of a fourth communication link according to an embodiment of the present application;

[0039] FIG. 3 is a flow diagram of a first slow disk identification method according to an embodiment of the present application;

[0040] FIG. 4 is a schematic diagram of a sliding window method processing latency information according to an embodiment of the present application;

[0041] FIG. 5 is a flow diagram of a second slow disk identification method according to an embodiment of the present application;

[0042] FIG. 6 is a flow diagram of a third slow disk identification method according to an embodiment of the present application;

[0043] FIG. 7 is a flow diagram of a fourth slow disk identification method according to an embodiment of the present application;

[0044] FIG. 8 is a flow diagram of a fifth slow disk identification method according to an embodiment of the present application;

[0045] FIG. 9 is a schematic diagram of another computing device according to an embodiment of the present application. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.

[0047] The term "and / or" in the present document is used to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the three cases of A alone, A and B together, and B alone. The symbol " / " in the present document represents the relationship of or, for example, A / B represents A or B.

[0048] The terms "first" and "second" and the like in the specification and claims of the present document are used to distinguish different objects, and are not used to describe the specific order of the objects. For example, the first response message and the second response message are used to distinguish different response messages, and are not used to describe the specific order of the response messages.

[0049] In the embodiments of the present application, the word "exemplary" or "for example" is used to mean serving as an example, instance, or illustration. Any embodiment or design presented as "exemplary" or "for example" in the embodiments of the present application is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "for example" is intended to present concepts in a concrete manner.

[0050] In the description of the embodiments of the present application, unless otherwise specified, "a plurality of" means two or more, for example, a plurality of processing units means two or more processing units, and the like; a plurality of elements means two or more elements, and the like.

[0051] In order to facilitate understanding of the scheme provided by the embodiments of the present application, some terms related to the present scheme are briefly introduced.

[0052] Redundant Array of Independent Disks (RAID), also known as Redundant Array of Inexpensive Disks, refers to a large disk system formed by a plurality of independent disks, so as to achieve better storage performance and higher reliability than a single disk. RAID includes RAID0, RAID1, RAID3, RAID5, RAID6, RAID10, RAID50, and RAID60, and the like, which are various types of redundant disk arrays. The RAID group refers to a plurality of independent disks in the RAID to form a disk system.

[0053] The VMD (Volume Management Device) function is a new technology of the Purley platform. The VMD is a RAID (Redundant Arrays of Independent Disks) volume management device of an NVMe (Non-Volatile Memory express) hard disk, that is, a controller of the NVMe hard disk. The VMD can perform RAID management and lamp control on the NVMe hard disk connected to the VMD. The VMD is also referred to as a PCIe (Peripheral Component Interconnect Express) controller, which is an integrated controller in the root complex of the CPU. The VMD is integrated in the CPU and communicates with the NVMe hard disk through a PCIe port to achieve, for example, support for hot plug operations, related storage management functions, and fault tolerance functions.

[0054] Software RAID (Intel Virtual RAID on CPU, INTELVROC), also known as virtual disk array, software RAID group, soft RAID, software RAID controller, etc., is a simpler RAID solution implemented through an Intel Volume Management Device (Intel VMD), without the need for additional RAID control cards to achieve RAID. Soft RAID is to aggregate several hard disks or partitions of the same capacity size into a large virtual RAID device (or RAID0, or RAID1, or RAID5, or RAID10…), according to different use directions, if the capacity of each hard disk or partition is inconsistent, based on the smallest capacity hard disk or partition. The members of soft RAID are the entire hard disk or partition. VROC is an enterprise-level RAID solution that can release the performance of NVMe solid-state disks, which is enabled by the Intel VMD function in the Intel Xeon scalable processor, and the VMD function is an integrated controller in the CPU PCIe root complex. While Intel VROC has these advantages, it avoids the complexity, high cost and high power consumption of the Host Bus Adapter (HBA) card of the traditional hardware RAID card placed between the driver and the CPU.

[0055] The embodiment of the present application provides a slow disk identification method and related device, and the BMC performs multiple read-write operations on the hard disk to be identified through certain communication links, and identifies whether the hard disk has a slow disk phenomenon according to IO time delay fed back by the multiple read-write operations.

[0056] That is, the embodiment of the present application solves the problem of detecting the hard disk by the BMC, and the main working steps of the BMC are: realizing the communication connection with the hard disk to be identified, reading and writing the space data of the hard disk to be identified; based on the time delay information when reading and writing data, the BMC realizes the slow disk detection function of the hard disk to be identified.

[0057] Please refer to Fig. 1a, which is a component schematic diagram of a computing device provided by the embodiment of the present application. As shown in Fig. 1a, the embodiment of the present application provides a computing device 100, mainly comprising: a BMC 110, a processing module 120 and a storage module 130. The storage module 130 can include multiple hard disks. For example, as shown in Fig. 1a, the storage module 130 includes hard disk 1, hard disk 2, …, hard disk n, n is an integer greater than or equal to 1.

[0058] The computing device 100 can be a server or other type of computing device, and embodiments of the present application are not limited in this respect. A server is a device that provides a service for other devices, e.g., a server is a device that responds to service requests and performs processing. A server is generally capable of handling service requests and ensuring the availability of services, and thus a server is required to have strong processing capability, high stability, high reliability, high security, scalability, and manageability. In embodiments of the present application, the server can be an x86 server, which is also referred to as a complex instruction set computer (CISC) architecture server, i.e., a personal computer (PC) server, which is based on a PC architecture and uses an Intel or other compatible x86 instruction set processor chip and a Windows operating system.

[0059] A server can vary greatly in configuration and performance, and can include at least one central processing unit (CPU) (e.g., at least one processor) and memory, at least one storage medium (e.g., at least one mass storage device) that stores applications or data. The memory and storage medium can be volatile or non-volatile storage. The programs stored in the storage medium can include at least one module, and each module can include a series of instruction operations on the server. Further, the central processing unit can be configured to communicate with the storage medium and execute the series of instruction operations in the storage medium on the server. The server can also include at least one power supply, at least one wired or wireless network interface, at least one input / output interface, and / or at least one operating system, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, NetWare, etc. In some possible implementations, the server can also be a cloud server, which is not limited herein.

[0060] BMC (Baseboard Management Controller) 110 is a dedicated controller for monitoring and managing the computing device 100 (e.g., a server), which can be regarded as a small operating system. For example, the temperature, voltage, and other information of the computing device 100 can be monitored, and corresponding adjustment work can be performed to ensure that the computing device 100 is in a normal running state. When the computing device 100 (e.g., a server) is in an abnormal state, the computing device 100 can also be restarted by means of reset. The BMC 110 can also record information and logs of various hardware, for prompting a user using the computing device 100 (e.g., a server) and for fault positioning. It should be noted that the BMC 110 is an independent device, which does not depend on other hardware (e.g., a processor or a memory, etc.) in the computing device 100 or on an OS of the server, but the BMC 110 can interact with the OS. Generally, the BMC 110 includes a BMC storage medium and a BMC processor, which interacts with the OS through the BMC processor, so as to play a better management role. The BMC storage medium is used to store instructions required when the BMC 110 runs and data generated when the BMC 110 runs. The BMC storage medium can be a flash, a random access memory (RAM), or a read-only memory (ROM), etc., which is not limited here.

[0061] It should be noted that in other embodiments, the BMC 110 has different names in different computing devices, for example, the BMC of a Huawei server, a super-convergence server is an iBMC, the BMC of an HPE server is an iLO, and the BMC of a DELL server is an iDRAC.

[0062] The processing module 120 is a control center of the computing device 100, which connects various parts of the computing device 100 through various interfaces and lines, executes software programs and / or modules stored in the storage module 130 and calls data stored in the storage module 130, performs various functions of the computing device 100 and processes data, so as to perform overall monitoring on the computing device 100. Optionally, the processing module 120 can include one or more processing units; preferably, the processing module 120 can integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, and an application program, etc., and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor can also not be integrated into the processing module 120. In some feasible implementation manners, the processing module 120 can be a central processing unit (CPU), or can be other processors, which are not limited here.

[0063] Hard disk is the actual physical carrier for storing data. Common storage devices on the market include hard disk drives (HDD) and solid state drives (SSD). In the HDD, all the disks are mounted on a rotating shaft, and each disk is parallel to each other. There is a magnetic head on the storage surface of each disk, and the distance between the magnetic head and the disk is 0.1 microns (μm) to 0.5 μm. The higher level has reached 0.005 μm to 0.01 μm. All the magnetic heads are connected to a head controller, which is responsible for the movement of each magnetic head. The reading and writing speed of the mechanical hard disk depends on the speed of the motor, because the motor needs to drive the disk to rotate at high speed to make the magnetic head find the specified position for reading and writing. SSD, also known as solid state drive, is a hard disk made of solid state electronic storage chip array.

[0064] Referring to FIG. 1b, FIG. 1b is a schematic diagram of a communication link between the BMC and the hard disk provided in an embodiment of the present application. As shown in FIG. 1b, in different computing devices 100, the BMC 110 can have different communication links.

[0065] Optionally, as shown in FIG. 1b, in some computing devices 100, the BMC 110 is in communication connection with a RAID card 121, and the RAID card 121 is in communication connection with one or more hard disks. This communication link is referred to as a first communication link. The RAID card 121 is used to manage multiple hard disks.

[0066] Optionally, as shown in FIG. 1b, in some computing devices 100, the BMC 110 is in communication connection with a CPU 122, the CPU 122 is in communication connection with a VMD 123, and the VMD 123 is in communication connection with one or more hard disks. This communication link is referred to as a second communication link. The soft RAID is generally deployed on the CPU 122, and the soft RAID is used to manage multiple hard disks.

[0067] Optionally, as shown in FIG. 1b, in some computing devices 100, the BMC 110 is in communication connection with a CPU 122, and the CPU 122 is in communication connection with one or more hard disks. This communication link is referred to as a third communication link. The CPU 122 is directly in communication connection with one or more hard disks, and manages the one or more hard disks.

[0068] Optionally, as shown in FIG. 1b, in some computing devices 100, the BMC 110 is communicatively connected with the CPU 122, the CPU 122 is communicatively connected with the RAID card 121, and the RAID card 121 is communicatively connected with one or more hard disks. This communication link is referred to as a fourth communication link. In this case, the RAID card 121 communicates with the BMC 110 through the CPU 122, for example, the RAID card 121 can send relevant messages or instructions to the CPU 122.

[0069] Referring to FIG. 2a, FIG. 2a is a schematic diagram of the first communication link according to an embodiment of the present application. As shown in FIG. 2a, in the computing device 100, one example of the processing module 120 is the RAID card 121. Optionally, the processing module 120 further includes a hard disk backplane. One example of the storage module 130 is a RAID group. For example, as shown in FIG. 2a, the RAID group includes hard disk 1, hard disk 2, …, hard disk n, and n is an integer greater than or equal to 1.

[0070] Referring to FIG. 2b, FIG. 2b is a schematic diagram of the second communication link according to an embodiment of the present application. As shown in FIG. 2b, in the computing device 100, one example of the processing module 120 is the CPU 122 and the VMD 123. Optionally, the CPU 122 is generally deployed with software RAID to implement RAID technology through the communication connection with the RAID group via the VMD 123. One example of the storage module 130 is a RAID group. For example, as shown in FIG. 2b, the RAID group can include hard disk 1, hard disk 2, …, hard disk n, and n is an integer greater than or equal to 1. In this case, the BMC 110 can be communicatively connected with the VMD 123 through the CPU 122, and the VMD 123 is an integrated controller that can implement data read and write operations on the hard disks in the RAID group.

[0071] Referring to FIG. 2c, FIG. 2c is a schematic diagram of the third communication link according to an embodiment of the present application. As shown in FIG. 2c, in the computing device 100, one example of the processing module 120 is the CPU 122; and one example of the storage module 130 is one or more hard disks. For example, as shown in FIG. 2b, the storage module 130 can be hard disk 1, hard disk 2, …, hard disk n, and n is an integer greater than or equal to 1.

[0072] Referring to FIG. 2d, FIG. 2d is a schematic diagram of a fourth communication link according to an embodiment of the present application. As shown in FIG. 2d, in the computing device 100, one example of the processing module 120 is the CPU 122 and the RAID card 121. Optionally, the processing module 120 further includes a hard disk backplane. One example of the storage module 130 is a RAID group. As an example, as shown in FIG. 2a, the RAID group includes the hard disk 1, the hard disk 2, …, and the hard disk n, where n is an integer greater than or equal to 1. In comparison with the first communication link, the RAID card 121 communicates with the BMC 110 through the CPU 122, for example, the RAID card 121 can send relevant packets or instructions to the CPU 122.

[0073] Further, FIG. 2a and FIG. 2d can be understood as a hardware architecture, that is, the RAID card can directly communicate with the BMC; the RAID card can also indirectly communicate with the BMC, for example, the RAID card can first send packets to the CPU, and then the CPU sends the packets to the BMC, thereby realizing indirect communication between the RAID card and the BMC.

[0074] Further, in combination with FIG. 2a to FIG. 2d, the four communication links from the BMC to the to-be-identified hard disk can be understood as three different hardware architectures or three different application scenarios.

[0075] Generally, the hard disk backplane is made of a printed circuit board (PCB) and is used to connect the processing module 120, the RAID card 121, and the storage module 130, and then realize data transmission between the processing module 120, the RAID card 121, and the storage module 130 through wiring. In this way, the processing module 120 and the RAID card 121 can be connected and communicate through a peripheral component interconnect express (PCIE).

[0076] Optionally, the hard disk can be a non-volatile random access memory (NVRAM). The hard disk stores processor and operation instructions, executable modules or data structures, or a subset thereof, or an extended set thereof, wherein the operation instructions can include various operation instructions for implementing various operations. It should be noted that the computing device 100 can be built-in with multiple hard disks, for example, 8 hard disks, which are not limited herein. In some possible implementations, each hard disk can be a different type of hard disk. For example, the hard disk can be a serial attached SCSI (SAS) hard disk, a serial ATA (SATA) hard disk, or a non-volatile memory express hard disk.

[0077] Generally, the BMC 110 communicates with the RAID card 121 through an I2C interface, and the RAID card 121 manages multiple hard disks through a SAS cable, obtains working parameters of the hard disks and logical disks, and feeds back the working parameters of the hard disks and logical disks to the BMC 110 in real time, so that the BMC 110 monitors the working parameters of each hard disk and logical disk, and generates an alarm or performs log recording when necessary.

[0078] Further, the RAID card 121 includes a logic controller and a RAID chip. The logic controller is an electronic component, an electronic assembly, and a digital circuit chip. Common logic controllers include complex programmable logic devices (CPLDs) or field programmable gate arrays (FPGAs). The BMC 110 communicates with the logic controller and the RAID chip through an I2C interface, and the logic controller communicates with the RAID chip through a GPIO interface.

[0079] Generally, the computing device 100 is usually equipped with the RAID card 121, and the RAID card 121 can manage the hard disks in the computing device 100. In some possible implementations, the communication between the RAID card 121 and the storage module 130 can be RAID pass-through, just a bunch of disks (JBOD), or group RAID, which are not limited herein.

[0080] Generally, the BMC 110 can generate operation control signals according to the received instruction opcodes and timing signals to complete the operations of obtaining instructions and executing instructions. The BMC 110 can include one or more interfaces. The interfaces can include an inter-integrated circuit (I2C) interface, an improved inter integrated circuit (I3C), a serial general purpose input / output (SGPIO) interface, and the like.

[0081] The BMC 110 can communicate with the CPU 122 through an out-of-band management interface of the computing device 100 independently of the CPU 122, and can perform remote maintenance and management of the computing device 100 through a dedicated data channel. The BMC 110 controls the CPU 122 to achieve slow disk recognition of one or more hard disks connected to the CPU 122.

[0082] In some possible implementations, the computing device 100 can further include a display module and an input module (for example, a keyboard, a mouse, a touch screen, and the like, which are not limited herein).

[0083] The display module can be used to display information input by a user or information provided to the user, as well as various interfaces of the computing device 100. The display module can include a display panel, which can be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like. Further, a touch panel can cover the display panel, and when the touch panel detects a touch operation on or near the touch panel, it transmits to the processing module 120 to determine the type of touch event, and then the processing module 120 provides corresponding visual output on the display panel according to the type of touch event.

[0084] The input module can be used to receive inputted digital or character information, and to generate key signal inputs related to user settings and function controls of the computing device 100. Specifically, the input module can include a touch panel and other input devices. The touch panel, also called a touch screen, can collect touch operations of a user thereon or adjacent thereto (such as operations of the user using a finger, a stylus, or any suitable object or accessory on or adjacent to the touch panel), and drive corresponding connection devices according to a pre-set program. Optionally, the touch panel can include two parts, a touch detection device and a touch controller. The touch detection device detects the touch position of the user and detects signals caused by the touch operation, and transmits the signals to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into touch coordinates, and sends it to the processing module 120, and can also receive commands from the processing module 120 and execute them. In addition, the touch panel can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch panel, the input module can also include other input devices. Specifically, the other input devices can include one or more of a physical keyboard, function keys (such as volume control buttons, on-off buttons, etc.), trackballs, mice, joysticks, etc.

[0085] Please refer to FIG. 3, which is a flowchart of a first slow disk identification method provided by the embodiment of the present application. As shown in FIG. 3, the slow disk identification method provided by the embodiment of the present application is applied to a server, the server includes a BMC and a hard disk to be identified, and the method mainly includes the following steps:

[0086] In step S310, the BMC performs multiple read-write operations on the hard disk to be identified to obtain time delay information. The time delay information is used to indicate the read-write time consumption of the multiple read-write operations.

[0087] In step S320, based on the time delay information, the BMC determines whether to identify the hard disk to be identified as a slow disk.

[0088] In the technical solution of the embodiment of the present application, the out-of-band management software BMC performs multiple read-write operations on the hard disk to be identified, and identifies whether the hard disk to be identified has a slow disk phenomenon according to the time delay information fed back by the multiple read-write operations. That is, the technical solution of the embodiment of the present application realizes slow disk detection and identification of one or more hard disks based on the BMC, without the need for slow disk identification work under the operating system, and has a wider use scenario.

[0089] It should be noted that the slow disk identification method shown in FIG. 3 can be applied to any communication link that can realize communication between the BMC and the hard disk to be identified, such as the first communication link, the second communication link, the third communication link, and the fourth communication link described above. The embodiment of the present application does not limit this.

[0090] In a possible implementation, based on the latency information, the BMC determines a proportion of the timeout times in the total number of the multiple read-write operations, the timeout times representing the number of read-write operations whose time consumption exceeds the latency threshold; and when the proportion is higher than a preset proportion, the BMC identifies the to-be-identified hard disk as a slow disk.

[0091] For example, in a sliding window manner, the latency information of the read-write operations in a period (e.g., x seconds*m times) is counted, and if the count proportion of y1 milliseconds exceeds 80%, it is considered that the slow disk phenomenon occurs. The preset proportion can be preset by a user, so that the setting of the slow disk judgment standard is more flexible.

[0092] In a possible implementation, the slow disk includes a general slow disk and a serious slow disk. Therefore, based on the latency information, the BMC can determine a first proportion of the first timeout times in the number of the multiple read-write operations, the first timeout times representing the number of read-write operations whose time consumption exceeds a first threshold; and when the first proportion is higher than a first preset proportion, the BMC identifies the to-be-identified hard disk as a general slow disk. Based on the latency information, the BMC determines a second proportion of the second timeout times in the number of the multiple read-write operations, the second timeout times representing the number of read-write operations whose time consumption exceeds a second threshold, the second threshold being greater than the first threshold; and when the second proportion is higher than a second preset proportion, the BMC identifies the to-be-identified hard disk as a serious slow disk.

[0093] In this implementation, the determination of the general slow disk phenomenon and the serious slow disk phenomenon of the to-be-identified hard disk is realized. For example, in a sliding window manner, the latency information of the read-write operations in a period (e.g., x seconds*m times) is counted, and if the count proportion of y1 milliseconds exceeds 80%, it is considered that the slow disk phenomenon occurs; and if the count proportion of y2 (y2>y1) milliseconds exceeds 70%, it is considered that the serious slow disk phenomenon occurs.

[0094] In a possible implementation, the read-write operation includes: writing target data to a preset region of the to-be-identified hard disk; and reading the target data from the preset region.

[0095] In this implementation, the read-write operation on the to-be-identified hard disk is realized by reading and writing data to the preset region of the to-be-identified hard disk. In other implementations, the normal read-write operation occurring on the business side can also be used as the read-write operation of the to-be-identified hard disk in the embodiments of the present application.

[0096] In a possible implementation, the determining whether the to-be-identified hard disk is a slow disk based on the time delay information includes: determining, by the BMC, whether the to-be-identified hard disk has a slow disk phenomenon based on the time delay information; when the to-be-identified hard disk has the slow disk phenomenon, determining, by the BMC, whether a communication link from the BMC to the to-be-identified hard disk has a communication fault; and when the communication link from the BMC to the to-be-identified hard disk does not have the communication fault, identifying, by the BMC, the to-be-identified hard disk as the slow disk.

[0097] Further, the determining whether the to-be-identified hard disk has the slow disk phenomenon is based on whether the time delay of reading and writing data is large. There are two reasons for the large time delay: one is that the communication link has a fault, which causes the communication to be blocked and further causes the large time delay of reading and writing data; and the other is that the hard disk itself has a fault (that is, the to-be-identified hard disk itself is a slow disk), which causes the large time delay of reading and writing data. Therefore, the BMC needs to first determine whether the communication link from the BMC to the to-be-identified hard disk has a fault, and then determine whether the to-be-identified hard disk is a slow disk. For example, the way of checking the fault in the communication link can be: checking the BMC log, the RAID card log and the operating system log to determine the position of the fault; or checking the fault by replacing components, such as replacing the RAID card and the cable.

[0098] That is, the fault position causing the slow disk phenomenon can be any position of the link from the BMC to the to-be-identified hard disk, so the fault of the link from the BMC to the to-be-identified hard disk needs to be further checked to finally determine whether the to-be-identified hard disk has a hard disk fault.

[0099] In other implementations, the BMC directly reads the hard disk log to determine whether the to-be-identified hard disk is a slow disk, and then performs hard disk marking, hard disk replacement and the like. Since the hard disk log is the time delay information of the reading and writing operation recorded by the to-be-identified hard disk, there is no communication link, so it is not necessary to further check whether the communication link has a fault, but the to-be-identified hard disk can be directly determined to be a slow disk according to the hard disk log.

[0100] In the embodiment of the application, the BMC identifies the slow disk problem of the link from the BMC to the hard disk, which can be detected without deploying software through the operating system, and the use scenario is more extensive and can be applied to scenarios where the operating system does not support slow disk identification, and there is no operating system.

[0101] In the embodiments of the present application, the slow disk phenomenon refers to a phenomenon that a read-write time-consuming between an execution subject of a read-write operation and the to-be-identified hard disk is long. It is further needed to exclude a failure of a link between the execution subject and the to-be-identified hard disk. For example, when the execution subject of the read-write operation is the to-be-identified hard disk itself, there is no problem of the link failure, and thus, when it is determined that the to-be-identified hard disk is a slow disk, it can be directly determined that the to-be-identified hard disk is a failure disk, that is, a slow disk failure occurs.

[0102] In a possible implementation, the time delay information is a statistical result of a read-write time-consuming of each read-write operation in multiple read-write operations, and the time delay information is a distribution of the read-write time-consuming corresponding to the multiple read-write operations.

[0103] For example, one example of the time delay information is as follows: the number of times that is less than or equal to 5 ms is 10000; the number of times that is greater than 5 ms and less than or equal to 100 ms is 5000; the number of times that is greater than 100 ms and less than or equal to 200 ms is 500; the number of times that is greater than 200 ms or equal to 100 ms is 50; and the number of times that is greater than 240 ms is 0.

[0104] Further, the read-write time-consuming information of the multiple read-write operations is itself complex and has a large amount of data, and the time delay information is a statistical result of the read-write time-consuming data, and thus, the time delay information has the characteristics of small data amount, full information amount and easy analysis.

[0105] In a possible implementation, the time delay information is processed by using a sliding window method to obtain a sliding window statistical result, and whether the to-be-identified hard disk is identified as a slow disk is determined according to the sliding window statistical result. The sliding window method is a common method and has high calculation efficiency.

[0106] Please refer to FIG. 4, which is a schematic diagram of a sliding window method for processing latency information according to an embodiment of the present application. As shown in FIG. 4, the purpose of the sliding window method is to find the number of times that the read-write time exceeds 100 ms. The sliding window method includes the following steps: first, in the initial state, the left edge of the window (left) and the right edge of the window (right) are both 0; the closed interval [left, right] is referred to as a "window". Second, the value of the right pointer is increased to expand the range of the window [left, right] until the maximum value (for example, 240 ms) of the read-write time appears in the window. Third, the increase of the value of the right pointer is stopped, and the value of the left pointer is increased to reduce the window [left, right] until the minimum value (for example, 100 ms) of the read-write time no longer appears in the window. Finally, the number of times in the window [left, right] is 250, i.e., the number of times that the read-write time exceeds 100 ms is 250. The number of times in the window [left, right] can be calculated by a counter.

[0107] Generally, the sliding window method, also referred to as the ruler taking method, can be used to solve the problem of finding the properties (length, etc.) of a continuous interval that meets certain conditions. Since the interval is continuous, when the interval changes, the search space can be pruned by using the existing calculation results, thereby reducing repeated calculations and lowering the time complexity.

[0108] In a possible implementation, the BMC periodically performs multiple read-write operations on the to-be-identified hard disk according to a first preset period to obtain the latency information.

[0109] In this implementation, the BMC periodically performs multiple read-write operations on the to-be-identified hard disk, thereby periodically performing the slow disk identification task on the to-be-identified hard disk, so as to timely find and process the hard disk that has the slow disk phenomenon, thereby reducing the business impact and cost loss caused by the slow disk phenomenon.

[0110] For example, the BMC periodically traverses one or more hard disks to perform read-write tasks, thereby periodically performing the slow disk identification task on the one or more hard disks by the BMC. Specifically, when the BMC performs the identification task on a to-be-identified hard disk, the BMC can write a piece of random data to the reserved area of the to-be-identified hard disk through a communication link such as a CPU or a RAID card every x seconds; then reads the data and calculates the read-write time (i.e., the latency information); and through the sliding window method, the read-write time in a period (for example, x seconds*m times) is calculated. If the count proportion of the read-write time exceeding y1 ms exceeds the threshold value of 80%, it is considered that the slow disk phenomenon occurs. If the count proportion of the read-write time exceeding y2 (y2>y1) ms exceeds the threshold value of 70%, it is considered that the serious slow disk phenomenon occurs.

[0111] Referring to FIG. 5, FIG. 5 is a flowchart of a second slow disk identification method provided by the embodiment of the present application. As shown in FIG. 5, the slow disk identification method provided by the embodiment of the present application is applied to a server, the server comprising a BMC, a RAID card and a to-be-identified hard disk, the BMC being in communication connection with the RAID card, and the RAID card being in communication connection with the to-be-identified hard disk, the communication link being referred to as the first communication link described above. As shown in FIG. 5, the method mainly comprises the following steps:

[0112] In step S510, the BMC sends a time delay information statistical instruction to the RAID card.

[0113] In step S520, in response to the time delay information statistical instruction, the RAID card performs multiple read-write operations on the to-be-identified hard disk to obtain time delay information. The time delay information is used to indicate the read-write time consumption of the multiple read-write operations.

[0114] In step S530, the BMC acquires the time delay information from the RAID card, and determines whether to identify the to-be-identified hard disk as a slow disk based on the time delay information, or the RAID card determines whether to identify the to-be-identified hard disk as a slow disk based on the time delay information.

[0115] In the technical solution of the embodiment of the present application, the out-of-band management software BMC sends a time delay information statistical instruction to the RAID card, the RAID card performs multiple read-write operations on the to-be-identified hard disk, and the BMC or the RAID card identifies whether the to-be-identified hard disk has a slow disk phenomenon according to the time delay information fed back by the multiple read-write operations. That is, the technical solution of the embodiment of the present application realizes slow disk detection and identification of one or more hard disks based on the BMC and the RAID card, without the need for slow disk identification work under an operating system, and is more widely used and can be applied to scenarios where the operating system does not support slow disk identification work or does not exist.

[0116] In a possible implementation manner, the BMC acquires the time delay information from the RAID card; based on the time delay information, the BMC determines a proportion of a timeout number in a total number of the multiple read-write operations, the timeout number representing a number of read-write operations whose time consumption exceeds a time delay threshold; and when the proportion is higher than a preset proportion, the BMC identifies the to-be-identified hard disk as a slow disk. Alternatively, based on the time delay information, the RAID card determines a proportion of a timeout number in a total number of the multiple read-write operations, the timeout number representing a number of read-write operations whose time consumption exceeds a time delay threshold; and when the proportion is higher than a preset proportion, the RAID card identifies the to-be-identified hard disk as a slow disk.

[0117] In the implementation, the BMC or the RAID card can determine whether the slow disk phenomenon occurs in the to-be-identified hard disk through the preset proportion relationship of the number of timeouts. The preset proportion can be preset by a user, so that the setting of the slow disk determination criterion is more flexible, and user experience is improved.

[0118] In a possible implementation, the slow disk includes a general slow disk and a serious slow disk. The BMC obtains the time delay information from the RAID card, and determines whether to identify the to-be-identified hard disk as a slow disk based on the time delay information, including: the BMC obtains the time delay information from the RAID card; based on the time delay information, the BMC determines a first proportion of a first number of timeouts in a number of read-write operations, the first number of timeouts representing a number of read-write operations whose time consumption exceeds a first threshold; when the first proportion is higher than a first preset proportion, the BMC identifies the to-be-identified hard disk as a general slow disk; based on the time delay information, the BMC determines a second proportion of a second number of timeouts in the number of read-write operations, the second number of timeouts representing a number of read-write operations whose write time consumption exceeds a second threshold, the second threshold being greater than the first threshold; when the second proportion is higher than a second preset proportion, the BMC identifies the to-be-identified hard disk as a serious slow disk. Alternatively, the RAID card determines whether to identify the to-be-identified hard disk as a slow disk based on the time delay information, including: based on the time delay information, the RAID card determines a first proportion of a first number of timeouts in a number of read-write operations, the first number of timeouts representing a number of read-write operations whose time consumption exceeds a first threshold; when the first proportion is higher than a first preset proportion, the RAID card identifies the to-be-identified hard disk as a general slow disk; based on the time delay information, the RAID card determines a second proportion of a second number of timeouts in the number of read-write operations, the second number of timeouts representing a number of read-write operations whose write time consumption exceeds a second threshold, the second threshold being greater than the first threshold; when the second proportion is higher than a second preset proportion, the RAID card identifies the to-be-identified hard disk as a serious slow disk.

[0119] In the implementation, the determination criteria of the two types of time delay information are determined by setting different second thresholds and first thresholds; the first preset proportion and the second preset proportion are set for the first number of timeouts exceeding the first threshold and the second number of timeouts exceeding the second threshold, respectively, so as to determine the general slow disk phenomenon and the serious slow disk phenomenon of the to-be-identified hard disk.

[0120] For example, the time delay information of the read / write operation in a period (such as x seconds*m times) is counted in a sliding window manner. If the count ratio of more than y1 milliseconds exceeds a threshold of 80%, it is considered that the slow disk phenomenon occurs. If the count ratio of more than y2 (y2>y1) milliseconds exceeds a threshold of 70%, it is considered that the serious slow disk phenomenon occurs. For example, assuming that the statistical data is as follows: the number of times greater than a first threshold (such as 5 ms) and less than or equal to a second threshold (such as 10 ms) is a; the number of times greater than the second threshold is b, so that repeated counting is avoided. Through the sliding window method, the first timeout number is (a+b); the second timeout number is b. For example, assuming that the statistical data is as follows: the number of times greater than the first threshold (such as 5 ms) is c; the number of times greater than the second threshold (such as 10 ms) is d, so that repeated counting exists, that is, the number of times c includes the number of times d greater than the second threshold.

[0121] In a possible implementation, the read / write operation described above includes: the RAID card writing target data to a preset area of the to-be-identified hard disk; and the RAID card reading the target data from the preset area.

[0122] In this implementation, the read / write operation of the RAID card to the to-be-identified hard disk is implemented by reading and writing data to the preset area of the to-be-identified hard disk through the RAID card. In other implementations, the normal read / write operation occurring on the business side can also be used as the read / write operation of the to-be-identified hard disk in the embodiments of the present application.

[0123] In a possible implementation, the BMC obtains the time delay information from the RAID card, and determines whether to identify the to-be-identified hard disk as a slow disk based on the time delay information, including: the BMC obtains the time delay information from the RAID card; based on the time delay information, the BMC determines whether the to-be-identified hard disk has a slow disk phenomenon; when the to-be-identified hard disk has the slow disk phenomenon, the BMC determines whether the communication link from the RAID card to the to-be-identified hard disk has a communication fault; and when the communication link from the RAID card to the to-be-identified hard disk does not have the communication fault, the BMC identifies the to-be-identified hard disk as a slow disk. Alternatively, the RAID card determines whether to identify the to-be-identified hard disk as a slow disk based on the time delay information, including: based on the time delay information, the RAID card determines whether the to-be-identified hard disk has a slow disk phenomenon; when the to-be-identified hard disk has the slow disk phenomenon, the RAID card determines whether the communication link from the RAID card to the to-be-identified hard disk has a communication fault; and when the communication link from the RAID card to the to-be-identified hard disk does not have the communication fault, the RAID card identifies the to-be-identified hard disk as a slow disk.

[0124] In the implementation, a fault location troubleshooting method for the slow disk phenomenon is provided. The fault location causing the slow disk phenomenon can be any location of the link from the RAID card to the to-be-identified hard disk, so the fault of the link from the RAID card to the to-be-identified hard disk needs to be processed. For example, the troubleshooting method for the fault in the link can be: judging the location of the fault by checking the RAID card log and the operating system log; or troubleshooting by replacing components, such as replacing the RAID card and replacing the cable.

[0125] In a possible implementation, the BMC obtains the time delay information from the RAID card, and determines whether to identify the to-be-identified hard disk as a slow disk based on the time delay information, including: the BMC obtains the time delay information from the RAID card; the BMC processes the time delay information by using a sliding window method to obtain a sliding window statistical result; and the BMC determines whether to identify the to-be-identified hard disk as a slow disk according to the sliding window statistical result. Alternatively, the RAID card determines whether to identify the to-be-identified hard disk as a slow disk based on the time delay information, including: the RAID card processes the time delay information by using a sliding window method to obtain a sliding window statistical result; and the RAID card determines whether to identify the to-be-identified hard disk as a slow disk according to the sliding window statistical result.

[0126] In the implementation, the sliding window method is a common method and has high calculation efficiency.

[0127] In a possible implementation, the RAID card performs multiple read-write operations on the to-be-identified hard disk to obtain the time delay information, including: the RAID card periodically performs multiple read-write operations on the to-be-identified hard disk according to a first preset period to obtain the time delay information.

[0128] In the implementation, the RAID card periodically performs multiple read-write operations on the to-be-identified hard disk, so that the BMC or the RAID card periodically performs a slow disk identification task on the to-be-identified hard disk, and a hard disk with the slow disk phenomenon is found and processed in time, so as to reduce the business impact and cost loss caused by the slow disk phenomenon.

[0129] In a possible implementation, the time delay information is a statistical result of read-write time consumption of each read-write operation in the multiple read-write operations, and is a distribution of the read-write time consumption corresponding to the multiple read-write operations.

[0130] In the implementation, the read-write time consumption information of the multiple read-write operations itself can be complex and have a large amount of data, and the time delay information is a statistical result of the read-write time consumption data, and has the characteristics of small data volume, full information, and easy analysis.

[0131] In a possible implementation, the BMC obtains the time delay information from the RAID card, including: the BMC periodically obtains the time delay information from the RAID card according to a second preset period.

[0132] In this implementation, the BMC periodically obtains the time delay information from the RAID card, so that the BMC can periodically perform the slow disk identification task on the to-be-identified hard disk, thereby discovering and processing the hard disk with the slow disk phenomenon in time, to reduce the business impact and cost loss caused by the slow disk phenomenon.

[0133] It should be noted that some possible implementations of the slow disk identification method shown in FIG. 5 and the technical effects thereof are described in the description of some possible implementations of the slow disk identification method shown in FIG. 3, which will not be repeated here. That is, the corresponding technical solution implementation of the slow disk identification method shown in FIG. 5 can be referred to the possible implementations of the slow disk identification method shown in FIG. 3 and the related description thereof.

[0134] Optionally, the slow disk identification method shown in FIG. 5 can also be used for the fourth communication link described above. The technical implementation of this technical solution can be referred to the related description of FIG. 5, which will not be repeated here.

[0135] It should be noted that, in the slow disk identification method shown in FIG. 5, the BMC needs to send the time delay information statistical instruction and receive the time delay information, and obtain the slow disk identification result. The RAID card can complete the multiple read-write operations on the to-be-identified hard disk by itself to obtain the time delay information. This method can reduce the workload of the BMC and improve the work efficiency of the BMC.

[0136] For example, the BMC issues the time delay information statistical instruction of the to-be-identified hard disk to the RAID card, and the RAID card performs the statistical task of the time delay information of reading and writing data. For example, the RAID card writes a random data to the reserved area of the hard disk through the CPU or the RAID card itself every x seconds; then reads the data and counts the time delay; the BMC periodically obtains the time delay information from the RAID card, and the BMC counts the time delay information by using the sliding window method. If the count ratio of more than 100 ms exceeds the threshold value of 80%, it is considered that the slow disk phenomenon occurs. If the count ratio of more than 200 ms exceeds the threshold value of 70%, it is considered that the serious slow disk phenomenon occurs. Alternatively, the RAID card counts the time delay information by using the sliding window method. If the count ratio of more than 100 ms exceeds the threshold value of 80%, it is considered that the slow disk phenomenon occurs. If the count ratio of more than 200 ms exceeds the threshold value of 70%, it is considered that the serious slow disk phenomenon occurs.

[0137] It should be noted that, as shown in FIG. 6, the slow disk identification method, the BMC sends a time delay information statistical instruction, the RAID card can complete multiple read and write operations on the to-be-identified hard disk to obtain time delay information, and based on the time delay information, it is determined whether the to-be-identified hard disk is identified as a slow disk. This method can reduce the workload of the BMC and improve the work efficiency of the BMC.

[0138] Further, through this example, the BMC can identify the slow disk problem of the link from the RAID card to the hard disk, and the specific fault position needs to be checked. That is, through this example, the BMC can identify the slow disk problem of the link from the RAID card to the hard disk, and can not implement slow disk detection through operating system deployment software.

[0139] Please refer to FIG. 6, which is a flowchart of a third slow disk identification method provided by an embodiment of the present application. As shown in FIG. 6, the present embodiment provides a slow disk identification method applied to a server, the server comprising a BMC, a CPU, a volume management device (VMD) and a to-be-identified hard disk, the BMC and the CPU being in communication connection; the CPU and the volume management device (VMD) being in communication connection, and the volume management device (VMD) and the to-be-identified hard disk being in communication connection. The method comprises the following steps:

[0140] In step S610, the BMC sends a time delay information statistical instruction to the volume management device (VMD) via the CPU.

[0141] In step S620, in response to the time delay information statistical instruction, the volume management device (VMD) performs multiple read and write operations on the to-be-identified hard disk to obtain time delay information. The time delay information is used to indicate the read and write time consumption of the multiple read and write operations.

[0142] In step S630, the BMC acquires the time delay information from the volume management device (VMD) via the CPU, and based on the time delay information, it is determined whether the to-be-identified hard disk is identified as a slow disk.

[0143] In a possible implementation, the method further comprises: when the to-be-identified hard disk is identified as a slow disk, the BMC judges whether a communication link from the volume management device (VMD) to the to-be-identified hard disk has a communication fault, so as to handle the communication fault.

[0144] It should be noted that the slow disk identification method shown in FIG. 6 is applicable to a computing device using a volume management device (VMD). In the computing device using the volume management device (VMD), a software RAID is arranged on the CPU, and the software RAID can realize the management of the RAID group disk by the CPU in software; the volume management device (VMD) is an integrated controller, and can realize the communication connection of the CPU to the RAID group disk in hardware. Further, the application scenario can be understood as a soft and hard combined management mode for the RAID disk group. The volume management device (VMD) of the computing device can provide the hardware RAID configuration capability and the hardware acceleration capability; and in the operating system, the management capability for the RAID disk group is presented in the form of software RAID.

[0145] For example, the BMC issues a time delay information statistical instruction of the to-be-identified hard disk to the volume management device (VMD), and the volume management device (VMD) performs a statistical task of reading and writing data time consumption (i.e. time delay information). For example, the volume management device (VMD) writes a random data to the reserved area of the hard disk through the CPU or the volume management device (VMD) itself every x seconds; then reads the data and counts the reading and writing time consumption; the BMC periodically acquires the time delay information from the volume management device (VMD), and the BMC acquires the time delay information from the volume management device (VMD) in a sliding window manner. If the count proportion of more than 100 ms exceeds the threshold value of 80%, it is considered that the slow disk phenomenon occurs. If the count proportion of more than 200 ms exceeds the threshold value of 70%, it is considered that the serious slow disk phenomenon occurs.

[0146] It should be noted that, in the slow disk identification method shown in FIG. 6, the BMC needs to send a time delay information statistical instruction and receive time delay information, and obtain the slow disk identification result. The volume management device (VMD) can complete the multiple reading and writing operations on the to-be-identified hard disk by itself to obtain the time delay information. The method can reduce the workload of the BMC and improve the working efficiency of the BMC.

[0147] Please refer to FIG. 7, which is a flowchart of a fourth slow disk identification method provided by the embodiment of the present application. As shown in FIG. 7, the embodiment of the present application provides a slow disk identification method applied to a server, the server comprising a BMC, a CPU, a volume management device (VMD) and a to-be-identified hard disk, the BMC and the CPU being in communication connection; the CPU and the volume management device (VMD) being in communication connection, and the volume management device (VMD) and the to-be-identified hard disk being in communication connection. The method comprises the following steps:

[0148] In step S710, the BMC sends a time delay information statistical instruction to the volume management device (VMD) via the CPU.

[0149] In step S720, in response to the time delay information statistical instruction, the volume management device (VMD) performs multiple read-write operations on the to-be-identified hard disk to obtain time delay information. The time delay information is used to indicate the read-write time consumption of the multiple read-write operations.

[0150] In step S730, the volume management device (VMD) determines whether to identify the to-be-identified hard disk as a slow disk based on the time delay information.

[0151] It should be noted that, as shown in FIG. 7, the BMC sends the time delay information statistical instruction, and the volume management device (VMD) can complete the multiple read-write operations on the to-be-identified hard disk to obtain the time delay information, and determine whether to identify the to-be-identified hard disk as a slow disk based on the time delay information. This method can greatly reduce the workload of the BMC and improve the work efficiency of the BMC.

[0152] For example, the BMC sends the time delay information statistical instruction of the to-be-identified hard disk to the volume management device (VMD), and the volume management device (VMD) performs the statistical task of read-write data time consumption (i.e., time delay information). For example, the volume management device (VMD) writes a random data to the reserved area of the hard disk through the CPU or the volume management device (VMD) itself every x seconds; then reads the data to count the read-write time consumption; and the volume management device (VMD) uses the sliding window method. If the count proportion of more than 100 ms exceeds the threshold value of 80%, it is considered that the slow disk phenomenon occurs, and if the count proportion of more than 200 ms exceeds the threshold value of 70%, it is considered that the serious slow disk phenomenon occurs.

[0153] Please refer to FIG. 8, which is a flowchart of a fifth slow disk identification method provided by an embodiment of the present application. As shown in FIG. 8, the present embodiment provides a slow disk identification method applied to a server, the server comprising a BMC and a to-be-identified hard disk, and the method comprises the following steps:

[0154] In step S810, the BMC sends a time delay information statistical instruction to the to-be-identified hard disk.

[0155] In step S820, in response to the time delay information statistical instruction, the to-be-identified hard disk performs multiple read-write operations to obtain time delay information. The time delay information is used to indicate the read-write time consumption of the multiple read-write operations.

[0156] In step S830, the BMC obtains the time delay information from the to-be-identified hard disk, and determines whether to identify the to-be-identified hard disk as a slow disk based on the time delay information.

[0157] It should be noted that the slow disk identification method shown in FIG. 8 does not limit the communication link. The BMC sends a time delay information statistical instruction; the to-be-identified hard disk performs multiple read-write operations according to the time delay information statistical instruction to obtain time delay information; and the BMC determines whether to identify the to-be-identified hard disk as a slow disk based on the time delay information. Exemplarily, the method can greatly reduce the workload of the BMC and improve the work efficiency of the BMC.

[0158] Exemplarily, the BMC issues a time delay information statistical instruction to the to-be-identified hard disk, and the to-be-identified hard disk performs a statistical task of time consumption (i.e., time delay information) of reading and writing data: the BMC periodically obtains time delay information from the hard disk, and the BMC considers that a slow disk phenomenon occurs if a count ratio of more than 100 ms exceeds a threshold of 80%, or considers that a serious slow disk phenomenon occurs if a count ratio of more than 200 ms exceeds a threshold of 70%, in a sliding window manner.

[0159] In the embodiment of the application, the slow disk identification method shown in FIG. 8 can identify the slow disk problem of the hard disk. Further, through the slow disk identification method shown in FIG. 8, the BMC can identify the slow disk problem of the hard disk, and can not implement slow disk detection through operating system deployment software.

[0160] Optionally, the to-be-identified hard disk can statistically record the read-write time consumption of the overall hard disk, and the read-write operation can be a read-write operation issued by the business side or a read-write operation on the reserved area based on the slow disk identification task.

[0161] Optionally, the hard disk log information is obtained, the performance data of the read-write time consumption is extracted, the time delay information is obtained, and then the slow disk identification and detection are implemented.

[0162] The embodiment of the application does not limit the channel and communication protocol between the BMC and the to-be-identified hard disk. The embodiment of the application does not limit the hard disk specifications, types and the like, as long as the out-of-band management of the BMC is supported. The embodiment of the application does not limit the hard disk controller type (such as software RAID, RAID card and the like), as long as the out-of-band management is supported.

[0163] In the embodiment of the application, through the slow disk identification method shown in FIG. 8, the BMC directly obtains the time delay information from the to-be-identified hard disk, and determines whether to identify the to-be-identified hard disk as a slow disk based on the time delay information. Since the time delay information is the time delay information of the read-write operation recorded by the to-be-identified hard disk, there is no communication link. Therefore, it is not necessary to further investigate whether the communication link has a fault, and the BMC can directly determine whether the to-be-identified hard disk is a slow disk according to the time delay information.

[0164] Based on the same concept as the foregoing slow disk identification method, the embodiment of the application further provides a computing device.

[0165] Referring to FIG. 9, FIG. 9 is a schematic diagram of another computing device according to an embodiment of the present application. As shown in FIG. 9, the computing device 900 includes at least one processor 910, a memory 920, and a communication interface 930. The processor 910, the memory 920, and the communication interface 930 are communicatively connected, which can be achieved by wired (for example, bus) or wireless communication. The communication interface 930 is configured to receive data sent by other devices, the memory 920 stores computer instructions, and the processor 910 executes the computer instructions to execute the method in the foregoing method embodiments.

[0166] It should be understood that, in the embodiments of the present application, the processor 910 can be a central processing unit CPU, and the processor 910 can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0167] The memory 920 can include read-only memory and random access memory, and provide instructions and data for the processor 910. The memory 920 can also include non-volatile random access memory.

[0168] The memory 920 can be a volatile memory or a nonvolatile memory, or can include both volatile and nonvolatile memory. The nonvolatile memory can be a read-only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically EPROM (EEPROM), or flash memory, among others. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example, and not limitation, many forms of RAM are available, for example, static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and direct Rambus RAM (DR RAM). The storage 930 can include a hard disk drive (HDD) or a solid state drive (SSD), among others. The storage 930 can be used to store data, software, programs, and / or databases, among others. The storage 930 can be used to store the operating system 910, the software 920, and the data 930, among others.

[0169] It should be understood that the computing device 900 according to the embodiments of the present application can perform the method mentioned in the embodiments of the present application, and the detailed description of the implementation of the method is described above. For brevity, it will not be repeated here.

[0170] The embodiments of the present application provide a computer readable storage medium, which stores a computer program. When the computer program is executed by a processor, the method mentioned above is implemented.

[0171] The embodiments of the present application provide a computer program or a computer program product, which includes instructions. When the instructions are executed, the computer performs the method mentioned above.

[0172] Those skilled in the art should further understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been described in the above description in a general manner. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0173] The steps of the method or algorithm described in combination with the embodiments disclosed herein can be implemented in hardware, software executed by a processor, or a combination of both. The software module can be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0174] The above specific embodiments further illustrate the purpose, technical solutions and beneficial effects of the present application. It should be understood that the above description is only a specific embodiment of the present application and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A slow disk recognition method, characterized by, The application is applied to a server, the server comprises a BMC, a RAID card and a hard disk to be identified, the BMC is in communication connection with the RAID card, the RAID card is in communication connection with the hard disk to be identified, and the method comprises: The BMC sends a time delay information statistical instruction to the RAID card; Based on the time delay information statistical instruction, the RAID card performs multiple read-write operations on the hard disk to be identified to obtain time delay information, and the time delay information is used to indicate the read-write time consumption of the multiple read-write operations; The BMC obtains the time delay information from the RAID card, and determines whether to identify the hard disk to be identified as a slow disk based on the time delay information, or the RAID card determines whether to identify the hard disk to be identified as a slow disk based on the time delay information.

2. The method of claim 1, wherein, The BMC obtains the time delay information from the RAID card, and determines whether to identify the hard disk to be identified as a slow disk based on the time delay information, or the RAID card determines whether to identify the hard disk to be identified as a slow disk based on the time delay information. The BMC obtains the time delay information from the RAID card; Based on the time delay information, the BMC determines a proportion of a timeout number in a total number of the multiple read-write operations, and the timeout number represents a number of read-write operations whose read-write time consumption exceeds a time delay threshold value; When the proportion is higher than a preset proportion, the BMC identifies the hard disk to be identified as a slow disk; Or, the RAID card determines whether to identify the hard disk to be identified as a slow disk based on the time delay information, comprising: Based on the time delay information, the RAID card determines a proportion of a timeout number in a total number of the multiple read-write operations, and the timeout number represents a number of read-write operations whose read-write time consumption exceeds a time delay threshold value; When the proportion is higher than a preset proportion, the RAID card identifies the hard disk to be identified as a slow disk.

3. The method of claim 1, wherein, The slow disk comprises a general slow disk and a serious slow disk; The BMC obtains the time delay information from the RAID card, and determines whether to identify the hard disk to be identified as a slow disk based on the time delay information, or the RAID card determines whether to identify the hard disk to be identified as a slow disk based on the time delay information. The BMC obtains the time delay information from the RAID card; Based on the time delay information, the BMC determines a first number proportion of a first timeout number in a number of the multiple read-write operations, and the first timeout number represents a number of read-write operations whose read-write time consumption exceeds a first threshold value; When the first number proportion is higher than a first preset number proportion, the BMC identifies the hard disk to be identified as a general slow disk; Based on the time delay information, the BMC determines a second number proportion of a second timeout number in the number of the multiple read-write operations, and the second timeout number represents a number of read-write operations whose read-write time consumption exceeds a second threshold value, and the second threshold value is greater than the first threshold value; When the second number proportion is higher than a second preset number proportion, the BMC identifies the hard disk to be identified as a serious slow disk; Or, the RAID card determines whether to identify the hard disk to be identified as a slow disk based on the time delay information, comprising: Based on the latency information, the RAID card determines a first time proportion of a first timeout number in the number of times of the plurality of read-write operations, the first timeout number representing a number of read-write operations whose read-write time consumption exceeds a first threshold value; When the first time proportion is higher than a first preset time proportion, the RAID card identifies the to-be-identified hard disk as a general slow disk; Based on the latency information, the RAID card determines a second time proportion of a second timeout number in the number of times of the plurality of read-write operations, the second timeout number representing a number of read-write operations whose write time consumption exceeds a second threshold value, the second threshold value being greater than the first threshold value; When the second time proportion is higher than a second preset time proportion, the RAID card identifies the to-be-identified hard disk as a serious slow disk.

4. The method according to any one of claims 1 to 3, characterized in that, The read-write operation includes: The RAID card writes target data to a preset area of the to-be-identified hard disk; The RAID card reads the target data from the preset area.

5. The method according to any one of claims 1 to 4, characterized in that, The BMC obtains the latency information from the RAID card, and determines whether to identify the to-be-identified hard disk as a slow disk based on the latency information, including: The BMC obtains the latency information from the RAID card; Based on the latency information, the BMC determines whether the to-be-identified hard disk has a slow disk phenomenon; When the to-be-identified hard disk has a slow disk phenomenon, the BMC determines whether a communication link from the RAID card to the to-be-identified hard disk has a communication failure; When the communication link from the RAID card to the to-be-identified hard disk does not have a communication failure, the BMC identifies the to-be-identified hard disk as a slow disk; Alternatively, the RAID card determines whether to identify the to-be-identified hard disk as a slow disk based on the latency information, including: Based on the latency information, the RAID card determines whether the to-be-identified hard disk has a slow disk phenomenon; When the to-be-identified hard disk has a slow disk phenomenon, the RAID card determines whether a communication link from the RAID card to the to-be-identified hard disk has a communication failure; When the communication link from the RAID card to the to-be-identified hard disk does not have a communication failure, the RAID card identifies the to-be-identified hard disk as a slow disk.

6. The method according to any one of claims 1 to 5, characterized in that, The BMC obtains the latency information from the RAID card, and determines whether to identify the to-be-identified hard disk as a slow disk based on the latency information, including: The BMC obtains the latency information from the RAID card; The BMC processes the latency information by a sliding window method to obtain a sliding window statistical result; According to the sliding window statistical result, the BMC determines whether to identify the to-be-identified hard disk as a slow disk; Alternatively, the RAID card determines whether to identify the to-be-identified hard disk as a slow disk based on the latency information, including: The RAID card processes the latency information by a sliding window method to obtain a sliding window statistical result; According to the sliding window statistical result, the RAID card determines whether to identify the to-be-identified hard disk as a slow disk.

7. A slow disk recognition method characterized by, Applied to a server, the server includes a BMC and a to-be-identified hard disk, and the method includes: The BMC performs multiple read-write operations on the to-be-identified hard disk to obtain time delay information, the time delay information being used to indicate read-write time consumption of the multiple read-write operations. Based on the time delay information, the BMC determines whether to identify the to-be-identified hard disk as a slow disk.

8. A slow disk recognition method characterized by, The application is applied to a server, the server comprising a BMC, a CPU, a volume management device and a to-be-identified hard disk, the BMC being in communication connection with the CPU; the CPU being in communication connection with the volume management device, the volume management device being in communication connection with the to-be-identified hard disk, the method comprising: The BMC sends a time delay information statistical instruction to the volume management device via the CPU; Based on the time delay information statistical instruction, the volume management device performs multiple read-write operations on the to-be-identified hard disk to obtain time delay information, the time delay information being used to indicate read-write time consumption of the multiple read-write operations; The BMC obtains the time delay information from the volume management device via the CPU, and determines whether to identify the to-be-identified hard disk as a slow disk based on the time delay information, or the volume management device determines whether to identify the to-be-identified hard disk as a slow disk based on the time delay information.

9. A slow disk recognition method characterized by, The application is applied to a server, the server comprising a BMC and a to-be-identified hard disk, the method comprising: The BMC sends a time delay information statistical instruction to the to-be-identified hard disk; Based on the time delay information statistical instruction, the to-be-identified hard disk performs multiple read-write operations to obtain time delay information, the time delay information being used to indicate read-write time consumption of the multiple read-write operations; The BMC obtains the time delay information from the to-be-identified hard disk, and determines whether to identify the to-be-identified hard disk as a slow disk based on the time delay information.

10. A computing device, comprising: The computing device comprises a processor and a memory, the memory storing instruction operations or codes; the processor is configured to communicate with the memory and execute the instruction operations or codes in the memory to execute the method in any one of claims 1-9.

Images