Storage array optimization method and device based on thermodynamic diagram perception and storage array

Abstract

The invention provides a storage array optimization method and device based on thermodynamic diagram perception and a storage array, and relates to the technical field of storage optimizing.The method comprises the steps that initial thermodynamic diagrams corresponding to at least one hard disk type in the storage array are obtained, the initial thermodynamic diagram is used for representing a predicted temperature distribution condition corresponding to each storage slot in the storage array; based on the initial thermodynamic diagrams, target slots corresponding to at least two in-place hard disks in the storage array are determined; the at least two in-place hard disks comprise a working hard disk and an idle hot spare disk; updating a real-time thermodynamic diagram based on each initial thermodynamic diagram and a target slot position corresponding to each working hard disk; and under the condition that the hard disk is abnormal, based on the updated real-time thermodynamic diagram, determining a first target hard disk from the idle hot spare disk to perform abnormal hard disk reconstruction so as to optimize the storage array. According to the invention, the reconstruction effect of the abnormal hard disk can be improved, so that the operation stability of the storage array is improved.

Description

Technical Field

[0001] The present invention relates to the field of storage optimization technology, and in particular to a storage array optimization method, device and storage array based on heat map perception. Background Art

[0002] In the event of a hard drive anomaly such as hard drive damage or data loss, the abnormal hard drive is generally rebuilt to restore data integrity and ensure the normal operation of the storage array. At the same time, it prevents the abnormal hard drive from developing into a more serious failure.

[0003] In existing technology, when rebuilding an abnormal hard drive, the system typically removes the abnormal drive from the storage array and replaces it with a new drive of the same specifications and capacity, automatically synchronizing the storage array and restoring data. However, this reconstruction process does not effectively optimize the thermal environment of the storage array, which in turn affects the operational stability of the storage array. Summary of the Invention

[0004] The present invention provides a storage array optimization method, device and storage array based on thermal map perception, which are used to solve the defect in the prior art that the optimization effect of the thermal environment corresponding to the storage array during the reconstruction process is poor, thereby affecting the operational stability of the storage array.

[0005] The present invention provides a storage array optimization method based on heat map perception, comprising:

[0006] Obtaining an initial thermal map corresponding to at least one hard disk type in a storage array, wherein the initial thermal map is used to represent a predicted temperature distribution corresponding to each storage slot in the storage array;

[0007] Based on each of the initial heat maps, determining target slots corresponding to at least two in-place hard disks in the storage array and a real-time heat map; the at least two in-place hard disks include a working hard disk and an idle hot spare disk;

[0008] Based on each of the initial heat maps and the target slots corresponding to the working hard disks, updating the real-time heat map;

[0009] In the case of a hard disk anomaly, based on the updated real-time heat map, a first target hard disk is determined from the idle hot spare disks to perform abnormal hard disk reconstruction, so as to optimize the storage array.

[0010] According to the storage array optimization method based on heat map perception provided by the present invention, updating the real-time heat map based on each of the initial heat maps and the target slots corresponding to the working hard disks includes:

[0011] Obtaining the busyness of each working hard disk in the current test cycle;

[0012] Determining a second target hard disk based on the busyness corresponding to each of the working hard disks;

[0013] Obtaining a detected temperature corresponding to the second target hard disk;

[0014] The real-time heat map is updated based on each of the initial heat maps, and the detected temperature and target slot corresponding to the second target hard disk.

[0015] According to the storage array optimization method based on heat map perception provided by the present invention, determining the second target hard disk based on the busyness corresponding to each of the working hard disks includes:

[0016] Determining at least one third target hard disk corresponding to a minimum busyness based on the busyness corresponding to each of the working hard disks;

[0017] Obtaining the IO queue duration or IO delay duration of each of the third target hard disks within a preset duration;

[0018] The third target hard disk corresponding to the minimum IO queueing time or the minimum IO delay time is determined as the second target hard disk.

[0019] According to the storage array optimization method based on heat map perception provided by the present invention, updating the real-time heat map based on each of the initial heat maps and the detected temperature and target slot corresponding to the second target hard disk includes:

[0020] Determining a target hard disk type corresponding to the second target hard disk;

[0021] Obtaining a predicted temperature corresponding to the target slot from an initial thermal map corresponding to the target hard disk type;

[0022] The real-time thermal map is updated based on the detected temperature and the predicted temperature.

[0023] According to the storage array optimization method based on heat map perception provided by the present invention, updating the real-time heat map based on the detected temperature and the predicted temperature includes:

[0024] Obtaining adjacent detected temperatures corresponding to adjacent hard disks of the second target hard disk and adjacent predicted temperatures of the adjacent hard disks in the initial heat map; determining a detected temperature ranking based on the detected temperatures and the adjacent detected temperatures, and determining a predicted temperature ranking based on the predicted temperatures and the adjacent predicted temperatures; and if the detected temperature ranking matches the predicted temperature ranking, determining the detected temperature as the real-time temperature corresponding to the target slot in the real-time heat map;

[0025] or,

[0026] Determine a temperature difference between the detected temperature and the predicted temperature. If the temperature difference is less than or equal to a preset threshold, determine the detected temperature as the real-time temperature corresponding to the target slot in the real-time thermal map.

[0027] According to the storage array optimization method based on heat map perception provided by the present invention, in the case of a hard disk abnormality, determining a first target hard disk from the idle hot spare disks based on the updated real-time heat map includes:

[0028] When it is determined that a hard disk is abnormal, determining a predicted temperature corresponding to each of the idle hot spare disks from the real-time thermal map;

[0029] The idle hot spare disk corresponding to the lowest predicted temperature is determined as the first target hard disk.

[0030] According to the storage array optimization method based on heat map perception provided by the present invention, determining target slots corresponding to at least two in-place hard disks in the storage array based on each of the initial heat maps includes:

[0031] Obtaining the predicted temperature corresponding to each storage slot in each of the initial thermal maps;

[0032] Sort all predicted temperatures in order from low to high to obtain the predicted sorting results;

[0033] Based on the prediction sorting results, determining the target slot corresponding to each of the working hard disks in sequence, and determining the recommended slots corresponding to the idle hot spare disks, where the number of the recommended slots is greater than or equal to the number of the idle hot spare disks;

[0034] The recommended slots having the same number as the idle hot spare disks among the recommended slots are determined as target slots corresponding to the idle hot spare disks.

[0035] The present invention also provides a storage array optimization device based on heat map perception, comprising:

[0036] an acquisition module, configured to acquire an initial thermal map corresponding to at least one type of hard disk in a storage array, wherein the initial thermal map is used to represent a predicted temperature distribution corresponding to each storage slot in the storage array;

[0037] A first determination module is configured to determine target slots corresponding to at least two in-place hard disks in the storage array and a real-time heat map based on each of the initial heat maps; the at least two in-place hard disks include a working hard disk and an idle hot spare disk;

[0038] A second determining module is configured to update the real-time heat map based on each of the initial heat maps and the target slots corresponding to the working hard disks;

[0039] The optimization module is used to determine a first target hard disk from the idle hot spare disks to perform abnormal hard disk reconstruction based on the updated real-time heat map in the event of a hard disk anomaly, so as to optimize the storage array.

[0040] The present invention also provides a storage array comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the storage array optimization method based on thermal map perception as described above is implemented.

[0041] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described storage array optimization methods based on thermal map perception.

[0042] The storage array optimization method, device and storage array based on heat map perception provided by the present invention, after obtaining the initial heat map corresponding to each storage slot in the storage array corresponding to each hard disk type, select the target slot corresponding to each in-place hard disk in the storage array according to each initial heat map, and then place the working hard disk and the idle hot spare disk in their respective corresponding target slots to obtain a real-time heat map. In the case of a hard disk abnormality, according to the real-time heat map, that is, according to the real-time thermal environment corresponding to the storage array, the first target hard disk is selected from the idle hot spare disks to rebuild the abnormal hard disk, optimize the heat dissipation layout of the storage array, provide a stable thermal environment for the reconstruction of the abnormal hard disk, improve the reconstruction effect of the abnormal hard disk, and thus improve the operating stability of the storage array. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0044] Figure 1 1 is a flow chart of a storage array optimization method based on heat map perception provided by an embodiment of the present invention;

[0045] Figure 2 is a schematic diagram of an initial heat map provided by an embodiment of the present invention;

[0046] Figure 3 is a schematic diagram of an initial real-time heat map provided by an embodiment of the present invention;

[0047] Figure 4 Schematic diagram of the structure of a storage array optimization device based on heat map perception provided by an embodiment of the present invention;

[0048] Figure 5 It is a schematic diagram of the structure of a storage array provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0049] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0050] In order to solve the problem that the optimization effect of the thermal environment corresponding to the storage array during the reconstruction process in the prior art is poor, thereby affecting the operational stability of the storage array, an embodiment of the present invention provides a storage array optimization method based on thermal map perception. Figure 1 is a flow chart of a storage array optimization method based on heat map perception provided by an embodiment of the present invention, such as Figure 1 As shown, the method includes:

[0051] Step 110: Obtain an initial thermal map corresponding to at least one type of hard disk in the storage array, wherein the initial thermal map is used to represent a predicted temperature distribution corresponding to each storage slot in the storage array.

[0052] Specifically, in storage arrays with different storage structures, due to different fan layouts and air duct structures, the hard disk temperatures of the same type of hard disks in different storage slots are different under the same business pressure, and the IO (Input Output) of the business carried by hard disks of different hard disk types is different, resulting in different hard disk temperature performance when carrying business. Therefore, the thermal environment of a high-density storage array is closely related to the hard disk type and the storage structure corresponding to the storage array. Therefore, in order to improve the reconstruction efficiency of abnormal hard disks, before rebuilding the abnormal hard disks, it is necessary to first determine the hard disk type of each hard disk in the storage array, as well as the initial thermal map corresponding to each hard disk type, and clarify the predicted temperature distribution corresponding to different storage slots in the storage array.

[0053] Optionally, each of the above initial heat maps is obtained by testing in a laboratory using the same type of hard drives stored in a storage structure with the same layout as the storage array. That is, the initial heat map corresponds one-to-one with the hard drive type. After the initial heat map is generated, it can be stored on the system disk of the storage array. After the storage array is started, the hard drive type can be determined and the initial heat map corresponding to the hard drive type can be retrieved.

[0054] Optionally, the initial thermal map may include the storage structure of the storage array, the preset temperature corresponding to each row and column of storage slots, the temperature change trend corresponding to each row and column of storage slots, the temperature difference between any two storage slots, and the air duct structure. For example, Figure 2 is a schematic diagram of the initial heat map provided by an embodiment of the present invention, such as Figure 2 As shown, the storage structure of the storage array corresponding to the initial thermal map is 4 rows and 3 columns, and there are a total of 12 storage slots in the storage array, that is, the storage array can store a total of 12 hard disks, wherein the temperature change trend of the storage slots in each row is that the temperature increases from the outside to the inside along the air duct, that is, the temperatures of storage slots 1, storage slots 2, and storage slots 3 in the first row of storage slots decrease in sequence, the temperatures of storage slots 4, storage slots 5, and storage slots 6 in the second row of storage slots decrease in sequence, the temperatures of storage slots 7, storage slots 8, and storage slots 9 in the third row of storage slots decrease in sequence, and the temperatures of storage slots 10, storage slots 11, and storage slots 12 in the fourth row of storage slots decrease in sequence. The temperature change trend of each column of storage slots is a decreasing temperature from high to low. That is, in the first column of storage slots, the temperatures of storage slots 1, 4, 7, and 10 decrease in sequence; in the second column of storage slots, the temperatures of storage slots 2, 5, 8, and 11 decrease in sequence; and in the third column of storage slots, the temperatures of storage slots 3, 6, 9, and 12 decrease in sequence. This embodiment of the present invention does not limit the storage structure of the storage array.

[0055] In addition, the initial heat map also includes storage slot placement recommendations in a non-full-frame hard drive environment, that is, which slots are recommended for placing hard drives in a non-full-frame hard drive environment and which slots are recommended to be vacant in a non-full-frame hard drive environment. After loading the initial heat map, the storage array can obtain placement recommendations on which slots are vacant and which slots can be used to place hard drives. The multiple hard drives in each storage slot in the storage array include working hard drives that carry business and idle hot spare disks that temporarily do not carry business. The idle hot spare disk is used to rebuild the abnormal working hard drive when the working hard drive that carries business is abnormal, replace the hard drive to carry business, and restore the business of the storage array.

[0056] Optionally, the hard disk type of the hard disk may include HDD (Hard Disk Drive, mechanical hard disk) and SSD (Solid State Drives, solid state drive), etc., which is not limited in the embodiment of the present invention.

[0057] Step 120: Based on each of the initial heat maps, determine target slots corresponding to at least two in-place hard disks in the storage array and a real-time heat map; the at least two in-place hard disks include a working hard disk and an idle hot spare disk.

[0058] Specifically, after determining each initial heat map, the target slot corresponding to each hard disk in the storage array is determined according to the hard disk placement suggestions in the initial heat map, that is, which storage slots are used to place working hard disks and which storage slots are used to place idle hot spare disks. When building the storage array, the thermal environment of each hard disk in place is pre-optimized according to the storage structure of the storage array. After placing the corresponding working hard disk and idle hot spare disk according to each target slot, a real-time heat map can be obtained.

[0059] Furthermore, determining target slots corresponding to at least two in-place hard disks in the storage array based on each of the initial heat maps includes:

[0060] Obtaining the predicted temperature corresponding to each storage slot in each of the initial thermal maps;

[0061] Sort all predicted temperatures in order from low to high to obtain the predicted sorting results;

[0062] Based on the prediction sorting results, determining the target slot corresponding to each of the working hard disks in sequence, and determining the recommended slots corresponding to the idle hot spare disks, where the number of the recommended slots is greater than or equal to the number of the idle hot spare disks;

[0063] The recommended slots having the same number as the idle hot spare disks among the recommended slots are determined as target slots corresponding to the idle hot spare disks.

[0064] Specifically, when hard disks are placed in each storage slot of the storage array according to the initial thermal map, the predicted temperature corresponding to each storage slot can be obtained from the initial thermal map. After sorting the predicted temperatures from low to high, each working hard disk is preferentially placed in a storage slot in a low-temperature area according to the predicted sorting results. Based on the storage structure of the storage array, the heat dissipation effect of each working hard disk is optimized. After all working hard disks are placed, the remaining storage slots except the target slots corresponding to each working hard disk are determined as recommended slots corresponding to idle hot spare disks, and the number of recommended slots is greater than or equal to the number of idle hot spare disks. Afterwards, the recommended slots with the same number of idle hot spare disks are arbitrarily selected from the recommended slots as the target slots corresponding to each idle hot spare disk.

[0065] For example, Figure 2As shown, when placing hard disks in each storage slot in the storage array, storage slot 6 and storage slot 9 can be selected to be vacant, and the remaining storage slots are all placed with hard disks, among which the number of working hard disks is eight and the number of idle hot spare disks is two. Storage slot 1, storage slot 4, storage slot 7, storage slot 10, storage slot 2, storage slot 5, storage slot 8 and storage slot 11 in the low-temperature area outside the air duct can be preferentially selected, and according to the predicted temperatures corresponding to the above storage slots in the initial thermal map, a predicted sorting result is constructed in the order of predicted temperatures from low to high. The predicted sorting result can be storage slot 10, storage slot 7, storage slot 4, storage slot 1, storage slot 11, storage slot 8, storage slot 5 and storage slot 2. According to the above predicted sorting result, the working hard disks are placed in the corresponding storage slots in turn. Secondly, the remaining storage slots 3 and 12 are determined as the recommended slots for the idle hot spare disks. When determining the target slots corresponding to the idle hot spare disks based on the recommended slots, the target slots corresponding to the idle hot spare disks can be arbitrarily selected from storage slots 3 and 12. For example, storage slot 3 is determined as the target slot corresponding to the idle hot spare disk 1, and storage slot 12 is determined as the target slot corresponding to the idle hot spare disk 2. Alternatively, storage slot 3 is determined as the target slot corresponding to the idle hot spare disk 2, and storage slot 12 is determined as the target slot corresponding to the idle hot spare disk 1. After placing the above-mentioned working hard disk and idle hot spare disk, and after each in-place hard disk is running, the following can be obtained. Figure 3 As shown in the real-time thermal diagram, the temperature of each row of hard disks decreases from the outside to the inside along the air duct, and the temperature of each column of hard disks decreases from high to low. Therefore, in this real-time thermal diagram, the temperature of the working hard disk 1 is the highest, and the temperature of the idle hot spare disk 12 is the lowest.

[0066] Step 130: Update the real-time heat map based on the initial heat maps and the target slots corresponding to the working hard disks.

[0067] Specifically, after determining each initial thermal map and placing the corresponding working hard disk and idle hot spare disk in each target slot, the initial thermal map and the presence status of each in-place hard disk are combined to obtain a real-time thermal map to reflect the real-time thermal environment in the storage array.

[0068] Furthermore, updating the real-time heat map based on each of the initial heat maps and the target slots corresponding to the working hard disks includes:

[0069] Obtaining the busyness of each working hard disk in the current test cycle;

[0070] Determining a second target hard disk based on the busyness corresponding to each of the working hard disks;

[0071] Obtaining a detected temperature corresponding to the second target hard disk;

[0072] The real-time heat map is updated based on each of the initial heat maps, and the detected temperature and target slot corresponding to the second target hard disk.

[0073] Specifically, after determining each initial heat map, the busyness of each working hard disk in the current test cycle in the storage array within a preset time period can be obtained. After obtaining the busyness corresponding to all working hard disks, a relatively idle second target hard disk can be determined based on each busyness, that is, a second target hard disk with less impact on the business. Then, when obtaining the detection temperature corresponding to the second target hard disk, the impact of the hard disk temperature on the performance can be minimized. Then, based on the detection temperature and target slot corresponding to the second target hard disk, the real-time heat map is updated.

[0074] Optionally, the busyness level may include the number of I / O operations performed by each working hard disk within a preset time period during the current test cycle, that is, the number of read and write operations performed by each working hard disk within the preset time period. Each read or write of data from or to a working hard disk may be considered an I / O operation. The embodiment of the present invention does not impose any limitation on the busyness level.

[0075] In addition, a high-temperature hard disk polling list can also be obtained, which includes n working hard disks. The working hard disks in the high-temperature hard disk polling list are traversed, and the perceived temperatures of m working hard disks are read each time. The perceived temperatures of the other m working hard disks are read after a period of time. This ensures that the storage array can update the initial thermal map and the real-time thermal map based on the read perceived temperatures. However, the method of traversing the high-temperature hard disk polling list to read the perceived temperatures of the hard disks has a greater impact on the carrying business.

[0076] Furthermore, determining the second target hard disk based on the busyness corresponding to each of the working hard disks includes:

[0077] Determining at least one third target hard disk corresponding to a minimum busyness based on the busyness corresponding to each of the working hard disks;

[0078] Obtaining the IO queue duration or IO delay duration of each of the third target hard disks within a preset duration;

[0079] The third target hard disk corresponding to the minimum IO queueing time or the minimum IO delay time is determined as the second target hard disk.

[0080] Specifically, after determining the busyness corresponding to each working hard disk, all busynesses can be sorted in ascending order, and at least one working hard disk with the highest sorting level can be determined as at least one third target hard disk in the storage array in the current test cycle. That is, at least one working hard disk corresponding to the minimum busyness level can be determined as at least one third target hard disk, so as to preliminarily minimize the impact of reading the detection temperature of each working hard disk on the carrying business. For example, taking the busyness as the number of IO times as an example, after determining the number of IO times corresponding to each working hard disk, each IO number can be compared, and at least one working hard disk corresponding to the minimum IO number can be determined as at least one third target hard disk in the storage array in the current test cycle.

[0081] After determining at least one third target hard disk, further obtain the IO queueing time or IO delay time of each third target hard disk within a preset time length, and compare or sort all the IO queueing time or IO delay time lengths. When all the IO queueing time lengths are obtained, the third target hard disk corresponding to the minimum IO queueing time length is determined as the second target hard disk. When all the IO delay time lengths are obtained, the third target hard disk corresponding to the minimum IO delay time length is determined as the second target hard disk. This facilitates minimizing the impact on the business carried by the second target hard disk when obtaining the detection temperature of the second target hard disk.

[0082] Furthermore, updating the real-time heat map based on each of the initial heat maps, and the detected temperature and target slot corresponding to the second target hard disk, includes:

[0083] Determining a target hard disk type corresponding to the second target hard disk;

[0084] Obtaining a predicted temperature corresponding to the target slot from an initial thermal map corresponding to the target hard disk type;

[0085] The real-time thermal map is updated based on the detected temperature and the predicted temperature.

[0086] Specifically, after determining the second target hard disk, due to the hard disk type and initial thermal Figure 1 One-to-one correspondence, therefore, according to the target hard disk type corresponding to the second target hard disk, the initial heat map that matches the target hard disk type can be determined, and from the initial heat map, the predicted temperature at the same position as the target slot of the second target hard disk is obtained, and the real-time heat map is updated according to the detected temperature and the predicted temperature, so as to facilitate the subsequent reconstruction of the abnormal hard disk. For example, Figure 3 As shown, taking the second target hard disk as the working hard disk 1 corresponding to the storage slot 1, and the target hard disk type corresponding to the working hard disk 1 as HDD as an example, the initial thermal load corresponding to the HDD can be obtained. Figure 1 , then, according to the target slot corresponding to the working hard disk 1, from the initial thermal Figure 1 The preset temperature 1 is obtained from the corresponding storage slot 1.

[0087] Furthermore, updating the real-time thermal map based on the detected temperature and the predicted temperature includes:

[0088] Obtaining adjacent detected temperatures corresponding to adjacent hard disks of the second target hard disk and adjacent predicted temperatures of the adjacent hard disks in the initial heat map; determining a detected temperature ranking based on the detected temperatures and the adjacent detected temperatures, and determining a predicted temperature ranking based on the predicted temperatures and the adjacent predicted temperatures; and if the detected temperature ranking matches the predicted temperature ranking, determining the detected temperature as the real-time temperature corresponding to the target slot in the real-time heat map;

[0089] or,

[0090] Determine a temperature difference between the detected temperature and the predicted temperature. If the temperature difference is less than or equal to a preset threshold, determine the detected temperature as the real-time temperature corresponding to the target slot in the real-time thermal map.

[0091] Specifically, after determining the detected temperature and the predicted temperature corresponding to the same storage slot, on the one hand, the adjacent detected temperature of the adjacent hard disk of the second target hard disk can be obtained. The adjacent hard disk can be a hard disk located in any position above, below, left, or right of the second target hard disk. Then, the detected temperature and the adjacent detected temperature of the second target hard disk are sorted to determine the detected temperature sorting. At the same time, the adjacent predicted temperatures and the predicted temperatures in the same storage slot as the adjacent hard disk in the initial thermal map are sorted to obtain the predicted temperature sorting. Then, the detected temperature sorting is compared with the predicted temperature sorting, that is, whether the order of the detected temperature in the detected temperature sorting is the same as the order of the predicted temperature in the predicted temperature sorting. If the order of the detected temperature in the detected temperature sorting is the same as the order of the predicted temperature in the predicted temperature sorting, it indicates that the detected temperature sorting matches the predicted temperature sorting, and further indicates that the detected temperature corresponding to the second target hard disk is consistent with the predicted temperature in the initial thermal map, that is, the second target hard disk is operating normally, and the temperature corresponding to the target slot in the real-time thermal map can be updated according to the detected temperature. It should be noted that the order of sorting in the detected temperature sorting is the same as the order of sorting in the predicted temperature sorting. For example, if the detected temperature sorting is sorted in descending order, the predicted temperature sorting is also sorted in descending order. The embodiment of the present invention does not limit the sorting order.

[0092] On the other hand, the temperature difference between the detected temperature and the predicted temperature can be calculated, and the temperature difference can be compared with a preset threshold. If the temperature difference is less than or equal to the preset threshold, it indicates that the detected temperature of the second target hard disk matches the predicted temperature in the initial thermal map. At this time, the temperature corresponding to the target slot in the real-time thermal map can be updated based on the detected temperature of the second target hard disk. If the temperature difference is greater than or equal to the preset threshold, it indicates that the detected temperature of the second target hard disk does not match the predicted temperature in the initial thermal map, indicating that the second target hard disk is abnormal. At this time, the hard disks around the second target hard disk can be actively inspected to determine whether the second target hard disk is abnormal. It should be noted that the above-mentioned preset threshold is an extremely small value, which is used to indicate that the gap between the perceived temperature and the preset temperature is small. The preset temperature can be 0.1°C, 0.15°C, 0.2°C, etc., and the embodiment of the present invention does not limit this.

[0093] Step 140: When a hard disk is abnormal, based on the updated real-time heat map, a first target hard disk is determined from the idle hot spare disks to perform abnormal hard disk reconstruction, so as to optimize the storage array.

[0094] Specifically, when there is a hard disk abnormality such as damage to the working hard disk or data loss in the working hard disk, the first target hard disk can be determined from the idle hot spare disks according to the real-time heat map, and the abnormal hard disk can be rebuilt based on the first target hard disk. The abnormal hard disk is rebuilt using the first target hard disk in the low-temperature area among multiple idle hot spare disks, which can optimize the heat dissipation layout of the storage array after reconstruction, realize the recovery of the carried business, and thus ensure the operational stability of the storage array.

[0095] Furthermore, in the case of a hard disk anomaly, determining a first target hard disk from the idle hot spare disks based on the updated real-time heat map includes:

[0096] When it is determined that a hard disk is abnormal, determining a predicted temperature corresponding to each of the idle hot spare disks from the real-time thermal map;

[0097] The idle hot spare disk corresponding to the lowest predicted temperature is determined as the first target hard disk.

[0098] Specifically, in the case of a hard disk anomaly, the predicted temperature corresponding to each idle hot spare disk can be read from the real-time thermal map, and all predicted temperatures can be sorted in ascending order. The idle hot spare disk at the top of the sorting result is determined as the first target hard disk, that is, the idle hot spare disk corresponding to the lowest predicted temperature is determined as the first target hard disk, and the abnormal hard disk is rebuilt using the first target hard disk, replacing the abnormal hard disk to carry business, thereby optimizing the storage array. For example, Figure 3As shown, both Hard Drive 3 and Hard Drive 12 in the storage array are idle hot spares. If Hard Drive 1 in the storage array is damaged or lost, the first target hard drive needs to be selected for reconstruction. In this case, because the predicted temperature of Hard Drive 12 is lower than that of Hard Drive 3, Hard Drive 12 can be selected as the first target hard drive to replace Hard Drive 1 in carrying services.

[0099] It should be noted that the predicted temperature corresponding to the idle hot spare disk is determined from the corresponding initial thermal map.

[0100] The storage array optimization method based on heat map perception provided by the present invention, after obtaining the initial heat map corresponding to each storage slot in the storage array corresponding to each hard disk type, selects the target slot corresponding to each in-place hard disk in the storage array according to each initial heat map, and then places the working hard disk and the idle hot spare disk in their respective corresponding target slots to obtain a real-time heat map. In the case of a hard disk abnormality, according to the real-time heat map, that is, according to the real-time thermal environment corresponding to the storage array, the first target hard disk is selected from the idle hot spare disks to rebuild the abnormal hard disk, thereby optimizing the heat dissipation layout of the storage array, providing a stable thermal environment for the reconstruction of the abnormal hard disk, improving the reconstruction effect of the abnormal hard disk, and thus improving the operating stability of the storage array.

[0101] The following describes a storage array optimization device based on thermal map perception provided by the present invention. The storage array optimization device based on thermal map perception described below and the storage array optimization method based on thermal map perception described above can refer to each other.

[0102] The embodiment of the present invention also provides a storage array optimization device based on heat map perception, Figure 4 Schematic diagram of the structure of a storage array optimization device based on heat map perception provided by an embodiment of the present invention. Figure 4 As shown, the storage array optimization device 400 based on heat map perception includes: an acquisition module 410, a first determination module 420, a second determination module 430 and an optimization module 440, wherein:

[0103] An acquisition module 410 is configured to acquire an initial thermal map corresponding to at least one type of hard disk in a storage array, wherein the initial thermal map is used to represent a predicted temperature distribution corresponding to each storage slot in the storage array;

[0104] A first determination module 420 is configured to determine target slots corresponding to at least two in-place hard disks in the storage array and a real-time heat map based on each of the initial heat maps; the at least two in-place hard disks include a working hard disk and an idle hot spare disk;

[0105] A second determining module 430 is configured to update the real-time heat map based on the initial heat maps and the target slots corresponding to the working hard disks;

[0106] The optimization module 440 is configured to determine a first target hard disk from the idle hot spare disks to rebuild the abnormal hard disk based on the updated real-time heat map when a hard disk abnormality occurs, so as to optimize the storage array.

[0107] The storage array optimization device based on heat map perception provided by the present invention obtains the initial heat map corresponding to each storage slot in the storage array corresponding to each hard disk type, and then selects the target slot corresponding to each in-place hard disk in the storage array according to each initial heat map, and then places the working hard disk and the idle hot spare disk in their respective corresponding target slots to obtain a real-time heat map. In the case of a hard disk abnormality, according to the real-time heat map, that is, according to the real-time thermal environment corresponding to the storage array, the first target hard disk is selected from the idle hot spare disks to rebuild the abnormal hard disk, thereby optimizing the heat dissipation layout of the storage array, providing a stable thermal environment for the reconstruction of the abnormal hard disk, improving the reconstruction effect of the abnormal hard disk, and thus improving the operating stability of the storage array.

[0108] Optionally, the first determining module 420 is specifically configured to:

[0109] Obtaining the predicted temperature corresponding to each storage slot in each of the initial thermal maps;

[0110] Sort all predicted temperatures in order from low to high to obtain the predicted sorting results;

[0111] Based on the prediction sorting results, determining the target slot corresponding to each of the working hard disks in sequence, and determining the recommended slots corresponding to the idle hot spare disks, where the number of the recommended slots is greater than or equal to the number of the idle hot spare disks;

[0112] The recommended slots having the same number as the idle hot spare disks among the recommended slots are determined as target slots corresponding to the idle hot spare disks.

[0113] Optionally, the second determining module 430 is specifically configured to:

[0114] Obtaining the busyness of each working hard disk in the current test cycle;

[0115] Determining a second target hard disk based on the busyness corresponding to each of the working hard disks;

[0116] Obtaining a detected temperature corresponding to the second target hard disk;

[0117] The real-time heat map is updated based on each of the initial heat maps, and the detected temperature and target slot corresponding to the second target hard disk.

[0118] Optionally, the second determining module 430 is specifically configured to:

[0119] Determining at least one third target hard disk corresponding to a minimum busyness based on the busyness corresponding to each of the working hard disks;

[0120] Obtaining the IO queue duration or IO delay duration of each of the third target hard disks within a preset duration;

[0121] The third target hard disk corresponding to the minimum IO queueing time or the minimum IO delay time is determined as the second target hard disk.

[0122] Optionally, the second determining module 430 is specifically configured to:

[0123] Determining a target hard disk type corresponding to the second target hard disk;

[0124] Obtaining a predicted temperature corresponding to the target slot from an initial thermal map corresponding to the target hard disk type;

[0125] The real-time thermal map is updated based on the detected temperature and the predicted temperature.

[0126] Optionally, the second determining module 430 is specifically configured to:

[0127] Obtaining adjacent detected temperatures corresponding to adjacent hard disks of the second target hard disk and adjacent predicted temperatures of the adjacent hard disks in the initial heat map; determining a detected temperature ranking based on the detected temperatures and the adjacent detected temperatures, and determining a predicted temperature ranking based on the predicted temperatures and the adjacent predicted temperatures; and if the detected temperature ranking matches the predicted temperature ranking, determining the detected temperature as the real-time temperature corresponding to the target slot in the real-time heat map;

[0128] or,

[0129] Determine a temperature difference between the detected temperature and the predicted temperature. If the temperature difference is less than or equal to a preset threshold, determine the detected temperature as the real-time temperature corresponding to the target slot in the real-time thermal map.

[0130] Optionally, the optimization module 440 is specifically configured to:

[0131] When it is determined that a hard disk is abnormal, determining a predicted temperature corresponding to each of the idle hot spare disks from the real-time thermal map;

[0132] The idle hot spare disk corresponding to the lowest predicted temperature is determined as the first target hard disk.

[0133] Figure 5 FIG. 1 is a schematic diagram of the structure of a storage array provided by an embodiment of the present invention. Figure 5As shown, the storage array may include: a processor 510, a communication interface 520, a memory 530, and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other via the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute the storage array optimization method based on thermal map perception, which includes:

[0134] Obtaining an initial thermal map corresponding to at least one hard disk type in a storage array, wherein the initial thermal map is used to represent a predicted temperature distribution corresponding to each storage slot in the storage array;

[0135] Based on each of the initial heat maps, determining target slots corresponding to at least two in-place hard disks in the storage array and a real-time heat map; the at least two in-place hard disks include a working hard disk and an idle hot spare disk;

[0136] Based on each of the initial heat maps and the target slots corresponding to the working hard disks, updating the real-time heat map;

[0137] In the case of a hard disk anomaly, based on the updated real-time heat map, a first target hard disk is determined from the idle hot spare disks to perform abnormal hard disk reconstruction, so as to optimize the storage array.

[0138] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0139] On the other hand, the present invention further provides a computer program product, which includes a computer program. The computer program can be stored on a computer-readable storage medium. When the computer program is executed by a processor, the computer can perform the storage array optimization method based on thermal map perception provided by the above methods, which includes:

[0140] Obtaining an initial thermal map corresponding to at least one hard disk type in a storage array, wherein the initial thermal map is used to represent a predicted temperature distribution corresponding to each storage slot in the storage array;

[0141] Based on each of the initial heat maps, determining target slots corresponding to at least two in-place hard disks in the storage array and a real-time heat map; the at least two in-place hard disks include a working hard disk and an idle hot spare disk;

[0142] Based on each of the initial heat maps and the target slots corresponding to the working hard disks, updating the real-time heat map;

[0143] In the case of a hard disk anomaly, based on the updated real-time heat map, a first target hard disk is determined from the idle hot spare disks to perform abnormal hard disk reconstruction, so as to optimize the storage array.

[0144] In another aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for optimizing a storage array based on thermal map perception provided by the above methods is implemented. The method includes:

[0145] Obtaining an initial thermal map corresponding to at least one hard disk type in a storage array, wherein the initial thermal map is used to represent a predicted temperature distribution corresponding to each storage slot in the storage array;

[0146] Based on each of the initial heat maps, determining target slots corresponding to at least two in-place hard disks in the storage array and a real-time heat map; the at least two in-place hard disks include a working hard disk and an idle hot spare disk;

[0147] Based on each of the initial heat maps and the target slots corresponding to the working hard disks, updating the real-time heat map;

[0148] In the case of a hard disk anomaly, based on the updated real-time heat map, a first target hard disk is determined from the idle hot spare disks to perform abnormal hard disk reconstruction, so as to optimize the storage array.

[0149] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0150] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0151] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A storage array optimization method based on heat map perception, characterized in that: include: Obtaining an initial thermal map corresponding to at least one hard disk type in a storage array, wherein the initial thermal map is used to represent a predicted temperature distribution corresponding to each storage slot in the storage array; Based on each of the initial heat maps, determining target slots corresponding to at least two in-place hard disks in the storage array and a real-time heat map; the at least two in-place hard disks include a working hard disk and an idle hot spare disk; Based on each of the initial heat maps and the target slots corresponding to the working hard disks, updating the real-time heat map; In the case of a hard disk anomaly, based on the updated real-time heat map, a first target hard disk is determined from the idle hot spare disks to perform abnormal hard disk reconstruction, so as to optimize the storage array.

2. The storage array optimization method based on heat map perception according to claim 1 is characterized in that: The updating of the real-time heat map based on the initial heat maps and the target slots corresponding to the working hard disks includes: Obtaining the busyness of each working hard disk in the current test cycle; Determining a second target hard disk based on the busyness corresponding to each of the working hard disks; Obtaining a detected temperature corresponding to the second target hard disk; The real-time heat map is updated based on each of the initial heat maps, and the detected temperature and target slot corresponding to the second target hard disk.

3. The storage array optimization method based on heat map perception according to claim 2 is characterized in that: The determining of the second target hard disk based on the busyness corresponding to each of the working hard disks includes: Determining at least one third target hard disk corresponding to a minimum busyness based on the busyness corresponding to each of the working hard disks; Obtaining the IO queue duration or IO delay duration of each of the third target hard disks within a preset duration; The third target hard disk corresponding to the minimum IO queueing time or the minimum IO delay time is determined as the second target hard disk.

4. The storage array optimization method based on heat map perception according to claim 2, characterized in that: The updating of the real-time heat map based on each of the initial heat maps, and the detected temperature and target slot corresponding to the second target hard disk, includes: Determining a target hard disk type corresponding to the second target hard disk; Obtaining a predicted temperature corresponding to the target slot from an initial thermal map corresponding to the target hard disk type; The real-time thermal map is updated based on the detected temperature and the predicted temperature.

5. The storage array optimization method based on heat map perception according to claim 4 is characterized in that: The updating of the real-time thermal map based on the detected temperature and the predicted temperature includes: Obtaining adjacent detected temperatures corresponding to adjacent hard disks of the second target hard disk and adjacent predicted temperatures of the adjacent hard disks in the initial heat map; determining a detected temperature ranking based on the detected temperatures and the adjacent detected temperatures, and determining a predicted temperature ranking based on the predicted temperatures and the adjacent predicted temperatures; and if the detected temperature ranking matches the predicted temperature ranking, determining the detected temperature as the real-time temperature corresponding to the target slot in the real-time heat map; or, Determine a temperature difference between the detected temperature and the predicted temperature. If the temperature difference is less than or equal to a preset threshold, determine the detected temperature as the real-time temperature corresponding to the target slot in the real-time thermal map.

6. The storage array optimization method based on heat map perception according to any one of claims 1 to 5, characterized in that: The method of determining a first target hard disk from the idle hot spare disks based on the updated real-time heat map when a hard disk anomaly occurs includes: When it is determined that a hard disk is abnormal, determining a predicted temperature corresponding to each of the idle hot spare disks from the real-time thermal map; The idle hot spare disk corresponding to the lowest predicted temperature is determined as the first target hard disk.

7. The storage array optimization method based on heat map perception according to any one of claims 1 to 5, characterized in that: The determining, based on each of the initial heat maps, target slots corresponding to at least two in-place hard disks in the storage array includes: Obtaining the predicted temperature corresponding to each storage slot in each of the initial thermal maps; Sort all predicted temperatures in order from low to high to obtain the predicted sorting results; Based on the prediction sorting results, determining the target slot corresponding to each of the working hard disks in sequence, and determining the recommended slots corresponding to the idle hot spare disks, where the number of the recommended slots is greater than or equal to the number of the idle hot spare disks; The recommended slots having the same number as the idle hot spare disks among the recommended slots are determined as target slots corresponding to the idle hot spare disks.

8. A storage array optimization device based on heat map perception, characterized in that: include: an acquisition module, configured to acquire an initial thermal map corresponding to at least one type of hard disk in a storage array, wherein the initial thermal map is used to represent a predicted temperature distribution corresponding to each storage slot in the storage array; A first determination module is configured to determine target slots corresponding to at least two in-place hard disks in the storage array and a real-time heat map based on each of the initial heat maps; the at least two in-place hard disks include a working hard disk and an idle hot spare disk; A second determining module is configured to update the real-time heat map based on each of the initial heat maps and the target slots corresponding to the working hard disks; The optimization module is used to determine a first target hard disk from the idle hot spare disks to perform abnormal hard disk reconstruction based on the updated real-time heat map in the event of a hard disk anomaly, so as to optimize the storage array.

9. A storage array comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the storage array optimization method based on heat map perception according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the storage array optimization method based on thermal map perception according to any one of claims 1 to 7 is implemented.

Images