Method and device for improving performance of solid state disk, storage medium and server

Abstract

The invention discloses a solid state disk performance improving method and device, a storage medium and a server, and the method comprises the steps that in a TRIMODE mode, the type of an independent disk redundant array card is determined, and the independent disk redundant array card and a solid state disk are used in a matched mode; determining a tuning strategy according to the type of the RAID card; and adjusting at least one of the parameters of the redundant array card of the independent disk, the solid state disk and the operating system according to the tuning strategy. According to the method, the problems that the performance of the solid state disk is too low and limited in the TRIMODE mode can be solved, and the performance of the solid state disk is improved.

Description

Technical Field

[0001] The present application relates to the technical field of hard disks, and in particular to a method for improving the performance of solid-state hard disks, a device for improving the performance of solid-state hard disks, a computer-readable storage medium, and a server. Background Art

[0002] In the new era of rapid data development, the amount of data that corporate customers need to process is getting larger and more complex. In addition to structured data of general business, they also need to process unstructured data composed of videos, pictures, and various electronic documents. Correspondingly, various data mining, intelligent analysis, transactions, decision-making and other activities will generate a large number of secondary small data, which poses a challenge to the data throughput performance of information technology infrastructure.

[0003] As NVME (Non-Volatile Memory Express) SSD (Solid State Drive) is increasingly used, customers have also put forward higher and more reliable usage requirements, not limited to the onboard use of NVME SSD, but requiring higher read and write speeds, data backup and other usage solutions. This has led to the TRIMODE mode solution, that is, the new RAID (Redundant Arrays of Independent Disks) card that supports the TRIMODE function is used with NVME SSD to form a RAID level suitable for the usage scenario. However, the speed of NVME SSD is several times that of the solid-state drive with the Serial ATA (Serial ATA) interface. How to improve the performance of NVME SSD under TRIMODE mode has become a problem that must be solved.

[0004] At present, the relevant technology needs to adjust the routing method of the solid-state hard disk on the server, which has poor flexibility. The performance of NVME SSD is improved by binding the number of CPU (Central Processing Unit) cores. However, if the 4-disk slot RAID5-level TRIMODE mode is only bound to the CPU core, the 4KRR (4K Random Read) performance cannot even reach the performance of a single disk. In this case, setting RAID5 is meaningless, the performance is too low, and the cost performance is low. Summary of the invention

[0005] The present application aims to solve at least one of the technical problems in the related art to a certain extent. To this end, the first purpose of the present application is to propose a method for improving the performance of a solid-state hard disk, in which the type of an independent disk redundant array card is determined in the TRIMODE mode, wherein the independent disk redundant array card is used in combination with a solid-state hard disk, and a tuning strategy is determined according to the type of the independent disk redundant array card, and at least one of the parameters of the independent disk redundant array card, the solid-state hard disk and the operating system is adjusted according to the tuning strategy, thereby solving the problem of too low performance and limited performance of the solid-state hard disk in the TRIMODE mode, and improving the performance of the solid-state hard disk.

[0006] The second objective of the present application is to provide a device for improving the performance of a solid state drive.

[0007] The third object of the present application is to provide a computer-readable storage medium.

[0008] The fourth objective of this application is to provide a server.

[0009] To achieve the above-mentioned purpose, the first aspect of the present application proposes a method for improving the performance of a solid-state hard disk, the method comprising: in TRIMODE mode, determining the type of an independent disk redundant array card, wherein the independent disk redundant array card is used in combination with the solid-state hard disk; determining a tuning strategy according to the type of the independent disk redundant array card; and adjusting at least one of the parameters of the independent disk redundant array card, the solid-state hard disk and the operating system according to the tuning strategy.

[0010] According to the method for improving the performance of the solid-state drive in the embodiment of the present application, in the TRIMODE mode, the type of the independent disk redundant array card is determined, wherein the independent disk redundant array card is used in combination with the solid-state drive, and the tuning strategy is determined according to the type of the independent disk redundant array card, and at least one of the parameters of the independent disk redundant array card, the solid-state drive, and the operating system is adjusted according to the tuning strategy. Therefore, the method can solve the problem of low performance and limited performance of the solid-state drive in the TRIMODE mode, and improve the performance of the solid-state drive.

[0011] In addition, the method for improving the performance of a solid state drive according to the above embodiment of the present application may also have the following additional technical features:

[0012] According to an embodiment of the present application, determining the tuning strategy according to the type of the redundant array of independent disks card includes: when the type of the redundant array of independent disks card is a first preset type, determining the tuning strategy to format the solid-state drive, update the firmware and driver of the redundant array of independent disks card, set the read and write strategy of the redundant array of independent disks card, perform core binding between the redundant array of independent disks card and a central processor corresponding to the solid-state drive, and optimize operating system parameters; when the type of the redundant array of independent disks card is a second preset type, determining the tuning strategy to format the solid-state drive, update the firmware and driver of the redundant array of independent disks card, set the read and write strategy of the redundant array of independent disks card, perform core binding between the redundant array of independent disks card and a central processor corresponding to the solid-state drive, optimize operating system parameters, and perform full disk initialization on the virtual disk.

[0013] According to an embodiment of the present application, formatting the solid-state drive includes: when the type of the independent disk redundant array card is the first preset type or the second preset type and the solid-state drive is connected to the server, formatting based on the nvmecli tool; when the type of the independent disk redundant array card is the first preset type and the solid-state drive is connected to the server through the independent disk redundant array card, formatting based on the arcconf tool; when the type of the independent disk redundant array card is the second preset type and the solid-state drive is connected to the server through the independent disk redundant array card, formatting based on the storcli tool.

[0014] According to an embodiment of the present application, updating the firmware and driver of the redundant array of independent disks card includes: when the type of the redundant array of independent disks card is a first preset type, updating the firmware of the redundant array of independent disks card based on an arcconf tool, and updating the version of the driver based on an rpm command; when the type of the redundant array of independent disks card is a second preset type, updating the firmware of the redundant array of independent disks card based on a storcli tool, and updating the version of the driver based on an rpm command, wherein the driver is a driver between the redundant array of independent disks card and an operating system.

[0015] According to an embodiment of the present application, the setting of the read and write strategy of the redundant array of independent disks card includes: setting the read and write parameters of the redundant array of independent disks card based on the read and write characteristics of the solid state drive.

[0016] According to one embodiment of the present application, the core binding of the independent disk redundant array card and the central processor corresponding to the solid-state hard disk includes: determining a high-speed serial data transmission interface address corresponding to the independent disk redundant array card; determining a processor identifier corresponding to the independent disk redundant array card based on the high-speed serial data transmission interface address; and binding a read / write request to the central processor corresponding to the solid-state hard disk based on the processor identifier.

[0017] According to one embodiment of the present application, the optimization of operating system parameters includes at least one of the following methods: in input / output requests, turning off the addition of randomness; in adjacent input / output requests, prohibiting the merging of adjacent read and write requests; setting the maximum number of requests in the scheduling queue in each input / output request to the maximum value; setting the storage device to a non-rotating medium; turning on input / output affinity; turning off the input / output scheduler; turning on input / output statistics; setting the maximum number of sectors for a single input / output request to the maximum value.

[0018] According to an embodiment of the present application, the full disk initialization of the virtual disk includes: full disk initialization of the virtual disk based on the storcli tool.

[0019] According to an embodiment of the present application, the determining of the independent disk redundant array card further includes: determining the type of the independent disk redundant array card based on a command corresponding to the operating system, or determining the type of the independent disk redundant array card based on a configuration tool, wherein the type of the independent disk redundant array card includes a first preset type and a second preset type, the first preset type is an MCHP independent disk redundant array card, the second preset type is a BRCM independent disk redundant array card, and the configuration tool is a storcli tool or an arcconf tool.

[0020] To achieve the above-mentioned purpose, the second aspect of the present application proposes a device for improving the performance of a solid-state hard disk, the device comprising: a first determination module, used to determine the type of an independent disk redundant array card in TRIMODE mode, wherein the independent disk redundant array card is used in combination with the solid-state hard disk; a second determination module, used to determine a tuning strategy according to the type of the independent disk redundant array card; and an adjustment module, used to adjust at least one of the parameters of the independent disk redundant array card, the solid-state hard disk and the operating system according to the tuning strategy.

[0021] According to the device for improving the performance of a solid-state hard disk in the embodiment of the present application, the first determination module is used to determine the type of an independent disk redundant array card in the TRIMODE mode, wherein the independent disk redundant array card is used in combination with a solid-state hard disk, the second determination module is used to determine the tuning strategy according to the type of the independent disk redundant array card, and the adjustment module is used to adjust at least one of the parameters of the independent disk redundant array card, the solid-state hard disk, and the operating system according to the tuning strategy. Thus, the device can solve the problem of too low performance and limited performance of the solid-state hard disk in the TRIMODE mode, and improve the performance of the solid-state hard disk.

[0022] To achieve the above-mentioned purpose, the third aspect of the present application proposes a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the above-mentioned method for improving the performance of a solid-state hard drive.

[0023] According to the computer-readable storage medium of the embodiment of the present application, by implementing the above-mentioned method for improving the performance of the solid-state hard disk during execution, it is possible to solve the problem of low performance and limited performance of the solid-state hard disk in the TRIMODE mode, thereby improving the performance of the solid-state hard disk.

[0024] To achieve the above-mentioned purpose, a server is proposed in the fourth aspect of the present application, including a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, the above-mentioned method for improving the performance of the solid-state hard drive is implemented.

[0025] According to the server of the embodiment of the present application, by executing the above-mentioned method for improving the performance of the solid-state hard disk, it is possible to solve the problem of low performance and limited performance of the solid-state hard disk in the TRIMODE mode, thereby improving the performance of the solid-state hard disk.

[0026] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 is a flow chart of a method for improving the performance of a solid state drive according to an embodiment of the present application;

[0028] Figure 2 A flowchart of a method for improving the performance of a solid-state hard disk according to a specific example of the present application;

[0029] Figure 3 It is a block diagram of a device for improving the performance of a solid state drive according to an embodiment of the present application;

[0030] Figure 4 It is a block diagram of a server according to an embodiment of the present application. DETAILED DESCRIPTION

[0031] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0032] The following describes, with reference to the accompanying drawings, a method for improving the performance of a solid-state hard disk, a device for improving the performance of a solid-state hard disk, a computer-readable storage medium, and a server proposed in an embodiment of the present application.

[0033] Figure 1 Flow chart of a method for improving solid state drive performance according to an embodiment of the present application.

[0034] like Figure 1 As shown, the method for improving the performance of a solid state drive according to an embodiment of the present application may include the following steps:

[0035] S1, in TRIMODE mode, determining a type of a redundant array of independent disks card, wherein the redundant array of independent disks card is used in combination with a solid state drive.

[0036] S2, determine the tuning strategy according to the type of independent disk redundant array card.

[0037] S3: Adjust at least one of the parameters of the independent disk redundant array card, the solid state drive, and the operating system according to the tuning strategy.

[0038] Specifically, in TRIMODE mode, determining the type of independent disk redundant array card is the first step in the tuning process. The purpose of this step is to identify the brand and model of the independent disk redundant array card used in the system (such as a server) so that the correct tuning strategy can be applied in subsequent steps. In other words, TRIMODE mode refers to the independent disk redundant array card supporting NVMe SSD storage devices. In this mode, the independent disk redundant array card can optimize its performance and resource allocation according to the type of connected storage device. Different types of independent disk redundant array cards have different performance characteristics and tuning parameters. Determining the type of independent disk redundant array card can ensure the application of the most appropriate tuning strategy and improve the overall performance of the system. For example, the type of the current independent disk redundant array card can be determined through the corresponding command of the operating system, such as running the lspci command to list all hardware interface devices in the system, including the independent disk redundant array card, and then determine the type of the independent disk redundant array card based on the output result.

[0039] After the type is determined, a tuning strategy can be determined according to the type of the independent disk redundant array card, and these tuning strategies are intended to improve the performance, reliability and stability of the system. At least one of the parameters of the independent disk redundant array card, the solid state drive and the operating system is adjusted according to the tuning strategy. That is, the parameters of the independent disk redundant array card can be adjusted, or the parameters of the solid state drive can be adjusted, or the parameters of the operating system can be adjusted, or the parameters of the independent disk redundant array card and the solid state drive can be adjusted, the parameters of the independent disk redundant array card and the operating system can be adjusted, the parameters of the solid state drive and the operating system can be adjusted, or the parameters of the independent disk redundant array card, the solid state drive and the operating system can be adjusted at the same time.

[0040] For example, you can format the SSD, update the driver of the independent disk redundant array card to the latest version, optimize the memory management parameters of the operating system to reduce the use of swap space by the operating system and improve memory usage efficiency, or increase the depth of the request queue to improve concurrent processing capabilities. Through these steps, you can ensure that the independent disk redundant array card and the SSD are in the best state before use, improving the overall performance and reliability of the system. These tuning measures are particularly suitable for scenarios that require high concurrency and high performance, such as high-performance computing, databases, and file servers.

[0041] As a result, the problem of low performance and limited performance of the solid-state hard disk in TRIMODE mode can be solved, thereby improving the performance of the solid-state hard disk.

[0042] According to an embodiment of the present application, determining a tuning strategy according to a type of an independent disk redundant array card includes: when the type of the independent disk redundant array card is a first preset type, determining the tuning strategy to format a solid-state drive, updating the firmware and driver of the independent disk redundant array card, setting a read / write strategy for the independent disk redundant array card, core-binding the independent disk redundant array card and a central processor corresponding to the solid-state drive, and optimizing operating system parameters; when the type of the independent disk redundant array card is a second preset type, determining the tuning strategy to format the solid-state drive, updating the firmware and driver of the independent disk redundant array card, setting a read / write strategy for the independent disk redundant array card, core-binding the independent disk redundant array card and a central processor corresponding to the solid-state drive, optimizing operating system parameters, and fully initializing a virtual disk.

[0043] Specifically, when determining the tuning strategy according to the type of the independent disk redundant array card, the type of the current independent disk redundant array card is judged, and different types correspond to different tuning strategies. When the type of the independent disk redundant array card is the first preset type, the tuning strategy can be determined to format the solid state drive, update the firmware and driver of the independent disk redundant array card, set the read and write strategy of the independent disk redundant array card, perform core binding on the central processor corresponding to the independent disk redundant array card and the solid state drive, and optimize the operating system parameters. In other words, through these adjustment strategies, formatting the solid state drive can clear all old data on the solid state drive, ensure that new data will not be interfered by old data when writing, optimize the internal structure, and improve performance, update the firmware and driver can fix known problems, improve performance and stability, set the read and write strategy can optimize the read and write strategy, and improve data transmission efficiency, core binding can reduce context switching, improve processing efficiency, and improve system response speed, optimize system parameters, reduce unnecessary overhead, improve data reading and writing speed, and improve system stability. In this way, it can be ensured that the independent disk redundant array card and the solid state drive are in the best state before use, and the overall performance and reliability of the system can be improved.

[0044] In the case where the type of the independent disk redundant array card is the second preset type, the tuning strategy can be determined as formatting the solid state drive, updating the firmware and driver of the independent disk redundant array card, setting the read and write strategy of the independent disk redundant array card, core binding the independent disk redundant array card and the central processor corresponding to the solid state drive, optimizing the operating system parameters, and initializing the virtual disk. In other words, through these adjustment strategies, formatting the solid state drive can clear all old data on the solid state drive, ensure that new data will not be interfered by old data when writing, optimize the internal structure, and improve performance, updating the firmware and driver can fix known problems, improve performance and stability, setting the read and write strategy can optimize the read and write strategy, and improve data transmission efficiency, core binding can reduce context switching, improve processing efficiency, and improve system response speed, optimizing system parameters, reducing unnecessary overhead, improving data reading and writing speed, and improving system stability. Initializing the virtual disk can clear all old data on the virtual disk, ensure that new data will not be interfered by old data when writing, optimize the internal structure, reduce garbage collection operations, and improve data reading and writing efficiency. This ensures that the independent disk redundant array card and the solid-state drive are in the best condition before use, thereby improving the overall performance and reliability of the system.

[0045] According to an embodiment of the present application, formatting a solid-state drive includes: when the type of an independent disk redundant array card is a first preset type or a second preset type and the solid-state drive is connected to a server, formatting based on an nvmecli tool; when the type of an independent disk redundant array card is a first preset type and the solid-state drive is connected to the server through an independent disk redundant array card, formatting based on an arcconf tool; when the type of an independent disk redundant array card is a second preset type and the solid-state drive is connected to the server through an independent disk redundant array card, formatting based on a storcli tool.

[0046] Specifically, when formatting the solid-state drive, the type of the independent disk redundant array card is judged. When the type of the independent disk redundant array card is the first preset type or the second preset type, the current connection mode between the solid-state drive and the server is judged. When the solid-state drive is directly connected to the server, it can be formatted according to the nvmecli tool, wherein nvmecli is a command line tool for managing and monitoring NVMe SSDs. For example, execute nvme format / dev / nvme* (*depends on the specific drive letter under the system) to ensure that the solid-state drive is in an empty disk state, so that when data is written, there is no large amount of garbage collection and other operations, which makes the writing speed faster and the performance volatility smaller. In addition, after formatting with the nvmecli tool, the solid-state drive is transferred to the independent disk redundant array card, that is, the solid-state drive is connected to the slot of the independent disk redundant array card to manage the solid-state drive through the independent disk redundant array card.

[0047] The type of the independent disk redundant array card is determined. When the type of the independent disk redundant array card is the first preset type, the current connection mode between the solid state drive and the server is determined. When the solid state drive is connected to the server through the independent disk redundant array card, the formatting process can be performed according to the arcconf tool. For example, the formatting can be performed by executing arcconftask start 1device TL secureerase pattern 5noprompt. In the command, 1 represents the ID number of the independent disk redundant array card, pattern 5 represents the use of a specific erase mode, noprompt represents not prompting the user for confirmation, and T and L represent the Reported Channel and Device number corresponding to a physical disk under the controller, which can be locked to a specific physical disk. After formatting, ensure that the solid state drive is in an empty disk state, so that when data is written, there is no large amount of garbage collection and other operations, so that the writing speed is faster and the performance volatility is smaller.

[0048] The type of the independent disk redundant array card is determined. If the type of the independent disk redundant array card is the second preset type, and the current connection mode between the solid-state drive and the server is determined, when the solid-state drive is connected to the server through the independent disk redundant array card, it can be formatted based on the storcli tool. For example, by executing storcli / c* / e* / s*start erase thorough patternA=00000000patternB=00000000, the * in c, e, and s in the command represents the number corresponding to a solid-state drive under a controller, which can be locked to a specific physical disk. PatternA and patternB indicate the use of a specific erase mode. After formatting, ensure that the disk is in an empty state so that when data is written, there is no large amount of garbage collection and other operations, which makes the writing speed faster and the performance volatility smaller.

[0049] This ensures that the SSD is in the best condition before use, improving the overall performance and reliability of the system.

[0050] According to an embodiment of the present application, the firmware and driver of an independent disk redundant array card are updated, including: when the type of the independent disk redundant array card is a first preset type, the firmware of the independent disk redundant array card is updated based on the arcconf tool, and the version of the driver is updated based on the rpm command; when the type of the independent disk redundant array card is a second preset type, the firmware of the independent disk redundant array card is updated based on the storcli tool, and the version of the driver is updated based on the rpm command, wherein the driver is a driver between the independent disk redundant array card and the operating system.

[0051] Specifically, when updating the firmware and driver of the independent disk redundant array card, the type of the current independent disk redundant array card is determined. When the type of the independent disk redundant array card is the first preset type, the firmware of the independent disk redundant array card can be updated according to the arcconf tool, for example, by executing arcconfromupdate 1***.bin to refresh the firmware, where 1 represents the first card, if there are multiple cards, the numbers need to be changed and refreshed separately, ***.bin represents the firmware file, and the version of the driver can be updated according to the rpm command, such as executing rpm-ivh***.rpm, where ***.rpm represents the driver file. After refreshing, the independent disk redundant array card can be more compatible with the system, which is beneficial to the performance of the independent disk redundant array card.

[0052] The type of the current redundant array of independent disks card is determined. If the type of the redundant array of independent disks card is the second preset type, the firmware of the redundant array of independent disks card can be updated based on the storcli tool, for example, by executing storcli / c*download file=***.rom noverchk to refresh the firmware, where * in c represents the controller number (redundant array of independent disks card), ***.rom represents the firmware file, and the version of the driver can be updated according to the rpm command, for example, by executing rpm–ivh***.rpm, where ***.rpm represents the driver file. After refreshing, the compatibility between the redundant array of independent disks card and the system can be improved, which is beneficial to the performance of the redundant array of independent disks card.

[0053] This ensures that the firmware and drivers for the redundant array of independent disks are up to date, thereby improving the overall performance and reliability of the system.

[0054] According to an embodiment of the present application, setting a read / write strategy for a redundant array of independent disks card includes setting read / write parameters of the redundant array of independent disks card based on the read / write characteristics of a solid state drive.

[0055] Specifically, when setting the read and write policy of the independent disk redundant array card, the read and write parameters of the independent disk redundant array card can be set according to the read and write characteristics based on the solid state drive. That is, the solid state drive (SSD) is significantly different from the traditional mechanical hard disk (HDD) in terms of read and write characteristics, that is, the solid state drive has the characteristics of high read and write speed, low latency, and durability. The read and write parameters of the independent disk redundant array card may include parameters such as READ Policy, Write Policy, and Strip Size, wherein the read policy includes No Read Ahead: no read pre-read operation, and Read Ahead: read pre-read operation, and the write policy includes Write Through: write operation directly writes to the hard disk and writes to the cache at the same time, and Write Back: write operation first writes to the cache, and the data in the cache is written to the hard disk at an appropriate time, and the stripe size is the block size of data distributed on multiple hard disks. Common stripe sizes are 4KB, 8KB, 16KB, 32KB, 64KB, etc. A larger stripe size can improve sequential read and write performance, but may increase the latency of random read and write.

[0056] When setting the read and write parameters of the independent disk redundant array card, you can set the READ Policy to NoRead Ahead, that is, the read speed of the SSD is very fast, and the pre-read operation may not bring significant performance improvement, but may increase unnecessary data transmission, so it can be set to not perform the read pre-read operation. And you can set the Write Policy to Write Through, that is, although Write Back can improve write performance, Write Through is safer, especially when using SSD, the write speed is already very fast, and Write Through can ensure data integrity. You can set the Strip Size to 64KB, that is, a larger stripe size can reduce the number of I / O operations and improve sequential read and write performance. 64KB is a common optimization value that is suitable for most SSDs. Therefore, through these steps, the read and write policy of the independent disk redundant array card can be optimized to improve the overall performance and reliability of the system.

[0057] According to an embodiment of the present application, core binding is performed on a redundant array of independent disks card and a central processor corresponding to a solid-state drive, including: determining a high-speed serial data transmission interface address corresponding to the redundant array of independent disks card; determining a processor identifier corresponding to the redundant array of independent disks card based on the high-speed serial data transmission interface address; and binding a read / write request to the central processor corresponding to the solid-state drive based on the processor identifier.

[0058] Specifically, when the independent disk redundant array card and the central processor corresponding to the solid-state drive are core-bound, the high-speed serial data transmission interface address corresponding to the independent disk redundant array card is first determined, and the PCIe (Peripheral Component Interconnect Express, a high-speed serial computer expansion bus standard) address of the independent disk redundant array card can be obtained by using the lspci command, such as executing lspci|egrep-i "BRCM|LSI" to obtain the PCIE address xx:xx.x corresponding to the independent disk redundant array card (subject to the actual address, such as 01:00.0). After determining the high-speed serial data transmission interface address, the processor identifier corresponding to the independent disk redundant array card can be determined according to the high-speed serial data transmission interface address. For example, the lspci-vvv command is used to obtain the NUMA node number of the independent disk redundant array card, such as executing lspci-vvv-s xx:xx.x|grep-i NUMA to obtain the NUMACODE value, which is 0 or 1 (taking a two-CPU configuration as an example).

[0059] It should be noted that the NUMA (Non-Uniform Memory Access) node number is used to identify a NUMA node in the system. A NUMA node is a logical unit that includes one or more CPU cores and local memory. In the NUMA architecture, each CPU core belongs to a specific NUMA node. Accessing local memory is faster than accessing remote memory. Determining the NUMA node can determine the corresponding processor identifier, so that the read and write requests can be bound to the central processor corresponding to the solid-state drive according to the processor identifier. For example, use the numactl command or add the --numa_cpu_nodes parameter in the performance test script to bind the I / O (input / output) request to the CPU core on a specific NUMA node. Therefore, after binding the CPU core, it can be ensured that when processing data, the CPU on the link where the independent disk redundant array card and the NVME SSD are located directly processes the data, avoiding the data processing delay caused by the data processing thread being assigned to other CPUs, thereby improving the data processing speed.

[0060] According to one embodiment of the present application, the operating system parameters are optimized, including at least one of the following methods: in the input / output request, turning off the addition of randomness; in adjacent input / output requests, prohibiting the merging of adjacent read and write requests; setting the maximum number of requests in the scheduling queue in each input / output request to the maximum value; setting the storage device to a non-rotating medium; turning on the affinity of input / output; turning off the input / output scheduler; turning on input / output statistics; setting the maximum number of sectors for a single input / output request to the maximum value.

[0061] Specifically, when optimizing the operating system parameters, you can turn off adding randomness in input / output requests, for example, execute echo 0> / sys / block / sd$mm / queue / add_random, that is, I / O requests (input / output requests) refer to read and write operations initiated by the operating system, which are sent to the hardware through the driver of the storage device (such as a hard disk or SSD). For example, when opening a file or saving data, the operating system generates I / O requests, which are sent to the hard disk or SSD for actual read and write operations. In high-performance storage devices (such as NVMe SSDs), it is usually not necessary to add randomness to I / O requests because these devices already have high performance and security. Therefore, by disabling add_random (parameter adding randomness), the system overhead can be reduced to improve the read and write performance of NVMe SSDs, especially in scenarios with high performance requirements.

[0062] Alternatively, when optimizing operating system parameters, you can prohibit the merging of adjacent read and write requests in adjacent input / output requests. For example, execute echo 2> / sys / block / sd$mm / queue / nomerges, that is, I / O request merging means that the operating system merges multiple adjacent I / O requests into a larger request, but on high-performance storage devices (such as NVMeSSD), reducing merging operations can further improve performance, that is, merging I / O requests requires additional computing and management overhead. On high-performance storage devices, these overheads may affect performance. Setting the nomerges parameter to 2 can prohibit merging operations and improve performance. As a result, each I / O request can be processed faster by reducing merging operations, thereby reducing latency, especially under high load conditions.

[0063] Alternatively, when optimizing operating system parameters, you can set the maximum number of requests in the scheduling queue for each input / output request to the maximum value. For example, by executing echo 2048> / sys / block / sd$mm / queue / nr_requests, you can set the nr_requests parameter to 2048, which means that the maximum number of requests allowed in the I / O scheduling queue is 2048. This can improve the concurrency of I / O operations, especially in scenarios with high load and high performance requirements, thereby reducing the queuing time of I / O requests and improving the overall response speed of the system.

[0064] Alternatively, when optimizing operating system parameters, you can set the storage device to non-rotational media. For example, execute echo 0> / sys / block / sd$mm / queue / rotational. This command is used to set the rotational attribute of a specific block device (such as a hard disk or SSD) in the Linux system. The rotational attribute is used to indicate whether the storage device is a rotational medium (such as a traditional mechanical hard disk). Setting the rotational attribute to 0 means that the system will treat the specified block device as a non-rotational medium (such as an SSD or NVMe SSD). This can optimize the I / O scheduling strategy and improve performance, especially in scenarios with high concurrency and high performance requirements.

[0065] Alternatively, when optimizing operating system parameters, you can enable input / output affinity, for example, by executing echo2> / sys / block / sd$mm / queue / rq_affinity, which is used to set the rq_affinity parameter for a specific block device (such as a hard disk or SSD) in the Linux system. The rq_affinity parameter controls the affinity of I / O requests, that is, the allocation strategy of I / O requests between CPU cores. Setting the rq_affinity parameter to 2 means that I / O requests will be strictly bound to the CPU core that initiated the request and will not be allowed to be processed on other CPU cores. This can reduce context switching and improve the efficiency of I / O operations, especially in scenarios with high concurrency and high performance requirements.

[0066] Alternatively, when optimizing the operating system parameters, turn off the input / output scheduler. For example, execute echonone> / sys / block / sd$mm / queue / scheduler. This command line is used to set the I / O scheduler of a specific block device (such as a hard disk or SSD) in the Linux system to none. None means disabling the I / O scheduler, allowing the storage device (such as an SSD or NVMeSSD) to use its internal optimization mechanism to process I / O requests. That is, by disabling the I / O scheduler, the operating system-level overhead can be reduced and performance can be improved. In a system that processes a large number of I / O requests, disabling the I / O scheduler can reduce the queuing time of I / O requests and improve the overall response speed of the system.

[0067] Alternatively, when optimizing operating system parameters, you can enable input / output statistics. For example, execute echo1> / sys / block / sd$mm / queue / iostats. This command line is used to enable the I / O statistics collection function for a specific block device (such as a hard disk or SSD) in the Linux system. The iostats parameter controls whether to enable the collection of I / O statistics. By setting the iostats parameter to 1, it means enabling the I / O statistics collection function for the specified block device, so that detailed statistics of I / O operations can be collected and recorded for performance monitoring and tuning.

[0068] Alternatively, when optimizing the operating system parameters, you can also set the maximum number of sectors for a single input / output request to the maximum value. For example, execute echo 1024> / sys / block / sd$mm / queue / max_sectors_kb. This command line is used to set the max_sectors_kb parameter for a specific block device (such as a hard disk or SSD) in the Linux system. The max_sectors_kb parameter controls the maximum number of sectors (in KB) allowed in a single I / O request. Setting the max_sectors_kb parameter to 1024 means that the maximum number of sectors allowed in a single I / O request is 1024KB, which can improve the efficiency of large block I / O operations, especially when processing large files.

[0069] It should be noted that when optimizing the operating system parameters, one or more of them may be optimized simultaneously. Through these steps, it is possible to ensure that the system is in the best state before use, thereby significantly improving the performance, reliability and stability of the system.

[0070] According to an embodiment of the present application, performing full disk initialization on the virtual disk includes: performing full disk initialization on the virtual disk based on the storcli tool.

[0071] Specifically, full disk initialization of the virtual disk is a key step to ensure data integrity and security. Full disk initialization can clear all old data on the virtual disk and ensure that new data will not be interfered with by old data when it is written, thereby improving data security and read and write efficiency. When full disk initialization of the virtual disk is performed, the virtual disk can be fully initialized according to the storcli tool, that is, through the storcli command, various configuration and management operations can be performed on the RAID card, including creating virtual disks, deleting virtual disks, and initializing virtual disks. In other words, in view of the operating mechanism of the BRCM RAID card, the newly established logical disk is fully initialized by executing storcli / c* / v*start init fullforce. In c, * represents the controller number (RAID card number), and v* is the ID number corresponding to the logical disk. Therefore, full disk initialization of the virtual disk can ensure data integrity and security, while improving data read and write efficiency.

[0072] According to one embodiment of the present application, determining an independent disk redundant array card further includes: determining a type of the independent disk redundant array card based on a command corresponding to an operating system, or determining a type of the independent disk redundant array card based on a configuration tool, wherein the type of the independent disk redundant array card includes a first preset type and a second preset type, the first preset type is an MCHP (Microchip Technology Incorporated) independent disk redundant array card, the second preset type is a BRCM (Broadcom Corporation) independent disk redundant array card, and the configuration tool is a storcli tool or an arcconf tool.

[0073] Specifically, when determining the independent disk redundant array card, the type of the independent disk redundant array card can be determined according to the corresponding command of the operating system. That is, the operating system can provide a command line tool to query hardware information, including the type of the independent disk redundant array card. For example, in a Linux system, the command lspci|egrep-i "BRCM|LSI" can be used. If there is return information of a BRCM RAID card, it is determined that the type of the independent disk redundant array card is the second preset type (BRCM independent disk redundant array card), that is, the server configuration includes a BRCM RAID card. By running lspci|egrep-i "Adaptec", if there is return information of a MCHP RAID card, it is determined that the type of the independent disk redundant array card is the first preset type (MCHP independent disk redundant array card), that is, the server configuration includes a MCHP RAID card.

[0074] Alternatively, the type of the redundant array of independent disks card may be determined based on a configuration tool. For example, when the storcli tool is used to run storcli show, if the returned result shows BRCM RAID card information, the type of the redundant array of independent disks card is determined to be the second preset type, that is, the server configuration includes a BRCM RAID card. When the arcconf tool is used to run arcconflist, if there is returned information of an MCHP RAID card, the type of the redundant array of independent disks card is determined to be the first preset type, that is, the server configuration includes an MCHP RAID card. Thus, the type of the redundant array of independent disks card may be determined by using a command line tool of the operating system or a specific configuration tool.

[0075] In addition, in one embodiment of the present application, the processor identifier (NUMA node number) can also be added to the preset performance test script to record the test performance result value, so as to analyze the results according to the test performance result value and the standard performance value of the solid-state drive and the performance bottleneck value of the independent disk redundant array card. That is to say, the performance test tool is used to perform a performance test on the NVMe SSD under the RAID5 configuration, and various performance indicators such as 4K random read and write IOPS, 128K sequential read and write bandwidth, etc. are recorded. The test results are compared with the standard performance value of the disk body of the NVMe SSD to see whether the actual performance is close to or reaches the maximum performance specification (standard performance value) provided by the manufacturer. For example, if the tested 4K random write IOPS is 1,000,000, and the standard performance value of the disk body is 1,200,000, it means that the actual performance has reached 83.3% of the standard performance value of the disk body. In addition, the test results are compared with the performance bottleneck value of the RAID card to see whether the actual performance is close to or reaches the maximum processing capacity of the RAID card. For example, if the RAID card's 4K random write performance bottleneck is 1,500,000 IOPS, and the test result is 1,350,000 IOPS, it means that the actual performance has reached 90% of the RAID card bottleneck. Therefore, adjustments can be made based on the results of the analysis (if the results are poor) to further improve the overall performance and reliability of the system.

[0076] As a specific example, combining Figure 2As shown, in TRIMODE mode, the type of the redundant array of independent disks card (RAID card) used in the operating system is first determined. When the type of the redundant array of independent disks card is the first preset type (MCHP RAID card), the level of the MCHP RAID card can be determined, such as RAID0 or RAID5. After determining the RAID level, five optimizations can be performed on the MCHP RAID card configuration, namely hard disk formatting and driver update, firmware version, read and write strategy setting, core binding and system parameter optimization. The specific optimization method can be determined according to the above detailed steps. After the tuning is completed, you can perform performance testing, such as adding it to the test script after binding the core. For example, the 4KRW test script reference is: fio--numa_cpu_nodes=1--ioengine=libaio--randrepeat=0--norandommap--th read--direct=1--stonewall--group_reporting--name=mytest--ramp_time=60--runtime=3600--time_based--numjobs=16--iodepth=128--filename= / dev / sd*--rw=randwrite--bs=4k--output=4K_randW.log--log_avg_msec=1000--write_iops_log=4K_randW_iops.lo. The test performance result value will be recorded in 4K_randW.log. After determining the performance test results, analyze the performance test results, that is, compare the performance test results with the disk SPEC and the RAID card bottleneck to analyze the performance test results. Among them, disk SPEC refers to the performance specifications of the hard disk (SSD or HDD) under standard test conditions, including read and write speeds, IOPS (number of input and output operations per second), latency and other indicators. These specifications are usually provided by the hard disk manufacturer to describe the maximum performance of the hard disk under ideal conditions. For example, the disk SPEC of an NVMe SSD may include its sequential read and write speeds (such as 3500MB / s read, 3000MB / s write) and random 4K read and write IOPS (such as 600,000IOPS read, 500,000IOPS write). The RAID card bottleneck refers to the maximum performance limit that the RAID card can achieve when processing data. This limit is affected by many factors such as the hardware design of the RAID card, the firmware (FW) version, driver optimization, and RAID level configuration. For example, a RAID card may have a 4K random write performance of 45,000IOPS when processing a RAID 5 configuration, which is the performance bottleneck of the RAID card under this configuration.

[0077] Similarly, when the type of the independent disk redundant array card is the second preset type (BRCM RAID card), the level of the BRCM RAID card can be determined, such as RAID0 or RAID5. After determining the RAID level, six optimizations can be performed on the MCHP RAID card configuration, namely hard disk formatting and driver update, firmware version, read and write policy settings, core binding, system parameter optimization, and full disk initialization of the virtual disk. The specific optimization method can be determined according to the above detailed steps. After the optimization is completed, performance testing can be performed, such as adding it to the test script after binding the core. Similarly, the test performance result value will be recorded in 4K_randW.log. After determining the performance test results, analyze the performance test results, that is, compare the performance test results with the disk SPEC and the RAID card bottleneck to analyze the performance test results.

[0078] Therefore, the present application can maximize the performance of NVME SSD in TRIMODE mode, so that the performance bottleneck is not limited to NVME SSD, which greatly improves the feasibility and rationality of NVME SSD application in TRIMODE mode, meets the industry's SSD development and application trends, and actual customer usage scenarios, and also provides technical accumulation and prerequisite guarantee for the future realization of NVME SSD replacement solutions for SATA SSD.

[0079] In summary, according to the method for improving the performance of the solid-state hard disk of the embodiment of the present application, in the TRIMODE mode, the type of the independent disk redundant array card is determined, wherein the independent disk redundant array card is used in combination with the solid-state hard disk, and the tuning strategy is determined according to the type of the independent disk redundant array card, and at least one of the parameters of the independent disk redundant array card, the solid-state hard disk and the operating system is adjusted according to the tuning strategy. Therefore, the method can solve the problem of low performance and limited performance of the solid-state hard disk in the TRIMODE mode, and improve the performance of the solid-state hard disk.

[0080] Corresponding to the above embodiments, the present application also proposes a device for improving the performance of a solid state drive.

[0081] like Figure 3 As shown, the device 100 for improving the performance of a solid state drive according to an embodiment of the present application includes: a first determination module 110 , a second determination module 120 and an adjustment module 130 .

[0082] The first determination module 110 is used to determine the type of the independent disk redundant array card in the TRIMODE mode, wherein the independent disk redundant array card is used in combination with the solid state drive. The second determination module 120 is used to determine the tuning strategy according to the type of the independent disk redundant array card. The adjustment module 130 is used to adjust at least one of the parameters of the independent disk redundant array card, the solid state drive, and the operating system according to the tuning strategy.

[0083] According to an embodiment of the present application, the second determination module 120 determines the tuning strategy according to the type of the independent disk redundant array card, and is specifically used to: when the type of the independent disk redundant array card is the first preset type, determine the tuning strategy to format the solid-state drive, update the firmware and driver of the independent disk redundant array card, set the read and write strategy of the independent disk redundant array card, perform core binding between the independent disk redundant array card and the central processor corresponding to the solid-state drive, and optimize the operating system parameters; when the type of the independent disk redundant array card is the second preset type, determine the tuning strategy to format the solid-state drive, update the firmware and driver of the independent disk redundant array card, set the read and write strategy of the independent disk redundant array card, perform core binding between the independent disk redundant array card and the central processor corresponding to the solid-state drive, optimize the operating system parameters, and perform full disk initialization on the virtual disk.

[0084] According to an embodiment of the present application, the adjustment module 130 formats the solid-state drive, specifically for: when the type of the independent disk redundant array card is the first preset type or the second preset type and the solid-state drive is connected to the server, formatting is performed based on the nvmecli tool; when the type of the independent disk redundant array card is the first preset type and the solid-state drive is connected to the server through the independent disk redundant array card, formatting is performed based on the arcconf tool; when the type of the independent disk redundant array card is the second preset type and the solid-state drive is connected to the server through the independent disk redundant array card, formatting is performed based on the storcli tool.

[0085] According to an embodiment of the present application, the adjustment module 130 updates the firmware and the driver of the redundant array of independent disks card, and is specifically used to: when the type of the redundant array of independent disks card is a first preset type, update the firmware of the redundant array of independent disks card based on the arcconf tool, and update the version of the driver based on the rpm command; when the type of the redundant array of independent disks card is a second preset type, update the firmware of the redundant array of independent disks card based on the storcli tool, and update the version of the driver based on the rpm command, wherein the driver is a driver between the redundant array of independent disks card and the operating system.

[0086] According to an embodiment of the present application, the adjustment module 130 sets the read and write strategy of the redundant array of independent disks card, specifically for setting the read and write parameters of the redundant array of independent disks card based on the read and write characteristics of the solid state drive.

[0087] According to an embodiment of the present application, the adjustment module 130 performs core binding on the independent disk redundant array card and the central processor corresponding to the solid-state hard disk, specifically for: determining the high-speed serial data transmission interface address corresponding to the independent disk redundant array card; determining the processor identifier corresponding to the independent disk redundant array card based on the high-speed serial data transmission interface address; and binding the read and write request to the central processor corresponding to the solid-state hard disk based on the processor identifier.

[0088] According to one embodiment of the present application, the adjustment module 130 optimizes the operating system parameters, including at least one of the following methods: in the input / output request, turning off the addition of randomness; in adjacent input / output requests, prohibiting the merging of adjacent read and write requests; setting the maximum number of requests in the scheduling queue in each input / output request to the maximum value; setting the storage device to a non-rotating medium; turning on the affinity of input / output; turning off the input / output scheduler; turning on input / output statistics; setting the maximum number of sectors for a single input / output request to the maximum value.

[0089] According to an embodiment of the present application, the adjustment module 130 performs full disk initialization on the virtual disk, specifically for: performing full disk initialization on the virtual disk based on the storcli tool.

[0090] According to an embodiment of the present application, the first determination module 110 determines an independent disk redundant array card, and is specifically used to: determine the type of the independent disk redundant array card based on a command corresponding to the operating system, or determine the type of the independent disk redundant array card based on a configuration tool, wherein the type of the independent disk redundant array card includes a first preset type and a second preset type, the first preset type is an MCHP independent disk redundant array card, the second preset type is a BRCM independent disk redundant array card, and the configuration tool is a storcli tool or an arcconf tool.

[0091] It should be noted that for details not disclosed in the device for improving the performance of a solid-state hard disk in the embodiment of the present application, please refer to the details disclosed in the method for improving the performance of a solid-state hard disk in the embodiment of the present application, and the details will not be repeated here.

[0092] According to the device for improving the performance of a solid-state hard disk according to the embodiment of the present application, the first determination module is used to determine the type of an independent disk redundant array card in the TRIMODE mode, wherein the independent disk redundant array card is used in combination with a solid-state hard disk, the second determination module is used to determine the tuning strategy according to the type of the independent disk redundant array card, and the adjustment module is used to adjust at least one of the parameters of the independent disk redundant array card, the solid-state hard disk, and the operating system according to the tuning strategy. Thus, the device can solve the problem of too low performance and limited performance of the solid-state hard disk in the TRIMODE mode, and improve the performance of the solid-state hard disk.

[0093] Corresponding to the above embodiments, the present application also proposes a computer-readable storage medium.

[0094] The computer-readable storage medium of the embodiment of the present application stores a program thereon, and when the program is executed by a processor, the above-mentioned method for improving the performance of the solid-state hard disk is implemented.

[0095] According to the computer-readable storage medium of the embodiment of the present application, by executing the above-mentioned method for improving the performance of the solid-state hard disk, the problem of low performance and limited performance of the solid-state hard disk in the TRIMODE mode can be solved, thereby improving the performance of the solid-state hard disk.

[0096] Corresponding to the above embodiment, the present application also proposes a server.

[0097] like Figure 4 As shown, the server 200 of the embodiment of the present application may include: a memory 210, a processor 220, and a program stored in the memory 210 and executable on the processor 220. When the processor 220 executes the program, the above-mentioned method for improving the performance of the solid state drive is implemented.

[0098] According to the server of the embodiment of the present application, by executing the above-mentioned method for improving the performance of the solid-state hard disk, it is possible to solve the problem of low performance and limited performance of the solid-state hard disk in the TRIMODE mode, thereby improving the performance of the solid-state hard disk.

[0099] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0100] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0101] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0102] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0103] In this application, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0104] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in the field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for improving the performance of a solid state drive, characterized in that: The method comprises: In the TRIMODE mode, determining the type of a redundant array of independent disks card, wherein the redundant array of independent disks card is used in conjunction with the solid state drive; Determining a tuning strategy according to the type of the independent disk redundant array card; At least one of the parameters of the redundant array of independent disks, the solid state drive, and the operating system is adjusted according to the tuning strategy.

2. The method for improving the performance of a solid state drive according to claim 1, characterized in that: The step of determining the tuning strategy according to the type of the redundant array of independent disks card comprises: In a case where the type of the redundant array of independent disks card is the first preset type, determining the tuning strategy to format the solid-state drive, update the firmware and driver of the redundant array of independent disks card, set the read and write strategy of the redundant array of independent disks card, perform core binding between the redundant array of independent disks card and a central processor corresponding to the solid-state drive, and optimize operating system parameters; When the type of the redundant array of independent disks card is the second preset type, the optimization strategy is determined to be formatting the solid state drive, updating the firmware and driver of the redundant array of independent disks card, setting the read and write strategy of the redundant array of independent disks card, core binding the redundant array of independent disks card and a central processing unit corresponding to the solid state drive, optimizing operating system parameters, and fully initializing the virtual disk.

3. The method for improving the performance of a solid state drive according to claim 2, characterized in that: The step of formatting the solid state hard disk includes: When the type of the independent disk redundant array card is the first preset type or the second preset type and the solid state drive is connected to the server, formatting is performed based on the nvmecli tool; When the type of the redundant array of independent disks card is the first preset type and the solid state drive is connected to the server through the redundant array of independent disks card, formatting is performed based on an arcconf tool; When the type of the redundant array of independent disks card is the second preset type and the solid state drive is connected to the server through the redundant array of independent disks card, formatting is performed based on the storcli tool.

4. The method for improving the performance of a solid state drive according to claim 2, characterized in that: The updating of the firmware and driver of the independent disk redundant array card includes: In a case where the type of the redundant array of independent disks card is a first preset type, updating the firmware of the redundant array of independent disks card based on an arcconf tool, and updating the version of the driver based on an rpm command; In a case where the type of the redundant array of independent disks card is a second preset type, the firmware of the redundant array of independent disks card is updated based on a storcli tool, and the version of the driver is updated based on an rpm command, wherein the driver is a driver between the redundant array of independent disks card and an operating system.

5. The method for improving the performance of a solid state drive according to claim 2, characterized in that: The step of setting the read and write strategy of the independent redundant array of disks card includes: The read and write parameters of the independent disk redundant array card are set based on the read and write characteristics of the solid state drive.

6. The method for improving the performance of a solid state drive according to claim 2, characterized in that: The step of core binding the independent disk redundant array card and the central processor corresponding to the solid state drive includes: Determine the high-speed serial data transmission interface address corresponding to the independent disk redundant array card; Determine a processor identifier corresponding to the redundant array of independent disks card based on the high-speed serial data transmission interface address; The read and write requests are bound to a central processor corresponding to the solid state drive based on the processor identifier.

7. The method for improving the performance of a solid state drive according to claim 2, wherein: The optimizing of the operating system parameters includes at least one of the following methods: In input / output requests, turn off adding randomness; In adjacent input / output requests, merging of adjacent read and write requests is prohibited; Set the maximum number of requests in the dispatch queue for each input / output request to the maximum value; Set the storage device to non-rotating media; Enable input / output affinity; Close the input / output scheduler; Enable input / output statistics; Set the maximum number of sectors for a single I / O request to the maximum value.

8. The method for improving the performance of a solid state drive according to claim 2, characterized in that: The full disk initialization of the virtual disk includes: The virtual disk is fully initialized based on the storcli tool.

9. The method for improving the performance of a solid state drive according to claim 1, characterized in that: The step of determining the independent disk redundant array card also includes: The type of the redundant array of independent disks card is determined based on a command corresponding to the operating system, or the type of the redundant array of independent disks card is determined based on a configuration tool, wherein the type of the redundant array of independent disks card includes a first preset type and a second preset type, the first preset type is an MCHP redundant array of independent disks card, the second preset type is a BRCM redundant array of independent disks card, and the configuration tool is a storcli tool or an arcconf tool.

10. A device for improving the performance of a solid state hard disk, characterized in that: The device comprises: A first determination module is used to determine the type of an independent disk redundant array card in the TRIMODE mode, wherein the independent disk redundant array card is used in conjunction with the solid state drive; A second determination module is used to determine the optimization strategy according to the type of the independent disk redundant array card; An adjustment module is used to adjust at least one of the parameters of the redundant array of independent disks, the solid state drive and the operating system according to the tuning strategy.

11. A computer-readable storage medium, characterized in that: A program is stored thereon, and when the program is executed by a processor, the method for improving the performance of a solid state drive according to any one of claims 1 to 9 is implemented.

12. A server, characterized in that: include: A memory, a processor, and a program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for improving the performance of a solid-state hard disk according to any one of claims 1 to 9 is implemented.

Images