WO2020037526A1 - 固态硬盘的存储性能的评估方法、装置和图像存储系统 - Google Patents

固态硬盘的存储性能的评估方法、装置和图像存储系统 Download PDF

Info

Publication number
WO2020037526A1
WO2020037526A1 PCT/CN2018/101636 CN2018101636W WO2020037526A1 WO 2020037526 A1 WO2020037526 A1 WO 2020037526A1 CN 2018101636 W CN2018101636 W CN 2018101636W WO 2020037526 A1 WO2020037526 A1 WO 2020037526A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
stored
hard disk
state hard
solid
Prior art date
Application number
PCT/CN2018/101636
Other languages
English (en)
French (fr)
Inventor
庹伟
张强
宋喆喆
Original Assignee
深圳市大疆创新科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市大疆创新科技有限公司 filed Critical 深圳市大疆创新科技有限公司
Priority to PCT/CN2018/101636 priority Critical patent/WO2020037526A1/zh
Priority to CN201880039850.9A priority patent/CN110785744A/zh
Publication of WO2020037526A1 publication Critical patent/WO2020037526A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
    • G06F11/3466—Performance evaluation by tracing or monitoring
    • G06F11/3476—Data logging
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
    • G06F11/3037—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system component is a memory, e.g. virtual memory, cache
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment

Definitions

  • the invention relates to the field of SSD (Solid State Drive, Solid State Drives) testing, in particular to a method, a device and an image storage system for evaluating the storage performance of a solid state drive.
  • SSD Solid State Drive, Solid State Drives
  • test data is written to the SSD in order to test the storage performance of the SSD, which reduces the service life of the SSD.
  • the PC test environment differs greatly from the actual use environment of the storage system.
  • the central processing unit CPU, memory DDR, and so on in the image storage system vary widely. PC-based test results are not significant for the image storage system.
  • the invention provides a method, a device and an image storage system for evaluating the storage performance of a solid state hard disk.
  • the present invention is implemented by the following technical solutions:
  • a method for evaluating storage performance of a solid-state hard disk includes:
  • an image storage system including:
  • a processor which is electrically connected to the solid state hard disk; wherein the processor is configured to:
  • a method for evaluating storage performance of a solid state hard disk includes:
  • the storage performance of the solid state hard disk is evaluated according to the time parameter when the image is stored in the solid state hard disk and the size of the image.
  • a storage performance evaluation device for a solid state hard disk including:
  • the storage device is configured to store program instructions
  • the processor calls the program instructions, and when the program instructions are executed, are used to:
  • the storage performance of the solid state hard disk is evaluated according to the time parameter when the image is stored in the solid state hard disk and the size of the image.
  • the present invention when the image to be stored is stored in the solid-state hard disk, the present invention records the time parameter when the image to be stored is stored in the solid-state hard disk, which facilitates the backend to evaluate the SSD based on the time parameter Storage performance, time parameter recording and image storage are performed at the same time.
  • the evaluation of the storage performance of the solid-state hard disk will not affect the storage of the image, nor will it reduce the life of the solid-state hard disk.
  • the invention can provide a basis for the performance evaluation of a new hard disk and a life evaluation for an old hard disk, and can provide a basis for a device to select a solid state hard disk.
  • FIG. 1 is a flowchart of a method for evaluating a storage performance of a solid state hard disk in an image storage system side according to an embodiment of the present invention
  • FIG. 2 is a structural block diagram of an image storage system in an embodiment of the present invention.
  • FIG. 3 is a structural block diagram of an image acquisition system in an embodiment of the present invention.
  • FIG. 4 is a schematic diagram of a manner of recording a time parameter by an image storage system in an embodiment of the present invention
  • FIG. 5 is a diagram showing a storage performance evaluation result of the solid state hard disk in an embodiment of the present invention.
  • FIG. 6 is a method flowchart of a method for evaluating storage performance of a solid-state hard disk on a back-end side according to an embodiment of the present invention
  • FIG. 7 is a flowchart of a specific method on the back-end side of a method for evaluating storage performance of a solid state hard disk in an embodiment of the present invention
  • FIG. 8 is a flowchart of another specific method of a method for evaluating storage performance of a solid-state hard disk in a back-end side according to an embodiment of the present invention
  • FIG. 9 is a structural block diagram of an apparatus for evaluating storage performance of a solid state hard disk in an embodiment of the present invention.
  • FIG. 10 is a structural block diagram of a solid state hard disk storage performance evaluation system according to an embodiment of the present invention.
  • FIG. 11 is a working flowchart of a solid-state hard disk storage performance evaluation system according to an embodiment of the present invention.
  • FIG. 1 is a method for evaluating the storage performance of a solid state hard disk provided by Embodiment 1 of the present invention.
  • the execution subject of the method for evaluating the storage performance of a solid state hard disk may be an image storage system, for example, an image storage system of an image acquisition system such as a camera or a video camera.
  • the method may include the following steps:
  • Step S101 acquiring an image to be stored
  • the image to be stored may be an image monitored by the photographing device, or may be another image to be stored, such as an image acquired from another device.
  • the image to be stored is an image monitored by the photographing device.
  • the shooting device is a part of the image acquisition system. Specifically, the image to be stored is an image monitored by the shooting device in real time. Without affecting the actual function of the image acquisition system (shooting function), the time parameters of the image when it is stored in the SSD are recorded in real time to provide data for later SSD performance evaluation. .
  • the solid-state hard disks are all referred to as the SSDs for short, which will not be described repeatedly later.
  • the image storage system 100 of this embodiment includes a first processor 110 and a solid state hard disk SSD (120 in FIG. 2 and FIG. 3).
  • the first processor 110 acquires an image monitored by the photographing device 130 in real time, it buffers the acquired image in the memory of the first processor 110, and the image to be stored is the cached image.
  • the first processor 110 may be a central processing unit (CPU).
  • the first processor 110 may further include a hardware chip.
  • the hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof.
  • the PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a universal array logic (GAL), or any combination thereof.
  • the first processor 110 in this embodiment is a CPU.
  • the photographing device 130 is mounted on a mobile device.
  • the mobile device can be an unmanned aerial vehicle, such as a drone; it can also be a ground mobile device, such as a remotely controlled vehicle; it can also be a surface mobile device, such as an unmanned ship; in addition, the mobile device can also be a handheld device , The user holds the handheld device, thereby driving the photographing device 130 to move.
  • Step S102 Store the image to be stored in the SSD, and record the time parameter when the image to be stored is stored in the SSD, so that the backend can evaluate the storage performance of the SSD according to the time parameter.
  • the image to be stored may be stored in the SSD after being packed, or may be directly stored in the SSD without being packed.
  • the image to be stored is a single frame image.
  • the image package having the single-frame image to be stored is stored in the SSD.
  • the image to be stored may be stored in the SSD frame by frame.
  • the recorded time parameter is a time parameter when an image to be stored in each frame is stored in the SSD, and the backend evaluates the storage performance of the SSD according to the time parameter when the image to be stored in each frame is stored in the SSD.
  • the backend may determine the storage bandwidth (ie, write bandwidth) of the image to be stored in each frame according to the time parameter when the image to be stored is stored in the SSD and the size of the image to be stored in each frame.
  • the storage bandwidth of the image to be stored in the frame to evaluate the storage performance of the SSD.
  • the image to be stored is an image packet including multiple frames of images.
  • the number of image frames in the image packet is less than a preset frame number threshold.
  • the preset frame number threshold can be selected as required, such as 4 frames, 5 frames, and so on.
  • the number of image frames included in multiple image packets may be equal or unequal.
  • the storage gap between two adjacent frames of images in the image packet is less than a preset gap threshold.
  • the storage gap between two adjacent frames of images in this embodiment refers to the time difference between the two adjacent frames of images being stored in the SSD.
  • the recorded time parameter is a time parameter when each image packet is stored in the SSD
  • the backend evaluates the storage performance of the SSD according to the time parameter when each image packet is stored in the SSD. Specifically, the backend determines the average storage bandwidth of multiple frames of images in each image packet according to the time parameter when each image packet is stored in the SSD and the size of each image packet. At this time, if the storage gap between two adjacent frames in the image packet is large, the accuracy of the average storage bandwidth of each frame image in the determined image packet is poor, which affects the evaluation of SSD storage performance.
  • the preset gap threshold in this embodiment may be selected according to requirements, such as 1 microsecond, 2 microseconds, and so on.
  • the image to be stored in the SSD each time cannot be too small, and the image to be stored each time in the SSD is also It should not be too large, or the storage time of the image to be stored will cause the deviation between the access time of the timer (the CPU is set by software) and the memory access time to be too large, and cause every time determined by the backend.
  • the storage bandwidth deviation of an image to be stored is too large, and it cannot accurately reflect the storage performance of the SSD.
  • the size of the image to be stored is related to the memory size of the SSD and the memory size of the central processing unit CPU. Specifically, the larger the SSD's memory, the larger the image to be stored.
  • the image to be stored is 4M or more and 100M or less, for example, 4M, 5M, 10M, 20M, 30M, 40M, 50M, 60M, 70M, 80M, 90M, 100M, and so on.
  • the time parameter includes a start time and an end time when the image to be stored is stored in the SSD.
  • the image storage system 100 records a start time when each frame image is stored in the SSD and an end time when each frame image is stored in the SSD.
  • the backend determines the storage bandwidth of each frame of image based on the start time and end time of each frame of image stored in the SSD and the size of each frame of image, and then evaluates the storage performance of the SSD based on the determined storage bandwidth of each frame of image.
  • the calculation method of the storage bandwidth of each frame of image is not limited to the above calculation formula.
  • the image storage system 100 records a start time when each image packet is stored in the SSD and an end time when each image packet is stored in the SSD.
  • the backend determines the average storage bandwidth of multiple frames of images in each image packet based on the start time and end time of each image packet being stored in the SSD, and the size of each image packet. Average storage bandwidth to evaluate the storage performance of the SSD.
  • the average storage bandwidth of the multi-frame images in each image packet can be calculated according to the following formula:
  • the average storage bandwidth of the multi-frame images in each image packet the size of the image packet / (the end time of the image packet being stored in the SSD -The start time when the image pack is stored in the SSD).
  • the calculation method of the average storage bandwidth of multiple frames of images in each image packet is not limited to the above calculation formula.
  • the time parameter includes a time period during which the image to be stored is stored in the SSD, and the time period during which the image to be stored is stored in the SSD is obtained according to a start time and an end time of the image to be stored in the SSD.
  • the backend evaluates the storage performance of the SSD, it directly determines the storage bandwidth of each image to be stored according to the duration of each image to be stored in the SSD and the size of each image to be stored, thereby evaluating the SSD's Storage performance.
  • the image storage system 100 records the length of time that each frame image is stored in the SSD.
  • the backend determines the storage bandwidth of each frame of image based on the length of time each frame is stored in the SSD and the size of each frame of image, and then evaluates the storage performance of the SSD based on the determined storage bandwidth of each frame of image.
  • the storage bandwidth of each frame of image can be calculated according to the following formula:
  • the storage bandwidth of each frame of image the size of the frame image / the length of time that the frame image is stored in the SSD.
  • the calculation method of the storage bandwidth of each frame of image is not limited to the above calculation formula.
  • the image storage system 100 records the length of time that each image packet is stored in the SSD.
  • the backend determines the average storage bandwidth of multi-frame images in each image packet according to the length of each image packet being stored in the SSD and the size of each image packet, and then according to the average storage bandwidth of multi-frame images in each image packet, Evaluate SSD storage performance.
  • the average storage bandwidth of the multi-frame images in each image packet can be calculated according to the following formula:
  • the average storage bandwidth of the multi-frame images in each image packet the size of the image packet / the length of time that the image packet is stored in the SSD.
  • the calculation method of the average storage bandwidth of multiple frames of images in each image packet is not limited to the above calculation formula.
  • the storage method of the image storage system 100 for storing time parameters may also be selected as required.
  • the image to be stored is stored in the SSD, and the time parameter when the image to be stored is stored in the SSD is recorded below.
  • the image to be stored may be cached in a continuous storage space, and a custom field is provided at the end of the storage space.
  • the time parameter when the image to be stored is stored in the SSD is recorded in the next to be stored. In the field at the end of the image.
  • the images to be stored include file1, file2, file3, ..., filen.
  • the image storage system 100 acquires the current time t1s (that is, the start time when file1 is stored in the SSD).
  • the image storage system 100 acquires The current time t1e (that is, the end time when file1 is stored in the SSD), the time difference between t1e and t1s is the time consumed by storing file1 in the SSD (that is, the length of time that file1 is stored in the SSD).
  • this embodiment stores the duration t1 when file1 is stored in the SSD into the last field of file2.
  • the duration t2 of file2 stored in the SSD is stored in the last field of file3
  • the duration tn-1 of filen-1 is stored in the SSD and stored in the end field of filen.
  • the backend can determine the storage bandwidth of the n-1 images to be stored according to the length of time when the n-1 images to be stored are stored in the SSD and the size of the n-1 images to be stored.
  • the backend can obtain the time parameter of each image being stored in the SSD and each of the images by reading the stored image information in the SSD and according to the read image information.
  • an image to be stored is stored in the SSD, and a time parameter when the image to be stored is stored in the SSD is recorded in a specific file.
  • the images to be stored include file1, file2, file3, ..., filen
  • the time parameters of file1, file2, file3, ..., and filen when they are stored in the SSD can be recorded through a specific file, that is, n numbers can be recorded in a specific file.
  • the time parameter when the image to be stored is stored in the SSD. Compared with the scheme for recording the time parameter in the stored image, this solution can record the time parameter when the nth image to be stored is stored in the SSD.
  • the specific file may be a notepad or other files capable of recording data. Further, while recording the time parameters when the image to be stored is stored in the SSD in a specific file, the size of the image to be stored can also be recorded in the specific file, so that when the specific file is accessed, the to-be-stored image can be obtained at the same time. The time parameter and the size of the image when it is stored. No need to visit the SSD to obtain the size of the image to be stored.
  • the way for the backend to obtain the time parameter may include, but is not limited to, the following two methods:
  • the image storage system 100 sends the time parameters to the backend.
  • the recorded time parameter may also be sent to the back end. Further, after the image to be stored is stored in the solid-state drive SSD and the time parameter when the image to be stored is stored in the SSD is recorded, the size of the image to be stored may be sent to the back end.
  • the image storage system 100 sends a specific file recording the time parameter when each image to be stored is stored in the SSD and the size of each image to be stored to the back end.
  • the image storage system 100 reads from a specific file the time parameter when each image to be stored is stored in the SSD, it sends the time parameter when each read image to be stored is stored in the SSD to The back end; and after the image storage system 100 reads the size of each image to be stored from a specific file, it sends the read size of each image to be stored to the back end.
  • the step of sending the recorded time parameter to the backend by the image storage system 100 is performed after the step of receiving the read request sent by the backend.
  • the image storage system 100 may select whether to use the backend according to the actual needs of the backend.
  • the recorded time parameters are sent to the back end, which is highly flexible.
  • the image storage system 100 sends the recorded time parameters to the backend at a preset frequency (such as 30 minutes / times), and the backend can analyze the storage performance of the SSD in time to avoid further losses.
  • the backend reads a specific file, thereby obtaining from the read specific file the time parameter when each image to be stored is stored in the SSD and the size of each image to be stored.
  • the method for evaluating the SSD storage performance in this embodiment may further include: receiving the storage performance evaluation result of the SSD sent by the backend, so that the image storage system 100 side obtains the storage performance evaluation result of the SSD.
  • the storage performance evaluation result of the SSD is generated by the backend according to the time parameter of the image to be stored in the SSD and the size of the image to be stored. Specifically, the backend first determines the storage bandwidth of each image stored in the SSD according to the time parameter of the image being stored in the SSD and the size of the image; then, according to the storage bandwidth of each image stored in the SSD, the storage of the SSD is performed. Performance is evaluated.
  • the backend determines the storage bandwidth of each frame image to be stored in the SSD according to the time parameter of each frame image being stored in the SSD and the size of each frame image, and then according to each The frame image is stored in the storage bandwidth of the SSD, and the storage performance of the SSD is evaluated.
  • the image to be stored is an image packet with multiple frames of images
  • the backend determines the storage bandwidth of each image packet stored in the SSD according to the time parameter of each image packet being stored in the SSD and the size of each image packet. Then, according to the storage bandwidth of each image packet stored in the SSD, the storage performance of the SSD is evaluated.
  • the backend evaluates the storage performance of the SSD according to the storage bandwidth of each image stored in the SSD, according to the chronological order of the storage bandwidth of multiple images stored in the SSD and each image stored in the SSD, Determine the fluctuation information of the storage bandwidth of the SSD; and then evaluate the storage performance of the SSD based on the fluctuation information of the storage bandwidth of the SSD.
  • the image to be stored is a single frame image
  • the fluctuation information of the storage bandwidth of the SSD is determined according to the chronological order of the storage bandwidth of the multi-frame image being stored in the SSD and each frame of the image being stored in the SSD; and then according to the SSD
  • the storage bandwidth fluctuation information is used to evaluate the storage performance of the SSD.
  • the backend determines fluctuation information of the storage bandwidth of the SSD according to the storage bandwidth of the multiple image packets stored in the SSD and the time sequence of each image packet stored in the SSD. ; Then, according to the fluctuation information of the storage bandwidth of the SSD, the storage performance of the SSD is evaluated.
  • the storage performance evaluation result of the SSD is an indicator line formed to characterize the storage bandwidth when each image is stored in the SSD.
  • the storage performance evaluation result of the SSD is not limited to the indication line form, and may also be discrete data, for example, the storage bandwidth of each image to be stored and the time sequence in which each image to be stored is stored in the SSD.
  • FIG. 5 is a display diagram showing the evaluation results of the storage performance of an SSD.
  • the ordinate represents the storage bandwidth
  • the abscissa is a number arranged according to the time sequence of each image to be stored in the SSD (the smaller the number, The earlier the image is stored in the SSD)
  • the ordinate corresponding to each point represents the storage bandwidth of the image stored in the SSD
  • the corresponding abscissa represents the number of the image.
  • the storage performance of the SSD suddenly drops, but it basically remains at about 500MB / s, and this performance can no longer meet the performance requirements of the image storage system 100. Therefore, the amount of image data in this embodiment needs to be sufficient to accurately judge the storage performance of the SSD.
  • the back end of this embodiment may be a mobile terminal, such as a mobile phone, a tablet computer, or a server.
  • the method for evaluating the storage performance of an SSD when an image to be stored is stored in the SSD, a time parameter when the image to be stored is stored in the SSD is recorded, which is convenient for the backend to evaluate the storage performance of the SSD based on the time parameter. Parameter recording and image storage are performed at the same time.
  • the evaluation of SSD storage performance will not affect image storage, nor will it reduce the service life of the SSD.
  • the invention can provide a basis for performance evaluation of a new hard disk and a life assessment for an old hard disk, and can provide a basis for a device to select an SSD.
  • the present invention uses the image monitored by the shooting device 130 as an image to be stored. This is because as the resolution of the shooting device 130 increases, The higher the pixel width becomes, the larger the data size of the images monitored by the shooting device 130 becomes. The data volume of each frame reaches the megabyte level, which is sufficient to test the storage performance of the SSD.
  • the image acquisition system has higher and higher requirements for the image storage system 100.
  • the SSD itself is a complex SOC system, and its performance fluctuates with factors such as environment, temperature, and market use. SSD firmware from different manufacturers is different. The performance is also very different. Through the method for evaluating the SSD storage performance of the present invention, the performance evaluation of the new hard disk and the life evaluation of the old hard disk can be provided, and the reliability of the image storage system 100 is improved.
  • the reasons for the decline in SSD storage performance may include the SSD ’s high temperature and a large number of random write operations.
  • the storage performance of the SSD in any state at any time can be obtained. It can be used to evaluate the storage performance change of the SSD during the process of writing the image, preventing the incomplete performance of the SSD from being used in the image acquisition system or other systems.
  • a second embodiment of the present invention provides an image storage system including a first processor 110 and an SSD.
  • the first processor 110 is electrically connected to the SSD (120 in FIG. 2 and FIG. 3).
  • the first processor 110 may implement a corresponding method as shown in the embodiment of FIG. 1 of the present invention.
  • the first processor 110 is configured to obtain an image to be stored; store the image to be stored in a solid-state drive SSD, and record a time parameter when the image to be stored is stored in the SSD, so that the backend can The time parameter evaluates the storage performance of the SSD.
  • the working principle of the first processor 110 may be further explained by referring to the method for evaluating SSD storage performance in the first embodiment, which is not described herein again.
  • the first processor 110 may include one or more.
  • the first processor 110 may be a central processing unit (CPU).
  • the first processor 110 may further include a hardware chip.
  • the hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof.
  • the PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a general array logic (GAL), or any combination thereof.
  • the image to be stored may be an image monitored by a photographing device, or may be another image to be stored, such as an image acquired from another device.
  • the image storage system 100 is part of an image acquisition system.
  • the image acquisition system further includes a photographing device 130, and the image to be stored is an image monitored by the photographing device 130.
  • the photographing device 130 is a part of an image acquisition system.
  • the image to be stored is an image monitored by the shooting device 130 in real time. Without affecting the actual function of the image acquisition system (shooting function), the time parameters of the image when it is stored in the SSD are recorded in real time to provide SSD performance evaluation in the future. data.
  • the photographing device 130 is mounted on a mobile device.
  • the mobile device can be an unmanned aerial vehicle, such as a drone; it can also be a ground mobile device, such as a remotely controlled vehicle; it can also be a surface mobile device, such as an unmanned ship; in addition, the mobile device can also be a handheld device , The user holds the handheld device, thereby driving the photographing device 130 to move.
  • the image storage system 100 when an image to be stored is stored in the SSD, a time parameter when the image to be stored is stored in the SSD is recorded. Recording and image storage are performed at the same time.
  • the evaluation of the storage performance of the SSD will not affect the storage of the image, nor will it reduce the life of the SSD.
  • the invention can provide a basis for performance evaluation of a new hard disk and a life assessment for an old hard disk, and can provide a basis for a device to select an SSD.
  • FIG. 6 is a method flowchart of a method for evaluating SSD storage performance according to Embodiment 3 of the present invention.
  • the execution body of the method for evaluating SSD storage performance may be a back end, and the back end may be a mobile terminal, such as a mobile phone, a tablet computer, or a server.
  • the method for evaluating SSD storage performance in this embodiment may include the following steps:
  • Step S601 acquiring a time parameter and an image size when the image is stored in the SSD;
  • the manner in which the back-end acquires the time parameters and image size when the image is stored in the solid-state drive SSD may include the following methods:
  • step 601 may also be: receiving a time parameter and an image size when the image sent by the image storage system is stored in the SSD.
  • the backend sends a read request to the image storage system before receiving the time parameter and image size when the image sent by the image storage system is stored in the SSD.
  • the image storage system after receiving the read request, sends a time parameter when the image is stored in the SSD and the size of the image to the back end. For example, the backend judges that the image is damaged (such as dropped frames) based on the image in the SSD, and then sends a read request to the image storage system to analyze the storage performance of the SSD and obtain whether the image damage is caused by the decline in SSD storage performance.
  • the image storage system sends the time parameters and image size recorded by the image storage system to the back end according to a preset frequency (such as 30 minutes / times).
  • the back end passively receives the image storage system.
  • the time parameter and image size when the sent image is stored in the SSD.
  • SSD software to write test data to the SSD to evaluate SSD storage performance
  • this method cannot be applied to embedded systems such as cameras and camcorders in the working state, so it is impossible to track embedded systems such as cameras and camcorders in a timely manner.
  • the back end of this embodiment tracks SSD storage performance according to the time parameter and image size recorded by the image storage system, which can be applied to drones, especially drones that are in the process of aerial photography.
  • the SSD storage performance is degraded, the aerial image cannot be stored in the SSD or the aerial image is damaged when it is stored in the SSD.
  • the drone may be useless because the image cannot be saved or the saved image is unavailable, resulting in waste of resources.
  • the storage performance of the SSD is tracked in a timely manner through the back end.
  • the drone can stop aerial photography in time, effectively prevent the drone from wasting unnecessary resources, and can timely find the cause of the SSD storage performance degradation In order to perform different strategic operations based on the reasons for the decline in SSD storage performance.
  • step 601 may further include: reading image information stored in the SSD; analyzing the read image information to obtain a time parameter when each image is stored in the SSD and a size of each image.
  • the back end reads and records the time parameters and the size of the image when the image is stored in the SSD.
  • the image storage system records the time parameter and the size of the image when the image is stored in the SSD in a specific file.
  • the specific file may be a notepad or other files capable of recording data.
  • the backend directly reads the images stored in the SSD and analyzes the read images to obtain the time parameters and the size of each image when each image is stored in the SSD.
  • the image is a single-frame image.
  • the image may be an image packet with a single-frame image or a single-frame image.
  • the time parameter is a time parameter when each frame of the image is stored in the SSD.
  • the image is an image packet including multiple frames of images.
  • the number of image frames in the image packet is less than a preset frame number threshold.
  • the preset frame number threshold can be selected as required, such as 4 frames, 5 frames, and so on.
  • the number of image frames included in multiple image packets may be equal or unequal.
  • the storage gap between two adjacent frames of images in the image packet is less than a preset gap threshold.
  • the storage gap between two adjacent frames of images in this embodiment refers to the time difference between the two adjacent frames of images being stored in the SSD.
  • the time parameter is a time parameter when each image packet is stored in the SSD.
  • the preset gap threshold in this embodiment may be selected according to requirements, such as 1 microsecond, 2 microseconds, and so on.
  • the time parameter includes a start time and an end time when the image is stored in the SSD.
  • the time parameter includes a start time when each frame image is stored in the SSD and an end time when each frame image is stored in the SSD.
  • the time parameter includes a start time when each image packet is stored in the SSD and an end time when each image packet is stored in the SSD.
  • the time parameter includes a time period during which the image is stored in the SSD, and the time period during which the image is stored in the SSD is obtained according to a start time and an end time of the image stored in the SSD.
  • the time parameter includes the duration of each frame image being stored in the SSD.
  • the storage method of the time parameter may also be selected as required.
  • the time parameter when the image is stored in the SSD is stored in the next image stored in the SSD.
  • the time parameter when the image is stored in the SSD is recorded in the last field of the next image stored in the SSD.
  • the images stored in the SSD include file1, file2, file3, ..., filen.
  • the start time of file1 stored in SSD is t1s and the end time is t1e
  • the start time of file2 stored in SSD is t2s and the end time is t2e
  • the start time of file3 stored in SSD is t3s and the end time is t3e
  • the start time of filen stored in SSD is tns, and the end time is tne.
  • the time parameters are the start time and end time of the image being stored in the SSD, the start time and end time of file1 being stored in the SSD are recorded in the end field of file2, and the file2 is stored in the start time and end time of the SSD.
  • filen-1 is stored in the start time and end time of the SSD and recorded in the end field of filen.
  • the time parameter is the duration of the image being stored in the SSD, the duration of file1 being stored in the SSD is recorded in the end field of file2, the duration of file2 is being stored in the SSD is recorded in the end field of file3, and so on, filen
  • the duration of -1 stored in SSD is recorded in the last field of filen.
  • the backend can obtain the time parameter and image size of the image stored in the SSD through the second method of obtaining the time parameter and image size when the image is stored in the solid-state drive SSD.
  • the time parameter when the image is stored in the SSD and the size of the image are correspondingly stored in a specific file.
  • the specific file records file1, file2, file3, ..., and filen corresponding to the time parameters when stored in the SSD and file1, file2, file3, ..., and filen correspond to the size of.
  • time parameter and the size of the image when the image is stored in the SSD are stored in a specific file, you can use the first or the second method to obtain the time parameter and the size of the image when the image is stored in the SSD. Get the time parameters and image size of the image being stored in the SSD.
  • Step S602 The storage performance of the SSD is evaluated according to the time parameter when the image is stored in the SSD and the size of the image.
  • the execution process of step S602 may include: determining a storage bandwidth (ie, a write bandwidth) of each image stored in the SSD according to a time parameter of the image being stored in the SSD and an image size; and a storage bandwidth of each image stored in the SSD To evaluate the storage performance of SSDs.
  • a storage bandwidth ie, a write bandwidth
  • the image storage system records the start time when each frame image is stored in the SSD and the end time when each frame image is stored in the SSD.
  • the backend determines the storage bandwidth of each frame of image based on the start time and end time of each frame of image stored in the SSD and the size of each frame of image, and then evaluates the storage performance of the SSD based on the determined storage bandwidth of each frame of image.
  • the calculation method of the storage bandwidth of each frame of image is not limited to the above calculation formula.
  • the image storage system records a start time when each image packet is stored in the SSD and an end time when each image packet is stored in the SSD.
  • the backend determines the average storage bandwidth of multiple frames of images in each image packet based on the start time and end time of each image packet being stored in the SSD, and the size of each image packet. Average storage bandwidth to evaluate the storage performance of the SSD.
  • the average storage bandwidth of the multi-frame images in each image packet can be calculated according to the following formula:
  • the average storage bandwidth of the multi-frame images in each image packet the size of the image packet / (the end time of the image packet being stored in the SSD -The start time when the image pack is stored in the SSD).
  • the calculation method of the average storage bandwidth of multiple frames of images in each image packet is not limited to the above calculation formula.
  • the time parameter includes a time period during which the image is stored in the SSD, and the time period during which the image is stored in the SSD is obtained according to a start time and an end time of the image stored in the SSD.
  • the image storage system records the duration of each frame image being stored in the SSD.
  • the backend determines the storage bandwidth of each frame of image based on the length of time each frame is stored in the SSD and the size of each frame of image, and then evaluates the storage performance of the SSD based on the determined storage bandwidth of each frame of image.
  • the calculation method of the storage bandwidth of each frame of image is not limited to the above calculation formula.
  • the image storage system records the length of time that each image packet is stored in the SSD.
  • the backend determines the average storage bandwidth of multi-frame images in each image packet according to the length of each image packet being stored in the SSD and the size of each image packet, and then according to the average storage bandwidth of multi-frame images in each image packet, Evaluate SSD storage performance.
  • the average storage bandwidth of the multi-frame images in each image packet can be calculated according to the following formula:
  • the average storage bandwidth of the multi-frame images in each image packet the size of the image packet / the length of time that the image packet is stored in the SSD.
  • the calculation method of the average storage bandwidth of multiple frames of images in each image packet is not limited to the above calculation formula.
  • FIG. 5 is a display diagram showing the evaluation results of the storage performance of an SSD.
  • the ordinate represents the storage bandwidth
  • the abscissa is a number arranged in the time sequence of each image stored in the SSD (the smaller the number, the image is stored The earlier the time of entering the SSD), the ordinate corresponding to each point indicates that the image is stored in the storage bandwidth of the SSD, and the corresponding abscissa indicates the number of the image. It can be seen from Figure 5 that before the image number is about 800, the overall performance of the hard disk is good, about 850MB / s, but because the amount of image data is small, if you use this performance to evaluate the hard disk, you will misjudge the SSD to meet the needs of the image storage system. .
  • the storage performance of the SSD suddenly drops, but it basically remains at about 500MB / s, and this performance can no longer meet the performance requirements of the image storage system. Therefore, the amount of image data in this embodiment needs to be sufficient to accurately judge the storage performance of the SSD.
  • the backend evaluates the storage performance of the SSD according to the time parameter when the image is stored in the SSD and the size of the image, it also sends the evaluation result of the storage performance of the SSD to the image storage system, so that the image storage system Keep up to date with the storage performance of the SSDs they are using.
  • the backend after the backend evaluates the storage performance of the SSD according to the time parameter when the image is stored in the SSD and the size of the image, it can also display the evaluation result of the storage performance of the SSD, thereby visually presenting the storage of the SSD.
  • Performance evaluation results In this embodiment, the storage performance evaluation result of the SSD may be displayed in the form of an indication line; of course, the display manner of the storage performance evaluation result of the SSD is not limited to the form of the indication line, and may also be discrete data, for example, as shown in FIG. 5 It can display the storage bandwidth of each image to be stored and the time sequence of each image to be stored being stored in the SSD.
  • the storage performance of multiple SSDs needs to be obtained in order to screen the SSDs that meet the requirements.
  • Each of the multiple SSDs stores at least one image.
  • the image storage system stores the images to be stored in multiple SSDs at the same time, and records the time parameters of each image to be stored in each SSD.
  • the image storage system stores each image to be stored in one of the SSDs, and records a time parameter of each image to be stored being stored in the corresponding SSD.
  • the backend obtains the time parameter and size when the image in each SSD is stored; and evaluates the storage performance of each SSD according to the time parameter and size when the image in each SSD is stored .
  • the back-end obtains the time parameter and size of the image when each SSD is stored, and the back-end implements the evaluation of the storage performance of each SSD based on the time parameter and size of the image when each SSD is stored. Please refer to the above embodiments, which will not be repeated here.
  • the backend After the backend evaluates the storage performance of each SSD according to the time parameter and size when the image in each SSD is stored, it filters multiple based on the evaluation results and preset policies of each SSD's storage performance.
  • the preset policy may include: fluctuation of the storage bandwidth of the SSD is less than or equal to a preset fluctuation threshold.
  • the preset policy may include: the storage bandwidth of the SSD is greater than or equal to a preset bandwidth threshold.
  • the preset policy may include: using an SSD having a maximum storage bandwidth of the SSD as a storage device.
  • the preset strategy may include: selecting an SSD with the smallest fluctuation in the storage bandwidth among the SSDs with a larger storage bandwidth of the SSD as the storage device.
  • the method for evaluating the SSD storage performance of the embodiment of the present invention when an image is stored in the SSD, a time parameter when the image is stored in the SSD is recorded. At the same time, the evaluation of the storage performance of the SSD will not affect the storage of the image, nor will it reduce the service life of the SSD.
  • the invention can provide a basis for performance evaluation of a new hard disk and a life assessment for an old hard disk, and can provide a basis for a device to select an SSD.
  • the amount of test data is small and cannot fully reflect the performance of the SSD.
  • the present invention uses the image monitored by the shooting device as the image to be stored. This is because the resolution of the shooting device is getting higher and higher The pixel width is getting deeper and deeper, and the data amount of the image monitored by the shooting device is getting larger and larger. The data amount of each frame has reached the level of megabytes, and the amount of data is sufficient to test the storage performance of the SSD.
  • the image acquisition system has higher and higher requirements for the image storage system.
  • the SSD itself is a complex SOC system, and its performance fluctuates with factors such as environment, temperature, and market use. SSD firmware from different manufacturers has different performance. It is also very different. Through the method for evaluating the SSD storage performance of the present invention, the performance evaluation of a new hard disk and the life evaluation of an old hard disk can be provided, which improves the reliability of the image storage system.
  • the reasons for the decline in SSD storage performance may include the SSD ’s high temperature and a large number of random write operations.
  • the storage performance of the SSD in any state at any time can be obtained. It can be used to evaluate the storage performance change of the SSD during the process of writing the image, preventing the incomplete performance of the SSD from being used in the image acquisition system or other systems.
  • a fourth embodiment of the present invention provides an SSD storage performance evaluation device, including a second processor 210 and a storage device 220.
  • the storage device 220 is configured to store program instructions.
  • the second processor 210 invokes a program instruction.
  • the program instruction When executed, it is used to obtain a time parameter and the size of the image when the image is stored in the SSD; according to the time parameter and the size of the image when the image is stored in the SSD, Evaluate the storage performance of the SSD.
  • the second processor 210 may implement corresponding methods as shown in the embodiments of FIG. 6, FIG. 7, and FIG. 8 of the present invention.
  • the working principle of the second processor 210 can be further explained by referring to the method for evaluating SSD storage performance in the third embodiment, which will not be repeated here.
  • the second processor 210 may include one or more.
  • the second processor 210 may be a central processing unit (CPU).
  • the second processor 210 may further include a hardware chip.
  • the hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof.
  • the PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a general array logic (GAL), or any combination thereof.
  • the storage device 220 may include volatile memory, such as random-access memory (RAM); the storage device 220 may also include non-volatile memory, such as flash memory (flash memory), hard disk (HDD) or solid-state drive (SSD); the storage device 220120 may further include a combination of the above types of memories.
  • volatile memory such as random-access memory (RAM)
  • non-volatile memory such as flash memory (flash memory), hard disk (HDD) or solid-state drive (SSD)
  • SSD solid-state drive
  • the storage device 220120 may further include a combination of the above types of memories.
  • the apparatus for evaluating the storage performance of an SSD records the time parameters when an image is stored in the SSD when the image is stored in the SSD, which is convenient for the backend to evaluate the storage performance of the SSD based on the time parameter. At the same time, the evaluation of the storage performance of the SSD will not affect the storage of the image, nor will it reduce the service life of the SSD.
  • the invention can provide a basis for performance evaluation of a new hard disk and a life assessment for an old hard disk, and can provide a basis for a device to select an SSD.
  • the fifth embodiment of the present invention provides an SSD storage performance evaluation system, which includes an image storage system 100 and a back-end 200.
  • the image storage system 100 and the back-end 200 are communicatively connected.
  • the image storage system 100 and the back-end 200 are communicatively connected based on a wireless communication method, or are communicatively connected based on a wired communication method.
  • the image storage system 100 includes a first processor 110 and an SSD electrically connected to the first processor 110, and the back-end 200 includes a second processor 210 and a storage device 220 electrically connected to the second processor 210.
  • the first processor 110 is communicatively connected with the second processor 210.
  • the work flow of the SSD storage performance evaluation system may include the following steps:
  • Step S1101 The image storage system 100 acquires an image to be stored
  • Step S1102 the image storage system 100 stores an image to be stored in the SSD, and records a time parameter when the image to be stored is stored in the SSD;
  • Step S1103 the backend 200 obtains the time parameter and the size of the image when the image is stored in the SSD;
  • Step S1104 The backend 200 evaluates the storage performance of the SSD according to the time parameter when the image is stored in the SSD and the size of the image.
  • the execution subject of steps S1101 and S1102 is the first processor 110, and the execution subject of steps S1103 and S1104 is the second processor 210.
  • the execution process of step S1101 and step S1102 refer to Embodiment 1 and Embodiment 2.
  • the execution process of step S1103 and step S1104 refer to Embodiment 3 and Embodiment 4, which are not repeated here.
  • the back end 200 in this embodiment may be a mobile terminal, such as a mobile phone, a tablet computer, or the like, or may be a server.
  • the sixth embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored.
  • the program is executed by a processor, the steps of the method for evaluating SSD storage performance of the first or third embodiment are implemented.
  • the program can be stored in a computer-readable storage medium.
  • the program When executed, the processes of the embodiments of the methods described above may be included.
  • the storage medium may be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM), or a random access memory (Random, Access Memory, RAM).

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Quality & Reliability (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Television Signal Processing For Recording (AREA)

Abstract

一种固态硬盘的存储性能的评估方法、装置和图像存储系统，其中，所述方法包括：获取待存储的图像；将所述待存储的图像存入所述固态硬盘，并记录所述待存储的图像被存入所述固态硬盘时的时间参数，以使得后端能够根据所述时间参数评估所述固态硬盘的存储性能。本发明在待存储的图像被存入固态硬盘时，记录待存储的图像被存入固态硬盘时的时间参数，便于后端基于时间参数评估固态硬盘的存储性能，时间参数的记录与图像存储同时进行，固态硬盘的存储性能的评估不会影响图像的存储，也不会降低固态硬盘的使用寿命。本发明可以对新硬盘的性能评估、对旧硬盘的寿命评估提供依据，并且能够给设备选择固态硬盘提供依据。

Description

固态硬盘的存储性能的评估方法、装置和图像存储系统 技术领域
本发明涉及SSD(固态硬盘，Solid State Drives)测试领域，尤其涉及一种固态硬盘的存储性能的评估方法、装置和图像存储系统。
背景技术
在进行SSD的存储性能测试时，通常基于PC上的软件写入测试数据至SSD，再根据测试数据写入SSD的结果对SSD的存储性能进行评估。上述方案中，为了测试SSD的存储性能而写入测试数据至SSD中，降低了SSD的使用寿命。并且，PC测试环境与存储系统的实际使用环境区别较大，图像存储系统中的中央处理器CPU、内存DDR等千差万别，基于PC的测试结果对图像存储系统来说意义不大。
发明内容
本发明提供一种固态硬盘的存储性能的评估方法、装置和图像存储系统。
具体地，本发明是通过如下技术方案实现的：
根据本发明的第一方面，提供一种固态硬盘的存储性能的评估方法，所述方法包括：
获取待存储的图像；
将所述待存储的图像存入所述固态硬盘，并记录所述待存储的图像被存入所述固态硬盘时的时间参数，以使得后端能够根据所述时间参数评估所述固态硬盘的存储性能。
根据本发明的第二方面，提供一种图像存储系统，包括：
固态硬盘；以及
处理器，所述处理器与所述固态硬盘电连接；其中，所述处理器用于：
获取待存储的图像；
将所述待存储的图像存入所述固态硬盘，并记录所述待存储的图像被存入所述固态硬盘时的时间参数，以使得后端能够根据所述时间参数评估所述固态硬盘的存储性能。
根据本发明的第三方面，提供一种固态硬盘的存储性能的评估方法，所述方法包括：
获取图像被存入所述固态硬盘时的时间参数及所述图像的大小；
根据所述图像被存入所述固态硬盘时的时间参数及所述图像的大小，对所述固态硬盘的存储性能进行评估。
根据本发明的第四方面，提供一种固态硬盘的存储性能评估装置，包括：
存储装置和处理器；
所述存储装置，用于存储程序指令；
所述处理器，调用所述程序指令，当所述程序指令被执行时，用于：
获取图像被存入所述固态硬盘时的时间参数及所述图像的大小；
根据所述图像被存入所述固态硬盘时的时间参数及所述图像的大小，对所述固态硬盘的存储性能进行评估。
由以上本发明实施例提供的技术方案可见，本发明在待存储的图像被存入固态硬盘时，记录待存储的图像被存入固态硬盘时的时间参数，便于后端基于时间参数评估SSD的存储性能，时间参数的记录与图像存储同时进行，固态硬盘的存储性能的评估不会影响图像的存储，也不会降低固态硬盘的使用寿命。本发明可以对新硬盘的性能评估、对旧硬盘的寿命评估提供依据，并且能够给设备选择固态硬盘提供依据。
附图说明
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1是本发明一实施例中的固态硬盘的存储性能的评估方法在图像存储系统侧的方法流程图；
图2是本发明一实施例中的图像存储系统的结构框图；
图3是本发明一实施例中的图像采集系统的结构框图；
图4是本发明一实施例中的图像存储系统记录时间参数的方式示意图；
图5是本发明一实施例中的固态硬盘的存储性能评估结果显示图；
图6是本发明一实施例中的固态硬盘存储性能的评估方法在后端侧的方法流程图；
图7是本发明一实施例中的固态硬盘存储性能的评估方法在后端侧的一具体方法流程图；
图8是本发明一实施例中的固态硬盘存储性能的评估方法在后端侧的另一具体方法流程图；
图9是本发明一实施例中的固态硬盘存储性能的评估装置的结构框图；
图10是本发明一实施例中的固态硬盘存储性能的评估系统的结构框图；
图11是本发明一实施例中的固态硬盘存储性能的评估系统的工作流程图。
具体实施方式
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
下面结合附图，对本发明的固态硬盘的存储性能的评估方法、装置和图像存储系统进行详细说明。在不冲突的情况下，下述的实施例及实施方式中的特征可以相互组合。
实施例一
图1为本发明实施例一提供的一种固态硬盘的存储性能的评估方法。所述固态硬盘的存储性能的评估方法的执行主体可以为图像存储系统，比如，相机、摄像机等图像采集系统的图像存储系统上。
如图1所示，所述方法可以包括以下步骤：
步骤S101：获取待存储的图像；
该步骤中，待存储的图像可以为拍摄装置监控的图像，也可以为其他待存储的图像，比如从其他设备中获取的图像。在本实施例中，待存储的图像为拍摄装置监控的图像。其中，拍摄装置为图像采集系统的一部分。具体的，待存储的图像为拍摄装置实时监控的图像，在不影响图像采集系统的实际功能(拍摄功能)条件下，实时记录图像被存入SSD时的时间参数，为后期SSD性能评估提供数据。
本发明实施例中，固态硬盘均以其简称SSD进行表示，在后面即不再重复进行说明。
参见图2和图3，本实施例的图像存储系统100包括第一处理器110和固态硬盘SSD(图2、图3中的120)。第一处理器110在获取到拍摄装置130实时监控的图像后，在第一处理器110的内存中缓存获取到的图像，待存储的图像即为缓存的图像。其中，第一处理器110可以为中央处理器CPU(central processing unit)。第一处理器110还可以进一步包括硬件芯片。上述硬件芯片可以是专用集成电路(application-specific integrated circuit，ASIC)，可编程逻辑器件(programmable logic device，PLD)或其组合。上述PLD可以是复杂可编程逻辑器件(complex programmable logic device，CPLD)，现场可编程逻辑门阵列(field-programmable gate array，FPGA)， 通用阵列逻辑(generic array logic，GAL)或其任意组合。本实施例的第一处理器110为CPU。
可选的，拍摄装置130搭载在可移动设备上。其中，可移动设备可以为无人飞行器，如无人机；也可以为地面可移动设备，如遥控车辆；还可以为水面移动设备，如无人船；此外，可移动设备还可以为手持设备，用户手持该手持设备，从而带动拍摄装置130移动。
步骤S102：将待存储的图像存入SSD，并记录待存储的图像被存入SSD时的时间参数，以使得后端能够根据时间参数评估SSD的存储性能。
在本实施例中，待存储的图像可经打包处理后再存入SSD，也可不经过打包处理直接存入SSD。例如，在一实施例中，待存储的图像为单帧图像。可选的，将单帧待存储的图像打包成图像包后，再将具有单帧待存储的图像的图像包存入SSD。可选的，可以将待存储的图像逐帧存入SSD。在本实施例中，所记录的时间参数为每帧待存储的图像被存入SSD时的时间参数，后端根据每帧待存储的图像被存入SSD时的时间参数来评估SSD的存储性能，具体的，后端可以根据每帧待存储的图像被存入SSD时的时间参数和每帧待存储的图像的大小，确定每帧待存储的图像的存储带宽(即写带宽)，根据每帧待存储的图像的存储带宽，评估SSD的存储性能。
在另一实施例中，待存储的图像为包括多帧图像的图像包。本实施例中，图像包具有的图像帧数小于预设帧数阈值。其中，预设帧数阈值可根据需要选择，如4帧、5帧等等。此外，多个图像包所包括的图像帧数可以相等，也可以不相等。进一步的，图像包中相邻两帧图像的存储间隙小于预设间隙阈值，本实施例的相邻两帧图像的存储间隙是指相邻两帧图像被存入SSD的时间差。在本实施例中，所记录的时间参数为每个图像包被存入SSD时的时间参数，后端根据每个图像包被存入SSD时的时间参数来评估SSD的存储性能。具体的，后端根据每个图像包被存入SSD时的时间参数和每个图像包的大小，确定每个图像包中多帧图像的平均存储带宽。此时，若图像包中相邻两帧图像的存储间隙较大，会导致所确定的图像包中每帧图像的平均存储带宽的准确度较差，影响SSD存储性能的评估。本实施例的预设间隙阈值可根据需要选择，例如1微秒、2微秒等等。
每次存入SSD的待存储的图像无论是单帧图像，还是具有多帧图像的图像包，每次存入SSD的待存储的图像不能太小，每次存入SSD的待存储的图像也不能太大，不然由于待存储的图像的存储时间的长短的问题，会使得计时器(CPU通过软件方式设定)访问时间和内存访问时间之间的偏差过大，并导致后端确定的每个待存储的图像的存储带宽偏差过大，也不能精确反映SSD的存储性能。本实施例中，待存储的图像的大小与SSD的内存大小以及中央处理器CPU的内存大小相关。具体的，SSD的内存越大，待存储的图像可以越大。CPU的内存越大，待存储的图像可以越大。可选 的，待存储的图像大于等于4M并小于等于100M，例如，4M、5M、10M、20M、30M、40M、50M、60M、70M、80M、90M、100M等。
在一实施例中，时间参数包括待存储的图像被存入SSD的开始时间和结束时间。后端在评估SSD的存储性能时，需要根据待存储的图像被存入SSD的开始时间和结束时间，确定每个待存储的图像被存入SSD的时长(每个待存储的图像被存入SSD的时长＝该待存储的图像被存入SSD的结束时间-该待存储的图像被存入SSD的开始时间)，再根据每个待存储的图像的被存入SSD的时长及每个待存储的图像的大小，确定每个待存储的图像的存储带宽，从而评估SSD的存储性能。
具体的，当待存储的图像为单帧图像时，图像存储系统100记录每帧图像被存入SSD的开始时间和每帧图像被存入SSD的结束时间。后端根据每帧图像被存入SSD的开始时间和结束时间以及每帧图像的大小，确定每帧图像的存储带宽，再根据确定出的每帧图像的存储带宽，评估SSD的存储性能。其中，每帧图像的存储带宽可按照如下公式计算：每帧图像的存储带宽＝该帧图像的大小/(该帧图像被存入SSD的结束时间-该帧图像被存入SSD的开始时间)。当然，每帧图像的存储带宽的计算方式并不局限于上述计算公式。
当待存储的图像为具有多帧图像的图像包时，图像存储系统100记录每个图像包被存入SSD的开始时间和每个图像包被存入SSD的结束时间。后端根据每个图像包被存入SSD的开始时间和结束时间以及每个图像包的大小，确定每个图像包中多帧图像的平均存储带宽，再根据每个图像包中多帧图像的平均存储带宽，评估SSD的存储性能。其中，每个图像包中多帧图像的平均存储带宽可按照如下公式计算：每个图像包中多帧图像的平均存储带宽＝该图像包的大小/(该图像包被存入SSD的结束时间-该图像包被存入SSD的开始时间)。当然，每个图像包中多帧图像的平均存储带宽的计算方式并不限于上述计算公式。
在另一实施例中，时间参数包括待存储的图像被存入SSD的时长，其中，待存储的图像被存入SSD的时长根据待存储的图像被存入SSD的开始时间和结束时间获得。本实施例中，待存储的图像被存入SSD的时长可按照如下公式计算：待存储的图像被存入SSD的时长＝(该待存储的图像被存入SSD的结束时间-待存储的图像被存入SSD的开始时间)。后端在评估SSD的存储性能时，直接根据每个待存储的图像的被存入SSD的时长及每个待存储的图像的大小，确定每个待存储的图像的存储带宽，从而评估SSD的存储性能。
具体的，当待存储的图像为单帧图像时，图像存储系统100记录每帧图像被存入SSD的时长。后端根据每帧图像被存入SSD的时长以及每帧图像的大小，确定每帧图像的存储带宽，再根据确定出的每帧图像的存储带宽，评估SSD的存储性能。其中，每帧图像的存储带宽可按照如下公式计算：每帧图像的存储带宽＝该帧图像的大小 /该帧图像被存入SSD的时长。当然，每帧图像的存储带宽的计算方式并不局限于上述计算公式。
当待存储的图像为具有多帧图像的图像包时，图像存储系统100记录每个图像包被存入SSD的时长。后端根据每个图像包被存入SSD的时长以及每个图像包的大小，确定每个图像包中多帧图像的平均存储带宽，再根据每个图像包中多帧图像的平均存储带宽，评估SSD的存储性能。其中，每个图像包中多帧图像的平均存储带宽可按照如下公式计算：每个图像包中多帧图像的平均存储带宽＝该图像包的大小/该图像包被存入SSD的时长。当然，每个图像包中多帧图像的平均存储带宽的计算方式并不限于上述计算公式。
图像存储系统100存储时间参数的存储方式也可根据需要选择，例如，在其中一实施例中，将待存储的图像存入SSD，并将待存储的图像被存入SSD时的时间参数记录在下一待存储的图像中。可选的，待存储的图像可以缓存在一个连续的存储空间内，该存储空间的末尾设有自定义字段，本实施例将待存储的图像被存入SSD时的时间参数记录在下一待存储的图像的末尾字段中。
在一具体实现方式中，待存储的图像包括file1、file2、file3、…、filen。参见图4，在SSD中存储第一个待存储的图像file1时，图像存储系统100会获取当前时间t1s(即file1被存入SSD时的开始时间)，file1存储完成时，图像存储系统100获取当前时间t1e(即file1被存入SSD时的结束时间)，t1e与t1s的时间差为在SSD中存储file1所消耗的时间(即file1被存入SSD的时长)。由于file1已经写入SSD中，如果从SSD中读出file1，再将file1被存入SSD的时长t1存储在file1中，势必会影响存储效率。对于此，本实施例将file1被存入SSD的时长t1存储到file2的末尾字段中。以此类推，file2被存入SSD的时长t2存储到file3的末尾字段中，filen-1被存入SSD的时长tn-1存储到filen的末尾字段中。这样在图像存储工作时就记录了前n-1个待存储的图像被存入SSD的时长，而第n个待存储的图像被存入SSD的时长可以未被记录。后端根据n-1个待存储的图像被存入SSD的时长以及n-1个待存储的图像的大小，即可确定n-1个待存储的图像的存储带宽。
进一步的，若时间参数记录在待存储的图像中，后端可通过读取SSD中已存储的图像信息，并根据读取的图像信息，获得每个图像被存入SSD的时间参数以及每个图像的大小，再根据每个图像被存入SSD的时间参数以及每个图像的大小，确定每个图像的存储带宽，以评估SSD的存储性能。
在另一实施例中，将待存储的图像存入SSD，并在特定文件中记录待存储的图像被存入SSD时的时间参数。当待存储的图像包括file1、file2、file3、…、filen时，通过特定文件可以记录file1、file2、file3、…、及filen被存入SSD时的时间参数，即可以在特定文件中记录n个待存储的图像被存入SSD时的时间参数，相对于将时间参 数记录在存储的图像中的方案，本方案能够记录第n个待存储的图像被存入SSD时的时间参数。
其中，特定文件可以为记事本，也可以为其他能够记录数据的文件。进一步地，在特定文件中记录待存储的图像被存入SSD时的时间参数的同时，还可以在特定文件中记录待存储的图像的大小，以在访问特定文件时，可以同时获取到待存储的图像被存入时的时间参数以及大小，无需再访问SSD获取已经存储的待存储的图像的大小。
进一步的，若时间参数存储在特定文件中，后端获取时间参数的方式可包括但不限于以下两种：
第一种，图像存储系统100将时间参数发送至后端。
在将待存储的图像存入固态硬盘SSD，并记录待存储的图像被存入SSD时的时间参数之后，还可以发送所记录的时间参数至后端。进一步的，在将待存储的图像存入固态硬盘SSD，并记录待存储的图像被存入SSD时的时间参数之后，可以发送待存储的图像的大小至后端。
可选的，图像存储系统100将记录有每个待存储的图像被存入SSD时的时间参数和每个待存储的图像的大小的特定文件发送至后端。可选的，图像存储系统100从特定文件中读取每个待存储的图像被存入SSD时的时间参数后，将读取的每个待存储的图像被存入SSD时的时间参数发送至后端；并且，图像存储系统100从特定文件中读取每个待存储的图像的大小后，将读取的每个待存储的图像的大小发送至后端。
在一些实施例中，图像存储系统100发送所记录的时间参数至后端的步骤是在接收后端发送的读取请求的步骤之后执行的，图像存储系统100可根据后端的实际需求来选择是否将所记录的时间参数发送至后端，灵活性强。在另一些实施例中，图像存储系统100按照预设频率(如30分钟/次)发送所记录的时间参数至后端，后端可及时分析SSD的存储性能，避免进一步的损失。
第二种，后端读取特定文件，从而从读取的特定文件中获取每个待存储的图像被存入SSD时的时间参数以及每个待存储的图像的大小。
此外，本实施例的SSD存储性能的评估方法还可包括：接收后端发送的SSD的存储性能评估结果，从而使得图像存储系统100侧获得SSD的存储性能评估结果。其中，SSD的存储性能评估结果为由后端根据待存储的图像被存入SSD的时间参数以及待存储的图像的大小生成。具体的，后端首先根据图像被存入SSD的时间参数和图像的大小，确定每一图像被存入SSD的存储带宽；接着，根据每一图像被存入SSD的存储带宽，对SSD的存储性能进行评估。具体而言，当待存储的图像为单帧图像时，后端根据每帧图像被存入SSD的时间参数和每帧图像的大小，确定每帧图像被存入SSD的存储带宽，再根据每帧图像被存入SSD的存储带宽，对SSD的存储性能进行评估。当待存储的图像为具有多帧图像的图像包时，后端根据每个图像包被存入SSD 的时间参数和每个图像包的大小，确定每个图像包被存入SSD的存储带宽，再根据每个图像包被存入SSD的存储带宽，对SSD的存储性能进行评估。
进一步的，后端在根据每一图像被存入SSD的存储带宽，对SSD的存储性能进行评估时，根据多个图像被存入SSD的存储带宽和每一图像被存入SSD的时间顺序，确定SSD的存储带宽的波动信息；再根据SSD的存储带宽的波动信息，对SSD的存储性能进行评估。具体而言，当待存储的图像为单帧图像时，根据多帧图像被存入SSD的存储带宽和每帧图像被存入SSD的时间顺序，确定SSD的存储带宽的波动信息；再根据SSD的存储带宽的波动信息，对SSD的存储性能进行评估。当待存储的图像为具有多帧图像的图像包时，后端根据多个图像包被存入SSD的存储带宽和每一图像包被存入SSD的时间顺序，确定SSD的存储带宽的波动信息；再根据SSD的存储带宽的波动信息，对SSD的存储性能进行评估。
本实施例中，SSD的存储性能评估结果为用于表征每一图像被存入SSD时的存储带宽所形成的指示线。当然，SSD的存储性能评估结果并不限于指示线形式，也可以为离散数据，例如，每个待存储的图像的存储带宽和每个待存储的图像被存入SSD的时间顺序。
图5为一SSD的存储性能评估结果显示图，如图5所示，纵坐标表示存储带宽，横坐标为按照每个待存储的图像被存入SSD的时间顺序排列的编号(编号越小，图像被存入SSD的时间越早)，每个点对应的纵坐标表示这个图像被存入SSD的存储带宽，对应的横坐标表示这个图像的编号。由图5可知，图像标号在约800之前，硬盘整体性能较好，约850MB/s，但由于图像数据量较小，如果用这个性能直接进行硬盘性能评估，就会误判SSD满足图像存储系统100的需求。图像的编号在约800之后，SSD的存储性能突然下降，但基本保持在约500MB/s左右，而这个性能已经不能满足图像存储系统100的性能要求。故本实施例的图像数据量需要足够多，才能准确判断SSD的存储性能。
另外，还需要说明的是，本实施例的后端可以为移动终端，比如手机、平板电脑等，也可以为服务器。
本发明实施例的SSD存储性能的评估方法，在待存储的图像被存入SSD时，记录待存储的图像被存入SSD时的时间参数，便于后端基于时间参数评估SSD的存储性能，时间参数的记录与图像存储同时进行，SSD的存储性能的评估不会影响图像的存储，也不会降低SSD的使用寿命。本发明可以对新硬盘的性能评估、对旧硬盘的寿命评估提供依据，并且能够给设备选择SSD提供依据。
在基于PC测试SSD存储性能时，测试数据量很小，不能全面反映SSD的性能，本发明将拍摄装置130监控的图像作为待存储的图像，这是由于随着拍摄装置130的分辨率越来越高，pixel位宽越来越深，拍摄装置130监控的图像的数据量越来越大， 每帧数据量达到了兆字节级别，数据量足够，便于测试SSD的存储性能。另外，图像采集系统对图像存储系统100要求也越来越高，SSD本身是一个复杂的SOC系统，其性能随环境，温度，使用市场等因素是波动的，不同厂商的SSD固件是不同的，性能也是千差万别，通过本发明的SSD存储性能的评估方法，可以对新硬盘的性能评估、对旧硬盘的寿命评估提供依据，提高了图像存储系统100的可靠性。
一般而言，SSD存储性能下降的原因可包括SSD由于温度过高、由于大量随机写操作等因素，采用本发明的SSD存储性能的评估方法，可以得到任意时刻任意状态下的SSD的存储性能，可评估出SSD在写入图像的过程中存储性能变化，防止测试不全面导致性能不满足的SSD被用于图像采集系统或其他系统中。
实施例二
参见图2和图3，本发明实施例二提供一种图像存储系统，包括第一处理器110和SSD。其中，第一处理器110与SSD(图2、图3中的120)电连接。
第一处理器110可以实现如本发明图1实施例中所示的相应方法。
具体的，第一处理器110用于，获取待存储的图像；并将待存储的图像存入固态硬盘SSD，并记录待存储的图像被存入SSD时的时间参数，以使得后端能够根据时间参数评估SSD的存储性能。
可参见上述实施例一的SSD存储性能的评估方法对第一处理器110的工作原理进一步解释，此处不再赘述。
在本实施例中，第一处理器110可包括一个或多个。具体的，第一处理器110可以是中央处理器(central processing unit，CPU)。第一处理器110还可以进一步包括硬件芯片。上述硬件芯片可以是专用集成电路(application-specific integrated circuit，ASIC)，可编程逻辑器件(programmable logic device，PLD)或其组合。上述PLD可以是复杂可编程逻辑器件(complex programmable logic device，CPLD)，现场可编程逻辑门阵列(field-programmable gate array，FPGA)，通用阵列逻辑(generic array logic，GAL)或其任意组合。
进一步的，待存储的图像可以为拍摄装置监控的图像，也可以为其他待存储的图像，比如从其他设备中获取的图像。在本实施例中，图像存储系统100为图像采集系统的一部分，该图像采集系统还包括拍摄装置130，待存储的图像为拍摄装置130监控的图像。其中，拍摄装置130为图像采集系统的一部分。具体的，待存储的图像为拍摄装置130实时监控的图像，在不影响图像采集系统的实际功能(拍摄功能)条件下，实时记录图像被存入SSD时的时间参数，为后期SSD性能评估提供数据。
可选的，拍摄装置130搭载在可移动设备上。其中，可移动设备可以为无人飞行器，如无人机；也可以为地面可移动设备，如遥控车辆；还可以为水面移动设备， 如无人船；此外，可移动设备还可以为手持设备，用户手持该手持设备，从而带动拍摄装置130移动。
本发明实施例的图像存储系统100，在待存储的图像被存入SSD时，记录待存储的图像被存入SSD时的时间参数，便于后端基于时间参数评估SSD的存储性能，时间参数的记录与图像存储同时进行，SSD的存储性能的评估不会影响图像的存储，也不会降低SSD的使用寿命。本发明可以对新硬盘的性能评估、对旧硬盘的寿命评估提供依据，并且能够给设备选择SSD提供依据。
实施例三
图6为本发明实施例三提供一种SSD存储性能的评估方法的方法流程图。所述SSD存储性能的评估方法的执行主体可以为后端，后端可以为移动终端，比如手机、平板电脑等，也可以为服务器。
如图6所示，本实施例的SSD存储性能的评估方法可以包括以下步骤：
步骤S601：获取图像被存入SSD时的时间参数及图像的大小；
后端获取图像被存入固态硬盘SSD时的时间参数及图像的大小的方式可包括以下方式：
第一种，参见图7，步骤601也可以为：接收图像存储系统发送的图像被存入SSD时的时间参数及图像的大小。
在一例子中，后端在接收图像存储系统发送的图像被存入SSD时的时间参数及图像的大小之前，会发送读取请求至图像存储系统。本实施例中，图像存储系统在接收到读取请求后，发送图像被存入SSD时的时间参数及图像的大小至后端。例如，后端根据SSD中的图像，判断图像存在损坏(如丢帧)，则发送读取请求至图像存储系统，以分析SSD的存储性能，获得图像损坏是否因SSD存储性能下降导致。
在另一例子中，图像存储系统按照预设频率(如30分钟/次)发送该图像存储系统所记录的时间参数和图像大小至后端，本实施例中，后端被动的接收图像存储系统发送的图像被存入SSD时的时间参数及图像的大小，通过后端跟踪SSD的存储性能，避免SSD存储性能下降后图像采集系统继续使用SSD而造成的损失。
相关技术一般通过PC上的软件写入测试数据至SSD来评估SSD存储性能，但这种方式无法应用于处于工作状态的相机、摄像机等嵌入式系统，从而无法及时跟踪相机、摄像机等嵌入式系统中SSD存储性能。本实施例的后端根据图像存储系统所记录的时间参数和图像大小来跟踪SSD存储性能，其可以应用于无人机，特别是处于航拍过程中的无人机。在实际应用中，若SSD存储性能下降，可能导致航拍的图像无法存入SSD或者航拍图像在存入SSD时损坏。而在SSD存储性能下降后，若无人机继续航拍，无人机可能会因为图像无法保存或保存的图像不可用而做无用功，导致资 源浪费。本实施例通过后端及时跟踪SSD的存储性能，在SSD存储性能下降后，无人机能够及时停止航拍，有效防止无人机做没必要的资源浪费，并能够及时查找SSD存储性能下降的原因，以根据SSD存储性能下降的原因进行不同的策略操作。
第二种，参见图8，步骤601还可以为：读取SSD所存储的图像信息；分析所读取的图像信息，获取每个图像被存入SSD时的时间参数及每个图像的大小。
在一例子中，后端读取记录有图像被存入SSD时的时间参数及图像的大小。本实施例中，图像存储系统将图像被存入SSD时的时间参数及图像的大小对应记录在特定文件中。其中，特定文件可以为记事本，也可以为其他能够记录数据的文件。在另一例子中，后端直接读取SSD存储的图像，并对读取到的图像进行分析，获取每个图像被存入SSD时的时间参数及每个图像的大小。
在一实施例中，图像为单帧图像，例如，可以为具有单帧图像的图像包，也可为一帧图像。在本实施例中，时间参数为每帧图像被存入SSD时的时间参数。
在另一实施例中，图像为包括多帧图像的图像包。本实施例中，图像包具有的图像帧数小于预设帧数阈值。其中，预设帧数阈值可根据需要选择，如4帧、5帧等等。此外，多个图像包所包括的图像帧数可以相等，也可以不相等。进一步的，图像包中相邻两帧图像的存储间隙小于预设间隙阈值，本实施例的相邻两帧图像的存储间隙是指相邻两帧图像被存入SSD的时间差。在本实施例中，时间参数为每个图像包被存入SSD时的时间参数。此时，若图像包中相邻两帧图像的存储间隙较大，会导致所确定的图像包中每帧图像的平均存储带宽的准确度较差，影响SSD存储性能的评估。本实施例的预设间隙阈值可根据需要选择，例如1微秒、2微秒等等。
在一实施例中，时间参数包括图像被存入SSD的开始时间和结束时间。具体的，当待存储的图像为单帧图像时，时间参数包括每帧图像被存入SSD的开始时间和每帧图像被存入SSD的结束时间。当待存储的图像为具有多帧图像的图像包时，时间参数包括每个图像包被存入SSD的开始时间和每个图像包被存入SSD的结束时间。
在另一实施例中，时间参数包括图像被存入SSD的时长，其中，图像被存入SSD的时长根据图像被存入SSD的开始时间和结束时间获得。本实施例中，图像被存入SSD的时长可按照如下公式计算：图像被存入SSD的时长＝(该图像被存入SSD的结束时间-图像被存入SSD的开始时间)。具体的，当图像为单帧图像时，时间参数包括每帧图像被存入SSD的时长。当待存储的图像为具有多帧图像的图像包时，图像存储系统记录每个图像包被存入SSD的时长。
时间参数的存储方式也可根据需要选择，例如，在其中一实施例中，图像被存入SSD时的时间参数被存储在下一被存入SSD的图像中。可选的，图像被存入SSD时的时间参数记录在下一被存入SSD的图像的末尾字段中。
在一具体实现方式中，被存入SSD的图像包括file1、file2、file3、…、filen。 参见图4，file1被存入SSD的开始时间为t1s，结束时间为t1e；file2被存入SSD的开始时间为t2s，结束时间为t2e；file3被存入SSD的开始时间为t3s，结束时间为t3e；以此类推，filen被存入SSD的开始时间为tns，结束时间为tne。在一例子中，时间参数为图像被存入SSD的开始时间和结束时间，file1被存入SSD的开始时间和结束时间记录在file2的末尾字段，file2被存入SSD的开始时间和结束时间记录在file3的末尾字段，以此类推，filen-1被存入SSD的开始时间和结束时间记录在filen的末尾字段。在另一例子中，时间参数为图像被存入SSD的时长，file1被存入SSD的时长记录在file2的末尾字段，file2被存入SSD的时长记录在file3的末尾字段，以此类推，filen-1被存入SSD的时长记录在filen的末尾字段。
进一步的，若时间参数记录在图像中，后端可通过上述第二种获取图像被存入固态硬盘SSD时的时间参数及图像的大小方式来获取图像被存入SSD的时间参数和图像大小。
在另一实施例中，图像被存入SSD时的时间参数及图像的大小对应存储在特定文件中。当图像包括file1、file2、file3、…、filen时，特定文件则记录有file1、file2、file3、…、及filen对应被存入SSD时的时间参数和file1、file2、file3、…、及filen对应的大小。
若图像被存入SSD时的时间参数及图像的大小对应存储在特定文件中，则可通过上述第一种或第二种获取图像被存入固态硬盘SSD时的时间参数及图像的大小方式来获取图像被存入SSD的时间参数和图像大小。
步骤S602：根据图像被存入SSD时的时间参数及图像的大小，对SSD的存储性能进行评估。
步骤S602的执行过程可包括：根据图像被存入SSD的时间参数和图像的大小，确定每一图像被存入SSD的存储带宽(即写带宽)；根据每一图像被存入SSD的存储带宽，对SSD的存储性能进行评估。
当时间参数包括图像被存入SSD的开始时间和结束时间时，后端在评估SSD的存储性能时，需要根据图像被存入SSD的开始时间和结束时间，确定每个图像被存入SSD的时长(每个图像被存入SSD的时长＝该图像被存入SSD的结束时间-该图像被存入SSD的开始时间)，再根据每个图像的被存入SSD的时长及每个图像的大小，确定每个图像的存储带宽，从而评估SSD的存储性能。
可选的，当图像为单帧图像时，图像存储系统记录每帧图像被存入SSD的开始时间和每帧图像被存入SSD的结束时间。后端根据每帧图像被存入SSD的开始时间和结束时间以及每帧图像的大小，确定每帧图像的存储带宽，再根据确定出的每帧图像的存储带宽，评估SSD的存储性能。其中，每帧图像的存储带宽可按照如下公式计算：每帧图像的存储带宽＝该帧图像的大小/(该帧图像被存入SSD的结束时间-该帧 图像被存入SSD的开始时间)。当然，每帧图像的存储带宽的计算方式并不局限于上述计算公式。
可选的，当图像为具有多帧图像的图像包时，图像存储系统记录每个图像包被存入SSD的开始时间和每个图像包被存入SSD的结束时间。后端根据每个图像包被存入SSD的开始时间和结束时间以及每个图像包的大小，确定每个图像包中多帧图像的平均存储带宽，再根据每个图像包中多帧图像的平均存储带宽，评估SSD的存储性能。其中，每个图像包中多帧图像的平均存储带宽可按照如下公式计算：每个图像包中多帧图像的平均存储带宽＝该图像包的大小/(该图像包被存入SSD的结束时间-该图像包被存入SSD的开始时间)。当然，每个图像包中多帧图像的平均存储带宽的计算方式并不限于上述计算公式。
在另一实施例中，时间参数包括图像被存入SSD的时长，其中，图像被存入SSD的时长根据图像被存入SSD的开始时间和结束时间获得。本实施例中，图像被存入SSD的时长可按照如下公式计算：图像被存入SSD的时长＝(该图像被存入SSD的结束时间-图像被存入SSD的开始时间)。后端在评估SSD的存储性能时，直接根据每个图像的被存入SSD的时长及每个图像的大小，确定每个图像的存储带宽，从而评估SSD的存储性能。
可选的，当图像为单帧图像时，图像存储系统记录每帧图像被存入SSD的时长。后端根据每帧图像被存入SSD的时长以及每帧图像的大小，确定每帧图像的存储带宽，再根据确定出的每帧图像的存储带宽，评估SSD的存储性能。其中，每帧图像的存储带宽可按照如下公式计算：每帧图像的存储带宽＝该帧图像的大小/该帧图像被存入SSD的时长。当然，每帧图像的存储带宽的计算方式并不局限于上述计算公式。
可选的，当图像为具有多帧图像的图像包时，图像存储系统记录每个图像包被存入SSD的时长。后端根据每个图像包被存入SSD的时长以及每个图像包的大小，确定每个图像包中多帧图像的平均存储带宽，再根据每个图像包中多帧图像的平均存储带宽，评估SSD的存储性能。其中，每个图像包中多帧图像的平均存储带宽可按照如下公式计算：每个图像包中多帧图像的平均存储带宽＝该图像包的大小/该图像包被存入SSD的时长。当然，每个图像包中多帧图像的平均存储带宽的计算方式并不限于上述计算公式。
本实施例中，在根据每一图像被存入SSD的存储带宽，对SSD的存储性能进行评估时，首先根据多个图像被存入SSD的存储带宽和每一图像被存入SSD的时间顺序，确定SSD的存储带宽的波动信息；再根据SSD的存储带宽的波动信息，对SSD的存储性能进行评估。图5为一SSD的存储性能评估结果显示图，如图5所示，纵坐标表示存储带宽，横坐标为按照每个图像被存入SSD的时间顺序排列的编号(编号越小，图像被存入SSD的时间越早)，每个点对应的纵坐标表示这个图像被存入SSD的 存储带宽，对应的横坐标表示这个图像的编号。由图5可知，图像标号在约800之前，硬盘整体性能较好，约850MB/s，但由于图像数据量较小，如果用这个性能进行硬盘评估，就会误判SSD满足图像存储系统的需求。图像的编号在约800之后，SSD的存储性能突然下降，但基本保持在约500MB/s左右，而这个性能已经不能满足图像存储系统的性能要求。故本实施例的图像数据量需要足够多，才能准确判断SSD的存储性能。
在一些实施例中，后端在根据图像被存入SSD时的时间参数及图像的大小，对SSD的存储性能进行评估之后，还发送SSD的存储性能评估结果至图像存储系统，使得图像存储系统及时获知其当前使用的SSD的存储性能。
在一些实施例中，后端在根据图像被存入SSD时的时间参数及图像的大小，对SSD的存储性能进行评估之后，还可以显示SSD的存储性能评估结果，从而直观地呈现SSD的存储性能评估结果。在本实施例中，可以以指示线形式显示SSD的存储性能评估结果；当然，SSD的存储性能评估结果的显示方式并不限于指示线形式，也可以为离散数据，例如，如图5所示，可以显示每个待存储的图像的存储带宽和每个待存储的图像被存入SSD的时间顺序。
在一实施例中，需要获取多个SSD的存储性能，以便于筛选满足需求的SSD。本实施例中，图像为多个，SSD为多个，多个SSD中的每一个存储有至少一个图像。可选的，图像存储系统将待存储的图像同时存入多个SSD，并记录各待存储的图像被存入各个SSD的时间参数。可选的，图像存储系统将每一待存储的图像存储在其中一个SSD中，并记录各待存储的图像被存入相应SSD的时间参数。
在本实施例中，后端获取每个SSD中图像被存入时的时间参数及大小；并根据每个SSD中图像被存入时的时间参数及大小，对每个SSD的存储性能进行评估。其中，后端获取每个SSD中图像被存入时的时间参数及大小以及后端根据每个SSD中图像被存入时的时间参数及大小，对每个SSD的存储性能进行评估的实现过程可参见上述实施例，此处不再赘述。
进一步的，后端在根据每个SSD中图像被存储时的时间参数及大小，对每个SSD的存储性能进行评估之后，根据每个SSD的存储性能的评估结果和预设策略，筛选多个SSD中的一个或多个作为存储设备。可选的，预设策略可以包括：SSD的存储带宽的波动小于或者等于预设波动阈值。可选的，预设策略可以包括：SSD的存储带宽大于或者等于预设带宽阈值。可选的，预设策略可以包括：将SSD的存储带宽最大的SSD作为存储设备。可选的，预设策略可以包括：将SSD的存储带宽较大的SSD中选择存储带宽的波动最小的SSD作为存储设备。
本发明实施例的SSD存储性能的评估方法，在图像被存入SSD时，记录图像被存入SSD时的时间参数，便于后端基于时间参数评估SSD的存储性能，时间参数 的记录与图像存储同时进行，SSD的存储性能的评估不会影响图像的存储，也不会降低SSD的使用寿命。本发明可以对新硬盘的性能评估、对旧硬盘的寿命评估提供依据，并且能够给设备选择SSD提供依据。
在基于PC测试SSD存储性能时，测试数据量很小，不能全面反映SSD的性能，本发明将拍摄装置监控的图像作为待存储的图像，这是由于随着拍摄装置的分辨率越来越高，pixel位宽越来越深，拍摄装置监控的图像的数据量越来越大，每帧数据量达到了兆字节级别，数据量足够，便于测试SSD的存储性能。另外，图像采集系统对图像存储系统要求也越来越高，SSD本身是一个复杂的SOC系统，其性能随环境，温度，使用市场等因素是波动的，不同厂商的SSD固件是不同的，性能也是千差万别，通过本发明的SSD存储性能的评估方法，可以对新硬盘的性能评估、对旧硬盘的寿命评估提供依据，提高了图像存储系统的可靠性。
一般而言，SSD存储性能下降的原因可包括SSD由于温度过高、由于大量随机写操作等因素，采用本发明的SSD存储性能的评估方法，可以得到任意时刻任意状态下的SSD的存储性能，可评估出SSD在写入图像的过程中存储性能变化，防止测试不全面导致性能不满足的SSD被用于图像采集系统或其他系统中。
实施例四
参见图9，本发明实施例四提供一种SSD存储性能评估装置，包括第二处理器210和存储装置220。
其中，存储装置220，用于存储程序指令。第二处理器210调用程序指令，当程序指令被执行时，用于获取图像被存入固态硬盘SSD时的时间参数及图像的大小；根据图像被存入SSD时的时间参数及图像的大小，对SSD的存储性能进行评估。
第二处理器210可以实现如本发明图6、图7和图8实施例中所示的相应方法。
可参见上述实施例三的SSD存储性能的评估方法对第二处理器210的工作原理进一步解释，此处不再赘述。
在本实施例中，第二处理器210可包括一个或多个。具体的，第二处理器210可以是中央处理器(central processing unit，CPU)。第二处理器210还可以进一步包括硬件芯片。上述硬件芯片可以是专用集成电路(application-specific integrated circuit，ASIC)，可编程逻辑器件(programmable logic device，PLD)或其组合。上述PLD可以是复杂可编程逻辑器件(complex programmable logic device，CPLD)，现场可编程逻辑门阵列(field-programmable gate array，FPGA)，通用阵列逻辑(generic array logic，GAL)或其任意组合。
存储装置220可以包括易失性存储器(volatile memory)，例如随机存取存储器(random-access memory，RAM)；存储装置220也可以包括非易失性存储器 (non-volatile memory)，例如快闪存储器(flash memory)，硬盘(hard disk drive，HDD)或固态硬盘(solid-state drive，SSD)；存储装置220120还可以包括上述种类的存储器的组合。
本发明实施例的SSD存储性能的评估装置，在图像被存入SSD时，记录图像被存入SSD时的时间参数，便于后端基于时间参数评估SSD的存储性能，时间参数的记录与图像存储同时进行，SSD的存储性能的评估不会影响图像的存储，也不会降低SSD的使用寿命。本发明可以对新硬盘的性能评估、对旧硬盘的寿命评估提供依据，并且能够给设备选择SSD提供依据。
实施例五
结合图10和图11，本发明实施例五提供一种SSD存储性能的评估系统，包括图像存储系统100和后端200，其中，图像存储系统100与后端200通信连接。可选的，图像存储系统100与后端200基于无线通信方式通信连接，或基于有线通信方式通信连接。
本实施例中，图像存储系统100包括第一处理器110和与第一处理器110电连接的SSD，后端200包括第二处理器210和与第二处理器210电连接的存储装置220，第一处理器110与第二处理器210通信连接。
参见图11，SSD存储性能的评估系统的工作流程可包括以下步骤：
步骤S1101：图像存储系统100获取待存储的图像；
步骤S1102：图像存储系统100将待存储的图像存入SSD，并记录待存储的图像被存入SSD时的时间参数；
步骤S1103：后端200获取图像被存入SSD时的时间参数及图像的大小；
步骤S1104：后端200根据图像被存入SSD时的时间参数及图像的大小，对SSD的存储性能进行评估。
其中，步骤S1101和步骤S1102的执行主体为第一处理器110，步骤S1103和步骤S1104的执行主体为第二处理器210。步骤S1101和步骤S1102的执行过程可参见实施例一和实施例二，步骤S1103和步骤S1104的执行过程可参见实施例三和实施例四，此处不再赘述。
本实施例的后端200可以为移动终端，比如手机、平板电脑等，也可以为服务器。
实施例六
本发明实施例六提供一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现上述实施例一或实施例三的SSD存储性能的评估方法的步骤。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，所述的存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory，ROM)或随机存储记忆体(Random Access Memory，RAM)等。
以上所揭露的仅为本发明部分实施例而已，当然不能以此来限定本发明之权利范围，因此依本发明权利要求所作的等同变化，仍属本发明所涵盖的范围。

Claims (73)

  1. 一种固定硬盘的存储性能的评估方法，其特征在于，所述方法包括：
    获取待存储的图像；
    将所述待存储的图像存入所述固态硬盘，并记录所述待存储的图像被存入所述固态硬盘时的时间参数，以使得后端能够根据所述时间参数评估所述固态硬盘的存储性能。
  2. 根据权利要求1所述的方法，其特征在于，所述待存储的图像为拍摄装置监控的图像。
  3. 根据权利要求2所述的方法，其特征在于，所述待存储的图像为拍摄装置实时监控的图像。
  4. 根据权利要求2所述的方法，其特征在于，所述拍摄装置搭载在可移动设备上。
  5. 根据权利要求1所述的方法，其特征在于，所述将所述待存储的图像存入固态硬盘，并记录所述待存储的图像被存入所述固态硬盘时的时间参数，包括：
    将所述待存储的图像存入所述固态硬盘，并将所述待存储的图像被存入所述固态硬盘时的时间参数记录在下一待存储的图像中；或者，
    将所述待存储的图像存入所述固态硬盘，并在特定文件中记录所述待存储的图像被存入所述固态硬盘时的时间参数。
  6. 根据权利要求5所述的方法，其特征在于，所述将所述待存储的图像存入所述固态硬盘，并在特定文件中记录所述待存储的图像被存入所述固态硬盘时的时间参数，进一步包括：
    在所述特定文件中记录所述待存储的图像的大小。
  7. 根据权利要求1所述的方法，其特征在于，所述时间参数包括：
    所述待存储的图像被存入所述固态硬盘的开始时间和结束时间；或者，
    所述待存储的图像被存入所述固态硬盘的时长，其中，所述时长为根据所述待存储的图像被存入所述固态硬盘的开始时间和结束时间获得。
  8. 根据权利要求1所述的方法，其特征在于，所述待存储的图像的大小与所述固态硬盘的内存大小以及中央处理器的内存大小相关。
  9. 根据权利要求8所述的方法，其特征在于，所述待存储的图像大于等于4M并小于等于100M。
  10. 根据权利要求1至9任一项所述的方法，其特征在于，所述待存储的图像为单帧图像。
  11. 根据权利要求1至9任一项所述的方法，其特征在于，所述待存储的图像为包括多帧图像的图像包。
  12. 根据权利要求11所述的方法，其特征在于，所述图像包具有的图像帧数小于预设帧数阈值。
  13. 根据权利要求11所述的方法，其特征在于，所述图像包中相邻两帧图像的存 储间隙小于预设间隙阈值。
  14. 根据权利要求1至9任一项所述的方法，其特征在于，所述将所述待存储的图像存入所述固态硬盘，并记录所述待存储的图像被存入所述固态硬盘时的时间参数之后，还包括：
    发送所记录的所述时间参数至所述后端。
  15. 根据权利要求14所述的方法，其特征在于，所述将所述待存储的图像存入所述固态硬盘，并记录所述待存储的图像被存入所述固态硬盘时的时间参数之后，进一步包括：
    发送所述待存储的图像的大小至所述后端。
  16. 根据权利要求14所述的方法，其特征在于，所述发送所记录的时间参数至所述后端之前，还包括：
    接收所述后端发送的读取请求。
  17. 根据权利要求14所述的方法，其特征在于，所述方法还包括：
    接收所述后端发送的所述固态硬盘的存储性能评估结果，所述固态硬盘的存储性能评估结果为由所述后端根据所述待存储的图像被存入所述固态硬盘的时间参数以及所述待存储的图像的大小生成。
  18. 根据权利要求17所述的方法，所述固态硬盘的存储性能评估结果为用于表征每一图像被存入所述固态硬盘时的存储带宽所形成的指示线。
  19. 根据权利要求1所述的方法，其特征在于，所述后端为移动终端或服务器。
  20. 一种图像存储系统，其特征在于，包括：
    固态硬盘；以及
    处理器，所述处理器与所述固态硬盘电连接；其中，所述处理器用于：
    获取待存储的图像；
    将所述待存储的图像存入所述固态硬盘，并记录所述待存储的图像被存入所述固态硬盘时的时间参数，以使得后端能够根据所述时间参数评估所述固态硬盘的存储性能。
  21. 根据权利要求20所述的图像存储系统，其特征在于，所述待存储的图像为拍摄装置监控的图像。
  22. 根据权利要求21所述的图像存储系统，其特征在于，所述待存储的图像为所述拍摄装置实时监控的图像。
  23. 根据权利要求21所述的图像存储系统，其特征在于，所述拍摄装置搭载在可移动设备上。
  24. 根据权利要求23所述的图像存储系统，其特征在于，所述可移动设备为无人机。
  25. 根据权利要求20所述的图像存储系统，其特征在于，所述处理器用于：
    将所述待存储的图像存入所述固态硬盘，并将所述待存储的图像被存入所述固态 硬盘时的时间参数记录在下一待存储的图像中；或者，
    将所述待存储的图像存入所述固态硬盘，并在特定文件中记录所述待存储的图像被存入所述固态硬盘时的时间参数。
  26. 根据权利要求25所述的图像存储系统，其特征在于，所述处理器用于：
    在所述特定文件中记录所述待存储的图像的大小。
  27. 根据权利要求20所述的图像存储系统，其特征在于，所述时间参数包括：
    所述待存储的图像被存入所述固态硬盘的开始时间和结束时间；或者，
    所述待存储的图像被存入所述固态硬盘的时长，其中，所述时长为根据所述待存储的图像被存入所述固态硬盘的开始时间和结束时间获得。
  28. 根据权利要求20所述的图像存储系统，其特征在于，所述待存储的图像的大小与所述固态硬盘的内存大小以及中央处理器CPU的内存大小相关。
  29. 根据权利要求28所述的图像存储系统，其特征在于，所述待存储的图像大于等于4M并小于等于100M。
  30. 根据权利要求20至29任一项所述的图像存储系统，其特征在于，所述待存储的图像为单帧图像。
  31. 根据权利要求20至29任一项所述的图像存储系统，其特征在于，所述待存储的图像为包括多帧图像的图像包。
  32. 根据权利要求31所述的图像存储系统，其特征在于，所述图像包具有的图像帧数小于预设帧数阈值。
  33. 根据权利要求31所述的图像存储系统，其特征在于，所述图像包中相邻两帧图像的存储间隙小于预设间隙阈值。
  34. 根据权利要求20至29任一项所述的图像存储系统，其特征在于，所述处理器将所述待存储的图像存入所述固态硬盘，并记录所述待存储的图像被存入所述固态硬盘时的时间参数之后，还用于：
    发送所记录的所述时间参数至所述后端。
  35. 根据权利要求34所述的图像存储系统，其特征在于，所述处理器将所述待存储的图像存入所述固态硬盘，并记录所述待存储的图像被存入所述固态硬盘时的时间参数之后，进一步用于：
    发送所述待存储的图像的大小至所述后端。
  36. 根据权利要求34所述的图像存储系统，其特征在于，所述处理器发送所记录的时间参数至所述后端之前，还用于：
    接收所述后端发送的读取请求。
  37. 根据权利要求34所述的图像存储系统，其特征在于，所述处理器还用于：
    接收所述后端发送的所述固态硬盘的存储性能评估结果，所述固态硬盘的存储性能评估结果为由所述后端根据所述待存储的图像被存入所述固态硬盘的时间参数以及所述待存储的图像的大小生成。
  38. 根据权利要求37所述的图像存储系统，所述固态硬盘的存储性能评估结果为用于表征每一图像被存入所述固态硬盘时的存储带宽所形成的指示线。
  39. 根据权利要求20所述的图像存储系统，其特征在于，所述后端为移动终端或服务器。
  40. 一种固态硬盘的存储性能的评估方法，其特征在于，所述方法包括：
    获取图像被存入所述固态硬盘时的时间参数及所述图像的大小；
    根据所述图像被存入所述固态硬盘时的时间参数及所述图像的大小，对所述固态硬盘的存储性能进行评估。
  41. 根据权利要求40所述的方法，其特征在于，所述获取图像被存入所述固态硬盘时的时间参数及所述图像的大小，包括：
    接收图像存储系统发送的所述图像被存入所述固态硬盘时的时间参数及所述图像的大小。
  42. 根据权利要求41所述的方法，其特征在于，所述接收图像存储系统发送的所述图像被存入所述固态硬盘时的时间参数及所述图像的大小之前，还包括：
    发送读取请求至图像存储系统。
  43. 根据权利要求40所述的方法，其特征在于，所述获取图像被存入所述固态硬盘时的时间参数及所述图像的大小，包括：
    读取所述固态硬盘所存储的图像信息；
    分析所读取的所述图像信息，获取每个图像被存入所述固态硬盘时的时间参数及每个图像的大小。
  44. 根据权利要求40所述的方法，其特征在于，所述时间参数包括：
    所述图像被存入所述固态硬盘的开始时间和结束时间；或者，
    所述图像被存入所述固态硬盘的时长，其中，所述时长为根据所述图像被存入所述固态硬盘的开始时间和结束时间获得。
  45. 根据权利要求40所述的方法，其特征在于，所述图像被存入所述固态硬盘时的时间参数被存储在下一被存入所述固态硬盘的图像中；或者，
    所述图像被存入所述固态硬盘时的时间参数及所述图像的大小对应存储在特定文件中。
  46. 根据权利要求40所述的方法，其特征在于，所述根据所述图像被存入所述固态硬盘时的时间参数及所述图像的大小，对所述固态硬盘的存储性能进行评估，包括：
    根据所述图像被存入固态硬盘的时间参数和所述图像的大小，确定每一所述图像被存入所述固态硬盘的存储带宽；
    根据每一图像被存入所述固态硬盘的存储带宽，对所述固态硬盘的存储性能进行评估。
  47. 根据权利要求46所述的方法，其特征在于，所述根据每帧图像被存入所述固态硬盘的存储带宽，对所述固态硬盘的存储性能进行评估，包括：
    根据多个所述图像被存入所述固态硬盘的存储带宽和每一所述图像被存入所述固态硬盘的时间顺序，确定所述固态硬盘的存储带宽的波动信息；
    根据所述固态硬盘的存储带宽的波动信息，对所述固态硬盘的存储性能进行评估。
  48. 根据权利要求40至47任一项所述的方法，其特征在于，所述图像为单帧图像。
  49. 根据权利要求40至47任一项所述的方法，其特征在于，所述图像为包括多帧图像的图像包。
  50. 根据权利要求49所述的方法，其特征在于，所述图像包具有的图像帧数小于预设帧数阈值。
  51. 根据权利要求49所述的方法，其特征在于，所述图像包中相邻两帧图像的存储间隙小于预设间隙阈值。
  52. 根据权利要求40所述的方法，其特征在于，所述根据所述图像被存入所述固态硬盘时的时间参数及所述图像的大小，对所述固态硬盘的存储性能进行评估之后，还包括：
    发送所述固态硬盘的存储性能评估结果至图像存储系统。
  53. 根据权利要求40所述的方法，其特征在于，根据所述图像被存入所述固态硬盘时的时间参数及所述图像的大小，对所述固态硬盘的存储性能进行评估之后，还包括：
    显示所述固态硬盘的存储性能评估结果。
  54. 根据权利要求53所述的方法，其特征在于，所述显示所述固态硬盘的存储性能评估结果，包括：
    以指示线形式显示所述固态硬盘的存储性能评估结果。
  55. 根据权利要求40所述的方法，其特征在于，所述图像为多个，所述固态硬盘为多个，多个所述固态硬盘中的每一个存储有至少一个所述图像，所述获取图像被存入固态硬盘时的时间参数及所述图像的大小，包括：
    获取每个所述固态硬盘中所述图像被存入时的时间参数及大小；
    所述根据所述图像被存入所述固态硬盘时的时间参数及所述图像的大小，对所述固态硬盘的存储性能进行评估，包括：
    根据每个所述固态硬盘中所述图像被存入时的时间参数及大小，对每个所述固态硬盘的存储性能进行评估。
  56. 根据权利要求55所述的方法，其特征在于，所述根据每个所述固态硬盘中所述图像被存储时的时间参数及大小，对每个所述固态硬盘的存储性能进行评估之后，还包括：
    根据每个所述固态硬盘的存储性能的评估结果和预设策略，筛选多个所述固态硬盘中的一个或多个作为存储设备。
  57. 一种固态硬盘的存储性能的评估装置，其特征在于，包括：
    存储装置和处理器；
    所述存储装置，用于存储程序指令；
    所述处理器，调用所述程序指令，当所述程序指令被执行时，用于：
    获取图像被存入所述固态硬盘时的时间参数及所述图像的大小；
    根据所述图像被存入所述固态硬盘时的时间参数及所述图像的大小，对所述固态硬盘的存储性能进行评估。
  58. 根据权利要求57所述的装置，其特征在于，所述获取图像被存入所述固态硬盘时的时间参数及所述图像的大小，包括：
    接收图像存储系统发送的所述图像被存入所述固态硬盘时的时间参数及所述图像的大小。
  59. 根据权利要求58所述的装置，其特征在于，所述接收图像存储系统发送的所述图像被存入所述固态硬盘时的时间参数及所述图像的大小之前，还包括：
    发送读取请求至图像存储系统。
  60. 根据权利要求57所述的装置，其特征在于，所述获取图像被存入所述固态硬盘时的时间参数及所述图像的大小，包括：
    读取所述固态硬盘所存储的图像信息；
    分析所读取的所述图像信息，获取每个图像被存入所述固态硬盘时的时间参数及每个图像的大小。
  61. 根据权利要求57所述的装置，其特征在于，所述时间参数包括：
    所述图像被存入所述固态硬盘的开始时间和结束时间；或者，
    所述图像被存入所述固态硬盘的时长，其中，所述时长为根据所述图像被存入所述固态硬盘的开始时间和结束时间获得。
  62. 根据权利要求57所述的装置，其特征在于，所述图像被存入所述固态硬盘时的时间参数被存储在下一被存入所述固态硬盘的图像中；或者，
    所述图像被存入所述固态硬盘时的时间参数及所述图像的大小对应存储在特定文件中。
  63. 根据权利要求57所述的装置，其特征在于，所述根据所述图像被存入所述固态硬盘时的时间参数及所述图像的大小，对所述固态硬盘的存储性能进行评估，包括：
    根据所述图像被存入固态硬盘的时间参数和所述图像的大小，确定每一所述图像被存入所述固态硬盘的存储带宽；
    根据每一所述图像被存入所述固态硬盘的存储带宽，对所述固态硬盘的存储性能进行评估。
  64. 根据权利要求63所述的装置，其特征在于，所述根据每帧图像被存入所述固态硬盘的存储带宽，对所述固态硬盘的存储性能进行评估，包括：
    根据多个所述图像被存入所述固态硬盘的存储带宽和每一所述图像被存入所述固态硬盘的时间顺序，确定所述固态硬盘的存储带宽的波动信息；
    根据所述固态硬盘的存储带宽的波动信息，对所述固态硬盘的存储性能进行评估。
  65. 根据权利要求57至64任一项所述的装置，其特征在于，所述图像为单帧图像。
  66. 根据权利要求57至64任一项所述的装置，其特征在于，所述图像为包括多帧图像的图像包。
  67. 根据权利要求66所述的装置，其特征在于，所述图像包具有的图像帧数小于预设帧数阈值。
  68. 根据权利要求66所述的装置，其特征在于，所述图像包中相邻两帧图像的存储间隙小于预设间隙阈值。
  69. 根据权利要求57所述的装置，其特征在于，所述根据所述图像被存入所述固态硬盘时的时间参数及所述图像的大小，对所述固态硬盘的存储性能进行评估之后，还包括：
    发送所述固态硬盘的存储性能评估结果至图像存储系统。
  70. 根据权利要求57所述的装置，其特征在于，根据所述图像被存入所述固态硬盘时的时间参数及所述图像的大小，对所述固态硬盘的存储性能进行评估之后，还包括：
    显示所述固态硬盘的存储性能评估结果。
  71. 根据权利要求70所述的装置，其特征在于，所述显示所述固态硬盘的存储性能评估结果，包括：
    以指示线形式显示所述固态硬盘的存储性能评估结果。
  72. 根据权利要求57所述的装置，其特征在于，所述图像为多个，所述固态硬盘为多个，多个所述固态硬盘中的每一个存储有至少一个所述图像，所述获取图像被存入所述固态硬盘时的时间参数及所述图像的大小，包括：
    获取每个所述固态硬盘中所述图像被存入时的时间参数及大小；
    所述根据所述图像被存入所述固态硬盘时的时间参数及所述图像的大小，对所述固态硬盘的存储性能进行评估，包括：
    根据每个所述固态硬盘中所述图像被存入时的时间参数及大小，对每个所述固态硬盘的存储性能进行评估。
  73. 根据权利要求72所述的装置，其特征在于，所述根据每个所述固态硬盘中所述图像被存储时的时间参数及大小，对每个所述固态硬盘的存储性能进行评估之后，还包括：
    根据每个所述固态硬盘的存储性能的评估结果和预设策略，筛选多个所述固态硬盘中的一个或多个作为存储设备。
PCT/CN2018/101636 2018-08-22 2018-08-22 固态硬盘的存储性能的评估方法、装置和图像存储系统 WO2020037526A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2018/101636 WO2020037526A1 (zh) 2018-08-22 2018-08-22 固态硬盘的存储性能的评估方法、装置和图像存储系统
CN201880039850.9A CN110785744A (zh) 2018-08-22 2018-08-22 固态硬盘的存储性能的评估方法、装置和图像存储系统

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/101636 WO2020037526A1 (zh) 2018-08-22 2018-08-22 固态硬盘的存储性能的评估方法、装置和图像存储系统

Publications (1)

Publication Number Publication Date
WO2020037526A1 true WO2020037526A1 (zh) 2020-02-27

Family

ID=69383259

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/101636 WO2020037526A1 (zh) 2018-08-22 2018-08-22 固态硬盘的存储性能的评估方法、装置和图像存储系统

Country Status (2)

Country Link
CN (1) CN110785744A (zh)
WO (1) WO2020037526A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115083506A (zh) * 2022-06-22 2022-09-20 上海威固信息技术股份有限公司 固态硬盘存储性能测试方法、系统、图像存储设备和硬盘

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101154416A (zh) * 2006-09-25 2008-04-02 佛山市顺德区顺达电脑厂有限公司 硬盘效能评估方法
CN107068199A (zh) * 2017-05-11 2017-08-18 郑州云海信息技术有限公司 一种ssd硬盘的性能测试方法
US20180032396A1 (en) * 2016-07-29 2018-02-01 Sandisk Technologies Llc Generalized syndrome weights

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103578568B (zh) * 2012-07-24 2016-08-17 苏州傲科创信息技术有限公司 固态硬盘的性能测试方法及装置
GB2503600B (en) * 2012-12-21 2014-05-14 Mobile Content Man Solutions Ltd Digital memory imaging system and method
US10140034B2 (en) * 2015-11-24 2018-11-27 International Business Machines Corporation Solid-state drive assignment based on solid-state drive write endurance

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101154416A (zh) * 2006-09-25 2008-04-02 佛山市顺德区顺达电脑厂有限公司 硬盘效能评估方法
US20180032396A1 (en) * 2016-07-29 2018-02-01 Sandisk Technologies Llc Generalized syndrome weights
CN107068199A (zh) * 2017-05-11 2017-08-18 郑州云海信息技术有限公司 一种ssd硬盘的性能测试方法

Also Published As

Publication number Publication date
CN110785744A (zh) 2020-02-11

Similar Documents

Publication Publication Date Title
US9736363B2 (en) Imaging apparatus and control method thereof
US20190087283A1 (en) Aircraft aerial photography data backup method, apparatus and device, and computer readable storage medium
US20070008852A1 (en) File recording method, file recording apparatus, and program
EP3869313A1 (en) Data storage method and apparatus
WO2020037526A1 (zh) 固态硬盘的存储性能的评估方法、装置和图像存储系统
CN111124303B (zh) 一种数据的存储方法、装置及系统
JP2007080465A (ja) 撮像装置
US9554082B2 (en) Recording apparatus, recording method, and program
US9462182B2 (en) Imaging apparatus and control method thereof
US20090162030A1 (en) Recording apparatus
JP5820973B2 (ja) データ記録装置
US10063735B2 (en) Image file management method, image capturing device, image storage device, and computer readable medium thereof
CN101261871B (zh) 信息记录设备和信息记录方法
US8699848B2 (en) Video/audio recording and reproducing apparatus
JP2007067916A (ja) デジタルビデオカメラ
JP2006115024A (ja) デジタルカメラ
CN107105341B (zh) 视频文件的处理方法及系统
CN105684423A (zh) 一种监控系统中的图像管理方法及系统
KR102369798B1 (ko) 데이터 관리 방법 및 데이터 관리 시스템
JP6436818B2 (ja) 記録装置及び方法
JP2011204314A (ja) 受信装置、受信方法、プログラムおよび送信装置
JP2013161491A (ja) 画像記録装置
JP5120841B2 (ja) 映像記録装置、監視システムおよび映像記録方法
US8081869B2 (en) Time-varying image recording device
TW201436558A (zh) 節目錄製裝置及方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18931263

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18931263

Country of ref document: EP

Kind code of ref document: A1