CN114443240A - Input and output request processing method and electronic device - Google Patents

Abstract

The application provides an input/output request processing method and electronic equipment. The method can be applied to electronic equipment which has storage capacity and needs frequent read-write operation, such as mobile phones, tablet computers and the like. By implementing the method, the electronic device can detect the average response time of IO requests with different priorities in real time. When the average response time of the IO request with the high priority is longer than the average response time of the IO request with the low priority, the electronic device may increase the IO allocation ratio of the high priority group and decrease the IO allocation ratio of the low priority group. Therefore, in the same time, the electronic equipment can process more high-priority IO requests, so that the number of the waiting high-priority IO requests is reduced, the average response time of the high-priority IO requests is lower than that of the low-priority IO requests, more IO resources are provided for foreground application, blocking is avoided, and the use experience of a user is improved.

Description

Input and output request processing method and electronic device

technical field

The present application relates to the field of terminals, and in particular, to a method and electronic device for processing input and output requests.

Background technique

In the scenario of running multiple application programs, the read-write scheduling module of electronic devices such as mobile phones and tablet computers can receive multiple read operation requests or write operation requests issued by the above-mentioned multiple application programs, that is, input and output requests (referred to as IO for short). ask).

The existing priority-based IO request scheduling method ensures that the underlying device preferentially responds to the IO request issued by the foreground application, and to a certain extent improves the efficiency of the underlying device responding to the IO request of the foreground application. However, due to the time-consuming effects of other operations attached to different types of read and write operations, such as encryption, decryption, compression, decompression, data verification, etc., the response time of high-priority IO requests is still higher than that of low-priority IO requests IO request.

That is to say, the pure priority-based IO request scheduling method cannot guarantee that high-priority IO requests must have a lower average response time. That is, in the case where the high-priority IO request issued by the foreground application is preferentially processed, the occupation of IO resources by the application running in the background still has a great influence on the foreground application.

SUMMARY OF THE INVENTION

The present application provides an input and output request processing method and electronic device. The electronic device implementing the input/output IO request processing method can detect in real time that the electronic device processes the IO service processing time of different priorities. When the processing time of high-priority IO services is longer than the processing time of low-priority IO services, the electronic device can increase the occupancy rate of high-priority IO services to IO resources, thereby improving the processing efficiency of high-priority IO services and avoiding blocked.

In a first aspect, an embodiment of the present application provides an input and output IO processing method, the method is applied to an electronic device, and the method includes: at the first time, taking out multiple IO services from multiple queues; The queue is used to store one or more IO services with the same IO processing priority. The IO processing priorities of IO services stored in different queues are different; IO processing is performed on multiple IO services retrieved according to the IO processing priority; The processing delay of multiple IO services, the processing delay of one IO service is used to indicate the time taken by an IO service from detecting the arrival of an IO service to the application receiving the IO processing result of an IO service; the second time, Take out multiple IO services from multiple queues; the second time is after the first time; if the processing time of IO services with high IO processing priority is longer than the processing delay of IO services with low IO processing priority, the second time The proportion of high-priority IO services among the multiple IO services retrieved at the first time is higher than the proportion of high-priority IO services among the multiple IO services retrieved at the first time.

By implementing the method provided by the first aspect, the electronic device can detect in real time the processing time of the electronic device processing IO services of different priorities. When the processing time of the high-priority IO service is longer than the processing time of the low-priority IO service, the electronic device can increase the occupancy rate of the IO resource by the high-priority IO service, so that the electronic device can process more IO resources in the same time. High-priority IO requests, thereby improving the processing efficiency of high-priority IO services, and the long response time affects user experience.

With reference to the embodiments provided in the first aspect, in some embodiments, after the multiple IO services are taken out from the multiple queues at the second time, the method further includes: holding the processing results of the IO services with low IO processing priority After the first time period, it returns to the application that initiates the IO service with low IO processing priority.

By implementing the method provided by the above embodiment, the electronic device can also reduce the activity of applications with low latency requirements such as background applications by limiting the return rate of low-priority IO services, so that the electronic device can process high-priority services faster. IO business.

With reference to the embodiments provided in the first aspect, in some embodiments, after the processing result of the low-priority IO request is retained for a first time period, it is returned to the application that initiated the low-priority IO request, specifically including: determining the electronic device The current load of the central processing unit CPU; if the current load is higher than the first threshold, the processing result of the low-priority IO request will be held for the first time, and then returned to the application that initiated the low-priority IO request. The threshold is preset.

By implementing the method provided by the above embodiment, the electronic device can judge whether it is necessary to limit the return rate of the priority IO service according to the current load of the CPU. When the current load of the CPU is too high, even if the IO resources occupied by the high-priority IO services are sufficient, they may not be processed in time due to insufficient CPU resources. Therefore, at this time, the electronic device can limit the return rate of priority IO services and reduce the activity of applications with low latency requirements such as background applications, thereby ensuring that high-priority IO services have sufficient CPU resources.

With reference to the embodiments provided in the first aspect, in some embodiments, taking out multiple IO services from multiple queues at a first time, specifically including: taking out multiple IO services from multiple queues at a first ratio at a first time services; at the second time, taking out multiple IO services from multiple queues, specifically including: at the second time, taking out multiple IO services from multiple queues according to a second ratio.

By implementing the method provided by the above embodiment, the electronic device can obtain different numbers of IO services by taking a preset ratio, and among the different numbers of IO services obtained at one time, the number of IO services with different priorities is different. In this way, when the above ratio is adjusted, the electronic device can accordingly obtain and adjust the quantity of IO services with different priorities obtained at one time.

With reference to the embodiments provided by the first aspect, in some embodiments, the number of proportional items of the first ratio is equal to the number of proportional items of the second ratio.

With reference to the embodiments provided in the first aspect, in some embodiments, the value of the first proportional item of the first ratio is lower than the value of the first proportional item of the second ratio, and the first proportional item is used to indicate that obtaining high IO processing priority The number of level IO services.

By implementing the method provided by the above embodiment, compared with obtaining IO services with different priorities according to the first ratio, when the electronic device obtains IO services with different priorities according to the second ratio, the electronic device can obtain more high-priority services. IO business.

With reference to the embodiments provided in the first aspect, in some embodiments, taking out multiple IO services from multiple queues according to a first ratio specifically includes: the number of the taken out multiple IO services is equal to or greater than each ratio of the first ratio The sum of the values of the items, and the ratio of the number of IO services with different IO processing priorities among the multiple IO services taken out is consistent with the first ratio; or, the number of multiple IO services taken out is less than the first ratio. the sum of the values.

Implementing the method provided by the above embodiment, the number of IO services of different priorities acquired by the electronic device in turn may be equal to the value of each proportional item in the first ratio; The value of each proportional item in the first ratio is in a multiple relationship; when the number of IO services of a certain priority is less than the number indicated by the corresponding proportional item in the first ratio, the number of IO services of the priority obtained by the electronic device may also be is less than the amount indicated by the corresponding proportional term in the first ratio.

With reference to the embodiments provided in the first aspect, in some embodiments, the processing delay specifically includes: the time taken from detecting the arrival of an IO service to when the application receives an IO processing result of an IO service; The average time taken for the application to receive the IO processing results of multiple one IO services after the arrival of multiple one IO services. Multiple one IO services are IO services with the same IO processing priority as one IO service.

Implementing the method provided by the above embodiment, when judging whether the processing delay of the high-priority IO service is longer than the processing delay of the low-priority IO service, the electronic device can use the actual processing delay of the high-priority IO service and this. Compared with the actual processing delay of low-priority IO services, the average processing delay of all IO services of the priority to which the high-priority IO service belongs and the average processing delay of all IO services of the priority of the low-priority IO service can also be used. Compare processing delays.

In a second aspect, the present application provides an electronic device comprising one or more processors and one or more memories; wherein the one or more memories are coupled to the one or more processors, and the one or more memories The memory is used to store computer program code, and the computer program code includes computer instructions, which when executed by one or more processors, cause the electronic device to perform the method described in the first aspect and any possible implementation of the first aspect.

In a third aspect, the present application provides a computer-readable storage medium, comprising instructions, when the above-mentioned instructions are executed on an electronic device, the above-mentioned electronic device is made to execute the first aspect and any possible implementation manner of the first aspect. method.

In a fourth aspect, the present application provides a computer program product containing instructions, when the computer program product is executed on an electronic device, the electronic device is made to execute the first aspect and any possible implementation manner of the first aspect. method.

Understandably, the electronic device provided in the second aspect, the computer storage medium provided in the third aspect, and the computer program product provided in the fourth aspect are all used to execute the method provided in this application. Therefore, for the beneficial effects that can be achieved, reference may be made to the beneficial effects in the corresponding method, which will not be repeated here.

Description of drawings

1 is a schematic diagram of a software architecture of an electronic device provided by an embodiment of the present application;

2 is a schematic diagram of a hardware structure of an electronic device provided by an embodiment of the present application;

3A-3B are schematic diagrams of a software architecture of an electronic device provided by an embodiment of the present application;

4A-4B are schematic diagrams of processing an IO request according to a scheduling policy by an electronic device provided by an embodiment of the present application;

4C is a flowchart of determining a return control strategy by an electronic device according to an embodiment of the present application;

5A-5C are schematic diagrams of a group of user interfaces provided by an embodiment of the present application;

FIG. 6 is a processing flowchart of an electronic device provided by an embodiment of the present application.

Detailed ways

The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations of the present application.

Electronic devices such as mobile phones and tablet computers (hereinafter referred to as the electronic device 100 ) can run multiple application programs at the same time. Applications can initiate IO requests. In response to the request, the electronic device 100 may perform read and write operations corresponding to the above-mentioned IO request.

FIG. 1 exemplarily shows the software architecture of the electronic device 100 .

The software system of the electronic device 100 may adopt a layered architecture, an event-driven architecture, a microkernel architecture, a microservice architecture, or a cloud architecture. The embodiments of the present application take an Android system with a layered architecture as an example to exemplarily describe the software structure of the electronic device 100 .

The layered architecture divides the software into several layers, and each layer has a clear role and division of labor. Layers communicate with each other through software interfaces. Generally, the layered architecture of Android includes: an application layer, a framework layer, a kernel layer, an Android runtime (Android runtime), a system library, and the like. In this embodiment of the present application, the software architecture of the electronic device 100 shown in FIG. 1 includes: an application layer and a kernel layer device layer. The kernel layer includes a file system and a block.

Below the application layer and the kernel layer is the device layer, that is, the hardware devices that respond to each IO request, including various storage devices, such as Multi media card (MMC)/Embedded Multi Media Card (eMMC), SCSI (Small Computer System Interface) hard disk \ Universal Flash Storage (Universal Flash Storage, UFS) and so on.

The application layer can have multiple applications installed. Taking application 1 (APP1) as an example, in response to a user operation, application 1 may initiate one or more IO requests. An IO request indicates an IO operation. The above IO requests include a write request (write), a read request (read), a synchronization request (fsync), a writeback (writeback) request, a forced buffer clearing request (flush), and the like. For example, in the process of playing a video, an application program performing the function of playing the video may initiate a read request, and in response to the request, the application program may read the video data stored in the storage, thereby playing the video.

The initiated IO request can pass through the file system to reach the IO scheduler layer in the block. Then, the read-write scheduling layer may sort the IO requests in the waiting state in the layer according to preset scheduling rules, and determine the priority of processing each IO request. Then, the storage device of the electronic device 100 may sequentially respond to the IO request according to the processing priority determined above, and perform the input and output operations indicated by the IO request. Blocks also include a generic block layer.

The read-write scheduling layer includes: a read-write scheduling layer using a multi-queue (Multi-queue, MQ) framework and a read-write scheduling layer using a single-queue (Single-queue, SQ) framework. In this embodiment of the present application, the read-write scheduling layer may be a read-write scheduling layer under the MQ framework. Generally, the read-write scheduling layer can use the absolutely fair (Completely Fair Queueing) scheduling algorithm to perform IO request scheduling. In addition, the scheduling algorithm also includes a read first (ROW) algorithm and so on.

In order to improve the efficiency of the electronic device 100 in responding to the application program being operated by the user and improve the user experience, the electronic device can mark the priorities of read and write requests issued by different types of application programs. For example, the electronic device can mark the read and write requests issued by the application that the user is operating as high-priority read and write requests, and the read and write requests issued by the application running in the background as low-priority requests. The application program that the user is operating may be referred to as a foreground application; the application program in the background running state may be referred to as a background application.

Then, the read and write scheduling layer can determine the order in which the underlying device responds to the read and write requests issued by each application program according to the priority of the read and write requests.

The above priority-based IO request scheduling method ensures that the underlying device preferentially responds to the IO request issued by the foreground application, and to a certain extent improves the efficiency of the underlying device responding to the IO request of the foreground application. However, due to the time-consuming impact of auxiliary operations attached to different types of read and write operations, such as encryption, decryption, compression, decompression, data verification, etc., the response time of high-priority IO requests may still be higher than that of low-priority IO requests. level IO request.

As shown in FIG. 1, the file system includes: Virtual File System (VFS), Fourth Extended File System (ext4), Flash-Friendly File System (F2FS) and Extendable Read-Only File System (EROFS), etc.

When performing the operation of writing (or writing out) data, different types of file systems will perform auxiliary operations on the data being written (or written out) at the same time, so as to improve the accuracy of the writing (or writing out) operation. safety. The above-mentioned auxiliary operations are, for example, operations such as encryption, decryption, compression, decompression, and data verification described above.

For example, when data is written (or written) to the memory through F2FS, the electronic device 100 needs to perform an encryption (or decryption) operation on the written (or written) data. At this time, auxiliary operations such as encryption and decryption increase the time required for the electronic device 100 to process the IO request. Therefore, when a high-priority IO request involves multiple auxiliary operations such as encryption, decryption, and compression, the response time of the high-priority IO request may be longer than that of a low-priority IO request.

Therefore, for high-priority IO requests, the average response time may be higher than for low-priority IO requests. That is to say, the pure priority-based IO request scheduling method cannot guarantee that high-priority IO requests must have a lower response time, which will lead to user experience.

In order to further ensure that the foreground application obtains sufficient IO resources and reduce the average response time of high-priority read and write requests, an embodiment of the present application provides a method for processing input and output requests. The method can be applied to electronic devices such as mobile phones and tablet computers that have storage capabilities and need to perform frequent read and write operations. In the introduction of the following embodiments, the above-mentioned electronic devices such as mobile phones and tablet computers are simply referred to as electronic devices 100 .

Not limited to cell phones, tablet computers, the electronic device 100 may also be a desktop computer, a laptop computer, a handheld computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, and a cellular phone, personal digital Assistant (personal digital assistant, PDA), augmented reality (augmented reality, AR) devices, virtual reality (virtual reality, VR) devices, artificial intelligence (artificial intelligence, AI) devices, wearable devices, in-vehicle devices, smart home devices and/or smart city equipment, the embodiments of the present application do not specifically limit the specific type of the electronic equipment.

By implementing the input and output request processing method provided by the embodiment of the present application, the electronic device 100 can detect the average response time of IO requests of different priorities in real time. When the average response time of high-priority IO requests is higher than the average response time of low-priority IO requests, the electronic device 100 may increase the IO allocation ratio of the high-priority group and decrease the IO allocation ratio of the low-priority group.

In this way, in the same time, the electronic device 100 can process more high-priority IO requests, thereby reducing the number of waiting high-priority IO requests, and ensuring that the average response time of higher-priority IO requests is lower than that of low-priority IO requests. The average response time of priority IO requests provides more IO resources for foreground applications to avoid congestion and improve user experience.

First, FIG. 2 exemplarily shows a schematic diagram of the hardware structure of the electronic device 100 .

The electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charge management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2 , mobile communication module 150, wireless communication module 160, audio module 170, speaker 170A, receiver 170B, microphone 170C, headphone jack 170D, sensor module 180, buttons 190, motor 191, indicator 192, camera 193, display screen 194, and Subscriber identification module (SIM) card interface 195 and the like. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, an air pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, and ambient light. Sensor 180L, bone conduction sensor 180M, etc.

The processor 110 may include one or more processing units, for example, the processor 110 may include an application processor (application processor, AP), a modem processor, a graphics processor (graphics processing unit, GPU), an image signal processor ( image signal processor, ISP), controller, video codec, digital signal processor (digital signal processor, DSP), baseband processor, and/or neural-network processing unit (neural-network processing unit, NPU), etc. Wherein, different processing units may be independent devices, or may be integrated in one or more processors.

The controller can generate an operation control signal according to the instruction operation code and timing signal, and complete the control of fetching and executing instructions.

A memory may also be provided in the processor 110 for storing instructions and data. In some embodiments, the memory in processor 110 is cache memory. This memory may hold instructions or data that have just been used or recycled by the processor 110 . If the processor 110 needs to use the instruction or data again, it can be called directly from the memory. Repeated accesses are avoided and the latency of the processor 110 is reduced, thereby increasing the efficiency of the system.

In some embodiments, the processor 110 may include one or more interfaces. The interface may include an integrated circuit (inter-integrated circuit, I2C) interface, an integrated circuit built-in audio (inter-integrated circuitsound, I2S) interface, a pulse code modulation (pulse code modulation, PCM) interface, a universal asynchronous receiver (universal asynchronous receiver) interface /transmitter, UART) interface, mobile industry processor interface (MIPI), general-purpose input/output (GPIO) interface, subscriber identity module (SIM) interface, and/or Universal serial bus (universal serial bus, USB) interface, etc.

The I2C interface is a bidirectional synchronous serial bus that includes a serial data line (SDA) and a serial clock line (SCL). In some embodiments, the processor 110 may contain multiple sets of I2C buses. The processor 110 can be respectively coupled to the touch sensor 180K, the charger, the flash, the camera 193 and the like through different I2C bus interfaces. For example, the processor 110 may couple the touch sensor 180K through the I2C interface, so that the processor 110 and the touch sensor 180K communicate with each other through the I2C bus interface, so as to realize the touch function of the electronic device 100 .

The I2S interface can be used for audio communication. In some embodiments, the processor 110 may contain multiple sets of I2S buses. The processor 110 may be coupled with the audio module 170 through an I2S bus to implement communication between the processor 110 and the audio module 170 . In some embodiments, the audio module 170 can transmit audio signals to the wireless communication module 160 through the I2S interface, so as to realize the function of answering calls through a Bluetooth headset.

The PCM interface can also be used for audio communications, sampling, quantizing and encoding analog signals. In some embodiments, the audio module 170 and the wireless communication module 160 may be coupled through a PCM bus interface. In some embodiments, the audio module 170 can also transmit audio signals to the wireless communication module 160 through the PCM interface, so as to realize the function of answering calls through the Bluetooth headset. Both the I2S interface and the PCM interface can be used for audio communication.

The UART interface is a universal serial data bus used for asynchronous communication. The bus may be a bidirectional communication bus. It converts the data to be transmitted between serial communication and parallel communication. In some embodiments, a UART interface is typically used to connect the processor 110 with the wireless communication module 160 . For example, the processor 110 communicates with the Bluetooth module in the wireless communication module 160 through the UART interface to implement the Bluetooth function. In some embodiments, the audio module 170 can transmit audio signals to the wireless communication module 160 through the UART interface, so as to realize the function of playing music through the Bluetooth headset.

The MIPI interface can be used to connect the processor 110 with peripheral devices such as the display screen 194 and the camera 193 . The MIPI interface includes a camera serial interface (camera serial interface, CSI), a display serial interface (displayserial interface, DSI), and the like. In some embodiments, the processor 110 communicates with the camera 193 through a CSI interface, so as to realize the photographing function of the electronic device 100 . The processor 110 communicates with the display screen 194 through the DSI interface to implement the display function of the electronic device 100 .

The GPIO interface can be configured by software. The GPIO interface can be configured as a control signal or as a data signal. In some embodiments, the GPIO interface may be used to connect the processor 110 with the camera 193, the display screen 194, the wireless communication module 160, the audio module 170, the sensor module 180, and the like. The GPIO interface can also be configured as I2C interface, I2S interface, UART interface, MIPI interface, etc.

The USB interface 130 is an interface that conforms to the USB standard specification, and may specifically be a Mini USB interface, a Micro USB interface, a USB Type C interface, and the like. The USB interface 130 can be used to connect a charger to charge the electronic device 100, and can also be used to transmit data between the electronic device 100 and peripheral devices. It can also be used to connect headphones to play audio through the headphones. The interface can also be used to connect other electronic devices, such as AR devices.

It can be understood that the interface connection relationship between the modules illustrated in the embodiment of the present invention is only a schematic illustration, and does not constitute a structural limitation of the electronic device 100 . In other embodiments of the present application, the electronic device 100 may also adopt different interface connection manners in the foregoing embodiments, or a combination of multiple interface connection manners.

The charging management module 140 is used to receive charging input from the charger. The charger may be a wireless charger or a wired charger. In some wired charging embodiments, the charging management module 140 may receive charging input from the wired charger through the USB interface 130 . In some wireless charging embodiments, the charging management module 140 may receive wireless charging input through a wireless charging coil of the electronic device 100 . While the charging management module 140 charges the battery 142 , it can also supply power to the electronic device through the power management module 141 .

The power management module 141 is used for connecting the battery 142 , the charging management module 140 and the processor 110 . The power management module 141 receives input from the battery 142 and/or the charging management module 140, and supplies power to the processor 110, the internal memory 121, the display screen 194, the camera 193, and the wireless communication module 160. The power management module 141 can also be used to monitor parameters such as battery capacity, battery cycle times, battery health status (leakage, impedance). In some other embodiments, the power management module 141 may also be provided in the processor 110 . In other embodiments, the power management module 141 and the charging management module 140 may also be provided in the same device.

The wireless communication function of the electronic device 100 may be implemented by the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, the modulation and demodulation processor, the baseband processor, and the like.

Antenna 1 and Antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in electronic device 100 may be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve antenna utilization. For example, the antenna 1 can be multiplexed as a diversity antenna of the wireless local area network. In other embodiments, the antenna may be used in conjunction with a tuning switch.

The mobile communication module 150 may provide wireless communication solutions including 2G/3G/4G/5G etc. applied on the electronic device 100 . The mobile communication module 150 may include at least one filter, switch, power amplifier, low noise amplifier (low noise amplifier, LNA) and the like. The mobile communication module 150 can receive electromagnetic waves from the antenna 1, filter and amplify the received electromagnetic waves, and transmit them to the modulation and demodulation processor for demodulation. The mobile communication module 150 can also amplify the signal modulated by the modulation and demodulation processor, and then turn it into an electromagnetic wave for radiation through the antenna 1 . In some embodiments, at least part of the functional modules of the mobile communication module 150 may be provided in the processor 110 . In some embodiments, at least part of the functional modules of the mobile communication module 150 may be provided in the same device as at least part of the modules of the processor 110 .

The modem processor may include a modulator and a demodulator. Wherein, the modulator is used to modulate the low frequency baseband signal to be sent into a medium and high frequency signal. The demodulator is used to demodulate the received electromagnetic wave signal into a low frequency baseband signal. Then the demodulator transmits the demodulated low-frequency baseband signal to the baseband processor for processing. The low frequency baseband signal is processed by the baseband processor and passed to the application processor. The application processor outputs sound signals through audio devices (not limited to the speaker 170A, the receiver 170B, etc.), or displays images or videos through the display screen 194 . In some embodiments, the modem processor may be a stand-alone device. In other embodiments, the modem processor may be independent of the processor 110, and may be provided in the same device as the mobile communication module 150 or other functional modules.

The wireless communication module 160 can provide wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), bluetooth (BT), and global navigation satellite systems applied on the electronic device 100 . (global navigation satellite system, GNSS), frequency modulation (frequency modulation, FM), near field communication technology (near field communication, NFC), infrared technology (infrared, IR) and other wireless communication solutions. The wireless communication module 160 may be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2 , frequency modulates and filters the electromagnetic wave signals, and sends the processed signals to the processor 110 . The wireless communication module 160 can also receive the signal to be sent from the processor 110 , perform frequency modulation on it, amplify it, and convert it into electromagnetic waves for radiation through the antenna 2 .

In some embodiments, the antenna 1 of the electronic device 100 is coupled with the mobile communication module 150, and the antenna 2 is coupled with the wireless communication module 160, so that the electronic device 100 can communicate with the network and other devices through wireless communication technology. The wireless communication technology may include global system for mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code Wideband code division multiple access (WCDMA), time-division code division multiple access (TD-SCDMA), long term evolution (LTE), BT, GNSS, WLAN, NFC, FM , and/or IR technology, etc. The GNSS may include a global positioning system (GPS), a global navigation satellite system (GLONASS), a Beidou satellite navigation system (BDS), a quasi-zenith satellite system (quasi- zenith satellite system, QZSS) and/or satellite based augmentation systems (SBAS).

The electronic device 100 implements a display function through a GPU, a display screen 194, an application processor, and the like. The GPU is a microprocessor for image processing, and is connected to the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. Processor 110 may include one or more GPUs that execute program instructions to generate or alter display information.

Display screen 194 is used to display images, videos, and the like. Display screen 194 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode or an active-matrix organic light-emitting diode (active-matrix organic light-emitting diode). , AMOLED), flexible light-emitting diode (flex light-emitting diode, FLED), Miniled, MicroLed, Micro-oLed, quantum dot light-emitting diodes (quantum dot light emitting diodes, QLED) and so on. In some embodiments, the electronic device 100 may include one or N display screens 194 , where N is a positive integer greater than one.

The electronic device 100 may implement a shooting function through an ISP, a camera 193, a video codec, a GPU, a display screen 194, an application processor, and the like.

The ISP is used to process the data fed back by the camera 193 . For example, when taking a photo, the shutter is opened, the light is transmitted to the camera photosensitive element through the lens, the light signal is converted into an electrical signal, and the camera photosensitive element transmits the electrical signal to the ISP for processing, and converts it into an image visible to the naked eye. ISP can also perform algorithm optimization on image noise, brightness, and skin tone. ISP can also optimize the exposure, color temperature and other parameters of the shooting scene. In some embodiments, the ISP may be provided in the camera 193 .

Camera 193 is used to capture still images or video. The object is projected through the lens to generate an optical image onto the photosensitive element. The photosensitive element may be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the optical signal into an electrical signal, and then transmits the electrical signal to the ISP to convert it into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. DSP converts digital image signals into standard RGB, YUV and other formats of image signals. In some embodiments, the electronic device 100 may include 1 or N cameras 193 , where N is a positive integer greater than 1.

A digital signal processor is used to process digital signals, in addition to processing digital image signals, it can also process other digital signals. For example, when the electronic device 100 selects a frequency point, the digital signal processor is used to perform Fourier transform on the frequency point energy and so on.

Video codecs are used to compress or decompress digital video. The electronic device 100 may support one or more video codecs. In this way, the electronic device 100 can play or record videos in various encoding formats, for example, moving picture experts group (MPEG) 1, MPEG2, MPEG3, MPEG4, and so on.

The NPU is a neural-network (NN) computing processor. By drawing on the structure of biological neural networks, such as the transfer mode between neurons in the human brain, it can quickly process the input information, and can continuously learn by itself. Applications such as intelligent cognition of the electronic device 100 can be implemented through the NPU, such as image recognition, face recognition, speech recognition, text understanding, and the like.

The internal memory 121 may include one or more random access memories (RAM) and one or more non-volatile memories (NVM).

Random access memory may include static random-access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous Dynamic random access memory (double data rate synchronous dynamic random access memory, DDR SDRAM, for example, fifth-generation DDR SDRAM is generally referred to as DDR5 SDRAM) and the like. Non-volatile memory may include magnetic disk storage devices, flash memory.

Flash memory can be divided into NOR FLASH, NAND FLASH, 3D NAND FLASH, etc. according to the operation principle, and can include single-level memory cell (SLC), multi-level memory cell (multi-level memory cell, SLC) according to the level of storage cell potential. cell, MLC), triple-level cell (TLC), quad-level cell (QLC), etc., according to storage specifications, it can include universal flash storage (English: universal flash storage, UFS), Embedded multimedia memory card (embedded multi media Card, eMMC) and so on.

The random access memory can be directly read and written by the processor 110, and can be used to store executable programs (eg, machine instructions) of an operating system or other running programs, and can also be used to store data of users and application programs.

The non-volatile memory can also store executable programs and store data of user and application programs, etc., and can be loaded into the random access memory in advance for the processor 110 to directly read and write.

The external memory interface 120 can be used to connect an external non-volatile memory, so as to expand the storage capacity of the electronic device 100 . The external non-volatile memory communicates with the processor 110 through the external memory interface 120 to realize the data storage function. For example, save music, video, etc. files in external non-volatile memory.

In this embodiment of the present application, in response to an IO request issued by the application layer, a storage device that performs input and output operations matching the IO request includes: an internal memory 121 and an external memory connected to the external memory interface 122 .

The electronic device 100 may implement audio functions through an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, an application processor, and the like. Such as music playback, recording, etc.

The audio module 170 is used for converting digital audio information into analog audio signal output, and also for converting analog audio input into digital audio signal. Audio module 170 may also be used to encode and decode audio signals. In some embodiments, the audio module 170 may be provided in the processor 110 , or some functional modules of the audio module 170 may be provided in the processor 110 .

Speaker 170A, also referred to as a "speaker", is used to convert audio electrical signals into sound signals. The electronic device 100 can listen to music through the speaker 170A, or listen to a hands-free call.

The receiver 170B, also referred to as "earpiece", is used to convert audio electrical signals into sound signals. When the electronic device 100 answers a call or a voice message, the voice can be answered by placing the receiver 170B close to the human ear.

The microphone 170C, also called "microphone" or "microphone", is used to convert sound signals into electrical signals. When making a call or sending a voice message, the user can make a sound by approaching the microphone 170C through a human mouth, and input the sound signal into the microphone 170C. The electronic device 100 may be provided with at least one microphone 170C. In other embodiments, the electronic device 100 may be provided with two microphones 170C, which can implement a noise reduction function in addition to collecting sound signals. In other embodiments, the electronic device 100 may further be provided with three, four or more microphones 170C to collect sound signals, reduce noise, identify sound sources, and implement directional recording functions.

The earphone jack 170D is used to connect wired earphones. The earphone port 170D may be the USB port 130 or a 3.5mm open mobile terminal platform (OMTP) standard port, a cellular telecommunications industry association of the USA (CTIA) standard port.

The electronic device 100 may further include a pressure sensor 180A, a gyro sensor 180B, an air pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, an ambient light sensor 180L, a fingerprint sensor 180H, a temperature sensor 180J, a bone Conductive sensor 180M.

Touch sensor 180K, also called "touch device". The touch sensor 180K may be disposed on the display screen 194 , and the touch sensor 180K and the display screen 194 form a touch screen, also called a “touch screen”. The touch sensor 180K is used to detect a touch operation on or near it. The touch sensor can pass the detected touch operation to the application processor to determine the type of touch event. Visual output related to touch operations may be provided through display screen 194 . In other embodiments, the touch sensor 180K may also be disposed on the surface of the electronic device 100 , which is different from the location where the display screen 194 is located.

In this embodiment of the present application, the electronic device 100 detects an operation acting on the screen of the mobile phone, such as clicking an application icon to run the application (refer to the user interface shown in FIG. 5A ), which can be accomplished by the touch sensor 180K.

The keys 190 include a power-on key, a volume key, and the like. Keys 190 may be mechanical keys. It can also be a touch key. The electronic device 100 may receive key inputs and generate key signal inputs related to user settings and function control of the electronic device 100 .

Motor 191 can generate vibrating cues. The motor 191 can be used for vibrating alerts for incoming calls, and can also be used for touch vibration feedback. For example, touch operations acting on different applications (such as taking pictures, playing audio, etc.) can correspond to different vibration feedback effects. The motor 191 can also correspond to different vibration feedback effects for touch operations on different areas of the display screen 194 . Different application scenarios (for example: time reminder, receiving information, alarm clock, games, etc.) can also correspond to different vibration feedback effects. The touch vibration feedback effect can also support customization.

The indicator 192 can be an indicator light, which can be used to indicate the charging state, the change of the power, and can also be used to indicate a message, a missed call, a notification, and the like.

The SIM card interface 195 is used to connect a SIM card. The SIM card can be contacted and separated from the electronic device 100 by inserting into the SIM card interface 195 or pulling out from the SIM card interface 195 . The electronic device 100 may support 1 or N SIM card interfaces, where N is a positive integer greater than 1. The SIM card interface 195 can support Nano SIM card, Micro SIM card, SIM card and so on. Multiple cards can be inserted into the same SIM card interface 195 at the same time. The types of the plurality of cards may be the same or different. The SIM card interface 195 can also be compatible with different types of SIM cards. The SIM card interface 195 is also compatible with external memory cards. The electronic device 100 interacts with the network through the SIM card to implement functions such as call and data communication. In some embodiments, the electronic device 100 employs an eSIM, ie: an embedded SIM card. The eSIM card can be embedded in the electronic device 100 and cannot be separated from the electronic device 100 .

It can be understood that, the structures illustrated in the embodiments of the present invention do not constitute a specific limitation on the electronic device 100 . In other embodiments of the present application, the electronic device 100 may include more or less components than shown, or combine some components, or separate some components, or arrange different components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

The following describes the input and output request processing method provided by the embodiment of the present application in detail.

Based on the software architecture of the electronic device 100 shown in FIG. 1 , an embodiment of the present application provides a schematic diagram of the software architecture of the improved electronic device 100 shown in FIG. 3A . The following describes in detail with reference to FIG. 3A : in the process of implementing the input and output request processing method provided by the embodiment of the present application, the work flow of the software and hardware of the electronic device 100 is described.

As shown in FIG. 3A , the software architecture of the electronic device 100 can also be divided into three layers: an application layer, a kernel layer and a device layer.

The application layer may include one or more application programs and a delay detection module 211 . The above-mentioned one or more application programs are, for example, application program 1 (APP1), application program 2 (APP2). The above-mentioned applications can be applications provided by the system or third-party applications.

In the process of running an application, the application may initiate one or more processes. For example, in the process of running an audio-visual application to play a video, the processes maintained by the application may include: a user operation monitoring process, a video data acquisition process, an image data rendering process, an audio processing process, and the like. For any process, the process can initiate one or more IO requests. Therefore, the electronic device 100 can simultaneously detect multiple IO requests initiated by one or more applications.

The delay detection module 211 can be used to detect the average response time of IO requests of different priorities. Specifically, after detecting that a certain process initiates an IO request, the delay detection module 211 may obtain the timestamp (initiating time) at which the process initiated the IO request. After performing the input and output operations indicated by the above IO request, the storage device 217 may return the processing result to the application layer. The processing result may include a time stamp (response time) when the storage device 217 completes the execution of the above-mentioned IO request. At this time, the delay detection module 211 can obtain the response time from the above processing result.

The time-consuming between the initiation time and the response time is the response time for the electronic device to process the IO request. The delay detection module 211 may perform group statistics on the response times of numerous IO requests issued by the application layer according to the type of priority, and then calculate the average response time of the IO requests of the same priority.

The kernel layer includes a file system 212 (File System) and a block (Block).

File system 212 reflects the method and form in which files are organized on a storage device. Different file systems 212 organize and manage files differently. Before the storage device of the electronic device 100 executes the IO request issued by the application layer, the above-mentioned IO request will pass through the file system 212 . The file system 212 will process the above-mentioned IO request according to the form of organization and management files preset by itself, so that the above-mentioned IO request becomes the operable data of the target storage space of the IO request.

For example, when the type of the file system 212 is F2FS, after receiving an IO request (input request or output request) sent by the application layer, F2FS can encrypt the IO request, so that the data corresponding to the IO request can be encrypted. Can be written to (or written to) more securely to the storage device.

Referring to the introduction of FIG. 1, there are many types of file systems 212. Due to the different methods of processing IO requests by different file systems 212, the backend delays of IO requests passing through different file systems 212 are different. The above-mentioned back-end delay refers to the time taken by the file system 212 to convert the IO request into operable data of the target storage space of the IO request according to its own preset method of organizing and managing files. Backend latency is an important factor affecting the response time of IO requests.

The block (Block) includes a grouping quota module 213 , a return control module 214 and a read-write scheduling module 215 .

The grouping quota module 213 can dynamically adjust the occupancy ratio of IO requests with different priorities to IO resources according to the average response time of IO requests with different priorities, that is, dynamically adjust the scheduling ratio of IO resources. The return control module 214 may be used to control the return rate of IO processing results. Here, the return rate refers to the rate at which the IO processing result is returned from the kernel layer Block to the application that initiated the IO request. The read-write scheduling module 215 can determine the number and sequence (ie, processing priority) of the electronic device 100 to process IO requests with different priorities according to the scheduling policy preset by the grouping quota module 213 .

Subsequent embodiments will introduce the working principles of the group quota module 213 , the return control module 214 , and the read-write scheduling module 215 in detail, which will not be expanded here.

The device layer includes storage devices 217 . The above-mentioned storage devices include volatile storage devices and non-volatile storage devices. The non-volatile storage device may be an SSD, MMC/eMMC, etc. For details, reference may be made to the introduction in FIG. 1 , which will not be repeated here. The controllable storage device 217 performs the input and output operations indicated by the IO request.

Based on the software architecture diagram shown in FIG. 3A , reference may be made to FIG. 3B for the process of the electronic device 100 processing the IO request issued by the application.

As shown in FIG. 3B , APP1 may be a foreground application (an application directly operated by the user); APP2 may be a background application (an application not directly operated by the user).

Generally, since the foreground application needs to give feedback to the user in time, the latency tolerance of the IO request initiated by the foreground application is low (that is, the latency requirement is high). The above-mentioned delay tolerance refers to the degree of delay in receiving the response. After detecting the IO request initiated by the foreground application, the electronic device 100 needs to process the IO request in the shortest possible time. However, since the background application does not need to give immediate feedback to the user, the background application has a higher latency tolerance (that is, a lower latency requirement). After detecting the IO request initiated by the background application, the electronic device 100 may process the IO request less urgently.

Therefore, after simultaneously detecting an IO request with a higher latency requirement and an IO request with a lower latency requirement, the electronic device 100 may preferentially process the IO request with a higher latency requirement.

For example, APP1 can initiate one IO request (IO1); APP2 can initiate two IO requests (IO2, IO3). The delay requirement of IO1 is for example 5ms, the delay requirement of IO2 is for example 10ms, and the delay requirement of IO3 is for example 15ms. Therefore, IO1 can be a high-priority IO request, and IO2 and IO3 can be low-priority IO requests. Among them, the priority of IO2 can be higher than that of IO3. That is, the priority IO1 is higher than IO2 and higher than IO3. Here, we use priorities A, B, and C (A>B>C) to represent the processing priorities of the electronic device 100 for processing the above three IO requests, respectively. Among them, the priority of IO1 is A; the priority of IO2 is B; the priority of IO3 is C. It can be understood that the above-mentioned corresponding relationship between the delay requirement and the IO processing priority is only an example, and should not constitute a limitation on the embodiments of the present application.

In the scenario where the electronic device 100 runs a video application and a gallery application at the same time: the video application in the background running state can initiate a write request to write and download video data to the storage device 217 (IO3); IO2 can be initiated by some system applications or processes IO request; the gallery application in the foreground running state can initiate a read request to read a certain picture (IO1) from the storage device 217. It can be understood that the delay requirements of different processes of the same application may also be different. Therefore, the above three IO requests may also be initiated by the same application.

Taking IO1 as an example, after APP1 initiates IO1, the delay detection module 211 can detect the arrival of IO1. At this time, the delay detection module 211 can record the current time as the initiation time of IO1. Similarly, the delay detection module 211 can record the time when APP2 initiates IO2 and IO3, that is, the respective initiation times of IO2 and IO3.

The IO request issued by the application layer can reach the block through the file system. The time delay of this delivery process can be recorded as Δt1. Combined with the introduction in Figure 1, due to the different file organization forms used in the target storage space of different IO requests, that is, the file systems that the IO requests pass through are different, and the values of Δt1 for different IO requests are different. This is also an important factor that causes the total delay of high priority to be longer than that of low priority.

After the IO request reaches the Block, the read/write scheduling module 215 may determine the order in which the underlying storage device 217 processes the IO request according to the priority of the IO request. The time spent waiting for the IO request to be processed in the read/write scheduling module 215 may be recorded as Δt2. In this embodiment of the present application, the read/write scheduling module 215 also relies on the group quota module 213 in the process of determining the order in which the storage device 217 processes IO requests.

Specifically, the working principles of the group quota module 213 and the read-write scheduling module 215 are as follows:

The group quota module 213 may record the ratio of the number of IO requests with different priorities processed by the electronic device 100 in one cycle, which is referred to as the scheduling ratio for short. The read-write scheduling module 215 can obtain a specific number of IO requests from the buffer area that receives the IO requests issued by the application layer according to the scheduling ratio recorded in the grouping quota module 213, and determine to issue the above-mentioned specific number of IO requests. order to storage device 217.

FIG. 4A exemplarily shows the process that the read-write scheduling module 215 processes the received IO request according to the scheduling ratio recorded in the group quota module 213 .

Corresponding to the priorities A, B, and C, the buffer area for receiving the IO request issued by the application layer may include three buffer queues, namely the A queue, the B queue, and the C queue. The above three queues are used to cache the above three types of IO requests with different priorities. Among them, queue A can be used to cache IO requests with priority A (type A IO requests); queue B can be used to cache IO requests with priority B (type B IO requests); queue C can be used to cache IO requests with priority C IO request (type C IO request).

After detecting the IO request sent by the application layer, the electronic device 100 can identify the priority of the IO request, and then the electronic device 100 can cache the IO request in a queue corresponding to the priority, and wait for a response from the underlying storage device.

Combined with IO1 (A), IO2 (B), and IO3 (C) shown in FIG. 3B , when IO1 is detected, the electronic device 100 can insert IO1 into the A queue; when IO2 is detected, the electronic device 100 IO2 may be inserted into the B queue; when IO3 is detected, the electronic device 100 may insert IO3 into the C queue.

It can be understood that, according to different division principles, or by combining or splitting the above three types of priorities, the priority types of the IO requests in the electronic device 100 may also be in other forms, that is, including more or less priority classifications. . Accordingly, the electronic device 100 may mark IO requests initiated by different applications or processes according to the new priority classification. This embodiment of the present application does not limit this. In other embodiments, IO requests with different priorities can also be cached in one storage area.

The electronic device 100 may also include a scheduling queue Q. The dispatch queue Q is also used to buffer IO requests. IO requests dequeued from queue A, queue B, and queue C can be buffered to dispatch queue Q. The order in which the IO requests are arranged in the dispatch queue Q may indicate the order in which the storage device 217 actually processes the IO requests.

After IO1, IO2, and IO3 arrive at the buffer queue, IO1, IO2, and IO3 can wait in the buffer queue. At this time, the read-write scheduling module 215 may obtain the current scheduling ratio from the grouping quota module 213 . Then, according to the scheduling ratio recorded in the grouping quota module 213, the electronic device 100 can sequentially fetch a corresponding number of A-type IO requests, B-type IO requests, and C-type IO requests from the A queue, B-queue and C-queue, and send The above IO requests are sequentially inserted into the scheduling queue Q. When IO requests with different priorities are buffered in one storage area, the read/write scheduling module 215 can identify the above IO requests according to the priority identifiers of each IO request, and determine whether to store them in the scheduling queue Q.

Generally, the electronic device 100 needs to prioritize IO requests with high priorities. Therefore, in most cases, the electronic device 100 needs to allocate more IO resources for high-priority IO requests. Therefore, in general, in the preset scheduling ratio, the value of the ratio item indicating the type A IO request will be larger. In this way, the electronic device 100 can allocate more IO resources to high-priority class A IO requests to quickly respond to the user's request.

For example, it is assumed that the scheduling ratio recorded in the group quota module 213 is 5:3:2. At this time, in one cycle, according to the above-mentioned scheduling ratio, the read-write scheduling module 215 can obtain 5 A-type IO requests, 3 B-type IO requests and 2 C-type IO requests respectively from the above-mentioned cache queues A, B, and C. IO requests, and sequentially insert the above IO requests into the scheduling queue Q. The above-mentioned 5 A-type IO requests, 3 B-type IO requests, and 2 C-type IO requests respectively include IO1, IO2, and IO3 waiting in the buffer queues A, B, and C. In other embodiments, according to the scheduling ratio of 5:3:2, the read-write scheduling module 215 can also obtain 10 A-type IO requests, 6 B-type IO requests and 4 C-type IO requests ( 10:6:4 = 5:3:2) and so on.

Then, the read-write scheduling module 215 can sequentially deliver the various IO requests in the scheduling queue Q to the storage device 217 in sequence. In response to the above IO request, the storage device 217 may perform the input and output operations indicated by the IO request.

Returning to FIG. 3B , after the storage device 217 finishes processing the IO request, the storage device 217 may return the processing result of the IO request to the application that initiated the IO request. The time taken by the storage device 217 to process the IO request can be recorded as Δt3. The time required for the storage device 217 to return to process the IO request until the application program receives the above-mentioned IO processing result may be recorded as Δt4. The main factor affecting Δt3 is the type of the storage device. Therefore, in this embodiment of the present application, the time for the storage device 217 to perform input and output operations in response to different IO requests can be regarded as the same, that is, the Δt3 of different IO requests can be regarded as the same .

For example, after the storage device 217 sequentially performs the input and output operations indicated by IO1, IO2, and IO3, the storage device 217 may return the processing results (IO processing results) of IO1, IO2, and IO3 to the application layer. The above processing results include acknowledgement characters (eg, ACK), and/or input or output data.

Before returning to the application layer, the IO processing result will go through the return control module 214 . FIG. 4B shows the working principle of the return control module 214 .

As shown in FIG. 4B , the return control module 214 can detect the IO processing result returned by the storage device 217 . First, the return control module 214 can identify the priority of the above processing result, and then the return control module 214 can control the return rate of the processing result of the low priority IO request according to the current return control policy.

Combined with multiple IO requests in the scheduling queue Q shown in FIG. 4A , as shown in FIG. 4B , the return control module 214 can sequentially receive the above-mentioned IO requests (5 type A IO requests, 3 type B IO requests, 3 type B IO requests) returned by the storage device 217 in sequence. IO request and 2 class C IO requests) processing results. Here, the rectangular block marked "IO" in Figure 4B has a different meaning from that of Figure 4A, where a rectangular block marked "IO" in Figure 4A represents an IO request, and a rectangular block marked "IO" in Figure 4B The rectangular blocks represent processing results generated after the storage device 217 processes an IO request.

For any IO request among the above IO requests, after receiving the processing result of the IO request, the return control module 214 can determine the IO request described in the processing result and the IO request according to the identifier of the IO request in the processing result. The priority of the request.

In a scenario where the return rate of the low-priority IO processing result is limited, if the above-mentioned processing result is a low-priority IO processing result, the return control module 214 may delay sending the processing result to the file system 212 and the application layer.

For example, in the scenario of limiting the return rate of the IO processing result of class C priority, when the received IO processing result is the processing result of the IO request of class A priority (or the processing result of the IO request of class B priority) ), the return control module 214 can normally return the above IO processing result to the application layer. When the received IO processing result is the processing result of the IO request with the C-class priority, the return control module 214 can delay the IO processing result in the return control module 214 for a period of time, and then transmit the IO processing result back to the application Floor. The above period of time is preset, such as 0.1ms and so on.

For any IO request, if the IO processing result is restricted by the return control module 214 when the IO processing result is returned to the application layer, the time Δt4 for returning to the application layer will be extended. In this way, due to the delayed receipt of the processing result of the low-priority IO request, the activity of the application that initiates the IO request will be reduced, thereby improving the efficiency of the electronic device 100 in processing the high-priority IO request.

The working principle of the return control module 214 for determining the return control strategy is first described in detail below. Taking the aforementioned three-level priority classification (A, B, C) shown in FIG. 4A as an example, FIG. 4C shows a flowchart of the electronic device 100 determining the return control strategy according to the current load of the CPU.

S101: The electronic device 100 queries the current load H0 of the CPU.

The electronic device 100 can determine the current load of the CPU through a function provided by the system to query the CPU working state, which is recorded as H0, including the occupancy of the CPU, the number of processes waiting for CPU resources, and the like.

For example, when all processing cores of the CPU are occupied and there are a large number of processes waiting for processing by the CPU, at this time, the electronic device 100 may determine that the CPU load is high (busy). The above functions are, for example, the vmstat() function, the mpstat() function, etc. provided by Linux, which are not limited in this embodiment of the present application.

Then, the electronic device 100 may compare the size of the current load with the preset load threshold, and determine whether to limit the return rate of the low-priority IO request.

The electronic device 100 may be provided with a load threshold H1 and a load threshold H2. Among them, H1<H2. The load thresholds set in two levels above may reflect different degrees to which the electronic device 100 limits the return rate of low-priority IO requests. Of course, the electronic device 100 may also set more or less load thresholds. This embodiment of the present application does not limit this.

After acquiring the current load of the CPU, the electronic device 100 may compare the current load with the load thresholds ( H1 , H2 ). First, S102: The electronic device 100 may compare the magnitude of the current load with the threshold H2, and determine whether the current load of the CPU is higher than the threshold H2.

If the current load is higher than H2, that is, H2<H0, the CPU of the electronic device 100 is very busy. At this time, S103: The electronic device 100 may limit the return rate of all low-priority IO requests (eg, limit the return rate of IO requests with priorities B and C). Reflected on the application, the electronic device 100 can limit the IO requests initiated by non-foreground applications, including the return rate of IO requests of system applications and background applications.

If the current load is lower than H2, and H0<H2, then S104: The electronic device 100 may continue to compare the current load with the threshold H1 to determine whether the current CPU load is higher than the threshold H1.

If the current load is higher than H1, that is, H1<H0<H2, the CPU of the electronic device 100 is relatively busy. At this time, S105: The electronic device 100 may limit the return rate of some low-priority IO requests (for example, only limit the return rate of IO requests with priority C). Reflected on the application, the electronic device 100 may only limit the return rate of IO requests initiated by background applications, but not the return rate of IO requests initiated by system applications.

If the current load is lower than H1, that is, H0<H1, the CPU of the electronic device 100 may be regarded as idle. At this time, S106: The electronic device 100 may not limit the return rate of any IO request.

In this way, when the processor of the electronic device 100 is busy but the IO resources are idle, the electronic device 100 can reduce the CPU resource occupation of the background application and improve the processing performance of the foreground application by controlling the return rate of the low-priority IO request. At the same time, restricting background applications from the return side can improve the utilization of IO resources.

Returning to FIG. 3B , after passing through the return control module 214 , through the file system 212 and the delay detection module 211 , the IO processing result can be returned to the application that initiated the IO request. For example, IO1 can return APP1, IO2, IO3 can return APP2.

When the IO processing result passes through the delay detection module 211 , the delay detection module 211 may determine that the current time is the time (end time) when the electronic device 100 completes the processing of the IO request corresponding to the IO processing result. Also taking IO1 as an example, after the processing result of IO1 reaches the delay detection module 211, the delay detection module 211 may determine that the current time is the time when the electronic device 100 finishes processing IO1. In combination with the above description, after APP1 initiates IO1, the time delay detection module 211 detects the time (initiation time) of IO1, and through the above two times (initiation time and end time), the delay detection module 211 can determine the electronic device 100 to process The total time of IO1, that is, the response time, is recorded as T1.

By analogy, the delay detection module 211 can sequentially determine the time for the electronic device 100 to process each IO request in one IO processing cycle, that is, the response time of each IO request. In this way, the delay detection module 211 can determine that the response time of IO2 is T2, and the response time of IO3 is T3.

Generally, the electronic device 100 preferentially processes the A-type IO request, so the response time of the A-type IO request should be the shortest. In IO1, IO2, IO3, the response time T1, T2, T3 of IO1, IO2, IO3 should satisfy: T1<T2<T3. However, due to the time consuming on paths such as Δt1 and Δt2, especially the file systems 212 that different IO requests pass through are different (Δt2 is different), this may cause the response time of high-priority IO requests to be longer than low-priority requests. The response time of the IO request. This is due to the different processing of data attachment (encryption, decryption, compression, decompression, data verification, etc.) in different file systems.

For example, the Δt1 of IO1 may be greater than the Δt1 of IO2 due to encryption and compression operations, so the response time of IO1 will be longer than that of IO1.

For example, T1=△t1(IO1)+△t2(IO1)+△t3(IO1)+△t4(IO1)=10ms;

T2=△t1(IO2)+△t2(IO2)+△t3(IO2)+△t4(IO2)=9ms;

T3=△t1(IO3)+△t2(IO3)+△t3(IO3)+△t4(IO3)=11ms;

Among them, T1>T2 does not satisfy T1<T2.

At this time, the group quota module 213 can obtain the response time of the above-mentioned different IO requests. Further, the grouping quota module 213 can determine whether the response time of the above-mentioned different IO requests is satisfied: the response time of the IO request of high priority is shorter than the response time of IO request of low priority.

Optionally, after the delay detection module 211 determines the response time of each IO request, the delay detection module 211 may also determine the average response time of the IO requests of the same priority.

For example, according to the order of the IO requests in the scheduling queue Q, the storage device 217 may first process the above-mentioned five A-type IO requests. After each IO request is processed, the storage device 217 may generate a processing result of the IO request. The processing result may include a time stamp (response time) when the storage device 217 finishes processing the IO request. At this time, in conjunction with the initiation time of the other IO request sent by the application, the delay detection module 211 can determine the total time it takes for the electronic device 100 to respond to the IO request, that is, the response time. After the above-mentioned five A-type IO requests are executed, the delay detection module 211 can determine the average response time of the A-type IO requests, which is recorded as AvgT1.

Similarly, with reference to the above processing method, the electronic device 100 can sequentially determine the average response time of the B-type IO request and the C-type IO request, which are recorded as AvgT2 and AvgT3. At this time, the electronic device 100 may determine the average response time of the A-type IO request, the B-type IO request and the C-type IO request, which are AvgT1, AvgT2 and AvgT3, respectively.

At this time, the group quota module 213 can obtain the average response time of the above-mentioned IO requests with different priorities. Further, the grouping quota module 213 may determine whether the above-mentioned average response time satisfies: the average response time of high-priority IO requests is less than the average response time of low-priority IO requests.

Taking the average response time as an example, after determining AvgT1, AvgT2, and AvgT3, the electronic device 100 may adjust the scheduling ratio in the packet quota module 213 according to the above-mentioned average response time.

Specifically, the grouping quota module 213 may obtain the average response time of the IO requests of each priority from the delay detection module 211 . Then, the packet quota module 213 may check whether the average response time of high-priority IO requests is lower than the average response time of low-priority IO requests. When the average response time of high-priority IO requests is lower than the average response time of low-priority IO requests, the group quota module 213 may determine that the current efficiency of processing high-priority IO requests cannot satisfy the user's desire to respond to high-priority requests as soon as possible IO request requirements. At this time, the electronic device 100 needs to adjust the allocation of IO resources and provide more IO resources to high-priority IO requests, that is, to increase the ratio of high-priority in the scheduling ratio to further meet the needs of foreground applications and avoid response time Too long affects the user experience.

For example, in the case where the scheduling ratio is 5:3:2, if AvgT1>AvgT2, that is, the average response time of class A IO requests is higher than the average response time of class B IO requests, the electronic device 100 can match the above scheduling ratio Adjusted to 6:2:2. In this way, the electronic device 100 can process 5 A-type IO requests from the original 1 ms, and can process 6 A-type IO requests in 1 ms. In this way, in the same unit time, the electronic device 100 can process more A-type IO requests, so the average response time of A-type IO requests can be reduced.

Similarly, if AvgT2>AvgT3, the electronic device 100 can increase the IO resource occupancy ratio of B-type IO requests and decrease the IO resource occupancy ratio of C-type IO requests. For example, the electronic device 100 can make the above scheduling ratio (5:3:2 ) is adjusted to 5:4:1, so that the electronic device 100 can handle more class B IO requests.

In this way, when the average response time of high-priority IO requests is higher than the average response time of low-priority IO requests, the electronic device 100 may determine that the IO resources currently allocated to high-priority IO requests cannot satisfy the high-priority IO requests request needs. Therefore, the electronic device 100 may readjust the allocation of IO resources, and allocate more IO resources for high-priority IO requests, so as to reduce the average response time of high-priority IO requests.

The grouping quota module 213 may also adjust the scheduling ratio according to the response time of a single IO request. For example, after the group quota module 213 obtains the response times T1, T2, and T3 of IO1, IO2, and IO3, and after determining that T1>T2, the group quota module 213 can also increase the ratio of the items described in IO1 in the scheduling ratio. Specifically, Refer to the above-mentioned adjustment method of the average response time, which will not be repeated here.

In some embodiments, when the foreground application is closed or the foreground application's demand for IO resources is significantly reduced, the number of Class A IO requests will decrease. At this time, the electronic device 100 may readjust the scheduling ratio, appropriately reduce the proportion of the IO resource occupied by the A-type IO request, and increase the proportion of the B-type IO request and the C-type IO request.

For example, in the process that the electronic device 100 obtains each group of IO requests according to the scheduling ratio of 6:2:2, if the number of Type A IO requests that are in the waiting state in the A queue is detected for many times lower than the above scheduling ratio When the number is indicated, the electronic device 100 can reduce the proportion of Class A IO requests to IO resources, for example, restore the scheduling ratio to 5:3:2, or further reduce the proportion of Class A IO requests to IO resources, for example, The scheduling ratio is adjusted to 4:4:2 or 4:3:3, etc. This embodiment of the present application does not limit this.

Of course, in other embodiments, when the foreground application is closed or the demand for IO resources of the foreground application is significantly reduced, the electronic device 100 may continue to use the aforementioned scheduling ratio, which will not be repeated here.

Then the read-write scheduling module can obtain IO requests with different priorities from the buffer queues A, B, and C according to the new scheduling ratio.

In other embodiments, after acquiring the data in the delay detection module 211, the group quota module 213 may check whether the response time of each IO request meets its own delay requirement. When the response time does not meet its own delay requirement, the grouping quota module 213 can also adjust the scheduling ratio of different priorities. For example, the response time of IO1 is 10ms, and its own delay requirement is 5ms, that is, the response time of IO1 does not meet its own delay requirement. At this time, the group quota module 213 can increase the priority ratio of IO1 in the scheduling ratio. .

It can be understood that, the structures illustrated in the embodiments of the present invention do not constitute a specific limitation on the electronic device 100 . In other embodiments of the present application, the electronic device 100 may include more or less hierarchical structures and functional modules than shown, or combine some hierarchical structures and functional modules, or split some hierarchical structures and functional modules, Or different hierarchies and arrangements of functional modules. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

5A-5B exemplarily show user interfaces of applications running on the electronic device 100 .

FIG. 5A shows the user interface of the electronic device 100 presenting an installed application. As shown in FIG. 5A, the user interface may include a status bar 413, one or more application icons 412, a tray 413 of frequently used application icons, a page indicator 414, and the like.

Wherein, the status bar 411 may include: one or more signal strength indicators of mobile communication signals (also referred to as cellular signals), one or more indicators of high-fidelity wireless communication (wire less fidelity, Wi-Fi) signals A signal strength indicator, battery status indicator, time indicator, etc.

The one or more application icons 412 may include icons of applications such as Settings, APP store, Gallery (Photos), and Browser (Browser). After detecting a user operation acting on any of the above icons, the electronic device 100 can run the application indicated by the icon. For example, after detecting a user operation acting on an icon of a gallery (Photos) application, such as a click operation, the electronic device 100 can run the gallery application.

Icons of one or more applications may be displayed in the frequently used application icon tray 413 . The above-mentioned one or more application programs are frequently useful applications set by the user, such as camera, address book, phone, information and other applications. The application icons in the frequently used application icon tray 413 remain displayed when switching pages. The above-mentioned tray icon is optional, which is not limited in this embodiment of the present application. The page indicator 414 may be used to indicate the positional relationship of the currently displayed page to other pages.

One or more application icons 412 may be distributed on multiple pages, and a page indicator 414 may also be used to indicate which page of applications the user is currently browsing. Users can swipe left and right in the area of other application icons to browse application icons in other pages.

In some embodiments, the user interface shown in FIG. 5A may present the home page of the application for the electronic device 100 . It can be understood that FIG. 5A only exemplarily shows a possible user interface of the electronic device 100 , and should not constitute a limitation to the embodiments of the present application.

In response to a user operation acting on any application icon, the electronic device 100 may execute the application indicated by the icon. In the process of running the gallery application, the application can initiate multiple IO requests. The above IO requests include IO requests to obtain computer program codes, system data and user data necessary for running the application.

FIG. 5B shows a user interface of the electronic device 100 running the gallery application. As shown in FIG. 5B, the user interface includes a search bar 421, icons 422 of one or more albums, a menu bar 423, and the like.

The search bar 421 can be used to search for pictures. For example, the user may enter the keyword "flower" in the search bar 421 . The electronic device 100 may detect a user operation acting on the search bar 421, and in response to the operation, the electronic device 100 may search for a picture whose picture content includes "flower" among all pictures stored in the gallery.

One or more album icons 422 may represent one or more folders in which image data is stored. As shown in FIG. 5B , the album includes a camera (Cmera), a screen shot (ScreenShot), a download (Download), and the like. The image displayed in the album icon can be any picture in the album.

Menu bar 423 may include one or more controls, such as photo controls, album controls, moment controls. The above controls provide the user with the ability to display images stored in the gallery in different arrangements. For example, after detecting a user operation acting on the time control, the electronic device 100 may display all the images in the gallery according to the time sequence of each image.

During the process of running the gallery application on the electronic device 100, the gallery application may initiate multiple IO requests. In response to the above-mentioned multiple IO requests, the gallery application may obtain computer program code, system data, and user data of the gallery application.

For example, when the gallery application needs to display the user interface shown in FIG. 5B , the gallery application can initiate an IO request to read the code of the user interface, including the page layout code. When the user interface shown in FIG. 5B is displayed, the gallery application may initiate an IO request to read the control icon resource. In addition, the gallery application can initiate IO requests to read images stored in the storage device. In this way, the user interface shown in FIG. 5B can display image data such as numerous pictures, dynamic pictures, and videos saved on the electronic device 100 .

The electronic device 100 may detect operations of multiple users clicking on an icon of an application program, and in response to the above user operations, the electronic device 100 may execute multiple application programs. For the above-mentioned multiple applications, some applications are applications that the user is operating, that is, foreground applications, while other applications are applications that are running in the background, that is, background applications. Meanwhile, the electronic device 100 also runs some system applications, processes or services that provide services for foreground applications and/or background applications.

In the process of displaying the user interface shown in FIG. 5B , the electronic device 100 may detect a certain user operation, and in response to the operation, the electronic device 100 may display a running application. For example, as shown in FIG. 5B , the electronic device 100 may detect that the user swipes up from the bottom of the screen. In response to the above operations, the electronic device 100 may display the user interface shown in FIG. 5C .

As shown in FIG. 5C , the user interface includes page 431 . The page 431 may represent a gallery application (Photos) that is executed in response to the user operation shown in FIG. 5A and FIG. 5B . In addition, the user interface also includes page 432 and page 433 . Page 432 may represent a running browser application (Browser); page 433 may represent a running settings application (Settings).

Not limited to the above browser application and setting application, the electronic device 100 can also run other more application programs, that is, the user interface shown in FIG. 5C can also display more pages.

The above-mentioned gallery application (the application that the user is directly operating) may be referred to as a foreground application. The above browser application, setting application and other applications that are not currently directly operated by the user may be referred to as background applications.

The latency requirements of different IO requests may be different. Generally, IO requests initiated by applications with low latency tolerance have higher latency requirements. The latency tolerance of foreground applications is low. Therefore, the latency requirement of the IO request initiated by the foreground application is high, that is, the electronic device 100 has a high priority for processing such IO request. The electronic device 100 needs to process this type of IO request as quickly as possible. Compared with the IO request initiated by the above-mentioned foreground application, the processing priority of the IO request initiated by the background application is relatively low. For example, the priority of the IO request initiated by the above gallery application is higher than that of the IO request initiated by the above browser application and setting application.

In this way, after receiving multiple IO requests, the electronic device 100 can process the above multiple IO requests in order from high to low according to the processing priorities of different IO requests, so as to make the IO requests with different delay requirements as much as possible Both can obtain the response of the electronic device 100 within the respective delay requirements.

FIG. 6 exemplarily shows a flowchart of the electronic device 100 implementing the input and output processing method provided by the embodiment of the present application.

S201: The electronic device 100 processes IO requests of different priorities according to a preset scheduling ratio.

After completing the initialization, the electronic device 100 may allocate IO resources to IO requests of different priorities according to a preset scheduling ratio, that is, to determine the number of IO requests of different priorities processed by the electronic device 100 in one processing cycle.

Specifically, with reference to FIG. 3A , the IO request initiated by the application layer can be delivered to the kernel layer Block. Generally, Block will receive multiple IO requests at the same time. After receiving the IO request, the electronic device 100 may determine the latency requirement of the IO request. For IO requests with high latency requirements, that is, IO requests that require an early response, Block will give priority to delivering the IO request to the storage driver of the target storage of the IO request.

In order to prevent low-priority IO requests from always preempting IO resources by high-priority IO requests, the electronic device 100 can process IO requests with different priorities according to a preset scheduling ratio to ensure that low-priority IO requests do not will be blocked.

For example, as shown in FIG. 4A , within a unit time, the electronic device 100 can sequentially process 5 high-priority (A) IO requests, 3 medium-priority (B) IO requests, and 2 low-priority (B) IO requests. C) IO request. Within the unit time, after the electronic device 100 processes the high-priority IO requests, even if there are other high-priority IO requests in the block, the electronic device 100 will first process some medium-priority and low-priority IO requests , so as to avoid blocking of IO requests with medium and low priorities, causing the application or process that initiated the IO request to be stuck.

Under the condition that IO requests with lower priority are not blocked, the electronic device 100 will allocate more IO resources to IO requests with high priority as much as possible. This is often because the applications or processes that initiate high-priority IO requests are mostly directly related to user operations. If high-priority IO requests are not guaranteed to have high response efficiency as much as possible, the user experience will be greatly reduced.

S202: The electronic device 100 updates the average response time of IO requests of different priorities in real time.

In the process of processing IO requests of different priorities according to the preset scheduling ratio, the electronic device 100 can detect the average response time of the IO requests of each priority in real time.

As shown in FIG. 3A , the electronic device 100 may be preset with a delay detection module 211 . The delay detection module 211 can calculate the average response time of the IO requests of the same priority during the process of the electronic device 100 processing the IO requests of different priorities.

Specifically, after an application-layer application or process initiates an IO request, the delay detection module 211 may determine the time stamp at which the above-mentioned application or process initiated the IO request, and mark it as the initiating time of the IO request. After the storage device of the electronic device 100 performs the input and output operations corresponding to the IO request according to the instruction of the IO request, the application layer can receive the processing result returned by the device layer. At this time, the delay detection module 211 can determine the time when the electronic device 100 finishes processing the IO request according to the above processing result. For example, the delay detection module 211 may determine that the time when the application layer receives the above processing result is the time when the electronic device 100 finishes processing the IO request (response time). According to the above-mentioned initiation time and response time, the delay detection module 211 can determine the response time for the electronic device 100 to process the IO request.

With reference to the schematic diagram shown in FIG. 4A , when the electronic device 100 executes five IO requests with priority A in the scheduling queue Q, the delay detection module 211 can determine the response time of the five IO requests according to the above method. Then, the delay detection module 211 may determine the average response time (AvgT1 ) of the five IO requests with priority A.

Similarly, when executing the IO requests with priorities B and C in the scheduling queue Q, the delay detection module 211 can sequentially determine the average response time (AvgT2) of the IO requests with the priority B, and the IO requests with the priority C in turn. Average response time for requests (AvgT3). Generally, AvgT1<AvgT2<AvgT3.

S203: The electronic device 100 determines whether to adjust the scheduling ratio according to the average response time.

After determining the average response time of IO requests of different priorities, the electronic device 100 may determine whether the average response time of high-priority IO requests is higher than the average response time of low-priority IO requests according to the above average response time.

When the average response time of the high-priority IO requests is higher than the average response time of the low-priority IO requests, the electronic device 100 may determine that the IO resources currently allocated by the system to the high-priority IO requests cannot satisfy the high-priority IO requests. need. Therefore, the electronic device 100 needs to allocate more IO resources for high-priority IO requests to improve the average response time of the high-priority IO requests.

With reference to the schematic diagram shown in FIG. 4A , if AvgT1 >AvgT2 , it means that the average response time of the electronic device for processing Type A IO requests is longer than the average response time for the electronic device to process Type B IO requests. This is inconsistent with the expected shortest average response time for Class A IO requests. The application program is: the average response time of the electronic device 100 for processing IO requests initiated by system applications is shorter than the average response time for processing IO requests initiated by foreground applications. This is not what the user expected.

Therefore, when the above situation occurs, the electronic device 100 may allocate more IO resources for the A-type IO request, so as to improve the average response time of the high-priority IO request. Specifically, the electronic device 100 can increase the scheduling ratio of class A IO requests, so that the electronic device 100 can process more class A IO requests per unit time. In this way, the average response time for Class A IO requests can be reduced.

For example, in the scenario where the scheduling ratio is 5:3:2, 5 class A IO requests, 3 class B IO requests, and 2 class C IO requests are processed in 1 ms, if AvgT2<AvgT1<AvgT3, then The electronic device 100 can increase the scheduling ratio of Class A IO requests from 5 to 6, and correspondingly reduce the ratio of Class B IO requests from 3 to 2, that is, the adjusted scheduling ratio is 6:2 :2. Further, to provide more IO resources for class A IO requests, the electronic device 100 may also adjust the scheduling ratio to 7:2:1.

Similarly, if AvgT1<AvgT3<AvgT2, the electronic device 100 can allocate part of the IO resources of the C-type IO request to the B-type IO request, so as to increase the IO resource occupancy rate of the B-type IO request, thereby improving the electronic device 100 to handle the B-type IO request. The efficiency of the request reduces the average response time of class B IO requests.

Here, the electronic device 100 does not adjust the high-priority IO resource occupancy rate. For example, the electronic device 100 does not allocate IO resources belonging to class A IO requests to class B IO requests. This is because: reducing the IO resource occupancy rate of high-priority IO requests and increasing the IO resource occupancy rate of low-priority IO requests, it is very likely that the average response time of high-priority IO requests will be lower than that of low-priority IO requests. Average response time for priority IO requests.

It can be understood that, if the average response time of high-priority IO requests is lower than the average response time of low-priority IO requests, the electronic device 100 may maintain the current scheduling ratio.

In some embodiments, the electronic device 100 may also determine whether to adjust the preset scheduling ratio according to whether the response time of a single high-priority IO request is lower than the response time of a low-priority IO request. In some embodiments, the electronic device 100 may also use the longest response time of the high-priority IO requests to compare with the shortest response time of the low-priority IO requests. This embodiment of the present application does not limit this.

S204: The electronic device 100 checks the load of the central processing unit to determine whether to limit the return rate of low-priority IO requests.

Optionally, while adjusting the scheduling ratio according to the average response time, the electronic device 100 may also check the load of the central processing unit to determine whether to limit the return rate of low-priority IO requests.

The electronic device 100 can periodically detect the load of a central processing unit (CPU) to determine whether the CPU is busy. If the CPU is busy, the electronic device 100 may limit the return rate of the processing result of the low-priority IO request.

In this way, before the electronic device 100 receives the processing result of processing the low-priority IO request, the activity of the application or process that initiates the IO request will decrease. Further, the CPU resource occupancy rate of the application or process will be reduced. Therefore, the electronic device 100 can provide more CPU resources for high-priority IO requests, thereby improving the efficiency of the electronic device 100 in processing high-priority IO requests.

A load threshold may be preset in the electronic device 100 . The electronic device 100 may periodically acquire the current load of the CPU. Then, the electronic device 100 compares the above-mentioned current load with a preset load threshold. If the above-mentioned current load does not exceed the load threshold, the electronic device may confirm that the CPU is not busy. At this time, the electronic device 100 may not limit the return rate of low-priority IO requests. If the above-mentioned current load exceeds the load threshold, the electronic device may confirm that the CPU is busy. At this time, the electronic device 100 can limit the return rate of low-priority IO requests, reduce the activity of priority applications or processes, and provide more CPU resources for high-priority applications or processes.

Specifically, the electronic device 100 determines whether to limit the return rate of low-priority IO processing results, and the process of determining which priorities to limit the return rate of IO processing results can refer to the introduction in FIG.

Taking the processing result of IO3 (priority IO request) as an example, after processing IO3, the electronic device 100 may generate the processing result of the IO request. The processing result can be returned to Block according to the original path. At this time, the Block can be delayed for a period of time, for example, by 0.1 ms, and then return the above processing result to the APP2 that initiated the IO request at the application layer.

Since the time for APP2 to receive the processing result of IO3 is delayed, the running state of APP2 is also slowed down accordingly, that is, the activity of APP2 is reduced. In this way, the occupation of CPU resources by APP2 is also reduced, so that the foreground application (eg, APP1 ) can obtain more CPU resources, thereby improving the efficiency of the electronic device 100 in processing APP1 .

In addition, processing from the return side to limit the return rate of IO requests can not only reduce the activity of low-priority applications or processes, so that foreground applications or processes can obtain more CPU resources, but also make full use of IO resources.

Specifically, after detecting a low-priority IO request initiated by an application or process, the electronic device 100 directly limits the rate at which the IO request is sent to the block or storage device. Then, in the case where IO resources are not tight, that is, the number of IO requests received by blocks and storage devices does not reach the maximum limit of their own processing, the utilization rate of IO resources will be significantly reduced, which will cause IO resources to a certain extent. waste.

In the embodiment of the present application, since the electronic device 100 limits the return rate of the IO request after responding to the low-priority IO request, this method can not only make full use of the existing IO resources, but also avoid the waste of the IO resources.

It can be understood that, in the process described in S202, the average response time of the IO requests with different priorities determined by the electronic device 100 is related to the return restriction policy of the return control module 214 in S204. In this embodiment of the present application, in the process of the delay detection module 211 detecting the average response time of IO requests with different priorities in a cycle, the scheduling ratio used by the group quota module 213 and the return control strategy used by the return control module 214 It is actually determined by the average response time of IO requests of different priorities detected last time.

S205: The electronic device 100 continues to process IO requests of different priorities according to the adjusted scheduling ratio and return rate.

After determining the new scheduling ratio and determining whether to limit the return rate of low-priority IO requests, that is, the new scheduling ratio and the new return control strategy. The electronic device 100 can process subsequent IO requests waiting to be processed according to a new policy, that is, a new scheduling ratio and a return rate of IO requests.

For example, in a scenario where the scheduling ratio is changed to 6:2:2, the electronic device 100 can process 6 class A IO requests, 2 class B IO requests, and 2 class C IO requests within 1 ms. If the CPU load is too high, the electronic device 100 may also limit the processing result of the type B IO request and/or the return rate of the processing result after the type C IO request, for example, delay 0.1ms to upload the above-mentioned low-priority processing result and so on. Then, the delay detection module 211 can recalculate the response time of each IO request and the average response time of the IO requests of the same priority, so as to guide the group matching module 213 whether to update the scheduling ratio again.

In some embodiments, the electronic device 100 may also readjust the scheduling ratio and the return control strategy at intervals of one or more cycles. This embodiment of the present application does not limit this.

By implementing the input and output request processing method provided by the embodiment of the present application, the electronic device 100 can detect the average response time of IO requests of different priorities in real time. When the average response time of high-priority IO requests is higher than the average response time of low-priority IO requests, the electronic device 100 can adjust the ratio of IO resources in time, thereby reducing the average response time of high-priority IO requests. Avoid too long response time to affect the user experience.

In addition to directly increasing the occupancy rate of IO resources of high-priority IO requests, the electronic device 100 can also reduce the activity of applications with low-latency requirements by limiting the return rate of low-priority IO requests, so as to save time Applications with high latency requirements provide more CPU resources to improve the efficiency of the electronic device 100 in processing the application requests. At the same time, limiting low-priority IO requests from the return side can also avoid wasting IO resources.

In the examples of this application:

An IO request initiated by the application layer and the input or read operation indicated by the request can be called an IO service.

In S201, the multiple IO services with priorities A, B, and C obtained by the read-write scheduling module 215 from the cache queues A, B, and C according to the preset scheduling ratio may be referred to as "fetching from multiple queues" Multiple IO Services".

In S202, the average response time of different priorities compared by the electronic devices can be regarded as "the processing delay of one IO service".

In S204, returning the low-priority IO service to the application that initiated the IO service after a delay of 0.1 ms may be referred to as "returning the processing result of the IO service with the low IO processing priority to the initiating Low IO processing priority IO business applications".

In FIG. 4C, the threshold H1 may be referred to as a first threshold.

In S201, the scheduling ratio of 5:3:2 may be referred to as the first ratio; in S203, the scheduling ratio of 6:2:2 may be referred to as the second ratio.

As used in the specification of this application and the appended claims, the singular expressions "a," "an," "the," "above," "the," and "the" are intended to also include Plural expressions unless the context clearly dictates otherwise. It will also be understood that, as used in this application, the term "and/or" refers to and includes any and all possible combinations of one or more of the listed items. As used in the above embodiments, the term "when" may be interpreted to mean "if" or "after" or "in response to determining..." or "in response to detecting..." depending on the context. Similarly, depending on the context, the phrases "in determining..." or "if detecting (the stated condition or event)" can be interpreted to mean "if determining..." or "in response to determining..." or "on detecting (the stated condition or event)" or "in response to the detection of (the stated condition or event)".

In the above-mentioned embodiments, it may be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented in software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer may be a general purpose computer, special purpose computer, computer network, or other programmable device. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be downloaded from a website site, computer, server, or data center Transmission to another website site, computer, server, or data center by wire (eg, coaxial cable, optical fiber, digital subscriber line) or wireless (eg, infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, a data center, or the like that includes an integration of one or more available media. The usable media may be magnetic media (eg, floppy disks, hard disks, magnetic tapes), optical media (eg, DVDs), or semiconductor media (eg, solid state drives), and the like.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented. The process can be completed by instructing the relevant hardware by a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed , which may include the processes of the foregoing method embodiments. The aforementioned storage medium includes: ROM or random storage memory RAM, magnetic disk or optical disk and other mediums that can store program codes.

Claims (11)

1. an input and output IO processing method, the method is applied to electronic equipment, it is characterized in that, described method comprises: For the first time, multiple IO services are taken from multiple queues; among the multiple queues, one queue is used to store one or more IO services with the same IO processing priority, and the IO processing of IO services stored in different queues has priority. different levels; Perform IO processing on the multiple IO services taken out according to the IO processing priority; Determine the processing delay of the multiple IO services in the IO processing, and the processing delay of one IO service is used to indicate that the one IO service is detected from the arrival of the one IO service to when the application receives the one IO service. Time consuming of IO processing result of IO business; A second time, taking out multiple IO services from the multiple queues; the second time is after the first time; If the processing delay of IO services with high IO processing priority is longer than the processing delay of IO services with low IO processing priority, the proportion of high-priority IO services among the multiple IO services retrieved at the second time is higher than that of all IO services. The proportion of high-priority among multiple IO services retrieved at the first time. 2. The method according to claim 1, wherein, at the second time, after taking out a plurality of IO services from the plurality of queues, the method further comprises: After the processing result of the IO service with the low IO processing priority is retained for the first time period, it is returned to the application that initiated the IO service with the low IO processing priority. 3. method according to claim 2, is characterized in that, after the processing result of low-priority IO request is held for a first duration, return to the application program that initiates described low-priority IO request, specifically comprises: determining the current load of the central processing unit CPU of the electronic device; If the current load is higher than a first threshold, the processing result of the low-priority IO request is held for a first time, and then returned to the application that initiated the low-priority IO request, where the first threshold is a predetermined threshold. set. 4. The method according to any one of claims 1-3, wherein the first time is to take out multiple IO services from multiple queues, specifically comprising: at the first time, according to the first time The ratio takes out multiple IO services from multiple queues; The second time, taking out multiple IO services from the multiple queues specifically includes: at the second time, taking out multiple IO services from the multiple queues according to the second ratio. 5. The method of claim 4, wherein the number of proportional terms of the first ratio is equal to the number of proportional terms of the second ratio. 6. The method according to claim 5, wherein the value of the first proportional term of the first ratio is lower than the value of the first proportional term of the second ratio, the first proportional term It is used to indicate the number of IO services that obtain the high IO processing priority. 7. The method according to any one of claims 4-6, wherein the taking out multiple IO services from multiple queues according to the first ratio specifically includes: The number of the retrieved multiple IO services is equal to or greater than the sum of the values of the proportional items of the first ratio, and the ratio of the number of IO services with different IO processing priorities among the multiple IO services retrieved is equal to the first ratio is consistent; Or, the quantity of the multiple IO services retrieved is less than the sum of the numerical values of the proportional items of the first ratio. 8. The method according to any one of claims 1-7, wherein the processing delay specifically comprises: Time-consuming from detecting the arrival of the one IO business to the application receiving the IO processing result of the one IO business; Or, the average time-consuming time from detecting the arrival of a plurality of the one IO services to the application receiving the IO processing results of the plurality of the one IO services, and the plurality of the one IO services are related to The one IO service is an IO service with the same IO processing priority. 9. An electronic device comprising one or more processors and one or more memories; wherein the one or more memories are coupled to the one or more processors, the one or more memories A memory is used to store computer program code comprising computer instructions which, when executed by the one or more processors, cause the method of any of claims 1-8 to be performed. 10. A computer program product comprising instructions which, when run on an electronic device, cause the electronic device to perform the method of any of claims 1-8. 11. A computer-readable storage medium comprising instructions, wherein the instructions, when executed on an electronic device, cause the method of any one of claims 1-8 to be performed.

Images