WO2024021485A1 - Processor performance adjustment method and apparatus, electronic device and storage medium - Google Patents

Processor performance adjustment method and apparatus, electronic device and storage medium Download PDF

Info

Publication number
WO2024021485A1
WO2024021485A1 PCT/CN2022/141792 CN2022141792W WO2024021485A1 WO 2024021485 A1 WO2024021485 A1 WO 2024021485A1 CN 2022141792 W CN2022141792 W CN 2022141792W WO 2024021485 A1 WO2024021485 A1 WO 2024021485A1
Authority
WO
WIPO (PCT)
Prior art keywords
processor
points
current
performance
computing power
Prior art date
Application number
PCT/CN2022/141792
Other languages
French (fr)
Chinese (zh)
Inventor
闫维金
张帆
吴健
刘智
淦飞
王庆兆
Original Assignee
天翼云科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 天翼云科技有限公司 filed Critical 天翼云科技有限公司
Publication of WO2024021485A1 publication Critical patent/WO2024021485A1/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46Multiprogramming arrangements
    • G06F9/50Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5027Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44Arrangements for executing specific programs
    • G06F9/445Program loading or initiating
    • G06F9/44505Configuring for program initiating, e.g. using registry, configuration files
    • G06F9/4451User profiles; Roaming
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44Arrangements for executing specific programs
    • G06F9/455Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533Hypervisors; Virtual machine monitors
    • G06F9/45558Hypervisor-specific management and integration aspects
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44Arrangements for executing specific programs
    • G06F9/455Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533Hypervisors; Virtual machine monitors
    • G06F9/45558Hypervisor-specific management and integration aspects
    • G06F2009/4557Distribution of virtual machine instances; Migration and load balancing
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02DCLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00Energy efficient computing, e.g. low power processors, power management or thermal management

Definitions

  • the present invention relates to the field of computer technology, and specifically to processor performance adjustment methods, devices, electronic equipment and storage media.
  • Cloud host is an important part of cloud computing in infrastructure applications. It is an information technology infrastructure capacity rental service that integrates computing, storage and network resources. It can provide users with on-demand usage and on-demand payment capabilities based on the cloud computing model. Server rental service.
  • the baseline performance of the cloud host is determined by the specifications of the cloud host. The baseline performance is the processor performance that the cloud host can continuously and stably provide.
  • embodiments of the present invention provide processor performance adjustment methods, devices, electronic devices, and storage media to flexibly adjust processor performance and improve user experience.
  • an embodiment of the present invention provides a processor performance adjustment method, which method includes:
  • the current score of the processor is adjusted to adjust the performance of the processor.
  • the processor performance adjustment method recharges points through a point recharge instruction to determine the current points of the processor.
  • the processor determines the operating performance of the processor and the size of the preset computing power threshold, and performs The accumulation or consumption of points is to adjust the current points of the processor, so that when the processor is running at a higher than the preset computing power threshold, the performance of the processor is improved by consuming the accumulated points.
  • This method can flexibly adjust the processor performance and improve user experience.
  • determining the current points of the processor in response to a point recharge instruction includes:
  • control group In response to the creation instruction of the control group, create a control group of the processor, and the control group corresponds to the processor one-to-one;
  • a point parameter is set in the control group of the processor to determine the current point of the processor.
  • setting points parameters in the control group of the processor to determine the current points of the processor includes:
  • the current points of the processor are obtained, and the recharge points are accumulated into the current points to determine the current points of the processor.
  • the method before obtaining the current operating performance of the processor, comparing the current operating performance with a preset computing power threshold, and obtaining the comparison result, the method further includes:
  • the preset computing power threshold is determined based on the performance of the processor.
  • adjusting the current points of the processor according to the comparison result to adjust the performance of the processor includes:
  • the current points are accumulated to increase the computing power of the processor.
  • accumulating the current points includes:
  • the current points are compared with the points upper limit threshold. When the current points exceed the points upper limit threshold, the current points are adjusted to the points upper limit threshold.
  • the method further includes:
  • an embodiment of the present invention provides a processor performance adjustment device, including:
  • a points recharge module configured to determine the current points of the processor in response to the points recharge instruction
  • a performance judgment module used to obtain the current operating performance of the processor, compare the current operating performance with the preset computing power threshold, and obtain a comparison result
  • a score adjustment module configured to adjust the current score of the processor according to the comparison result to adjust the performance of the processor
  • an embodiment of the present invention provides an electronic device, including: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor By executing the computer instructions, the processor performance adjustment method described in the first aspect or any implementation manner of the first aspect is executed.
  • embodiments of the present invention provide a computer-readable storage medium that stores computer instructions, and the computer instructions are used to cause the computer to execute the first aspect or any of the first aspects.
  • Figure 1 is a flow chart of a processor performance adjustment method according to an embodiment of the present invention
  • Figure 2 is a flow chart of a method for determining the current score of a processor according to an embodiment of the present invention
  • Figure 3 is a flow chart of a method for adjusting processor performance according to an embodiment of the present invention.
  • Figure 4 is a schematic diagram of a processor performance adjustment method according to an embodiment of the present invention.
  • Figure 5 is a structural block diagram of a processor performance adjustment device according to an embodiment of the present invention.
  • FIG. 6 is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention.
  • Control group is a mechanism provided by the Linux kernel that can limit the resources used by a single or multiple processes, and can achieve fine-grained control over resources such as processors and memory.
  • this application uses the processor points method to add parameters to the cgroup, thereby controlling points and adjusting the performance of the processor.
  • an embodiment of a processor performance adjustment method is provided. It should be noted that the steps shown in the flow chart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and, Although a logical sequence is shown in the flowcharts, in some cases the steps shown or described may be performed in a sequence different from that herein.
  • FIG. 1 is a flow chart of a processor performance adjustment method according to an embodiment of the present invention, as shown in Figure 1 , the process includes the following steps:
  • the configuration information includes the point configuration of the processor in the cloud host.
  • the point configuration of the processor includes the upper point threshold of the processor, that is, the points that the processor can accumulate. Maximum points value.
  • the cloud host When the cloud host is turned on, there may still be points in the processor itself.
  • the current points of the processor can be determined by adding the recharged points with the existing points.
  • the preset computing power threshold is set in advance based on the processor's own specifications and performance, which is the baseline performance.
  • the cloud host When the cloud host is running, it may run in a mode that is lower than the preset computing power threshold, or it may run in a mode that exceeds the preset computing power threshold.
  • the comparison result is obtained by comparing the current operating performance with the preset computing power threshold.
  • the current points of the processor When the current operating performance is less than the preset computing power threshold, that is, when the cloud host is running in a mode lower than the baseline performance, the current points of the processor will increase with the passage of time, that is, the accumulated current points will not exceed the preset Set the upper limit of points threshold.
  • the current operating performance is greater than the preset computing power threshold, that is, when the cloud host is running in a mode higher than the baseline performance, and the processor usage reaches the quota, you can use the accumulated current points to additionally use the processor computing power. Until the points are consumed, the processor's computing power will fall back to the quota value until points are accumulated again or points are recharged.
  • the processor performance adjustment method recharges points through a point recharge instruction to determine the current points of the processor.
  • the processor determines the operating performance of the processor and the size of the preset computing power threshold, and performs
  • the accumulation or consumption of points means adjusting the current points of the processor, so that when the processor is running higher than the preset computing power threshold, it can improve the performance of the processor by consuming the accumulated points.
  • This method can flexibly adjust the processing server performance and improve user experience.
  • FIG. 1 is a flow chart of the method of determining the current points of the processor according to this embodiment, as shown in Figure 2 As shown, the process includes the following steps:
  • control group In response to the creation instruction of the control group, create a control group of the processor, and the control group corresponds to the processor one-to-one.
  • the limit for virtual processor threads is to create a cgroup for each virtual processor and set it in the virtual processor's cgroup.
  • the points value is written into the parameters of the point recharge instruction, that is, the points are recharged to the processor, thereby determining the recharge points to the processor.
  • the method before comparing the current running performance with the preset computing power threshold and obtaining the comparison result, the method further includes: obtaining the performance of the processor, and responding to the performance threshold configuration instruction for the processor, based on the performance of the processor Determine the preset computing power threshold.
  • the preset computing power threshold is the baseline performance.
  • FIG. 3 is a flow chart of the method for adjusting processor performance according to this embodiment, as shown in Figure 3. The process includes the following steps:
  • the current points of the processor When the current operating performance is less than the preset computing power threshold, that is, when the cloud host is running in a mode lower than the baseline performance, the current points of the processor will increase over time, that is, the current points will be accumulated.
  • the processor usage When the current operating performance is greater than the preset computing power threshold, that is, when the cloud host is running in a mode higher than the baseline performance, and the processor usage reaches the quota, you can use the accumulated current points to additionally use the processor computing power. Until the points are consumed, the processor's computing power will fall back to the quota value until points are accumulated or recharged again.
  • This embodiment provides a specific embodiment of a processor performance adjustment method, as shown in Figure 4.
  • the integration of the processor is controlled by adding three parameters to the cgroup.
  • the parameters are as follows:
  • cpu.cfs_burst_ns Indicates the maximum points that can be accumulated, that is, the upper limit threshold of points. The parameter can be read and written. 0 (default value) means that the processor credit mechanism is not enabled. Setting other parameters means that the credit mechanism is enabled.
  • cpu.cfs_remain_time Indicates the currently available processor points, that is, the current points of the processor.
  • the parameter is read-only.
  • cpu.cfs_recharge_time Indicates the processor points recharge parameters, that is, recharge points. The parameters can be read and written. Writing a number to this interface indicates recharging processor points.
  • Os OpenStack
  • libvirt virtualization management software
  • the OS calls the interface of libvirt to configure the processor points.
  • the points function is enabled for the created cloud host, its configuration information includes the points configuration of the processor, such as:
  • global_burst is the upper limit threshold of points for the processor. This configuration in the xml indicates that the cloud host has enabled the points mechanism. When the cloud host is turned on, the remaining points of the cloud host will be restored by calling the recharge interface of libvirt.
  • libvirt supports limiting the overall processor usage of the virtual machine process (global_period/global_quota), the processor usage of the vcpu (virtual processor) thread (period/quota), and the processor usage of other QEMU threads (such as io threads), etc. wait.
  • libvirt limits the overall utilization of the virtual machine by modifying the processor parameters under the virtual machine cgroup.
  • the restriction on vcpu threads is to create a cgroup (called vcpu cgroup) for each vcpu and set the processor parameters in the vcpu group. .
  • processor points are limited for the entire virtual machine process, when implementing the libvirt control processor points function, you only need to modify the cpu.cfs_burst_ns and cpu.cfs_recharge_time parameters under the virtual machine cgroup.
  • the processor points mechanism can be turned on by modifying the cpu.cfs_burst_ns parameter.
  • the CPU points slowly accumulate until the points reach the upper limit of cpu.cfs_burst_ns and stop accumulating.
  • the process is busy, and when the processor usage reaches the quota, you can use the accumulated points to use additional processor computing power.
  • the processor usage will fall back to the quota value until there are more points available. .
  • cgroup When recharging processor points for a process, you can directly write the point value into the cpu.cfs_recharge_time parameter. At this time, cgroup will accumulate the value of cpu.cfs_recharge_time to cpu.cfs_remain_time. If the accumulated value of cpu.cfs_remain_time exceeds the cpu.cfs_burst_ns limit, Then set the cpu.cfs_remain_time value to cpu.cfs_burst_ns.
  • libvirt detects the QEMU process termination event, it obtains the remaining points in the cgroup of the virtual machine, and then reports the remaining points to the OS through the VIR_DOMAIN_EVENT_ID_TUNABLE event.
  • the data reported by the event received by the OS is as follows:
  • the OS listens to this event and persists the remaining points in the event processing interface.
  • the current score of the processor in the virtual machine is obtained, the current score is saved, and the current score is added to the target virtual machine.
  • the points function is enabled on the cloud host before migration and there are remaining points, then after the migration, the points function must be enabled on the target cloud host and the remaining points restored to ensure that the migration operation does not affect the points of the virtual machine.
  • the cloud host migration operation is initiated by the OS. If it is a live migration, the migration process is mainly controlled by libvirt. In the case of cold migration, the migration process is mainly controlled by the OS. No matter which party controls it, the remaining points need to be saved first. After the target cloud host is started, the remaining points are recharged to the target cloud host.
  • the target cloud host is the target virtual machine.
  • the cloud host configuration information in libvirt's memory records the global_burst configuration that enables processor credits. Therefore, libvirt automatically sets the cgroup to enable the credits function when creating the target cloud host.
  • libvirt migrates the cloud host's data (memory data, device status, etc.) according to normal logic. After the migration is completed, libvirt immediately pauses the cloud host, obtains the remaining points of the processor in the virtual machine, that is, the current points, and adds The remaining points are recharged to the destination cloud host. After the points recharge is completed, restore the target cloud host.
  • the cloud host persists the remaining points into the database when it shuts down. When it is turned on again after the migration, the OS listens to the resume event and recharges the remaining points to the target virtual machine.
  • the processor performance adjustment method provided by this application can accumulate the computing power of the cloud host through points when it is idle, and consume the accumulated processor points during the period when sudden performance is required to achieve excess use of the processor computing power. When the accumulated points are exhausted, the processor computing power can be limited to restore it to the baseline performance range. In addition to accumulating points during low-performance work, it can also be recharged through points, allowing users to recharge points according to actual needs. In addition, cloud host configuration, migration or power-on/off will not affect the processor points. It reduces the user's usage costs to a certain extent. There is no need to upgrade cloud hosts or purchase high-specification cloud hosts for occasional high processor usage services, improve resource utilization, and more flexibly configure and limit processor usage. performance, improving user experience.
  • module may be a combination of software and/or hardware that implements a predetermined function.
  • the apparatus described in the following embodiments is preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
  • This embodiment provides a processor performance adjustment device, as shown in Figure 5, including:
  • a points recharge module used to determine the current points of the processor in response to the points recharge instruction
  • a performance judgment module used to obtain the current operating performance of the processor, compare the current operating performance with the preset computing power threshold, and obtain a comparison result
  • a score adjustment module configured to adjust the current score of the processor according to the comparison result to adjust the performance of the processor.
  • the points recharge module includes:
  • a control group establishment subunit configured to create a control group of the processor in response to a control group creation instruction, where the control group corresponds to the processor one-to-one;
  • the current points determination subunit is configured to set points parameters in the control group of the processor in response to a point recharge instruction to determine the current points of the processor.
  • the current integral determination subunit includes:
  • the device further includes:
  • a computing power threshold determination module is configured to obtain the performance of the processor; in response to a performance threshold configuration instruction for the processor, determine the preset computing power threshold based on the performance of the processor.
  • the points adjustment module includes:
  • a points consumption subunit configured to consume the current points when the current operating performance exceeds the preset computing power threshold
  • the computing power improvement subunit is used to accumulate the current points when the current operating performance does not reach the preset computing power threshold, so as to improve the computing power of the processor.
  • the computing power improvement subunit is also used to:
  • the current points are compared with the points upper limit threshold. When the current points exceed the points upper limit threshold, the current points are adjusted to the points upper limit threshold.
  • the device further includes:
  • a points migration module configured to obtain the current points of the processor when the virtual machine migrates data to the target virtual machine, save the current points, and add the current points to the target virtual machine.
  • the processor performance adjustment device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC circuit, a processor and memory that executes one or more software or fixed programs, and/or others that can provide the above functions. device.
  • An embodiment of the present invention also provides an electronic device having the processor performance adjustment device shown in Figure 5 above.
  • Figure 6 is a schematic structural diagram of an electronic device provided by an optional embodiment of the present invention.
  • the electronic device may include: at least one processor 601, such as a CPU (Central Processing Unit, Central Processing Unit). processor), at least one communication interface 603, memory 604, and at least one communication bus 602.
  • the communication bus 602 is used to realize connection communication between these components.
  • the communication interface 603 may include a display screen (Display) and a keyboard (Keyboard), and the optional communication interface 603 may also include a standard wired interface and a wireless interface.
  • the memory 604 may be a high-speed RAM memory (Random Access Memory, volatile random access memory) or a non-volatile memory (non-volatile memory), such as at least one disk memory.
  • the memory 604 may optionally be at least one storage device located remotely from the aforementioned processor 601.
  • the processor 601 can be combined with the device described in FIG. 5 , the memory 604 stores an application program, and the processor 601 calls the program code stored in the memory 604 to execute any of the above method steps.
  • the communication bus 602 may be a peripheral component interconnect (PCI) bus or an extended industry standard structure (extended industry standard architecture (referred to as EISA) bus, etc.
  • PCI peripheral component interconnect
  • EISA extended industry standard architecture
  • the communication bus 602 can be divided into an address bus, a data bus, a control bus, etc. For ease of presentation, only one thick line is used in Figure 6, but it does not mean that there is only one bus or one type of bus.
  • the memory 604 may include volatile memory (English: volatile memory), such as random access memory (English: random-access memory). memory, abbreviation: RAM); memory can also include non-volatile memory (English: non-volatile memory), such as flash memory (English: flash memory), hard disk (English: hard disk drive, abbreviation: HDD) or solid state Hard disk (English: solid-state drive, abbreviation: SSD); the memory 604 may also include a combination of the above types of memory.
  • volatile memory such as random access memory (English: random-access memory).
  • RAM random access memory
  • memory abbreviation: RAM
  • non-volatile memory such as flash memory (English: flash memory), hard disk (English: hard disk drive, abbreviation: HDD) or solid state Hard disk (English: solid-state drive, abbreviation: SSD); the memory 604 may also include a combination of the above types of memory.
  • the processor 601 may be a central processing unit (English: central processing unit, abbreviation: CPU), a network processor (English: network processor, abbreviation: NP) or a combination of CPU and NP.
  • CPU central processing unit
  • NP network processor
  • the processor 601 may further include a hardware chip.
  • the above-mentioned hardware chips can be application-specific integrated circuits (English: application-specific integrated circuit, abbreviation: ASIC), programmable logic devices (English: programmable logic device (abbreviation: PLD) or a combination thereof.
  • the above-mentioned PLD can be a complex programmable logic device (English: complex programmable logic device, abbreviation: CPLD), a field-programmable gate array (English: field-programmable gate array, abbreviation: FPGA), a general array logic (English: generic array logic, abbreviation: GAL) or any combination thereof.
  • memory 604 is also used to store program instructions.
  • the processor 601 can call program instructions to implement the processor performance adjustment method shown in the embodiments of this application.
  • Embodiments of the present invention also provide a non-transitory computer storage medium.
  • the computer storage medium stores computer-executable instructions.
  • the computer-executable instructions can execute the processor performance adjustment method in any of the above method embodiments.
  • the storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), or a flash memory (Flash). Memory), hard disk (Hard Disk Drive (abbreviation: HDD) or solid-state drive (Solid-State Drive, SSD), etc.; the storage medium may also include a combination of the above types of memories.

Abstract

The present invention discloses a processor performance adjustment method and apparatus, an electronic device and a storage medium. The method comprises: in response to a point recharging instruction, determining current points of a processor; obtaining the current operating performance of the processor, and comparing the current operating performance with a preset computing power threshold to obtain a comparison result; and adjusting the current points of the processor according to the comparison result so as to adjust the performance of the processor. The method can flexibly adjust the performance of the processor and improve the user experience.

Description

处理器性能调整方法、装置、电子设备及存储介质Processor performance adjustment method, device, electronic equipment and storage medium 技术领域Technical field
本发明涉及计算机技术领域,具体涉及处理器性能调整方法、装置、电子设备及存储介质。The present invention relates to the field of computer technology, and specifically to processor performance adjustment methods, devices, electronic equipment and storage media.
背景技术Background technique
云主机是云计算在基础设施应用上的重要组成部分,是整合了计算、存储与网络资源的信息技术基础设施能力租用服务,能为用户提供基于云计算模式的按需使用和按需付费能力的服务器租用服务。云主机的基准性能由云主机的规格决定,基准性能是云主机可以持续稳定提供的处理器性能。Cloud host is an important part of cloud computing in infrastructure applications. It is an information technology infrastructure capacity rental service that integrates computing, storage and network resources. It can provide users with on-demand usage and on-demand payment capabilities based on the cloud computing model. Server rental service. The baseline performance of the cloud host is determined by the specifications of the cloud host. The baseline performance is the processor performance that the cloud host can continuously and stably provide.
技术问题technical problem
在使用时,需要限定处理器的使用率,使其不超过基准性能,否则可能会对同台宿主机上的其他云主机造成影响。当云主机中的处理器长时间以较低性能工作,偶尔需要处理器以高性能工作时,用户只能选择较高规格的云主机来满足需求,增加了用户的使用成本。When using it, you need to limit the processor usage so that it does not exceed the baseline performance, otherwise it may affect other cloud hosts on the same host. When the processor in the cloud host works at low performance for a long time and occasionally needs the processor to work at high performance, the user can only choose a cloud host with higher specifications to meet the demand, which increases the user's cost.
技术解决方案Technical solutions
有鉴于此,本发明实施例提供了处理器性能调整方法、装置、电子设备及存储介质,以灵活调整处理器的性能,提升用户体验。In view of this, embodiments of the present invention provide processor performance adjustment methods, devices, electronic devices, and storage media to flexibly adjust processor performance and improve user experience.
根据第一方面,本发明实施例提供了一种处理器性能调整方法,所述方法包括:According to a first aspect, an embodiment of the present invention provides a processor performance adjustment method, which method includes:
响应于积分充值指令,确定处理器的当前积分;In response to the points recharge instruction, determine the current points of the processor;
获取所述处理器的当前运行性能,将所述当前运行性能和预设算力阈值比较,得到比较结果;Obtain the current operating performance of the processor, compare the current operating performance with a preset computing power threshold, and obtain a comparison result;
根据所述比较结果,调整所述处理器的当前积分,以调整所述处理器的性能。According to the comparison result, the current score of the processor is adjusted to adjust the performance of the processor.
本发明实施例提供的处理器性能调整方法,通过积分充值指令,进行积分充值,确定处理器的当前积分,在处理器运行时,判断处理器的运行性能与预设算力阈值的大小,进行积分的累计或消耗,即调整处理器的当前积分,从而使得处理器在以高于预设算力阈值进行运行时,通过消耗累计的积分来提高处理器的性能,本方法可以灵活调整处理器的性能,提升用户体验。The processor performance adjustment method provided by the embodiment of the present invention recharges points through a point recharge instruction to determine the current points of the processor. When the processor is running, it determines the operating performance of the processor and the size of the preset computing power threshold, and performs The accumulation or consumption of points is to adjust the current points of the processor, so that when the processor is running at a higher than the preset computing power threshold, the performance of the processor is improved by consuming the accumulated points. This method can flexibly adjust the processor performance and improve user experience.
结合第一方面,在一种实施方式中,所述响应于积分充值指令,确定所述处理器的当前积分,包括:With reference to the first aspect, in one implementation, determining the current points of the processor in response to a point recharge instruction includes:
响应于控制组的创建指令,创建所述处理器的控制组,所述控制组与所述处理器一一对应; In response to the creation instruction of the control group, create a control group of the processor, and the control group corresponds to the processor one-to-one;
响应于积分充值指令,在所述处理器的控制组中设置积分参数,以确定所述处理器的当前积分。In response to the point recharge instruction, a point parameter is set in the control group of the processor to determine the current point of the processor.
结合第一方面,在一种实施方式中,所述响应于积分充值指令,在所述处理器的控制组中设置积分参数,以确定所述处理器的当前积分,包括:In conjunction with the first aspect, in one implementation, in response to a points recharge instruction, setting points parameters in the control group of the processor to determine the current points of the processor includes:
响应于积分充值指令,在所述处理器的控制组中设置积分参数,以确定所述处理器的充值积分;In response to the points recharge instruction, setting points parameters in the control group of the processor to determine the recharge points of the processor;
获取所述处理器的当前积分,将所述充值积分累加至所述当前积分中,以确定所述处理器的当前积分。The current points of the processor are obtained, and the recharge points are accumulated into the current points to determine the current points of the processor.
结合第一方面,在一种实施方式中,所述获取所述处理器的当前运行性能,将所述当前运行性能和预设算力阈值比较,得到比较结果之前,所述方法还包括:With reference to the first aspect, in one implementation, before obtaining the current operating performance of the processor, comparing the current operating performance with a preset computing power threshold, and obtaining the comparison result, the method further includes:
获取所述处理器的性能;Obtain the performance of the processor;
响应于对处理器的算力阈值配置指令, 基于所述处理器的性能确定所述预设算力阈值。In response to a computing power threshold configuration instruction for the processor, the preset computing power threshold is determined based on the performance of the processor.
结合第一方面,在一种实施方式中,所述根据所述比较结果,调整所述处理器的当前积分,以调整所述处理器的性能,包括:In conjunction with the first aspect, in one implementation, adjusting the current points of the processor according to the comparison result to adjust the performance of the processor includes:
当所述当前运行性能超过所述预设算力阈值,消耗所述当前积分;When the current operating performance exceeds the preset computing power threshold, the current points are consumed;
当所述当前运行性能未达到所述预设算力阈值,累计所述当前积分,以提高所述处理器的算力。When the current running performance does not reach the preset computing power threshold, the current points are accumulated to increase the computing power of the processor.
结合第一方面,在一种实施方式中,所述当所述当前运行性能未达到所述预设算力阈值,累计所述当前积分,包括:With reference to the first aspect, in one implementation, when the current operating performance does not reach the preset computing power threshold, accumulating the current points includes:
当所述当前运行性能未达到所述预设算力阈值,累计所述当前积分,并获取当前积分;When the current operating performance does not reach the preset computing power threshold, accumulate the current points and obtain the current points;
响应于积分上限指令,确定所述处理器的积分上限阈值;In response to a credit cap instruction, determining a credit cap threshold of the processor;
将所述当前积分与所述积分上限阈值比较,当所述当前积分超过所述积分上限阈值,将所述当前积分调整为所述积分上限阈值。The current points are compared with the points upper limit threshold. When the current points exceed the points upper limit threshold, the current points are adjusted to the points upper limit threshold.
结合第一方面,在一种实施方式中,所述方法还包括:In conjunction with the first aspect, in one embodiment, the method further includes:
当虚拟机将数据迁移至目标虚拟机时,获取所述虚拟机中处理器的当前积分,并保存所述当前积分;When the virtual machine migrates data to the target virtual machine, obtain the current score of the processor in the virtual machine and save the current score;
将所述当前积分添加至所述目标虚拟机。Add the current points to the target virtual machine.
根据第二方面,本发明实施例提供了一种处理器性能调整装置,包括:According to a second aspect, an embodiment of the present invention provides a processor performance adjustment device, including:
积分充值模块,用于响应于积分充值指令,确定所述处理器的当前积分;A points recharge module, configured to determine the current points of the processor in response to the points recharge instruction;
性能判断模块,用于获取所述处理器的当前运行性能,将所述当前运行性能和预设算力阈值比较,得到比较结果;A performance judgment module, used to obtain the current operating performance of the processor, compare the current operating performance with the preset computing power threshold, and obtain a comparison result;
积分调整模块,用于根据所述比较结果,调整所述处理器的当前积分,以调整所述处理器的性能A score adjustment module, configured to adjust the current score of the processor according to the comparison result to adjust the performance of the processor
根据第三方面,本发明实施例提供了一种电子设备,包括:存储器和处理器,所述存储器和所述处理器之间互相通信连接,所述存储器中存储有计算机指令,所述处理器通过执行所述计算机指令,从而执行第一方面或第一方面的任意一种实施方式中所述的处理器性能调整方法。According to a third aspect, an embodiment of the present invention provides an electronic device, including: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor By executing the computer instructions, the processor performance adjustment method described in the first aspect or any implementation manner of the first aspect is executed.
根据第四方面,本发明实施例提供了一种计算机可读存储介质,所述计算机可读存储介质存储计算机指令,所述计算机指令用于使所述计算机执行第一方面或第一方面的任意一种实施方式中所述的处理器性能调整方法、装置、电子设备及存储介质。According to a fourth aspect, embodiments of the present invention provide a computer-readable storage medium that stores computer instructions, and the computer instructions are used to cause the computer to execute the first aspect or any of the first aspects. The processor performance adjustment method, device, electronic equipment and storage medium described in one embodiment.
附图说明Description of drawings
为了更清楚地说明本发明具体实施方式或现有技术中的技术方案,下面将对具体实施方式或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图是本发明的一些实施方式,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。In order to more clearly explain the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings that need to be used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description The drawings illustrate some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without exerting any creative effort.
图1是根据本发明实施例的一种处理器性能调整方法的流程图;Figure 1 is a flow chart of a processor performance adjustment method according to an embodiment of the present invention;
图2是根据本发明实施例的确定处理器的当前积分方法的流程图;Figure 2 is a flow chart of a method for determining the current score of a processor according to an embodiment of the present invention;
图3是根据本发明实施例的调整处理器性能的方法的流程图;Figure 3 is a flow chart of a method for adjusting processor performance according to an embodiment of the present invention;
图4是根据本发明实施例的处理器性能调整方法的示意图;Figure 4 is a schematic diagram of a processor performance adjustment method according to an embodiment of the present invention;
图5是根据本发明实施例的处理器性能调整装置的结构框图;Figure 5 is a structural block diagram of a processor performance adjustment device according to an embodiment of the present invention;
图6是本发明实施例提供的电子设备的硬件结构示意图。FIG. 6 is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention.
本发明的实施方式Embodiments of the invention
为使本发明实施例的目的、技术方案和优点更加清楚,下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments These are some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the scope of protection of the present invention.
Cgroup(Control group,控制组)是Linux内核提供的一种可以限制单个或多个进程所使用资源的机制,可以对处理器、内存等资源实现精细化的控制。为了提升服务器中处理器的性能,提升用户体验,本申请采用处理器积分方法,为cgroup增加参数,从而实现对积分的控制,以便调整处理器的性能。Cgroup (Control group) is a mechanism provided by the Linux kernel that can limit the resources used by a single or multiple processes, and can achieve fine-grained control over resources such as processors and memory. In order to improve the performance of the processor in the server and improve the user experience, this application uses the processor points method to add parameters to the cgroup, thereby controlling points and adjusting the performance of the processor.
根据本发明实施例,提供了一种处理器性能调整方法实施例,需要说明的是,在附图的流程图示出的步骤可以在诸如一组计算机可执行指令的计算机系统中执行,并且,虽然在流程图中示出了逻辑顺序,但是在某些情况下,可以以不同于此处的顺序执行所示出或描述的步骤。According to an embodiment of the present invention, an embodiment of a processor performance adjustment method is provided. It should be noted that the steps shown in the flow chart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and, Although a logical sequence is shown in the flowcharts, in some cases the steps shown or described may be performed in a sequence different from that herein.
在本实施例中提供了一种处理器性能调整方法,可用于如手机、平板电脑、电脑等终端,图1是根据本发明实施例的处理器性能调整方法的流程图,如图1所示,该流程包括如下步骤:This embodiment provides a processor performance adjustment method, which can be used in terminals such as mobile phones, tablets, computers, etc. Figure 1 is a flow chart of a processor performance adjustment method according to an embodiment of the present invention, as shown in Figure 1 , the process includes the following steps:
S11,响应于积分充值指令,确定处理器的当前积分。S11. In response to the point recharge instruction, determine the current points of the processor.
为创建的云主机开启积分功能,并为其配置信息,配置信息中包含了云主机中处理器的积分配置,处理器的积分配置包括了该处理器的积分上限阈值,即处理器可以累计的最大积分值。Enable the points function for the created cloud host and configure its information. The configuration information includes the point configuration of the processor in the cloud host. The point configuration of the processor includes the upper point threshold of the processor, that is, the points that the processor can accumulate. Maximum points value.
修改虚拟机的cgroup下的积分充值指令,通过在积分充值指令中设置参数,从而为处理器充值积分。在云主机开启时,处理器中本身可能还存在积分,当充值积分时,将充值的积分与本身存在的积分进行累加,可以确定处理器的当前积分。Modify the points recharge instruction under the cgroup of the virtual machine and set parameters in the points recharge instruction to recharge points for the processor. When the cloud host is turned on, there may still be points in the processor itself. When recharging points, the current points of the processor can be determined by adding the recharged points with the existing points.
S12,获取处理器的当前运行性能,将当前运行性能和预设算力阈值比较,得到比较结果。S12: Obtain the current operating performance of the processor, compare the current operating performance with the preset computing power threshold, and obtain the comparison result.
预设算力阈值是根据处理器的自身规格和性能预先设置的,即基准性能。在云主机运行时,可能以低于预设算力阈值的模式运行,也可能超出预设算力阈值的模式运行,通过将当前运行性能和预设算力阈值进行比较,得到比较结果。The preset computing power threshold is set in advance based on the processor's own specifications and performance, which is the baseline performance. When the cloud host is running, it may run in a mode that is lower than the preset computing power threshold, or it may run in a mode that exceeds the preset computing power threshold. The comparison result is obtained by comparing the current operating performance with the preset computing power threshold.
S13,根据比较结果,调整处理器的当前积分,以调整处理器的性能。S13: According to the comparison result, adjust the current points of the processor to adjust the performance of the processor.
当当前运行性能小于预设算力阈值,即云主机以低于基准性能的模式在运行时,处理器的当前积分会随着时间流逝而增加,即累计当前积分,累计的当前积分不超过预先设置的积分上限阈值。当当前运行性能大于预设算力阈值,即云主机以高于基准性能的模式在运行时,且处理器的使用率达到配额后,可以通过消耗累计的当前积分来额外使用处理器算力,直至积分消耗完,处理器的算力将回退到配额值,直到再次积累计分或充值了积分。When the current operating performance is less than the preset computing power threshold, that is, when the cloud host is running in a mode lower than the baseline performance, the current points of the processor will increase with the passage of time, that is, the accumulated current points will not exceed the preset Set the upper limit of points threshold. When the current operating performance is greater than the preset computing power threshold, that is, when the cloud host is running in a mode higher than the baseline performance, and the processor usage reaches the quota, you can use the accumulated current points to additionally use the processor computing power. Until the points are consumed, the processor's computing power will fall back to the quota value until points are accumulated again or points are recharged.
本发明实施例提供的处理器性能调整方法,通过积分充值指令,进行积分充值,确定处理器的当前积分,在处理器运行时,判断处理器的运行性能与预设算力阈值的大小,进行积分的累计或消耗,即调整处理器的当前积分,从而使得处理器在以高于预设算力阈值进行运行时,可以通过消耗累计的积分来提高处理器的性能,本方法可以灵活调整处理器的性能,提升用户体验。The processor performance adjustment method provided by the embodiment of the present invention recharges points through a point recharge instruction to determine the current points of the processor. When the processor is running, it determines the operating performance of the processor and the size of the preset computing power threshold, and performs The accumulation or consumption of points means adjusting the current points of the processor, so that when the processor is running higher than the preset computing power threshold, it can improve the performance of the processor by consuming the accumulated points. This method can flexibly adjust the processing server performance and improve user experience.
在本实施例中提供了确定处理器的当前积分方法,可用于如手机、平板电脑、电脑等终端,图2是根据本实施例的确定处理器的当前积分方法的流程图,如图2所示,该流程包括如下步骤:This embodiment provides a method for determining the current points of the processor, which can be used for terminals such as mobile phones, tablets, computers, etc. Figure 2 is a flow chart of the method of determining the current points of the processor according to this embodiment, as shown in Figure 2 As shown, the process includes the following steps:
S21,响应于控制组的创建指令,创建处理器的控制组,控制组与处理器一一对应。S21. In response to the creation instruction of the control group, create a control group of the processor, and the control group corresponds to the processor one-to-one.
S22,响应于积分充值指令,在处理器的控制组中设置积分参数,以确定处理器的当前积分。S22. In response to the points recharge instruction, set points parameters in the control group of the processor to determine the current points of the processor.
可以通过修改虚拟机控制组(cgroup)下的处理器参数来限制虚拟机的整体利用率,而对于虚拟处理器线程的限制是为每个虚拟处理器创建一个cgroup,并在虚拟处理器的cgroup中设置处理器参数。即通过积分充值指令在处理器的控制组中设置参数,从而确定处理器的当前积分。具体地,确定当前积分还包括如下步骤:You can limit the overall utilization of a virtual machine by modifying the processor parameters under the virtual machine control group (cgroup). The limit for virtual processor threads is to create a cgroup for each virtual processor and set it in the virtual processor's cgroup. Set processor parameters in . That is, the parameters are set in the control group of the processor through the point recharge instruction to determine the current points of the processor. Specifically, determining the current points also includes the following steps:
(1)响应于积分充值指令,在处理器的控制组中设置积分参数,以确定处理器的充值积分。(1) In response to the points recharge instruction, set the points parameters in the control group of the processor to determine the recharge points of the processor.
将积分值写入积分充值指令的参数中,即对处理器进行积分的充值,从而确定给处理器的充值积分。The points value is written into the parameters of the point recharge instruction, that is, the points are recharged to the processor, thereby determining the recharge points to the processor.
(2)获取处理器的当前积分,将充值积分累加至当前积分中,以确定处理器的当前积分。(2) Obtain the current points of the processor and add the recharge points to the current points to determine the current points of the processor.
获取处理器的当前积分,将充值积分的值累加到当前积分值中,如果累加后的当前积分值超过预设的积分上限阈值,则将当前积分值设置为积分上限阈值。Obtain the current points of the processor and add the value of the recharge points to the current points value. If the accumulated current points value exceeds the preset points upper limit threshold, the current points value is set to the points upper limit threshold.
在一种实施方式中,在将当前运行性能和预设算力阈值比较,得到比较结果之前,还包括:获取处理器的性能,响应于对处理器的性能阈值配置指令, 基于处理器的性能确定预设算力阈值。In one embodiment, before comparing the current running performance with the preset computing power threshold and obtaining the comparison result, the method further includes: obtaining the performance of the processor, and responding to the performance threshold configuration instruction for the processor, based on the performance of the processor Determine the preset computing power threshold.
其中,预设算力阈值即基准性能。Among them, the preset computing power threshold is the baseline performance.
在本实施例中提供了调整处理器性能的方法,可用于如手机、平板电脑、电脑等终端,图3是根据本实施例的调整处理器性能的方法的流程图,如图3所示,该流程包括如下步骤:This embodiment provides a method for adjusting processor performance, which can be used for terminals such as mobile phones, tablets, computers, etc. Figure 3 is a flow chart of the method for adjusting processor performance according to this embodiment, as shown in Figure 3. The process includes the following steps:
S31,当当前运行性能超过预设算力阈值,消耗当前积分。S31, when the current running performance exceeds the preset computing power threshold, current points are consumed.
S32,当当前运行性能未达到预设算力阈值,累计当前积分,以提高处理器的算力。S32: When the current running performance does not reach the preset computing power threshold, current points are accumulated to increase the computing power of the processor.
具体地,包括如下步骤:Specifically, it includes the following steps:
(1)当当前运行性能未达到预设算力阈值,累计当前积分,并获取当前积分。(1) When the current operating performance does not reach the preset computing power threshold, the current points are accumulated and the current points are obtained.
当当前运行性能小于预设算力阈值,即云主机以低于基准性能的模式在运行时,处理器的当前积分会随着时间流逝而增加,即累计当前积分。When the current operating performance is less than the preset computing power threshold, that is, when the cloud host is running in a mode lower than the baseline performance, the current points of the processor will increase over time, that is, the current points will be accumulated.
(2)响应于积分上限指令,确定处理器的积分上限阈值。(2) In response to the integral upper limit instruction, determine the integral upper limit threshold of the processor.
当创建的云主机开启积分功能后,对其进行信息配置,可以通过积分上限指令配置其中的处理器积分,设置处理器的积分上限阈值。After the points function is enabled on the created cloud host, you can configure its information. You can use the points upper limit command to configure the processor points and set the processor's points upper limit threshold.
(3)将当前积分与积分上限阈值比较,当当前积分超过积分上限阈值,将当前积分调整为积分上限阈值。(3) Compare the current points with the points upper limit threshold. When the current points exceed the points upper limit threshold, adjust the current points to the points upper limit threshold.
将经过累计的当前积分与积分上限阈值进行比较,由于累计的当前积分不超过预先设置的积分上限阈值,当当前积分超过积分上限阈值,则将当前积分值设置为积分上限阈值,也就是说当前积分的最大值就是积分上限阈值。Compare the accumulated current points with the upper limit threshold of points. Since the accumulated current points do not exceed the preset upper limit threshold of points, when the current points exceed the upper limit threshold of points, the current points value is set to the upper limit threshold of points, that is to say, the current points The maximum value of the points is the points upper limit threshold.
当当前运行性能大于预设算力阈值,即云主机以高于基准性能的模式在运行时,且处理器的使用率达到配额后,可以通过消耗累计的当前积分来额外使用处理器算力,直至积分消耗完,处理器的算力将回退到配额值,直到再次累计积分或充值积分。When the current operating performance is greater than the preset computing power threshold, that is, when the cloud host is running in a mode higher than the baseline performance, and the processor usage reaches the quota, you can use the accumulated current points to additionally use the processor computing power. Until the points are consumed, the processor's computing power will fall back to the quota value until points are accumulated or recharged again.
在本实施例中提供了一种处理器性能调整方法的具体实施例,如图4所示。This embodiment provides a specific embodiment of a processor performance adjustment method, as shown in Figure 4.
本实施例中,通过为cgroup增加三个参数来控制处理器的积分,参数如下:In this embodiment, the integration of the processor is controlled by adding three parameters to the cgroup. The parameters are as follows:
cpu.cfs_burst_ns:表示可以累积的最大积分,即积分上限阈值,参数可读写。0(默认值)表示未开启处理器积分机制,设置其他参数后表示开启积分机制。cpu.cfs_burst_ns: Indicates the maximum points that can be accumulated, that is, the upper limit threshold of points. The parameter can be read and written. 0 (default value) means that the processor credit mechanism is not enabled. Setting other parameters means that the credit mechanism is enabled.
cpu.cfs_remain_time:表示当前可用的处理器积分,即处理器的当前积分,参数只读。cpu.cfs_remain_time: Indicates the currently available processor points, that is, the current points of the processor. The parameter is read-only.
cpu.cfs_recharge_time:表示处理器积分充值参数,即充值积分,参数可读写。向该接口写入数字表示充值处理器积分。cpu.cfs_recharge_time: Indicates the processor points recharge parameters, that is, recharge points. The parameters can be read and written. Writing a number to this interface indicates recharging processor points.
Os(OpenStack)会监听云主机的resume事件,libvirt(虚拟化管理软件)在虚拟机正常启动、迁移、重启、变配后都会上报该事件。OS调用libvirt 的接口配置处理器积分。当创建的云主机开启积分功能后,其配置信息中包含了处理器的积分配置,如:Os (OpenStack) will monitor the resume event of the cloud host, and libvirt (virtualization management software) will report this event after the virtual machine starts, migrates, restarts, and changes configuration normally. The OS calls the interface of libvirt to configure the processor points. When the points function is enabled for the created cloud host, its configuration information includes the points configuration of the processor, such as:
<domain type='kvm'><domain type='kvm'>
  <cputune><cputune>
    <global_period>100000</global_period><global_period>100000</global_period>
    <global_quota>50000</global_quota><global_quota>50000</global_quota>
                   <global_burst>50000</global_burst>                                                                                                  
  </cputune></cputune>
  ...........
</domain></domain>
其中,global_burst为处理器的积分上限阈值,xml中有该配置说明该云主机开启了积分机制。当云主机开机时,会将云主机之前的剩余积分,调用libvirt的充值接口恢复。Among them, global_burst is the upper limit threshold of points for the processor. This configuration in the xml indicates that the cloud host has enabled the points mechanism. When the cloud host is turned on, the remaining points of the cloud host will be restored by calling the recharge interface of libvirt.
libvirt支持限制虚拟机进程整体的处理器使用率(global_period/ global_quota)、vcpu(虚拟处理器)线程的处理器使用率(period/quota)和QEMU其他线程(比如io线程)的处理器使用率等等。libvirt supports limiting the overall processor usage of the virtual machine process (global_period/global_quota), the processor usage of the vcpu (virtual processor) thread (period/quota), and the processor usage of other QEMU threads (such as io threads), etc. wait.
libvirt通过修改虚拟机cgroup下的处理器参数来限制虚拟机整体利用率,而对于vcpu线程的限制则是为每个vcpu创建一个cgroup(称为vcpu cgroup),并在vcpu group中设置处理器参数。libvirt limits the overall utilization of the virtual machine by modifying the processor parameters under the virtual machine cgroup. The restriction on vcpu threads is to create a cgroup (called vcpu cgroup) for each vcpu and set the processor parameters in the vcpu group. .
由于处理器积分是针对虚拟机整体进程进行的限制,因此在实现libvirt控制处理器积分功能时,只需要修改虚拟机cgroup下的cpu.cfs_burst_ns和cpu. cfs_recharge_time参数。Since processor points are limited for the entire virtual machine process, when implementing the libvirt control processor points function, you only need to modify the cpu.cfs_burst_ns and cpu.cfs_recharge_time parameters under the virtual machine cgroup.
通过修改cpu.cfs_burst_ns参数可以开启处理器积分机制,当进程空闲时cpu积分慢慢累积,直到积分值达到cpu.cfs_burst_ns上限后停止累计。进程繁忙,并且当处理器使用率达到配额后,可以通过消耗累计的积分来额外使用处理器算力,当积分消耗完后,处理器使用率将回退到配额值,直到又有可用积分使用。The processor points mechanism can be turned on by modifying the cpu.cfs_burst_ns parameter. When the process is idle, the CPU points slowly accumulate until the points reach the upper limit of cpu.cfs_burst_ns and stop accumulating. The process is busy, and when the processor usage reaches the quota, you can use the accumulated points to use additional processor computing power. When the points are consumed, the processor usage will fall back to the quota value until there are more points available. .
在对进程充值处理器积分时,可直接将积分值写入cpu.cfs_recharge_time参数中,此时cgroup将cpu.cfs_recharge_time的值累加到cpu. cfs_remain_time,如果累加后cpu. cfs_remain_time值超过cpu.cfs_burst_ns限制,则将cpu. cfs_remain_time值设置为cpu.cfs_burst_ns。When recharging processor points for a process, you can directly write the point value into the cpu.cfs_recharge_time parameter. At this time, cgroup will accumulate the value of cpu.cfs_recharge_time to cpu.cfs_remain_time. If the accumulated value of cpu.cfs_remain_time exceeds the cpu.cfs_burst_ns limit, Then set the cpu.cfs_remain_time value to cpu.cfs_burst_ns.
当云主机关机时,需要上报处理器积分,即云主机的剩余积分在关机后将保留下来,以便在下次开机时继续使用保存的积分。实现逻辑如下:When the cloud host is shut down, the processor points need to be reported, that is, the remaining points of the cloud host will be retained after the shutdown, so that the saved points can be continued to be used the next time it is turned on. The implementation logic is as follows:
云主机关机后,对应的QEMU进程将中止。libvirt在检查到QEMU进程终止事件时,获取虚拟机的cgroup中的剩余积分,然后通过VIR_DOMAIN_EVENT_ID_TUNABLE事件将剩余积分上报给OS。After the cloud host shuts down, the corresponding QEMU process will be terminated. When libvirt detects the QEMU process termination event, it obtains the remaining points in the cgroup of the virtual machine, and then reports the remaining points to the OS through the VIR_DOMAIN_EVENT_ID_TUNABLE event.
例如,OS接收到该事件上报的数据如下:For example, the data reported by the event received by the OS is as follows:
{'cputune.global_remain_time':15563169L,'cputune.global_burst':36000000000L}{'cputune.global_remain_time':15563169L,'cputune.global_burst':36000000000L}
OS监听该事件,并在事件处理接口中将剩余积分持久化保存下来。The OS listens to this event and persists the remaining points in the event processing interface.
在一种实施方式中,当虚拟机将数据迁移至目标虚拟机时,获取虚拟机中处理器的当前积分,并保存当前积分,将当前积分添加至目标虚拟机。In one implementation, when the virtual machine migrates data to the target virtual machine, the current score of the processor in the virtual machine is obtained, the current score is saved, and the current score is added to the target virtual machine.
如果迁移前云主机开启了积分功能并且有剩余积分,那么在迁移后,也必须要对目标云主机开启积分功能并恢复剩余积分,保证迁移操作不影响虚拟机的积分。If the points function is enabled on the cloud host before migration and there are remaining points, then after the migration, the points function must be enabled on the target cloud host and the remaining points restored to ensure that the migration operation does not affect the points of the virtual machine.
云主机的迁移操作由OS发起,如果是热迁移,则迁移流程主要由libvirt控制。如果是冷迁移,则迁移流程主要由OS控制。无论由哪方控制,都需要先将剩余积分保存,在目标云主机启动后,将剩余积分充值至目标云主机,目标云主机即目标虚拟机。The cloud host migration operation is initiated by the OS. If it is a live migration, the migration process is mainly controlled by libvirt. In the case of cold migration, the migration process is mainly controlled by the OS. No matter which party controls it, the remaining points need to be saved first. After the target cloud host is started, the remaining points are recharged to the target cloud host. The target cloud host is the target virtual machine.
具体地,OS发起迁移后,libvirt内存中的云主机配置信息记录了开启处理器积分的global_burst配置,因此libvirt在创建目标云主机时会自动设置cgroup以开启积分功能。在进行热迁移时,libvirt按正常逻辑迁移云主机的数据(内存数据,设备状态等),迁移完成后,libvirt立即暂停云主机,获取虚拟机中处理器的剩余积分,即当前积分,并将剩余积分充值到目的云主机中。积分充值完成后,恢复目标云主机。在进行冷迁移时,云主机关机时将剩余积分持久化到数据库中,当迁移完再次开机时,OS监听到resume事件,会将剩余积分充值到目标虚拟机上。Specifically, after the OS initiates migration, the cloud host configuration information in libvirt's memory records the global_burst configuration that enables processor credits. Therefore, libvirt automatically sets the cgroup to enable the credits function when creating the target cloud host. During live migration, libvirt migrates the cloud host's data (memory data, device status, etc.) according to normal logic. After the migration is completed, libvirt immediately pauses the cloud host, obtains the remaining points of the processor in the virtual machine, that is, the current points, and adds The remaining points are recharged to the destination cloud host. After the points recharge is completed, restore the target cloud host. During cold migration, the cloud host persists the remaining points into the database when it shuts down. When it is turned on again after the migration, the OS listens to the resume event and recharges the remaining points to the target virtual machine.
本申请提供的处理器性能调整方法,可以将云主机闲时的算力通过积分方式累计起来,在需要突发性能的时间段内通过消耗累计的处理器积分从而实现超额使用处理器算力。当累计的积分耗尽时,可以限制处理器算力,使其恢复至基准性能范围内。除了通过累计低性能工作时的积分之外,还可以通过积分充值,使用户可以根据实际需求充值积分。另外,云主机变配、迁移或开关机都不影响其中的处理器积分。在一定程度上降低了用户的使用成本,无需为偶发的高处理器使用率业务来升配云主机或购买高规格的云主机,提升了资源的利用率,更加灵活地配置和限制处理器的性能,提升了用户的体验。The processor performance adjustment method provided by this application can accumulate the computing power of the cloud host through points when it is idle, and consume the accumulated processor points during the period when sudden performance is required to achieve excess use of the processor computing power. When the accumulated points are exhausted, the processor computing power can be limited to restore it to the baseline performance range. In addition to accumulating points during low-performance work, it can also be recharged through points, allowing users to recharge points according to actual needs. In addition, cloud host configuration, migration or power-on/off will not affect the processor points. It reduces the user's usage costs to a certain extent. There is no need to upgrade cloud hosts or purchase high-specification cloud hosts for occasional high processor usage services, improve resource utilization, and more flexibly configure and limit processor usage. performance, improving user experience.
在本实施例中还提供了一种处理器性能调整装置,该装置用于实现上述实施例,已经进行过说明的不再赘述。如以下所使用的,术语“模块”可以实现预定功能的软件和/或硬件的组合。尽管以下实施例所描述的装置较佳地以软件来实现,但是硬件,或者软件和硬件的组合的实现也是可能并被构想的。This embodiment also provides a processor performance adjustment device, which is used to implement the above embodiment. What has already been described will not be described again. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
本实施例提供一种处理器性能调整装置,如图5所示,包括:This embodiment provides a processor performance adjustment device, as shown in Figure 5, including:
积分充值模块,用于响应于积分充值指令,确定处理器的当前积分;A points recharge module, used to determine the current points of the processor in response to the points recharge instruction;
性能判断模块,用于获取所述处理器的当前运行性能,将所述当前运行性能和预设算力阈值比较,得到比较结果;A performance judgment module, used to obtain the current operating performance of the processor, compare the current operating performance with the preset computing power threshold, and obtain a comparison result;
积分调整模块,用于根据所述比较结果,调整所述处理器的当前积分,以调整所述处理器的性能。A score adjustment module, configured to adjust the current score of the processor according to the comparison result to adjust the performance of the processor.
在一种实施方式中,积分充值模块包括:In one implementation, the points recharge module includes:
控制组建立子单元,用于响应于控制组的创建指令,创建所述处理器的控制组,所述控制组与所述处理器一一对应; A control group establishment subunit, configured to create a control group of the processor in response to a control group creation instruction, where the control group corresponds to the processor one-to-one;
当前积分确定子单元,用于响应于积分充值指令,在所述处理器的控制组中设置积分参数,以确定所述处理器的当前积分。The current points determination subunit is configured to set points parameters in the control group of the processor in response to a point recharge instruction to determine the current points of the processor.
在一种实施方式中,当前积分确定子单元包括:In one implementation, the current integral determination subunit includes:
响应于积分充值指令,在所述处理器的控制组中设置积分参数,以确定所述处理器的充值积分;获取所述处理器的当前积分,将所述充值积分累加至所述当前积分中,以确定所述处理器的当前积分。In response to the points recharge instruction, set points parameters in the control group of the processor to determine the recharge points of the processor; obtain the current points of the processor, and accumulate the recharge points into the current points to determine the current score of the processor.
在一种实施方式中,装置还包括:In one embodiment, the device further includes:
算力阈值确定模块,用于获取所述处理器的性能;响应于对所述处理器的性能阈值配置指令, 基于所述处理器的性能确定所述预设算力阈值。A computing power threshold determination module is configured to obtain the performance of the processor; in response to a performance threshold configuration instruction for the processor, determine the preset computing power threshold based on the performance of the processor.
在一种实施方式中,积分调整模块包括:In one implementation, the points adjustment module includes:
积分消耗子单元,用于当所述当前运行性能超过所述预设算力阈值,消耗所述当前积分;A points consumption subunit, configured to consume the current points when the current operating performance exceeds the preset computing power threshold;
算力提高子单元,用于当所述当前运行性能未达到所述预设算力阈值,累计所述当前积分,以提高所述处理器的算力。The computing power improvement subunit is used to accumulate the current points when the current operating performance does not reach the preset computing power threshold, so as to improve the computing power of the processor.
在一种实施方式中,算力提高子单元还用于:In one implementation, the computing power improvement subunit is also used to:
当所述当前运行性能未达到所述预设算力阈值,累计所述当前积分,并获取当前积分;When the current operating performance does not reach the preset computing power threshold, accumulate the current points and obtain current points;
响应于积分上限指令,确定所述处理器的积分上限阈值;In response to a credit cap instruction, determining a credit cap threshold of the processor;
将所述当前积分与所述积分上限阈值比较,当所述当前积分超过所述积分上限阈值,将所述当前积分调整为所述积分上限阈值。The current points are compared with the points upper limit threshold. When the current points exceed the points upper limit threshold, the current points are adjusted to the points upper limit threshold.
在一种实施方式中,装置还包括:In one embodiment, the device further includes:
积分迁移模块,用于当所述虚拟机将数据迁移至目标虚拟机时,获取所述处理器的当前积分,并保存所述当前积分;将所述当前积分添加至所述目标虚拟机。A points migration module, configured to obtain the current points of the processor when the virtual machine migrates data to the target virtual machine, save the current points, and add the current points to the target virtual machine.
本实施例中的处理器性能调整装置是以功能单元的形式来呈现,这里的单元是指ASIC电路,执行一个或多个软件或固定程序的处理器和存储器,和/或其他可以提供上述功能的器件。The processor performance adjustment device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC circuit, a processor and memory that executes one or more software or fixed programs, and/or others that can provide the above functions. device.
上述各个模块的更进一步的功能描述与上述对应实施例相同,在此不再赘述。Further functional descriptions of each of the above modules are the same as those in the above corresponding embodiments, and will not be described again here.
本发明实施例还提供一种电子设备,具有上述图5所示的处理器性能调整装置。An embodiment of the present invention also provides an electronic device having the processor performance adjustment device shown in Figure 5 above.
请参阅图6,图6是本发明可选实施例提供的一种电子设备的结构示意图,如图6所示,该电子设备可以包括:至少一个处理器601,例如CPU(Central Processing Unit,中央处理器),至少一个通信接口603,存储器604,至少一个通信总线602。其中,通信总线602用于实现这些组件之间的连接通信。其中,通信接口603可以包括显示屏(Display)、键盘(Keyboard),可选通信接口603还可以包括标准的有线接口、无线接口。存储器604可以是高速RAM存储器(Random Access Memory,易挥发性随机存取存储器),也可以是非不稳定的存储器(non-volatile memory),例如至少一个磁盘存储器。存储器604可选的还可以是至少一个位于远离前述处理器601的存储装置。其中处理器601可以结合图5所描述的装置,存储器604中存储应用程序,且处理器601调用存储器604中存储的程序代码,以用于执行上述任一方法步骤。Please refer to Figure 6. Figure 6 is a schematic structural diagram of an electronic device provided by an optional embodiment of the present invention. As shown in Figure 6, the electronic device may include: at least one processor 601, such as a CPU (Central Processing Unit, Central Processing Unit). processor), at least one communication interface 603, memory 604, and at least one communication bus 602. Among them, the communication bus 602 is used to realize connection communication between these components. Among them, the communication interface 603 may include a display screen (Display) and a keyboard (Keyboard), and the optional communication interface 603 may also include a standard wired interface and a wireless interface. The memory 604 may be a high-speed RAM memory (Random Access Memory, volatile random access memory) or a non-volatile memory (non-volatile memory), such as at least one disk memory. The memory 604 may optionally be at least one storage device located remotely from the aforementioned processor 601. The processor 601 can be combined with the device described in FIG. 5 , the memory 604 stores an application program, and the processor 601 calls the program code stored in the memory 604 to execute any of the above method steps.
其中,通信总线602可以是外设部件互连标准(peripheral component interconnect,简称PCI)总线或扩展工业标准结构(extended industry standard architecture,简称EISA)总线等。通信总线602可以分为地址总线、数据总线、控制总线等。为便于表示,图6中仅用一条粗线表示,但并不表示仅有一根总线或一种类型的总线。The communication bus 602 may be a peripheral component interconnect (PCI) bus or an extended industry standard structure (extended industry standard architecture (referred to as EISA) bus, etc. The communication bus 602 can be divided into an address bus, a data bus, a control bus, etc. For ease of presentation, only one thick line is used in Figure 6, but it does not mean that there is only one bus or one type of bus.
其中,存储器604可以包括易失性存储器(英文:volatile memory),例如随机存取存储器(英文:random-access memory,缩写:RAM);存储器也可以包括非易失性存储器(英文:non-volatile memory),例如快闪存储器(英文:flash memory),硬盘(英文:hard disk drive,缩写:HDD)或固态硬盘(英文:solid-state drive,缩写:SSD);存储器604还可以包括上述种类的存储器的组合。Among them, the memory 604 may include volatile memory (English: volatile memory), such as random access memory (English: random-access memory). memory, abbreviation: RAM); memory can also include non-volatile memory (English: non-volatile memory), such as flash memory (English: flash memory), hard disk (English: hard disk drive, abbreviation: HDD) or solid state Hard disk (English: solid-state drive, abbreviation: SSD); the memory 604 may also include a combination of the above types of memory.
其中,处理器601可以是中央处理器(英文:central processing unit,缩写:CPU),网络处理器(英文:network processor,缩写:NP)或者CPU和NP的组合。The processor 601 may be a central processing unit (English: central processing unit, abbreviation: CPU), a network processor (English: network processor, abbreviation: NP) or a combination of CPU and NP.
其中,处理器601还可以进一步包括硬件芯片。上述硬件芯片可以是专用集成电路(英文:application-specific integrated circuit,缩写:ASIC),可编程逻辑器件(英文:programmable logic device,缩写:PLD)或其组合。上述PLD可以是复杂可编程逻辑器件(英文:complex programmable logic device,缩写:CPLD),现场可编程逻辑门阵列(英文:field-programmable gate array,缩写:FPGA),通用阵列逻辑(英文:generic array logic, 缩写:GAL)或其任意组合。The processor 601 may further include a hardware chip. The above-mentioned hardware chips can be application-specific integrated circuits (English: application-specific integrated circuit, abbreviation: ASIC), programmable logic devices (English: programmable logic device (abbreviation: PLD) or a combination thereof. The above-mentioned PLD can be a complex programmable logic device (English: complex programmable logic device, abbreviation: CPLD), a field-programmable gate array (English: field-programmable gate array, abbreviation: FPGA), a general array logic (English: generic array logic, abbreviation: GAL) or any combination thereof.
可选地,存储器604还用于存储程序指令。处理器601可以调用程序指令,实现如本申请实施例中所示的处理器性能调整方法。Optionally, memory 604 is also used to store program instructions. The processor 601 can call program instructions to implement the processor performance adjustment method shown in the embodiments of this application.
本发明实施例还提供了一种非暂态计算机存储介质,所述计算机存储介质存储有计算机可执行指令,该计算机可执行指令可执行上述任意方法实施例中的处理器性能调整方法。其中,所述存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory,ROM)、随机存储记忆体(Random Access Memory,RAM)、快闪存储器(Flash Memory)、硬盘(Hard Disk Drive,缩写:HDD)或固态硬盘(Solid-State Drive,SSD)等;所述存储介质还可以包括上述种类的存储器的组合。Embodiments of the present invention also provide a non-transitory computer storage medium. The computer storage medium stores computer-executable instructions. The computer-executable instructions can execute the processor performance adjustment method in any of the above method embodiments. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), or a flash memory (Flash). Memory), hard disk (Hard Disk Drive (abbreviation: HDD) or solid-state drive (Solid-State Drive, SSD), etc.; the storage medium may also include a combination of the above types of memories.
虽然结合附图描述了本发明的实施例,但是本领域技术人员可以在不脱离本发明的精神和范围的情况下做出各种修改和变型,这样的修改和变型均落入由所附权利要求所限定的范围之内。Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope of the appended rights. within the scope of the requirements.

Claims (10)

  1. 一种处理器性能调整方法,其特征在于,所述方法包括: A processor performance adjustment method, characterized in that the method includes:
    响应于积分充值指令,确定处理器的当前积分;In response to the points recharge instruction, determine the current points of the processor;
    获取所述处理器的当前运行性能,将所述当前运行性能和预设算力阈值比较,得到比较结果;Obtain the current operating performance of the processor, compare the current operating performance with a preset computing power threshold, and obtain a comparison result;
    根据所述比较结果,调整所述处理器的当前积分,以调整所述处理器的性能。According to the comparison result, the current score of the processor is adjusted to adjust the performance of the processor.
  2. 根据权利要求1所述的方法,其特征在于,所述响应于积分充值指令,确定处理器的当前积分,包括: The method according to claim 1, characterized in that, in response to a point recharge instruction, determining the current points of the processor includes:
    响应于控制组的创建指令,创建所述处理器的控制组,所述控制组与所述处理器一一对应; In response to the creation instruction of the control group, create a control group of the processor, and the control group corresponds to the processor one-to-one;
    响应于积分充值指令,在所述处理器的控制组中设置积分参数,以确定所述处理器的当前积分。In response to the point recharge instruction, a point parameter is set in the control group of the processor to determine the current point of the processor.
  3. 根据权利要求2所述的方法,其特征在于,所述响应于积分充值指令,在所述处理器的控制组中设置积分参数,以确定所述处理器的当前积分,包括: The method according to claim 2, characterized in that, in response to the points recharge instruction, setting points parameters in the control group of the processor to determine the current points of the processor includes:
    响应于积分充值指令,在所述处理器的控制组中设置积分参数,以确定为所述处理器的充值积分;In response to the points recharge instruction, set points parameters in the control group of the processor to determine recharge points for the processor;
    获取所述处理器的当前积分,将所述充值积分累加至所述当前积分中,以确定所述处理器的当前积分。The current points of the processor are obtained, and the recharge points are accumulated into the current points to determine the current points of the processor.
  4. 根据权利要求1所述的方法,其特征在于,所述获取所述处理器的当前运行性能,将所述当前运行性能和预设算力阈值比较,得到比较结果之前,所述方法还包括: The method according to claim 1, characterized in that, before obtaining the current operating performance of the processor, comparing the current operating performance with a preset computing power threshold, and obtaining the comparison result, the method further includes:
    获取所述处理器的性能;Obtain the performance of the processor;
    响应于对所述处理器的性能阈值配置指令, 基于所述处理器的性能确定所述预设算力阈值。In response to a performance threshold configuration instruction for the processor, the preset computing power threshold is determined based on the performance of the processor.
  5. 根据权利要求1所述的方法,其特征在于,所述根据所述比较结果,调整所述处理器的当前积分,以调整所述处理器的性能,包括: The method of claim 1, wherein adjusting the current score of the processor according to the comparison result to adjust the performance of the processor includes:
    当所述当前运行性能超过所述预设算力阈值,消耗所述当前积分;When the current operating performance exceeds the preset computing power threshold, the current points are consumed;
    当所述当前运行性能未达到所述预设算力阈值,累计所述当前积分,以提高所述处理器的算力。When the current running performance does not reach the preset computing power threshold, the current points are accumulated to increase the computing power of the processor.
  6. 根据权利要求5所述的方法,其特征在于,所述当所述当前运行性能未达到所述预设算力阈值,累计所述当前积分,包括: The method according to claim 5, characterized in that when the current operating performance does not reach the preset computing power threshold, accumulating the current points includes:
    当所述当前运行性能未达到所述预设算力阈值,累计所述当前积分,并获取当前积分;When the current operating performance does not reach the preset computing power threshold, accumulate the current points and obtain current points;
    响应于积分上限指令,确定所述处理器的积分上限阈值;In response to a credit cap instruction, determining a credit cap threshold for the processor;
    将所述当前积分与所述积分上限阈值比较,当所述当前积分超过所述积分上限阈值,将所述当前积分调整为所述积分上限阈值。The current points are compared with the points upper limit threshold. When the current points exceed the points upper limit threshold, the current points are adjusted to the points upper limit threshold.
  7. 根据权利要求1所述的方法,其特征在于,所述方法还包括: The method of claim 1, further comprising:
    当虚拟机将数据迁移至目标虚拟机时,获取所述虚拟机中处理器的当前积分,并保存所述当前积分;When the virtual machine migrates data to the target virtual machine, obtain the current score of the processor in the virtual machine and save the current score;
    将所述当前积分添加至所述目标虚拟机。Add the current points to the target virtual machine.
  8. 一种处理器性能调整装置,其特征在于,包括: A processor performance adjustment device, characterized by including:
    积分充值模块,用于响应于积分充值指令,确定处理器的当前积分;A points recharge module, used to determine the current points of the processor in response to the points recharge instruction;
    性能判断模块,用于获取所述处理器的当前运行性能,将所述当前运行性能和预设算力阈值比较,得到比较结果;A performance judgment module, used to obtain the current operating performance of the processor, compare the current operating performance with the preset computing power threshold, and obtain a comparison result;
    积分调整模块,用于根据所述比较结果,调整所述处理器的当前积分,以调整所述处理器的性能。A score adjustment module, configured to adjust the current score of the processor according to the comparison result to adjust the performance of the processor.
  9. 一种电子设备,其特征在于,包括: An electronic device, characterized by including:
    存储器和处理器,所述存储器和所述处理器之间互相通信连接,所述存储器中存储有计算机指令,所述处理器通过执行所述计算机指令,从而执行权利要求1-7中任一项所述的处理器性能调整方法。A memory and a processor. The memory and the processor are communicatively connected to each other. The memory stores computer instructions. The processor executes the computer instructions to execute any one of claims 1-7. The processor performance adjustment method.
  10. 一种计算机可读存储介质,其特征在于,所述计算机可读存储介质存储有计算机指令,所述计算机指令用于使计算机执行权利要求1-7中任一项所述的处理器性能调整方法。 A computer-readable storage medium, characterized in that the computer-readable storage medium stores computer instructions, and the computer instructions are used to cause the computer to execute the processor performance adjustment method according to any one of claims 1-7. .
PCT/CN2022/141792 2022-07-29 2022-12-26 Processor performance adjustment method and apparatus, electronic device and storage medium WO2024021485A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210906733.6 2022-07-29
CN202210906733.6A CN115454617A (en) 2022-07-29 2022-07-29 Processor performance adjusting method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
WO2024021485A1 true WO2024021485A1 (en) 2024-02-01

Family

ID=84295972

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/141792 WO2024021485A1 (en) 2022-07-29 2022-12-26 Processor performance adjustment method and apparatus, electronic device and storage medium

Country Status (2)

Country Link
CN (1) CN115454617A (en)
WO (1) WO2024021485A1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115454617A (en) * 2022-07-29 2022-12-09 天翼云科技有限公司 Processor performance adjusting method and device, electronic equipment and storage medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6845456B1 (en) * 2001-05-01 2005-01-18 Advanced Micro Devices, Inc. CPU utilization measurement techniques for use in power management
CN114461382A (en) * 2021-12-27 2022-05-10 天翼云科技有限公司 Flexibly configurable computing power scheduling implementation method and device and storage medium
WO2022100534A1 (en) * 2020-11-12 2022-05-19 华为云计算技术有限公司 Virtual instance setting method and apparatus
CN115454617A (en) * 2022-07-29 2022-12-09 天翼云科技有限公司 Processor performance adjusting method and device, electronic equipment and storage medium

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6845456B1 (en) * 2001-05-01 2005-01-18 Advanced Micro Devices, Inc. CPU utilization measurement techniques for use in power management
WO2022100534A1 (en) * 2020-11-12 2022-05-19 华为云计算技术有限公司 Virtual instance setting method and apparatus
CN114461382A (en) * 2021-12-27 2022-05-10 天翼云科技有限公司 Flexibly configurable computing power scheduling implementation method and device and storage medium
CN115454617A (en) * 2022-07-29 2022-12-09 天翼云科技有限公司 Processor performance adjusting method and device, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN115454617A (en) 2022-12-09

Similar Documents

Publication Publication Date Title
US10990431B2 (en) Virtual machine hot migration method and apparatus, and system
US9110669B2 (en) Power management of a storage device including multiple processing cores
WO2019075980A1 (en) Thread adjustment method and terminal thereof
US10089266B2 (en) Power saving feature for storage subsystems
US20110173374A1 (en) Solid-state memory management
EP4030289A1 (en) Method and device for virtual machine memory management
US20150334040A1 (en) Bursting cloud resources to affect state change performance
CN113312142A (en) Virtualization processing system, method, device and equipment
WO2024021485A1 (en) Processor performance adjustment method and apparatus, electronic device and storage medium
WO2017193964A1 (en) Component upgrade method, apparatus and system
WO2023160397A1 (en) Memory management methods and apparatuses
US20220253252A1 (en) Data processing method and apparatus
WO2022222721A1 (en) Computational resource scheduling method and apparatus
CN103955389A (en) System startup method based on PCM (Phase Change Random Access Memory)
US9524189B2 (en) Information processing device, information processing method, and computer program product
CN112134752B (en) Method, system, equipment and medium for monitoring switch based on BMC
WO2021207923A1 (en) Cluster expansion method and apparatus, storage medium, and electronic device
WO2023193527A1 (en) Thread execution method and apparatus, electronic device, and computer-readable storage medium
WO2023155695A1 (en) Processor, control method, device, and medium
US20170308154A1 (en) Fast system setting changes
CN116644011A (en) Quick identification method, device and equipment of I2C equipment and storage medium
US20220114086A1 (en) Techniques to expand system memory via use of available device memory
CN114880042A (en) Application starting method and device, electronic equipment and computer readable storage medium
CN114115703A (en) Bare metal server online migration method and system
CN111143055A (en) Virtual cloud host pre-allocation method and device, readable storage medium and electronic equipment

Legal Events

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

Ref document number: 22952914

Country of ref document: EP

Kind code of ref document: A1