WO2017113861A1 - 一种数据访问方法和装置 - Google Patents
一种数据访问方法和装置 Download PDFInfo
- Publication number
- WO2017113861A1 WO2017113861A1 PCT/CN2016/097817 CN2016097817W WO2017113861A1 WO 2017113861 A1 WO2017113861 A1 WO 2017113861A1 CN 2016097817 W CN2016097817 W CN 2016097817W WO 2017113861 A1 WO2017113861 A1 WO 2017113861A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- service host
- access
- main memory
- data stored
- storage device
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/061—Improving I/O performance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0646—Horizontal data movement in storage systems, i.e. moving data in between storage devices or systems
- G06F3/0647—Migration mechanisms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/0671—In-line storage system
- G06F3/0683—Plurality of storage devices
Definitions
- the present invention relates to the field of data storage, and in particular, to a data access method and apparatus.
- Enterprise data center data is growing at an unprecedented rate. With the increasing variety and number of enterprise applications, the number of storage arrays in data centers is increasing. Each service has its own data storage access characteristics. The frequency of storing and reading accesses is different. The high-performance storage resources in the data center are expensive and the storage resources are limited. How to make full use of high-performance storage resources to accelerate the on-demand of services has become an urgent problem for enterprises.
- the existing tiered storage technology deploys high-performance storage media in the storage array, identifies hotspots and non-hotspot data according to the access frequency of data in the current storage array, and allocates different storage media according to hotspots and non-hotspot data, and frequently accesses Hotspot data is automatically migrated to high-performance storage media, such as Solid State Drives (SSDs), while non-hotspot data for low-cycle access is automatically migrated to high-capacity, low-cost storage media such as near-line Nearline Serial Attached SCSI Drives (NL-SAS).
- SSDs Solid State Drives
- NL-SAS near-line Nearline Serial Attached SCSI Drives
- the existing tiered storage technology cannot accelerate the data access across the storage array.
- the high-performance storage resources cannot be shared in the entire storage resource pool, which has a large storage acceleration limitation and cannot provide data access acceleration services for all hosts.
- the performance and feature advantages of high-performance storage resources in the data center cannot be fully utilized, resulting in waste of high-performance storage resources.
- the embodiment of the invention provides a data access method and device, which solves the problem that the storage acceleration problem caused by the inability to implement data access acceleration across the storage array in the existing hierarchical storage technology is large.
- a data access management server is provided, the server and at least one The service host is connected to the acceleration storage device, and each service host corresponds to a main memory, and the main storage is used to provide data storage for the service host, and the storage speed of the acceleration storage device is greater than the storage speed of the main storage device.
- the management server includes:
- a detecting unit configured to detect, in the at least one service host, a first service host that needs to accelerate access to the corresponding main memory
- a connecting unit configured to establish a connection relationship between the first service host and the acceleration storage device when the detecting unit detects the first service host
- a migration unit migrating data stored in the first memory corresponding to the first service host to the acceleration storage device, and controlling the first service host to switch from accessing data stored in the first main memory to the access station Accelerate the data stored in the storage device.
- the migrating unit is further configured to switch to control accessing the accelerated storage from accessing data stored in the first main memory by the first service host
- the detecting unit detects that the first service host does not need to accelerate access to the corresponding first main memory, and migrates the data stored in the accelerated storage device to the first main memory. Controlling, by the first service host, switching from accessing data stored in the accelerated storage device to accessing data stored in the first main memory.
- the detecting unit is configured to: when detecting that the first service host needs to accelerate access to the corresponding first main memory, specifically:
- the detecting unit detects that the time when the first service host initiates access to the first main memory is within an accelerated access time range configured for the first service host, determining that the first service host needs to accelerate access to the corresponding first main memory ;or,
- the detecting unit detects that the frequency value of the first service host initiating access to the first main memory is greater than the acceleration access frequency threshold configured in advance for the first service host, determining that the first service host needs to accelerate access to the corresponding first main memory .
- the method includes:
- the detecting unit is further configured to detect whether the current time reaches the end time point of the accelerated access time range, and if yes, determine that the first service host does not need to accelerate access to the corresponding first main memory; or
- the detecting unit is further configured to: detect whether the access frequency of the first service host to the first main memory is less than an acceleration access frequency threshold configured for the first service host, and if yes, determine that the first service host does not need to be accelerated. Access the corresponding first main memory.
- the migration unit is further configured to control, when the first service host is controlled, from accessing the accelerated storage device After the data is switched back to access the data stored in the first main memory, the data stored in the accelerated storage device is cleared.
- a data access method including:
- the data stored in the device
- Each service host corresponds to a main memory, and the main memory is used to provide data storage for the service host, and the storage speed of the acceleration storage device is greater than the storage speed of the main storage.
- the second aspect in a first possible implementation manner of the second aspect, after detecting that the first service host switches from accessing data stored in the first main memory to accessing data stored in the acceleration storage device, detecting And when the first service host does not need to accelerate access to the corresponding first main memory, the data stored in the acceleration storage device is migrated to the first main memory, and the first service host is controlled to access the accelerated storage. The data stored in the device is switched back to accessing data stored in the first main memory.
- the detecting that the first service host needs to accelerate access to the corresponding first main memory includes:
- the frequency value of the first service host initiating access to the first main memory is greater than the acceleration access frequency threshold configured in advance for the first service host, it is determined that the first service host needs to accelerate access to the corresponding first main memory.
- the method further includes:
- the controlling the first service host to switch back to access the data stored in the accelerated storage device After storing the data in the main memory it also includes:
- a third aspect provides a data access system, including: at least one service host, at least one main storage, an acceleration storage device, and a management server, wherein:
- Each main memory is used to store data that the corresponding service host needs to access
- the storage speed of the accelerated storage device is greater than the storage speed of any one of the main memories
- the management server is configured to detect a first service host that needs to accelerate access to the corresponding main memory in the at least one service host; and when the detecting unit detects the first service host, establish the first service host and Accelerating a connection relationship of the storage device; the first service host The data stored in the corresponding first memory is migrated to the acceleration storage device, and the first service host is controlled to switch from accessing data stored in the first main memory to accessing data stored in the acceleration storage device.
- the management server when the management server detects that the first service host needs to speed up access to the corresponding first main memory, the management server is specifically configured to:
- the management server When the management server detects that the time when the first service host initiates access to the first main memory is within the accelerated access time range configured for the first service host, determining that the first service host needs to accelerate access to the corresponding first main memory .
- the management server is configured to: when detecting that the first service host needs to speed up accessing the corresponding first main memory,
- the management server When the management server detects that the frequency value of the first service host initiating access to the first main memory is greater than the acceleration access frequency threshold configured in advance for the first service host, determining that the first service host needs to accelerate access to the corresponding first main memory. .
- the management server is further configured to detect whether the current time reaches the Accelerating the end time point of the access time range, and if so, determining that the first service host does not need to accelerate access to the corresponding first main memory; or
- the management server is further configured to detect whether the access frequency of the first service host to the first main memory is less than an accelerated access frequency threshold configured for the first service host, and if yes, determine that the first service host does not need to accelerate access Corresponding first main memory.
- the management server is further configured to control, when the first service host is accessed from accessing the first main memory, After the data is switched to access the data stored in the accelerated storage device, when it is detected that the first service host does not need to accelerate access to the corresponding first main memory, the data stored in the accelerated storage device is migrated to the In the first main memory, the first service host is controlled to switch back from accessing data stored in the acceleration storage device to access data stored in the first main memory.
- the management server is further configured to control the first service host from After accessing the data stored in the accelerated storage device to switch back to accessing data stored in the first main memory, the data stored in the accelerated storage device is cleared.
- the data access method and device in the embodiment of the present invention can utilize the high-performance storage device to perform data access acceleration for each service host in real time, thereby avoiding the storage acceleration performance required by the hot data in a certain period of time in the prior art.
- Low-level problem in addition, it can provide data access acceleration service for each service host that needs data access acceleration through accelerating storage devices with higher storage performance, and solves the problem that one existing high-performance storage device can only be one service host. Accelerating data access, resulting in greater storage acceleration limitations, improved data access efficiency, simple implementation, easy to promote and use.
- FIG. 1A is a schematic structural diagram A of a data access management server according to an embodiment of the present invention.
- FIG. 1B is a schematic structural diagram B of a data access management server according to an embodiment of the present invention.
- FIG. 2 is a schematic diagram of a data access system according to an embodiment of the present invention.
- FIG. 3 is a flowchart of a data access method according to an embodiment of the present invention.
- FIG. 4 is a schematic diagram of a scenario when triggering data acceleration access in an embodiment of the present invention.
- FIG. 5 is a schematic diagram of a scenario when an accelerated access path is switched to an acceleration storage device according to an embodiment of the present invention
- FIG. 6 is a schematic diagram of a scenario when an accelerated access storage device is accelerated in an embodiment of the present invention.
- FIG. 7 is a schematic diagram of a scenario when an access path is switched to a main memory at the end of an accelerated access according to an embodiment of the present invention
- FIG. 8 is a schematic diagram of a data access device according to an embodiment of the present invention.
- the embodiment of the invention provides a data access acceleration method and device, which solves the problem that the storage acceleration problem caused by the data access acceleration cannot be realized across the storage array in the existing hierarchical storage technology is large.
- the method and the device are based on the same inventive concept. Since the principles of the method and the device for solving the problem are similar, the implementation of the device and the method can be referred to each other, and the repeated description is not repeated.
- an embodiment of the present invention provides a data access management server, which may include a memory 101, a processor 102, and a receiver 103.
- the processor 102 may be a central processing unit (CPU) or an application specific integrated circuit (ASIC), and may be one or more integrated circuits for controlling program execution, and may be a field programmable gate array.
- the hardware circuit developed by Field Programmable Gate Array (FPGA) can be a baseband chip.
- the number of memories 101 may be one or more.
- the memory 101 may include a read only memory (ROM), a random access memory (RAM), and a disk storage.
- the receiver 103 can be used to communicate with an external device, for example, the receiver 103 can communicate with a service host, each storage device.
- the management server may further include a transmitter 104, which may be used to communicate with an external device.
- the transmitter 104 may also communicate with the service host and each storage device.
- the transmitter 104 and the receiver 103 may be the same physical module, for example, may be a physical module capable of implementing a transceiving function, such as a transceiver, or the transmitter 104 and the receiver 103. Can be a separate physical module.
- These memories 101, transmitters 104 and receivers 103 may be coupled to the processor 102 via a bus (as in this case, FIGS. 1A-1B), or may be coupled to the processor 102 via dedicated connection lines, respectively.
- the code corresponding to the method shown below is solidified into the chip, so that the chip can perform the method shown in FIG. 3 below when it is running. How to design and program the processor 102 is a technique well known to those skilled in the art, and details are not described herein.
- the management server may be implemented by software, for example, may be a software program that is solidified in the device, or may be implemented by hardware, for example, may be a hardware module added in the device, or may use the device in the original
- Some hardware module implementations such as the processor 102 may be implemented by a data processing system in the device, the memory 101 may be implemented by a storage device in the device, or the memory 101 may also be implemented by an internal cache of the data processing system in the device, the transmitter 104 and receiver 103 can be implemented by a data transceiving system in the device.
- an embodiment of the present invention further provides a data access system, which may include at least one service host, at least one main memory, an acceleration storage device, and may also include FIG. 1A or FIG. Management server shown in 1B. among them:
- Each main memory is used to store data that the corresponding service host needs to access
- the storage performance of the accelerated storage device is higher than the storage performance of any one of the main memories
- the management server is configured to detect a first service host that needs to accelerate access to the corresponding main memory in the at least one service host; and when the detecting unit detects the first service host, establish the first service a connection relationship between the host and the acceleration storage device; migrating data stored in the first storage corresponding to the first service host to the acceleration storage device, and controlling the first service host to access the first main storage device
- the data stored in the switch is switched to access data stored in the accelerated storage device.
- the service host, main storage, acceleration storage device, and management server in the system in FIG. 2 are located in different devices, such as may be located in different servers, or may be located in different In his type of device.
- the storage medium of the main storage is a near-line SAS hard disk, and the storage medium of the accelerated storage device is a solid-state hard disk.
- the storage medium of the main storage and the acceleration storage device is not specifically limited.
- an embodiment of the present invention further provides a data access method, where the specific process includes:
- Step 300 Detect a first service host in the at least one service host that needs to accelerate access to the corresponding main memory.
- Each of the service hosts corresponds to a main memory that stores data, and the main memory is used to provide data storage for the service host.
- the first service host when it is detected that the time when the first service host initiates access to the first main memory is within the accelerated access time range configured for the first service host, it is determined that the first service host needs to accelerate access to the corresponding first main host. Memory.
- the second case is: when it is detected that the frequency value of the first service host initiating access to the first main memory is greater than the acceleration access frequency threshold configured in advance for the first service host, determining that the first service host needs to accelerate access to the corresponding first main host Memory.
- Step 301 Establish a connection relationship between the first service host and the acceleration storage device.
- Step 302 migrating data stored in the first memory corresponding to the first service host to the acceleration storage device, and controlling the first service host to switch from accessing data stored in the first main memory to the access station. Accelerate the data stored in the storage device.
- the storage speed of the acceleration storage device is greater than the storage speed of the main storage
- the management server sets the time plus according to the first service host in advance.
- the speed policy or the frequency acceleration policy triggers the storage access acceleration of the first service host at a suitable point in time.
- the management server automatically maps the storage data on the first main storage to the acceleration storage device, and the storage multi-path software of the first service host at the host layer identifies the first main storage and the acceleration storage device as different access paths of the first service host.
- the data access path of the first service host is still directly accessed from the original path, that is, the first main memory, and the storage multi-path software is used to manage the access path of the service host, thereby implementing the function of switching the access path of the service host.
- the management server sends a path switching command to the storage multi-path software of the host layer, triggering the first service host to switch the storage access path to the accelerated storage device through the multi-path software, and the accelerated storage device takes over the host.
- All input and output (IO) start the data copy of the first main memory to the accelerated storage device.
- the write IO issued by the first service host is simultaneously written to the first main memory and the acceleration storage device, and the read IO is directly read from the acceleration storage device if it is a data block that has been copied, if it is an uncompleted copy.
- the data block is forwarded by the acceleration storage device to the first main memory, read from the first main memory, and returned to the first service host through the acceleration storage device.
- the management server monitors the data storage replication progress of the first main storage to the acceleration storage device, and disconnects the replication relationship between the first main storage and the acceleration storage device after the completion of the replication, and disconnects the An interface mapping relationship between a main memory and the first host and the accelerated storage device.
- the acceleration storage device saves the bitmap information of the data block that has changed since the storage replication is disconnected.
- the first main memory does not participate in any IO of the first service host, and the first service host only accesses the acceleration during the peak period of the service application.
- An accelerated storage device on a storage device is
- the data stored in the acceleration storage device is migrated to the first main memory. Controlling, by the first service host, switching from accessing data stored in the accelerated storage device to accessing the number stored in the first main memory according to.
- the data stored in the accelerated storage device is cleared.
- the management server restores the data replication relationship between the first main storage and the acceleration storage device according to the time acceleration policy or the frequency acceleration policy preset for the first service host, according to the bitmap information. Synchronizing data, the management server sends a switch command to the host, and triggers the host to switch to the first main memory for access by the storage multipath software. Finally, the management server deletes the data stored in the accelerated storage device on the accelerated storage device, and releases the high-performance storage resource.
- an embodiment of the present invention further provides a data access device, where the device is respectively connected to at least one service host and an acceleration storage device, and each service host corresponds to a main memory, and the main memory
- the storage speed of the acceleration storage device is greater than the storage speed of the main storage, and the device may include:
- the detecting unit 80 is configured to detect, in the at least one service host, a first service host that needs to accelerate access to the corresponding main memory;
- the connecting unit 81 is configured to establish a connection relationship between the first service host and the acceleration storage device when the detecting unit 80 detects the first service host.
- the migration unit 82 migrates data stored in the first memory corresponding to the first service host to the acceleration storage device, and controls the first service host to switch from accessing data stored in the first main memory to accessing The accelerating data stored in the storage device.
- the migrating unit 82 is further configured to: after detecting, by the first service host, switching from accessing data stored in the first main memory to accessing data stored in the acceleration storage device, detecting, by the detecting unit 80 And when the first service host does not need to accelerate access to the corresponding first main memory, the data stored in the acceleration storage device is migrated to the first main memory, and the first service host is controlled to access the accelerated storage. The data stored in the device is switched back to access the first main memory Data stored in the reservoir
- the detecting unit 80 when detecting that the first service host needs to accelerate access to the corresponding first main memory, the detecting unit 80 is specifically configured to:
- the detecting unit 80 detects that the time when the first service host initiates access to the first main memory is within the accelerated access time range configured for the first service host, it is determined that the first service host needs to accelerate access to the corresponding first main host. Memory; or,
- the detecting unit 80 detects that the frequency value of the first service host initiating access to the first main memory is greater than the acceleration access frequency threshold configured in advance for the first service host, determining that the first service host needs to accelerate access to the corresponding first main host Memory.
- the detecting unit 80 is further configured to detect whether the current time reaches an end time point of the accelerated access time range, and if yes, determine that the first service host does not need to accelerate access to the corresponding first main memory; or
- the detecting unit 80 is further configured to: detect whether the access frequency of the first service host to the first main memory is less than an acceleration access frequency threshold configured for the first service host, and if yes, determine that the first service host does not need to be Accelerate access to the corresponding first main memory.
- the migrating unit is further configured to: after controlling the first service host to switch back to access data stored in the accelerated storage device to access data stored in the first main memory, the accelerating storage device The data stored in the file is cleared.
- the first service host that needs to accelerate access to the corresponding main memory is detected in the at least one service host; when the first service host is detected, the first service host is established and the Accelerating the connection relationship of the storage device; migrating data stored in the first memory corresponding to the first service host to the acceleration storage device, and controlling the first service host to access data stored in the first main memory Switching to access data stored in the accelerated storage device, wherein each service host corresponds to a main memory, the main memory is configured to provide data storage for the service host, and the storage speed of the acceleration storage device is greater than The storage speed of the main memory, so that data access acceleration can be performed for each service host in real time, avoiding the prior art The problem of low-speed storage performance caused by the hotspot data in a certain period of time is required.
- the data storage acceleration service is provided for each service host that needs data access acceleration through the storage storage device with higher storage performance, thereby solving the existing A high-performance storage device can only accelerate data access for one service host, which causes
- embodiments of the present invention can be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware. Moreover, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
- computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
- the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
- the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
- These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
- the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
一种数据访问方法和装置，以解决现有的分级存储技术中无法跨存储阵列实现数据访问加速造成的存储加速局限性较大的问题。该方法为，检测至少一个业务主机中需要加速访问对应主存储器的第一业务主机（300）；在检测到所述第一业务主机时，建立第一业务主机与所述加速存储设备的连接关系（301）；将所述第一业务主机对应的第一存储器中存储的数据迁移到所述加速存储设备中，并控制所述第一业务主机从访问第一主存储器中存储的数据切换至访问所述加速存储设备中存储的数据（302），其中，所述加速存储设备的存储速度大于所述主存储器的存储速度，这样能够为每个需要数据访问加速的业务主机提供数据访问加速服务，解决了现有的存储加速局限性较大的问题。
Description
本发明涉及数据存储领域，尤其涉及一种数据访问方法和装置。
企业数据中心的数据以前所未有的速度迅猛增长，随着企业应用的业务种类和数量越来越多，数据中心的存储阵列数量也在不断增加，每个业务都有自己的数据存储访问特点，不同的时间段存储读写访问的频率也不一样。数据中心的高性能存储资源价格昂贵，存储资源有限，如何充分利用高性能存储资源实现业务的按需加速，成为企业迫切要解决的问题。
现有的分级存储技术在存储阵列内部署高性能存储介质，根据对当前存储阵列中数据的访问频率，识别出热点与非热点数据，根据热点与非热点数据分配不同的存储介质，将频繁访问的热点数据自动迁移到高性能的存储介质中，例如固态硬盘(Solid State Drives，SSD)中，而将低周期访问的非热点数据自动迁移到大容量，低成本的存储介质中，例如近线串行连接硬盘(Nearline Serial Attached SCSI Drives,NL-SAS)。
但是，现有的分级存储技术无法跨存储阵列实现数据访问加速，高性能存储资源无法在整个存储资源池内共享，使存储加速局限性较大，无法向上为所有主机承载的业务提供数据访问加速服务，不能充分发挥数据中心中高性能存储资源的性能和特性优势，造成了高性能存储资源的浪费。
发明内容
本发明实施例提供一种数据访问方法和装置，以解决现有的分级存储技术中无法跨存储阵列实现数据访问加速造成的存储加速局限性较大的问题。
本发明实施例提供的具体技术方案如下：
第一方面，提供一种数据访问管理服务器，所述服务器分别与至少一个
业务主机和加速存储设备连接，每个业务主机对应一个主存储器，所述主存储器用于为所述业务主机提供数据存储，所述加速存储设备的存储速度大于所述主存储器的存储速度，所述管理服务器包括：
检测单元，用于检测所述至少一个业务主机中需要加速访问对应主存储器的第一业务主机；
连接单元，用于在所述检测单元检测到所述第一业务主机时，建立所述第一业务主机与所述加速存储设备的连接关系；
迁移单元，将所述第一业务主机对应的第一存储器中存储的数据迁移到所述加速存储设备中，并控制所述第一业务主机从访问第一主存储器中存储的数据切换至访问所述加速存储设备中存储的数据。
结合第一方面，在第一方面的第一种可能的实现方式中，所述迁移单元，还用于在控制第一业务主机从访问第一主存储器中存储的数据切换至访问所述加速存储设备中存储的数据之后，在所述检测单元检测到所述第一业务主机不需要加速访问对应的第一主存储器时，将所述加速存储设备中存储的数据迁移到所述第一主存储器中，控制第一业务主机从访问所述加速存储设备中存储的数据切换回访问所述第一主存储器中存储的数据。
结合第一方面，在第一方面的第二种可能的实现方式中，所述检测单元在检测到第一业务主机需要加速访问对应的第一主存储器时，具体用于：
所述检测单元检测到第一业务主机发起访问第一主存储器的时间处于预先为所述第一业务主机配置的加速访问时间范围内时，确定第一业务主机需要加速访问对应的第一主存储器；或，
所述检测单元检测到第一业务主机发起访问第一主存储器的频率值大于预先为所述第一业务主机配置的加速访问频率阈值时，确定第一业务主机需要加速访问对应的第一主存储器。
结合第一方面的第二种可能的实现方式，在第一方面的第三种可能的实现方式中，包括：
所述检测单元，还用于检测当前时间是否到达所述加速访问时间范围的结束时间点，若是，则确定所述第一业务主机不需要加速访问对应的第一主存储器；或
所述检测单元，还用于检测第一业务主机对第一主存储器的访问频率是否小于为所述第一业务主机配置的加速访问频率阈值，若是，则确定所述第一业务主机不需要加速访问对应的第一主存储器。
结合第一方面的第一种可能的实现方式，在第一方面的第四种可能的实现方式中，所述迁移单元，还用于在控制第一业务主机从访问所述加速存储设备中存储的数据切换回访问所述第一主存储器中存储的数据之后，将所述加速存储设备中存储的数据清除。
第二方面，提供一种数据访问方法，包括：
检测至少一个业务主机中需要加速访问对应主存储器的第一业务主机；
在检测到所述第一业务主机时，建立所述第一业务主机与所述加速存储设备的连接关系；
将所述第一业务主机对应的第一存储器中存储的数据迁移到所述加速存储设备中，并控制所述第一业务主机从访问第一主存储器中存储的数据切换至访问所述加速存储设备中存储的数据，
其中，每个业务主机对应一个主存储器，所述主存储器用于为所述业务主机提供数据存储，所述加速存储设备的存储速度大于所述主存储器的存储速度。
结合第二方面，在第二方面的第一种可能的实现方式中，在控制第一业务主机从访问第一主存储器中存储的数据切换至访问所述加速存储设备中存储的数据之后，检测到所述第一业务主机不需要加速访问对应的第一主存储器时，将所述加速存储设备中存储的数据迁移到所述第一主存储器中，控制第一业务主机从访问所述加速存储设备中存储的数据切换回访问所述第一主存储器中存储的数据。
结合第二方面，在第二方面的第二种可能的实现方式中，检测到第一业务主机需要加速访问对应的第一主存储器，包括：
检测到第一业务主机发起访问第一主存储器的时间处于预先为所述第一业务主机配置的加速访问时间范围内时，确定第一业务主机需要加速访问对应的第一主存储器；或，
检测到第一业务主机发起访问第一主存储器的频率值大于预先为所述第一业务主机配置的加速访问频率阈值时，确定第一业务主机需要加速访问对应的第一主存储器。
结合第二方面的第二种可能的实现方式，在第二方面的第三种可能的实现方式中，还包括：
检测当前时间是否到达所述加速访问时间范围的结束时间点，若是，则确定所述第一业务主机不需要加速访问对应的第一主存储器；或
检测第一业务主机对第一主存储器的访问频率是否小于为所述第一业务主机配置的加速访问频率阈值，若是，则确定所述第一业务主机不需要加速访问对应的第一主存储器。
结合第二方面的第一种可能的实现方式，在第二方面的第四种可能的实现方式中，在控制第一业务主机从访问所述加速存储设备中存储的数据切换回访问所述第一主存储器中存储的数据之后，还包括：
将所述加速存储设备中存储的数据清除。
第三方面，提供一种数据访问系统，包括：至少一个业务主机、至少一个主存储器、加速存储设备、管理服务器，其中：
每个主存储器，分别用于存储对应业务主机需要存取的数据；
所述加速存储设备的存储速度大于任意一个主存储器的存储速度；
所述管理服务器，用于检测所述至少一个业务主机中需要加速访问对应主存储器的第一业务主机；在所述检测单元检测到所述第一业务主机时，建立所述第一业务主机与所述加速存储设备的连接关系；将所述第一业务主机
对应的第一存储器中存储的数据迁移到所述加速存储设备中，并控制所述第一业务主机从访问第一主存储器中存储的数据切换至访问所述加速存储设备中存储的数据。
结合第三方面，在第三方面的第一种可能的实现方式中，所述管理服务器在检测到第一业务主机需要加速访问对应的第一主存储器时，具体用于：
所述管理服务器检测到第一业务主机发起访问第一主存储器的时间处于预先为所述第一业务主机配置的加速访问时间范围内时，确定第一业务主机需要加速访问对应的第一主存储器。
结合第三方面，在第三方面的第二种可能的实现方式中，所述管理服务器在检测到第一业务主机需要加速访问对应的第一主存储器时，具体用于：
所述管理服务器检测到第一业务主机发起访问第一主存储器的频率值大于预先为所述第一业务主机配置的加速访问频率阈值时，确定第一业务主机需要加速访问对应的第一主存储器。
结合第三方面的第一种可能的实现方式或第二种可能的实现方式，在第三方面的第三种可能的实现方式中，所述管理服务器，还用于检测当前时间是否到达所述加速访问时间范围的结束时间点，若是，则确定所述第一业务主机不需要加速访问对应的第一主存储器；或
所管理服务器，还用于检测第一业务主机对第一主存储器的访问频率是否小于为所述第一业务主机配置的加速访问频率阈值，若是，则确定所述第一业务主机不需要加速访问对应的第一主存储器。
结合第三方面的第三种可能的实现方式，在第三方面的第四种可能的实现方式中，所述管理服务器，还用于在控制第一业务主机从访问第一主存储器中存储的数据切换至访问所述加速存储设备中存储的数据之后，在检测到所述第一业务主机不需要加速访问对应的第一主存储器时，将所述加速存储设备中存储的数据迁移到所述第一主存储器中，控制第一业务主机从访问所述加速存储设备中存储的数据切换回访问所述第一主存储器中存储的数据。
结合第三方面的第三种可能的实现方式或第四种可能的实现方式，在第三方面的第五种可能的实现方式中，所述管理服务器，还用于在控制第一业务主机从访问所述加速存储设备中存储的数据切换回访问所述第一主存储器中存储的数据之后，将所述加速存储设备中存储的数据清除。
本发明实施例中的数据访问方法和装置，能够利用高性能的存储设备，实时的为各业务主机进行数据访问加速，避免了现有技术中需要在统计一定时间内的热点数据造成存储加速性能低的问题，此外还能通过存储性能更高的加速存储设备为每个需要数据访问加速的业务主机提供数据访问加速服务，解决了现有的一台高性能存储设备只能为一台业务主机进行数据访问加速，而造成存储加速局限性较大的问题，提高了数据访问效率，实现方式简单，便于推广利用。
图1A为本发明实施例中数据访问管理服务器的结构示意图A；
图1B为本发明实施例中数据访问管理服务器的结构示意图B；
图2为本发明实施例中数据访问系统示意图；
图3为本发明实施例中的数据访问方法流程图；
图4为本发明实施例中触发数据加速访问时的场景示意图；
图5为本发明实施例中加速访问路径切换到加速存储设备时的场景示意图；
图6为本发明实施例中加速访问加速存储设备时的场景示意图；
图7为本发明实施例中加速访问结束时访问路径切换到主存储器时的的场景示意图；
图8为本发明实施例中的数据访问装置示意图。
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，并不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
本发明实施例提供一种数据访问加速方法和装置，以解决现有的分级存储技术中无法跨存储阵列实现数据访问加速造成的存储加速局限性较大的问题。其中，方法和装置是基于同一发明构思的，由于方法及装置解决问题的原理相似，因此装置与方法的实施可以相互参见，重复之处不再赘述。
下面结合附图对本发明优选的实施方式进行详细说明。
请参见图1A，本发明实施例提供一种数据访问管理服务器，该管理服务器可以包括存储器101、处理器102和接收器103。
其中，处理器102可以是中央处理器(CPU)或特定应用集成电路(Application Specific Integrated Circuit，ASIC)，可以是一个或多个用于控制程序执行的集成电路，可以是使用现场可编程门阵列(Field Programmable Gate Array，FPGA)开发的硬件电路，可以是基带芯片。
存储器101的数量可以是一个或多个。存储器101可以包括只读存储器(Read Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)和磁盘存储器。
接收器103可以用于与外部设备进行通信，例如接收器103可以与业务主机、各储设备进行通信。
可选的，请参见图1B，该管理服务器还可以包括发送器104，可以用于与外部设备进行通信，例如发送器104也可以与业务主机、各存储设备进行通信。
发送器104和接收器103可以是同一实体模块，例如可以是能够实现收发功能的实体模块，比如可以称为收发器，或者发送器104和接收器103也
可以是单独的实体模块。
这些存储器101、发送器104和接收器103可以通过总线与处理器102相连接(图1A-图1B以此为例)，或者也可以通过专门的连接线分别与处理器102连接。
通过对处理器102进行设计编程，将下面所示的方法所对应的代码固化到芯片内，从而使芯片在运行时能够执行下面图3所示的方法。如何对处理器102进行设计编程为本领域技术人员所公知的技术，这里不再赘述。
其中，该管理服务器可以通过软件方式实现，比如可以是固化在设备中的一套软件程序，或者也可以通过硬件方式实现，比如可以是在设备中新增的硬件模块，或者也可以利用设备中原有的硬件模块实现，比如处理器102可以由设备中的数据处理系统实现，存储器101可以由设备中的存储器件实现，或者存储器101也可以由设备中的数据处理系统的内部缓存实现，发送器104和接收器103可以由设备中的数据收发系统实现。
请参见图2，基于同一发明构思，本发明实施例还提供一种数据访问系统，该数据访问系统可以包括至少一个业务主机、至少一个主存储器、加速存储设备，还可以包括如图1A或图1B所示的管理服务器。其中：
每个主存储器，分别用于存储对应业务主机需要存取的数据；
所述加速存储设备的存储性能高于任意一个主存储器的存储性能；
所述管理服务器，用于用于检测所述至少一个业务主机中需要加速访问对应主存储器的第一业务主机；在所述检测单元检测到所述第一业务主机时，建立所述第一业务主机与所述加速存储设备的连接关系；将所述第一业务主机对应的第一存储器中存储的数据迁移到所述加速存储设备中，并控制所述第一业务主机从访问第一主存储器中存储的数据切换至访问所述加速存储设备中存储的数据。
图2中的系统中的业务主机、主存储器、加速存储设备和管理服务器位于不同的设备中，比如可以位于不同的服务器中，或者也可以位于不同的其
他类型的设备中。
由于固态硬盘的存储性能和存储容量远远优于近线SAS硬盘，可选的，所述主存储器的存储介质为近线SAS硬盘，所述加速存储设备的存储介质为固态硬盘，这里指示一种举例，并不具体限定主存储器和加速存储设备的存储介质。
下面介绍本发明实施例提供的方法。
基于图2中的数据访问系统，参阅图3所示，本发明实施例还提供一种数据访问方法，具体流程包括：
步骤300：检测至少一个业务主机中需要加速访问对应主存储器的第一业务主机。
其中，每个业务主机各自对应一个存放数据的主存储器，所述主存储器用于为所述业务主机提供数据存储。
具体的，检测第一业务主机需要加速访问对应的第一主存储器时，包括以下两种情形：
第一种情形：检测到第一业务主机发起访问第一主存储器的时间处于预先为所述第一业务主机配置的加速访问时间范围内时，确定第一业务主机需要加速访问对应的第一主存储器。
第二种情形：检测到第一业务主机发起访问第一主存储器的频率值大于预先为所述第一业务主机配置的加速访问频率阈值时，确定第一业务主机需要加速访问对应的第一主存储器。
步骤301：建立所述第一业务主机与所述加速存储设备的连接关系。
步骤302：将所述第一业务主机对应的第一存储器中存储的数据迁移到所述加速存储设备中，并控制所述第一业务主机从访问第一主存储器中存储的数据切换至访问所述加速存储设备中存储的数据。
其中，所述加速存储设备的存储速度大于所述主存储器的存储速度
例如，参阅图4所示，管理服务器根据预先为第一业务主机设置时间加
速策略或频率加速策略在合适的时间点触发第一业务主机的存储访问加速。管理服务器自动将第一主存储器上的存储数据映射给加速存储设备，位于主机层的第一业务主机的存储多路径软件，识别第一主存储器和加速存储设备为第一业务主机的不同访问路径，此时第一业务主机的数据访问路径仍然从原路径即第一主存储器直接访问，所述存储多路径软件用于管理业务主机的访问路径，实现对业务主机访问路径的切换功能。
例如，参阅图5所示，管理服务器发送路径切换命令到主机层的存储多路径软件，触发第一业务主机通过多路径软件切换存储访问路径到加速存储设备，此时加速存储设备接管该主机的所有输入输出(Input Output，IO)，开始第一主存储器到加速存储设备的数据复制。此时，第一业务主机下发的写IO同时写到第一主存储器和加速存储设备，读IO如果是已经完成拷贝的数据块则直接从加速存储设备中进行读取，如果是未完成拷贝的数据块则由加速存储设备转发写IO给第一主存储器，从第一主存储器上读取后通过加速存储设备返回给第一业务主机。
进一步的，参阅图6所示，管理服务器监控第一主存储器到加速存储设备的数据存储复制进度，在复制完成后断开第一主存储器和加速存储设备之间的复制关系，并断开第一主存储器到第一主机和加速存储设备之间的接口映射关系。加速存储设备保存从存储复制断开开始，发生过改变的数据块位图信息，此时第一主存储器不参与第一业务主机的任何IO，第一业务主机在业务应用的高峰时段只访问加速存储设备上的加速存储设备。
进一步的，在控制第一业务主机从访问第一主存储器中存储的数据切换至访问所述加速存储设备中存储的数据之后，若检测到当前时间到达所述加速访问时间范围的结束时间点时或者检测到第一业务主机对第一主存储器的访问频率小于为所述第一业务主机配置的加速访问频率阈值时，将所述加速存储设备中存储的数据迁移到所述第一主存储器中，控制第一业务主机从访问所述加速存储设备中存储的数据切换回访问所述第一主存储器中存储的数
据。
具体的，在控制第一业务主机从访问所述加速存储设备中存储的数据切换回访问所述第一主存储器中存储的数据之后，将所述加速存储设备中存储的数据清除。
例如，参阅图7所示，管理服务器根据为第一业务主机预设的时间加速策略或频率加速策略，在业务高峰过后，恢复第一主存储器到加速存储设备的数据复制关系，根据位图信息同步数据，管理服务器发送切换命令到主机，触发主机通过存储多路径软件切换到第一主存储器进行访问。最后由管理服务器删除加速存储设备上的加速存储设备中存储的数据，释放高性能存储资源。
请参见图8，基于同一发明构思，本发明实施例还提供一种数据访问装置，所述装置分别与至少一个业务主机和加速存储设备连接，每个业务主机对应一个主存储器，所述主存储器用于为所述业务主机提供数据存储，所述加速存储设备的存储速度大于所述主存储器的存储速度，该装置可以包括：
检测单元80，用于检测所述至少一个业务主机中需要加速访问对应主存储器的第一业务主机；
连接单元81，用于在所述检测单元80检测到所述第一业务主机时，建立所述第一业务主机与所述加速存储设备的连接关系；
迁移单元82，将所述第一业务主机对应的第一存储器中存储的数据迁移到所述加速存储设备中，并控制所述第一业务主机从访问第一主存储器中存储的数据切换至访问所述加速存储设备中存储的数据。
可选的，所述迁移单元82，还用于在控制第一业务主机从访问第一主存储器中存储的数据切换至访问所述加速存储设备中存储的数据之后，在所述检测单元80检测到所述第一业务主机不需要加速访问对应的第一主存储器时，将所述加速存储设备中存储的数据迁移到所述第一主存储器中，控制第一业务主机从访问所述加速存储设备中存储的数据切换回访问所述第一主存
储器中存储的数据
可选的，所述检测单元80在检测到第一业务主机需要加速访问对应的第一主存储器时，具体用于：
所述检测单元80检测到第一业务主机发起访问第一主存储器的时间处于预先为所述第一业务主机配置的加速访问时间范围内时，确定第一业务主机需要加速访问对应的第一主存储器；或，
所述检测单元80检测到第一业务主机发起访问第一主存储器的频率值大于预先为所述第一业务主机配置的加速访问频率阈值时，确定第一业务主机需要加速访问对应的第一主存储器。
可选的，所述检测单元80，还用于检测当前时间是否到达所述加速访问时间范围的结束时间点，若是，则确定所述第一业务主机不需要加速访问对应的第一主存储器；或
所述检测单元80，还用于检测第一业务主机对第一主存储器的访问频率是否小于为所述第一业务主机配置的加速访问频率阈值，若是，则确定所述第一业务主机不需要加速访问对应的第一主存储器。
可选的，所述迁移单元，还用于在控制第一业务主机从访问所述加速存储设备中存储的数据切换回访问所述第一主存储器中存储的数据之后，将所述加速存储设备中存储的数据清除。
综上所述，本发明实施例中，检测至少一个业务主机中需要加速访问对应主存储器的第一业务主机；在检测到所述第一业务主机时，建立所述第一业务主机与所述加速存储设备的连接关系；将所述第一业务主机对应的第一存储器中存储的数据迁移到所述加速存储设备中，并控制所述第一业务主机从访问第一主存储器中存储的数据切换至访问所述加速存储设备中存储的数据，其中，每个业务主机对应一个主存储器，所述主存储器用于为所述业务主机提供数据存储，所述加速存储设备的存储速度大于所述主存储器的存储速度，这样，能够实时的为各业务主机进行数据访问加速，避免了现有技术
中需要在统计一定时间内的热点数据造成存储加速性能低的问题，此外还能通过存储性能更高的加速存储设备为每个需要数据访问加速的业务主机提供数据访问加速服务，解决了现有的一台高性能存储设备只能为一台业务主机进行数据访问加速，而造成存储加速局限性较大的问题。
本领域内的技术人员应明白，本发明的实施例可提供为方法、系统、或计算机程序产品。因此，本发明可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
尽管已描述了本发明的优选实施例，但本领域内的技术人员一旦得知了基本创造性概念，则可对这些实施例作出另外的变更和修改。所以，所附权利要求意欲解释为包括优选实施例以及落入本发明范围的所有变更和修改。
显然，本领域的技术人员可以对本发明实施例进行各种改动和变型而不脱离本发明实施例的精神和范围。这样，倘若本发明实施例的这些修改和变型属于本发明权利要求及其等同技术的范围之内，则本发明也意图包含这些改动和变型在内。
Claims (10)
- 一种数据访问管理服务器，其特征在于，所述服务器分别与至少一个业务主机和加速存储设备连接，每个业务主机对应一个主存储器，所述主存储器用于为所述业务主机提供数据存储，所述加速存储设备的存储速度大于所述主存储器的存储速度，所述管理服务器包括：检测单元，用于检测所述至少一个业务主机中需要加速访问对应主存储器的第一业务主机；连接单元，用于在所述检测单元检测到所述第一业务主机时，建立所述第一业务主机与所述加速存储设备的连接关系；迁移单元，将所述第一业务主机对应的第一存储器中存储的数据迁移到所述加速存储设备中，并控制所述第一业务主机从访问第一主存储器中存储的数据切换至访问所述加速存储设备中存储的数据。
- 如权利要求1所述的服务器，其特征在于，所述迁移单元，还用于在控制第一业务主机从访问第一主存储器中存储的数据切换至访问所述加速存储设备中存储的数据之后，在所述检测单元检测到所述第一业务主机不需要加速访问对应的第一主存储器时，将所述加速存储设备中存储的数据迁移到所述第一主存储器中，控制第一业务主机从访问所述加速存储设备中存储的数据切换回访问所述第一主存储器中存储的数据。
- 如权利要求1所述的服务器，其特征在于，所述检测单元在检测到第一业务主机需要加速访问对应的第一主存储器时，具体用于：所述检测单元检测到第一业务主机发起访问第一主存储器的时间处于预先为所述第一业务主机配置的加速访问时间范围内时，确定第一业务主机需要加速访问对应的第一主存储器；或，所述检测单元检测到第一业务主机发起访问第一主存储器的频率值大于预先为所述第一业务主机配置的加速访问频率阈值时，确定第一业务主机需要加速访问对应的第一主存储器。
- 如权利要求3所述的服务器，其特征在于，包括：所述检测单元，还用于检测当前时间是否到达所述加速访问时间范围的结束时间点，若是，则确定所述第一业务主机不需要加速访问对应的第一主存储器；或所述检测单元，还用于检测第一业务主机对第一主存储器的访问频率是否小于为所述第一业务主机配置的加速访问频率阈值，若是，则确定所述第一业务主机不需要加速访问对应的第一主存储器。
- 如权利要求2所述的服务器，其特征在于，所述迁移单元，还用于在控制第一业务主机从访问所述加速存储设备中存储的数据切换回访问所述第一主存储器中存储的数据之后，将所述加速存储设备中存储的数据清除。
- 一种数据访问方法，其特征在于，包括：检测至少一个业务主机中需要加速访问对应主存储器的第一业务主机；在检测到所述第一业务主机时，建立所述第一业务主机与所述加速存储设备的连接关系；将所述第一业务主机对应的第一存储器中存储的数据迁移到所述加速存储设备中，并控制所述第一业务主机从访问第一主存储器中存储的数据切换至访问所述加速存储设备中存储的数据，其中，每个业务主机对应一个主存储器，所述主存储器用于为所述业务主机提供数据存储，所述加速存储设备的存储速度大于所述主存储器的存储速度。
- 如权利要求6所述的方法，其特征在于，还包括：在控制第一业务主机从访问第一主存储器中存储的数据切换至访问所述加速存储设备中存储的数据之后，检测到所述第一业务主机不需要加速访问对应的第一主存储器时，将所述加速存储设备中存储的数据迁移到所述第一主存储器中，控制第一业务主机从访问所述加速存储设备中存储的数据切 换回访问所述第一主存储器中存储的数据。
- 如权利要求6所述的方法，其特征在于，检测到第一业务主机需要加速访问对应的第一主存储器，包括：检测到第一业务主机发起访问第一主存储器的时间处于预先为所述第一业务主机配置的加速访问时间范围内时，确定第一业务主机需要加速访问对应的第一主存储器；或，检测到第一业务主机发起访问第一主存储器的频率值大于预先为所述第一业务主机配置的加速访问频率阈值时，确定第一业务主机需要加速访问对应的第一主存储器。
- 如权利要求8所述的方法，其特征在于，还包括：检测当前时间是否到达所述加速访问时间范围的结束时间点，若是，则确定所述第一业务主机不需要加速访问对应的第一主存储器；或检测第一业务主机对第一主存储器的访问频率是否小于为所述第一业务主机配置的加速访问频率阈值，若是，则确定所述第一业务主机不需要加速访问对应的第一主存储器。
- 如权利要求7所述的方法，其特征在于，在控制第一业务主机从访问所述加速存储设备中存储的数据切换回访问所述第一主存储器中存储的数据之后，还包括：将所述加速存储设备中存储的数据清除。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511033374.4A CN105677248A (zh) | 2015-12-31 | 2015-12-31 | 一种数据访问方法和装置 |
| CN201511033374.4 | 2015-12-31 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2017113861A1 true WO2017113861A1 (zh) | 2017-07-06 |
Family
ID=56190038
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2016/097817 WO2017113861A1 (zh) | 2015-12-31 | 2016-09-01 | 一种数据访问方法和装置 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN105677248A (zh) |
| WO (1) | WO2017113861A1 (zh) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105677248A (zh) * | 2015-12-31 | 2016-06-15 | 华为技术有限公司 | 一种数据访问方法和装置 |
| CN106774018B (zh) * | 2017-02-15 | 2018-03-27 | 山东省环境保护信息中心 | 一种污染源自动监测设备动态管控系统 |
| CN107133128A (zh) * | 2017-05-11 | 2017-09-05 | 上海新储集成电路有限公司 | 一种数据云存储系统及方法 |
| US12056374B2 (en) * | 2021-02-03 | 2024-08-06 | Alibaba Group Holding Limited | Dynamic memory coherency biasing techniques |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1664794A (zh) * | 2005-03-14 | 2005-09-07 | 北京邦诺存储科技有限公司 | 一种可扩充的高速存储网络缓存系统 |
| US20130111172A1 (en) * | 2011-10-31 | 2013-05-02 | International Business Machines Corporation | Data Migration Between Storage Devices |
| CN104102454A (zh) * | 2013-04-07 | 2014-10-15 | 杭州信核数据科技有限公司 | 一种自动实现分层存储的方法和管理分层存储的系统 |
| CN104199784A (zh) * | 2014-08-20 | 2014-12-10 | 浪潮(北京)电子信息产业有限公司 | 一种基于分级存储的数据迁移方法及装置 |
| CN104793901A (zh) * | 2015-04-09 | 2015-07-22 | 北京鲸鲨软件科技有限公司 | 一种存储装置及存储方法 |
| CN105677248A (zh) * | 2015-12-31 | 2016-06-15 | 华为技术有限公司 | 一种数据访问方法和装置 |
-
2015
- 2015-12-31 CN CN201511033374.4A patent/CN105677248A/zh active Pending
-
2016
- 2016-09-01 WO PCT/CN2016/097817 patent/WO2017113861A1/zh active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1664794A (zh) * | 2005-03-14 | 2005-09-07 | 北京邦诺存储科技有限公司 | 一种可扩充的高速存储网络缓存系统 |
| US20130111172A1 (en) * | 2011-10-31 | 2013-05-02 | International Business Machines Corporation | Data Migration Between Storage Devices |
| CN104102454A (zh) * | 2013-04-07 | 2014-10-15 | 杭州信核数据科技有限公司 | 一种自动实现分层存储的方法和管理分层存储的系统 |
| CN104199784A (zh) * | 2014-08-20 | 2014-12-10 | 浪潮(北京)电子信息产业有限公司 | 一种基于分级存储的数据迁移方法及装置 |
| CN104793901A (zh) * | 2015-04-09 | 2015-07-22 | 北京鲸鲨软件科技有限公司 | 一种存储装置及存储方法 |
| CN105677248A (zh) * | 2015-12-31 | 2016-06-15 | 华为技术有限公司 | 一种数据访问方法和装置 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105677248A (zh) | 2016-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6564082B2 (ja) | バーチャル環境におけるダイナミックストレージ階層化 | |
| US8782335B2 (en) | Latency reduction associated with a response to a request in a storage system | |
| US20230350595A1 (en) | Data Migration Method, Host, and Solid State Disk | |
| US10462012B1 (en) | Seamless data migration to the cloud | |
| CN106569738B (zh) | 一种删除级联快照的方法及装置 | |
| US9354907B1 (en) | Optimized restore of virtual machine and virtual disk data | |
| TWI706315B (zh) | 儲存元件 | |
| US9182912B2 (en) | Method to allow storage cache acceleration when the slow tier is on independent controller | |
| WO2016078420A1 (zh) | 虚拟机处理方法和虚拟计算机系统 | |
| US10552089B2 (en) | Data processing for managing local and distributed storage systems by scheduling information corresponding to data write requests | |
| WO2017113861A1 (zh) | 一种数据访问方法和装置 | |
| WO2014124576A1 (zh) | 内存管理方法、内存管理装置及numa系统 | |
| US8732429B2 (en) | Preserving a deleted data volume | |
| US8868877B2 (en) | Creating encrypted storage volumes based on thin-provisioning mode information | |
| CN106534308B (zh) | 一种分布式存储系统中解决数据块访问热点的方法及装置 | |
| CN106776147B (zh) | 一种差异数据备份方法和差异数据备份装置 | |
| US8572338B1 (en) | Systems and methods for creating space-saving snapshots | |
| US20160110265A1 (en) | Handling server and client operations uninterruptedly during pack and audit processes | |
| TW201723857A (zh) | 使用多串流的系統、方法以及製品 | |
| WO2015035814A1 (zh) | 一种写数据方法及存储设备 | |
| WO2015078193A1 (zh) | 存储空间的管理方法和存储管理装置 | |
| WO2023103704A1 (zh) | 数据处理方法、存储介质和处理器 | |
| US9645946B2 (en) | Encryption for solid state drives (SSDs) | |
| JP2017531892A (ja) | ブロックレベル記憶デバイスのスナップショットを実行するための改善された装置および方法 | |
| CN109144403B (zh) | 一种用于云盘模式切换的方法与设备 |
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: 16880654 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 16880654 Country of ref document: EP Kind code of ref document: A1 |