CN103473180A - Method and system for storing data - Google Patents
Method and system for storing data Download PDFInfo
- Publication number
- CN103473180A CN103473180A CN2013103893437A CN201310389343A CN103473180A CN 103473180 A CN103473180 A CN 103473180A CN 2013103893437 A CN2013103893437 A CN 2013103893437A CN 201310389343 A CN201310389343 A CN 201310389343A CN 103473180 A CN103473180 A CN 103473180A
- Authority
- CN
- China
- Prior art keywords
- data
- ram
- water level
- dirty data
- dirty
- Prior art date
- Legal status (The legal status 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 status listed.)
- Granted
Links
Images
Landscapes
- Techniques For Improving Reliability Of Storages (AREA)
- Memory System Of A Hierarchy Structure (AREA)
Abstract
本发明实施例公开了一种数据存储方法及系统,获取RAM脏数据水位值,检测RAM脏数据水位提高,比较RAM脏数据水位值和预设阈值,当RAM脏数据水位值小于预设阈值,识别RAM脏数据是否为热点数据,识别为热点的数据再写入高速存储设备,可以避免过多的数据写入高速存储设备,解决非热点数据占用高速存储设备的过多资源导致的热点数据被挤出高速存储设备的问题;同时还能解决过多数据写入高速存储设备导致减少高速存储设备的使用寿命的问题。并且,若RAM脏数据水位提高,并且RAM脏数据水位值大于预设阈值,直接将RAM脏数据写入高速存储设备,可以解决数据写入低速存储设备,导致严重影响数据的存储速率,形成存储延时的问题。
The embodiment of the present invention discloses a data storage method and system, which acquires the water level value of RAM dirty data, detects the increase of the water level of RAM dirty data, compares the water level value of RAM dirty data with a preset threshold value, and when the water level value of RAM dirty data is less than the preset threshold value, Identify whether dirty data in RAM is hot data, and then write hot data to high-speed storage devices, which can avoid excessive data writing to high-speed storage devices, and solve the problem of hot data being blocked due to non-hot data occupying too many resources of high-speed storage devices. The problem of squeezing out high-speed storage devices; at the same time, it can also solve the problem of reducing the service life of high-speed storage devices due to excessive data writing into high-speed storage devices. Moreover, if the water level of RAM dirty data increases, and the water level value of RAM dirty data is greater than the preset threshold, directly writing RAM dirty data into high-speed storage devices can solve the problem of data writing into low-speed storage devices, which will seriously affect the data storage rate and cause storage Delay problem.
Description
技术领域technical field
本发明涉及数据处理技术领域,更具体地说,涉及一种数据存储方法及系统。The present invention relates to the technical field of data processing, and more specifically, to a data storage method and system.
背景技术Background technique
目前,现有的数据存储方法一般为:存储数据前先对数据进行热点识别,若识别为热点数据,则将热点数据写入高速存储设备,例如:SSD(Solid StateDisk,固态硬盘);若识别为非热点数据,则将非热点数据写入低速存储设备,例如:HDD(Hard Disk Drive,硬盘驱动器)。At present, the existing data storage methods are generally as follows: before storing the data, first identify the hotspot of the data, if it is identified as hotspot data, then write the hotspot data into a high-speed storage device, such as: SSD (Solid State Disk, solid state drive); If it is non-hot data, write the non-hot data to a low-speed storage device, such as: HDD (Hard Disk Drive, hard disk drive).
然而,在上述数据存储方法中,当出现突发写的情况时,由于突发写数据一般为非热点数据,会被写入低速存储设备。但是低速存储设备性能低,会严重影响数据的存储速率,形成存储延时。However, in the above data storage method, when a burst write occurs, since the burst write data is generally non-hot data, it will be written into a low-speed storage device. However, the low performance of low-speed storage devices will seriously affect the data storage rate and cause storage delay.
为解决上述问题,现有技术还有一种数据存储方法,即存储数据前不进行热点识别,而直接将数据写入高速存储设备,再写入低速存储设备。然而,该方法会导致非热点数据占用过多高速存储设备的过多资源,导致热点数据被挤出高速存储设备;并且,过多数据写入高速存储设备还会减少高速存储设备的使用寿命。In order to solve the above problems, there is another data storage method in the prior art, that is, without performing hotspot identification before storing data, but directly writing data into a high-speed storage device, and then writing it into a low-speed storage device. However, this method will cause non-hot data to occupy too many resources of the high-speed storage device, causing hot data to be squeezed out of the high-speed storage device; and writing too much data to the high-speed storage device will also reduce the service life of the high-speed storage device.
发明内容Contents of the invention
有鉴于此,本发明实施例提供一种数据存储方法,以解决现有数据存储方法中存在的非热点数据占用高速存储设备的过多资源,导致热点数据被挤出高速存储设备的问题以及过多数据写入高速存储设备导致减少高速存储设备的使用寿命的问题。In view of this, an embodiment of the present invention provides a data storage method to solve the problems in existing data storage methods that non-hot data occupy too many resources of high-speed storage devices, causing hot data to be squeezed out of high-speed storage devices and the problem of excessive Writing a lot of data to a high-speed storage device leads to a problem of reducing the service life of the high-speed storage device.
为了实现上述目的,现提出的方案如下:In order to achieve the above purpose, the proposed scheme is as follows:
本发明实施例的第一方面提供一种数据存储方法,包括:The first aspect of the embodiments of the present invention provides a data storage method, including:
获取随机存储器RAM脏数据水位值;Obtain the random access memory RAM dirty data water level value;
根据获取的所述RAM脏数据水位值,判断所述RAM脏数据水位是否提高;According to the obtained RAM dirty data water level value, it is judged whether the RAM dirty data water level has increased;
若所述RAM脏数据水位提高,则比较所述RAM脏数据水位值和预设阈值;If the RAM dirty data water level increases, then compare the RAM dirty data water level value with a preset threshold;
若所述RAM脏数据水位值小于所述预设阈值,则识别所述RAM脏数据是否为热点数据;If the RAM dirty data water level value is less than the preset threshold, then identify whether the RAM dirty data is hot data;
若识别为热点数据,则将所述RAM脏数据写入高速存储设备;否则写入低速存储设备;If identified as hot data, then write the RAM dirty data into a high-speed storage device; otherwise, write it into a low-speed storage device;
若所述RAM脏数据水位提高,并且所述RAM脏数据水位值大于所述预设阈值,将所述RAM脏数据写入所述高速存储设备。If the RAM dirty data water level increases, and the RAM dirty data water level value is greater than the preset threshold, write the RAM dirty data into the high-speed storage device.
在本发明实施例的第一方面的第一种实施方式中,所述数据存储方法还包括:In the first implementation manner of the first aspect of the embodiments of the present invention, the data storage method further includes:
若所述RAM脏数据水位未提高,获取所述RAM脏数据占用的存储空间值;If the water level of the dirty data in the RAM has not increased, obtain the value of the storage space occupied by the dirty data in the RAM;
若所述RAM脏数据占用的存储空间值大于预设值,将所述RAM脏数据写入所述低速存储设备。If the storage space occupied by the RAM dirty data is greater than a preset value, write the RAM dirty data into the low-speed storage device.
在本发明实施例的第一方面的第一实施例方式中或者本发明实施例的第一方面的第二实施例方式中,所述判断所述RAM脏数据水位是否提高包括:In the first embodiment of the first aspect of the embodiments of the present invention or the second embodiment of the first aspect of the embodiments of the present invention, the judging whether the RAM dirty data level has increased includes:
判断所述RAM脏数据水位值的提升速率是否达到预设速率;Judging whether the promotion rate of the RAM dirty data water level value reaches a preset rate;
或者,判断所述RAM脏数据水位值是否达到预设水位值。Or, it is judged whether the water level value of the RAM dirty data reaches a preset water level value.
在本发明实施例的第一方面的第一实施例方式中或者本发明实施例的第一方面的第二实施例方式中,在所述RAM脏数据水位值小于所述预设阈值、且识别所述RAM脏数据为热点数据,将所述RAM脏数据写入所述高速存储设备后,还包括:对所述高速存储设备存储的所述RAM脏数据进行标记。In the first embodiment of the first aspect of the embodiments of the present invention or in the second embodiment of the first aspect of the embodiments of the present invention, when the RAM dirty data water level value is less than the preset threshold and the identification The RAM dirty data is hot data, and after writing the RAM dirty data into the high-speed storage device, the method further includes: marking the RAM dirty data stored in the high-speed storage device.
在本发明实施例的第一方面的第一实施例方式中或者本发明实施例的第一方面的第二实施例方式中,在所述RAM脏数据水位值大于所述预设阈值情况下,将所述RAM脏数据写入所述高速存储设备后,还包括:对所述高速存储设备存储的所述RAM脏数据进行标记。In the first embodiment of the first aspect of the embodiments of the present invention or the second embodiment of the first aspect of the embodiments of the present invention, when the RAM dirty data water level value is greater than the preset threshold, After writing the RAM dirty data into the high-speed storage device, the method further includes: marking the RAM dirty data stored in the high-speed storage device.
在本发明实施例的第一方面的第四实施例方式中或者本发明实施例的第一方面的第五实施例方式中,所述数据存储方法还包括:In the fourth embodiment of the first aspect of the embodiments of the present invention or the fifth embodiment of the first aspect of the embodiments of the present invention, the data storage method further includes:
接收到淘汰所述高速存储设备存储的数据的指令后,查询所述高速存储设备上存储的设置有所述标记的数据;After receiving the instruction to eliminate the data stored in the high-speed storage device, query the data stored on the high-speed storage device with the mark;
将设置有所述标记的数据由所述高速存储设备写入所述低速存储设备。Writing the data set with the flag from the high-speed storage device to the low-speed storage device.
在本发明实施例的第一方面的第六实施例方式中,所述查询所述高速存储设备上存储的设置有所述标记的数据后还包括:In the sixth embodiment of the first aspect of the embodiments of the present invention, after querying the data stored on the high-speed storage device with the tag set, it further includes:
选取预设数量的设置有所述标记的数据对应的存储块;Select a preset number of storage blocks corresponding to the data set with the mark;
将所述选取的存储块合并为一个存储块。Merge the selected storage blocks into one storage block.
在本发明实施例的第一方面的第一实施例方式中或者本发明实施例的第一方面的第二实施例方式中,所述预设阈值包括预设低水位阈值和预设高水位阈值,其中,所述预设高水位阈值大于所述预设低水位阈值。In the first embodiment of the first aspect of the embodiment of the present invention or in the second embodiment of the first aspect of the embodiment of the present invention, the preset threshold includes a preset low water level threshold and a preset high water level threshold , wherein the preset high water level threshold is greater than the preset low water level threshold.
在本发明实施例的第一方面的第八实施例方式中,所述若所述RAM脏数据水位值小于所述预设阈值,则识别所述RAM脏数据是否为热点数据,为:In the eighth embodiment of the first aspect of the embodiments of the present invention, if the RAM dirty data water level value is less than the preset threshold, then identifying whether the RAM dirty data is hot data is:
若所述RAM脏数据水位值小于所述预设低水位阈值,则识别所述RAM脏数据是否为热点数据;If the RAM dirty data water level value is less than the preset low water level threshold, then identify whether the RAM dirty data is hot data;
或者,所述RAM脏数据水位值小于所述预设高水位阈值,则识别所述RAM脏数据是否为热点数据。Alternatively, if the RAM dirty data water level value is smaller than the preset high water level threshold, it is identified whether the RAM dirty data is hot data.
在本发明实施例的第一方面的第八实施例方式中,所述若所述RAM脏数据水位提高,并且所述RAM脏数据水位值大于所述预设阈值,将所述RAM脏数据写入所述高速存储设备,为:In the eighth embodiment of the first aspect of the embodiments of the present invention, if the RAM dirty data water level increases, and the RAM dirty data water level value is greater than the preset threshold, the RAM dirty data is written to Into the high-speed storage device, for:
若所述RAM脏数据水位提高,并且所述RAM缓存数据水位值大于所述预设高水位阈值,将所述RAM脏数据写入所述高速存储设备;If the RAM dirty data water level increases, and the RAM cache data water level value is greater than the preset high water level threshold, write the RAM dirty data into the high-speed storage device;
或者,若所述RAM脏数据水位提高,并且所述RAM脏数据水位值大于所述预设低水位阈值,将所述RAM脏数据写入所述高速存储设备。Or, if the RAM dirty data water level increases, and the RAM dirty data water level value is greater than the preset low water level threshold, write the RAM dirty data into the high-speed storage device.
在本发明实施例的第一方面提供了一种数据存储系统,包括:A data storage system is provided in a first aspect of an embodiment of the present invention, including:
第一获取单元,用于获取所述RAM脏数据水位值;A first acquisition unit, configured to acquire the RAM dirty data water level value;
判断单元,用于根据获取的所述RAM脏数据水位值,判断所述RAM脏数据水位是否提高;A judging unit, configured to judge whether the RAM dirty data water level has increased according to the obtained RAM dirty data water level value;
第一比较单元,用于所述判断单元判断所述RAM脏数据水位提高时,比较所述RAM脏数据水位值和预设阈值;The first comparison unit is used for comparing the RAM dirty data water level value with a preset threshold value when the judging unit judges that the RAM dirty data water level increases;
热点识别单元,用于所述第一比较单元判断所述RAM脏数据水位值小于预设阈值,识别所述RAM脏数据是否为热点数据;A hotspot identification unit, used for the first comparison unit to judge that the RAM dirty data water level value is less than a preset threshold, and identify whether the RAM dirty data is hotspot data;
数据写入单元,用于所述热点识别单元识别所述RAM脏数据为热点数据,将所述RAM脏数据写入高速存储设备;所述热点识别单元识别所述RAM脏数据为非热点数据,将所述RAM脏数据写入低速存储设备;所述第一比较单元判断所述RAM缓存数据水位值大于预设阈值,将所述RAM脏数据写入所述高速存储设备。A data writing unit, used for the hotspot identification unit to identify the RAM dirty data as hotspot data, and write the RAM dirty data into a high-speed storage device; the hotspot identification unit identifies the RAM dirty data as non-hotspot data, Writing the RAM dirty data into a low-speed storage device; the first comparison unit judges that the RAM cache data water level value is greater than a preset threshold, and writes the RAM dirty data into the high-speed storage device.
在本发明实施例的第二方面的第一实施例方式中,所述数据存储系统还包括:In the first embodiment of the second aspect of the embodiments of the present invention, the data storage system further includes:
第二获取单元,用于所述判断单元判断所述RAM脏数据水位未提高,获取所述RAM脏数据占用的存储空间值;The second acquisition unit is used for the judging unit to judge that the water level of the RAM dirty data has not increased, and to acquire the storage space value occupied by the RAM dirty data;
第二比较单元,用于比较所述RAM脏数据占用的存储空间值和预设值;The second comparison unit is used to compare the storage space value occupied by the RAM dirty data with a preset value;
所述数据写入单元还用于所述第二比较单元判断所述RAM脏数据占用的存储空间值大于预设值,将所述RAM脏数据写入所述低速存储设备。The data writing unit is also used for the second comparison unit to judge that the storage space occupied by the RAM dirty data is greater than a preset value, and write the RAM dirty data into the low-speed storage device.
在本发明实施例的第二方面的第一实施例方式中或者在本发明实施例的第二方面的第二实施例方式中,所述判断单元包括:In the first embodiment of the second aspect of the embodiments of the present invention or in the second embodiment of the second aspect of the embodiments of the present invention, the judging unit includes:
第一判断单元,用于判断所述RAM脏数据水位值的提升速率是否达到预设速率;The first judging unit is used to judge whether the raising rate of the RAM dirty data water level reaches a preset rate;
第二判断单元,用于判断所述RAM脏数据水位值是否达到预设水位值。The second judging unit is configured to judge whether the dirty data water level of the RAM reaches a preset water level.
在本发明实施例的第二方面的第一实施例方式中或者在本发明实施例的第二方面的第二实施例方式中,所述数据存储系统还包括:In the first embodiment of the second aspect of the embodiments of the present invention or in the second embodiment of the second aspect of the embodiments of the present invention, the data storage system further includes:
第一标记单元,用于在所述数据写入单元在所述热点识别单元识别所述RAM脏数据为热点数据,对写入所述高速存储设备的RAM脏数据进行标记。The first marking unit is configured to identify the RAM dirty data as hotspot data in the data writing unit and the hot spot identifying unit, and mark the RAM dirty data written into the high-speed storage device.
在本发明实施例的第二方面的第一实施例方式中或者在本发明实施例的第二方面的第二实施例方式中,所述数据存储系统还包括:In the first embodiment of the second aspect of the embodiments of the present invention or in the second embodiment of the second aspect of the embodiments of the present invention, the data storage system further includes:
第二标记单元,用于在所述第一比较单元判断所述RAM脏数据水位值大于所述预设阈值情况下,对写入所述高速存储设备的RAM脏数据进行标记。The second marking unit is configured to mark the RAM dirty data written into the high-speed storage device when the first comparison unit judges that the RAM dirty data water level value is greater than the preset threshold.
在本发明实施例的第二方面的第四实施例方式中或者在本发明实施例的第二方面的第五实施例方式中,所述数据存储系统还包括:In the fourth embodiment of the second aspect of the embodiments of the present invention or in the fifth embodiment of the second aspect of the embodiments of the present invention, the data storage system further includes:
接收单元,用于接收淘汰所述高速存储设备存储的数据的指令;a receiving unit, configured to receive an instruction to eliminate data stored in the high-speed storage device;
查询单元,用于所述接收单元接收到淘汰所述高速存储设备存储的数据的指令后,查询所述高速存储设备上存储的设置有所述标记的数据;a query unit, configured to query the data stored on the high-speed storage device with the flag after the receiving unit receives an instruction to eliminate the data stored in the high-speed storage device;
删除单元,用于将设置有所述标记的数据由所述高速存储设备写入所述低速存储设备。A deletion unit, configured to write the data set with the flag from the high-speed storage device into the low-speed storage device.
在本发明实施例的第二方面的第六实施例方式中,所述数据存储系统还包括:In the sixth embodiment of the second aspect of the embodiments of the present invention, the data storage system further includes:
选取单元,用于选取预设数量的设置有所述标记的数据对应的存储块;A selection unit, configured to select a preset number of storage blocks corresponding to the data with the flag set;
合并单元,用于将所述选取的存储块合并为一个存储块。The merging unit is configured to combine the selected storage blocks into one storage block.
在本发明实施例的第二方面的第一实施例方式中或者在本发明实施例的第二方面的第二实施例方式中,所述第一比较单元包括:In the first embodiment of the second aspect of the embodiments of the present invention or in the second embodiment of the second aspect of the embodiments of the present invention, the first comparison unit includes:
阈值比较单元,用于将所述RAM脏数据水位值分别与预设低水位阈值和预设高水位阈值进行比较,其中,所述预设高水位阈值大于所述预设低水位阈值。A threshold comparison unit, configured to compare the RAM dirty data water level with a preset low water level threshold and a preset high water level threshold, wherein the preset high water level threshold is greater than the preset low water level threshold.
在本发明实施例的第二方面的第八实施例方式中,所述热点识别单元包括:In the eighth embodiment of the second aspect of the embodiments of the present invention, the hotspot identification unit includes:
第一热点识别单元,用于所述阈值比较单元判断所述RAM脏数据水位值小于所述预设低水位阈值,识别所述RAM脏数据是否为热点数据;The first hotspot identification unit is used for the threshold comparison unit to judge that the RAM dirty data water level value is less than the preset low water level threshold, and to identify whether the RAM dirty data is hotspot data;
或者,所述热点识别单元包括:Alternatively, the hotspot identification unit includes:
第二热点识别单元,用于所述阈值比较单元判断所述RAM脏数据水位值小于所述预设高水位阈值,识别所述RAM脏数据是否为热点数据。The second hotspot identification unit is used for the threshold comparison unit to determine whether the RAM dirty data water level is smaller than the preset high water level threshold, and to identify whether the RAM dirty data is hotspot data.
在本发明实施例的第二方面的第八实施例方式中,所述数据写入单元包括:In the eighth embodiment of the second aspect of the embodiments of the present invention, the data writing unit includes:
第一数据写入单元,用于所述阈值比较单元判断所述RAM缓存数据水位值大于所述预设高水位阈值,将所述RAM脏数据写入所述高速存储设备;The first data writing unit is used for the threshold comparison unit to judge that the RAM cache data water level value is greater than the preset high water level threshold, and write the RAM dirty data into the high-speed storage device;
或者,所述数据写入单元包括:Alternatively, the data writing unit includes:
第二数据写入单元,用于所述阈值比较单元判断所述RAM脏数据水位值大于所述预设低水位阈值,将所述RAM脏数据写入所述高速存储设备。The second data writing unit is used for the threshold comparison unit to judge that the RAM dirty data water level value is greater than the preset low water level threshold, and write the RAM dirty data into the high-speed storage device.
从上述的技术方案可以看出,本发明实施例公开的数据存储方法中,在存储数据前,先获取RAM脏数据水位值,当检测到所述RAM脏数据水位提高时,说明当前出现突发写情况,此时,根据RAM脏数据水位值和预设阈值的关系确定RAM脏数据的存储方式,具体的,当所述RAM脏数据水位值小于预设阈值,说明需要写入的数据比较少,识别所述RAM脏数据是否为热点数据,识别为热点的数据再写入高速存储设备,可以避免过多的数据写入高速存储设备,解决非热点数据占用高速存储设备的过多资源导致的热点数据被挤出高速存储设备的问题;同时还能解决过多数据写入高速存储设备导致减少高速存储设备的使用寿命的问题。It can be seen from the above technical solutions that in the data storage method disclosed in the embodiment of the present invention, before storing data, the RAM dirty data water level value is obtained first, and when it is detected that the RAM dirty data water level has increased, it indicates that a burst Write situation, at this time, determine the storage mode of RAM dirty data according to the relationship between the RAM dirty data water level value and the preset threshold value, specifically, when the RAM dirty data water level value is less than the preset threshold value, it means that the data to be written is relatively small , identify whether the RAM dirty data is hot data, and then write the hot data into the high-speed storage device, which can avoid excessive data writing into the high-speed storage device, and solve the problem caused by non-hot data occupying too many resources of the high-speed storage device The problem of hot data being squeezed out of high-speed storage devices; at the same time, it can also solve the problem of reducing the service life of high-speed storage devices due to excessive data writing into high-speed storage devices.
并且,本发明实施例公开的数据存储方法中,若所述RAM脏数据水位提高,并且所述RAM脏数据水位值大于预设阈值,说明需要写入的数据比较多,此时直接将RAM脏数据写入高速存储设备,可以解决数据写入低速存储设备,由于低速存储设备性能低,导致严重影响数据的存储速率,形成存储延时的问题。Moreover, in the data storage method disclosed in the embodiment of the present invention, if the RAM dirty data water level increases, and the RAM dirty data water level value is greater than the preset threshold value, it means that there is more data to be written. Writing data to high-speed storage devices can solve the problem of data writing to low-speed storage devices. Due to the low performance of low-speed storage devices, it will seriously affect the data storage rate and cause storage delays.
附图说明Description of drawings
为了更清楚地说明本发明实施例中的技术方案,下面将对实施例描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings that need to be used in the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those skilled in the art, other drawings can also be obtained based on these drawings without creative effort.
图1为本发明实施例公开的一种数据存储方法的流程图;FIG. 1 is a flowchart of a data storage method disclosed in an embodiment of the present invention;
图2为本发明另一实施例公开的一种数据存储方法的流程图;Fig. 2 is a flow chart of a data storage method disclosed in another embodiment of the present invention;
图3为本发明另一实施例公开的一种数据存储方法的流程图;FIG. 3 is a flow chart of a data storage method disclosed in another embodiment of the present invention;
图4为本发明另一实施例公开的一种数据存储方法的流程图;Fig. 4 is a flowchart of a data storage method disclosed in another embodiment of the present invention;
图5为本发明另一实施例公开的一种数据存储方法的流程图;Fig. 5 is a flowchart of a data storage method disclosed in another embodiment of the present invention;
图6为本发明实施例公开的一种数据存储系统的结构示意图;FIG. 6 is a schematic structural diagram of a data storage system disclosed in an embodiment of the present invention;
图7为本发明另一实施例公开的一种数据存储系统的结构示意图;Fig. 7 is a schematic structural diagram of a data storage system disclosed in another embodiment of the present invention;
图8为本发明另一实施例公开的一种数据存储系统的应用图。Fig. 8 is an application diagram of a data storage system disclosed by another embodiment of the present invention.
具体实施方式Detailed ways
下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有作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。The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
以下先将本发明实施例应用到的关键术的中英文对照译义进行说明。The Chinese and English translations of the key techniques applied in the embodiments of the present invention will be described below.
RAM:random access memory,随机存储器;RAM: random access memory, random access memory;
SSD:Solid State Device/Solid State Drive,固态硬盘;SSD: Solid State Device/Solid State Drive, solid state drive;
HDD:Hard Disk Drive,硬盘驱动器。HDD: Hard Disk Drive, hard disk drive.
本发明实施例提供一种数据存储方法,以解决现有数据存储方法中存在的非热点数据占用高速存储设备的过多资源,导致热点数据被挤出高速存储设备的问题以及过多数据写入高速存储设备导致减少高速存储设备的使用寿命的问题。The embodiment of the present invention provides a data storage method to solve the problem of non-hot data occupying too many resources of high-speed storage devices in existing data storage methods, causing hot data to be squeezed out of high-speed storage devices and excessive data writing A high-speed memory device causes a problem of reducing the service life of the high-speed memory device.
此处需要说明的是:本发明以下所有实施例中所提到的高速存储设备为现有技术中存储速度较快的存储设备,如:SSD盘,SSD阵列等;对应的,低速存储设备为存储速度较慢的存储设备,如:HDD等。What needs to be explained here is: the high-speed storage device mentioned in all the following embodiments of the present invention is a storage device with a faster storage speed in the prior art, such as: SSD disk, SSD array, etc.; correspondingly, the low-speed storage device is Storage devices with slow storage speed, such as HDD, etc.
参见图1,本发明实施例公开的数据存储方法,包括步骤:Referring to Fig. 1, the data storage method disclosed by the embodiment of the present invention includes steps:
S101、获取RAM脏数据水位值;S101. Acquiring the water level value of RAM dirty data;
其中:数据在存储过程中,先将数据缓存到RAM中,然后,再将RAM中的数据写入到高速存储设备或者低速存储设备。而需要从RAM写入到高速存储设备或者低速存储设备中的数据就称为RAM脏数据。Wherein: during the data storage process, the data is first cached in the RAM, and then the data in the RAM is written into a high-speed storage device or a low-speed storage device. Data that needs to be written from the RAM to a high-speed storage device or a low-speed storage device is called RAM dirty data.
并且,RAM中的变量信息包括有标识信息,该标识信息反映RAM中缓存的数据是否为脏数据。所述RAM脏数据水位即反映RAM中缓存的脏数据的数量,当缓存的数量多时,所述RAM脏数据水位值高,当缓存的数量少时,所述RAM脏数据水位值低。而当发生突发写情况时,缓存入RAM的数据会是大批量的,这样会导致需要从RAM写入到高速存储设备或者低速存储设备中的数据也是大批量,此时,RAM的脏数据就会增多,RAM的脏数据的水位值就会提升。Moreover, the variable information in the RAM includes identification information, and the identification information reflects whether the data cached in the RAM is dirty data. The RAM dirty data water level reflects the amount of dirty data cached in the RAM. When the cached quantity is large, the RAM dirty data water level value is high, and when the cached quantity is small, the RAM dirty data water level value is low. When a burst write situation occurs, the data cached into RAM will be in large quantities, which will lead to a large quantity of data that needs to be written from RAM to high-speed storage devices or low-speed storage devices. At this time, the dirty data of RAM It will increase, and the water level value of the dirty data in RAM will increase.
S102、根据获取的所述RAM脏数据水位值,判断所述RAM脏数据水位是否提高;S102. According to the obtained RAM dirty data water level value, judge whether the RAM dirty data water level has increased;
其中,通过判断所述RAM脏数据水位是否提高可以得知是否发生了突发生写情况。Wherein, by judging whether the water level of dirty data in the RAM has increased, it can be known whether a sudden writing situation has occurred.
具体的,根据获取的所述RAM脏数据水位值,判断所述RAM脏数据水位是否提高的方式可以为:判断所述RAM脏数据水位值的提升速率是否达到预设速率;Specifically, according to the obtained RAM dirty data water level value, the method of judging whether the RAM dirty data water level is increased may be: judging whether the increase rate of the RAM dirty data water level value reaches a preset rate;
其中,当所述RAM脏数据水位值的提升速率达到预设速率,说明所述RAM脏数据水位提高,此时发生了突发写情况。Wherein, when the increase rate of the dirty data water level of the RAM reaches a preset rate, it indicates that the dirty data water level of the RAM has increased, and a burst write situation has occurred at this time.
或者,通过判断所述RAM脏数据水位值是否达到预设水位值的方式确定RAM脏数据水位是否提高。Alternatively, determine whether the RAM dirty data water level has increased by judging whether the RAM dirty data water level reaches a preset water level value.
其中,当所述RAM脏数据水位值达到预设水位值时,说明RAM脏数据水位提高,发生了突发写情况。Wherein, when the dirty data water level of the RAM reaches a preset water level, it means that the dirty data water level of the RAM has increased, and a sudden writing situation has occurred.
本实施例中,评判所述RAM脏数据水位是否提高的速率和水位值的选取范围,本技术领域人员均可以根据实际情况确定。In this embodiment, the rate for judging whether the RAM dirty data water level increases and the selection range of the water level value can be determined by those skilled in the art according to actual conditions.
若提高,则执行S103、比较所述RAM脏数据水位值和预设阈值;其中,当确定RAM脏数据水位提高,说明此时发生了突发写情况,将获取的RAM脏数据水位值和预设阈值进行比较,根据比较结果选取RAM脏数据的存储方式。If it increases, then execute S103, compare the dirty data water level of the RAM with the preset threshold value; wherein, when it is determined that the dirty data water level of the RAM increases, it means that a sudden write situation has occurred at this time, and the obtained RAM dirty data water level value and preset Set the threshold for comparison, and select the storage method of RAM dirty data according to the comparison result.
具体的,所述预设阈值为RAM脏数据水位的合理水位值,反映RAM积累有脏数据,但并没有积累大量脏数据。其中,可以根据RAM的写页面的存储空间值确定阈值的取值范围,可以为RAM的写页面的存储空间值的任意的百分比,优选地,该百分比可以为50%。Specifically, the preset threshold is a reasonable water level value of the dirty data water level of the RAM, which reflects that the RAM has accumulated dirty data, but has not accumulated a large amount of dirty data. Wherein, the value range of the threshold may be determined according to the storage space value of the write page of the RAM, and may be any percentage of the storage space value of the write page of the RAM, preferably, the percentage may be 50%.
S104、若所述RAM脏数据水位值小于所述预设阈值,则识别所述RAM脏数据是否为热点数据;S104. If the water level value of the RAM dirty data is less than the preset threshold, identify whether the RAM dirty data is hot data;
其中,当所述RAM脏数据水位值小于预设阈值,说明对应的RAM脏数据比较少,即突发写的数据比较少,此时再进行存储数据之前先识别数据是否为热点数据。Wherein, when the water level value of the RAM dirty data is less than the preset threshold value, it means that the corresponding RAM dirty data is relatively small, that is, the burst write data is relatively small, and at this time, before storing the data, first identify whether the data is hot data.
具体的,所述识别数据是否为热点数据的方式可以包括:统计单位时间数据的写入频率,当写入频率达到一定值之后,认定该数据为热点数据;还可以对写入的数据进行计数,当计数达到一定值之后,认定该数据为热点数据。其中,本技术领域人员应当知道上述两种方式的设定值的设定方式及选择范围。Specifically, the method of identifying whether the data is hot data may include: counting the writing frequency of data per unit time, and when the writing frequency reaches a certain value, the data is determined to be hot data; the written data may also be counted , when the count reaches a certain value, the data is identified as hot data. Wherein, those skilled in the art should know the setting methods and selection ranges of the setting values of the above two methods.
当然,本实施例中的识别所述RAM脏数据是否为热点数据的方式不仅仅限于上述两种,还包括现有技术中所有方式,此处不再赘述。Of course, the methods for identifying whether the RAM dirty data is hot data in this embodiment are not limited to the above two methods, but also include all methods in the prior art, which will not be repeated here.
S105、若识别为热点数据,则将所述RAM脏数据写入所述高速存储设备;否则执行S106、把所述RAM脏数据写入所述低速存储设备;S105. If identified as hot data, write the RAM dirty data into the high-speed storage device; otherwise, perform S106, write the RAM dirty data into the low-speed storage device;
S107、若所述RAM脏数据水位提高,并且所述RAM缓存数据水位值大于预设阈值,将所述RAM脏数据写入所述高速存储设备。S107. If the RAM dirty data level increases and the RAM cache data level value is greater than a preset threshold, write the RAM dirty data into the high-speed storage device.
其中,当所述RAM脏数据水位提高,并且所述RAM脏数据水位值大于预设阈值,说明对应的RAM脏数据比较多,即突发写的数据比较多,此时直接将RAM脏数据写入所述高速存储设备,可以解决过多数据写入所述低速存储设备,由于所述低速存储设备性能低,导致严重影响数据的存储速率,形成存储延时的问题。Wherein, when the dirty data water level of the RAM increases, and the dirty data water level value of the RAM is greater than the preset threshold value, it means that the corresponding RAM dirty data is more, that is, there are more data written in a burst, and at this time, the dirty data of the RAM is directly written Entering the high-speed storage device can solve the problem that too much data is written into the low-speed storage device. Due to the low performance of the low-speed storage device, the storage rate of data is seriously affected and the storage delay is formed.
本实施例公开的数据存储方法中,在存储数据前,先获取所述RAM脏数据水位值,当检测到RAM脏数据水位提高时,说明当前出现突发写情况,此时,根据RAM脏数据水位值和预设阈值的关系确定RAM脏数据的存储方式,具体的,当所述RAM脏数据水位值小于预设阈值,说明需要写入的数据比较少,识别所述RAM脏数据是否为热点数据,识别为热点的数据再写入高速存储设备,可以避免过多的数据写入高速存储设备,解决非热点数据占用高速存储设备的过多资源导致的热点数据被挤出高速存储设备的问题;同时还能解决过多数据写入高速存储设备导致减少高速存储设备的使用寿命的问题。In the data storage method disclosed in this embodiment, before storing data, first obtain the water level value of the dirty data in the RAM. When it is detected that the water level of the dirty data in the RAM increases, it means that a burst write situation occurs at present. At this time, according to the dirty data in the RAM The relationship between the water level value and the preset threshold value determines the storage mode of RAM dirty data. Specifically, when the water level value of the RAM dirty data is less than the preset threshold value, it means that there is less data to be written, and it is possible to identify whether the RAM dirty data is a hotspot Data, the data identified as hotspots are then written into high-speed storage devices, which can avoid excessive data writing into high-speed storage devices, and solve the problem that non-hotspot data occupying too many resources of high-speed storage devices causes hot data to be squeezed out of high-speed storage devices ; At the same time, it can also solve the problem of reducing the service life of the high-speed storage device due to excessive data writing into the high-speed storage device.
本发明另一实施例还公开了一种数据存储方法,参见图2,包括步骤:Another embodiment of the present invention also discloses a data storage method, see Fig. 2, including steps:
S201、获取RAM脏数据水位值;S201. Obtain the water level value of RAM dirty data;
S202、根据获取的所述RAM脏数据水位值,判断所述RAM脏数据水位是否提高;S202. According to the obtained RAM dirty data water level value, determine whether the RAM dirty data water level has increased;
与上述实施例相同,判断所述RAM脏数据水位是否提高的方式可以为:Same as the above-mentioned embodiment, the method for judging whether the dirty data level of the RAM is increased can be as follows:
判断所述RAM脏数据水位值的提升速率是否达到预设速率;或者,判断所述RAM脏数据水位值是否达到预设水位值。Judging whether the increase rate of the RAM dirty data water level reaches a preset rate; or judging whether the RAM dirty data water level reaches a preset water level.
判断所述RAM脏数据水位未提高,则执行S203:获取所述RAM脏数据占用的存储空间值;If it is judged that the water level of the RAM dirty data has not increased, then perform S203: acquire the value of the storage space occupied by the RAM dirty data;
此处需要说明的是,当发生突发写情况后,会产生大批量数据缓存到RAM中,此时,所述RAM脏数据水位会提高,其中,对应突发写情况的数据可以是数据本身大,也可以是数据本身不大,但数量多,这两种情况都会导致述RAM脏数据水位提高。What needs to be explained here is that when a burst write situation occurs, a large amount of data will be cached in the RAM. At this time, the dirty data level of the RAM will increase, wherein the data corresponding to the burst write situation can be the data itself It can also be that the data itself is not large, but the number is large. Both of these situations will lead to an increase in the level of dirty data in the RAM.
然而,若只有个别数据缓存到RAM中,无论数据本身是大还是小,都不会导致所述RAM脏数据水位提高。However, if only individual data is cached in the RAM, no matter whether the data itself is large or small, the level of dirty data in the RAM will not increase.
S204、若所述RAM脏数据占用的存储空间值大于预设值,将所述RAM脏数据写入低速存储设备;S204. If the storage space value occupied by the RAM dirty data is greater than a preset value, write the RAM dirty data into a low-speed storage device;
其中,当出现个别数据缓存到RAM中的情况,获取所述RAM脏数据占用的存储空间值,将该值与预设值进行比对,当判断大于预设值,将所述RAM脏数据写入低速存储设备。这样,可以避免大数据写入高速存储设备占用资源的问题。Wherein, when individual data is cached in the RAM, the storage space value occupied by the dirty data of the RAM is obtained, and the value is compared with the preset value, and when it is judged to be greater than the preset value, the dirty data of the RAM is written into a low-speed storage device. In this way, the problem of resource occupation by writing large data into a high-speed storage device can be avoided.
并且,所述预设值可以根据实际需要进行设定,没有具体要求。Moreover, the preset value can be set according to actual needs, and there is no specific requirement.
若提高,则执行S205、比较所述RAM脏数据水位值和预设阈值;If it increases, execute S205, compare the RAM dirty data water level value with a preset threshold;
S206、若所述RAM脏数据水位值小于预设阈值,识别所述RAM脏数据是否为热点数据;S206. If the water level value of the RAM dirty data is less than a preset threshold, identify whether the RAM dirty data is hot data;
S207、若识别为热点数据,则将所述RAM脏数据写入所述高速存储设备;否则执行S208、把所述RAM脏数据写入所述低速存储设备;S207. If identified as hot data, write the RAM dirty data into the high-speed storage device; otherwise, execute S208, write the RAM dirty data into the low-speed storage device;
S209、若所述RAM脏数据水位提高,所述RAM缓存数据水位值大于预设阈值,将所述RAM脏数据写入高速存储设备。S209. If the RAM dirty data level increases, and the RAM cache data level value is greater than a preset threshold, write the RAM dirty data into a high-speed storage device.
本实施例中各个步骤的具体实现过程与上述实施例公开的内容相同,请参见上述实施例公开的内容,此处不再赘述。The specific implementation process of each step in this embodiment is the same as the content disclosed in the above embodiment, please refer to the content disclosed in the above embodiment, and will not be repeated here.
此处需要说明的是,在上述实施例的步骤S204中,若所述RAM脏数据占用的存储空间值大于预设值,将所述RAM脏数据写入低速存储设备,可以采用透写方式将所述RAM脏数据写入所述低速存储设备。It should be noted here that, in step S204 of the above embodiment, if the storage space occupied by the RAM dirty data is greater than a preset value, the RAM dirty data can be written into a low-speed storage device, and the write-through method can be used to write The RAM dirty data is written into the low-speed storage device.
具体的,所述透写方式具体指:当数据缓存到RAM后,并不反馈写完成指令,等数据写入到所述低速存储设备之后,再返回写完成指令。Specifically, the write-through mode specifically refers to: after the data is cached in the RAM, the write completion command is not fed back, and the write completion command is returned after the data is written into the low-speed storage device.
或者,步骤S204中,若所述RAM脏数据占用的存储空间值大于预设值,将所述RAM脏数据写入所述低速存储设备,可以采用回写方式将所述RAM脏数据写入低速存储设备。Alternatively, in step S204, if the storage space value occupied by the RAM dirty data is greater than a preset value, the RAM dirty data is written into the low-speed storage device, and the RAM dirty data can be written into the low-speed storage device in a write-back manner. storage device.
具体的,所述回写方式具体指:当数据缓存到RAM后,不管数据是否写入到所述低速存储设备,都返回写完成指令。Specifically, the write-back manner specifically refers to: after the data is cached in the RAM, no matter whether the data is written to the low-speed storage device, a write completion command is returned.
当然,在RAM脏数据占用的存储空间值大于预设值的情况下,将所述RAM脏数据写入所述低速存储设备的方式还可以为其他方式,此处不一一说明。Of course, in the case that the storage space occupied by the RAM dirty data is greater than a preset value, other ways of writing the RAM dirty data into the low-speed storage device may also be used, which will not be described here one by one.
本发明另一实施例还公开了一种数据存储方法,如图3所示,包括步骤:Another embodiment of the present invention also discloses a data storage method, as shown in Figure 3, including steps:
S301、获取RAM脏数据水位值;S301. Obtain the water level value of RAM dirty data;
S302、根据获取的所述RAM脏数据水位值,判断所述RAM脏数据水位是否提高;S302. According to the obtained RAM dirty data water level value, judge whether the RAM dirty data water level has increased;
若提高,则执行S303、比较所述RAM脏数据水位值和预设阈值;If it increases, execute S303, comparing the RAM dirty data water level value with a preset threshold;
S304、若所述RAM脏数据水位值小于预设阈值,识别所述RAM脏数据是否为热点数据;S304. If the water level value of the RAM dirty data is less than a preset threshold, identify whether the RAM dirty data is hot data;
S305、若识别为热点数据,则将所述RAM脏数据写入所述高速存储设备;否则执行S306、把所述RAM脏数据写入所述低速存储设备;S305. If identified as hot data, write the RAM dirty data into the high-speed storage device; otherwise, execute S306, write the RAM dirty data into the low-speed storage device;
S307、若所述RAM脏数据水位提高,并且所述RAM缓存数据水位值大于预设阈值,将所述RAM脏数据写入所述高速存储设备;S307. If the RAM dirty data water level increases, and the RAM cache data water level value is greater than a preset threshold, write the RAM dirty data into the high-speed storage device;
S308、对所述高速存储设备存储的RAM脏数据进行标记。S308. Mark the RAM dirty data stored in the high-speed storage device.
其中:步骤S305和S307中,均是将所述RAM脏数据写入高速存储设备,在将数据写入高速存储设备之后,对数据进行标记。Wherein: in steps S305 and S307, the RAM dirty data is written into the high-speed storage device, and after the data is written into the high-speed storage device, the data is marked.
本实施例中需要说明的是,将数据写入到高速存储设备一般称之为数据缓存,只有将数据最终写入到低速存储设备才称为存储数据。因此,在本发明其他的实施例中,该实施例除包括对应图3的实施例的内容外,还包括:What needs to be explained in this embodiment is that writing data to a high-speed storage device is generally called a data cache, and only writing data to a low-speed storage device is called storing data. Therefore, in other embodiments of the present invention, in addition to including the content of the embodiment corresponding to FIG. 3 , this embodiment also includes:
接收到淘汰所述高速存储设备存储的数据的指令后,查询所述高速存储设备上存储的设置有所述标记的数据;After receiving the instruction to eliminate the data stored in the high-speed storage device, query the data stored on the high-speed storage device with the mark;
将设置有所述标记的数据由所述高速存储设备写入所述低速存储设备。Writing the data set with the flag from the high-speed storage device to the low-speed storage device.
其中,对应所述高速存储设备存储有标记RAM脏数据的情况下,被标记的RAM脏数据为突发写情况时的数据,将该数据由所述高速存储设备删除至所述低速存储设备,可以释放所述高速存储设备的存储空间;并且,将数据由所述高速存储设备淘汰至所述低速存储设备,可以避免数据直接由高速存储设备删除造成数据丢失的问题。Wherein, when corresponding to the high-speed storage device storing marked RAM dirty data, the marked RAM dirty data is data in a burst write situation, and the data is deleted from the high-speed storage device to the low-speed storage device, The storage space of the high-speed storage device can be released; and the data is eliminated from the high-speed storage device to the low-speed storage device, which can avoid the problem of data loss caused by directly deleting data from the high-speed storage device.
并且,所述有标记的数据是作为优先淘汰的数据,当接收到淘汰所述高速存储设备存储的数据的指令后,先将所述高速存储设备中设置有标记的数据优先淘汰,当淘汰结束之后还可以再判断是否满足接收到的淘汰高速存储设备存储的数据的指令的需求,若仍没有满足要求,再将所述高速存储设备中没有进行标记的数据淘汰。Moreover, the marked data is data that is prioritized to be eliminated. After receiving the instruction to eliminate the data stored in the high-speed storage device, the data with the mark in the high-speed storage device is first eliminated. When the elimination is completed Afterwards, it may be further judged whether the received instruction for eliminating data stored in the high-speed storage device is satisfied, and if the requirement is still not met, then the unmarked data in the high-speed storage device is eliminated.
对应将所述高速存储设备存储的数据淘汰到所述低速存储设备的方式不同,本发明另一实施例还公开了一种数据存储方式,参见图4,包括步骤:Corresponding to the different methods of eliminating the data stored in the high-speed storage device to the low-speed storage device, another embodiment of the present invention also discloses a data storage method, as shown in FIG. 4 , including steps:
S401、获取RAM脏数据水位值;S401. Obtain the water level value of RAM dirty data;
S402、根据获取的所述RAM脏数据水位值,判断所述RAM脏数据水位是否提高;S402. According to the acquired RAM dirty data water level value, determine whether the RAM dirty data water level has increased;
若提高,则执行S403、比较所述RAM脏数据水位值和预设阈值;If it increases, execute S403, comparing the RAM dirty data water level with a preset threshold;
S404、若所述RAM脏数据水位值小于预设阈值,识别所述RAM脏数据是否为热点数据;S404. If the water level value of the RAM dirty data is less than a preset threshold, identify whether the RAM dirty data is hot data;
S405、若识别为热点数据,则将所述RAM脏数据写入所述高速存储设备;否则执行S406、把所述RAM脏数据写入所述低速存储设备;S405. If identified as hot data, write the RAM dirty data into the high-speed storage device; otherwise, execute S406, write the RAM dirty data into the low-speed storage device;
S407、若所述RAM缓存数据水位值大于预设阈值,将所述RAM脏数据写入高速存储设备;S407. If the RAM cache data water level value is greater than a preset threshold, write the RAM dirty data into a high-speed storage device;
S408、对所述高速存储设备存储的RAM脏数据进行标记;S408. Mark the RAM dirty data stored in the high-speed storage device;
同样,步骤S405和S407中,均是将所述RAM脏数据写入所述高速存储设备,在将数据写入高速存储设备之后,对数据进行标记。Similarly, in steps S405 and S407, the RAM dirty data is written into the high-speed storage device, and after the data is written into the high-speed storage device, the data is marked.
S409、接收到淘汰高速存储设备存储的数据的指令后,查询所述高速存储设备上存储的设置有所述标记的数据;S409. After receiving the instruction to eliminate the data stored in the high-speed storage device, query the data stored on the high-speed storage device with the flag;
S410、选取预设数量的设置有所述标记的数据对应的存储块;S410. Select a preset number of storage blocks corresponding to the data with the flag set;
其中,高速存储设备分为多个存储块,将数据写入高速存储设备指代将数据写入到存储块中,当数据比较大时,一个存储块不足以存储数据时,则还需要存储到相邻的存储块中。Among them, the high-speed storage device is divided into multiple storage blocks. Writing data into the high-speed storage device refers to writing data into the storage block. When the data is relatively large and one storage block is not enough to store the data, it needs to be stored in in adjacent storage blocks.
当需要将所述高速存储设备中的数据淘汰至所述低速存储设备之前,查找在所述高速存储设备的存储块中存储的数据的标记,若查找到标记,说明存储块内存储的数据是需要淘汰到所述低速存储设备中。Before the data in the high-speed storage device needs to be eliminated to the low-speed storage device, search for the mark of the data stored in the storage block of the high-speed storage device, if the mark is found, it means that the data stored in the storage block is Needs to be phased out to the low speed storage device.
并且,为了提高将数据从所述高速存储设备淘汰至所述低速存储设备的速度,可以多个将存储有具有标记的数据的存储块合并;其中,合并的数量可以是两个,也可以是其他个,可以根据实际情况设定。And, in order to improve the speed of eliminating data from the high-speed storage device to the low-speed storage device, multiple storage blocks with marked data can be stored; wherein, the number of mergers can be two or can be Others can be set according to the actual situation.
此处需要说明是,本领域技术人员应当知道选取合并的存储块为相邻的存储块。It should be noted here that those skilled in the art should know that the merged storage blocks are selected as adjacent storage blocks.
S411、将所述选取的存储块合并为一个存储块;S411. Merge the selected storage blocks into one storage block;
具体的,以合并两个存储块为例进行说明,相邻的两个存储块,有各自的起始地址和长度,第一个存储块的起始地址+长度即等于第二个存储块的起始地址。当需要合并两个存储块时,将被合并的两个存储块的第一个存储块的起始地址作为合并之后的存储块的起始地址,将两个存储块的长度作为合并后的存储块的长度。Specifically, take merging two storage blocks as an example for illustration. Two adjacent storage blocks have their own start addresses and lengths. The start address + length of the first storage block is equal to the address of the second storage block. initial address. When two storage blocks need to be merged, the starting address of the first storage block of the two storage blocks to be merged is used as the starting address of the combined storage block, and the length of the two storage blocks is used as the combined storage The length of the block.
S412、将设置有所述标记的数据由所述高速存储设备写入所述低速存储设备。S412. Write the data set with the flag from the high-speed storage device to the low-speed storage device.
此时,存储有设置有标记的数据的存储块是合并之后,将合并后的存储块的数据写入低速存储设备。At this time, after the memory blocks storing the data with the flags are merged, the data of the merged memory blocks are written into the low-speed storage device.
本发明另一实施例还公开了一种数据存储方法,如图5所示,包括:Another embodiment of the present invention also discloses a data storage method, as shown in Figure 5, including:
S501、获取RAM脏数据水位值;S501. Acquiring the water level value of RAM dirty data;
S502、根据获取的所述RAM脏数据水位值,判断所述RAM脏数据水位是否提高;S502. According to the obtained RAM dirty data water level value, determine whether the RAM dirty data water level has increased;
若提高,则执行S503、将所述RAM脏数据水位值分别与预设低水位阈值和预设高水位阈值进行比较;If it increases, then execute S503, and compare the dirty data water level value of the RAM with a preset low water level threshold and a preset high water level threshold;
其中,本实施例中,设置有低水位阈值和高水位阈值,分别将所述RAM脏数据水位值与低水位阈值和高水位阈值比较,这样,可以更加准确的得知对应的RAM脏数据的大小,即突发写的数据的大小。Wherein, in the present embodiment, a low water level threshold and a high water level threshold are set, and the RAM dirty data water level is compared with the low water level threshold and the high water level threshold respectively, so that the corresponding RAM dirty data can be known more accurately Size, that is, the size of the data written in a burst.
并且,高水位阈值和低水位阈值分别为RAM的写页面的存储空间值的任意的百分比,可以根据实际情况进行设定,只需保证高水位阈值大于低水位阈值即可。Moreover, the high water level threshold and the low water level threshold are respectively arbitrary percentages of the storage space value of the write page of the RAM, which can be set according to the actual situation, as long as the high water level threshold is greater than the low water level threshold.
S504、若所述RAM脏数据水位值小于所述预设低水位阈值,识别所述RAM脏数据是否为热点数据;S504. If the RAM dirty data water level value is less than the preset low water level threshold, identify whether the RAM dirty data is hot data;
S505、若识别为热点数据,则将所述RAM脏数据写入所述高速存储设备;否则执行S506、把所述RAM脏数据写入所述低速存储设备;S505. If identified as hot data, write the RAM dirty data into the high-speed storage device; otherwise, execute S506, write the RAM dirty data into the low-speed storage device;
S507、若所述RAM脏数据水位提高,并且所述RAM缓存数据水位值大于所述预设高水位阈值,将所述RAM脏数据写入所述高速存储设备。S507. If the RAM dirty data water level increases, and the RAM cache data water level value is greater than the preset high water level threshold, write the RAM dirty data into the high-speed storage device.
在本实施例中,所述RAM脏数据水位值小于预设低水位阈值,在进行数据存储之前,需要识别所述RAM脏数据是否为热点数据;而在RAM脏数据水位值大于预设高水位阈值,直接将所述RAM脏数据写入所述高速存储设备。In this embodiment, the RAM dirty data water level value is less than the preset low water level threshold, and before data storage, it is necessary to identify whether the RAM dirty data is hot data; and when the RAM dirty data water level value is greater than the preset high water level threshold, and directly write the RAM dirty data into the high-speed storage device.
若将所述RAM脏数据水位值与预设高水位阈值和预设低水位阈值的比较结果为:所述RAM脏数据位于预设高水位阈值和预设低水位阈值之间时,可以直接将所述RAM脏数据写入所述高速存储设备。If the comparison result of the RAM dirty data water level with the preset high water level threshold and the preset low water level threshold is: when the RAM dirty data is between the preset high water level threshold and the preset low water level threshold, it can be directly The RAM dirty data is written into the high-speed storage device.
当然,在所述RAM脏数据水位值位于预设高水位阈值和预设低水位阈值之间时,也可以热点识别所述RAM脏数据,根据热点识别的结果存储所述RAM脏数据。Certainly, when the water level of the RAM dirty data is between a preset high water level threshold and a preset low water level threshold, the RAM dirty data may also be hotspot identified, and the RAM dirty data may be stored according to a hot spot identification result.
并且,本实施例中,所述AM脏数据水位值位于预设高水位阈值和预设低水位阈值之间可以包括预设高水位阈值和预设低水位阈值这两个端点值。Moreover, in this embodiment, the AM dirty data water level value between the preset high water level threshold and the preset low water level threshold may include two endpoint values, the preset high water level threshold and the preset low water level threshold.
对应图3、图4和图5的实施例中,均还可以包括以下步骤:In the embodiment corresponding to Fig. 3, Fig. 4 and Fig. 5, the following steps may also be included:
判断所述RAM脏数据水位未提高,获取所述RAM脏数据占用的存储空间值;Judging that the water level of the RAM dirty data has not increased, and obtaining the storage space value occupied by the RAM dirty data;
若所述RAM脏数据占用的存储空间值大于预设值,将所述RAM脏数据写入所述低速存储设备。If the storage space occupied by the RAM dirty data is greater than a preset value, write the RAM dirty data into the low-speed storage device.
并且,在所述RAM脏数据占用的存储空间值大于预设值时,可以采用透写方式或回写方式将所述RAM脏数据写入低速存储设备。Moreover, when the storage space occupied by the dirty RAM data is greater than a preset value, the dirty RAM data may be written into the low-speed storage device in a write-through or write-back manner.
具体的,上述两个步骤的具体实施过程请参见对应图2的实施例的内容,此处不再赘述。Specifically, for the specific implementation process of the above two steps, please refer to the content of the embodiment corresponding to FIG. 2 , which will not be repeated here.
本发明另一实施例还公开了一种数据存储系统,如图6所示,包括:Another embodiment of the present invention also discloses a data storage system, as shown in Figure 6, including:
第一获取单元101,用于获取所述RAM脏数据水位值;The first acquiring
判断单元102,用于根据获取的所述RAM脏数据水位值,判断所述RAM脏数据水位是否提高;A judging
优选地,判断单元102可以包括第一判断单元和第二判断单元,其中:Preferably, the judging
所述第一判断单元用于检测所述RAM脏数据水位值的提升速率是否达到预设速率;第二判断单元用于检测所述RAM脏数据水位值是否达到预设水位值。The first judging unit is used to detect whether the increase rate of the RAM dirty data level value reaches a preset rate; the second judging unit is used to detect whether the RAM dirty data water level value reaches a preset water level value.
具体的,当所述第一判断单元检测所述RAM脏数据水位值的提升速率达到预设速率或者第二判断单元检测所述RAM脏数据水位值达到预设水位值,均说明所述RAM脏数据水位提高,此时发生突发写情况。Specifically, when the first judging unit detects that the increase rate of the RAM dirty data water level reaches a preset rate or the second judging unit detects that the RAM dirty data water level reaches a preset water level, it means that the RAM is dirty. The data water level increases, and a burst write occurs at this time.
第一比较单元103,用于判断单元102判断所述RAM脏数据水位提高,比较所述RAM脏数据水位值和预设阈值;The
热点识别单元104,用于第一比较单元103判断所述RAM脏数据水位值小于预设阈值,识别所述RAM脏数据是否为热点数据;The
数据写入单元105,用于热点识别单元104识别所述RAM脏数据为热点数据,将所述RAM脏数据写入高速存储设备;热点识别单元104识别所述RAM脏数据为非热点数据,将所述RAM脏数据写入低速存储设备;第一比较单元103判断所述RAM缓存数据水位值大于预设阈值,将所述RAM脏数据写入所述高速存储设备。The
具体的,本实施例公开的数据存储系统中,第一获取单元获取所述RAM脏数据水位值,当判断单元判断所述RAM脏数据水位提高时,说明当前出现突发写情况,此时,数据写入单元105根据第一比较单元103的比较结果确定所述RAM脏数据的存储方式,具体的,当第一比较单元103判断所述RAM脏数据水位值小于预设阈值,由热点识别单元104识别所述RAM脏数据是否为热点数据,且当热点识别单元104识别为热点数据,数据写入单元105将数据写入高速存储设备,可以避免过多的数据写入高速存储设备,识别为非热点数据,数据写入单元105将数据写入低速存储设备,这样,解决非热点数据占用高速存储设备的过多资源导致的热点数据被挤出高速存储设备的问题;同时还能解决过多数据写入高速存储设备导致减少高速存储设备的使用寿命的问题。Specifically, in the data storage system disclosed in this embodiment, the first acquiring unit acquires the water level value of the RAM dirty data, and when the judging unit judges that the water level of the dirty data in the RAM has increased, it indicates that a burst write situation occurs currently, and at this time, The
并且,当第一比较单元103判断所述RAM脏数据水位值大于预设阈值,说明对应的RAM脏数据比较多,即突发写的数据比较多,此时数据写入单元105直接将RAM脏数据写入高速存储设备,可以解决过多数据写入低速存储设备,由于低速存储设备性能低,导致严重影响数据的存储速率,形成存储延时的问题。Moreover, when the
本实施例提供的数据存储系统中各个单元的具体工作过程请参见对应图1的实施例,此处不再赘述。For the specific working process of each unit in the data storage system provided in this embodiment, please refer to the embodiment corresponding to FIG. 1 , which will not be repeated here.
本发明另一实施例还公开了一种数据存储系统,如图7所示,除包括:第一获取单元201、判断单元202、第一比较单元203、热点识别单元204和数据写入单元205之外,还包括:Another embodiment of the present invention also discloses a data storage system, as shown in FIG. In addition, it also includes:
第二获取单元206,用于判断单元202判断所述RAM脏数据水位未提高,获取所述RAM脏数据占用的存储空间值;The second acquiring unit 206 is used for the judging unit 202 to judge that the RAM dirty data water level has not increased, and acquire the storage space value occupied by the RAM dirty data;
第二比较单元207,用于比较所述RAM脏数据占用的存储空间值和预设值;The second comparison unit 207 is configured to compare the storage space value occupied by the RAM dirty data with a preset value;
其中,第一获取单元201、判断单元202、第一比较单元203、热点识别单元204和数据写入单元205的工作过程与上述实施例公开的第一获取单元101、判断单元102、第一比较单元103、热点识别单元104和数据写入单元105相同,请参照上述实施例的内容,除此之外,本实施例中,数据写入单元205还用于在第二比较单元207判断所述RAM脏数据占用的存储空间值大于预设值时,将所述RAM脏数据写入所述低速存储设备。Among them, the working process of the first acquiring unit 201, the judging unit 202, the first comparing unit 203, the hotspot identifying unit 204 and the data writing unit 205 are the same as those disclosed in the above-mentioned embodiments. The
具体的,当有个别数据缓存到RAM中,无论数据本身是大还是小,都不会导致所述RAM脏数据水位提高,此时,第二获取单元206获取所述RAM脏数据占用的存储空间值;第二比较单元207比较所述RAM脏数据占用的存储空间值和预设值;当第二比较单元207判断所述RAM脏数据占用的存储空间值超过预设值时,数据写入单元205将所述RAM脏数据写入所述低速存储设备。这样,可以避免大数据写入所述高速存储设备占用资源的问题。Specifically, when individual data is cached in the RAM, no matter whether the data itself is large or small, the water level of the dirty data in the RAM will not increase. At this time, the second acquisition unit 206 acquires the storage space occupied by the dirty data in the RAM. value; the second comparison unit 207 compares the storage space value and the preset value occupied by the RAM dirty data; when the second comparison unit 207 judges that the storage space value occupied by the RAM dirty data exceeds the preset value, the data writing unit 205 Write the RAM dirty data into the low-speed storage device. In this way, the problem of resource occupation by writing large data into the high-speed storage device can be avoided.
此处需要说明的是,数据写入单元205将所述RAM脏数据写入所述低速存储设备可以采用透写方式将所述RAM脏数据写入所述低速存储设备;或者,采用回写方式将所述RAM脏数据写入所述低速存储设备。It should be noted here that the data writing unit 205 may write the RAM dirty data into the low-speed storage device by using a write-through method to write the RAM dirty data into the low-speed storage device; or, use a write-back method Writing the RAM dirty data into the low-speed storage device.
当然,在RAM脏数据占用的存储空间值大于预设值的情况下,数据写入单元205将所述RAM脏数据写入所述低速存储设备的方式还可以为其他方式,此处不一一说明。Certainly, in the case that the storage space value occupied by RAM dirty data is greater than a preset value, the mode of writing the RAM dirty data into the low-speed storage device by the data writing unit 205 can also be other ways, which are not mentioned here one by one. illustrate.
优选地,在上述的实施例中,所述数据存储单元还可以包括:Preferably, in the above-mentioned embodiments, the data storage unit may further include:
第一标记单元,用于在所述数据写入单元在所述热点识别单元识别所述RAM脏数据为热点数据,对写入所述高速存储设备的RAM脏数据进行标记;The first marking unit is used to identify the RAM dirty data as hotspot data in the hot spot identification unit in the data writing unit, and mark the RAM dirty data written in the high-speed storage device;
第二标记单元,用于在所述第一比较单元判断所述RAM脏数据水位值大于所述预设阈值情况下,对写入所述高速存储设备的RAM脏数据进行标记。The second marking unit is configured to mark the RAM dirty data written into the high-speed storage device when the first comparison unit judges that the RAM dirty data water level value is greater than the preset threshold.
本发明另一实施例还公开了一种数据存储系统,如图8所示,包括:Another embodiment of the present invention also discloses a data storage system, as shown in Figure 8, including:
第一获取单元301、判断单元302、第一比较单元303、热点识别单元304和数据写入单元305,还包括:The first acquiring unit 301, the judging unit 302, the first comparing unit 303, the hot spot identifying unit 304 and the data writing unit 305 also include:
标记单元306,用于对所述高速存储设备存储的RAM脏数据进行标记;A marking unit 306, configured to mark RAM dirty data stored in the high-speed storage device;
接收单元307,用于接收淘汰高速存储设备存储数据的指令;The receiving unit 307 is configured to receive an instruction to eliminate data stored in the high-speed storage device;
查询单元308,用于接收单元307接收到淘汰高速存储设备存储数据的指令后,查询所述高速存储设备上存储的设置有所述标记的数据;The query unit 308 is configured to query the data stored on the high-speed storage device with the mark after the receiving unit 307 receives the instruction to eliminate the data stored in the high-speed storage device;
删除单元309,用于将设置有所述标记的数据由所述高速存储设备写入低速存储设备。The deletion unit 309 is configured to write the data set with the flag from the high-speed storage device into the low-speed storage device.
本实施例中,对应所述高速存储设备存储有标记RAM脏数据的情况下,被标记的RAM脏数据为突发写情况时的数据。当接收单元307接收外界输入的淘汰高速存储设备存储数据的指令,查询单元308查找所述高速存储设备上存储的设置有标记的数据,删除单元309将查询单元308查找的设置有标记的数据由所述高速存储设备淘汰至所述低速存储设备,可以释放高速存储设备的存储空间;并且,将数据由所述高速存储设备淘汰至所述低速存储设备,可以避免数据直接由所述高速存储设备删除造成数据丢失的问题。In this embodiment, corresponding to the case where the high-speed storage device stores marked RAM dirty data, the marked RAM dirty data is data in a burst write situation. When the receiving unit 307 receives an instruction from the outside to eliminate data stored in the high-speed storage device, the query unit 308 searches for the marked data stored on the high-speed storage device, and the deleting unit 309 removes the marked data searched by the query unit 308 from Removing the high-speed storage device to the low-speed storage device can release the storage space of the high-speed storage device; and, eliminating data from the high-speed storage device to the low-speed storage device can prevent data from being directly transferred from the high-speed storage device Delete issues that cause data loss.
优选地,在上述实施例中公开的数据存储系统,还可以包括:Preferably, the data storage system disclosed in the above embodiments may further include:
选取单元,用于选取预设数量的设置有的所述标记的数据对应的存储块;a selection unit, configured to select a preset number of storage blocks corresponding to the marked data;
合并单元,用于将所述选取的存储块合并为一个存储块。The merging unit is configured to combine the selected storage blocks into one storage block.
此时,高速存储设备分为多个存储块,存储有设置有所述标记的数据的存储块是合并之后,将合并后的存储块的数据写入所述低速存储设备,可以提高将所述高速存储设备中数据写入所述低速存储设备的速度。At this time, the high-speed storage device is divided into a plurality of storage blocks, and after the storage blocks storing the data provided with the mark are merged, the data of the merged storage block is written into the low-speed storage device, which can improve the speed of the storage. The speed at which data in the high-speed storage device is written to the low-speed storage device.
并在本发明的上述几个实施例中,优选地,第一比较单元包括:阈值比较单元,用于将所述RAM脏数据水位值分别与预设低水位阈值和预设高水位阈值进行比较,其中,所述预设高水位阈值大于所述预设低水位阈值。And in the above several embodiments of the present invention, preferably, the first comparison unit includes: a threshold comparison unit, configured to compare the RAM dirty data water level with a preset low water level threshold and a preset high water level threshold respectively , wherein the preset high water level threshold is greater than the preset low water level threshold.
此时,热点识别单元为:第一热点识别单元,用于所述阈值比较单元判断所述RAM脏数据水位值小于所述预设低水位阈值,热点识别所述RAM脏数据;At this time, the hot spot identification unit is: a first hot spot identification unit, used for the threshold comparison unit to judge that the RAM dirty data water level value is less than the preset low water level threshold, and the hot spot identifies the RAM dirty data;
或者,所述热点识别单元为:第二热点识别单元,用于所述阈值比较单元判断所述RAM脏数据水位值小于所述预设高水位阈值,识别所述RAM脏数据是否为热点数据。Alternatively, the hotspot identification unit is: a second hotspot identification unit, configured for the threshold comparison unit to judge that the RAM dirty data water level is less than the preset high water level threshold, and to identify whether the RAM dirty data is hotspot data.
对应的,所述数据写入单元为:第一数据写入单元,用于所述阈值比较单元判断所述RAM缓存数据水位值大于所述预设高水位阈值,将所述RAM脏数据写入所述高速存储设备;Correspondingly, the data writing unit is: a first data writing unit, used for the threshold comparison unit to judge that the RAM cache data water level value is greater than the preset high water level threshold, and write the RAM dirty data into The high-speed storage device;
或者,所述数据写入单元为:第二数据写入单元,用于所述阈值比较单元判断所述RAM脏数据水位值大于所述预设低水位阈值,将所述RAM脏数据写入所述高速存储设备。Alternatively, the data writing unit is: a second data writing unit, used for the threshold comparison unit to judge that the RAM dirty data water level value is greater than the preset low water level threshold, and write the RAM dirty data into the high-speed storage devices.
本实施例中公开的单元的具体工作过程请参见对应图5的实施例,此处不再赘述。For the specific working process of the units disclosed in this embodiment, please refer to the embodiment corresponding to FIG. 5 , which will not be repeated here.
最后,还需要说明的是,在本文中,诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来,而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下,由语句“包括一个......”限定的要素,并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。Finally, it should also be noted that in this text, relational terms such as first and second etc. are only used to distinguish one entity or operation from another, and do not necessarily require or imply that these entities or operations, any such actual relationship or order exists. Furthermore, the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus comprising a set of elements includes not only those elements, but also includes elements not expressly listed. other elements of or also include elements inherent in such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising said element.
本说明书中各个实施例采用递进的方式描述,每个实施例重点说明的都是与其他实施例的不同之处,各个实施例之间相同相似部分互相参见即可。Each embodiment in this specification is described in a progressive manner, each embodiment focuses on the difference from other embodiments, and the same and similar parts of each embodiment can be referred to each other.
对所公开的实施例的上述说明,使本领域专业技术人员能够实现或使用本发明。对这些实施例的多种修改对本领域的专业技术人员来说将是显而易见的,本文中所定义的一般原理可以在不脱离本发明的精神或范围的情况下,在其它实施例中实现。因此,本发明将不会被限制于本文所示的这些实施例,而是要符合与本文所公开的原理和新颖特点相一致的最宽的范围。The above description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention will not be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (20)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310389343.7A CN103473180B (en) | 2013-08-30 | 2013-08-30 | Date storage method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310389343.7A CN103473180B (en) | 2013-08-30 | 2013-08-30 | Date storage method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103473180A true CN103473180A (en) | 2013-12-25 |
| CN103473180B CN103473180B (en) | 2017-03-01 |
Family
ID=49798044
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310389343.7A Active CN103473180B (en) | 2013-08-30 | 2013-08-30 | Date storage method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103473180B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103713861A (en) * | 2014-01-09 | 2014-04-09 | 浪潮(北京)电子信息产业有限公司 | File processing method and system based on hierarchical division |
| WO2016206463A1 (en) * | 2015-06-23 | 2016-12-29 | 中兴通讯股份有限公司 | Write operation control method, device and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7146469B2 (en) * | 2002-10-24 | 2006-12-05 | Sony Corporation | Method, apparatus, and system for improving memory access speed |
| CN101458613A (en) * | 2008-12-31 | 2009-06-17 | 成都市华为赛门铁克科技有限公司 | Method for implementing mixed hierarchical array, the hierarchical array and storage system |
| CN101794259A (en) * | 2010-03-26 | 2010-08-04 | 成都市华为赛门铁克科技有限公司 | Data storage method and device |
| US20120124278A1 (en) * | 1999-07-09 | 2012-05-17 | Renesas Electronics Corporation | Memory system for portable telephone |
-
2013
- 2013-08-30 CN CN201310389343.7A patent/CN103473180B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120124278A1 (en) * | 1999-07-09 | 2012-05-17 | Renesas Electronics Corporation | Memory system for portable telephone |
| US7146469B2 (en) * | 2002-10-24 | 2006-12-05 | Sony Corporation | Method, apparatus, and system for improving memory access speed |
| CN101458613A (en) * | 2008-12-31 | 2009-06-17 | 成都市华为赛门铁克科技有限公司 | Method for implementing mixed hierarchical array, the hierarchical array and storage system |
| CN101794259A (en) * | 2010-03-26 | 2010-08-04 | 成都市华为赛门铁克科技有限公司 | Data storage method and device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103713861A (en) * | 2014-01-09 | 2014-04-09 | 浪潮(北京)电子信息产业有限公司 | File processing method and system based on hierarchical division |
| WO2016206463A1 (en) * | 2015-06-23 | 2016-12-29 | 中兴通讯股份有限公司 | Write operation control method, device and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103473180B (en) | 2017-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105094686B (en) | Data cache method, caching and computer system | |
| RU2661280C2 (en) | Massive controller, solid state disk and data recording solid state disk control method | |
| CN107430551B (en) | Data caching method, storage control device, and storage device | |
| EP3059679B1 (en) | Controller, flash memory device, method for identifying data block stability and method for storing data on flash memory device | |
| US20150378888A1 (en) | Controller, flash memory apparatus, and method for writing data into flash memory apparatus | |
| JP2013521579A5 (en) | ||
| CN101645043A (en) | Methods for reading and writing data and memory device | |
| CN112286459A (en) | A data processing method, device, equipment and medium | |
| CN111309687A (en) | Object storage small file processing method, device, device and storage medium | |
| CN105677236B (en) | A kind of storage device and its method for storing data | |
| CN104731515B (en) | Control the method and apparatus of storage device group of planes abrasion equilibrium | |
| CN104503703A (en) | Cache processing method and device | |
| CN103176753B (en) | Storing device and data managing method thereof | |
| US10853250B2 (en) | Storage management method, electronic device and computer program product | |
| CN102087646A (en) | Method and device for establishing index | |
| WO2020063355A1 (en) | Method and device for buffering data blocks, computer device, and computer-readable storage medium | |
| US9063667B2 (en) | Dynamic memory relocation | |
| CN108959500A (en) | A kind of object storage method, device, equipment and computer readable storage medium | |
| CN103473180B (en) | Date storage method and system | |
| CN104156173A (en) | Method and device for disk defragmentation | |
| US10083117B2 (en) | Filtering write request sequences | |
| CN103019963B (en) | The mapping method of a kind of high-speed cache and storage device | |
| CN107273303B (en) | Flash memory data management system and method, flash memory chip and storage device | |
| CN115469796A (en) | Data storage method, device, equipment and storage medium | |
| CN106649860B (en) | A Defragmentation Method Applied to Aggregated Files |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |