CN102043732A - Cache allocation method and device - Google Patents

Cache allocation method and device Download PDF

Info

Publication number
CN102043732A
CN102043732A CN2010106161456A CN201010616145A CN102043732A CN 102043732 A CN102043732 A CN 102043732A CN 2010106161456 A CN2010106161456 A CN 2010106161456A CN 201010616145 A CN201010616145 A CN 201010616145A CN 102043732 A CN102043732 A CN 102043732A
Authority
CN
China
Prior art keywords
virtual
capacity
data
resource pool
access
Prior art date
Application number
CN2010106161456A
Other languages
Chinese (zh)
Inventor
林宇
肖飞
Original Assignee
成都市华为赛门铁克科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 成都市华为赛门铁克科技有限公司 filed Critical 成都市华为赛门铁克科技有限公司
Priority to CN2010106161456A priority Critical patent/CN102043732A/en
Publication of CN102043732A publication Critical patent/CN102043732A/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F12/00Accessing, addressing or allocating within memory systems or architectures
    • G06F12/02Addressing or allocation; Relocation
    • G06F12/08Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
    • G06F12/0802Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches

Abstract

The embodiment of the invention discloses a cache allocation method and device, which is used for avoiding negotiation process between a first controller and a second controller due to two-terminal control. The method comprises the following steps: a cache resource pool is divided into virtual sub-resource pools which are provided with the same number of logical units in advance; each virtual sub-resource pool is corresponding to a logical unit; and the cache resource storage of each virtual sub-resource pool is corresponding to service data of the logical unit. According to the embodiment of the invention, complicated communication negotiation process between the first controller and the second controller can be avoided, thereby guarantying data safety.

Description

一种缓存分配方法及装置 A dispensing method and device cache

技术领域 FIELD

[0001] 本发明涉及通信领域,特别涉及一种缓存分配方法及装置。 [0001] The present invention relates to the field of communications, particularly to a method and apparatus for cache allocation. 背景技术 Background technique

[0002] 固态硬盘(SSD,Solid State Disk或Solid State Drive),也称作电子硬盘或者固态电子盘,由于固态硬盘没有普通硬盘的旋转介质,因而抗震性极佳,且其芯片的工作温度范围很宽(-40°C〜85°C),目前广泛应用于军事、车载、工控、视频监控、网络监控、网络终端、电力、医疗、航空等、导航设备等领域,SSD Cache是将SSD运用到存储系统中一种新型应用,属于二级缓存,它主要利用SSD读写响应较短,尤其是读响应时间很短,将热点数据存储在SSD中,当访问这些数据时,可以从SSD中而不是从传统磁盘中读取,这样可以大大提高系统的性能,1-4个SSD盘片组成SSD Cache资源池,SSD盘片一般只能供存储系统的一端控制器使用,当存储系统的一端控制器失效后,存储在其中的热点数据丢失,从而影响系统的整体性能。 [0002] The solid state disk (SSD, Solid State Disk or Solid State Drive), also referred to as electronic hard disk or solid state electronics, since SSD is no common rotating disk medium, and thus an excellent shock resistance, and the chip operating temperature range very wide (-40 ° C~85 ° C), is currently widely used in military, automotive, industrial control, video surveillance, network monitoring, network terminals, electricity, medical, aviation, navigation devices, SSD Cache SSD is to use to the storage system a new application, belong to the secondary cache, which mainly use the SSD write a short response, in particular read response time is very short, will be in the SSD, when access to the data, from the SSD data storage hotspot instead of reading from a conventional disk, which can greatly improve system performance, 1-4 SSD SSD platters the Cache resource pool, generally only SSD disk storage system controller for end use, when the end of the storage system after the controller fails, the data stored therein is lost in the hot, thus affecting the overall performance of the system.

[0003] 现有技术中,SSD盘片组成的SSD Cache资源池可以供存储系统的两端控制器使用,即使系统的一端控制器失效,另一个控制器也会接管其业务,不会影响系统的整体性能。 [0003] In the prior art, the SSD of the SSD Cache platters resource pool can be used by both ends of the storage system controller to use, even if the one end of the controller system fails, the other controller will take over the operations, it does not affect the system overall performance.

[0004] 但是在上述现有技术中,如果出现分属于两端控制器的两个或两个以上的逻辑单元(LUN,Logical Unit Number)需要同时访问一处缓存资源中数据的问题,那么两端控制器之间便需要对因存储数据及读取数据产生的冲突进行通信协商,协商过程比较复杂,可能会出现异常造成数据丢失等严重后果。 [0004] However, in the above-described prior art, if two or more logical units belonging to both ends in the controller's (LUN, Logical Unit Number) in question need to access data in a cache resources, then the two they need to store data and read conflict due to data generated by controller communication between end the negotiation process is complex, there may be abnormal data loss and other serious consequences.

发明内容 SUMMARY

[0005] 本发明实施例提供了一种缓存分配方法及装置,可以避免两个及两个以上LUN同时访问缓存资源池中的数据,从而避免控制两端控制器之间复杂的通信协商过程,保障数据的安全。 [0005] Embodiments of the present invention provides a method and apparatus for cache allocation can be avoided by two or more LUN simultaneously access the data buffer pool resources, thereby avoiding complicated control communication between the two ends of the negotiation process controller, protect the security of the data.

[0006] 本发明实施例提供的一种缓存分配方法包括: [0006] A cache allocation method according to an embodiment of the present invention comprises:

[0007] 确定获取到的业务数据需要存储的逻辑单元;查找与所述逻辑单元对应的虚拟子资源池;将所述业务数据存储于查找到的虚拟子资源池所包括的缓存资源中;其中,缓存资源池被预先划分为与所述逻辑单元数量相等的虚拟子资源池,每个虚拟子资源池对应一个不同的逻辑单元,且每个虚拟子资源池所包括的缓存资源存储对应逻辑单元的业务数据。 [0007] determines that the acquired data to store service logic unit; lookup logical units corresponding to the virtual sub-resource pools; cache resources of the service data stored in the searched virtual sub included in the resource pool; wherein , the cache is pre-divided into a resource pool to the virtual logical unit is equal to the number of child resource pools, each virtual resource pool corresponding to a different sub-logic unit, and the cache memory resources corresponding to each virtual logical unit included in the child resource pools business data.

[0008] 本发明实施例提供的一种缓存分配装置包括: [0008] A cache allocation apparatus according to an embodiment of the present invention comprises:

[0009] 确定单元,用于确定获取到的业务数据需要存储的逻辑单元;查找单元,用于查找与所述逻辑单元对应的虚拟子资源池;存储单元,用于将所述业务数据存储于查找到的虚拟子资源池所包括的缓存资源中;划分单元,用于缓存资源池被预先划分为与所述逻辑单元数量相等的虚拟子资源池。 [0009] determination unit configured to store the service data needed to determine the acquired logical unit; searching unit configured to find a virtual child resource pool corresponding to the logical unit; a storing unit configured to store the service data cache resources located virtual sub included in resource pool; dividing unit for pre-caching the resource pool is divided into the virtual logical unit is equal to the number of sub-resource pools. [0010] 从以上技术方案可以看出,本发明实施例具有以下优点:根据LUN的数量将缓存资源池划分为数量相等的虚拟子资源池,每个虚拟子资源池与不同的逻辑单元LUN—一对应,每个虚拟子资源池只供各自对应的LUN访问缓存数据,因此避免分别来自两端控制器的两个及两个以上LUN同时访问同一缓存数据,从而避免控制两端控制器之间为访问同一缓存资源数据而进行复杂的通信协商过程,保障数据的安全。 [0010] As can be seen from the foregoing technical solutions, embodiments of the present invention has the following advantages: according to the number of cache LUN resource pools are divided into an equal number of virtual sub-resource pools, each virtual resource pool with a different sub-logic unit LUN- a correspondence between each virtual resource pool is for each sub-LUN corresponding to the data access to the cache, thus avoiding the two ends, respectively, from the two or more controllers and LUN to access the same cache data, thereby avoiding the controller across the control to access the same cache resource data and complex negotiation process communication, to protect the security of data.

附图说明 BRIEF DESCRIPTION

[0011] 图1为本发明实施例中缓存分配方法的一个实施例示意图; [0011] Figure 1 embodiment of the method of cache allocation schematic diagram of a embodiment of the present invention;

[0012] 图2为本发明实施例缓存分配过程中的缓存系统结构示意图; [0012] FIG. 2 is a schematic configuration example of a cache system in the embodiment of the buffer allocation process of the present invention;

[0013] 图3为本发明实施例中缓存分配方法的另一个实施例示意图; A schematic view of another embodiment [0013] FIG. 3 embodiment of the present invention, cache allocation method of embodiment;

[0014] 图4为本发明实施例中缓存分配装置的一个实施例示意图。 [0014] Figure 4 a schematic view of the embodiment of the dispensing device cache embodiment of a embodiment of the present invention.

具体实施方式 Detailed ways

[0015] 本发明实施例提供了一种缓存分配方法及装置,可以将缓存资源池供存储系统的两端控制器均衡使用,即使系统的一端控制器失效,另一个控制器也会接管其业务,因实现双控而提高系统整体性能,下面分别进行详细说明。 [0015] Example embodiments provide a method and cache dispensing device of the invention, the controller may be equalized at both ends of the cache memory system resource pool for use, even if the one end of the controller system fails, the other controller will take over its business , due to dual control to improve overall system performance, are described in detail below.

[0016] 请参阅图1,本发明实施例中缓存分配方法的一个实施例包括: [0016] Referring to FIG. 1, the embodiment of cache allocation method of an embodiment of the present invention comprises:

[0017] 101、确定获取到的业务数据需要存储的逻辑单元; [0017] 101, a determination logic unit acquires service data need to be stored;

[0018] 各类型业务数据均需要存储到系统的逻辑单元LUN中,LUN是唯一的,不同LUN的业务数据类型可能会是相同的。 [0018] Each type of traffic data to the storage are required in the system logical unit LUN, the LUN is unique, different LUN business data types may be the same.

[0019] 本发明实施例中,首先要确定获取得到的业务数据对应的LUN。 [0019] Example embodiments of the present invention, first determines whether the acquired service data obtained corresponding LUN.

[0020] 102、查找与逻辑单元对应的虚拟子资源池; [0020] 102, to find the corresponding virtual logical unit child resource pool;

[0021] 本发明实施例中,SSD Cache缓存资源被预先划分为与逻辑单元数量相等的虚拟子资源池,每个虚拟子资源池与一个不同的逻辑单元对应,即每个虚拟子资源池的数据仅供一个LUN访问,而且每个虚拟子资源池所包括的缓存资源存储对应逻辑单元的业务数据,每个LUN在其对应的虚拟子资源池中对数据的访问均独立于其他LUN进行,但每个虚拟子资源池的数据有机会供任意LUN访问。 [0021] embodiment, SSD Cache cache resources are divided in advance with the embodiment of the present invention is a virtual logical unit is equal to the number of child resource pools, with each virtual sub-resource pool corresponding to a different logical units, i.e., each virtual sub-resource pool data for a LUN access, and traffic data buffer memory resources corresponding to each virtual logical unit included in a child resource pool, each LUN access to the data in the corresponding virtual sub-resource pools are independently of the other LUN, However, data for each virtual child resource pools have a chance for any LUN access.

[0022] 需要说明的是,各SSD Cache虚拟子资源池的初始容量可以相同,也可以不同,但各虚拟子资源池只能使用划分的容量。 [0022] It should be noted that the initial capacity of each SSD Cache virtual child resource pool can be the same or different, but each virtual child resource pool can only use this breakdown.

[0023] 103、将业务数据存储于查找到的虚拟子资源池所包括的缓存资源中。 [0023] 103, cache resources stored in a lookup service data of the virtual sub included in resource pool.

[0024] 根据在步骤102中查找到与LUN对应的虚拟子资源池后,将业务数据也对应的存储于分属不同LUN的不同虚拟子资源池所包括的缓存资源中。 [0024] According to the LUN after finding the corresponding virtual resource pool in the sub-step 102, cache resources corresponding to traffic data is also stored in the LUN belonging to different virtual sub different included in the resource pool.

[0025] 本发明实施例中,确定业务数据所要存储的逻辑单元,查找逻辑单元对应的虚拟子资源池并将该业务数据存储其中,由于SSD Cache缓存资源被预先划分为与逻辑单元数量相等的虚拟子资源池,每个虚拟子资源池与一个不同的逻辑单元对应,因此避免分别来自两端控制器的多个LUN同时访问同一缓存数据,从而避免控制两端控制器之间为访问同一缓存资源数据而进行复杂的通信协商过程。 [0025] The embodiments of the present invention, determination logic traffic data to be stored, the lookup logic unit corresponding to the virtual sub-resource pools and the service data stored therein, since SSD Cache cache resources are pre-divided into a number of logical units equal to virtual child resource pool, with each virtual sub-resource pool corresponding to a different logical unit, thus avoiding the two ends from each of the plurality of LUN controller to access the same data cache, thereby avoiding access control between both ends of the same cache controller resource data and complex negotiation process communication.

[0026] 本发明实施例中,缓存分配过程中的缓存系统结构示意图请参阅图2,缓存系统有两端控制器,201为第一控制器,202为第二控制器,203是缓存系统的业务层,LUNO, LUNl及LUN2均为业务层的业务,其中LUNO与LUNl由第一控制器201控制,LUN2由第二控制器202控制,204是缓存系统的资源层,其中,208为固态硬盘缓存资源层,由固态硬盘组成,根据不同的LUN业务的数量,将SSD Cache资源池划分成不同数量的SSD Cache虚拟子资源池,具体划分为第一虚拟子资源池205,第二虚拟子资源池206,第三虚拟子资源池207,该各虚拟子资源池对应各自的LUN业务,如图所示,第一虚拟子资源池205对应LUN0,第二虚拟子资源池206对应LUN1,第三虚拟子资源池207对应LUN2。 [0026] The embodiments of the present invention, a cache system configuration schematic cache allocation process Referring to FIG. 2, both ends cache system controller, the first controller 201, second controller 202, caching system 203 is business layer, LUNO, LUNl service and service are LUN2 layer, and wherein Luno LUNl 201 controlled by the first controller, LUN2 controlled by the second controller 202, 204 is a resource-level cache system, wherein the solid state disk 208 cache resource layer, composed of a solid state disk, according to the number of different services LUN, the SSD cache resource pools are divided into a different number of virtual sub SSD cache resource pools, particularly sub-divided into a first virtual resource pool 205, a second virtual resource sub pool 206, the third virtual sub-pool resource 207, the resource pool corresponding to each of the virtual sub-services each LUN, as shown, a first dummy sub-tank 205 corresponds LUNO resource, the second resource sub-pool 206 corresponding to virtual LUN1 for the third virtual child resource pool 207 correspond LUN2.

[0027] 为了便于理解,下面以另一实施例对本发明实施例中的缓存分配方法进行详细描述,请参阅图3,本发明实施例中的缓存分配方法的另一实施例包括: [0027] For ease of understanding, the following another embodiment of cache allocation method in the detailed description of the embodiments of the present invention, see Figure 3, a further embodiment includes a method of cache allocation in the embodiment of the present invention:

[0028] 301〜303、本发明实施中步骤301至303的内容,请参见前述图1所述实施例中步骤101至103所描述的内容,此处不再赘述。 [0028] 301~303, embodiments of the present invention, the content of step 301 to 303, see FIG. 1 the content 101-103 Step embodiment described embodiments will not be repeated here.

[0029] 304、当到达预置时长时,获取所划分的虚拟子资源池中所存储数据的访问热度值; [0029] 304, when reaching the preset length of time, heat value of gaining access to the resource pool of virtual sub-divided stored data;

[0030] 在SSD Cache资源池系统内,可设置调整线程,预先设置一定的时长,每到达该预置的时长则获取步骤101中所划分的虚拟子资源池中存储的数据的访问热度值,该时长的设定与实际应用过程相关,时长的具体数值此处不作限定。 [0030] In the SSD Cache resource pool system, may be provided to adjust the thread, a preset constant time duration, each arriving access popularity value of data stored in the duration of the preset is acquired in step 101 the divided virtual sub-resource pool, the duration of the actual application process associated with the setting, which is not limited to the specific length values ​​here.

[0031] 需要说明的是,访问热度值包括虚拟子资源池中存储的数据的访问频率及虚拟子资源池中存储的热点数据数量,访问频率越高,热点数据数量越多,表示访问热度值越高。 [0031] Incidentally, the number of hotspot access popularity value comprises data access frequency of the data stored virtual resource pools and sub-sub-stored virtual resource pool, the higher the access frequency, the more the hot data representing access popularity value higher.

[0032] 需要进一步说明的是,虚拟子资源池中存储数据的访问频率及虚拟子资源池中存储的热点数据数量均可由系统内部的计数器进行计数,具体为本领域技术人员公知技术, 此处不再赘述。 [0032] It is further noted that the number of hot spots virtual data access frequency sub-pool of storage resources and data stored virtual child resource pools can be counted by an internal counter of the system, particularly well-known to those skilled in art, where No longer.

[0033] 305、将虚拟子资源池的容量调整至与当前存储数据访问热度值相匹配的容量; [0033] 305, the virtual pool capacity adjustment child resource to the access to the current popularity value of the stored data matches the capacity;

[0034] 根据预置的访问热度值与虚拟子资源池容量的匹配关系,将虚拟子资源池的容量调整至与当前存储数据访问热度值相匹配的容量。 [0034] The matching relationship with the heat value of the preset access virtual child resource pool size, the capacity of the virtual child resource pool is adjusted to the current popularity value of the stored data matches the access capacity.

[0035] 访问热度值可以在一定程度上反映访问存储数据的频繁程度,一般访问数据越频繁则需要的缓存资源越多,因此可以设置为,访问热度值则对应的虚拟子资源池的容量也大,访问热度值小则对应的虚拟子资源池的容量也小,具体设置过程与实际应用过程相关, 此处不作限定。 Capacity [0035] The access popularity value may be reflected to some extent on the frequency of access to stored data, the more frequent the normal access data is more required cache resources, may be provided, access to the heat value of the corresponding virtual child resource pools also large, small-capacity access popularity value corresponding virtual child resource pool is small, and the specific process of setting related to the actual application process, is not limited herein.

[0036] 在系统内,可预先设置虚拟子资源池中所存储数据的访问热度值与虚拟子资源池的容量的对应关系,在实际应用中,该对应关系一般不设置为具体数值之间的对应,而是设置为两个范围内数值的对应,例如,当访问热度值为50〜100时,其对应的虚拟子资源池的容量在30兆字节至60兆字节,那么如果某虚拟子资源池的容量为40兆字节,当前存储数据访问热度值为60,则可确定此时的虚拟子资源池的容量与当前存储数据访问热度值向匹配。 [0036] In the system, access may be pre-set heat value of the virtual sub-data stored in the resource pool corresponding to a virtual relationship between the capacity of the sub-resource pools and, in practical application, generally do not set the correspondence between specific values corresponds to, but is set to correspond to two values ​​within a range, e.g., when the access value is 50~100 temperature, the capacity of the corresponding virtual child resource pools of 30 megabytes to 60 megabytes, so if a virtual child resource pool capacity is 40 megabytes, the current temperature is 60 to access the data stored, the capacity may be determined in this case virtual child resource pool to access the stored data matches the current temperature value.

[0037] 具体的,若根据预置的访问热度值与虚拟子资源池的容量的匹配关系,可知某个虚拟子资源池的容量高于与当前存储数据访问热度值相匹配的容量,那么从存储数据访问热度值角度分析,则表明当前存储数据访问热度值较低,访问数据频率低,当前的虚拟子资源池容量偏大,与存储数据访问热度值不匹配,为节省缓存资源,则减少该虚拟子资源池的容量,因调整而空余出来的容量可供其他需要增加容量的虚拟子资源池使用。 [0037] Specifically, if the access according to the matching relation the capacity of the heat value of the preset virtual child resource pool, the capacity of a virtual understood child resource pools than the currently stored temperature data access capacity values ​​match, then the store data access popularity value point of view, it indicates a lower temperature value currently stored in the data access, the data access frequency is low, the current capacity of the virtual child resource pool is too large, accessing the data does not match the stored temperature values, in order to save resources, cache, reducing the the sub-capacity virtual resource pool, because of the adjustment and spare capacity available to other out of the need to increase the capacity of virtual child resource pools.

[0038] 若根据预置的访问热度值与虚拟子资源池的容量的匹配关系,可知某个虚拟子资源池的容量低于与当前存储数据访问热度值相匹配的容量,那么从存储数据访问热度值角度分析,则表明当前存储数据访问热度值高,访问数据频率高,当前的虚拟子资源池容量偏小,可能无法提供足够的容量满足存储数据的需求,则增加该虚拟子资源池的容量,可从当某个虚拟子资源池的容量偏高而被减少的容量中划取。 [0038] If the access according to the matching relation the capacity of the heat value of the preset virtual child resource pool, the capacity of a virtual sub-known resource pool is less than the currently stored temperature data access capacity values ​​match, then access to stored data from heat value point of view, it indicates a high heat value currently stored data access, data access frequency is high, the current virtual child resource pool capacity is too small, it may not provide sufficient capacity to meet the needs of data storage, increase the virtual child resource pool capacity, when the capacity to withdraw from a virtual sub-resource pool is high in reduced capacity.

[0039] 306、删除虚拟子资源池中的非热点数据。 [0039] 306, the non-hotspot data delete virtual child resource pool.

[0040] 由于各虚拟子资源池只能使用划分给自身的缓存资源,那么,若当前划分给虚拟子资源池的容量低于与当前存储数据访问热度值相匹配的容量时,虚拟子资源池没有可供业务数据存储的容量时,可通过删除该虚拟子资源池中的非热点数据获取更多空余容量。 [0040] Due to the respective virtual sub-resource pools can only use resources allocated to its own cache, then, if the current child resource allocated to the virtual pool capacity is lower than the value currently stored temperature data access matches the capacity of the virtual sub-resource pools when there is no available data storage capacity of the business, get more spare capacity by removing non-hot data to the virtual child resource pool.

[0041] 具体的,当虚拟子资源池没有可供业务数据存储的容量时,可将该虚拟子资源池中数据的访问频率进行排序,排序方式可由高到低,也可由低到高,然后删除访问频率排序最末尾的一个或多个数据,具体删除的数据数量,与实际应用过程相关,此处不作具体限定。 [0041] Specifically, when the virtual sub-service data resource pools Not available storage capacity, the virtual sub-data access frequency resources pool, the sort descending manner, but also by low to high, then remove the rearmost access frequency ordering one or more data, particularly the number of deleted data, related to the actual application process, here is not specifically limited.

[0042] 需要说明的是,虚拟子资源池中数据的访问频率可由系统内计数器进行计数,具体为本领域技术人员公知技术,此处不再赘述。 [0042] Incidentally, the data access to the pool of virtual sub-resources within a frequency counter for counting by the system, particularly well known to those skilled art, will not be repeated here.

[0043] 本发明实施例中,还需要对缓存资源池进行以下的初始化配置: [0043] Example embodiments of the present invention, it is also necessary to cache resources pool following initial configuration:

[0044] 将SSD Cache资源池根据业务的类型划分成多个数据块,由于LUN对应的业务有多种类型,而不同类型的业务数据所需要的缓存容量不同,一般来说,来自网页请求的业务所产生的热点数据需要的缓存容量小,而来自视频请求或者数据块业务所产生的热点数据需要的缓存容量大,相应的,根据业务数据所需容量大小划分缓存资源池,或对逻辑单元所对应的虚拟子资源池容量进行调整,使得存储数据需要缓存容量大的业务分配到的缓存容量大,存储数据需要缓存容量小的业务分配到的缓存容量小。 [0044] The SSD Cache resource pool is divided according to a type of traffic into a plurality of data blocks, since the LUN corresponding service There are many types, and different types of service data cache capacity required, in general, from a web page requested hotspot data cache capacity required traffic generated is small and the capacity of the buffer from the video data request or a hotspot service requires data blocks generated is large, corresponding to the required buffer capacity size is divided according to the resource pool service data or logic unit corresponding to the virtual sub-resource pool capacity is adjusted so that the storage capacity of the cache data requires a large traffic capacity allocated to a cache, store data requires a small buffer capacity assigned to the traffic buffer capacity is small.

[0045] 本发明实施例中,当到达一定的预置时长时,根据预置的访问热度值与虚拟子资源池容量的匹配关系,将虚拟子资源池的容量调整至与当前存储数据访问热度值相匹配的容量,不断动态调整各虚拟子资源池的容量,使得对虚拟子资源池的容量分配更符合实际应用,对缓存资源池的应用更合理。 [0045] The embodiments of the present invention, when it reaches a certain preset length of time, based on the matching relationship access popularity value with a preset capacity of the virtual pool child resource, the capacity of the virtual pool is adjusted to child resource currently stored temperature data access value that matches the capacity to continuously adjust the dynamic capacity of each virtual child resource pool, making for capacity allocation virtual child resource pool of more practical application, the application cache resource pool is more reasonable.

[0046] 本发明实施例还提供了一种缓存分配装置,请参阅图4,本发明实施例中缓存分配装置的一个实施例包括: [0046] The present invention further provides a dispensing device cache, see Figure 4, for example, a cache dispensing apparatus embodiment of the present invention includes:

[0047] 确定单元401,用于确定获取到的业务数据需要存储的逻辑单元,确定逻辑单元对应的业务数据类型; [0047] determination unit 401 for determining data to be acquired service logic means for storing, corresponding service logic unit determining the data type;

[0048] 查找单元402,用于查找与逻辑单元对应的虚拟子资源池; [0048] The search unit 402, and logic unit for finding the corresponding virtual sub-resource pools;

[0049] 存储单元403,用于将业务数据存储于查找到的虚拟子资源池所包括的缓存资源中; [0049] The storage unit 403, a traffic data stored in the buffer of the virtual resource lookup sub included in the resource pool;

[0050] 划分单元404,用于缓存资源池被预先划分为与逻辑单元数量相等的虚拟子资源池。 [0050] dividing unit 404, a resource pool buffer is previously divided into logical sub-unit is equal to the number of virtual resource pools.

[0051] 本实施例中的缓存分配装置还可以进一步包括: [0051] Cache dispensing apparatus according to the present embodiment may further comprise:

[0052] 获取单元405,用于当到达预置时长时,获取所划分的虚拟子资源池中所存储数据的访问热度值; [0052] The acquisition unit 405, to reach the preset duration when obtaining access to the heat value of the virtual sub-data stored in the resource pool divided;

[0053] 调整单元406,用于根据预置的访问热度值与虚拟子资源池容量的匹配关系,将虚拟子资源池的容量调整至与当前存储数据访问热度值相匹配的容量,还用于根据业务数据类型对逻辑单元所对应的虚拟子资源池容量进行调整; [0053] The adjusting unit 406, for access according to the matching relation with a preset value of heat capacity of the virtual pool child resource, the capacity of the virtual child resource pool is adjusted to the current popularity value of the stored data matches the access capacity for further adjust the virtual child resource pool corresponding to the capacity of the logical unit according to the service type of data;

[0054] 排序单元407,用于当虚拟子资源池没有可供业务数据存储的容量时,将虚拟子资源池中数据的访问频率进行排序; [0054] The sorting unit 407, a virtual sub-resource pools when no available traffic data storage capacity, access to the virtual sub-frequency resource pools data sorting;

[0055] 删除单元408,用于删除访问频率最低的数据。 [0055] The deleting unit 408 for deleting the data of the lowest access frequency.

[0056] 需要说明的是,本实施例中的调整单元406还可以进一步包括: [0056] Note that the present embodiment adjustment unit 406 may further comprises:

[0057] 第一调整单元4061,用于若虚拟子资源池的容量高于与当前存储数据访问热度值相匹配的容量,则减少该虚拟子资源池的容量; [0057] The first adjustment unit 4061, if the virtual capacity for child resource pools than the current popularity value of the stored data matches the access capacity, reduce the capacity of the virtual child resource pools;

[0058] 第二调整单元4062,用于若虚拟子资源池的容量低于与当前存储数据访问热度值相匹配的容量,则增加该虚拟子资源池的容量,增加的虚拟子资源池的容量不大于减少的虚拟子资源池的容量。 [0058] The second adjustment unit 4062, if the virtual capacity for child resource pools below the current popularity value of the stored data matches the access capacity, increase the capacity of the virtual child resource pool, increasing the capacity of the virtual sub-resource pools capacity not greater than the decrease of virtual child resource pool.

[0059] 为了便于理解,下面以一具体应用场景对本实施例中缓存分配装置的各单元之间的联系进行说明。 [0059] For ease of understanding, the following a specific application scenario of the links between the various units of the cache allocation apparatus embodiment will be described.

[0060] 本发明实施例中,确定单元401确定逻辑单元对应的业务数据类型,且确定单元401确定获取到的业务数据需要存储的逻辑单元LUN,查找单元402查找与逻辑单元对应的虚拟子资源池。 [0060] The embodiments of the present invention, the determining unit 401 determines a logical unit corresponding to the service type of data, and determining a logical unit LUN unit 401 determines that the acquired service data required to be stored, to find the virtual sub-resource unit 402 to find logical unit corresponding to pool.

[0061] 需要说明的是,SSD Cache缓存资源被划分单元404预先划分为与逻辑单元数量相等的虚拟子资源池,每个虚拟子资源池与一个不同的逻辑单元对应,即每个虚拟子资源池的数据仅供一个LUN访问,而且每个虚拟子资源池所包括的缓存资源存储对应逻辑单元的业务数据,每个LUN在其对应的虚拟子资源池中对数据的访问均独立于其他LUN进行,但每个虚拟子资源池的数据有机会供任意LUN访问。 [0061] Incidentally, SSD Cache cache resources are pre-dividing unit 404 divided into an equal number of virtual logical sub-unit resource pool, with each virtual sub-resource pool corresponding to a different logical units, i.e., each virtual sub-resources traffic data pool only access a LUN, and each virtual resource pool comprises sub-cache memory corresponding to the logical unit resources, access to the data for each LUN in the corresponding virtual sub-resource pools are independent of the other LUN , but the data in each virtual child resource pools have a chance for any LUN access.

[0062] 存储单元403将业务数据存储于查找到的虚拟子资源池所包括的缓存资源中,存储过程可参见前述图1所示实施例中步骤103所描述的相关内容,此处不再赘述。 [0062] The storage unit 403 the service data stored in the buffer of the virtual resource lookup sub included in the resource pool, stored procedures can be found in the embodiment shown in Figure 1 the content in step 103 described embodiments will not be repeated here .

[0063] 当到达预置时长时,获取单元405获取所划分的虚拟子资源池中所存储数据的访问热度值,在SSD Cache资源池系统内,可设置调整线程,预先设置一定的时长,每到达该预置的时长则获取所划分的虚拟子资源池中存储的数据的访问热度值,该时长的设定与实际应用过程相关,时长的具体数值此处不作限定。 [0063] When reaching the preset length of time, obtaining acquired virtual Son resource pools for storing data of the divided access popularity value unit 405, within the SSD Cache resource pool system, may be provided to adjust the thread, a preset constant duration, each when reaching the preset length of the heat value of gaining access to data stored in virtual sub-divided resource pool, the duration of the actual application process associated with the setting, which is not limited to the specific length values ​​here.

[0064] 需要说明的是,访问热度值包括虚拟子资源池中存储的数据的访问频率及虚拟子资源池中存储的热点数据数量,访问频率越高,热点数据数量越多,表示访问热度值越高, 虚拟子资源池中存储数据的访问频率及虚拟子资源池中存储的热点数据数量均可由系统内部的计数器进行计数,具体为本领域技术人员公知技术,此处不再赘述。 [0064] Incidentally, the number of hotspot access popularity value comprises data access frequency of the data stored virtual resource pools and sub-sub-stored virtual resource pool, the higher the access frequency, the more the hot data representing access popularity value the higher the number of hot spots virtual data access frequency sub-pool of storage resources and data stored virtual child resource pools can be counted by an internal counter of the system, particularly well-known to those skilled in art, is not repeated herein.

[0065] 根据预置的访问热度值与虚拟子资源池容量的匹配关系,调整单元406将虚拟子资源池的容量调整至与当前存储数据访问热度值相匹配的容量,其中,若虚拟子资源池的容量高于与当前存储数据访问热度值相匹配的容量,则第一调整单元4061减少该虚拟子资源池的容量,若虚拟子资源池的容量低于与当前存储数据访问热度值相匹配的容量,则第二调整单元4062增加该虚拟子资源池的容量,增加的虚拟子资源池的容量不大于减少的虚拟子资源池的容量,具体调整过程请参见前述图3所示实施例中步骤305所描述的内容,此处不再赘述。 [0065] The matching relationship with the heat value of the battery capacity to access a virtual sub-resources preset virtual capacity adjustment unit 406 is adjusted to child resource pools currently stored temperature data access capacity values ​​match, wherein, if the virtual sub-resource pool capacity than the current popularity value of the stored data matches the access capacity of the first adjustment unit 4061 to reduce the capacity of the virtual child resource pool, if the capacity of the virtual child resource pools below match the current value stored in the data access popularity the capacity of the second adjustment unit 4062 to increase the capacity of the virtual child resource pool, increasing the capacity of the virtual resource pool is not larger than the sub-reduced capacity virtual child resource pools, see the specific adjustment process embodiment shown in Figure 3 the embodiment of FIG. step 305 described hereinabove, is not repeated here.

[0066] 由于各虚拟子资源池只能使用划分给自身的缓存资源,那么,若当前划分给虚拟子资源池的容量低于与当前存储数据访问热度值相匹配的容量时,虚拟子资源池没有可供业务数据存储的容量时,可由删除单元408删除该虚拟子资源池中的非热点数据获取更多空余容量,具体的,由排序单元407将该虚拟子资源池中数据的访问频率进行排序,排序方式可由高到低,也可由低到高,然后由删除单元408删除访问频率排序最末尾的一个或多个数据,具体删除的数据数量,与实际应用过程相关,此处不作具体限定。 [0066] Due to the respective virtual sub-resource pools can only use resources allocated to its own cache, then, if the current child resource allocated to the virtual pool capacity is lower than the value currently stored temperature data access matches the capacity of the virtual sub-resource pools when there is no service available data storage capacity by deleting unit 408 to delete the virtual non-hotspot data for more sub-resource pool available capacity. specifically, the sorting unit 407 by the data access frequency virtual sub-resource pool , the sort mode may be from high to low, low to high may also be, and then sort the rearmost one or more data deleting unit 408 to delete from the access frequency, the number of data specific deletion associated with practical applications, where not specifically defined .

[0067] 需要说明的是,虚拟子资源池中数据的访问频率可由系统内计数器进行计数,具体为本领域技术人员公知技术,此处不再赘述。 [0067] Incidentally, the data access to the pool of virtual sub-resources within a frequency counter for counting by the system, particularly well known to those skilled art, will not be repeated here.

[0068] 本发明实施例中,SSD Cache缓存资源被划分单元404预先划分为与逻辑单元数量相等的虚拟子资源池,每个虚拟子资源池与一个不同的逻辑单元对应,即每个虚拟子资源池的数据仅供一个LUN访问,而且每个虚拟子资源池所包括的缓存资源存储对应逻辑单元的业务数据,由于每个虚拟子资源池与一个不同的逻辑单元对应,因此避免分别来自两端控制器的多个LUN同时访问同一缓存数据,从而避免控制两端控制器之间为访问同一缓存资源数据而进行复杂的通信协商过程,根据预置的访问热度值与虚拟子资源池容量的匹配关系,调整单元406将虚拟子资源池的容量调整至与当前存储数据访问热度值相匹配的容量,不断动态调整各虚拟子资源池的容量,使得对虚拟子资源池的容量分配更符合实际应用。 [0068] embodiment, SSD Cache resource partitioning the cache unit 404 is divided into a predetermined equal number of virtual logical sub-unit resource pools, each virtual sub-resource pool is different corresponding to a logical unit, i.e., each virtual sub-embodiment of the present invention traffic data resource pool is only a LUN access, and each virtual resource pool comprises sub-cache memory corresponding to the logical unit resources, since each sub-resource pool to a virtual logical unit corresponding to different, thus avoiding respectively from two a plurality of LUN of the controller to access the same data cache to avoid cache control access to the same data resources complex negotiation between both ends of the communication controller in accordance with a preset value of closeness to access the virtual child resource pool capacity matching relation, the adjusting unit 406 the capacity of the virtual sub-resource pool is adjusted to the currently stored data access popularity value matches the capacity of continuously dynamically adjusting the capacity of each virtual sub-resource pool, such that the capacity allocation virtual child resource pools more realistic application.

[0069] 上述实施例中的缓存资源以SSD Cache资源为例,可以理解的是,也可应用在其他相同类型的存储资源,缓存资源应用的具体类型与实际应用过程相关,此处不作限定。 [0069] Examples of the above-described embodiments SSD Cache cache resources to resources, for example, be appreciated that the same may also be applied in other types of storage resources, cache resources specific type of application associated with the practical application of the process, is not limited herein.

[0070] 本领域普通技术人员可以理解实现上述实施例方法中的全部或部分步骤是可以通过程序来指令相关的硬件完成,所述的程序可以存储于一种计算机可读存储介质中,上述提到的存储介质可以是只读存储器,磁盘或光盘等。 [0070] Those of ordinary skill in the art may understand that the above embodiments of the method steps may be all or part by a program instructing relevant hardware, the program may be stored in a computer-readable storage medium, the above mentioned the storage medium may be a read-only memory, magnetic or optical disk.

[0071] 以上对本发明所提供的一种分配缓存方法及装置进行了详细介绍,对于本领域的一般技术人员,依据本发明实施例的思想,在具体实施方式及应用范围上均会有改变之处, 综上所述,本说明书内容不应理解为对本发明的限制。 [0071] The above detailed description of a dispensing apparatus and the caching method of the present invention provides, for those of ordinary skill in the art, according to the idea of ​​an embodiment of the present invention, in the particular embodiment and application scopes of change , the summary, the present specification shall not be construed as limiting the present invention.

Claims (10)

1. 一种缓存分配方法,其特征在于,包括:确定获取到的业务数据需要存储的逻辑单元; 查找与所述逻辑单元对应的虚拟子资源池;将所述业务数据存储于查找到的虚拟子资源池所包括的缓存资源中; 其中,缓存资源池被预先划分为与所述逻辑单元数量相等的虚拟子资源池,每个虚拟子资源池对应一个不同的逻辑单元,且每个虚拟子资源池所包括的缓存资源存储对应逻辑单元的业务数据。 A cache allocation method, comprising: determining traffic data acquired logical unit needs to be stored; find the corresponding virtual logical units child resource pool; the service data stored in the searched virtual child resource pool cache resources included in; wherein the buffer pool resources are divided in advance to be equal to the number of virtual sub-logic unit resource pools, each virtual resource pool corresponding to a different sub-logic unit, and each virtual sub traffic data buffer memory resources corresponding to the logical unit included in the resource pool.
2.根据权利要1所述的方法,其特征在于,还包括:当到达预置时长时,获取所划分的虚拟子资源池中所存储数据的访问热度值; 根据预置的访问热度值与虚拟子资源池容量的匹配关系,将虚拟子资源池的容量调整至与当前存储数据访问热度值相匹配的容量。 2. A method according to claim 1, characterized in that, further comprising: when the duration reaches the preset, gain access to the divided value of closeness of the virtual sub-data stored in the resource pool; access in accordance with a preset value of closeness subpool match between the virtual resources, the capacity of the virtual child resource pools to adjust to the current popularity value of the stored data access that matches the capacity.
3.根据权利要求1所述的方法,其特征在于,所述方法还包括:当虚拟子资源池没有可供业务数据存储的容量时,将所述虚拟子资源池中数据的访问频率进行排序;删除所述访问频率排序中末尾一位或多位数据。 3. The method according to claim 1, wherein said method further comprises: when the virtual sub-service data resource pools Not available storage capacity, the data access frequency resource subpool virtual sorting ; delete the access frequency ordering the end of the one or more data.
4.根据权利要求1至3中任意一项所述的方法,其特征在于,还包括: 确定逻辑单元对应的业务数据类型;根据业务数据类型对逻辑单元所对应的虚拟子资源池容量进行调整。 4. The method according to any one of claims 1 to 3, characterized in that, further comprising: determining a logical data type of the corresponding service unit; adjusted according to the type of service data units corresponding to the logical sub-virtual resource pool size .
5.根据权利要求1至3中任意一项所述的方法,其特征在于,所述根据预置的访问热度值与虚拟子资源池容量的匹配关系,将虚拟子资源池的容量调整至与当前存储数据访问热度值相匹配的容量包括:若所述虚拟子资源池的容量高于与当前存储数据访问热度值相匹配的容量,则减少所述虚拟子资源池的容量;若所述虚拟子资源池的容量低于与当前存储数据访问热度值相匹配的容量,则增加所述虚拟子资源池的容量,所述增加的虚拟子资源池的容量不大于所述减少的虚拟子资源池的容量。 5. The method according to any one of claims 1 to 3, wherein the access according to the matching relation with the heat value of the virtual sub-resource pool size preset, the capacity of the virtual pool is adjusted to child resource and the current popularity value of the stored data matches the access capacity includes: if the capacity of the virtual pool is higher than the child resource currently stored temperature data access capacity values ​​match, then reduce the capacity of the virtual child resource pools; if the virtual resource pool is less than the capacity of the sub memory data access with the current popularity value matches the capacity, increasing the capacity of the virtual sub-resource pool, increasing the capacity of the virtual sub-resource pool is not greater than the reduced virtual child resource pool capacity.
6. 一种缓存分配装置,其特征在于,包括:确定单元,用于确定获取到的业务数据需要存储的逻辑单元; 查找单元,用于查找与所述逻辑单元对应的虚拟子资源池;存储单元,用于将所述业务数据存储于查找到的虚拟子资源池所包括的缓存资源中; 划分单元,用于缓存资源池被预先划分为与所述逻辑单元数量相等的虚拟子资源池。 A cache allocation apparatus comprising: a determining unit configured to store the service data needed to determine the acquired logical unit; searching unit, the logic unit for finding the corresponding virtual child resource pool; storage means for caching the resource data stored in a lookup service to virtual sub included in resource pool; dividing unit for pre-caching the resource pool is divided into the virtual logical unit is equal to the number of sub-resource pools.
7.根据权利要求6所述的装置,其特征在于,所述装置还包括:获取单元,用于当到达预置时长时,获取所划分的虚拟子资源池中所存储数据的访问热度值;调整单元,用于根据预置的访问热度值与虚拟子资源池容量的匹配关系,将虚拟子资源池的容量调整至与当前存储数据访问热度值相匹配的容量。 7. The device according to claim 6, characterized in that said apparatus further comprises: an acquisition unit for a long time when it reaches the preset, gain access to the heat value of the virtual sub-data stored in the resource pool divided; adjusting unit, for access according to a preset matching relationship with the heat value of the battery capacity of the virtual sub-resources, the capacity of the virtual child resource pool is adjusted to the current popularity value of the stored data matches the access capacity.
8.根据权利要求6所述的装置,其特征在于,所述装置还包括:排序单元,用于当虚拟子资源池没有可供业务数据存储的容量时,将所述虚拟子资源池中数据的访问频率进行排序;删除单元,用于删除所述访问频率排序中末尾一位或多位数据。 8. The apparatus according to claim 6, characterized in that said apparatus further comprising: a sorting unit for, when there is no available resource pools virtual sub-service data storage capacity of the virtual sub-data resource pool access frequency sorting; deleting means for deleting the access frequency at the end of one or more ordering data.
9.根据权利要求7所述的装置,其特征在于,所述确定单元,还用于确定逻辑单元对应的业务数据类型;所述调整单元,还用于根据业务数据类型对逻辑单元所对应的虚拟子资源池容量进行调整。 9. The apparatus according to claim 7, wherein said determining means further configured to determine a logical data type of the corresponding service unit; the adjustment unit is further configured according to the service type of data corresponding to the logical unit virtual child resource pool of capacity to adjust.
10.根据权利要求6至9任意一项所述的装置,其特征在于,所述调整单元包括:第一调整单元,用于若所述虚拟子资源池的容量高于与当前存储数据访问热度值相匹配的容量,则减少所述虚拟子资源池的容量;第二调整单元,用于若所述虚拟子资源池的容量低于与当前存储数据访问热度值相匹配的容量,则增加所述虚拟子资源池的容量,所述增加的虚拟子资源池的容量不大于所述减少的虚拟子资源池的容量。 10. The apparatus according to any one of claims 6-9, wherein said adjusting means comprises: a first adjusting unit, the capacity for the virtual sub-resource pool is higher than if the currently stored access data heat capacity values ​​match, then reduce the capacity of the virtual child resource pools; a second adjusting unit, if the virtual capacity for child resource pools below the currently stored temperature data access capacity values ​​match, then the increase in capacity capacity capacity said virtual child resource pool, increasing the pool of virtual sub-resource is not larger than the reduced virtual child resource pools.
CN2010106161456A 2010-12-30 2010-12-30 Cache allocation method and device CN102043732A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN2010106161456A CN102043732A (en) 2010-12-30 2010-12-30 Cache allocation method and device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN2010106161456A CN102043732A (en) 2010-12-30 2010-12-30 Cache allocation method and device
PCT/CN2011/084927 WO2012089144A1 (en) 2010-12-30 2011-12-29 Cache allocation method and device

Publications (1)

Publication Number Publication Date
CN102043732A true CN102043732A (en) 2011-05-04

Family

ID=43909883

Family Applications (1)

Application Number Title Priority Date Filing Date
CN2010106161456A CN102043732A (en) 2010-12-30 2010-12-30 Cache allocation method and device

Country Status (2)

Country Link
CN (1) CN102043732A (en)
WO (1) WO2012089144A1 (en)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102207830A (en) * 2011-05-27 2011-10-05 杭州宏杉科技有限公司 Cache dynamic allocation management method and device
CN102262512A (en) * 2011-07-21 2011-11-30 浪潮(北京)电子信息产业有限公司 The system, apparatus and method for implementing a partitioned cache disk array
WO2012089144A1 (en) * 2010-12-30 2012-07-05 成都市华为赛门铁克科技有限公司 Cache allocation method and device
CN103218179A (en) * 2013-04-23 2013-07-24 深圳市京华科讯科技有限公司 Second-level system acceleration method based on virtualization
CN103678414A (en) * 2012-09-25 2014-03-26 腾讯科技(深圳)有限公司 Method and device for storing and inquiring data
CN103744614A (en) * 2013-12-17 2014-04-23 记忆科技(深圳)有限公司 Method for accessing solid state disc and solid state disc thereof
CN104349172A (en) * 2013-08-02 2015-02-11 杭州海康威视数字技术股份有限公司 Cluster management method of network video recorder and device thereof
CN106201921A (en) * 2016-07-18 2016-12-07 浪潮(北京)电子信息产业有限公司 The method of adjustment of a kind of cache partitions capacity and device
CN106502576A (en) * 2015-09-06 2017-03-15 中兴通讯股份有限公司 Migration strategy method of adjustment, capacity change suggesting method and device
WO2017036428A3 (en) * 2015-09-06 2017-04-13 中兴通讯股份有限公司 Capacity change suggestion method and device
CN107171792A (en) * 2017-06-05 2017-09-15 北京邮电大学 A kind of virtual key pond and the virtual method of quantum key resource

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103067467B (en) * 2012-12-21 2016-08-03 深圳市深信服电子科技有限公司 Caching method and device
CN103530240B (en) * 2013-10-25 2016-09-07 华为技术有限公司 Data-block cache method and apparatus

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060064536A1 (en) * 2004-07-21 2006-03-23 Tinker Jeffrey L Distributed storage architecture based on block map caching and VFS stackable file system modules
CN101044483A (en) * 2004-12-10 2007-09-26 国际商业机器公司 Storage pool space allocation across multiple locations
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
CN101620569A (en) * 2008-07-03 2010-01-06 英业达股份有限公司 Expansion method of logical volume storage space
CN101840308A (en) * 2009-10-28 2010-09-22 创新科存储技术有限公司;创新科软件技术(深圳)有限公司 Hierarchical memory system and logical volume management method thereof

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4307202B2 (en) * 2003-09-29 2009-08-05 株式会社日立製作所 Storage system and storage control device
CN1798094A (en) * 2004-12-23 2006-07-05 华为技术有限公司 Method of using buffer area
US9223516B2 (en) * 2009-04-22 2015-12-29 Infortrend Technology, Inc. Data accessing method and apparatus for performing the same using a host logical unit (HLUN)
CN101609432B (en) * 2009-07-13 2011-04-13 中国科学院计算技术研究所 Shared cache management system and method thereof
CN102043732A (en) * 2010-12-30 2011-05-04 成都市华为赛门铁克科技有限公司 Cache allocation method and device

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060064536A1 (en) * 2004-07-21 2006-03-23 Tinker Jeffrey L Distributed storage architecture based on block map caching and VFS stackable file system modules
CN101044483A (en) * 2004-12-10 2007-09-26 国际商业机器公司 Storage pool space allocation across multiple locations
CN101620569A (en) * 2008-07-03 2010-01-06 英业达股份有限公司 Expansion method of logical volume storage space
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
CN101840308A (en) * 2009-10-28 2010-09-22 创新科存储技术有限公司;创新科软件技术(深圳)有限公司 Hierarchical memory system and logical volume management method thereof

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012089144A1 (en) * 2010-12-30 2012-07-05 成都市华为赛门铁克科技有限公司 Cache allocation method and device
CN102207830A (en) * 2011-05-27 2011-10-05 杭州宏杉科技有限公司 Cache dynamic allocation management method and device
CN102207830B (en) * 2011-05-27 2013-06-12 杭州宏杉科技有限公司 Cache dynamic allocation management method and device
CN102262512A (en) * 2011-07-21 2011-11-30 浪潮(北京)电子信息产业有限公司 The system, apparatus and method for implementing a partitioned cache disk array
CN103678414A (en) * 2012-09-25 2014-03-26 腾讯科技(深圳)有限公司 Method and device for storing and inquiring data
CN103218179A (en) * 2013-04-23 2013-07-24 深圳市京华科讯科技有限公司 Second-level system acceleration method based on virtualization
CN104349172A (en) * 2013-08-02 2015-02-11 杭州海康威视数字技术股份有限公司 Cluster management method of network video recorder and device thereof
CN104349172B (en) * 2013-08-02 2017-10-13 杭州海康威视数字技术股份有限公司 The cluster management method and its device of Internet video storage device
CN103744614B (en) * 2013-12-17 2017-07-07 记忆科技(深圳)有限公司 Method and its solid state hard disc that solid state hard disc is accessed
CN103744614A (en) * 2013-12-17 2014-04-23 记忆科技(深圳)有限公司 Method for accessing solid state disc and solid state disc thereof
CN106502576A (en) * 2015-09-06 2017-03-15 中兴通讯股份有限公司 Migration strategy method of adjustment, capacity change suggesting method and device
WO2017036428A3 (en) * 2015-09-06 2017-04-13 中兴通讯股份有限公司 Capacity change suggestion method and device
CN106201921A (en) * 2016-07-18 2016-12-07 浪潮(北京)电子信息产业有限公司 The method of adjustment of a kind of cache partitions capacity and device
CN107171792A (en) * 2017-06-05 2017-09-15 北京邮电大学 A kind of virtual key pond and the virtual method of quantum key resource

Also Published As

Publication number Publication date
WO2012089144A1 (en) 2012-07-05

Similar Documents

Publication Publication Date Title
US7065616B2 (en) System and method for policy based storage provisioning and management
US7747836B2 (en) Integrated storage virtualization and switch system
US6195703B1 (en) Dynamic routing for performance partitioning in a data processing network
US8290972B1 (en) System and method for storing and accessing data using a plurality of probabilistic data structures
US7136862B2 (en) Method for creation and management of virtual volumes for DBMs
US8874850B1 (en) Hierarchically tagged cache
US6948044B1 (en) Methods and apparatus for storage virtualization
EP1702271B1 (en) Adaptive file readahead based on multiple factors
US8046422B2 (en) Automatic load spreading in a clustered network storage system
KR101726824B1 (en) Efficient Use of Hybrid Media in Cache Architectures
US7146389B2 (en) Method for rebalancing free disk space among network storages virtualized into a single file system view
US9348842B2 (en) Virtualized data storage system optimizations
US8127077B2 (en) Virtual path storage system and control method for the same
EP1569085B1 (en) Method and apparatus for increasing data storage capacity
US7676628B1 (en) Methods, systems, and computer program products for providing access to shared storage by computing grids and clusters with large numbers of nodes
JP4278445B2 (en) Network system and switch
US20050198062A1 (en) Method and apparatus for accelerating data access operations in a database system
JP4139675B2 (en) Virtual volume storage area allocation method, apparatus and program thereof
JP2007536612A (en) Storage switch traffic bandwidth control
US20110078343A1 (en) Distributed storage network including memory diversity
US8407436B2 (en) Methods and apparatus for migrating thin provisioning volumes between storage systems
US20110107052A1 (en) Virtual Disk Mapping
US9342443B2 (en) Systems and methods for memory system management based on thermal information of a memory system
US8984221B2 (en) Method for assigning storage area and computer system using the same
KR20160138448A (en) Methods and systems for converged networking and storage

Legal Events

Date Code Title Description
C06 Publication
C10 Entry into substantive examination
C53 Correction of patent for invention or patent application
COR Change of bibliographic data

Free format text: CORRECT: APPLICANT; FROM: CHENGDU HUAWEI SYMANTEC TECHNOLOGIES CO., LTD. TO: HUAWEI DIGITAL TECHNOLOGY (CHENGDU) CO., LTD.

C12 Rejection of a patent application after its publication