WO2017092480A1 - 一种数据迁移的方法及装置 - Google Patents

一种数据迁移的方法及装置 Download PDF

Info

Publication number
WO2017092480A1
WO2017092480A1 PCT/CN2016/098863 CN2016098863W WO2017092480A1 WO 2017092480 A1 WO2017092480 A1 WO 2017092480A1 CN 2016098863 W CN2016098863 W CN 2016098863W WO 2017092480 A1 WO2017092480 A1 WO 2017092480A1
Authority
WO
WIPO (PCT)
Prior art keywords
access heat
weight
write
read
storage
Prior art date
Application number
PCT/CN2016/098863
Other languages
English (en)
French (fr)
Inventor
林春恭
熊艳辉
Original Assignee
华为技术有限公司
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 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2017092480A1 publication Critical patent/WO2017092480A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
    • G06F3/061—Improving I/O performance
    • G06F3/0611—Improving I/O performance in relation to response time
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
    • G06F3/0646—Horizontal data movement in storage systems, i.e. moving data in between storage devices or systems
    • G06F3/0647—Migration mechanisms
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
    • G06F3/067—Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601—Interfaces specially adapted for storage systems
    • G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
    • G06F3/0671—In-line storage system
    • G06F3/0683—Plurality of storage devices
    • G06F3/0689—Disk arrays, e.g. RAID, JBOD

Definitions

  • the present invention relates to the field of computer technologies, and in particular, to a data migration method and apparatus.
  • a plurality of storage tiers are included in the tiered storage system.
  • the performance of the storage media in different storage tiers is different. The higher the performance of the storage tiers in the storage tier, the higher the performance, and one or more storage media may be included in one storage tier.
  • the hotter data data with higher access heat
  • the hotter data is stored in a higher-level storage hierarchy, and when one data is changed from cold (hot) data to hot (cold) data, the data Migration is also done between storage tiers.
  • a method for migrating data by a centralized controller in a hierarchical storage system includes: obtaining read access heat and write access heat of the data at the storage level. Comparing the sum of the read access heat and the write access heat with a specific threshold. When the sum of the read access heat and the write access heat is greater than the specific threshold (in this case, the data is hot data), the data is migrated to the level. Higher storage level.
  • each storage level has a RAID level.
  • the RAID level corresponds to a write amplification factor
  • the write amplification factor corresponding to the RAID level of one storage level refers to a storage medium that is actually generated when a write access is made to the logical address of the data stored in the storage hierarchy.
  • the number of accesses to which the storage medium belongs For example, when writing a data stored in a RAID level with a RAID level of 5, a write access to the logical address of the data is required, and each write access to the logical address of a data will result in two actual pairs.
  • the storage medium for actually storing the data due to the write operation of the data cannot be truly reflected. Quality access pressure.
  • Embodiments of the present invention provide a data migration method and apparatus for improving access speed of data in a storage hierarchy.
  • a method of data migration including:
  • the weight is determined according to the amplification factor corresponding to the data protection mechanism of the first storage level, and the amplification factor refers to the number of accesses to the storage medium of the storage target data actually generated when the logical address of the target data is accessed once, and the storage medium belongs to the first Storage level
  • the target data is migrated to the second storage level.
  • the access heat is a write access heat
  • the weight is a first weight of the write access heat determined according to the write amplification factor corresponding to the data protection mechanism
  • the write access heat is the target data.
  • the number of write accesses of the first storage level or the number of write accesses of the target data at the first storage level per unit time, and the write amplification factor refers to the storage of the storage target data actually generated when a write access is made to the logical address of the target data. The number of accesses to the media.
  • the access heat includes a write access heat and a read access heat
  • the weight includes a first weight of the write access heat determined according to the write amplification factor corresponding to the data protection mechanism and according to the data protection a second weight of the read access heat determined by the read amplification factor corresponding to the mechanism
  • the write access heat is the number of write accesses of the target data at the first storage level
  • the read access heat is the number of read accesses of the target data at the first storage level; or, the write access heat is the target data at the first storage level per unit time.
  • the number of write accesses, the read access heat is the number of read accesses of the target data at the first storage level per unit time;
  • the write amplification factor refers to writing the logical address of the target data once.
  • the number of accesses to the storage medium storing the target data actually generated at the time of access, and the read amplification factor is the number of accesses to the storage medium storing the target data actually generated when the logical address of the target data is read once.
  • the first possible implementation manner or the second possible implementation manner of the first aspect in a third possible implementation manner, when the preset condition is greater than the first threshold, the second storage level The performance of the storage medium is better than the performance of the storage medium in the first storage level; or, when the preset condition is less than the second threshold, the performance of the storage medium in the first storage level is better than that in the second storage level The performance of the storage medium, the first threshold being greater than the second threshold.
  • the first weight is a write amplification factor
  • the second weight is a read amplification factor
  • the first weight is a first value
  • the second weight is a second value
  • the ratio of the first value to the second value and the ratio of the write amplification factor to the read amplification factor are the same.
  • the data protection mechanism comprises an independent redundant disk array RAID level or Erasure code EC.
  • a data migration apparatus including:
  • An obtaining unit configured to acquire access heat of the target data at the first storage level
  • a determining unit configured to determine a weight according to an amplification factor corresponding to a data protection mechanism of the first storage level, where the amplification factor refers to an access number of the storage medium that actually generates the storage target data when the logical address of the target data is accessed once,
  • the storage medium belongs to the first storage level;
  • the migration unit is configured to migrate the target data to the second storage level when the target result satisfies the preset condition.
  • the access heat is the write access heat
  • the weight is the first weight of the write access heat determined according to the write amplification factor corresponding to the data protection mechanism
  • the write access heat is the target data.
  • the number of write accesses of the first storage level or the number of write accesses of the target data at the first storage level per unit time, and the write amplification factor refers to the logical address of the target data once The number of accesses to the storage medium storing the target data actually generated when the access is written.
  • the access heat includes a write access heat and a read access heat
  • the weight includes a first weight of the write access heat determined according to the write amplification factor corresponding to the data protection mechanism and according to the data protection a second weight of the read access heat determined by the read amplification factor corresponding to the mechanism
  • the write access heat is the number of write accesses of the target data at the first storage level, and the read access heat is the number of read accesses of the target data at the first storage level; or, the write access heat is the target data at the first storage level per unit time.
  • the number of write accesses, the read access heat is the number of read accesses of the target data in the first storage level per unit time;
  • the write amplification factor refers to the storage of the storage target data actually generated when a write access is made to the logical address of the target data.
  • the number of accesses of the medium, the read amplification factor refers to the number of accesses to the storage medium storing the target data actually generated when the logical address of the target data is read once.
  • the first possible implementation manner or the second possible implementation manner of the second aspect in a third possible implementation manner, when the preset condition is greater than the first threshold, the second storage level The performance of the storage medium is better than the performance of the storage medium in the first storage level; or, when the preset condition is less than the second threshold, the performance of the storage medium in the first storage level is better than that in the second storage level The performance of the storage medium, the first threshold being greater than the second threshold.
  • the first weight is a write amplification factor
  • the second weight is a read amplification factor
  • the first weight is a first value
  • the second weight is a second value
  • the ratio of the first value to the second value and the ratio of the write amplification factor to the read amplification factor are the same.
  • the data protection mechanism includes an independent redundant disk array RAID level or Erasure code EC.
  • a data migration apparatus comprising: a memory and a processor, the memory is configured to store a set of codes, and the processor performs the following actions according to the set of codes:
  • the weight is determined according to the amplification factor corresponding to the data protection mechanism of the first storage level, and the amplification factor refers to the number of accesses to the storage medium of the storage target data actually generated when the logical address of the target data is accessed once, and the storage medium belongs to the first Storage level
  • the target data is migrated to the second storage level.
  • the access heat is a write access heat
  • the weight is a first weight of the write access heat determined according to the write amplification factor corresponding to the data protection mechanism
  • the write access heat is the target data.
  • the number of write accesses of the first storage level or the number of write accesses of the target data at the first storage level per unit time, and the write amplification factor refers to the storage of the storage target data actually generated when a write access is made to the logical address of the target data. The number of accesses to the media.
  • the access heat includes a write access heat and a read access heat
  • the weight includes a first weight of the write access heat determined according to the write amplification factor corresponding to the data protection mechanism and according to the data protection. a second weight of the read access heat determined by the read amplification factor corresponding to the mechanism;
  • the write access heat is the number of write accesses of the target data at the first storage level, and the read access heat is the number of read accesses of the target data at the first storage level; or, the write access heat is the target data at the first storage level per unit time.
  • the number of write accesses, the read access heat is the number of read accesses of the target data in the first storage level per unit time;
  • the write amplification factor refers to the storage of the storage target data actually generated when a write access is made to the logical address of the target data.
  • the number of accesses of the medium, the read amplification factor refers to the number of accesses to the storage medium storing the target data actually generated when the logical address of the target data is read once.
  • the first possible implementation manner or the second possible implementation manner of the third aspect in a third possible implementation manner, when the preset condition is greater than the first threshold, the second storage level The performance of the storage medium is better than the performance of the storage medium in the first storage level; or, when the preset condition is less than the second threshold, the performance of the storage medium in the first storage level is better than that in the second storage level The performance of the storage medium, the first threshold being greater than the second threshold.
  • One weight is a write amplification factor, and the second weight is a read amplification factor; or, the first weight is a first value, the second weight is a second value, a ratio of the first value to the second value, and a write amplification factor and a read amplification factor The ratio is the same.
  • the data protection mechanism includes an independent redundant disk array RAID level or Erasure code EC.
  • the method and the device provided by the embodiment of the present invention determine the weight according to the amplification factor corresponding to the data protection mechanism of the first storage level of the storage target data, and calculate the target result according to the weight and the access heat of the target data, thereby determining whether to migrate the target data. Therefore, compared with the prior art, the target result can more realistically reflect the access pressure to the storage medium storing the target data actually generated by accessing the logical address of the target data, according to the target result and the preset of the target data.
  • Conditions migrating target data to a second storage tier at the appropriate time may allow each storage tier to withstand access pressures appropriate to its capabilities, preventing the first storage tier from being limited due to excessive access to data in the first storage tier The access speed of the data in it.
  • FIG. 1 is a schematic diagram of a connection between a hierarchical storage system and an external device according to an embodiment of the present invention
  • FIG. 2 is a schematic diagram of a storage hierarchy included in a storage module according to an embodiment of the present disclosure
  • FIG. 3 is a flowchart of a method for data migration according to an embodiment of the present invention.
  • FIG. 4 is a flowchart of still another method for data migration according to an embodiment of the present invention.
  • FIG. 5 is a schematic structural diagram of a data migration apparatus according to an embodiment of the present disclosure.
  • FIG. 6 is a schematic structural diagram of still another data migration apparatus according to an embodiment of the present invention.
  • the method provided in the embodiment of the present invention may be applied to at least a hierarchical storage system.
  • the hierarchical storage system includes one or more network nodes, and one network node may be composed of one or more servers, and each network node.
  • the network may be connected to a storage module by using a low-latency, high-throughput network.
  • the network may be Fibre Channel (FC) or 10Gigabit Ethernet.
  • FC Fibre Channel
  • 10Gigabit Ethernet 10Gigabit Ethernet.
  • the external device can read and write data stored in the hierarchical storage system through an interface with the hierarchical storage system.
  • the storage module includes a plurality of storage media.
  • the storage medium in the present invention refers to a carrier that stores data, such as a floppy disk, an optical disk, or a hard disk.
  • the storage medium is divided into different storage levels, and the storage module includes a plurality of storage levels, which are storage level 1 to storage level N (N ⁇ 1, N is an integer), and the level is higher in the storage level.
  • the performance of the storage medium is higher (the level of storage level 1 is the highest in Figure 2).
  • An embodiment of the present invention provides a data migration method, as shown in FIG. 3, including:
  • the execution body in the embodiment of the present invention may be a centralized controller in the hierarchical storage system, and the centralized controller may be a network node having a centralized control function in the hierarchical storage system. It should be noted that the storage module and the network node shown in FIG. 1 can also be placed in the same device.
  • the target data may be any one of the data stored in the first storage level, and the method for obtaining the access heat of the target data may refer to the prior art.
  • the amplification factor refers to the number of accesses actually generated by the storage medium storing the target data when the logical address of the target data is accessed once, and the storage medium belongs to the first storage level.
  • the amplification factor corresponding to the data protection mechanism includes a write amplification factor and a read amplification factor, where the write amplification factor refers to the number of accesses to the storage medium storing the target data actually generated when the logical address of the target data is once accessed.
  • the read amplification factor refers to the number of accesses to the storage medium storing the target data actually generated when the logical address of the target data is read once, wherein
  • the number of accesses to the storage medium storing the target data refers to the sum of the number of read accesses and the number of write accesses to the storage medium storing the target data.
  • the access heat may include only the read access heat or the write access heat, and may also include the read access heat and the write access heat.
  • the weights determined in different cases are as follows:
  • the access heat is the write access heat
  • the weight is the first weight of the write access heat determined according to the write amplification factor corresponding to the data protection mechanism
  • the write access heat is the number of write accesses or unit time of the target data at the first storage level. The number of write accesses to the target data level at the first storage level.
  • the access heat includes a write access heat and a read access heat
  • the weight includes a first weight of the write access heat determined according to the write amplification factor corresponding to the data protection mechanism and a read access heat determined according to the read amplification factor corresponding to the data protection mechanism.
  • the write access heat is the number of write accesses of the target data at the first storage level
  • the read access heat is the number of read accesses of the target data at the first storage level; or, the write access heat is the target data at the first storage level per unit time.
  • the number of write accesses, the read access heat is the number of read accesses of the target data at the first storage level per unit time.
  • the access heat is the read access heat
  • the weight is the second weight of the read access heat determined according to the read amplification factor corresponding to the data protection mechanism
  • the read access heat is the number of read accesses or unit time of the target data at the first storage level. The number of read accesses of the target data at the first storage level.
  • the unit time may be 1 minute or 1 hour, or may be other preset time periods.
  • the write amplification factor is larger, the first weight is larger, and when the read amplification factor is larger, the second weight is larger.
  • the data protection mechanism includes a RAID level or an erasure coding (EC).
  • EC erasure coding
  • the data protection mechanism is taken as an example of a RAID level.
  • the write amplification is caused by a RAID write penalty. For example, when a data is written to a RAID level of a storage level of RAID 5, the data needs to be written. The logical address makes a write access, and the write access will actually generate two read operations on the storage medium storing the data and two write operations on the storage medium, specifically reading the old data from the storage medium and Data verification information, writing new data to the storage medium And the data verification information, it can be known that the write amplification factor corresponding to RAID5 is 4. When performing a read operation on the data, a read access to the logical address of the data is required, and the read access will actually generate a pair. The read operation of the storage medium storing the data shows that the read amplification factor corresponding to RAID 5 is 1.
  • the write amplification factor and the read amplification factor corresponding to the partial RAID level are shown by Table 1.
  • the target result first weight ⁇ write access heat.
  • the first weight may be a write amplification factor corresponding to the RAID level, or may be other values smaller than the write amplification factor and greater than 1.
  • the target result first weight ⁇ write access heat + second weight ⁇ read access heat.
  • the first weight is a write amplification factor
  • the second weight is a read amplification factor; or, the first weight is a first value, the second weight is a second value, a ratio of the first value to the second value, and a write amplification
  • the ratio of the coefficient to the read amplification factor is the same; or, the first weight is less than or equal to the write amplification factor and other values greater than 1, and the second weight is 1.
  • the first weight when determining the first weight and the second weight, taking the RAID level as the RAID 5 as an example, the first weight may be 4, the second weight is 1, or the first weight may be 0.8, and the second weight is 0.2. .
  • the target result second weight ⁇ read access heat.
  • the second weight can be a read amplification factor.
  • the target data is migrated to a second storage level.
  • first storage level and the second storage level may be continuous storage levels or discontinuous storage levels.
  • the performance of the storage medium in the second storage level is better than the performance of the storage medium in the first storage level; or, when the pre- When the condition is less than the second threshold, the performance of the storage medium in the first storage level is better than the performance of the storage medium in the second storage level, and the first threshold is greater than the second threshold.
  • the storage layer with better performance of the storage medium in the storage hierarchy can withstand the access pressure, so that when the target result is greater than the first threshold, the target data can be migrated to the storage medium for better performance.
  • the target result is less than the second threshold, it indicates that the access heat of the target data is not high, and therefore, the target data can be migrated to the storage level of the storage medium with lower performance.
  • the first storage level may be any one of the storage levels.
  • the first storage level may be storage level 2.
  • the first threshold may be a threshold when the data is migrated between the storage level 1 and the storage level 2
  • the second threshold may be a threshold when the data is migrated between the storage level 2 and the storage level 3.
  • a method for determining the first threshold and the second threshold provided in the embodiment of the present invention is as follows:
  • the target results of all the data in all storage levels are calculated every preset time period, and all the target results are sorted in descending order, and the front X is selected from the sorting results according to the capacity of the storage level 1.
  • X ⁇ 1, X is an integer
  • one or more data blocks composed of data, and storing the one or more data blocks in the storage level 1, the storage space occupied by the first X data and the storage level 1 The capacity is the same or similar; according to the capacity of the storage level 2, one or more data blocks composed of X+1th to Yth (Y ⁇ X+1, Y is an integer) data are selected from the sorting result, and Storing the one or more data blocks in the storage level 2, the storage space occupied by the X+1th to the Yth data is the same as or similar to the storage level 2; after the Yth data in the sort result
  • the data is stored in the storage level 3 (it is assumed in the present embodiment that all of the data occupies less space than the sum of the storage level 1, the storage level 2, and the storage
  • the target result of the Xth data in the sorting result is determined as the first threshold, and the target result of the Yth data in the sorted result is determined. Determined as the second threshold.
  • the first threshold and the second threshold may also be determined by other methods, and the embodiment of the present invention merely provides a method exemplarily.
  • the target data is migrated to the storage level 1, when the target data is less than 100.
  • the first storage level may be the storage level 3.
  • the first threshold may be between the storage level 1 and the storage level 2.
  • the threshold value when the data is migrated and the second threshold may be a threshold when the data is migrated between the storage level 4 and the storage level 5.
  • a method of determining a threshold value when migrating data between storage levels can be referred to the above embodiment.
  • the centralized controller may perform the foregoing method periodically, or may perform the foregoing method, and the specific condition may be determined according to the actual application scenario, which is not specifically limited in this embodiment of the present invention.
  • the method provided by the embodiment of the present invention determines the weight according to the amplification factor corresponding to the data protection mechanism of the first storage level of the storage target data, and calculates the target result according to the weight and the access heat of the target data, thereby determining whether to migrate the target data.
  • the target result can more realistically reflect the access pressure on the storage medium storing the target data actually generated by accessing the logical address of the target data, according to the target result and the preset condition of the target data.
  • each storage tier can be subjected to access pressures adapted to its own capabilities, preventing the restriction in the first storage tier due to excessive access to data in the first storage tier.
  • the access speed of the data is migrated to the second storage tier.
  • the embodiment of the present invention further provides a data migration method, which is used to exemplify the data migration method provided by the foregoing embodiment.
  • the first storage level is the storage level 2
  • the first threshold is the foregoing storage.
  • the second threshold is a threshold value when the data is migrated between the storage level 2 and the storage level 3, as shown in FIG. 4, the method includes:
  • the target data is stored in a storage medium in the storage level 2.
  • the write access heat is the number of write accesses of the target data at the storage level 2
  • the read access heat is the read access number of the target data at the storage level 2; or, the write access heat is the write access of the target data at the storage level 2 per unit time.
  • the number of times, the read access heat is the number of read accesses of the target data at the storage level 2 per unit time.
  • the first weight is a write amplification factor corresponding to a RAID level of the storage level 2, and the second weight is a read amplification factor corresponding to the RAID level; or, the first weight is a first value, and the second weight is a second value,
  • the ratio of the first value to the second value is the same as the ratio of the write amplification factor corresponding to the RAID level of the storage level 2 to the read amplification factor corresponding to the RAID level.
  • the target data is not migrated.
  • the level of the storage level 1 is higher than the level of the storage level 2, and the level of the storage level 2 is higher than the level of the storage level 3, when the target data is originally stored in the storage medium in the storage level 2.
  • the target result calculated according to the foregoing method is greater than the first threshold, the target data may be migrated to the storage level 1, and when the target result is less than the second threshold, the target data may be migrated to the storage level 3.
  • the first weight is determined according to the write amplification factor corresponding to the RAID level of the storage level of the storage data, and the read amplification factor corresponding to the RAID level of the storage level is determined.
  • the second weight is determined, and the target result is calculated according to the first weight, the write access heat, the second weight, and the read access heat, the first weight is the weight of the write access heat, and the second weight is the weight of the read access heat, therefore, compared
  • the target result can more realistically reflect the access pressure to the storage medium storing the data due to the write operation and the read operation of the data, because the performance of the storage medium in the storage hierarchy is better.
  • the access pressure that the storage tier can withstand is also greater.
  • the data when the target result of the data is greater than the first threshold, the data can be migrated to a storage tier with better performance of the storage medium when the target result of the data is less than the second threshold.
  • the data can be migrated to a lower performance storage tier of the storage medium such that the storage tier is subjected to access pressures appropriate to its capabilities, preventing the first storage from being constrained by excessive access to data in the first storage tier The access speed of the data in the hierarchy.
  • the embodiment of the present invention further provides a data migration device 50 for performing the above method.
  • the device 50 includes:
  • the obtaining unit 501 is configured to acquire the access heat of the target data at the first storage level
  • a determining unit 502 configured to determine a weight according to an amplification factor corresponding to the data protection mechanism of the first storage level, where the amplification factor refers to a storage pair actually generated when the logical address of the target data is accessed once The number of accesses of the storage medium of the target data, the storage medium belonging to the first storage level;
  • a calculating unit 503 configured to calculate a target result according to the access heat and the weight
  • the migration unit 504 is configured to migrate the target data to the second storage level when the target result satisfies a preset condition.
  • the access heat is a write access heat
  • the weight is a first weight of the write access heat determined according to a write amplification factor corresponding to the data protection mechanism
  • the write access heat is the target data.
  • the number of write accesses of the target data at the first storage level in the number of write accesses or the unit time of the first storage level.
  • the access heat includes a write access heat and a read access heat
  • the weight includes a first weight and a root of the write access heat determined according to a write amplification factor corresponding to the data protection mechanism.
  • a second weight of the read access heat determined according to a read amplification factor corresponding to the data protection mechanism
  • the write access heat is the number of write accesses of the target data at the first storage level, and the read access heat is the number of read accesses of the target data at the first storage level; or
  • the write access heat is the number of write accesses of the target data at the first storage level per unit time, and the read access heat is the number of read accesses of the target data at the first storage level per unit time.
  • the performance of the storage medium in the second storage level is better than the performance of the storage medium in the first storage level; or, when the pre- When the condition is less than the second threshold, the performance of the storage medium in the first storage level is better than the performance of the storage medium in the second storage level, and the first threshold is greater than the second threshold.
  • the first weight is the write amplification factor
  • the second weight is the read amplification factor
  • the first weight is a first value
  • the second weight is a second value
  • the ratio of the first value to the second value and the ratio of the write amplification factor to the read amplification factor are the same.
  • the calculating unit 503 is specifically configured to:
  • the access heat is a read access heat
  • the weight is a second weight of the read access heat determined according to a read amplification factor corresponding to the data protection mechanism, and the read access heat is the target data.
  • the data protection mechanism includes a RAID level or an EC.
  • the device provided by the embodiment of the present invention determines the weight according to the amplification factor corresponding to the data protection mechanism of the first storage level of the storage target data, and calculates the target result according to the weight and the access heat of the target data, thereby determining whether to migrate the target data.
  • the target result can more realistically reflect the access pressure on the storage medium storing the target data actually generated by accessing the logical address of the target data, according to the target result and the preset condition of the target data.
  • each storage tier can be subjected to access pressures adapted to its own capabilities, preventing the data in the first storage tier from being limited due to excessive access to data in the first storage tier. Access speed.
  • the various units in the data migration device 50 may be embedded in or independent of the processor of the data migration device 50 in hardware, or may be stored in the memory of the data migration device 50 in software for processing.
  • the device is configured to perform the operations corresponding to the foregoing units, and the processor may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or an embodiment configured to implement the embodiment of the present invention.
  • One or more integrated circuits may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or an embodiment configured to implement the embodiment of the present invention.
  • CPU central processing unit
  • ASIC application specific integrated circuit
  • the embodiment of the present invention further provides a data migration apparatus 60 for performing the above method.
  • the apparatus 60 includes: a memory 601 and a processor 602, wherein the memory 601 is configured to store a set of codes, and the processor 602 performs the following actions according to the set of codes:
  • amplification factor refers to a storage medium that is actually generated when the logical address of the target data is accessed once for storing the target data. Number of accesses, the storage medium belongs to the first storage level;
  • the target data is migrated to a second storage level.
  • the access heat is a write access heat
  • the weight is a first weight of the write access heat determined according to a write amplification factor corresponding to the data protection mechanism
  • the write access heat is the target data.
  • the number of write accesses of the target data at the first storage level in the number of write accesses or the unit time of the first storage level.
  • the access heat includes a write access heat and a read access heat
  • the weight includes a first weight of the write access heat determined according to a write amplification factor corresponding to the data protection mechanism, and according to the data protection mechanism. a second weight of the read access heat determined by the corresponding read amplification factor;
  • the write access heat is the number of write accesses of the target data at the first storage level, and the read access heat is the number of read accesses of the target data at the first storage level; or
  • the write access heat is the number of write accesses of the target data at the first storage level per unit time, and the read access heat is the number of read accesses of the target data at the first storage level per unit time.
  • the performance of the storage medium in the second storage level is better than the performance of the storage medium in the first storage level; or, when the pre- When the condition is less than the second threshold, the performance of the storage medium in the first storage level is better than the performance of the storage medium in the second storage level, and the first threshold is greater than the second threshold.
  • the first weight is the write amplification factor
  • the second weight is the read amplification factor
  • the first weight is a first value
  • the second weight is a second value
  • the ratio of the first value to the second value and the ratio of the write amplification factor to the read amplification factor are the same.
  • the processor 602 is specifically configured to:
  • the access heat is a read access heat
  • the weight is a second weight of the read access heat determined according to a read amplification factor corresponding to the data protection mechanism, and the read access heat is the target data.
  • the data protection mechanism includes a RAID level or an EC.
  • the device provided by the embodiment of the present invention determines the weight according to the amplification factor corresponding to the data protection mechanism of the first storage level of the storage target data, and calculates the target result according to the weight and the access heat of the target data, thereby determining whether to migrate the target data.
  • the target result can more realistically reflect the access pressure on the storage medium storing the target data actually generated by accessing the logical address of the target data, according to the target result and the preset condition of the target data.
  • each storage tier can be subjected to access pressures adapted to its own capabilities, preventing the restriction in the first storage tier due to excessive access to data in the first storage tier.
  • the access speed of the data is migrated to the second storage tier.
  • the disclosed apparatus and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the modules is only a logical function division.
  • there may be another division manner for example, multiple modules or components may be combined or Can be integrated into another system, or some features can be ignored or not executed.
  • the modules described as separate components may or may not be physically separated.
  • the components displayed as modules may or may not be physical modules, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional module in each embodiment of the present invention may be integrated into one processing module, or two or more modules may be integrated into one module.
  • the above integrated modules can be implemented in the form of hardware or in the form of hardware plus software function modules.
  • the above-described integrated modules implemented in the form of software function modules can be stored in a computer readable storage medium.
  • the software functional modules described above are stored in a storage medium and include instructions for causing a computer device (which may be a personal computer, server, or network device, etc.) to perform some of the steps of the methods described in various embodiments of the present invention.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like, and the program code can be stored. Medium.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Techniques For Improving Reliability Of Storages (AREA)

Abstract

一种数据迁移的方法及装置，涉及计算机技术领域，用于提高存储层级中的数据的存取速度。该方法包括：获取目标数据在第一存储层级的访问热度（301）；根据所述第一存储层级的数据保护机制对应的放大系数确定权重（302），所述放大系数是指对所述目标数据的逻辑地址进行一次访问时所实际产生的对存储所述目标数据的存储介质的访问次数，所述存储介质属于所述第一存储层级；根据所述访问热度和所述权重计算目标结果（303）；当所述目标结果满足预设条件时，迁移所述目标数据至第二存储层级（304）。该方法用于对属于不同存储层级中的数据进行迁移。

Description

一种数据迁移的方法及装置 技术领域
本发明涉及计算机技术领域，尤其涉及一种数据迁移的方法及装置。
背景技术
在分级存储***中包括多个存储层级，不同存储层级中的存储介质的性能不同，级别越高的存储层级中的存储介质的性能越高，一个存储层级中可以包括一个或多个存储介质。为了提高用户体验，将越热的数据(访问热度越高的数据)存储在级别越高的存储层级中，并且，当一个数据由冷(热)数据变为热(冷)数据后，该数据还会在存储层级之间进行迁移。
以一个存储在某一存储层级中的数据由冷数据变为热数据为例，分级存储***中的集中控制器迁移数据的方法包括：获取该数据在该存储层级的读访问热度和写访问热度，将读访问热度与写访问热度之和与特定阈值进行比较，当读访问热度与写访问热度之和大于该特定阈值时(此时，说明该数据为热数据)，将该数据迁移至级别更高的存储层级中。
需要说明的是，某些应用场景下，存储层级中的数据通过采用独立冗余磁盘阵列(Redundant Arrays of Independent Disks，简称RAID)技术进行保护，因此，每个存储层级都有一个RAID级别，每个RAID级别对应一个写放大系数，一个存储层级的RAID级别对应的写放大系数是指对存储在该存储层级中的数据的逻辑地址进行一次写访问时所实际产生的对存储该数据的存储介质的访问次数，该存储介质属于该存储层级。例如，当对一个RAID级别为RAID5的存储层级内存储的数据进行写操作时，需要对该数据的逻辑地址进行写访问，对一个数据的逻辑地址的每一次写访问将产生两个实际的对存储该数据的存储介质的读操作和两个实际的对该存储介质的写操作，具体为从该存储介质中读旧的数据和数据校验信息，向该存储介质中写新的数据和数据校验信息。根据存储在一个存储层级中的数据的写访问热度和读访问热度迁移数据，并不能真实的反映由于对该数据进行写操作所实际产生的对存储该数据的存储介 质的访问压力。
发明内容
本发明的实施例提供一种数据迁移的方法及装置，用于提高存储层级中的数据的存取速度。
为达到上述目的，本发明的实施例采用如下技术方案：
第一方面，提供一种数据迁移的方法，包括：
获取目标数据在第一存储层级的访问热度；
根据第一存储层级的数据保护机制对应的放大系数确定权重，放大系数是指对目标数据的逻辑地址进行一次访问时所实际产生的对存储目标数据的存储介质的访问次数，存储介质属于第一存储层级；
根据访问热度和权重计算目标结果；
当目标结果满足预设条件时，迁移目标数据至第二存储层级。
结合第一方面，在第一种可能的实现方式中，访问热度为写访问热度，权重为根据数据保护机制对应的写放大系数确定的写访问热度的第一权重，写访问热度为目标数据在第一存储层级的写访问次数或者单位时间内目标数据在第一存储层级的写访问次数，写放大系数是指对目标数据的逻辑地址进行一次写访问时所实际产生的对存储目标数据的存储介质的访问次数。
结合第一方面，在第二种可能的实现方式中，访问热度包括写访问热度和读访问热度，权重包括根据数据保护机制对应的写放大系数确定的写访问热度的第一权重和根据数据保护机制对应的读放大系数确定的读访问热度的第二权重；
其中，写访问热度为目标数据在第一存储层级的写访问次数，读访问热度为目标数据在第一存储层级的读访问次数；或者，写访问热度为单位时间内目标数据在第一存储层级的写访问次数，读访问热度为单位时间内目标数据在第一存储层级的读访问次数；写放大系数是指对目标数据的逻辑地址进行一次写 访问时所实际产生的对存储目标数据的存储介质的访问次数，读放大系数是指对目标数据的逻辑地址进行一次读访问时所实际产生的对存储目标数据的存储介质的访问次数。
结合第一方面，第一方面的第一种可能的实现方式或第二种可能的实现方式，在第三种可能的实现方式中，当预设条件为大于第一阈值时，第二存储层级中的存储介质的性能优于第一存储层级中的存储介质的性能；或者，当预设条件为小于第二阈值时，第一存储层级中的存储介质的性能优于第二存储层级中的存储介质的性能，第一阈值大于第二阈值。
结合第一方面的第二种可能的实现方式，在第四种可能的实现方式中，第一权重为写放大系数，第二权重为读放大系数；或者，第一权重为第一数值，第二权重为第二数值，第一数值与第二数值的比值和写放大系数与读放大系数的比值相同。
结合第一方面，第一方面的第一种可能的实现方式至第四种可能的实现方式任一种，在第五种可能的实现方式中，数据保护机制包括独立冗余磁盘阵列RAID级别或纠删码EC。
第二方面，提供一种数据迁移装置，包括：
获取单元，用于获取目标数据在第一存储层级的访问热度；
确定单元，用于根据第一存储层级的数据保护机制对应的放大系数确定权重，放大系数是指对目标数据的逻辑地址进行一次访问时所实际产生的对存储目标数据的存储介质的访问次数，存储介质属于第一存储层级；
计算单元，用于根据访问热度和权重计算目标结果；
迁移单元，用于当目标结果满足预设条件时，迁移目标数据至第二存储层级。
结合第二方面，在第一种可能的实现方式中，访问热度为写访问热度，权重为根据数据保护机制对应的写放大系数确定的写访问热度的第一权重，写访问热度为目标数据在第一存储层级的写访问次数或者单位时间内目标数据在第一存储层级的写访问次数，写放大系数是指对目标数据的逻辑地址进行一次 写访问时所实际产生的对存储目标数据的存储介质的访问次数。
结合第二方面，在第二种可能的实现方式中，访问热度包括写访问热度和读访问热度，权重包括根据数据保护机制对应的写放大系数确定的写访问热度的第一权重和根据数据保护机制对应的读放大系数确定的读访问热度的第二权重；
其中，写访问热度为目标数据在第一存储层级的写访问次数，读访问热度为目标数据在第一存储层级的读访问次数；或者，写访问热度为单位时间内目标数据在第一存储层级的写访问次数，读访问热度为单位时间内目标数据在第一存储层级的读访问次数；写放大系数是指对目标数据的逻辑地址进行一次写访问时所实际产生的对存储目标数据的存储介质的访问次数，读放大系数是指对目标数据的逻辑地址进行一次读访问时所实际产生的对存储目标数据的存储介质的访问次数。
结合第二方面，第二方面的第一种可能的实现方式或第二种可能的实现方式，在第三种可能的实现方式中，当预设条件为大于第一阈值时，第二存储层级中的存储介质的性能优于第一存储层级中的存储介质的性能；或者，当预设条件为小于第二阈值时，第一存储层级中的存储介质的性能优于第二存储层级中的存储介质的性能，第一阈值大于第二阈值。
结合第二方面的第二种可能的实现方式，在第四种可能的实现方式中，第一权重为写放大系数，第二权重为读放大系数；或者，第一权重为第一数值，第二权重为第二数值，第一数值与第二数值的比值和写放大系数与读放大系数的比值相同。
结合第二方面，第二方面的第一种可能的实现方式至第四种可能的实现方式任一种，在第五种可能的实现方式中，数据保护机制包括独立冗余磁盘阵列RAID级别或纠删码EC。
第三方面，提供一种数据迁移装置，包括：存储器和处理器，存储器用于存储一组代码，处理器根据该组代码执行以下动作：
获取目标数据在第一存储层级的访问热度；
根据第一存储层级的数据保护机制对应的放大系数确定权重，放大系数是指对目标数据的逻辑地址进行一次访问时所实际产生的对存储目标数据的存储介质的访问次数，存储介质属于第一存储层级；
根据访问热度和权重计算目标结果；
当目标结果满足预设条件时，迁移目标数据至第二存储层级。
结合第三方面，在第一种可能的实现方式中，访问热度为写访问热度，权重为根据数据保护机制对应的写放大系数确定的写访问热度的第一权重，写访问热度为目标数据在第一存储层级的写访问次数或者单位时间内目标数据在第一存储层级的写访问次数，写放大系数是指对目标数据的逻辑地址进行一次写访问时所实际产生的对存储目标数据的存储介质的访问次数。
结合第三方面，在第二种可能的实现方式中，访问热度包括写访问热度和读访问热度，权重包括根据数据保护机制对应的写放大系数确定的写访问热度的第一权重和根据数据保护机制对应的读放大系数确定的读访问热度的第二权重；
其中，写访问热度为目标数据在第一存储层级的写访问次数，读访问热度为目标数据在第一存储层级的读访问次数；或者，写访问热度为单位时间内目标数据在第一存储层级的写访问次数，读访问热度为单位时间内目标数据在第一存储层级的读访问次数；写放大系数是指对目标数据的逻辑地址进行一次写访问时所实际产生的对存储目标数据的存储介质的访问次数，读放大系数是指对目标数据的逻辑地址进行一次读访问时所实际产生的对存储目标数据的存储介质的访问次数。
结合第三方面，第三方面的第一种可能的实现方式或第二种可能的实现方式，在第三种可能的实现方式中，当预设条件为大于第一阈值时，第二存储层级中的存储介质的性能优于第一存储层级中的存储介质的性能；或者，当预设条件为小于第二阈值时，第一存储层级中的存储介质的性能优于第二存储层级中的存储介质的性能，第一阈值大于第二阈值。
结合第三方面的第二种可能的实现方式，在第四种可能的实现方式中，第 一权重为写放大系数，第二权重为读放大系数；或者，第一权重为第一数值，第二权重为第二数值，第一数值与第二数值的比值和写放大系数与读放大系数的比值相同。
结合第三方面，第三方面的第一种可能的实现方式至第四种可能的实现方式任一种，在第五种可能的实现方式中，数据保护机制包括独立冗余磁盘阵列RAID级别或纠删码EC。
本发明实施例提供的方法及装置，根据存储目标数据的第一存储层级的数据保护机制对应的放大系数确定权重，并根据权重和目标数据的访问热度计算目标结果，进而确定是否迁移目标数据，因此，相比现有技术来说，目标结果可以更加真实的反应由于对目标数据的逻辑地址进行访问所实际产生的对存储目标数据的存储介质的访问压力，根据目标数据的目标结果和预设条件在适当的时候将目标数据迁移至第二存储层级，可以使得每个存储层级承受与自身能力相适应的访问压力，防止由于对第一存储层级中的数据访问过多而限制第一存储层级中的数据的存取速度。
附图说明
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍。
图1为本发明实施例提供的一种分级存储***与外部设备连接示意图；
图2为本发明实施例提供的一种存储模块中包括的存储层级的示意图；
图3为本发明实施例提供的一种数据迁移的方法的流程图；
图4为本发明实施例提供的又一种数据迁移的方法的流程图；
图5为本发明实施例提供的一种数据迁移装置的结构示意图；
图6为本发明实施例提供的又一种数据迁移装置的结构示意图。
具体实施方式
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。
本发明实施例中提供的方法至少可以应用在分级存储***中，如图1所示，分级存储***中包括一个或多个网络节点，一个网络节点可以由一个或多个服务器组成，各个网络节点通过低延迟、高吞吐量的网络相连，该网络具体可以为光纤通道(Fibre Channel，简称FC)或10G以太网(10Gigabit Ethernet)等，每个网络节点与存储模块连接。外部设备可以通过与分级存储***之间的接口读写分级存储***中存储的数据。其中，如图1所示，存储模块内包括多个存储介质，本发明中的存储介质是指存储数据的载体，比如软盘、光盘或硬盘等。如图2所示，存储介质被划分为不同的存储层级，存储模块包括多个存储层级，分别为存储层级1至存储层级N(N≥1，N为整数)，级别越高的存储层级中的存储介质的性能越高(图2中存储层级1的级别最高)。
本发明实施例提供一种数据迁移的方法，如图3所示，包括：
301、获取目标数据在第一存储层级的访问热度。
本发明实施例中的执行主体可以为分级存储***中的集中控制器，集中控制器可以为分级存储***中的一个具备集中控制功能的网络节点。需要说明的是，图1中所示的存储模块和网络节点也可以置于同一设备中。
具体的，目标数据可以为第一存储层级中存储的任意一个数据，获取目标数据的访问热度的方法可以参见现有技术。
302、根据所述第一存储层级的数据保护机制对应的放大系数确定权重。
其中，所述放大系数是指对所述目标数据的逻辑地址进行一次访问时所实际产生的对存储所述目标数据的存储介质的访问次数，所述存储介质属于所述第一存储层级。
具体的，上述数据保护机制对应的放大系数包括写放大系数和读放大系数，写放大系数是指对目标数据的逻辑地址进行一次写访问时所实际产生的对存储目标数据的存储介质的访问次数，读放大系数是指对目标数据的逻辑地址进行一次读访问时所实际产生的对存储目标数据的存储介质的访问次数，其中 所述的对存储目标数据的存储介质的访问次数是指对存储目标数据的存储介质的读访问次数和写访问次数之和。
其中，上述访问热度可以仅包含读访问热度或写访问热度，也可以包含读访问热度和写访问热度，不同情况下确定的权重如下：
情况一：访问热度为写访问热度，权重为根据数据保护机制对应的写放大系数确定的写访问热度的第一权重，写访问热度为目标数据在第一存储层级的写访问次数或者单位时间内目标数据在第一存储层级的写访问次数。
情况二：访问热度包括写访问热度和读访问热度，权重包括根据数据保护机制对应的写放大系数确定的写访问热度的第一权重和根据数据保护机制对应的读放大系数确定的读访问热度的第二权重；
其中，写访问热度为目标数据在第一存储层级的写访问次数，读访问热度为目标数据在第一存储层级的读访问次数；或者，写访问热度为单位时间内目标数据在第一存储层级的写访问次数，读访问热度为单位时间内目标数据在第一存储层级的读访问次数。
情况三：访问热度为读访问热度，权重为根据数据保护机制对应的读放大系数确定的读访问热度的第二权重，读访问热度为目标数据在第一存储层级的读访问次数或者单位时间内目标数据在第一存储层级的读访问次数。
其中，单位时间可以为1分钟或1小时等，也可以为其他的预设时间段。
需要说明的是，当写放大系数越大时，第一权重越大，当读放大系数越大时，第二权重越大。
可选的，所述数据保护机制包括RAID级别或纠删码(erasure coding，简称EC)。
其中，以数据保护机制为RAID级别为例，写放大是由于RAID写惩罚造成的，示例性的，当对一个RAID级别为RAID5的存储层级中的数据进行一次写操作时，需要对该数据的逻辑地址进行一次写访问，而该次写访问将实际产生两个对存储该数据的存储介质的读操作和两个对该存储介质的写操作，具体为从该存储介质中读旧的数据和数据校验信息，向该存储介质中写新的数据 和数据校验信息，由此可知，RAID5对应的写放大系数为4，当对该数据进行一次读操作时，需要对该数据的逻辑地址进行一次读访问，该次读访问将实际产生一个对存储该数据的存储介质的读操作，由此可知，RAID5对应的读放大系数为1。
具体的，本发明实施例中通过表1示出了部分RAID级别对应的写放大系数和读放大系数。
表1
RAID级别 写放大系数 读放大系数
RAID10 2 1
RAID5 4 1
RAID6 6 1
303、根据所述访问热度和所述权重计算目标结果。
针对上述情况一，目标结果＝第一权重×写访问热度。该情况下，第一权重可以为RAID级别对应的写放大系数，也可以为小于该写放大系数、且大于1的其他数值。
针对上述情况二，目标结果＝第一权重×写访问热度+第二权重×读访问热度。该情况下，第一权重为写放大系数，第二权重为读放大系数；或者，第一权重为第一数值，第二权重为第二数值，第一数值与第二数值的比值和写放大系数与读放大系数的比值相同；或者，第一权重为小于或等于写放大系数、且大于1的其他数值，第二权重为1。
示例性的，在确定第一权重及第二权重时，以RAID级别为RAID5为例，第一权重可以为4，第二权重为1，或者，第一权重可以为0.8，第二权重为0.2。
针对上述情况三，目标结果＝第二权重×读访问热度。该情况下，第二权重可以为读放大系数。
304、当所述目标结果满足预设条件时，迁移所述目标数据至第二存储层级。
需要说明的是，第一存储层级与第二存储层级可以为连续的存储层级，也可以为不连续的存储层级。
可选的，当所述预设条件为大于第一阈值时，所述第二存储层级中的存储介质的性能优于所述第一存储层级中的存储介质的性能；或者，当所述预设条件为小于第二阈值时，所述第一存储层级中的存储介质的性能优于所述第二存储层级中的存储介质的性能，所述第一阈值大于所述第二阈值。
需要说明的是，存储层级中的存储介质的性能更好的存储层级能够承受的访问压力也越大，因此，当目标结果大于第一阈值时，可以将目标数据迁移至存储介质的性能更好的存储层级中。当目标结果小于第二阈值时，说明目标数据的访问热度也不高，因此，可以将目标数据迁移至存储介质的性能较低的存储层级中。
具体的，在上述方法中，第一存储层级可以为全部存储层级中的任意一个存储层级。
以图2为例，第一存储层级可以为存储层级2。该情况下，第一阈值可以为存储层级1与存储层级2之间迁移数据时的阈值，第二阈值可以为存储层级2与存储层级3之间迁移数据时的阈值。具体的，本发明实施例中提供的一种确定第一阈值和第二阈值的方法如下：
每隔预设时间段，计算所有存储层级中的所有数据的目标结果，并按由大至小的顺序对所有的目标结果进行排序，根据存储层级1的容量，从排序结果中选出前X(X≥1，X为整数)个数据所组成的一个或多个数据块，并将该一个或多个数据块存储在存储层级1中，该前X个数据占用的存储空间与存储层级1的容量相同或相近；根据存储层级2的容量，从排序结果中选出第X+1至第Y(Y≥X+1，Y为整数)个数据所组成的一个或多个数据块，并将该一个或多个数据块存储在存储层级2中，该第X+1至第Y个数据占用的存储空间与存储层级2的容量相同或相近；将排序结果中的第Y个数据之后的数据存储在存储层级3中(本实施例中假设所有的数据占用的空间小于存储层级1、存储层级2和存储层级3的容量之和)。具体的，将排序结果中的第X个数据的目标结果确定为第一阈值，将排序结果中的第Y个数据的目标结果 确定为第二阈值。当然，还可以通过其他的方法确定第一阈值和第二阈值，本发明实施例只是示例性的提供了一种方法。
示例性的，在一种应用场景下，若第一阈值为400，第二阈值为100，该情况下，当目标结果大于400时，将目标数据迁移至存储层级1，当目标数据小于100时，将目标数据迁移至存储层级3。需要说明的是，当目标结果等于400时，可以将目标数据迁移至存储层级1，也可以不迁移；当目标结果等于100时，可以将目标数据迁移至存储层级3，也可以不迁移。
以图2为例，需要说明的是，若存储模块中包括5个存储层级时，第一存储层级可以为存储层级3，该情况下，第一阈值可以为存储层级1与存储层级2之间迁移数据时的阈值，第二阈值可以为存储层级4与存储层级5之间迁移数据时的阈值。具体的，确定存储层级之间的迁移数据时的阈值的方法可以参见上述实施例。
具体的，集中控制器可以周期性的执行上述方法，也可以在满足特定条件的情况下执行上述方法，特定条件可以根据实际应用场景确定，本发明实施例对此不做具体限定。
本发明实施例提供的方法，根据存储目标数据的第一存储层级的数据保护机制对应的放大系数确定权重，并根据权重和目标数据的访问热度计算目标结果，进而确定是否迁移目标数据，因此，相比现有技术来说，目标结果可以更加真实的反应由于对目标数据的逻辑地址进行访问所实际产生的对存储目标数据的存储介质的访问压力，根据目标数据的目标结果和预设条件在适当的时候将目标数据迁移至第二存储层级，可以使得每个存储层级承受与自身能力相适应的访问压力，防止由于对第一存储层级中的数据访问过多而限制第一存储层级中的数据的存取速度。
本发明实施例还提供一种数据迁移的方法，用于对上述实施例提供的数据迁移方法作示例性说明，该实施例中以第一存储层级为上述存储层级2、第一阈值为上述存储层级1与上述存储层级2之间迁移数据时的阈值，第二阈值为上述存储层级2与上述存储层级3之间迁移数据时的阈值为例，如图4所示，该方法包括：
401、获取目标数据在存储层级2的写访问热度和读访问热度。
其中，目标数据存储在存储层级2中的存储介质中。
其中，写访问热度为目标数据在存储层级2的写访问次数，读访问热度为目标数据在存储层级2的读访问次数；或者，写访问热度为单位时间内目标数据在存储层级2的写访问次数，读访问热度为单位时间内目标数据在存储层级2的读访问次数。
本发明实施例中的相关解释可以参见上述实施例。
402、根据存储层级2的RAID级别对应的写放大系数确定第一权重，根据该RAID级别对应的读放大系数确定第二权重。
具体的，第一权重为存储层级2的RAID级别对应的写放大系数，第二权重为该RAID级别对应的读放大系数；或者，第一权重为第一数值，第二权重为第二数值，第一数值与第二数值的比值和存储层级2的RAID级别对应的写放大系数与该RAID级别对应的读放大系数的比值相同。
403、根据“目标结果＝第一权重×写访问热度+第二权重×读访问热度”计算目标结果。
404、将目标结果与第一阈值和第二阈值进行比较，当目标结果大于第一阈值时，将目标数据迁移至存储层级1，或者，当目标结果小于第二阈值时，将目标数据迁移至存储层级3。
需要说明的是，当目标结果小于第一阈值并且大于第二阈值时，不迁移目标数据。
示例性的，以图2为例，存储层级1的级别高于存储层级2的级别，存储层级2的级别高于存储层级3的级别，当目标数据原本存储在存储层级2中的存储介质中时，根据上述方法计算得到的目标结果大于第一阈值时，可以将该目标数据迁移至存储层级1，当该目标结果小于第二阈值时，可以将该目标数据迁移至存储层级3。
本发明实施例提供的方法，根据存储数据的存储层级的RAID级别对应的写放大系数确定第一权重，根据该存储层级的RAID级别对应的读放大系数确 定第二权重，并根据第一权重、写访问热度、第二权重和读访问热度计算目标结果，第一权重为写访问热度的权重，第二权重为读访问热度的权重，因此，相比现有技术来说，目标结果可以更加真实的反应由于对该数据进行写操作和读操作所实际产生的对存储该数据的存储介质的访问压力，由于存储层级中的存储介质的性能更好的存储层级能够承受的访问压力也越大，因此，当数据的目标结果大于第一阈值时，可以将该数据迁移至存储介质的性能更好的存储层级中，当数据的目标结果小于第二阈值时，可以将该数据迁移至存储介质的性能较低的存储层级中，使得存储层级承受与自身能力相适应的访问压力，防止由于对第一存储层级中的数据访问过多而限制第一存储层级中的数据的存取速度。
本发明实施例还提供一种数据迁移装置50，用于执行上述方法，如图5所示，该装置50包括：
获取单元501，用于获取目标数据在第一存储层级的访问热度；
确定单元502，用于根据所述第一存储层级的数据保护机制对应的放大系数确定权重，所述放大系数是指对所述目标数据的逻辑地址进行一次访问时所实际产生的对存储所述目标数据的存储介质的访问次数，所述存储介质属于所述第一存储层级；
计算单元503，用于根据所述访问热度和所述权重计算目标结果；
迁移单元504，用于当所述目标结果满足预设条件时，迁移所述目标数据至第二存储层级。
可选的，所述访问热度为写访问热度，所述权重为根据所述数据保护机制对应的写放大系数确定的所述写访问热度的第一权重，所述写访问热度为所述目标数据在所述第一存储层级的写访问次数或者单位时间内所述目标数据在所述第一存储层级的写访问次数。
可选的，所述访问热度包括写访问热度和读访问热度，所述权重包括根据所述数据保护机制对应的写放大系数确定的所述写访问热度的第一权重和根 据所述数据保护机制对应的读放大系数确定的所述读访问热度的第二权重；
其中，所述写访问热度为所述目标数据在所述第一存储层级的写访问次数，所述读访问热度为所述目标数据在所述第一存储层级的读访问次数；或者，所述写访问热度为单位时间内所述目标数据在所述第一存储层级的写访问次数，所述读访问热度为单位时间内所述目标数据在所述第一存储层级的读访问次数。
可选的，当所述预设条件为大于第一阈值时，所述第二存储层级中的存储介质的性能优于所述第一存储层级中的存储介质的性能；或者，当所述预设条件为小于第二阈值时，所述第一存储层级中的存储介质的性能优于所述第二存储层级中的存储介质的性能，所述第一阈值大于所述第二阈值。
可选的，所述第一权重为所述写放大系数，所述第二权重为所述读放大系数；或者，所述第一权重为第一数值，所述第二权重为第二数值，所述第一数值与所述第二数值的比值和所述写放大系数与所述读放大系数的比值相同。
可选的，所述计算单元503，具体用于：
将所述第一权重与所述写访问热度相乘得到第一结果；
将所述第二权重与所述读访问热度相乘得到第二结果；
将所述第一结果与所述第二结果相加得到目标结果。
可选的，所述访问热度为读访问热度，所述权重为根据所述数据保护机制对应的读放大系数确定的所述读访问热度的第二权重，所述读访问热度为所述目标数据在所述第一存储层级的读访问次数或者单位时间内所述目标数据在所述第一存储层级的读访问次数。
可选的，所述数据保护机制包括RAID级别或EC。
本发明实施例提供的装置，根据存储目标数据的第一存储层级的数据保护机制对应的放大系数确定权重，并根据权重和目标数据的访问热度计算目标结果，进而确定是否迁移目标数据，因此，相比现有技术来说，目标结果可以更加真实的反应由于对目标数据的逻辑地址进行访问所实际产生的对存储目标数据的存储介质的访问压力，根据目标数据的目标结果和预设条件在适当的时 候将目标数据迁移至第二存储层级，可以使得每个存储层级承受与自身能力相适应的访问压力，防止由于对第一存储层级中的数据访问过多而限制第一存储层级中的数据的存取速度。
在硬件实现上，数据迁移装置50中的各个单元可以以硬件形式内嵌于或独立于数据迁移装置50的处理器中，也可以以软件形式存储于数据迁移装置50的存储器中，以便于处理器调用执行以上各个单元对应的操作，该处理器可以为中央处理器(Central Processing Unit，简称CPU)、特定集成电路(Application Specific Integrated Circuit，简称ASIC)或者是被配置成实施本发明实施例的一个或多个集成电路。
本发明实施例还提供一种数据迁移装置60，用于执行上述方法，如图6所示，该装置60包括：存储器601和处理器602，其中，存储器601用于存储一组代码，处理器602根据该组代码执行以下动作：
获取目标数据在第一存储层级的访问热度；
根据所述第一存储层级的数据保护机制对应的放大系数确定权重，所述放大系数是指对所述目标数据的逻辑地址进行一次访问时所实际产生的对存储所述目标数据的存储介质的访问次数，所述存储介质属于所述第一存储层级；
根据所述访问热度和所述权重计算目标结果；
当所述目标结果满足预设条件时，迁移所述目标数据至第二存储层级。
可选的，所述访问热度为写访问热度，所述权重为根据所述数据保护机制对应的写放大系数确定的所述写访问热度的第一权重，所述写访问热度为所述目标数据在所述第一存储层级的写访问次数或者单位时间内所述目标数据在所述第一存储层级的写访问次数。
可选的，所述访问热度包括写访问热度和读访问热度，所述权重包括根据所述数据保护机制对应的写放大系数确定的所述写访问热度的第一权重和根据所述数据保护机制对应的读放大系数确定的所述读访问热度的第二权重；
其中，所述写访问热度为所述目标数据在所述第一存储层级的写访问次数，所述读访问热度为所述目标数据在所述第一存储层级的读访问次数；或者， 所述写访问热度为单位时间内所述目标数据在所述第一存储层级的写访问次数，所述读访问热度为单位时间内所述目标数据在所述第一存储层级的读访问次数。
可选的，当所述预设条件为大于第一阈值时，所述第二存储层级中的存储介质的性能优于所述第一存储层级中的存储介质的性能；或者，当所述预设条件为小于第二阈值时，所述第一存储层级中的存储介质的性能优于所述第二存储层级中的存储介质的性能，所述第一阈值大于所述第二阈值。
可选的，所述第一权重为所述写放大系数，所述第二权重为所述读放大系数；或者，所述第一权重为第一数值，所述第二权重为第二数值，所述第一数值与所述第二数值的比值和所述写放大系数与所述读放大系数的比值相同。
可选的，处理器602具体用于：
将所述第一权重与所述写访问热度相乘得到第一结果；
将所述第二权重与所述读访问热度相乘得到第二结果；
将所述第一结果与所述第二结果相加得到目标结果。
可选的，所述访问热度为读访问热度，所述权重为根据所述数据保护机制对应的读放大系数确定的所述读访问热度的第二权重，所述读访问热度为所述目标数据在所述第一存储层级的读访问次数或者单位时间内所述目标数据在所述第一存储层级的读访问次数。
可选的，所述数据保护机制包括RAID级别或EC。
本发明实施例提供的装置，根据存储目标数据的第一存储层级的数据保护机制对应的放大系数确定权重，并根据权重和目标数据的访问热度计算目标结果，进而确定是否迁移目标数据，因此，相比现有技术来说，目标结果可以更加真实的反应由于对目标数据的逻辑地址进行访问所实际产生的对存储目标数据的存储介质的访问压力，根据目标数据的目标结果和预设条件在适当的时候将目标数据迁移至第二存储层级，可以使得每个存储层级承受与自身能力相适应的访问压力，防止由于对第一存储层级中的数据访问过多而限制第一存储层级中的数据的存取速度。
在本申请所提供的几个实施例中，应该理解到，所揭露的装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述模块的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个模块或组件可以结合或者可以集成到另一个***，或一些特征可以忽略，或不执行。
所述作为分离部件说明的模块可以是或者也可以不是物理上分开的，作为模块显示的部件可以是或者也可以不是物理模块，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能模块可以集成在一个处理模块中，也可以两个或两个以上模块集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用硬件加软件功能模块的形式实现。
上述以软件功能模块的形式实现的集成的模块，可以存储在一个计算机可读取存储介质中。上述软件功能模块存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本发明各个实施例所述方法的部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，简称ROM)、随机存取存储器(Random Access Memory，简称RAM)、磁碟或者光盘等各种可以存储程序代码的介质。

Claims (24)

  1. 一种数据迁移的方法，其特征在于，包括：
    获取目标数据在第一存储层级的访问热度；
    根据所述第一存储层级的数据保护机制对应的放大系数确定权重，所述放大系数是指对所述目标数据的逻辑地址进行一次访问时所实际产生的对存储所述目标数据的存储介质的访问次数，所述存储介质属于所述第一存储层级；
    根据所述访问热度和所述权重计算目标结果；
    当所述目标结果满足预设条件时，迁移所述目标数据至第二存储层级。
  2. 根据权利要求1所述的方法，其特征在于，所述访问热度为写访问热度，所述权重为根据所述数据保护机制对应的写放大系数确定的所述写访问热度的第一权重，所述写访问热度为所述目标数据在所述第一存储层级的写访问次数或者单位时间内所述目标数据在所述第一存储层级的写访问次数。
  3. 根据权利要求1所述的方法，其特征在于，所述访问热度包括写访问热度和读访问热度，所述权重包括根据所述数据保护机制对应的写放大系数确定的所述写访问热度的第一权重和根据所述数据保护机制对应的读放大系数确定的所述读访问热度的第二权重；
    其中，所述写访问热度为所述目标数据在所述第一存储层级的写访问次数，所述读访问热度为所述目标数据在所述第一存储层级的读访问次数；或者，所述写访问热度为单位时间内所述目标数据在所述第一存储层级的写访问次数，所述读访问热度为单位时间内所述目标数据在所述第一存储层级的读访问次数。
  4. 根据权利要求1-3任一项所述的方法，其特征在于，当所述预设条件为大于第一阈值时，所述第二存储层级中的存储介质的性能优于所述第一存储层级中的存储介质的性能；或者，当所述预设条件为小于第二阈值时，所述第一存储层级中的存储介质的性能优于所述第二存储层级中的存储介质的性能，所述第一阈值大于所述第二阈值。
  5. 根据权利要求3所述的方法，其特征在于，所述第一权重为所述写放大系数，所述第二权重为所述读放大系数；或者，所述第一权重为第一数值，所述第二权重为第二数值，所述第一数值与所述第二数值的比值和所述写放大系数与所述读放大系数的比值相同。
  6. 根据权利要求5所述的方法，其特征在于，所述根据所述访问热度和所述权重计算目标结果，包括：
    将所述第一权重与所述写访问热度相乘得到第一结果；
    将所述第二权重与所述读访问热度相乘得到第二结果；
    将所述第一结果与所述第二结果相加得到目标结果。
  7. 根据权利要求1所述的方法，其特征在于，所述访问热度为读访问热度，所述权重为根据所述数据保护机制对应的读放大系数确定的所述读访问热度的第二权重，所述读访问热度为所述目标数据在所述第一存储层级的读访问次数或者单位时间内所述目标数据在所述第一存储层级的读访问次数。
  8. 根据权利要求1-7任一项所述的方法，其特征在于，所述数据保护机制包括独立冗余磁盘阵列RAID级别或纠删码EC。
  9. 一种数据迁移装置，其特征在于，包括：
    获取单元，用于获取目标数据在第一存储层级的访问热度；
    确定单元，用于根据所述第一存储层级的数据保护机制对应的放大系数确定权重，所述放大系数是指对所述目标数据的逻辑地址进行一次访问时所实际产生的对存储所述目标数据的存储介质的访问次数，所述存储介质属于所述第一存储层级；
    计算单元，用于根据所述访问热度和所述权重计算目标结果；
    迁移单元，用于当所述目标结果满足预设条件时，迁移所述目标数据至第二存储层级。
  10. 根据权利要求9所述的装置，其特征在于，所述访问热度为写访问热度，所述权重为根据所述数据保护机制对应的写放大系数确定的所述写访问热度的第一权重，所述写访问热度为所述目标数据在所述第一存储层级的写访问次数或者单位时间内所述目标数据在所述第一存储层级的写访问次数。
  11. 根据权利要求9所述的装置，其特征在于，所述访问热度包括写访问热度和读访问热度，所述权重包括根据所述数据保护机制对应的写放大系数确定的所述写访问热度的第一权重和根据所述数据保护机制对应的读放大系数确定的所述读访问热度的第二权重；
    其中，所述写访问热度为所述目标数据在所述第一存储层级的写访问次 数，所述读访问热度为所述目标数据在所述第一存储层级的读访问次数；或者，所述写访问热度为单位时间内所述目标数据在所述第一存储层级的写访问次数，所述读访问热度为单位时间内所述目标数据在所述第一存储层级的读访问次数。
  12. 根据权利要求9-11任一项所述的装置，其特征在于，当所述预设条件为大于第一阈值时，所述第二存储层级中的存储介质的性能优于所述第一存储层级中的存储介质的性能；或者，当所述预设条件为小于第二阈值时，所述第一存储层级中的存储介质的性能优于所述第二存储层级中的存储介质的性能，所述第一阈值大于所述第二阈值。
  13. 根据权利要求11所述的装置，其特征在于，所述第一权重为所述写放大系数，所述第二权重为所述读放大系数；或者，所述第一权重为第一数值，所述第二权重为第二数值，所述第一数值与所述第二数值的比值和所述写放大系数与所述读放大系数的比值相同。
  14. 根据权利要求13所述的装置，其特征在于，所述计算单元，具体用于：
    将所述第一权重与所述写访问热度相乘得到第一结果；
    将所述第二权重与所述读访问热度相乘得到第二结果；
    将所述第一结果与所述第二结果相加得到目标结果。
  15. 根据权利要求9所述的装置，其特征在于，所述访问热度为读访问热度，所述权重为根据所述数据保护机制对应的读放大系数确定的所述读访问热度的第二权重，所述读访问热度为所述目标数据在所述第一存储层级的读访问次数或者单位时间内所述目标数据在所述第一存储层级的读访问次数。
  16. 根据权利要求9-15任一项所述的装置，其特征在于，所述数据保护机制包括独立冗余磁盘阵列RAID级别或纠删码EC。
  17. 一种数据迁移装置，其特征在于，包括：存储器和处理器，所述存储器用于存储一组代码，所述处理器根据该组代码执行以下动作：
    获取目标数据在第一存储层级的访问热度；
    根据所述第一存储层级的数据保护机制对应的放大系数确定权重，所述放大系数是指对所述目标数据的逻辑地址进行一次访问时所实际产生的对存储 所述目标数据的存储介质的访问次数，所述存储介质属于所述第一存储层级；
    根据所述访问热度和所述权重计算目标结果；
    当所述目标结果满足预设条件时，迁移所述目标数据至第二存储层级。
  18. 根据权利要求17所述的装置，其特征在于，所述访问热度为写访问热度，所述权重为根据所述数据保护机制对应的写放大系数确定的所述写访问热度的第一权重，所述写访问热度为所述目标数据在所述第一存储层级的写访问次数或者单位时间内所述目标数据在所述第一存储层级的写访问次数。
  19. 根据权利要求17所述的装置，其特征在于，所述访问热度包括写访问热度和读访问热度，所述权重包括根据所述数据保护机制对应的写放大系数确定的所述写访问热度的第一权重和根据所述数据保护机制对应的读放大系数确定的所述读访问热度的第二权重；
    其中，所述写访问热度为所述目标数据在所述第一存储层级的写访问次数，所述读访问热度为所述目标数据在所述第一存储层级的读访问次数；或者，所述写访问热度为单位时间内所述目标数据在所述第一存储层级的写访问次数，所述读访问热度为单位时间内所述目标数据在所述第一存储层级的读访问次数。
  20. 根据权利要求17-19任一项所述的装置，其特征在于，当所述预设条件为大于第一阈值时，所述第二存储层级中的存储介质的性能优于所述第一存储层级中的存储介质的性能；或者，当所述预设条件为小于第二阈值时，所述第一存储层级中的存储介质的性能优于所述第二存储层级中的存储介质的性能，所述第一阈值大于所述第二阈值。
  21. 根据权利要求19所述的装置，其特征在于，所述第一权重为所述写放大系数，所述第二权重为所述读放大系数；或者，所述第一权重为第一数值，所述第二权重为第二数值，所述第一数值与所述第二数值的比值和所述写放大系数与所述读放大系数的比值相同。
  22. 根据权利要求21所述的装置，其特征在于，所述处理器具体用于：
    将所述第一权重与所述写访问热度相乘得到第一结果；
    将所述第二权重与所述读访问热度相乘得到第二结果；
    将所述第一结果与所述第二结果相加得到目标结果。
  23. 根据权利要求17所述的装置，其特征在于，所述访问热度为读访问热度，所述权重为根据所述数据保护机制对应的读放大系数确定的所述读访问热度的第二权重，所述读访问热度为所述目标数据在所述第一存储层级的读访问次数或者单位时间内所述目标数据在所述第一存储层级的读访问次数。
  24. 根据权利要求17-23任一项所述的装置，其特征在于，所述数据保护机制包括独立冗余磁盘阵列RAID级别或纠删码EC。
PCT/CN2016/098863 2015-12-04 2016-09-13 一种数据迁移的方法及装置 WO2017092480A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510887513.3A CN105487823B (zh) 2015-12-04 2015-12-04 一种数据迁移的方法及装置
CN201510887513.3 2015-12-04

Publications (1)

Publication Number Publication Date
WO2017092480A1 true WO2017092480A1 (zh) 2017-06-08

Family

ID=55674828

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/098863 WO2017092480A1 (zh) 2015-12-04 2016-09-13 一种数据迁移的方法及装置

Country Status (2)

Country Link
CN (1) CN105487823B (zh)
WO (1) WO2017092480A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110825908A (zh) * 2019-11-04 2020-02-21 安超云软件有限公司 一种对象的迁移方法、装置、电子设备及存储介质
CN116820351A (zh) * 2023-07-21 2023-09-29 北京得瑞领新科技有限公司 冷热数据标定方法、装置、存储介质及电子设备
CN116974468A (zh) * 2023-07-18 2023-10-31 广东华原网络工程有限公司 一种基于大数据的设备数据存储管理方法及***
CN117149098A (zh) * 2023-10-31 2023-12-01 苏州元脑智能科技有限公司 一种条带单元分配方法、装置、计算机设备及存储介质

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105487823B (zh) * 2015-12-04 2018-06-05 华为技术有限公司 一种数据迁移的方法及装置
CN106227466B (zh) * 2016-07-15 2019-03-15 浪潮(北京)电子信息产业有限公司 一种数据段迁移方法及***
CN107256252A (zh) * 2017-06-09 2017-10-17 浪潮软件集团有限公司 一种第三方多维数据迁移方法及装置
CN112328168A (zh) * 2017-06-29 2021-02-05 华为技术有限公司 分片管理方法和分片管理装置
CN107450862A (zh) * 2017-08-18 2017-12-08 郑州云海信息技术有限公司 一种固态硬盘读操作的仲裁方法
CN112825023A (zh) * 2019-11-20 2021-05-21 上海商汤智能科技有限公司 集群资源管理方法、装置、电子设备和存储介质
CN113918378A (zh) * 2020-07-10 2022-01-11 华为技术有限公司 数据存储方法、存储***、存储设备及存储介质
CN114356244B (zh) * 2022-01-12 2023-07-07 平安科技（深圳）有限公司 时序数据的数据存储方法、装置、设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102156738A (zh) * 2011-04-13 2011-08-17 成都市华为赛门铁克科技有限公司 数据块处理方法、数据块存储设备及***
CN102831088A (zh) * 2012-07-27 2012-12-19 国家超级计算深圳中心(深圳云计算中心) 基于混合存储器的数据迁移方法和装置
US20130013729A1 (en) * 2011-07-07 2013-01-10 International Business Machines Corporation Multi-level adaptive caching within asset-based web systems
CN104317731A (zh) * 2014-10-17 2015-01-28 杭州华为数字技术有限公司 一种分层存储管理方法、装置及存储***
CN105487823A (zh) * 2015-12-04 2016-04-13 华为技术有限公司 一种数据迁移的方法及装置

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8291131B2 (en) * 2009-07-06 2012-10-16 Micron Technology, Inc. Data transfer management
GB2493243B (en) * 2011-07-26 2014-04-23 Ibm Method and storage controller for determining an access characteristic of a data entity
CN105009092A (zh) * 2013-04-26 2015-10-28 株式会社日立制作所 存储***
US9348520B2 (en) * 2014-03-24 2016-05-24 Western Digital Technologies, Inc. Lifetime extension of non-volatile semiconductor memory for data storage device

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102156738A (zh) * 2011-04-13 2011-08-17 成都市华为赛门铁克科技有限公司 数据块处理方法、数据块存储设备及***
US20130013729A1 (en) * 2011-07-07 2013-01-10 International Business Machines Corporation Multi-level adaptive caching within asset-based web systems
CN102831088A (zh) * 2012-07-27 2012-12-19 国家超级计算深圳中心(深圳云计算中心) 基于混合存储器的数据迁移方法和装置
CN104317731A (zh) * 2014-10-17 2015-01-28 杭州华为数字技术有限公司 一种分层存储管理方法、装置及存储***
CN105487823A (zh) * 2015-12-04 2016-04-13 华为技术有限公司 一种数据迁移的方法及装置

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110825908A (zh) * 2019-11-04 2020-02-21 安超云软件有限公司 一种对象的迁移方法、装置、电子设备及存储介质
CN110825908B (zh) * 2019-11-04 2023-04-25 安超云软件有限公司 一种对象的迁移方法、装置、电子设备及存储介质
CN116974468A (zh) * 2023-07-18 2023-10-31 广东华原网络工程有限公司 一种基于大数据的设备数据存储管理方法及***
CN116974468B (zh) * 2023-07-18 2024-02-20 广东华原网络工程有限公司 一种基于大数据的设备数据存储管理方法及***
CN116820351A (zh) * 2023-07-21 2023-09-29 北京得瑞领新科技有限公司 冷热数据标定方法、装置、存储介质及电子设备
CN116820351B (zh) * 2023-07-21 2024-04-09 北京得瑞领新科技有限公司 冷热数据标定方法、装置、存储介质及电子设备
CN117149098A (zh) * 2023-10-31 2023-12-01 苏州元脑智能科技有限公司 一种条带单元分配方法、装置、计算机设备及存储介质
CN117149098B (zh) * 2023-10-31 2024-02-06 苏州元脑智能科技有限公司 一种条带单元分配方法、装置、计算机设备及存储介质

Also Published As

Publication number Publication date
CN105487823A (zh) 2016-04-13
CN105487823B (zh) 2018-06-05

Similar Documents

Publication Publication Date Title
WO2017092480A1 (zh) 一种数据迁移的方法及装置
US11023147B2 (en) Mapping storage extents into resiliency groups
US8478939B2 (en) Relative heat index based hot data determination for block based storage tiering
CN104583930B (zh) 数据迁移的方法、控制器和数据迁移装置
CN104268099B (zh) 一种管理数据读写的方法及装置
US20110258379A1 (en) Method and apparatus to manage tier information
CN107273046B (zh) 一种基于固态盘阵列的数据处理方法及***
WO2019000950A1 (zh) 分片管理方法和分片管理装置
US11676671B1 (en) Amplification-based read disturb information determination system
US10437691B1 (en) Systems and methods for caching in an erasure-coded system
CN103473266A (zh) 固态硬盘及其删除重复数据的方法
CN104035886B (zh) 磁盘重映射方法、装置及电子设备
CN112817540B (zh) 一种基于磁盘阵列扩展的数据块重分布方法及装置
US20150242145A1 (en) Storage apparatus and method of controlling storage apparatus
US11010091B2 (en) Multi-tier storage
US11929135B2 (en) Read disturb information determination system
US20170031630A1 (en) Handling shingled magnetic recording (smr) drives in a tiered storage system
Cady et al. A stochastic analysis of hard disk drives
US11281573B2 (en) Modification-frequency-based tiered data storage and garbage collection system
CN111880900A (zh) 一种面向超融合设备的近数据处理***的设计方法
CN111880739A (zh) 一种面向超融合设备的近数据处理***
US9760287B2 (en) Method and system for writing to and reading from computer readable media
US11763898B2 (en) Value-voltage-distirubution-intersection-based read disturb information determination system
US11847351B2 (en) Automatic identification and ranking of migration candidate storage groups based on relative performance impact to current storage array components
US11922035B2 (en) Read-disturb-based read temperature adjustment system

Legal Events

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

Ref document number: 16869791

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16869791

Country of ref document: EP

Kind code of ref document: A1