CN108874594A - Disk replacing options, device, equipment and storage medium in a kind of storage cluster - Google Patents
Disk replacing options, device, equipment and storage medium in a kind of storage cluster Download PDFInfo
- Publication number
- CN108874594A CN108874594A CN201810661713.0A CN201810661713A CN108874594A CN 108874594 A CN108874594 A CN 108874594A CN 201810661713 A CN201810661713 A CN 201810661713A CN 108874594 A CN108874594 A CN 108874594A
- Authority
- CN
- China
- Prior art keywords
- magnetic disc
- ordinary magnetic
- disk
- data processing
- storage cluster
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/16—Error detection or correction of the data by redundancy in hardware
- G06F11/20—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
- G06F11/202—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where processing functionality is redundant
- G06F11/2023—Failover techniques
- G06F11/2033—Failover techniques switching over of hardware resources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/16—Error detection or correction of the data by redundancy in hardware
- G06F11/20—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
- G06F11/2053—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where persistent mass storage functionality or persistent mass storage control functionality is redundant
- G06F11/2094—Redundant storage or storage space
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Memory System Of A Hierarchy Structure (AREA)
Abstract
The invention discloses disk replacing options in a kind of storage cluster, this method includes：When the failure of the first ordinary magnetic disc needs replacing in storage cluster, stop the data processing finger daemon of the first ordinary magnetic disc；Clear up the relevant information of the data processing finger daemon of the first ordinary magnetic disc；The first cache sector that the first ordinary magnetic disc uses is distributed in determination；Remove the residual data of the data processing finger daemon of the first ordinary magnetic disc in the first cache sector；After the first ordinary magnetic disc is changed to the second ordinary magnetic disc by determination, the first cache sector is reassigned to the data processing finger daemon of the second ordinary magnetic disc；Start the data processing finger daemon of the second ordinary magnetic disc and carries out reliability configuration.Using technical solution provided by the embodiment of the present invention, the influence to storage cluster can be reduced with quick-replaceable disk.The invention also discloses disk more changing device, equipment and storage mediums in a kind of storage cluster, have relevant art effect.
Description
Technical field
The present invention relates to computer application technologies, more particularly to disk replacing options, dress in a kind of storage cluster
It sets, equipment and storage medium.
Background technique
With the fast development of computer technology, the distributed storage cluster for mass data storage is obtained in various industries
Extensive use is arrived.
In actual application, the scale of storage cluster is increasing, and user wants for storage cluster read or write speed
Ask also higher and higher, then consider in storage cluster using the faster SSD of read or write speed (Solid State Drives, Gu
State hard disk) disk.But for the cost consideration to SSD disk, most storage cluster will not be but comprehensive all using SSD disk
Close the ordinary magnetic disc and SSD disk for using low speed.By the way that cache sector is arranged on SSD disk, by the number of ordinary magnetic disc
The data that the file and needs for needing frequently to read and write according to processing finger daemon are frequently read and write from ordinary magnetic disc are put into accordingly
Cache sector, to improve the read or write speed of entire storage cluster.
Although improving the read or write speed and efficiency of storage cluster in this way, if there is event in the disk in storage cluster
Barrier, when can not be normally carried out reading and writing data, it is necessary to be replaced to disk, but there is presently no quick replacing options.
It is that current those skilled in the art are anxious in conclusion how to efficiently solve disk replacement problem in storage cluster
Technical problem to be solved.
Summary of the invention
The object of the present invention is to provide disk replacing options, device, equipment and storage mediums in a kind of storage cluster, with fast
Speed replaces disk in storage cluster, reduces the influence to storage cluster.
In order to solve the above technical problems, the present invention provides the following technical solutions：
Disk replacing options in a kind of storage cluster, the storage cluster includes multiple ordinary magnetic discs and at least one SSD
Disk is provided at least one cache sector at least one SSD disk, and each cache sector is for distributing to phase
The ordinary magnetic disc answered carries out caching acceleration, the method includes：
When the failure of the first ordinary magnetic disc needs replacing in the storage cluster, stop first ordinary magnetic disc
Data processing finger daemon；
Clear up the relevant information of the data processing finger daemon of the first ordinary magnetic disc described in the storage cluster；
The first cache sector that first ordinary magnetic disc uses is distributed in determination；
Remove the residual number of the data processing finger daemon of the first ordinary magnetic disc described in first cache sector
According to；
After first ordinary magnetic disc is changed to the second ordinary magnetic disc by determination, by first cache sector weight
It is newly assigned to the data processing finger daemon of second ordinary magnetic disc；
Start the data processing finger daemon of second ordinary magnetic disc and carries out reliability configuration.
In a kind of specific embodiment of the invention, the first ordinary magnetic disc described in the cleaning storage cluster
The relevant information of data processing finger daemon, including：
Clear up reliability configuration relevant to the data processing finger daemon of first ordinary magnetic disc；
The data processing finger daemon for first ordinary magnetic disc is cleared up from the monitoring service of the storage cluster
Monitoring.
In a kind of specific embodiment of the invention, first that first ordinary magnetic disc uses is distributed in the determination
Cache sector, including：
Obtain the slot number of first ordinary magnetic disc；
According to the slot number of the slot number of first ordinary magnetic disc and pre-recorded ordinary magnetic disc and cache point
The first cache sector that first ordinary magnetic disc uses is distributed in the corresponding relationship of the identification number in area, determination.
In a kind of specific embodiment of the invention, further include：
When the failure of the first SSD disk needs replacing in the storage cluster, determine that cache sector is located at institute
State all third ordinary magnetic discs on the first SSD disk；
Stop the data processing finger daemon of each third ordinary magnetic disc；
Clear up the relevant information of the data processing finger daemon of each third ordinary magnetic disc in the storage cluster；
After the first SSD disk is changed to the 2nd SSD disk by determination, according to pre-recorded the first SSD
The cache sector information of disk is cached the division of subregion to the 2nd SSD disk；
From newly mark off come cache sector in be each third ordinary magnetic disc data processing finger daemon distribution
Cache sector；
Start the data processing finger daemon of each third ordinary magnetic disc and carries out reliability configuration.
In a kind of specific embodiment of the invention, each third ordinary magnetic disc in the cleaning storage cluster
The relevant information of data processing finger daemon, including：
Clear up reliability configuration relevant to the data processing finger daemon of each third ordinary magnetic disc；
The data processing finger daemon for each third ordinary magnetic disc is cleared up from the monitoring service of the storage cluster
Monitoring.
In a kind of specific embodiment of the invention, the determining cache sector is located at the first SSD disk
On all third ordinary magnetic discs, including：
Obtain the slot number of the first SSD disk；
According to slot number and the high speed that is thereon arranged of the slot number of the first SSD disk, pre-recorded SSD disk
The identification number of the slot number and cache sector of the corresponding relationship of the identification number of cache partitions and pre-recorded ordinary magnetic disc
Corresponding relationship, determine all third ordinary magnetic discs that cache sector is located on the first SSD disk.
In a kind of specific embodiment of the invention, it is described from newly mark off come cache sector in be each
After the data processing finger daemon distribution cache sector of third ordinary magnetic disc, further include：
The corresponding relationship of the slot number of the SSD disk and the identification number for the cache sector being arranged thereon is updated, and
The corresponding relationship of the identification number of the slot number and cache sector of the ordinary magnetic disc.
Disk more changing device in a kind of storage cluster, the storage cluster includes multiple ordinary magnetic discs and at least one SSD
Disk is provided at least one cache sector at least one SSD disk, and each cache sector is for distributing to phase
The ordinary magnetic disc answered carries out caching acceleration, and described device includes：
First process stopping modular, in the storage cluster the first ordinary magnetic disc failure need replacing when,
Stop the data processing finger daemon of first ordinary magnetic disc；
First information cleaning modul, the data processing for clearing up the first ordinary magnetic disc described in the storage cluster are guarded
The relevant information of process；
Subregion determining module, for determining the first cache sector distributing to first ordinary magnetic disc and using；
Data dump module, for removing the data processing of the first ordinary magnetic disc described in first cache sector
The residual data of finger daemon；
First subregion distribution module, for inciting somebody to action after first ordinary magnetic disc is changed to the second ordinary magnetic disc by determination
First cache sector is reassigned to the data processing finger daemon of second ordinary magnetic disc；
First process configuration module, for starting the data processing finger daemon of second ordinary magnetic disc and carrying out reliable
Property configuration.
In a kind of specific embodiment of the invention, further include：
Disk determining module, for determining high when the failure of the first SSD disk needs replacing in the storage cluster
Fast cache partitions are located at all third ordinary magnetic discs on the first SSD disk；
Second process stopping modular, for stopping the data processing finger daemon of each third ordinary magnetic disc；
Second information cleaning modul, the data processing for clearing up each third ordinary magnetic disc in the storage cluster are guarded
The relevant information of process；
Subregion division module, for determine the first SSD disk is changed to the 2nd SSD disk after, according to preparatory
The cache sector information of the first SSD disk of record, is cached subregion to the 2nd SSD disk and draws
Point；
Second subregion distribution module, for being each third ordinary magnetic disc from newly marking off in the cache sector come
Data processing finger daemon distributes cache sector；
Second process configuration module, for starting the data processing finger daemon of each third ordinary magnetic disc and carrying out reliable
Property configuration.
Disk more exchange device in a kind of storage cluster, including：
Memory, for storing computer program；
Processor realizes disk replacement side in storage cluster described in any of the above-described when for executing the computer program
The step of method.
A kind of computer readable storage medium is stored with computer program on the computer readable storage medium, described
The step of disk replacing options in storage cluster described in any of the above-described are realized when computer program is executed by processor.
Using technical solution provided by the embodiment of the present invention, it is provided at least one SSD disk in storage cluster
It is common to stop first when the failure of the first ordinary magnetic disc needs replacing in storage cluster at least one cache sector
The data processing finger daemon of disk, clears up the relevant information of the data processing finger daemon in storage cluster, and determination is distributed to
The first cache sector that first ordinary magnetic disc uses is removed in the first cache sector at the data of the first ordinary magnetic disc
The residual data for managing finger daemon, after the first ordinary magnetic disc is changed to the second ordinary magnetic disc by determination, by the first cache
Subregion is reassigned to the data processing finger daemon of the second ordinary magnetic disc, the data processing of the second ordinary magnetic disc of starting guard into
Journey simultaneously carries out reliability configuration, so that the second ordinary magnetic disc after replacement is added rapidly to work in storage cluster,
Reduce the influence to storage cluster.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of implementation flow chart of disk replacing options in storage cluster in the embodiment of the present invention；
Fig. 2 is the implementation flow chart of disk replacing options in another storage cluster in the embodiment of the present invention；
Fig. 3 is a kind of structural schematic diagram of disk more changing device in storage cluster in the embodiment of the present invention；
Fig. 4 is the structural schematic diagram of disk more changing device in another storage cluster in the embodiment of the present invention；
Fig. 5 is a kind of structural schematic diagram of disk more exchange device in storage cluster in the embodiment of the present invention.
Specific embodiment
Core of the invention is to provide disk replacing options in a kind of storage cluster.In embodiments of the present invention, storage collection
Group is made of multiple memory nodes, including multiple ordinary magnetic discs and at least one SSD disk, is arranged at least one SSD disk
There is at least one cache sector.For balancing performance, for each memory node in storage cluster, the memory node meeting
For each low speed of itself ordinary magnetic disc distributed on the SSD disk of itself subregion for cache acceleration, such point
Area is cache sector.I.e. each cache sector carries out caching acceleration for distributing to corresponding ordinary magnetic disc.Phase
Compared with for, ordinary magnetic disc is low-speed device, and SSD disk is high-speed equipment.
In order to enable those skilled in the art to better understand the solution of the present invention, with reference to the accompanying drawings and detailed description
The present invention is described in further detail.Obviously, described embodiments are only a part of the embodiments of the present invention, rather than
Whole embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creative work premise
Under every other embodiment obtained, shall fall within the protection scope of the present invention.
It is shown in Figure 1, for the implementation stream of disk replacing options in a kind of storage cluster provided by the embodiment of the present invention
Cheng Tu, this method may comprise steps of：
S110：When the failure of the first ordinary magnetic disc needs replacing in storage cluster, stop the number of the first ordinary magnetic disc
According to processing finger daemon.
As described, storage cluster includes multiple ordinary magnetic discs and at least one SSD disk.With storage cluster
Lasting to use, disk in storage cluster is it is possible that failure, to influence the normal work of storage cluster, this is just needed pair
The disk of failure is replaced.
In practical applications, each ordinary magnetic disc carries out the works such as reading and writing data by respective data processing finger daemon
Make.When the failure of the first ordinary magnetic disc needs replacing in storage cluster, can first it stop at the data of the first ordinary magnetic disc
Manage finger daemon.First ordinary magnetic disc is the ordinary magnetic disc that any one in storage cluster uses cache sector.
S120：Clear up the relevant information of the data processing finger daemon of the first ordinary magnetic disc in storage cluster.
After the data processing finger daemon for stopping the first ordinary magnetic disc, the data processing in storage cluster can be cleared up and kept
The relevant information of shield process.
Specifically, reliability configuration relevant to the data processing finger daemon of the first ordinary magnetic disc can be cleared up, from depositing
The monitoring of the data processing finger daemon for the first ordinary magnetic disc is cleared up in the monitoring service of accumulation.
S130：The first cache sector that the first ordinary magnetic disc uses is distributed in determination.
In storage cluster, a cache sector can be distributed for each ordinary magnetic disc, to improve read or write speed.?
When the failure of the first ordinary magnetic disc needs replacing in storage cluster, it can determine and distribute to the first ordinary magnetic disc uses first
Cache sector, the first cache sector are set on SSD disk.
In a kind of specific embodiment of the invention, step S130 be may comprise steps of：
Step 1：Obtain the slot number of the first ordinary magnetic disc；
Step 2：According to the slot number of the first ordinary magnetic disc and the slot number and cache of pre-recorded ordinary magnetic disc
The first cache sector that the first ordinary magnetic disc uses is distributed in the corresponding relationship of the identification number of subregion, determination.
It is illustrated for ease of description, above-mentioned two step is combined.
It in embodiments of the present invention, can be with the slot number of pre-recorded ordinary magnetic disc and the identification number of cache sector
Corresponding relationship.Specifically, record in storage cluster deployment phase and carry out real-time update to it.Cache sector
Identification number be system unique number, the identification number of different cache subregion is different.
The corresponding relation data structure of the identification number of the slot number and cache sector of pre-recorded ordinary magnetic disc can
With reference table 1：
| Ordinary magnetic disc slot number | Int type |
| The cache sector used | Varchar type |
Table 1
It, can be according to the slot number and the slot of pre-recorded ordinary magnetic disc after the slot number for obtaining the first ordinary magnetic disc
Corresponding relationship of the position number with the identification number of cache sector, determines the mark of the corresponding cache sector of the first ordinary magnetic disc
Number, it determines therefrom that and distributes to the first cache sector that the first ordinary magnetic disc uses.
Corresponding relationship caused by drive caused by memory node is restarted drifts about can be prevented using slot number to become
The problem of change.
S140：Remove the residual data of the data processing finger daemon of the first ordinary magnetic disc in the first cache sector.
When the first ordinary magnetic disc works normally, the data processing finger daemon of the first ordinary magnetic disc will use the first high speed
Cache partitions carry out the operation such as reading and writing data, are stored with corresponding operation data in the first cache sector.It is distributed determining
Behind the first cache sector used to the first ordinary magnetic disc, the first ordinary magnetic disc in the first cache sector can be removed
Data processing finger daemon residual data, with prevent replacement new building after new process is interfered.
S150：After the first ordinary magnetic disc is changed to the second ordinary magnetic disc by determination, again by the first cache sector
Distribute to the data processing finger daemon of the second ordinary magnetic disc.
First ordinary magnetic disc is changed to the second ordinary magnetic disc, carries out the replacement of physical disk.Specifically, can be by technology
Personnel replace.
After the first ordinary magnetic disc is changed to the second ordinary magnetic disc, the data processing of the second ordinary magnetic disc can be guarded
Process is pre-processed.The slot number of second ordinary magnetic disc is the slot number of the first ordinary magnetic disc, and the second ordinary magnetic disc will generation
For the work of the first ordinary magnetic disc.At this point it is possible to which the first cache sector to be reassigned to the data of the second ordinary magnetic disc
Handle finger daemon.
S160：Start the data processing finger daemon of the second ordinary magnetic disc and carries out reliability configuration.
After first cache sector to be reassigned to the data processing finger daemon of the second ordinary magnetic disc, it can star
The data processing finger daemon of second ordinary magnetic disc simultaneously carries out reliability configuration, so far completes more changing jobs for ordinary magnetic disc, deposits
Accumulation can operate normally.
Using method provided by the embodiment of the present invention, it is provided at least at least one SSD disk in storage cluster
One cache sector stops the first ordinary magnetic disc when the failure of the first ordinary magnetic disc needs replacing in storage cluster
Data processing finger daemon, clear up storage cluster in the data processing finger daemon relevant information, determination distribute to first
The first cache sector that ordinary magnetic disc uses, the data processing for removing the first ordinary magnetic disc in the first cache sector are kept
The residual data of shield process, after the first ordinary magnetic disc is changed to the second ordinary magnetic disc by determination, by the first cache sector
It is reassigned to the data processing finger daemon of the second ordinary magnetic disc, starts the data processing finger daemon of the second ordinary magnetic disc simultaneously
Reliability configuration is carried out, so that the second ordinary magnetic disc after replacement is added rapidly to work in storage cluster, is reduced
Influence to storage cluster.
Shown in Figure 2, in one embodiment of the invention, this method may also comprise the following steps:：
S210：The failure of the first SSD disk is when needing replacing in storage cluster, determines that cache sector is located at the
All third ordinary magnetic discs on one SSD disk.
In storage cluster, at least one cache sector is provided in SSD disk, each cache sector is used for
It distributes to corresponding ordinary magnetic disc and carries out caching acceleration, once SSD disk failures need replacing, will affect corresponding general
The normal work of logical disk.
So can first determine cache sector when the failure of the first SSD disk needs replacing in storage cluster
All third ordinary magnetic discs on the first SSD disk.First SSD disk is that any one in storage cluster is provided with high speed
The SSD disk of cache partitions.Third ordinary magnetic disc can have one or more.
In a kind of specific embodiment of the invention, step S210 be may comprise steps of：
First step：Obtain the slot number of the first SSD disk；
Second step：According to the slot number of the first SSD disk, pre-recorded SSD disk slot number with set thereon
The slot number and cache sector of the corresponding relationship of the identification number for the cache sector set and pre-recorded ordinary magnetic disc
Identification number corresponding relationship, determine all third ordinary magnetic discs that cache sector is located on the first SSD disk.
It is illustrated for ease of description, above-mentioned two step is combined.
In embodiments of the present invention, except pair of the identification number of the slot number and cache sector of pre-recorded ordinary magnetic disc
It, can be corresponding with the identification number for the cache sector being arranged thereon with the slot number of pre-recorded SSD disk outside should being related to
Relationship.Specifically, record in storage cluster deployment phase and carry out real-time update to it.
The corresponding relationship number of the slot number of pre-recorded SSD disk and the identification number for the cache sector being arranged thereon
It can be with reference table 2 according to structure：
| SSD disk slot number | Int type |
| The cache sector being arranged thereon | Varchar type is separated using comma between subregion |
Table 2
It, can be according to the slot number of the first SSD disk and pre-recorded after the slot number for obtaining the first SSD disk
The corresponding relationship of the slot number of SSD disk and the identification number for the cache sector being arranged thereon, determines and sets on the first SSD disk
The identification number for each cache sector set, slot number and cache sector further according to pre-recorded ordinary magnetic disc
The corresponding relationship of identification number, determines the corresponding ordinary magnetic disc in each cache sector, that is, determines that cache sector is located at the
All third ordinary magnetic discs on one SSD disk.
S220：Stop the data processing finger daemon of each third ordinary magnetic disc.
In practical applications, each ordinary magnetic disc carries out the works such as reading and writing data by respective data processing finger daemon
Make.After determining that cache sector is located at all third ordinary magnetic discs on the first SSD disk for breaking down and needing replacing,
The data processing finger daemon of each third ordinary magnetic disc can first be stopped.
S230：Clear up the relevant information of the data processing finger daemon of each third ordinary magnetic disc in storage cluster.
For each third ordinary magnetic disc, after the data processing finger daemon for stopping the third ordinary magnetic disc, Ke Yiji
The relevant information of the continuous data processing finger daemon for clearing up the third ordinary magnetic disc.
Specifically, reliability configuration relevant to the data processing finger daemon of each third ordinary magnetic disc can be cleared up；
The monitoring of the data processing finger daemon for each third ordinary magnetic disc is cleared up from the monitoring service of storage cluster.
S240：After the first SSD disk is changed to the 2nd SSD disk by determination, according to the first pre-recorded SSD disk
Cache sector information, the division of subregion is cached to the 2nd SSD disk.
Because the failure of the first SSD disk needs to change, it is possible to specific physics replacement operation is carried out by technical staff, it will
First SSD disk is changed to the 2nd SSD disk.
After the first SSD disk is changed to the 2nd SSD disk, the slot number of the 2nd SSD disk is the first SSD disk
Slot number, the 2nd SSD disk will replace the first SSD disk work.At this point it is possible to according to the first pre-recorded SSD magnetic
The cache sector information of disk, the division of subregion is cached to the 2nd SSD disk.
The cache sector information of first SSD disk may include the cache sector being arranged in the first SSD disk
Number information and each cache sector size information.
S250：From newly mark off come cache sector in be each third ordinary magnetic disc data processing finger daemon
Distribute cache sector.
Before carrying out the replacement of SSD disk, corresponding one of each cache sector being arranged on the first SSD disk the
Three ordinary magnetic discs, the cache sector information after the first SSD disk is changed to the 2nd SSD disk, according to the first SSD disk
It is cached the division of subregion to the 2nd SSD disk, is that each third is general from newly marking off in the cache sector come
The data processing finger daemon of logical disk distributes cache sector so that the data processing of each third ordinary magnetic disc guard into
Journey continues to use corresponding cache sector and carries out the operation such as reading and writing data.
S260：Start the data processing finger daemon of each third ordinary magnetic disc and carries out reliability configuration.
Start the data processing finger daemon of each third ordinary magnetic disc and carry out reliability configuration, so far completes SSD magnetic
Disk more changes jobs, and storage cluster can operate normally.
Provided technical solution through the embodiment of the present invention, the 2nd SSD disk after can making replacement rapidly join
It works into storage cluster, reduces the influence to storage cluster.
In one embodiment of the invention, after step S250, this method may also comprise the following steps:：
The corresponding relationship of the slot number and the identification number for the cache sector being arranged thereon of SSD disk is updated, and common
The corresponding relationship of the identification number of the slot number and cache sector of disk.
It is understood that it is slow to carry out high speed to the 2nd SSD disk after the first SSD disk is changed to the 2nd SSD disk
The division for depositing subregion, the cache sector newly marked off have system unique number, i.e., newly mark off the cache point come
The identification number in area is different from the identification number of cache sector of the first SSD disk.It is therefore desirable to update the slot position of SSD disk
Number with the corresponding relationship of the identification number for the cache sector being arranged thereon and the slot number of ordinary magnetic disc and cache sector
Identification number corresponding relationship, use when to carry out disk replacement again, avoid corresponding relationship entanglement cause storage cluster without
Method works normally.
Corresponding to above method embodiment, the embodiment of the invention also provides disks in a kind of storage cluster more to change the outfit
It sets, storage cluster includes multiple ordinary magnetic discs and at least one SSD disk, is provided at least one at least one SSD disk
Cache sector, each cache sector carries out caching acceleration for distributing to corresponding ordinary magnetic disc, described below
Disk more changing device can correspond to each other ginseng with disk replacing options in a kind of above-described storage cluster in a kind of storage cluster
According to.
Shown in Figure 3, which comprises the following modules：
First process stopping modular 310, for stopping when the failure of the first ordinary magnetic disc needs replacing in storage cluster
The only data processing finger daemon of the first ordinary magnetic disc；
First information cleaning modul 320, for clearing up the data processing finger daemon of the first ordinary magnetic disc in storage cluster
Relevant information；
Subregion determining module 330, for determining the first cache sector distributing to the first ordinary magnetic disc and using；
Data dump module 340, the data processing for removing the first ordinary magnetic disc in the first cache sector are guarded
The residual data of process；
First subregion distribution module 350, for after determining the first ordinary magnetic disc being changed to the second ordinary magnetic disc, by the
One cache sector is reassigned to the data processing finger daemon of the second ordinary magnetic disc；
First process configuration module 360, for starting the data processing finger daemon of the second ordinary magnetic disc and carrying out reliable
Property configuration.
Using device provided by the embodiment of the present invention, it is provided at least at least one SSD disk in storage cluster
One cache sector stops the first ordinary magnetic disc when the failure of the first ordinary magnetic disc needs replacing in storage cluster
Data processing finger daemon, clear up storage cluster in the data processing finger daemon relevant information, determination distribute to first
The first cache sector that ordinary magnetic disc uses, the data processing for removing the first ordinary magnetic disc in the first cache sector are kept
The residual data of shield process, after the first ordinary magnetic disc is changed to the second ordinary magnetic disc by determination, by the first cache sector
It is reassigned to the data processing finger daemon of the second ordinary magnetic disc, starts the data processing finger daemon of the second ordinary magnetic disc simultaneously
Reliability configuration is carried out, so that the second ordinary magnetic disc after replacement is added rapidly to work in storage cluster, is reduced
Influence to storage cluster.
In a kind of specific embodiment of the invention, first information cleaning modul 320 is specifically used for：
Clear up reliability configuration relevant to the data processing finger daemon of the first ordinary magnetic disc；
The monitoring of the data processing finger daemon for the first ordinary magnetic disc is cleared up from the monitoring service of storage cluster.
In a kind of specific embodiment of the invention, subregion determining module 330 is specifically used for：
Obtain the slot number of the first ordinary magnetic disc；
According to the slot number and cache sector of the slot number of the first ordinary magnetic disc and pre-recorded ordinary magnetic disc
The first cache sector that the first ordinary magnetic disc uses is distributed in the corresponding relationship of identification number, determination.
It is shown in Figure 4, in a kind of specific embodiment of the invention, further include：
Disk determining module 410, for determining high when the failure of the first SSD disk needs replacing in storage cluster
Fast cache partitions are located at all third ordinary magnetic discs on the first SSD disk；
Second process stopping modular 420, for stopping the data processing finger daemon of each third ordinary magnetic disc；
Second information cleaning modul 430, the data processing for clearing up each third ordinary magnetic disc in storage cluster are guarded
The relevant information of process；
Subregion division module 440, for being remembered after the first SSD disk is changed to the 2nd SSD disk by determination according to preparatory
The cache sector information of first SSD disk of record, the division of subregion is cached to the 2nd SSD disk；
Second subregion distribution module 450, for being the common magnetic of each third from newly marking off in the cache sector come
The data processing finger daemon of disk distributes cache sector；
Second process configuration module 460, for starting the data processing finger daemon of each third ordinary magnetic disc and carrying out
Reliability configuration.
In a kind of specific embodiment of the invention, the second information cleaning modul 430 is specifically used for：
Clear up reliability configuration relevant to the data processing finger daemon of each third ordinary magnetic disc；
The prison of the data processing finger daemon for each third ordinary magnetic disc is cleared up from the monitoring service of storage cluster
Control.
In a kind of specific embodiment of the invention, disk determining module 410 is specifically used for：
Obtain the slot number of the first SSD disk；
According to slot number and the cache that is thereon arranged of the slot number of the first SSD disk, pre-recorded SSD disk
Pair of the identification number of the slot number and cache sector of the corresponding relationship of the identification number of subregion and pre-recorded ordinary magnetic disc
It should be related to, determine all third ordinary magnetic discs that cache sector is located on the first SSD disk.
In a kind of specific embodiment of the invention, further includes relationship update module, be used for：
It is being the data processing finger daemon point of each third ordinary magnetic disc from the cache sector newly marked off
After cache sector, the slot number for updating SSD disk is corresponding with the identification number for the cache sector being arranged thereon
The corresponding relationship of the identification number of the slot number and cache sector of relationship and ordinary magnetic disc.
It is shown in Figure 5, above method embodiment is corresponded to, the embodiment of the invention also provides in a kind of storage cluster
Disk more exchange device, including：
Memory 510, for storing computer program；
Processor 520, the step of disk replacing options in above-mentioned storage cluster are realized when for executing computer program.
Corresponding to above method embodiment, the embodiment of the invention also provides a kind of computer readable storage medium, meters
It is stored with computer program on calculation machine readable storage medium storing program for executing, is realized when computer program is executed by processor in above-mentioned storage cluster
The step of disk replacing options.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with it is other
The difference of embodiment, same or similar part may refer to each other between each embodiment.For being filled disclosed in embodiment
For setting, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is referring to method part
Explanation.
Professional further appreciates that, unit described in conjunction with the examples disclosed in the embodiments of the present disclosure
And algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware and
The interchangeability of software generally describes each exemplary composition and step according to function in the above description.These
Function is implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Profession
Technical staff can use different methods to achieve the described function each specific application, but this realization is not answered
Think beyond the scope of this invention.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can directly be held with hardware, processor
The combination of capable software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
Used herein a specific example illustrates the principle and implementation of the invention, and above embodiments are said
It is bright to be merely used to help understand technical solution of the present invention and its core concept.It should be pointed out that for the common of the art
, without departing from the principle of the present invention, can be with several improvements and modifications are made to the present invention for technical staff, these
Improvement and modification are also fallen within the protection scope of the claims of the present invention.
Claims (11)
1. disk replacing options in a kind of storage cluster, which is characterized in that the storage cluster includes multiple ordinary magnetic discs and extremely
Lack a SSD disk, at least one cache sector is provided at least one SSD disk, each cache sector is used
Caching acceleration is carried out in distributing to corresponding ordinary magnetic disc, the method includes：
When the failure of the first ordinary magnetic disc needs replacing in the storage cluster, stop the data of first ordinary magnetic disc
Handle finger daemon；
Clear up the relevant information of the data processing finger daemon of the first ordinary magnetic disc described in the storage cluster；
The first cache sector that first ordinary magnetic disc uses is distributed in determination；
Remove the residual data of the data processing finger daemon of the first ordinary magnetic disc described in first cache sector；
After first ordinary magnetic disc is changed to the second ordinary magnetic disc by determination, first cache sector is divided again
The data processing finger daemon of second ordinary magnetic disc described in dispensing；
Start the data processing finger daemon of second ordinary magnetic disc and carries out reliability configuration.
2. disk replacing options in storage cluster according to claim 1, which is characterized in that the cleaning storage collection
The relevant information of the data processing finger daemon of first ordinary magnetic disc described in group, including：
Clear up reliability configuration relevant to the data processing finger daemon of first ordinary magnetic disc；
The prison of the data processing finger daemon for first ordinary magnetic disc is cleared up from the monitoring service of the storage cluster
Control.
3. disk replacing options in storage cluster according to claim 1, which is characterized in that the determination is distributed to described
The first cache sector that first ordinary magnetic disc uses, including：
Obtain the slot number of first ordinary magnetic disc；
According to the slot number and cache sector of the slot number of first ordinary magnetic disc and pre-recorded ordinary magnetic disc
The first cache sector that first ordinary magnetic disc uses is distributed in the corresponding relationship of identification number, determination.
4. the disk replacing options into described in any item storage clusters among 3 according to claim 1, which is characterized in that also wrap
It includes：
The failure of the first SSD disk is when needing replacing in the storage cluster, determines that cache sector is located at described the
All third ordinary magnetic discs on one SSD disk；
Stop the data processing finger daemon of each third ordinary magnetic disc；
Clear up the relevant information of the data processing finger daemon of each third ordinary magnetic disc in the storage cluster；
After the first SSD disk is changed to the 2nd SSD disk by determination, according to pre-recorded the first SSD disk
Cache sector information, the division of subregion is cached to the 2nd SSD disk；
From newly mark off come cache sector in be each third ordinary magnetic disc data processing finger daemon distribution high speed
Cache partitions；
Start the data processing finger daemon of each third ordinary magnetic disc and carries out reliability configuration.
5. disk replacing options in storage cluster according to claim 4, which is characterized in that the cleaning storage collection
The relevant information of the data processing finger daemon of each third ordinary magnetic disc in group, including：
Clear up reliability configuration relevant to the data processing finger daemon of each third ordinary magnetic disc；
The prison of the data processing finger daemon for each third ordinary magnetic disc is cleared up from the monitoring service of the storage cluster
Control.
6. disk replacing options in storage cluster according to claim 4, which is characterized in that the determining cache point
Area is located at all third ordinary magnetic discs on the first SSD disk, including：
Obtain the slot number of the first SSD disk；
According to slot number and the cache that is thereon arranged of the slot number of the first SSD disk, pre-recorded SSD disk
Pair of the identification number of the slot number and cache sector of the corresponding relationship of the identification number of subregion and pre-recorded ordinary magnetic disc
It should be related to, determine all third ordinary magnetic discs that cache sector is located on the first SSD disk.
7. disk replacing options in storage cluster according to claim 6, which is characterized in that described next from newly marking off
Cache sector in be each third ordinary magnetic disc data processing finger daemon distribution cache sector after, also wrap
It includes：
Update the corresponding relationship of the slot number of the SSD disk and the identification number for the cache sector being arranged thereon and described
The corresponding relationship of the identification number of the slot number and cache sector of ordinary magnetic disc.
8. disk more changing device in a kind of storage cluster, which is characterized in that the storage cluster includes multiple ordinary magnetic discs and extremely
Lack a SSD disk, at least one cache sector is provided at least one SSD disk, each cache sector is used
Caching acceleration is carried out in distributing to corresponding ordinary magnetic disc, described device includes：
First process stopping modular, for stopping when the failure of the first ordinary magnetic disc needs replacing in the storage cluster
The data processing finger daemon of first ordinary magnetic disc；
First information cleaning modul, for clearing up the data processing finger daemon of the first ordinary magnetic disc described in the storage cluster
Relevant information；
Subregion determining module, for determining the first cache sector distributing to first ordinary magnetic disc and using；
Data dump module, the data processing for removing the first ordinary magnetic disc described in first cache sector are guarded
The residual data of process；
First subregion distribution module will be described for after determining first ordinary magnetic disc being changed to the second ordinary magnetic disc
First cache sector is reassigned to the data processing finger daemon of second ordinary magnetic disc；
First process configuration module is matched for starting the data processing finger daemon of second ordinary magnetic disc and carrying out reliability
It sets.
9. disk replacing options in storage cluster according to claim 1, which is characterized in that further include：
Disk determining module, for determining that high speed is slow when the failure of the first SSD disk needs replacing in the storage cluster
Deposit all third ordinary magnetic discs that subregion is located on the first SSD disk；
Second process stopping modular, for stopping the data processing finger daemon of each third ordinary magnetic disc；
Second information cleaning modul, for clearing up the data processing finger daemon of each third ordinary magnetic disc in the storage cluster
Relevant information；
Subregion division module, for determine the first SSD disk is changed to the 2nd SSD disk after, according to pre-recorded
The first SSD disk cache sector information, the division of subregion is cached to the 2nd SSD disk；
Second subregion distribution module, for being the data of each third ordinary magnetic disc from the cache sector newly marked off
It handles finger daemon and distributes cache sector；
Second process configuration module is matched for starting the data processing finger daemon of each third ordinary magnetic disc and carrying out reliability
It sets.
10. disk more exchange device in a kind of storage cluster, which is characterized in that including：
Memory, for storing computer program；
Processor realizes the disk in storage cluster as described in any one of claim 1 to 7 when for executing the computer program
The step of replacing options.
11. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program realizes that disk is more in storage cluster as described in any one of claim 1 to 7 when the computer program is executed by processor
The step of changing method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810661713.0A CN108874594B (en) | 2018-06-25 | 2018-06-25 | Disk replacement method, device, equipment and storage medium in storage cluster |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810661713.0A CN108874594B (en) | 2018-06-25 | 2018-06-25 | Disk replacement method, device, equipment and storage medium in storage cluster |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108874594A true CN108874594A (en) | 2018-11-23 |
| CN108874594B CN108874594B (en) | 2021-10-22 |
Family
ID=64295463
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810661713.0A Active CN108874594B (en) | 2018-06-25 | 2018-06-25 | Disk replacement method, device, equipment and storage medium in storage cluster |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108874594B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110764949A (en) * | 2019-09-29 | 2020-02-07 | 北京浪潮数据技术有限公司 | Hard disk replacement method, hard disk replacement device, and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120096289A1 (en) * | 2010-10-18 | 2012-04-19 | Hitachi, Ltd. | Storage apparatus and power control method |
| CN103713973A (en) * | 2014-01-08 | 2014-04-09 | 浪潮(北京)电子信息产业有限公司 | Mixed storage backup method and system based on HDD and SSD |
| CN103713861A (en) * | 2014-01-09 | 2014-04-09 | 浪潮(北京)电子信息产业有限公司 | File processing method and system based on hierarchical division |
| CN103729149A (en) * | 2013-12-31 | 2014-04-16 | 创新科存储技术有限公司 | Data storage method |
| CN105446665A (en) * | 2015-12-18 | 2016-03-30 | 长城信息产业股份有限公司 | Computer storage acceleration system and optimization method thereof |
| CN106844052A (en) * | 2017-01-22 | 2017-06-13 | 郑州云海信息技术有限公司 | A kind of method and device that fusion cluster is built based on Windows Server |
-
2018
- 2018-06-25 CN CN201810661713.0A patent/CN108874594B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120096289A1 (en) * | 2010-10-18 | 2012-04-19 | Hitachi, Ltd. | Storage apparatus and power control method |
| CN103729149A (en) * | 2013-12-31 | 2014-04-16 | 创新科存储技术有限公司 | Data storage method |
| CN103713973A (en) * | 2014-01-08 | 2014-04-09 | 浪潮(北京)电子信息产业有限公司 | Mixed storage backup method and system based on HDD and SSD |
| CN103713861A (en) * | 2014-01-09 | 2014-04-09 | 浪潮(北京)电子信息产业有限公司 | File processing method and system based on hierarchical division |
| CN105446665A (en) * | 2015-12-18 | 2016-03-30 | 长城信息产业股份有限公司 | Computer storage acceleration system and optimization method thereof |
| CN106844052A (en) * | 2017-01-22 | 2017-06-13 | 郑州云海信息技术有限公司 | A kind of method and device that fusion cluster is built based on Windows Server |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110764949A (en) * | 2019-09-29 | 2020-02-07 | 北京浪潮数据技术有限公司 | Hard disk replacement method, hard disk replacement device, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108874594B (en) | 2021-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105739924B (en) | Caching method and system based on cache cluster | |
| US8788755B2 (en) | Mass data storage system and method of operating thereof | |
| JP2654346B2 (en) | Disk array system, storage method, and control device | |
| JP5256149B2 (en) | Fast data recovery from HDD failure | |
| US20200043524A1 (en) | RAID Storage System with Logical Data Group Priority | |
| CN103761190B (en) | Data processing method and apparatus | |
| JP4229626B2 (en) | File management system | |
| US10564865B2 (en) | Lockless parity management in a distributed data storage system | |
| KR101574451B1 (en) | Imparting durability to a transactional memory system | |
| JP2014174992A (en) | System, method and computer-readable medium for managing cache store to achieve improved cache ramp-up across system reboots | |
| JPH08221326A (en) | Device and method for controlling memory | |
| CN108228396B (en) | Method and apparatus for handling errors of a drive | |
| US11169927B2 (en) | Efficient cache management | |
| CN103558992A (en) | Off-heap direct-memory data stores, methods of creating and/or managing off-heap direct-memory data stores, and/or systems including off-heap direct-memory data store | |
| CN111587423A (en) | Hierarchical data policy for distributed storage systems | |
| WO2016137402A1 (en) | Data stripping, allocation and reconstruction | |
| CN101976181A (en) | Management method and device of storage resources | |
| CN111858189B (en) | Offline processing of storage disks | |
| CN111857540A (en) | Data access method, device and computer program product | |
| US20120011314A1 (en) | Storage system with reduced energy consumption and method of operating thereof | |
| CN111587421A (en) | Method and system for distributed storage system power failure impedance | |
| US11860746B2 (en) | Resilient data storage system with efficient space management | |
| CN109558068B (en) | Data migration method and migration system | |
| CN108874594A (en) | Disk replacing options, device, equipment and storage medium in a kind of storage cluster | |
| CN101997919B (en) | Storage resource management method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |