CN103699340A - Request processing method and equipment - Google Patents
Request processing method and equipment Download PDFInfo
- Publication number
- CN103699340A CN103699340A CN201310687352.4A CN201310687352A CN103699340A CN 103699340 A CN103699340 A CN 103699340A CN 201310687352 A CN201310687352 A CN 201310687352A CN 103699340 A CN103699340 A CN 103699340A
- Authority
- CN
- China
- Prior art keywords
- request
- redundancy
- son
- read
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Abstract
The invention provides a request processing method and request processing equipment. The request processing method comprises the steps of generating a second reading request of an RAID (redundant array of independent discs) system after receiving a first reading request sent by a host; distributing a reading page for the second reading request; splitting the second reading request into a plurality of sub requests; if a slow IO (input/output) condition arises in any one sub request, and the sub request arising the slow IO condition is a redundancy sub request, performing RAID system degrading reading on the redundancy sub request, and returning data corresponding to the redundancy sub request. Thus, when a slow IO condition arises in any one sub request, and the sub request arising the slow IO condition is a redundancy sub request, the RAID system degrading reading can be performed on the redundancy sub request without waiting for the returning of the redundancy sub request, and data corresponding to the redundancy sub request are returned, so that the effect of fast returning data by sub requests arising the slow IO condition is realized, and the occasionally arising problem that the sub request arising the slow IO condition cannot fast return data is solved.
Description
Technical field
The present invention relates to RAID systems technology field, particularly a kind of request processing method and equipment.
Background technology
At RAID(Redundant Array of Independent Disks, Redundant Array of Independent Disks (RAID)) in system, it receives the read request of a main frame, this read request can be split into a plurality of son requests and be issued to executed in parallel on a plurality of hard disks in RAID system, the processing time of main frame read request is depended on the maximum processing time of this little request, while having a request processing time slower in the sub-request of these fractionations, may cause whole main frame read request overtime, and then affect the performance of whole RAID system.There is slow IO(Input/Output, I/O in certain hard disk when the hard disk number of RAID system is more) probability will linearly increase, wherein slow IO is that IO response is slower, wherein IO response refers to the response of antithetical phrase request.This slow IO has become more typical problem in RAID system problem.
A kind of method of the slow IO of existing solution is the identification increasing slow dish, in finding RAID system, certain hard disk continues within a period of time to occur that the slower situation of IO response defines this dish for slow dish, in the situation that having redundancy, RAID system can, by this slow dish off-line, can get rid of like this this and coil slowly the impact on whole RAID system.Wherein RAID system has redundancy to refer to that hard disk can read return data by the RAID system degradation by other hard disks, and will coil slowly off-line is that this slow dish is removed from RAID system.
Although the processing time that the mode of the slow dish of this off-line can improve main frame read request, it is only applicable to occur continuously the hard disk of slow IO within a period of time, for the hard disk of accidental slow IO, cannot process.And further, directly will coil slowly off-line and may cause whole RAID system to read return data by RAID system degradation, increase the risk that double plate lost efficacy.In addition, RAID system will coiled after off-line slowly, need to be reconstructed the data of other hard disks, can affect equally the IO performance of whole RAID system.
Summary of the invention
Technical matters to be solved by this invention is to provide a kind of request processing method and equipment, cannot be on the hard disk processing of accidental slow IO in order to solve in prior art, will coil slowly that double plate that off-line causes lost efficacy and will coil slowly the problem of the IO performance of the whole RAID system of impact that off-line causes.Technical scheme is as follows:
First aspect, the embodiment of the present invention provides a kind of request processing method, comprising:
After the first read request that Receiving Host sends, generate the second read request of individual disc redundancy array system, described the second read request is for the hard disk reading out data from described individual disc redundancy array system;
For the page of reading of described the second read request distribution, the wherein said page of reading is for storing data corresponding to described the second read request;
Described the second read request is split into a plurality of son requests, and wherein split sub-request number depends on the data area that described the second read request is asked, and described in each, son request is for reading the data of corresponding hard disk;
If described in any one there is slow IO situation in son request, and the described son request that occurs slow IO situation is the request of redundancy, described redundancy being asked to carry out individual disc redundancy array system degradation reads, return to data corresponding to described redundancy request, the request of wherein said redundancy is for asking by individual disc redundancy array system of reading return data of demoting.
In the first of first aspect may implementation, described method also comprises: obtain described in each son request with respect to the off-set value of described the second read request, and described in each off-set value separately of record and the address of described the second read request in son request.
May implementation in conjunction with the first of first aspect, in the second of first aspect may implementation, to described redundancy, request is carried out individual disc redundancy array system degradation and is read, and returns to data corresponding to described redundancy request, comprising:
By copying the field information of described redundancy request, generate a new son request, wherein said new son request is for reading the data of hard disk corresponding to described redundancy request;
Address according to the second read request described in described new son request, finds described the second read request, and redistributes and read the page for described the second read request;
According to hard disk corresponding to described new son request and the redundancy relationship between other hard disks, the data of described other hard disk corresponding positions are carried out to verification calculating, obtain data corresponding to described new son request, that wherein redistributes reads the page for the subpage frame of son request memory allocated data described in each, and other hard disks are asked corresponding hard disk for splitting the son except the request of described redundancy in all son requests that obtain.
In conjunction with the first possibility implementation of first aspect or first aspect or the second possibility implementation of first aspect, in the third possibility implementation of first aspect, the determination processing time surpasses the described son of threshold value asks the slow IO situation of appearance.
In the third possibility implementation in conjunction with first aspect, in the 4th kind of possibility implementation of first aspect, it is the sub-request of redundancy that definite described son with redundancy sign is asked.
In conjunction with the first possibility implementation of first aspect or first aspect or the second possibility implementation of first aspect, in the 5th kind of possibility implementation of first aspect, described method also comprises:
Discharge the sub-request of described redundancy, and described in reclaiming, read the subpage frame that the page is described redundancy request distribution.
Second aspect, the embodiment of the present invention also provides a kind of request treatment facility, comprising:
Receiving element, after the first read request sending, generates the second read request of individual disc redundancy array system for Receiving Host, and described the second read request is for the hard disk reading out data from described individual disc redundancy array system;
Allocation units, are used to the page of reading that described the second read request distributes, and the wherein said page of reading is for storing data corresponding to described the second read request;
Split cells, for described the second read request being split into a plurality of son requests, wherein split sub-request number depends on the data area that described the second read request is asked, described in each, son request is for reading the data of corresponding hard disk;
Data capture unit, if there is slow IO situation for son request described in any one, and the described son request that occurs slow IO situation is the request of redundancy, described redundancy is asked to carry out individual disc redundancy array system degradation to be read, return to data corresponding to described redundancy request, the request of wherein said redundancy is for asking by individual disc redundancy array system of reading return data of demoting.
In the first possibility implementation of second aspect, described equipment also comprises: acquiring unit, for obtaining described in each son request with respect to the off-set value of described the second read request, and described in each off-set value separately of record and the address of described the second read request in son request.
In conjunction with the first possibility implementation of second aspect, in the second possibility implementation of second aspect, described data capture unit, comprising:
Request generates subelement, for there is slow IO situation when son request described in any one, and when the described son request that occurs slow IO situation is asked for redundancy, by copying the field information of described redundancy request, generate a new son request, wherein said new son request is for reading the data of hard disk corresponding to described redundancy request;
Search subelement, for according to the address of described second read request of described new son request, find described the second read request, and redistribute and read the page for described the second read request;
Data acquisition subelement, for asking corresponding hard disk and the redundancy relationship between other hard disks according to described new son, the data of described other hard disk corresponding positions are carried out to verification calculating, obtain data corresponding to described new son request, that wherein redistributes reads the page for the subpage frame of son request memory allocated data described in each, and other hard disks are asked corresponding hard disk for splitting the son except the request of described redundancy in all son requests that obtain.
In conjunction with the first possibility implementation of second aspect or second aspect or the second possibility implementation of second aspect, in the third of second aspect may implementation, described data capture unit specifically for: there is slow IO situation in the described son request that the determination processing time surpasses threshold value.
May implementation in conjunction with the third of second aspect, the 4th kind of second aspect may implementation in, described data capture unit further specifically for: determine that the described son request with redundancy sign is the request of redundancy.
In conjunction with the first possibility implementation of second aspect or second aspect or the second possibility implementation of second aspect, in the 5th kind of possibility implementation of second aspect, described equipment also comprises: recovery unit, be used for discharging the sub-request of described redundancy, and described in reclaiming, read the subpage frame that the page is described redundancy request distribution.
Compared with prior art, the present invention includes following advantage:
In embodiments of the present invention, after receiving the first read request of main frame transmission, generate second read request for the hard disk reading out data from RAID system, and be that the page is read in the second read request distribution.The second read request is split into a plurality of son requests to read the data in hard disk, when slow IO situation appears in any one son request, and when the sub-request that occurs slow IO situation is the request of redundancy, in the situation that returning without this redundancy request of wait, can carry out RAID system degradation to the request of redundancy reads, return to data corresponding to redundancy request, realized the problem to there are the redundancy request fast return data of slow IO situation, solve occurring once in a while that the sub-request of slow IO cannot fast return data.After occurring that the sub-request of slow IO situation is returned, can also reclaim this sub-request, avoid this son to ask after long-time return data, main frame read request to be processed and impacted.
Further, the request processing method that the embodiment of the present invention provides is in the situation that there is slow IO in sub-request, still retain its corresponding hard disk, like this when its revert to can the slow IO of normal process hard disk time, can utilize data in this hard disk to carry out RAID system degradation to other slow dishes and read, reduce the risk that double plate lost efficacy.RAID system is reconstructed without the data to hard disk simultaneously, guarantees the IO performance of whole RAID system.
Accompanying drawing explanation
In order to be illustrated more clearly in the technical scheme in the embodiment of the present invention, below the accompanying drawing of required use during embodiment is described is briefly described, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skills, do not paying under the prerequisite of creative work, can also obtain according to these accompanying drawings other accompanying drawing.
Fig. 1 is a kind of process flow diagram of a kind of request processing method of providing of the embodiment of the present invention;
Fig. 2 is the another kind of process flow diagram of a kind of request processing method of providing of the embodiment of the present invention;
Fig. 3 is a kind of a kind of structural representation of asking treatment facility that the embodiment of the present invention provides;
Fig. 4 is a kind of another kind of structural representation of asking treatment facility that the embodiment of the present invention provides;
Fig. 5 is a kind of kernel texture schematic diagram of asking treatment facility that the embodiment of the present invention provides;
Fig. 6 is a kind of another structural representation of asking treatment facility that the embodiment of the present invention provides.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is only the present invention's part embodiment, rather than whole embodiment.Embodiment based in the present invention, those of ordinary skills, not making the every other embodiment obtaining under creative work prerequisite, belong to the scope of protection of the invention.
Refer to Fig. 1, a kind of process flow diagram that it shows a kind of request processing method that the embodiment of the present invention provides, can comprise the following steps:
Step 101: after the first read request that Receiving Host sends, generate the second read request of RAID system, the second read request is for the hard disk reading out data from RAID system.
Be understandable that: the first read request represent main frame need to be from each hard disk of RAID system reading out data.When RAID system receives after this first read request, generate the second read request for the hard disk reading out data from RAID system.
Step 102: be the page of reading of the second read request distribution, wherein read the page for storing data corresponding to the second read request.
RAID system be the second read request divide be used in each hard disk institute return data of storage read the page, this is read the page and distributes independently data space for each hard disk, after hard disk return data, RAID system is stored in corresponding data space.
Step 103: the second read request is split into a plurality of son requests.
When the second read request is being issued on the path of hard disk, and split into a plurality of son requests, wherein split sub-request number depends on the data area that the second read request is asked.The data area that for example certain second read request is asked is 0-100, in the second read request, issue in process, the RAID layer of RAID system determines which hard disk is this data area be stored in, using the quantity of these hard disks as the quantity that splits into son request, the every height request after fractionation is respectively used to read the data in corresponding hard disk.
Concrete, request split process is according to RAID system and LUN(Logical Unit Number, logical unit number) specific object carry out, itself and existing request split identical, this embodiment of the present invention are no longer set forth to the process of request fractionation.And the mapping relations of son request and hard disk are followed mapping relations and the computing formula of each RAID level definition in RAID system, identical with hard disk mapping with existing son request, this present embodiment is no longer elaborated.
Step 104: if slow IO situation appears in any one son request, and the sub-request that occurs slow IO situation is the request of redundancy, redundancy being asked to carry out RAID system degradation reads, return to data corresponding to redundancy request, wherein the request of redundancy is asked for the son that can read return data by RAID system degradation.
In embodiments of the present invention, RAID system can comprise a timer, for recording the processing time of every height request, the processing time of group request, while surpassing threshold value there is slow IO situation in this sub-request that the RAID layer of RAID system surpasses threshold value by the determination processing time.
Further, group request, in issuing process, can be determined according to the rank of RAID system the number of redundancy request.For example, when RAID system level is RAID5 rank, in RAID system all hard disks all not during off-line all son requests be the request of redundancy, if all son requests are all irredundant son requests while having an above hard disk off-line.When RAID system level is RAID6 rank, the equal off-line or while only having a hard disk off-line not of all hard disks in RAID system, all son requests are the request of redundancy, if all son requests are all irredundant son requests while having two above hard disk off-lines, wherein irredundant son request refers to that the son that cannot read return data by RAID system degradation asks.
When RAID layer, judge son request and occur slow IO situation, and when this sub-request is the request of redundancy, RAID layer carries out RAID system degradation to it and reads, wherein to read be except this redundancy, to ask other data in hard disks corresponding hard disk by reading in RAID system for RAID system degradation, then by RAID algorithm, calculates the data that the sub-request of this redundancy need to be read.The data that wherein read in the hard disk that data in other hard disks and this redundancy ask have same memory location and length, and other hard disks are asked corresponding hard disk for splitting in all son requests that obtain except the son that described redundancy is sub asking.
For example: when RAID system level is RAID5, hard disk corresponding to its all son request is respectively disk1, disk2, disk3, now to read and on disk1, be stored in the data that position 1 length is 100, if the sub-request that disk1 is corresponding is the request of redundancy, can first read and on disk2 and disk3, be stored in the data that position 1 length is 100, again the data that read on these two dishes are carried out to parity checking, just can calculate and on disk1, be stored in the data that position 1 length is 100.
Application technique scheme, after receiving the first read request of main frame transmission, generates second read request for the hard disk reading out data from RAID system, and is that the page is read in the second read request distribution.The second read request is split into a plurality of son requests to read the data in hard disk, when slow IO situation appears in any one son request, and when the sub-request that occurs slow IO situation is the request of redundancy, in the situation that returning without this redundancy request of wait, can carry out RAID system degradation to the request of redundancy reads, return to data corresponding to redundancy request, realized the problem to there are the redundancy request fast return data of slow IO situation, solve occurring once in a while that the sub-request of slow IO cannot fast return data.After occurring that the sub-request of slow IO situation is returned, can also reclaim this sub-request, avoid this son to ask after long-time return data, main frame read request to be processed and impacted.
Further, the request processing method that the embodiment of the present invention provides is in the situation that there is slow IO in sub-request, still retain its corresponding hard disk, like this when its revert to can the slow IO of normal process hard disk time, can utilize data in this hard disk to carry out RAID system degradation to other slow dishes and read, reduce the risk that double plate lost efficacy.RAID system is reconstructed without the data to hard disk simultaneously, guarantees the IO performance of whole RAID system.
Refer to Fig. 2, it shows the another kind of process flow diagram of a kind of request processing method that the embodiment of the present invention provides, and has set forth the process of how reading return data by RAID system degradation, can comprise the following steps:
Step 201: after the first read request that Receiving Host sends, generate the second read request of RAID system, the second read request is for the hard disk reading out data from RAID system.
Step 202: be the page of reading of the second read request distribution, wherein read the page for storing data corresponding to the second read request.
Step 203: the second read request is split into a plurality of son requests.
Step 201 is to step 203: identical to step 103 with step 101, this embodiment of the present invention is no longer set forth.
Step 204: obtain every height request with respect to the off-set value of the second read request, and in every height request off-set value separately of record and the address of the second read request.
For example the start address of the second read request is lba=0, length is lenth=100, this second read request is split into two son request REQ1 and REQ2, REQ1lba=0lenth=20 wherein, REQ2lba=20lenth=100, so in these two son requests, REQ1 is 0, REQ2 with respect to the skew of the second read request REQ0 is 20 with respect to the skew of the second read request REQ0.
The every one deck splitting in RAID system due to request all can carry out, so a sub-request corresponding to hard disk may be that the second read request generates after N time splits, so need to be in the address of tearing time-sharing recording the second read request open at every turn, the in the situation that of sub-request timed out, can also pass through like this second read request of its correspondence of address search of ground two read requests, improve the search procedure of the second read request.
Step 205: if slow IO situation appears in any one son request, and the sub-request that occurs slow IO situation is the request of redundancy, by copying the field information of redundancy request, generate a new son request, wherein new son request is for reading the data of hard disk corresponding to redundancy request.
In embodiments of the present invention, RAID system comprises a timer, and for recording the processing time of every height request, this timer can be added on block device layer.The processing time of group request, while surpassing threshold value there is slow IO situation in the described son request that the RAID layer determination processing time of RAID system surpasses threshold value.When further group request has redundancy sign, determine that described son request is for the request of redundancy.Definite explanation referring in step 104 of redundancy request, is not setting forth this.
In addition block device layer, after receiving son request, has redundant marks if the sub-request receiving detected, and generates a new son request, and this new son request generates by copying all fields of redundancy request.Further this new son request mark has " fast return page replacement " mark directly to return to RADI layer with failure result, and wherein fast return page replacement is used for prompting for the second read request and redistributes and read the page.
Step 206: the address according to the second read request in new son request, finds the second read request, and be that the second read request is redistributed and read the page.
Step 207: according to hard disk corresponding to new son request and the redundancy relationship between other hard disks, the data of other hard disk corresponding positions are carried out to verification calculating, obtain data corresponding to new son request, that wherein redistributes reads the subpage frame that the page is every height request memory allocated data, and other hard disks are asked corresponding hard disk for splitting the son except redundancy is asked in all son requests that obtain.
RAID layer is received after the request that failure result returns, the mark that judges whether this request has " fast return page replacement ", if had, according to needing to carry out page replacement in request: follow according to sub-request and directly find " original read request " and apply for the address of the second new read request, find the second read request, and be that the second read request is redistributed and read the page, the page of reading that this is redistributed is every height request distribute data storage space again, this data space can be different from the data space distributing before, the data space that employing is redistributed replaces it the data space of front distribution, take that to avoid redundancy request be the data space of its distribution before taking after long-time return data, main frame cannot be determined and read which data, main frame read data is impacted, cause the waste of storage space simultaneously.
Further, RAID layer, according to hard disk corresponding to new son request and the redundancy relationship between other hard disks, carries out verification calculating to the data of other hard disk corresponding positions, obtains data corresponding to new son request, complete RADI system degradation and read, thus returning without wait timeout IO.
It should be noted is that: every height request may be read the data of certain position in hard disk, is from other hard disks, to read the data of same position carrying out that RADI system degradation reads.When carrying out verification calculating, the pre-stored redundancy relationship having between hard disk of RAID layer, therefore, after receiving new son request, can ask corresponding hard disk according to new son, find other hard disks with it with redundancy relationship from pre-stored redundancy relationship.
In addition, block device layer has after redundant marks the sub-request receiving being detected, and adds " backstage recoverys " and is tagged in the request of redundancy, and to SCSI layer, issue abort order and finish that this redundancy is sub asks.When the redundancy request with " backstage recovery " mark is back to RAID layer, RAID judges whether mark " backstage recovery " mark, if had, it is the subpage frame that the request of redundancy distributes that the page is read in directly this redundancy request, and recovery, avoids main frame read request to process and impact.
Embodiment is corresponding with said method, and the embodiment of the present invention also provides a kind of request treatment facility, and its structural representation as shown in Figure 3, can comprise: receiving element 11, allocation units 12, split cells 13 and data capture unit 14, wherein:
Receiving element 11, after the first read request sending, generates the second read request of RAID system for Receiving Host, and the second read request is for the hard disk reading out data from RAID system.
Be understandable that: the first read request represent main frame need to be from each hard disk of RAID system reading out data.When RAID system receives after this first read request, generate the second read request for the hard disk reading out data from RAID system.
When the second read request is being issued on the path of hard disk, and split into a plurality of son requests, wherein split sub-request number depends on the data area that the second read request is asked.The data area that for example certain second read request is asked is 0-100, in the second read request, issue in process, the RAID layer of RAID system determines which hard disk is this data area be stored in, using the quantity of these hard disks as the quantity that splits into son request, the every height request after fractionation is respectively used to read the data in corresponding hard disk.
Concrete, request split process is carried out according to the specific object of RAID system and LUN, and it is identical with existing request fractionation, the process that the request of no longer setting forth splits to this embodiment of the present invention.And the mapping relations of son request and hard disk are followed mapping relations and the computing formula of each RAID level definition in RAID system, identical with hard disk mapping with existing son request, this present embodiment is no longer elaborated.
There is slow IO situation in the sub-request that wherein, data capture unit 14 surpasses threshold value specifically for: determination processing time.When further group request has redundancy sign, data capture unit 14 determines that son request is for the request of redundancy.
It is by reading other data in hard disks except the corresponding hard disk of this redundancy request in RAID system, then calculating by RAID algorithm the data that the sub-request of this redundancy need to be read that RAID system degradation is read.The data that wherein read in the hard disk that data in other hard disks and this redundancy ask have same memory location and length.
For example: when RAID system level is RAID5, hard disk corresponding to all son requests is respectively disk1, disk2, disk3, now to read and on disk1, be stored in the data that position 1 length is 100, if the sub-request that disk1 is corresponding is the request of redundancy, can first read and on disk2 and disk3, be stored in the data that position 1 length is 100, again the data that read on these two dishes are carried out to parity checking, just can calculate and on disk1, be stored in the data that position 1 length is 100.
Application technique scheme, when slow IO situation appears in any one son request, and when the sub-request that occurs slow IO situation is the request of redundancy, in the situation that returning without this redundancy request of wait, can carry out RAID system degradation to the request of redundancy reads, return to data corresponding to redundancy request, realized the problem to there are the redundancy request fast return data of slow IO situation, solve occurring once in a while that the sub-request of slow IO cannot fast return data.After occurring that the sub-request of slow IO situation is returned, can also reclaim this sub-request, avoid this son to ask after long-time return data, main frame read request to be processed and impacted.
Further, in the situation that slow IO appears in sub-request, still retain its corresponding hard disk, like this when its revert to can the slow IO of normal process hard disk time, can utilize data in this hard disk to carry out RAID system degradation to other slow dishes and read, reduce the risk that double plate lost efficacy.RAID system is reconstructed without the data to hard disk simultaneously, guarantees the IO performance of whole RAID system.
On Fig. 3 basis, the request treatment facility that the embodiment of the present invention provides can further include: acquiring unit 15, as shown in Figure 4.Wherein acquiring unit 15, for obtaining every height request with respect to the off-set value of the second read request, and in every height request off-set value separately of record and the address of the second read request.
The every one deck splitting in RAID system due to request all can carry out, so a sub-request corresponding to hard disk may be that the second read request generates after N time splits, so need to the address of the second read request be recorded in son request by acquiring unit 15 when each fractionation, the in the situation that of sub-request timed out, can also pass through like this second read request of its correspondence of address search of ground two read requests, improve the search procedure of the second read request.
In the request treatment facility shown in above-mentioned Fig. 3 and Fig. 4, the structural representation of data capture unit 14 can be consulted shown in Fig. 5, can comprise: request generates subelement 141, searches subelement 142 and data acquisition subelement 143.Wherein,
Request generates subelement 141, for there is slow IO situation when any one son request, and the sub-request that occurs slow IO situation is the request of redundancy, by copying the field information of redundancy request, generate a new son request, wherein new son request is for reading the data of hard disk corresponding to redundancy request.
In embodiments of the present invention, request generates subelement 141 can be by judging whether definite son request of processing time of son request occurs slow IO situation, the processing time of group request, while surpassing threshold value there is slow IO situation in the sub-request that the request generation 141 determination processing times of subelement surpass threshold value.When further group request has redundancy sign, request generates subelement 141 and determines that son request is for the request of redundancy.
It should be noted is that: every height request may be read the data of certain position in hard disk, is from other hard disks, to read the data of same position carrying out that RADI system degradation reads.For example: son request 1 data that read in hard disk disk1 position 2, if for there is the redundancy request of slow IO situation in fruit request 1, there are the data that the disk2 of corresponding relation and disk3 can read in position 2 separately with it and carry out parity checking, calculate on disk1 and be stored in the data in position 2, complete the process that RAID system degradation is read.
In addition, the request treatment facility that the embodiment of the present invention provides can further include: recovery unit, be used for discharging the request of redundancy, and reclaim and read the subpage frame that the page is redundancy request distribution, to avoid the request of redundancy when returning to data to subpage frame, corresponding which read request of data that causes main frame to determine storing in subpage frame, impacts main frame read request.
The embodiment of the present invention also provides another kind of request treatment facility, and its structural representation can be consulted shown in Fig. 6, can comprise: data-interface 21(is not shown in FIG.), storer 22 and controller 23.
Wherein, data-interface 21 is connected with the data-interface of main frame 24 by data connection device, as forming communication link by netting twine, data-interface 21 is connected with the data-interface of main frame 24, the first read request sending with Receiving Host 24, and the first read request is sent to controller 23 by inner passage.
In embodiments of the present invention, wherein the second read request is for the hard disk reading out data from RAID system, the split sub-request number of the second read request depends on the data area that described the second read request is asked, and described in each, son request is for reading the data of corresponding hard disk.
When controller 23 generates after the second read request, in storer 22, for the page of reading of described the second read request distribution, wherein read the page for storing data corresponding to the second read request, the data that the every height request splitting into is returned are all stored in and read in the page.
It should be noted that, each embodiment in this instructions all adopts the mode of going forward one by one to describe, and each embodiment stresses is the difference with other embodiment, between each embodiment identical similar part mutually referring to.For device class embodiment, because it is substantially similar to embodiment of the method, so description is fairly simple, relevant part is referring to the part explanation of embodiment of the method.
Finally, also it should be noted that, in this article, relational terms such as the first and second grades is only used for an entity or operation to separate with another entity or operational zone, and not necessarily requires or imply and between these entities or operation, have the relation of any this reality or sequentially.And, term " comprises ", " comprising " or its any other variant are intended to contain comprising of nonexcludability, thereby the process, method, article or the equipment that make to comprise a series of key elements not only comprise those key elements, but also comprise other key elements of clearly not listing, or be also included as the intrinsic key element of this process, method, article or equipment.The in the situation that of more restrictions not, the key element being limited by statement " comprising ... ", and be not precluded within process, method, article or the equipment that comprises described key element and also have other identical element.
While for convenience of description, describing above device, with function, being divided into various unit describes respectively.Certainly, when enforcement is of the present invention, the function of each unit can be realized in same or a plurality of software and/or hardware.
As seen through the above description of the embodiments, those skilled in the art can be well understood to the mode that the present invention can add essential general hardware platform by software and realizes.Understanding based on such, the part that technical scheme of the present invention contributes to prior art in essence in other words can embody with the form of software product, this computer software product can be stored in storage medium, as ROM/RAM, magnetic disc, CD etc., comprise that some instructions are with so that a computer equipment (can be personal computer, server, or the network equipment etc.) carry out the method described in some part of each embodiment of the present invention or embodiment.
Above a kind of request processing method provided by the present invention and equipment are described in detail, applied specific case herein principle of the present invention and embodiment are set forth, the explanation of above embodiment is just for helping to understand method of the present invention and core concept thereof; , for one of ordinary skill in the art, according to thought of the present invention, all will change in specific embodiments and applications, in sum, this description should not be construed as limitation of the present invention meanwhile.
Claims (12)
1. a request processing method, is characterized in that, comprising:
After the first read request that Receiving Host sends, generate the second read request of individual disc redundancy array system, described the second read request is for the hard disk reading out data from described individual disc redundancy array system;
For the page of reading of described the second read request distribution, the wherein said page of reading is for storing data corresponding to described the second read request;
Described the second read request is split into a plurality of son requests, and wherein split sub-request number depends on the data area that described the second read request is asked, and described in each, son request is for reading the data of corresponding hard disk;
If described in any one there is slow IO situation in son request, and the described son request that occurs slow IO situation is the request of redundancy, described redundancy being asked to carry out individual disc redundancy array system degradation reads, return to data corresponding to described redundancy request, the request of wherein said redundancy is for asking by individual disc redundancy array system of reading return data of demoting.
2. method according to claim 1, it is characterized in that, described method also comprises: obtain described in each son request with respect to the off-set value of described the second read request, and described in each off-set value separately of record and the address of described the second read request in son request.
3. method according to claim 2, is characterized in that, described redundancy is asked to carry out individual disc redundancy array system degradation and read, and returns to data corresponding to described redundancy request, comprising:
By copying the field information of described redundancy request, generate a new son request, wherein said new son request is for reading the data of hard disk corresponding to described redundancy request;
Address according to the second read request described in described new son request, finds described the second read request, and redistributes and read the page for described the second read request;
According to hard disk corresponding to described new son request and the redundancy relationship between other hard disks, the data of described other hard disk corresponding positions are carried out to verification calculating, obtain data corresponding to described new son request, that wherein redistributes reads the page for the subpage frame of son request memory allocated data described in each, and other hard disks are asked corresponding hard disk for splitting the son except the request of described redundancy in all son requests that obtain.
4. according to the method described in claims 1 to 3 any one, it is characterized in that, there is slow IO situation in the described son request that the determination processing time surpasses threshold value.
5. method according to claim 4, is characterized in that, determines that having the described sub of redundancy sign asks as the request of redundancy.
6. according to the method described in claims 1 to 3 any one, it is characterized in that, described method also comprises:
Discharge the sub-request of described redundancy, and described in reclaiming, read the subpage frame that the page is described redundancy request distribution.
7. a request treatment facility, is characterized in that, comprising:
Receiving element, after the first read request sending, generates the second read request of individual disc redundancy array system for Receiving Host, and described the second read request is for the hard disk reading out data from described individual disc redundancy array system;
Allocation units, are used to the page of reading that described the second read request distributes, and the wherein said page of reading is for storing data corresponding to described the second read request;
Split cells, for described the second read request being split into a plurality of son requests, wherein split sub-request number depends on the data area that described the second read request is asked, described in each, son request is for reading the data of corresponding hard disk;
Data capture unit, if there is slow IO situation for son request described in any one, and the described son request that occurs slow IO situation is the request of redundancy, described redundancy is asked to carry out individual disc redundancy array system degradation to be read, return to data corresponding to described redundancy request, the request of wherein said redundancy is for asking by individual disc redundancy array system of reading return data of demoting.
8. equipment according to claim 7, it is characterized in that, described equipment also comprises: acquiring unit, for obtaining described in each son request with respect to the off-set value of described the second read request, and described in each off-set value separately of record and the address of described the second read request in son request.
9. equipment according to claim 8, is characterized in that, described data capture unit, comprising:
Request generates subelement, for there is slow IO situation when son request described in any one, and when the described son request that occurs slow IO situation is asked for redundancy, by copying the field information of described redundancy request, generate a new son request, wherein said new son request is for reading the data of hard disk corresponding to described redundancy request;
Search subelement, for according to the address of described second read request of described new son request, find described the second read request, and redistribute and read the page for described the second read request;
Data acquisition subelement, for asking corresponding hard disk and the redundancy relationship between other hard disks according to described new son, the data of described other hard disk corresponding positions are carried out to verification calculating, obtain data corresponding to described new son request, that wherein redistributes reads the page for the subpage frame of son request memory allocated data described in each, and other hard disks are asked corresponding hard disk for splitting the son except the request of described redundancy in all son requests that obtain.
10. according to the equipment described in claim 7 to 9 any one, it is characterized in that, there is slow IO situation in the described son request that described data capture unit surpasses threshold value specifically for: determination processing time.
11. equipment according to claim 10, is characterized in that, described data capture unit further specifically for: determine that the described son request with redundancy sign is the request of redundancy.
12. according to the equipment described in claim 7 to 9 any one, it is characterized in that, described equipment also comprises: recovery unit, for discharging the sub-request of described redundancy, and described in reclaiming, read the subpage frame that the page is described redundancy request distribution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310687352.4A CN103699340B (en) | 2013-12-16 | 2013-12-16 | A kind of request processing method and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310687352.4A CN103699340B (en) | 2013-12-16 | 2013-12-16 | A kind of request processing method and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103699340A true CN103699340A (en) | 2014-04-02 |
| CN103699340B CN103699340B (en) | 2016-12-07 |
Family
ID=50360881
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310687352.4A Active CN103699340B (en) | 2013-12-16 | 2013-12-16 | A kind of request processing method and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103699340B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106534242A (en) * | 2015-09-14 | 2017-03-22 | 阿里巴巴集团控股有限公司 | Processing method and device for requests in distributed system |
| WO2017114232A1 (en) * | 2015-12-30 | 2017-07-06 | 华为技术有限公司 | Data reading method, raid controller, and storage device |
| CN110727401A (en) * | 2019-09-09 | 2020-01-24 | 无锡江南计算技术研究所 | Memory access system |
| CN110896415A (en) * | 2019-11-22 | 2020-03-20 | 浪潮电子信息产业股份有限公司 | Data readdir method, system, equipment and computer medium |
| CN116661708A (en) * | 2023-07-31 | 2023-08-29 | 苏州浪潮智能科技有限公司 | Processing method of read-write task based on hard disk array and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101055557A (en) * | 2006-04-13 | 2007-10-17 | 国际商业机器公司 | Data processing system and method |
| CN101657802A (en) * | 2006-12-06 | 2010-02-24 | 弗森多系统公司（dba弗森-艾奥） | The device, the system and method that are used for long-range direct memory access (DMA) solid storage device |
| US20110202929A1 (en) * | 2010-02-16 | 2011-08-18 | Stephen Schleimer | Method and system for parallelizing database requests |
| US20120173725A1 (en) * | 2010-12-30 | 2012-07-05 | International Business Machines Corporation | Distributed topology enabler for identity manager |
-
2013
- 2013-12-16 CN CN201310687352.4A patent/CN103699340B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101055557A (en) * | 2006-04-13 | 2007-10-17 | 国际商业机器公司 | Data processing system and method |
| CN101657802A (en) * | 2006-12-06 | 2010-02-24 | 弗森多系统公司（dba弗森-艾奥） | The device, the system and method that are used for long-range direct memory access (DMA) solid storage device |
| US20110202929A1 (en) * | 2010-02-16 | 2011-08-18 | Stephen Schleimer | Method and system for parallelizing database requests |
| US20120173725A1 (en) * | 2010-12-30 | 2012-07-05 | International Business Machines Corporation | Distributed topology enabler for identity manager |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106534242A (en) * | 2015-09-14 | 2017-03-22 | 阿里巴巴集团控股有限公司 | Processing method and device for requests in distributed system |
| WO2017114232A1 (en) * | 2015-12-30 | 2017-07-06 | 华为技术有限公司 | Data reading method, raid controller, and storage device |
| CN106933495A (en) * | 2015-12-30 | 2017-07-07 | 华为技术有限公司 | A kind of method for reading data, RAID controller and storage device |
| CN106933495B (en) * | 2015-12-30 | 2019-07-23 | 华为技术有限公司 | A kind of method for reading data, RAID controller and storage equipment |
| CN110727401A (en) * | 2019-09-09 | 2020-01-24 | 无锡江南计算技术研究所 | Memory access system |
| CN110896415A (en) * | 2019-11-22 | 2020-03-20 | 浪潮电子信息产业股份有限公司 | Data readdir method, system, equipment and computer medium |
| CN110896415B (en) * | 2019-11-22 | 2022-05-24 | 浪潮电子信息产业股份有限公司 | Data readdir method, system, equipment and computer medium |
| CN116661708A (en) * | 2023-07-31 | 2023-08-29 | 苏州浪潮智能科技有限公司 | Processing method of read-write task based on hard disk array and electronic equipment |
| CN116661708B (en) * | 2023-07-31 | 2023-11-03 | 苏州浪潮智能科技有限公司 | Processing method of read-write task based on hard disk array and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103699340B (en) | 2016-12-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10210045B1 (en) | Reducing concurrency bottlenecks while rebuilding a failed drive in a data storage system | |
| US10126988B1 (en) | Assigning RAID extents and changing drive extent allocations within RAID extents when splitting a group of storage drives into partnership groups in a data storage system | |
| US9851909B2 (en) | Intelligent data placement | |
| US8612678B2 (en) | Creating logical disk drives for raid subsystems | |
| US8239584B1 (en) | Techniques for automated storage management | |
| CN103064765B (en) | Data reconstruction method, device and cluster storage system | |
| US8495295B2 (en) | Mass storage system and method of operating thereof | |
| CN105487823A (en) | Data migration method and device | |
| CN102981927A (en) | Distribution type independent redundant disk array storage method and distribution type cluster storage system | |
| CN103699340A (en) | Request processing method and equipment | |
| WO2017173623A1 (en) | Method and storage device for processing stripes in storage device | |
| US10324794B2 (en) | Method for storage management and storage device | |
| US8868877B2 (en) | Creating encrypted storage volumes based on thin-provisioning mode information | |
| US10678643B1 (en) | Splitting a group of physical data storage drives into partnership groups to limit the risk of data loss during drive rebuilds in a mapped RAID (redundant array of independent disks) data storage system | |
| WO2016107167A1 (en) | Storage architecture creation method, storage access method and storage system | |
| CN103534688A (en) | Data recovery method, storage equipment and storage system | |
| CN103577115B (en) | Arrangement processing method, device and the server of data | |
| CN101840364A (en) | Method for recovering data and storage device thereof | |
| CN102077175A (en) | Method and system for execution of applications in conjunction with distributed raid | |
| CN107729536A (en) | A kind of date storage method and device | |
| CN103530206B (en) | A kind of method and apparatus of date restoring | |
| CN106462481A (en) | Duplicate data using cyclic redundancy check | |
| US20200341873A1 (en) | Data access method, apparatus and computer program product | |
| CN102226892A (en) | Disk fault tolerance processing method and device thereof | |
| CN104932830A (en) | Information processing method and electronic device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |