CN114610244A

CN114610244A - Method, system and equipment for degrading independent redundant disk array

Info

Publication number: CN114610244A
Application number: CN202210301609.7A
Authority: CN
Inventors: 吴睿振; 陈静静; 张旭; 张永兴; 王凛
Original assignee: Shandong Yunhai Guochuang Cloud Computing Equipment Industry Innovation Center Co Ltd
Current assignee: Shandong Yunhai Guochuang Cloud Computing Equipment Industry Innovation Center Co Ltd
Priority date: 2022-03-25
Filing date: 2022-03-25
Publication date: 2022-06-10

Abstract

The invention provides a method, a system and equipment for degrading an independent redundant disk array, which comprise the following steps: transforming the relationship of TP-RAID to RAID6 degradation, so that the degraded check data is reserved as a designated check code combination p1p2 when any check disk is extracted; updating a check relation, firstly considering the check relation degradation of TP-RAID to RAID6 under the condition of no load balancing requirement to obtain a data and check relational expression, and then obtaining the degraded relational expression of RAID6 under the condition of considering the degraded operational relation, wherein a check block P3 which is abstracted in the operation is directly determined by a host machine in a manner of being decoupled from the actual degradation operation based on the degradation requirement, and the operation is started; updating data change caused by load balance position change, adjusting arrangement of the RAID without load balance based on load balance according to a relational expression of the degraded RAID6, updating the encoding and decoding conditions to obtain a RAID6 group, and adjusting the position of data and/or the position of check codes. The invention reduces the complexity of the operation.

Description

Method, system and equipment for degrading independent redundant disk array

Technical Field

The invention relates to the technical field of data storage, in particular to the technical field of Redundant Array of Independent Disks (RAID), and specifically relates to a technology for degrading a Redundant Array of Independent Disks (RAID), in particular to a technology for degrading a TP-RAID to RAID 6.

Background

With the rapid development of communication technology and network technology, the digital information is exponentially and explosively increased, and the data storage technology is also greatly challenged. The reliability of data in memory systems and the power consumption of memory systems are of increasing concern. Now facing such a huge data scale, the reliability of data in a storage system is inversely proportional to the number of components contained in the storage system, i.e. the greater the number of components of the storage system, the lower the reliability of data in the storage system. According to related research, about 30 disks are damaged every month in an internet data center consisting of 600 disks, and data reliability reduction caused by disk failure is a serious problem in a large-scale storage system, and researches on related fault-tolerant technologies have been carried out.

In 1988, RAID architecture proposed by professor d.a. patterson et al of berkeley division of university of california became a key technology for increasing storage space, and RAID (redundant Arrays of Independent disks) is a disk array with redundancy capability, which is obtained by combining a plurality of Independent disks to obtain a disk group with huge capacity. By adopting the RAID storage technology, the storage capacity can be greatly improved, the input and output request processing capacity of the system is improved, and the reliability of data is improved by the distributed storage technology of data, a parallel access means and an information redundancy technology.

RAID design has been proposed and rapidly accepted by the industry, and RAID technology is now widely used in production and life as a high-performance and high-reliability storage technology. The RAID mainly uses data striping, data check, and mirroring techniques to obtain higher performance, higher reliability, better fault-tolerance capability, and higher scalability. The strategies and architectures of these three techniques may be applied or combined according to different data application requirements, so RAID may be divided into different levels according to different strategies and architectures: RAID0, 1, 5, 6, 10.

Among them, RAID0 is the earliest RAID mode, i.e., Data striping technology. RAID0 is the simplest form in the disk array, only needs more than 2 hard disks, has low cost, and can improve the performance and the throughput of the whole disk. RAID0 does not provide redundancy or error repair capability but the implementation cost is the lowest.

The simplest implementation of RAID0 is to concatenate N identical hard disks together in hardware via an intelligent disk controller or in software using a disk driver in an operating system to create a large volume set. When in use, the computer data are written into each hard disk in sequence, and the biggest advantage is that the capacity of the hard disk can be improved by a whole time. If three 80GB hard disks are used to form a RAID0 mode, the disk capacity is 240 GB. The speed of the hard disk drive is identical to that of a single hard disk. The biggest defect is that any hard disk fails, the whole system is damaged, and the reliability is only 1/N of that of a single hard disk.

The RAID 1 is called disk mirroring, and the principle is to mirror data of one disk to another disk, that is, data is written into one disk, and a mirror image file is generated on another idle disk, so that the reliability and the repairability of the system are ensured to the maximum extent without affecting the performance, as long as at least one disk in any pair of mirror image disks in the system can be used, and even when half of the hard disks have a problem, the system can normally operate, and when one hard disk fails, the system ignores the hard disk, and uses the remaining mirror image disks to read and write data instead, and has a good disk redundancy capability. Although this is absolutely safe for data, the cost is also significantly increased, with a 50% disk utilization and only 160GB of disk space available for four 80GB capacity disks. In addition, the RAID system with the hard disk failure is no longer reliable, and the damaged hard disk should be replaced in time, otherwise the remaining mirror image disks are also problematic, and the entire system may crash. The original data can need to be mirrored synchronously for a long time after the new disk is replaced, and the access to the data from the outside is not influenced, but the performance of the whole system is reduced at the moment. Therefore, RAID 1 is often used in situations where critically important data is preserved.

RAID5 (distributed parity independent disk architecture). Its parity code exists on all disks, with p0 representing the parity value for stripe 0, and the other meanings are the same. RAID5 has high read efficiency and general write efficiency, and block type collective access efficiency is good. Because the parity codes are on different disks, reliability is improved. It does not solve well for the parallelism of the data transfer and the design of the controller is rather difficult. For RAID5, most data transfers operate on only one disk, and parallel operations may be performed. There is a "write penalty" in RAID5, i.e., each write operation will result in four actual read/write operations, where the old data and parity information is read twice and the new data and parity information is written twice.

RAID6 is a parity-check code independent disk architecture with two types of distributed storage. The method is an extension of RAID5 and is mainly used for occasions requiring that data can not be mistaken absolutely. Due to the introduction of the second parity check value, N +2 disks are needed, and the design of the controller becomes very complicated, so that the data reliability of the disk array is further improved. More space is required to store the check value with a higher performance penalty in write operations.

RAID technology is widely used in distributed storage servers today, and RAID5 and RAID6 can recover one or two error blocks respectively, but each data recovery is still limited by the speed limit of reading a large amount of data from each disk.

Therefore, in order to solve the above drawbacks and problems in the prior art, it is necessary to provide an optimized RAID degradation method, which simplifies the operation as much as possible and improves the degradation efficiency.

Disclosure of Invention

In view of the above, the present invention provides an improved RAID degrading method, system and device, so as to solve the problems of complex operation and low efficiency in the prior art.

In view of the above objects, in one aspect, the present invention provides a method for degrading an raid, wherein the method includes the following steps:

transforming the relationship of TP-RAID to RAID6 degradation, so that the degraded check data are all reserved as a designated check code combination p1p2 under the condition of extracting any check disk;

updating a check relation, wherein a relational expression of data and check is obtained by considering the check relation degradation of TP-RAID to RAID6 under the condition of no load balancing requirement, and then a relational expression of RAID6 after degradation is obtained under the condition of considering the operation relation of degradation, wherein a check block p3 which is extracted in the operation is determined by a host (host) directly in a manner of decoupling from the actual degradation operation based on the degradation requirement, and the operation is started;

updating data change caused by load balance position change, adjusting arrangement of the RAID without load balance based on load balance according to a relational expression of the degraded RAID6, updating the encoding and decoding conditions to obtain a RAID6 group, wherein the position of the data and/or the position of the check code are adjusted.

In some embodiments of the method for degrading an array of independent redundant disks according to the present invention, transforming the relationship of degrading the TP-RAID to the RAID6, so that the degraded parity data is retained as a specified combination when any parity disk is extracted, further includes:

the relationship of degradation is expressed based on the following formula, wherein:

TP-RAID:

x≥2 (4)

and

RAID6:

wherein d is₁-d_aRepresenting a block of data, p₁、p₂、p₃Three check codes, p, representing TP-RAID₁' and p₂' the check code of RAID6 obtained by re-operation after the load balancing related operation is completed after the destaging operation, a represents the number of user data disks.

In some embodiments of the raid demotion method according to the present invention, the updating the check relationship further includes:

and (3) obtaining a relational expression of data and check by considering the checking relation degradation from TP-RAID to RAID6 under the condition of no load balancing requirement based on the following formula:

x≥2(6)

the first half part of the formula represents parameters and operational relations which need to be met by data information, and the relations are determined based on load balancing requirements; the second half part of the formula represents parameters and operational relations which need to be met by the check information, different m, n and o relations are corresponded based on different load balancing requirements, and m, n and o respectively correspond to the positions of the check codes in the strip under load balancing, wherein

Indicating an exclusive or operation and k indicating the number of user data disks actually used.

the relational expression of degraded RAID6 is obtained in consideration of the degraded operational relationship based on the transformation of the above equation (6) and the following equation:

expressions in which operational variations of check code combinations p1p2 through p1 'p 2' are considered

Wherein, the delta p1 and the delta p2 are the added difference needed for directly operating from p1p2 to p1 'p 2', and the difference is obtained

Based on (11) the encoding of Δ p1 and Δ p2 was accomplished using p3, it was found that

Wherein the parameter values of m, n, o are determined by the host (host) and the operation is started.

In some embodiments of the raid demotion method according to the present invention, the updating the check relationship further includes: and obtaining a check code value for reducing the TP-RAID arranged under the existing load balancing condition to RAID6 through delta p1 and delta p2, wherein the check code value is calculated based on the following formula:

in some embodiments of the raid demotion method according to the present invention, the updating the data change caused by the load balancing location change further comprises:

based on the degraded RAID6:

wherein, P1 'and P2' are encoding relations meeting RAID6 under the current structure, and m and n represent position parameters meeting a load balancing algorithm under TP-RAID.

In some embodiments of the raid demotion method according to the present invention, the updating the data change caused by the load balancing location change further comprises: the position of the data is adjusted, wherein equation (14) is updated as:

d1 'and d 2' are data information meeting load balancing requirements after position updating, and corresponding checks meeting load balancing are p1 "and p 2", and m and n represent positions where the checks are located.

In some embodiments of the raid demotion method according to the present invention, the updating the data change caused by the load balancing location change further comprises: the positions of all data and the positions of all check codes are adjusted, wherein the positions of the data are first adjusted based on formula (15), and then the check data are updated and shifted based on the positions involved in the new load balancing based on the following formula:

wherein p1 'and p 2' are verification information updated by data migration, p1_m"and p2_m"is the verification information after the verification position change, m and n are the original verification positions, and m 'and n' are the verification positions after the load balancing adjustment.

In another aspect of the present invention, a system for degrading an array of independent redundant disks is further provided, which includes:

the system comprises a degradation relation transformation module, a data analysis module and a data analysis module, wherein the degradation relation transformation module is configured to transform the relation from TP-RAID to RAID6 degradation, so that the degraded verification data are reserved as a designated verification code combination p1p2 under the condition that any verification disk is extracted;

a check relation updating module configured to update a check relation, wherein a data and check relation expression is obtained by considering the check relation degradation from TP-RAID to RAID6 under the condition of no load balancing requirement, and then a degraded relation expression of RAID6 is obtained under the condition of considering degraded operational relation, wherein a check block p3 extracted during operation is directly determined by a host (host) in a manner of being decoupled from an actual degradation operation based on the degradation requirement, and operation is started;

and the data change updating module is configured to update data changes caused by load balance position changes, and update the encoding and decoding conditions of the RAID without load balance based on load balance adjustment arrangement according to the relational expression of the degraded RAID6 to obtain a RAID6 group, wherein the positions of the data and/or the positions of the check codes are adjusted.

In still another aspect of the present invention, there is also provided a computer-readable storage medium storing computer program instructions, which when executed, implement any of the above methods for degrading raid according to the present invention.

In still another aspect of the present invention, there is also provided a computer apparatus including a memory and a processor, the memory storing a computer program, the computer program being executed by the processor to perform any one of the above-mentioned methods for degrading an raid according to the present invention.

The invention has at least the following beneficial technical effects: according to the rapid and simple scheme for degrading the TP-RAID to the RAID6 provided by the invention, different work related to degradation operation is firstly split, a complex scene is simplified, and respective solutions are provided for different scenes.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other embodiments can be obtained by using the drawings without creative efforts.

In the figure:

FIG. 1 is a schematic diagram illustrating the degradation of a TP-RAID to RAID6 without regard to load requirements according to an embodiment of the RAID degradation method of the present invention;

FIG. 2 is a schematic diagram illustrating load balancing based adjustment of destaging for an embodiment of a RAID destaging method in accordance with the present invention;

FIG. 3 is a schematic block diagram illustrating an embodiment of a RAID destaging method in accordance with the present invention;

FIG. 4 illustrates a schematic block diagram of an embodiment of a RAID destaging system in accordance with the present invention;

FIG. 5 is a schematic diagram illustrating an embodiment of a computer-readable storage medium to implement a RAID destaging method in accordance with the present invention;

fig. 6 is a hardware configuration diagram of an embodiment of a computer device implementing a redundant array of independent disks demotion method according to the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the following embodiments of the present invention are described in further detail with reference to the accompanying drawings.

It should be noted that all expressions using "first" and "second" in the embodiments of the present invention are used for distinguishing two non-identical entities with the same name or different parameters, and it is understood that "first" and "second" are only used for convenience of expression and should not be construed as limiting the embodiments of the present invention. Furthermore, the terms "comprises" and "comprising," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements does not include all of the other steps or elements inherent in the list.

The traditional RAID group has RAID of different combinations of RAID0, 1, 5, 6, etc., but with the development of technology, users have higher requirements on the amount of stored data and the performance of silent recovery, which requires that only conceptualized TP-RAID is put into practical use formally before. TP-RAID (Triple-RAID) is a RAID algorithm (with check codes p1, p2 and p3) which is based on RAID5 and 6 and is subjected to check expansion by using a similar algorithm to achieve three checks. The core of the TP-RAID is that in addition to being capable of three checks, upgrading from RAID5, 6 to TP-RAID upwards and downgrading from TP-RAID to RAID5, 6 can be achieved. Since the TP-RAID checking algorithm is much more complex than RAID5, 6, and the codec calculations to calculate the checks or recovery from errors are also much more complex. Therefore, the TP-RAID of the three-check can only be solved by a matrix inversion method or a ternary linear equation method in a similar erasure correcting mode, and the solving complexity is high, the time loss is large, and the calculation power loss is also large. Therefore, the invention provides a rapid and simple degradation scheme aiming at the operation of degrading TP-RAID to RAID6, and compared with the algorithm of coding and decoding, the invention is much simpler and can achieve the advantage of simplifying operation.

After completion of the RAID group, the RAID group may need to be downgraded based on the needs of the user. The demotion refers to that the existing well-organized RAID group is descended by one or two levels, the position where the check data is originally stored is vacated, and the vacation of the hard disk is realized for use as other functional requirements. The present invention is directed to a downgrade operation of TP-RAID to RAID 6. To illustrate the present invention, the algorithmic relationship that RAID6 and TP-RAID need to follow is first described.

The algorithm principle of RAID6 is:

wherein, d1 (d)₁)、d2(d₂)、d3(d₃)…da(d_a) User data disc representing participation in

encodingData

1, 2, 3 … a in (1). d denotes the data disk data, 1, 2, 3 … a denotes its number, and different numbers denote disk numbers landed on different disks in different stripes.

Concerning p1 (p)₁)、p2(p₂)、p3(p₃) Where p denotes a parity (parity), which is a parity value generated by user data encoding for data protection of RAID. Different RAID levels have different RAID protection check code numbers, wherein only one RAID5 is provided, so that the number is p1, two RAID6 are provided, so that the number is p1p2, and similarly, the TP-RAID is provided with three check codes p1p2p 3. In the illustrated RAID group, n check code values are provided under the same stripe, denoted as p1 through pn.

The coding and decoding algorithm of RAID is to solve the above relation equation with p as unknown number. The operation here uses galois field operation in storage, so it can be known that in conventional RAID6, p has the following relations:

RAID6:

in a storage system, in order to reduce the operation complexity and ensure that data does not overflow, the above unified and stored encoding and decoding operations are generally implemented by galois fields. That is, in the hardware implementation, the addition and subtraction can be implemented by exclusive or operation, and the multiplication and division can be implemented by galois multiplication and division for different galois field polynomials, which is not described in detail herein.

Based on the above-mentioned operation requirement of upgrading the RAID6 to the TP-RAID and degrading the TP-RAID to the RAID6, it can be obtained that the obtained TP-RAID needs to satisfy the following algorithm relationship on the premise of the formulas (1) and (2):

TP-RAID:

x≥2

(3)

as shown in formula (3), the formulas in the first two rows respectively correspond to preconditions compatible with RAIDs 5 and 6 respectively after one check is added to meet the requirements of TP-RAID, and the formulas in the third row construct solvable relations based on vandermonde using similar principles, where x is a power, and the power is greater than or equal to 2 in order to meet the requirements of vandermonde construction.

When the TP-RAID is degraded to RAID6, corresponding to any one of the three checks, RAID6 is formed. Although the extraction behavior is any check disk extracted, based on formula (1), it can be seen that the remaining check needs to be in accordance with the relationship between p1 and p2 in formula (1), and therefore, no matter any check disk is extracted, the finally degraded check data needs to be changed to p1p2 in formula (1).

Based on the above requirements, it can be known that a parity disk extracted by a user cannot be guaranteed to be a certain parity under TP-RAID, and a final degradation result needs to be p1p2, so that the conventional operation method needs to perform operation again to meet the condition.

To this end, in a first aspect of the present invention, a Redundant Array of Independent Disks (RAID) destaging method 100 is provided. FIG. 3 is a schematic block diagram illustrating an embodiment of a RAID destaging method in accordance with the present invention. In the embodiment shown in fig. 1, the method comprises:

step S110: transforming the relationship of TP-RAID to RAID6 degradation, so that the degraded check data are all reserved as a designated check code combination p1p2 under the condition of extracting any check disk;

step S120: updating a check relation, wherein a relational expression of data and check is obtained by considering the check relation degradation of TP-RAID to RAID6 under the condition of no load balancing requirement, and then a relational expression of RAID6 after degradation is obtained under the condition of considering the operation relation of degradation, wherein a check block p3 which is extracted in the operation is determined by a host (host) directly in a manner of decoupling from the actual degradation operation based on the degradation requirement, and the operation is started;

step S130: updating data change caused by load balance position change, adjusting arrangement of the RAID without load balance based on load balance according to a relational expression of the degraded RAID6, updating the encoding and decoding conditions to obtain a RAID6 group, wherein the position of the data and/or the position of the check code are adjusted.

In summary, in view of the above problems in the prior art, the method according to the present invention mainly consists in transforming the relationship of degrading TP-RAID to RAID6, updating the check relationship, and updating the data change caused by the location change of load balancing. The actual implemented TP-RAID may check at different locations for load balancing requirements. In order to satisfy the requirement that no matter how to extract a disk when degradation from TP-RAID to RAID6 is completed, the reserved RAID6 should satisfy the requirement that P3 is extracted in an actual operation relationship, and only RAID6 composed of check code combinations P1P2 is reserved, first, the relationship from TP-RAID to RAID6 degradation in step S110 is transformed, so that the degraded check data is reserved as the designated check code combinations P1P2 when any check disk is extracted.

Based on step S110, when the destage operation from the TP-RAID to the RAID6 is normally completed, a new RAID6 structure meeting load balancing needs to be considered, and all the corresponding p1 'and p 2' need to be re-operated based on the new load balancing structure, which results in a large operation loss and high complexity in the standard flow manner. Therefore, to improve the operation structure, the checking relationship is updated in step S120, in which the relational expression of data and checks is obtained by first degrading the checking relationship from TP-RAID to RAID6 under the condition of no load balancing requirement, and then the relational expression of degraded RAID6 is obtained under the condition of degraded operation relationship, wherein the check block P3 which is abstracted from the operation is determined directly by the host (host) in a manner of decoupling from the actual degrading operation based on the degrading requirement, and the operation is started.

Based on the above operations, the relationship of the degraded RAID6 has been derived to meet the aforementioned relationship requirements. On this basis, in step S130, data changes caused by load balancing location changes are updated, and according to the relational expression of the degraded RAID6, the RAID without load balancing is arranged based on load balancing adjustment, and the encoding and decoding conditions are updated, so that a RAID6 group is obtained, where the location of data and/or the location of check codes are adjusted.

Further, the invention starts from the verified characteristic, and improves the verified characteristic in the following specific way:

1. transforming TP-RAID degraded relation

The actual implemented TP-RAID may check that the data falls on different positions for the requirement of load balancing, and for the case of formula (1), in actual implementation, the formula relationship may be expressed as:

TP-RAID：

x≥2 (4)

wherein d is₁-d_aRepresenting a block of data, p₁、p₂、p₃Three check codes, p, representing TP-RAID₁' and p₂' the check code of RAID6 obtained by recalculating load balancing related operations after the destaging operation is completed, and a represents the number of user data disks.

1, 2, 3, 4, … (a +3) in formula (4): representing the parameters of the encoding. In order to form a RAID group, it is necessary that the check code added thereto is decodable, and thus the establishment of the formula requires a parameter. This parameter is generally related to the load balancing algorithm of the RAID group, for example, the disk dropping situation of the first stripe is d1d2d3p1p2, and their corresponding parameters are 12345, where a is 3 and a is the number of user data disks. The second stripe may be arranged as p1p2d1d2d3, and the parameters corresponding to p1p2 are 1 and 2, respectively, and so on.

x represents the power of the formula and can take other natural numbers larger than 2, such as 2, 3, 4 and the like.

Based on the above analysis, in the case of load balancing, no matter how the disk is extracted when the degradation from TP-RAID to RAID6 is completed, the reserved RAID6 should satisfy the condition that p3 is extracted in the actual operation relationship, and only RAID6 composed of check code p1p2 is reserved, and the TP-RAID in formula (4) is targeted. At this time, if the successful downgrade is completed, the resulting RAID6 should satisfy equation (5): RAID6:

p in formula (5)₁' and p₂' after the destage operation, the load balancing related operation is completed, and the two check codes of the obtained RAID6 are recalculated, wherein the relationship of the two check codes should meet the requirement of the formula (5).

2. Updating check relationships

Based on the first step, when the TP-RAID to RAID6 downgrade operation is normally completed, a new RAID6 structure meeting load balance needs to be considered, and all p are corresponding₁’、p₂' re-operation is required based on a new load balancing structure, and the standard flow method causes great operation loss and high complexity.

To improve this operation structure, the present invention first assumes that there is no load balancing requirement, and only considers the verification relationship degradation from TP-RAID to RAID6, the relationship can be expressed as:

x≥2 (6)

the relation between data and verification is separately expressed, the left half part in the formula (6) expresses parameters and operation relation which need to be met by data information, and the relation is determined based on load balancing requirement; the right half part of the formula represents parameters and operational relations which need to be met by the check information, different m, n and o relations exist based on different load balancing requirements, and m, n and o respectively correspond to the positions of the check codes in the strip under load balancing, wherein the positions of the check codes in the strip are the positions of the check codes in the strip under load balancing

Considering the degraded operation relationship, if the parity of RAID6 obtained after the degradation is expressed as p1p2, the following should be obtained according to the expression of the above formula (6):

considering the difference between the degraded operation and equations (6) and (7), based on the relation of the exclusive or operation, the rewrite to equation (6) can be obtained as:

x≥2 (8)

considering the operational variations of the check code combinations p1p2 to p1 'p 2', one can obtain:

here, Δ p1 and Δ p2 can be considered as the difference required to be increased by directly performing the operation from p1p2 to p1 'p 2'. If the difference is available, the degraded parity code can be updated directly without re-operation based on equation (7).

Considering the relationship between Δ p1 and Δ p2 below, based on the observation and modification of equations (7) (8), it can be found that:

a summary of the results obtained for equation (10) can be expressed as:

m, n, and o are the above parameter values respectively, and correspond to the positions of the check codes in the stripe under load balancing, for example, p1p2p3 is at 2, 3, and 4 positions in the stripe respectively, so that m is 2, n is 3, and o is 4.

As can be seen from the observation of equation (11), which satisfies the operation formula of RAID6 for Δ p1, Δ p2 and p3, it can be assumed that equation (11) is to complete the encoding work of Δ p1 and Δ p2 by using p3, that is, the solution of Δ p1 and Δ p2 can be completed by applying the equation of RAID6, and the relationship is satisfied:

as can be seen from equation (12), p3 is a check block actually extracted during actual destaging operation regardless of the operation performed by the user based on the destaging requirement, so that the data can be determined directly by the host (host) and the operation can be started regardless of the actual destaging operation. The m, n and o are determined based on the load balancing algorithm, so that the parameter values of the m, n and o can be determined in advance by a host (host) and the operation can be started no matter how the actual operation is.

Finishing the operation of Δ p1 and Δ p2, that is, obtaining a check code value reduced to RAID6 based on TP-RAID arranged under the existing load balancing condition through Δ p1 and Δ p2, wherein the calculation method is as follows:

as described above, the complex encoding and decoding operations in the original method are replaced by the operations, and the data reading amount only needs three data blocks of p1, p2 and p 3. Taking the TP-RAID algorithm with the data volume of 29 and the check block of 3 as an example, in the encoding process of generating the new RAID6, the data reading volume is reduced from 29 to 3, and the speed is increased by 9.7 times.

3. Updating data changes caused by load balancing location changes

Based on the above operations, we have obtained a degraded RAID6 whose relationship satisfies:

here, P1 'and P2' are encoding relationships satisfying RAID6 in the current configuration, and m and n represent location parameters satisfying the load balancing algorithm in the previous TP-RAID. The structure embodied in detail may be exemplified as shown in fig. 1.

As shown in fig. 1, 1 in fig. 1 is the case of TP-RAID after load balancing satisfying left-hand misalignment, and 2 is the degraded operation, where disk number 4 (dotted line portion) is extracted for other applications.

In fig. 1, in order to implement the destage operation, the operations of the parts (1) and (2) of the present invention are first used, and it is known that, according to the method of the present invention, p3 is taken out of the RAID group, and the parity is updated on the premise that the load balance does not change, and the RAID6 group satisfying the arrangement condition at this time is shown as the part 2 in the figure.

As shown, in order to form a real RAID6 group, it is necessary to arrange the RAID6 group based on load balancing adjustment, update the codec, and obtain a RAID6 group. The operation at this time is as shown in fig. 2.

As shown in fig. 2, after degradation, the position is adjusted based on load balancing, and the resulting data operation mainly has three types, where the first type is that only the position of data changes, and the position of the check code does not change; the second type is that the position of the data and the position of partial verification are changed; the third category is that all data and checks have changed.

Three categories need to be adjusted separately.

The first type: if the data information has changed in location on the premise that the RAID6 is downgraded to satisfy equation (14), the data information for each location may be considered to have changed, and equation (14) may be updated as follows:

here, d 1'd 2' is the data information meeting the load balancing requirement after location update, and the corresponding checks meeting the load balancing are p1 ", p 2", m and n, which indicate the locations of the checks, and in the case of the first category in fig. 2, m and n are respectively 4 and 1. Then the calculated relationship based on RAID6 may be:

it can be seen that the new checks p1 "and p 2" can be updated by the formula (16).

Then, the operation at this time is to label the position where the data changes based on the new load balancing requirement, perform data shifting, calculate respective Δ data during data shifting, calculate a checked Δ value by using equation (16), and then obtain a check meeting the load balancing requirement by using the update check.

The second type: at this time, the position of the data is changed, and the position is also changed in the verification. The value at which the check position changes is first updated at this time.

Taking the example that p 1' has changed position in the second case of the second category, the formula relationship at this time is:

it can be seen that the second type of updating only p1 does not achieve the operation, that is, when any position in the check is changed, all checks need to be updated, that is, the second type of case is equal to the third type of case, and the check code involved cannot be changed.

Therefore, the second case is not specifically set here, and the same operation method as the third case can be used.

In the third category: all cases involving a change in the position of the check code are calculated in a third type of manner.

In this case, the first method is used to move the data assuming that the verified position has not changed, calculate the Δ value of the verification based on the Δ value of the moved data, and update the verification to obtain the verified data value at the new data position.

The parity data is then updated and shifted based on the location involved in the new load balancing.

The specific way in the case of the third category in fig. 2 is:

in the formula (18), p1 'and p 2' are verification information updated by data migration, and p1_m"and p2_m"is the verification information after the verification position is changed. m and n are original checking positions, and m 'and n' are checking positions after load balance adjustment. Based on the derivation of the above formula, p1 is obtained after the change_m"and p2_m"satisfies the RAID6 algorithm operated by p 1" and p2 ", and thus it can be finally calculated by p 1" and p2 ", in the manner shown in equation (18).

In the second category, when the position information is not changed, the corresponding unchanged m or n is directly replaced by the corresponding m 'or n', and then the operation is completed based on the formula (18).

In the above, the TP-RAID is degraded to RAID6, and all operations including load balancing are completed.

The operation can simplify the complex condition of degradation, the data migration influences the data operation, the check code influences the operation of the check code, the operation can be completed through delta data along with the movement of the data, the encoding operation does not need to be carried out again, the operation complexity is reduced, and the speed is improved.

In a second aspect of the present invention, a Redundant Array of Independent Disks (RAID) destaging system 200 is also provided. FIG. 4 illustrates a schematic block diagram of an embodiment of a RAID destaging system 200 in accordance with the present invention. As shown in fig. 4, the system includes:

a degradation relation transformation module 210, wherein the degradation relation transformation module 210 is configured to transform the relation of TP-RAID degrading to RAID6, so that the degraded check data is retained as a designated check code combination P1P2 when any check disk is extracted;

a check relation updating module 220, wherein the check relation updating module 220 is configured to update the check relation, wherein a data and check relation expression is obtained by degrading the check relation from TP-RAID to RAID6 under the condition of no load balancing requirement, and then a degraded relation expression of RAID6 is obtained under the condition of degraded operation relation, wherein a check block P3 extracted in operation is directly determined by a host (host) in a manner of being decoupled from an actual degrading operation based on the degrading requirement, and operation is started;

and a data change updating module 230, wherein the data change updating module 230 is configured to update data changes caused by load balancing position changes, and according to a relational expression of the degraded RAID6, the RAID without load balancing is arranged based on load balancing adjustment, and the coding and decoding conditions are updated to obtain a RAID6 group, where the positions of the data and/or the positions of the check codes are adjusted.

In a third aspect of the embodiments of the present invention, a computer-readable storage medium is further provided, and fig. 5 is a schematic diagram of a computer-readable storage medium of a redundant array of independent disks demotion method provided in an embodiment of the present invention. As shown in fig. 5, the computer-readable storage medium 300 stores computer program instructions 310, the computer program instructions 310 being executable by a processor. The computer program instructions 310, when executed, implement the method of any of the embodiments described above.

It should be understood that all of the embodiments, features and advantages set forth above with respect to the RAID destaging method according to the present invention are equally applicable to RAID destaging systems and storage media according to the present invention without conflict therebetween.

In a fourth aspect of the embodiments of the present invention, there is further provided a computer device 400, comprising a memory 420 and a processor 410, wherein the memory stores a computer program, and the computer program, when executed by the processor, implements the method of any one of the above embodiments.

Fig. 6 is a schematic hardware structural diagram of an embodiment of a computer device for executing a redundant array of independent disks demotion method according to the present invention. Taking the computer device 400 shown in fig. 6 as an example, the computer device includes a processor 410 and a memory 420, and may further include: an input device 430 and an output device 440. The processor 410, the memory 420, the input device 430, and the output device 440 may be connected by a bus or other means, such as the bus connection in fig. 6. Input device 430 may receive input numeric or character information and generate signal inputs related to RAID degradation. The output device 440 may include a display device such as a display screen.

The memory 420 is a non-volatile computer-readable storage medium, and can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as program instructions/modules corresponding to the resource monitoring method in the embodiment of the present application. The memory 420 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created by use of the resource monitoring method, and the like. Further, the memory 420 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, memory 420 may optionally include memory located remotely from processor 410, which may be connected to local modules via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The processor 410 executes various functional applications of the server and data processing by executing nonvolatile software programs, instructions and modules stored in the memory 420, that is, implements the resource monitoring method of the above-described method embodiment.

Finally, it should be noted that the computer-readable storage medium (e.g., memory) herein can be either volatile memory or nonvolatile memory, or can include both volatile and nonvolatile memory. By way of example, and not limitation, nonvolatile memory can include Read Only Memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM), which can act as external cache memory. By way of example and not limitation, RAM is available in a variety of forms such as synchronous RAM (DRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The storage devices of the disclosed aspects are intended to comprise, without being limited to, these and other suitable types of memory.

Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as software or hardware depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the disclosed embodiments of the present invention.

The various illustrative logical blocks, modules, and circuits described in connection with the disclosure herein may be implemented or performed with the following components designed to perform the functions herein: a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination of these components. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP, and/or any other such configuration.

The foregoing is an exemplary embodiment of the present disclosure, but it should be noted that various changes and modifications could be made herein without departing from the scope of the present disclosure as defined by the appended claims. The functions, steps and/or actions of the method claims in accordance with the disclosed embodiments described herein need not be performed in any particular order. Furthermore, although elements of the disclosed embodiments of the invention may be described or claimed in the singular, the plural is contemplated unless limitation to the singular is explicitly stated.

It should be understood that, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly supports the exception. It should also be understood that "and/or" as used herein is meant to include any and all possible combinations of one or more of the associated listed items. The numbers of the embodiments disclosed in the embodiments of the present invention are merely for description, and do not represent the merits of the embodiments.

Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant only to be exemplary, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to these examples; within the idea of an embodiment of the invention, also technical features in the above embodiment or in different embodiments may be combined and there are many other variations of the different aspects of the embodiments of the invention as described above, which are not provided in detail for the sake of brevity. Therefore, any omissions, modifications, substitutions, improvements, and the like that may be made without departing from the spirit and principles of the embodiments of the present invention are intended to be included within the scope of the embodiments of the present invention.

Claims

1. A method for degrading an independent redundant disk array is characterized by comprising the following steps:

updating a check relation, wherein a data and check relational expression is obtained by considering the check relation degradation from TP-RAID to RAID6 under the condition of no load balancing requirement, then a degraded relational expression of RAID6 is obtained under the condition of considering the degraded operational relation, wherein a check block p3 which is extracted in the operation is directly determined by a host in a decoupling manner with the actual degradation operation based on the degradation requirement, and the operation is started;

and updating data change caused by load balance position change, and updating coding and decoding conditions of the RAID without load balance based on load balance adjustment arrangement according to the relational expression of the degraded RAID6 to obtain a RAID6 group, wherein the position of the data and/or the position of the check code are/is adjusted.

2. The method of claim 1, wherein transforming the relationship of TP-RAID downgrading to RAID6 such that the downgraded parity data remains in a specified combination if any parity disk is popped further comprises:

and

3. The method of claim 2, wherein updating the check relationship further comprises:

4. The method of claim 3, wherein updating the check relationship further comprises:

Wherein, the delta p1 and the delta p2 are the increased difference needed by the direct operation from p1p2 to p1 'p 2', and the difference is obtained

Wherein the parameter values of m, n and o are determined by the host and the operation is started.

5. The method of claim 4, wherein updating the check relationship further comprises: and obtaining a check code value for reducing the TP-RAID arranged under the existing load balancing condition to RAID6 through delta p1 and delta p2, wherein the check code value is calculated based on the following formula:

6. the method of claim 5, wherein updating the data changes caused by load balancing location changes further comprises:

based on the degraded RAID6:

7. The method of claim 6, wherein updating the data changes caused by load balancing location changes further comprises: the position of the data is adjusted, wherein equation (14) is updated as:

8. The method of claim 7, wherein updating the data changes caused by load balancing location changes further comprises: the positions of all data and the positions of all check codes are adjusted, wherein the positions of the data are first adjusted based on formula (15), and then the check data are updated and shifted based on the positions involved in the new load balancing based on the following formula:

9. A raid destaging system comprising:

the system comprises a degradation relation transformation module, a data storage module and a data processing module, wherein the degradation relation transformation module is configured to transform the relation from TP-RAID to RAID6, so that the degraded check data are reserved as a designated combination p1p2 under the condition that any check disk is extracted;

10. A computer device comprising a memory and a processor, wherein the memory has stored therein a computer program that, when executed by the processor, performs the raid destaging method of any one of claims 1-8.