(19)
(11)EP 3 229 139 B1

(12)EUROPEAN PATENT SPECIFICATION

(45)Mention of the grant of the patent:
15.05.2019 Bulletin 2019/20

(21)Application number: 17150332.9

(22)Date of filing:  31.12.2014
(51)Int. Cl.: 
G06F 11/14  (2006.01)
G06F 11/10  (2006.01)
G06F 3/06  (2006.01)

(54)

METHOD FOR WRITING DATA INTO STORAGE SYSTEM AND STORAGE SYSTEM

VERFAHREN ZUM SCHREIBEN VON DATEN IN EIN SPEICHERSYSTEM SOWIE SPEICHERSYSTEM

PROCÉDÉ D'ÉCRITURE DE DONNÉES DANS UN SYSTÈME DE MÉMOIRE ET SYSTÈME DE MÉMOIRE


(84)Designated Contracting States:
AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

(43)Date of publication of application:
11.10.2017 Bulletin 2017/41

(62)Application number of the earlier application in accordance with Art. 76 EPC:
14909472.4 / 3128429

(73)Proprietor: Huawei Technologies Co., Ltd.
Longgang District Shenzhen, Guangdong 518129 (CN)

(72)Inventors:
  • YI, Letian
    Shenzhen, Guangdong (CN)
  • FANG, Xin
    Shenzhen, Guangdong (CN)
  • ZHANG, Zhenhua
    Shenzhen, Guangdong (CN)

(74)Representative: Kreuz, Georg Maria 
Huawei Technologies Duesseldorf GmbH Riesstraße 25
80992 München
80992 München (DE)


(56)References cited: : 
US-A1- 2004 250 161
US-A1- 2012 221 533
  
      
    Note: Within nine months from the publication of the mention of the grant of the European patent, any person may give notice to the European Patent Office of opposition to the European patent granted. Notice of opposition shall be filed in a written reasoned statement. It shall not be deemed to have been filed until the opposition fee has been paid. (Art. 99(1) European Patent Convention).


    Description

    TECHNICAL FIELD



    [0001] Embodiments of the present invention relate to the field of storage technologies, and in particular, to a method for writing data into a storage system and a storage system.

    BACKGROUND



    [0002] In a storage system, multiple storage servers are connected to each other to form a distributed system, to complete a data storage task in coordination. When a task is being executed, the task may fail if a storage server is out of service. Therefore, to tolerate the out-of-service storage server, the storage system generally uses a manner of data redundancy storage. In a conventional approach, a redundant array of independent disks (full name: Redundant Array of Independent Disks, RAID for short) technology is used. According to the RAID technology, one piece of data is divided into multiple data units, a check unit is obtained through calculation by using exclusive OR among the multiple data units, and the data units and the check unit are stored in different storage servers. When a storage server is out of service, content of data stored in the out-of-service storage server can be obtained again through calculation by using the data units and the check unit that are stored in a storage server that is not out of service, and therefore, that the storage server is out of service is tolerable. During the out-of-service period of the storage server, because the content of the data stored in the out-of-service storage server can be acquired again through calculation, the storage system is still allowed to provide a service externally, and the service in this case is referred to as a degraded service.

    [0003] Generally, being permanently out of service means that a storage server in a storage system is faulty and permanently leaves the storage system; being transiently out of service means that a storage server in a storage system is determined to be out of service within a period of time due to performance jitter or the like, but after a period of time, the storage server may join the storage system again.

    [0004] If an out-of-service storage server is merely out of service transiently, and another storage server is out of service after the transiently out-of-service storage server joins the storage system again within a relatively short period of time, data loss may be caused.

    [0005] US 2004/0250161 A1 discloses a technique in which data stored on a failed storage device is reconstructed and stored on unused portions of storage devices that did not fail.

    SUMMARY



    [0006] Embodiments of the present invention provide a method for writing data into a storage system and a storage system, so that even if another storage device is permanently out of service after a transiently out-of-service storage device joins a storage system again, provided that a quantity of members stored in the permanently out-of-service storage device does not exceed a quantity of out-of-service members that is allowed by a RAID, data reliability can still be ensured. The invention is defined by the appended independent claims.

    [0007] A first aspect of the embodiments of the present invention provides a method for writing data into a storage system, where the storage system includes a redundant array of independent disks (RAID), the RAID includes a control device and X storage devices, a data stripe is stored in the RAID, and the stripe includes (N+M) members, where N is a quantity of data units in the members, M is a quantity of check units generated according to the N data units, N>=2, M=2, and the RAID is RAID 6 with N+M=X or N+M=2X or (N+M)>X, where when (N+M)>X and (N+M) is not equal to a multiple of X, each storage device stores one or two members of the stripe; and the method is performed by the control device and includes: determining, by the control device, that at least one first storage device of the X storage devices is out of service, where at least one member is stored in the first storage device; the method being characterized by: determining that a quantity of out-of-service members reaches a quantity of out-of-service members that is tolerable to the RAID 6; updating the members of the data stripe stored on the remaining not out of service storage devices by writing new data to the members; and writing target data into (Y+1) second storage devices of the X storage devices, where Y=M-(┌(N+M)/X┐-1), and the target data is a data unit or a check unit used to update the at least one member that is stored in the first storage device and where [(N + M)/X] represents performing rounding up on (N+M)/X, and where the target data is obtained through calculation by using the updated members of the data stripe stored on the remaining not out of service storage devices.

    [0008] In a first possible implementation manner of the first aspect, the method further includes: determining, by the control device, that the target data is the data unit or the check unit used to update the at least one member that is stored in the first storage device.

    [0009] A second aspect of the embodiments of the present invention provides a storage system, where the storage system includes a redundant array of independent disks (RAID), the RAID includes a control device and X storage devices, a data stripe stripe is stored in the RAID, and the data stripe includes (N+M) members, where N is a quantity of data units in the members, M is a quantity of check units generated according to the N data units, N>=2, M=2, and the RAID is RAID 6 with N+M=X, or N+M=2X or (N+M)>X, where when (N+M)>X and (N+M) is not equal to a multiple of X, each storage device stores one or two members of the stripe; where each of the X storage devices is configured to store one of the (N+M) members ; and the control device is configured to determine that at least one first storage device of the X storage devices is out of service, where at least one member is stored in the first storage device;
    and the storage system being characterized in that the control device is configured to: determine that a quantity of out-of-service members reaches a quantity of out-of-service members that is tolerable to the RAID 6; update the members of the data stripe stored on the remaining not out of service storage devices by writing new data to the members; and write target data into (Y+1) second storage devices of the X storage devices, where Y=M-(┌(N+M)/X┐-1), and the target data is a data unit or a check unit used to update the at least one member that is stored in the first storage device, and where ┌(N + M)/X┐ represents performing rounding up on (N+M)/X, and where the target data is obtained through calculation by using the updated members of the data stripe stored on the remaining not out of service storage devices.

    [0010] In a first possible implementation manner of the second aspect, the control device is further configured to determine that the target data is the data unit or the check unit used to update the at least one member that is stored in the first storage device.

    BRIEF DESCRIPTION OF DRAWINGS



    [0011] To describe the technical solutions in the embodiments of the present invention more clearly, the following briefly introduces the accompanying drawings required for describing the embodiments or in the prior art. Apparently, the accompanying drawings in the following description show merely some embodiments of the present invention, and a person of ordinary skill in the art may still derive other drawings from these accompanying drawings without creative efforts.

    FIG. 1 is a schematic diagram of a scenario in which a storage server in the prior art is permanently out of service according to an embodiment of the present invention;

    FIG. 2 is a structural composition diagram of a storage system according to an embodiment of the present invention;

    FIG. 3 is another structural composition diagram of a storage system according to an embodiment of the present invention;

    FIG. 4 is still another structural composition diagram of a storage system according to an embodiment of the present invention;

    FIG. 5A is a schematic diagram of selecting a replacement for an out-of-service storage server according to an embodiment of the present invention;

    FIG. 5B is another schematic diagram of selecting a replacement for an out-of-service storage server according to an embodiment of the present invention;

    FIG. 5C is still another schematic diagram of selecting a replacement for an out-of-service storage server according to an embodiment of the present invention;

    FIG. 5D is yet another schematic diagram of selecting a replacement for an out-of-service storage server according to an embodiment of the present invention;

    FIG. 5E is yet another schematic diagram of selecting a replacement for an out-of-service storage server according to an embodiment of the present invention;

    FIG. 5F is yet another schematic diagram of selecting a replacement for an out-of-service storage server according to an embodiment of the present invention;

    FIG. 5G is yet another schematic diagram of selecting a replacement for an out-of-service storage server according to an embodiment of the present invention;

    FIG. 5H is yet another schematic diagram of selecting a replacement for an out-of-service storage server according to an embodiment of the present invention;

    FIG. 6 is a schematic flowchart of a method for writing data into a storage system according to an embodiment of the present invention; and

    FIG. 7 is a schematic flowchart of a method for another implementation manner for writing data into a storage system according to an embodiment of the present invention.


    DESCRIPTION OF EMBODIMENTS



    [0012] Embodiments of the present invention provide a method for writing data into a storage system and a storage system, so that even if another storage device is permanently out of service after a transiently out-of-service storage device joins a storage system again, provided that a quantity of members stored in the permanently out-of-service storage device does not exceed a quantity of out-of-service members that is allowed by a RAID, data reliability can still be ensured.

    [0013] In the prior art, if a storage system provides a degraded service, when there is a data update operation, a data unit or a check unit of only storage servers that are in service is updated. As shown in FIG. 1, storage servers 1 to 6 form a RAID. A, B, C, and D are data units, and P and Q are check units obtained through calculation according to the data units. A, B, C, D, P, and Q together form a stripe (stripe) of the RAID and are written into the storage servers 1 to 6.

    [0014] At a time T0, the data units and the check units all are in a 0th version, where P0 and Q0 are obtained through calculation by using the data units A0, B0, C0, and D0. In this case, the storage server 5 and the storage server 6 are transiently out of service, the rest storage servers work properly, and the storage system enters a degraded service mode.

    [0015] At a time T1, a user writes new data into the stripe, to update A0, B0, C0, and D0 to A1, B1, C1, and D1. However, the new data is not written into PI and Q1. In this case, data stored in the RAID is A1, B1, C1, D1, P0, and Q0.

    [0016] If the storage server 5 and the storage server 6 are merely transiently out of service, at a time T2, after the storage server 5 and the storage server 6 join the RAID again and when P0 and Q0 have not been updated with P1 and Q1 according to calculation on A1, B1, C1, and D1, the storage server 3 and the storage server 4 are permanently out of service. In this case, data of C1 and D1 are lost forever. The reason is that only A1, B1, P0, and Q0 are stored in the storage system, and C1 and D1 cannot be obtained according to A1, B1, P0, and Q0.

    [0017] In view of this, the embodiments of the present invention provide a method for writing data into a storage system and a storage system. After a first storage device is determined to be transiently out of service, a proper replacement may be selected for the transiently out-of-service first storage device, so that when another storage device is permanently out of service after the first storage device joins the storage system again, provided that a quantity of members stored in the permanently out-of-service storage device does not exceed a quantity of out-of-service members that is allowed by a RAID, data loss does not occur, thereby ensuring data reliability.

    [0018] The following describes application scenarios of the embodiments of the present invention.
    Scenario 1: As shown in FIG. 2, FIG. 2 shows a composition diagram of a storage system 10 according to an embodiment of the present invention. The storage system 10 shown in FIG. 2 includes one or more hosts 40 (in FIG. 2, one host is used as an example) and multiple storage servers 20. The host may be a computing device, for example, a terminal device such as a server or a desktop computer. The storage server 20 may be a storage device, for example, a storage array. Communication may be performed between the host 40 and the storage servers 20 and between the storage servers 20 by using the Network File System (full name: Network File System, NFS for short)/Common Internet File System (full name: Common Internet File System, CIFS for short) protocol or the Fiber Channel (full name: Fiber Channel, FC for short) protocol. The multiple storage servers 20 may form one or more RAIDs. For ease of description, in the embodiments, an example in which the multiple storage servers 20 form one RAID is used.

    [0019] The host 40 may send a write data request to the storage system 10, where the write data request carries a data object that is to be written into the storage system, and the data object may be block data or a file. After receiving the write data request, any one storage server of the multiple storage servers 20 divides the data object into multiple data units, and obtains a check unit of the multiple data units through calculation by using exclusive OR check or in another manner. The multiple data units and the check unit may form one stripe and be stored in the RAID, where each data unit or check unit is a member of the stripe. The storage server 20 receiving the write data request then sends each member to a corresponding storage server 20 for storage.

    [0020] In an optional implementation manner, in the storage system 10 shown in FIG. 2, a storage server 20 may be used as a primary server. The primary server is responsible for receiving the write data request sent by the host 40 to the storage system 10, dividing the data object into multiple data units, obtaining the check unit of the multiple data units through calculation, and then sending each member of the stripe to a corresponding storage server 20 for storage.

    Scenario 2: As shown in FIG. 3, besides storage servers forming a RAID, a storage system 10 may further include a hot spare server 30. The hot spare server 30 does not belong to the RAID, and the hot spare server 30 is a storage server specially used for replacing, when a storage server is transiently out of service, the transiently out-of-service storage server. It may be understood that normally the hot spare server 30 does not carry a data service, but once a storage server is transiently out of service, the hot spare server 30 can carry the data service in place of the transiently out-of-service storage server. For example, data that is to be written into the transiently out-of-service storage server is written into the hot spare server 30. Generally, in the storage system 10, there may be one or more hot spare servers 30.

    Scenario 3: As shown in FIG. 4, a storage system 10 shown in FIG. 4 includes at least one host 40, at least one controller 50, and multiple disks 60. The host 40 may be a computing device, for example, a terminal device such as a server or a desktop computer. The controller 50 may be a storage server that manages multiple disks 60, and the multiple disks 60 form a RAID. The host 40 may send a write data request to the controller 50, where the write data request carries a data object that is to be written into the storage system. After receiving the write data request, the controller 50 divides data into multiple data units and obtains a check unit of the multiple data units through calculation by using exclusive OR check or in another manner. The multiple data units and the check unit may form one stripe and be stored in the RAID, where each data unit or check unit is a member of the stripe. The controller 50 then sends the members to corresponding disks for storage. In addition, besides the disks forming the RAID, a hot spare disk (which is not shown in the figure) may be further included. A function of the hot spare disk is similar to that of the hot spare server shown in FIG. 3, and details are not described herein again.



    [0021] As shown in FIG. 4, a controller 50 mainly includes a processor (processor) 518, a cache (cache) 520, a memory (memory) 522, a communications bus (bus for short) 526, and a communications interface (Communication Interface) 528. The processor 518, the cache 520, the memory 522, and the communications interface 528 communicate with each other by using the communications bus 526.

    [0022] The communications interface 528 is configured to communicate with a host 40 or a disk 60.

    [0023] The memory 522 is configured to store a program 524. The memory 522 may include a high-speed RAM memory, and may further include a non-volatile memory (non-volatile memory), for example, at least one magnetic disk memory. It may be understood that, the memory 522 may be various non-transitory (non-transitory) machine-readable media that can store program code, for example, a random access memory (Random-Access Memory, RAM), a hard disk, a memory, an optical disc, a solid-state memory (Solid State Disk, SSD), or a non-volatile memory.

    [0024] The program 524 may include program code, where the program code includes a file system 210 and other program code.

    [0025] The cache 520 (Cache) is configured to temporarily store data received from an application server 10 or read data from the disk 60. The cache 520 may be various non-transitory (non-transitory) machine-readable media that can store data, for example, a RAM, a ROM, a flash memory (Flash memory), or a solid-state memory (Solid State Disk, SSD), which is not limited herein.

    [0026] In addition, the memory 522 and the cache 520 may be integrated or disposed separately, which is not limited in this embodiment of the present invention.

    [0027] The processor 518 may be a central processing unit CPU or an application-specific integrated circuit ASIC (Application Specific Integrated Circuit), or is configured as one or more integrated circuits that implement this embodiment of the present invention. In this embodiment of the present invention, the processor 518 may be configured to receive various data processing requests from the host 40, for example, a read data operation, a write data operation, and a modify data operation.

    [0028] In the above three application scenarios, the host 40 may also divide a data object into multiple data units, obtain a check unit of the multiple data units through calculation, and then separately send each member of the stripe to a corresponding storage server 20 or the controller 50 for storage.

    [0029] The following uses scenario 1 or scenario 2 as an example to describe how to select, when a storage server 20 in the storage system 10 is transiently out of service, a replacement for the transiently out-of-service storage server 20.

    [0030] In this embodiment, there may be one or more check units, depending on a type of a RAID. For example, there is one check unit in a RAID 5, and there are two check units in a RAID 6.

    [0031] For ease of description, in this embodiment, N represents a quantity of data units, M represents a quantity of check units, and X represents a quantity of storage servers 20 in the storage system, where N is an integer greater than or equal to 2, M is an integer greater than or equal to 1, and (N+M) is greater than or equal to X.

    [0032] When (N+M)=X, each storage server 20 stores a member of a stripe. For example, assuming that members of one stripe include A, B, C, D, P, and Q, where A, B, C, and D are data units, and P and Q are check units (the RAID 6 is used as an example herein), and the RAID includes 6 storage servers 20, storage of each member in storage servers whose IDs are 1 to 6 is shown in Table 1. In addition, a person skilled in the art may understand that, in this case, a quantity of out-of-service members that is tolerable to the RAID is 2.
    Table 1
    Storage server ID 1 2 3 4 5 6
    Member of a stripe A B C D P Q


    [0033] When (N+M)>X, and (N+M) is equal to a multiple of X, each storage server 20 stores at least one member of a stripe, and each storage server 20 stores more than one member of the stripe. For example, assuming that the RAID includes only three storage servers 20, storage of each member of the stripe in storage servers whose IDs are 1 to 3 is shown in Table 2.
    Table 2
    Storage server ID 1 2 3
    Member of a stripe A B C
    D P Q


    [0034] When (N+M)>X, and (N+M) is not equal to a multiple of X, each storage server 20 stores at least one member of a stripe, and at least one storage server 20 stores more than one member of the stripe. For example, assuming that the RAID includes only five storage servers 20, storage of each member of the stripe in storage servers whose IDs are 1 to 5 is shown in Table 3.
    Table 3
    Storage server ID 1 2 3 4 5
    Member of a stripe A B C D P
    Q        


    [0035] The following cases are separately described below: (N+M)=X; (N+M)>X and (N+M) is equal to a multiple of X; and (N+M)>X, and (N+M) is not equal to a multiple of X.

    Case 1: (N+M)=X



    [0036] 
    1. 1. For a RAID 6, assuming that the RAID includes six storage servers, members of the stripe include four data units and two check units, and a quantity of out-of-service members that is tolerable is 2 (a storage manner shown in Table 1). In addition, it should be noted that, an example in which a quantity of out-of-service members reaches the quantity of out-of-service members that is tolerable to the RAID is used in the following descriptions. In a case in which the quantity of out-of-service members does not reach the quantity of out-of-service members that is tolerable to the RAID, another manner may also be used to select a replacement, which is not described in detail in this embodiment.


    [0037] For the scenario 2 (as shown in FIG. 3), when the storage system 10 includes enough hot spare servers 30, the hot spare servers 30 may be used as replacements of a transiently out-of-service storage server 20.

    [0038] For the scenario 1 (as shown in FIG. 2), when the storage system 10 does not include a hot spare server 30, a storage server 20 that is not transiently out of service needs to be selected from the RAID to work as a replacement of a transiently out-of-service storage server 20.

    [0039] Generally, there is a relatively low risk in data loss when a storage server 20 storing relatively few members is selected as a replacement (in this embodiment, the storage server storing relatively few members refers to a storage server in which a quantity of stored members is less than an average quantity). However, because (N+M)=X, and each storage server 20 stores one member, the storage server 20 storing relatively few members cannot be selected as a replacement. Therefore, in a case in which each storage server 20 stores one member, how many replacements need to be selected to prevent data loss is a problem to be described in this embodiment.
    1. (1) As shown in FIG. 5A, it is assumed that at a time T0, data units and check units all are in a 0th version, where P0 and Q0 are obtained through calculation by using the data units A0, B0, C0, and D0. A0, B0, C0, D0, P0, and Q0 are respectively stored in storage servers 1 to 6.


    [0040] At a time T1, the storage server 5 and the storage server 6 are transiently out of service, and the check units P0 and Q0 stored in the storage server 5 and the storage server 6 are lost. In addition, all the rest data units and check units are updated to be in a 1st version. In this case, because the storage server 5 and the storage server 6 are out of service, normal storage servers need to be selected from the other storage servers to work as replacements of the storage server 5 and the storage server 6. Assuming that the storage server 3 is used as a replacement of the storage server 5, the storage server 3 stores PI besides C1. Assuming that the storage server 4 is used as a replacement of the storage server 6, the storage server 4 stores Q1 besides D1. P1 and Q1 may be obtained through calculation according to A1, B1, C1, and D1. It can be seen that, in this case, although the storage server 5 and the storage server 6 are transiently out of service, the RAID can still provide a degraded service.

    [0041] Assuming that at a time T2, the storage server 5 and the storage server 6 are restored and join the RAID again, but the storage server 3 and the storage server 4 are permanently out of service, C1, D1, P1, and Q1 are lost. In this case, only A1 and B1 are stored in the stripe, and C1 and D1 cannot be obtained through calculation according to A1 and B1. As a result, data is lost forever.

    [0042] Therefore, for the RAID 6, when two storage servers 20 are transiently out of service, resulting in that a quantity of the out-of-service members reaches a quantity of out-of-service members that is tolerable to the RAID 6, if one replacement is selected for each storage server 20, when another storage server 20 in the storage system 10 is permanently out of service, data is very likely to be lost. When only a single storage server is out of service or both the storage server 1 and the storage server 2 are out of service, a quantity of out-of-service members does not exceed a quantity of tolerable out-of-service members, which does not cause data loss. In other cases, for example, both the storage server 1 and the storage server 3 are out of service, a quantity of the out-of-service members exceeds a quantity of tolerable out-of-service members, which causes data loss.
    (2) As shown in FIG. 5B, if at a time T1, a storage server 5 and a storage server 6 are transiently out of service, two storage servers are separately selected as replacements of the storage server 5 and the storage server 6. For example, a storage server 1 and a storage server 3 are replacements of the storage server 5, and a storage server 2 and a storage server 4 are replacements of the storage server 6.

    [0043] Then, at a time T2, when the storage server 5 and the storage server 6 are restored and join the RAID again, if the storage server 1 and the storage server 3 are permanently out of service, A1, C1, and PI are lost. A1, C1, and PI cannot be obtained through calculation according to B1, D1, and Q1, and data loss still occurs.

    [0044] Therefore, for the RAID 6, when two storage servers 20 are transiently out of service, resulting in that a quantity of the out-of-service members reaches a quantity of out-of-service members that is tolerable to the RAID 6, if two replacements are selected for each storage server 20, when two more storage servers 20 in a storage system 10 are permanently out of service, data loss occurs.
    (3) As shown in FIG. 5C, if at a time T1, a storage server 5 and a storage server 6 are transiently out of service, three storage servers are separately selected as replacements of the storage server 5 and the storage server 6. For example, a storage server 1, a storage server 2, and a storage server 3 are replacements of the storage server 5, and the storage server 1, the storage server 2, and a storage server 4 are replacements of the storage server 6.

    [0045] Then, at a time T2, when the storage server 5 and the storage server 6 are restored and join the RAID again, even if any two storage servers are permanently out of service, data loss does not occur.

    [0046] Therefore, for the case in which (N+M)=X, when a type of a RAID is RAID 6 and the RAID includes two check units, if two storage servers are transiently out of service, three replacements need to be selected for each storage server.
    2. For a RAID 5, assuming that the RAID includes five storage servers 20, members of a stripe include four data units and one check unit, and a quantity of tolerable out-of-service members is 1.

    [0047] For the scenario 2, when the storage system 10 includes enough hot spare servers 30, the hot spare servers 30 may be used as replacements of a transiently out-of-service storage server 20.

    [0048] For the scenario 1, when the storage system 10 does not include a hot spare server 30, a storage server 20 that is not transiently out of service needs to be selected from the RAID to work as a replacement of a transiently out-of-service storage server 20.
    1. (1) As shown in FIG. 5D, it is assumed that at a time T0, data units and a check unit all are in a 0th version, where P0 is obtained through calculation according to the data units A0, B0, C0, and D0. A0, B0, C0, D0, and P0 are respectively stored in storage servers 1 to 5.


    [0049] At a time T1, the storage server 5 is transiently out of service, and the check unit P0 stored in the storage server 5 is lost. In addition, all the rest data units and check units are updated to be in a 1st version. In this case, if one storage server (for example, the storage server 3) is selected from the other storage servers for the storage server 5, the storage server 3 stores PI besides C1, where PI may be obtained through calculation according to A1, B1, C1, and D1. It can be seen that, in this case, although the storage server 5 is transiently out of service, the RAID can still provide a degraded service.

    [0050] Assuming that at a time T2, the storage server 5 is restored and joins the RAID again, but the storage server 3 is permanently out of service, C1 and P1 are lost. In this case, only A1, B1, and D1 are stored in the stripe, and C1 and P1 cannot be obtained through calculation according to A1, B1, and D1. As a result, data is lost forever.

    [0051] Therefore, for the RAID 5, when one storage server 20 is transiently out of service, resulting in that a quantity of the out-of-service members reaches a quantity of out-of-service members that is tolerable to the RAID 5, if one replacement is selected for the out-of-service storage server 20, when another storage server 20 in the storage system 10 is permanently out of service, data may be lost.
    (2) As shown in FIG. 5E, if at a time T1, a storage server 5 is transiently out of service, two storage servers are selected as replacements of the storage server 5. For example, a storage server 2 and a storage server 3 are replacements of the storage server 5.

    [0052] Then, at a time T2, when the storage server 5 is restored and joins the RAID again, if any storage service is permanently out of service, data loss does not occur.

    [0053] Therefore, for the case in which (N+M)=X, when a type of a RAID is RAID 5, if one storage server is transiently out of service, two replacements need to be selected for the storage server.

    Case 2: (N+M)>X, and (N+M) is equal to a multiple of X



    [0054] For a RAID 6, when (N+M)>X, and (N+M) is equal to a multiple of X (for example, (N+M) is equal to twice of X), each storage server 20 stores an equal quantity of members. The case is similar to the case in which (N+M)=X. That is, when a type of a RAID is RAID 6, the RAID includes two check units, and each storage server stores two members, if one storage server is transiently out of service, two replacements need to be selected for each storage server. Details are not described herein again.

    [0055] For a RAID 5, because a quantity of tolerable out-of-service members is 1, when each storage server 20 stores multiple members, none of the storage servers 20 is allowed to be out of service. Therefore, the case is not applicable to the RAID 5.

    Case 3: (N+M)>X, and (N+M) is not equal to a multiple of X



    [0056] For a RAID 6, it is assumed that the RAID includes five storage servers. Because members of a stripe include four data units and two check units, at least one storage server 20 stores more than one member of the stripe (a storage manner shown in Table 3). In addition, although a quantity of out-of-service members that is tolerable to the RAID 6 is 2, because at least one storage server 20 stores more than one member of the stripe, a quantity of out-of-service servers tolerable to the RAID 6 is 1.

    [0057] For the scenario 2 (as shown in FIG. 3), when the storage system 10 includes enough hot spare servers 30, the hot spare servers 30 may be used as replacements of a transiently out-of-service storage server 20.

    [0058] For the scenario 1 (as shown in FIG. 2), when the storage system 10 does not include a hot spare server 30, a storage server 20 that is not transiently out of service needs to be selected from the RAID to work as a replacement of a transiently out-of-service storage server 20.

    [0059] Generally, there is a relatively low risk in data loss when a storage server 20 storing relatively few members is selected as a replacement, for example, a storage server 20 in which a quantity of stored members is less than (N+M)/X. Therefore, the storage server 20 in which a quantity of stored members is less than (N+M)/X may be preferentially selected as a replacement.

    [0060] As shown in FIG. 5F, at a time T0, data units and check units all are in a 0th version, where P0 and Q0 are obtained through calculation according to the data units A0, B0, C0, and D0. A0 and Q0 are stored in a storage server 1, B0 is stored in a storage server 2, C0 is stored in a storage server 3, D0 is stored in a storage server 4, and P0 is stored in a storage server 5.

    [0061] At a time T1, the storage server 3 is transiently out of service, and the data unit C0 stored in the storage server 3 is lost. In addition, all the rest data units and check units are updated to be in a 1st version. In this case, a storage server needs to be selected from the other normal storage servers to work as a replacement of the storage server 3.

    [0062] If the storage server 2 is selected as the replacement of the storage server 3, the storage server stores C1 besides B1. C1 may be obtained through calculation according to A1, B1, D1, P1, and Q1.

    [0063] Assuming that at a time T2, the storage server 3 is restored and joins the RAID again, even if any storage service is permanently out of service, data loss does not occur.

    [0064] In an exemplary implementation manner, a storage server 20 storing the fewest members may be selected as the replacement, so that a risk in data loss is the lowest.

    [0065] In another implementation manner, a storage server 20 in which a quantity of stored members is not less than (N+M)/X may also be selected as a replacement. However, in this case, if only one replacement is selected, data loss is still caused.

    [0066] As shown in FIG. 5G, at a time T0, data units and check units all are in a 0th version, where P0 and Q0 are obtained through calculation according to the data units A0, B0, C0, and D0. A0 and Q0 are stored in a storage server 1, B0 is stored in a storage server 2, C0 is stored in a storage server 3, D0 is stored in a storage server 4, and P0 is stored in a storage server 5.

    [0067] At a time T1, the storage server 3 is transiently out of service, and the data unit C0 stored in the storage server 3 is lost. In addition, all the rest data units and check units are updated to be in a 1st version.

    [0068] If the storage server 1 is selected as a replacement of the storage server 3, where a quantity of members of the stripe that are stored in the storage server 1 is 2, which is greater than (N+M)/X. After being used as the replacement of the storage server 3, the storage server 1 stores C1 besides A1 and Q1. C1 may be obtained through calculation according to A1, B1, D1, P1, and Q1.

    [0069] Assuming that at a time T2, the storage server 3 is restored and joins the RAID again, but the storage server 1 is permanently out of service, A1, C1, and Q1 are lost. In this case, only B1, D1, and PI are stored in the stripe, and A1 and Q1 cannot be obtained through calculation. As a result, data loss occurs.

    [0070] Therefore, if a storage server 20 in which a quantity of stored members is not less than (N+M)/X is selected as a replacement, one more storage server 20 needs to be selected as a replacement.

    [0071] As shown in FIG. 5H, at a time T1, a storage server 1 and a storage server 2 may be selected together as replacements of the storage server 3. In this case, the storage server 1 stores A1, Q1, and C1, and the storage server 2 stores B1 and C1.

    [0072] Assuming that at a time T2, the storage server 3 is restored and joins the RAID again, but the storage server 1 is permanently out of service, A1 and Q1 are lost. In this case, B1, C1, D1, and PI are stored in the stripe, and A1 and Q1 can still be obtained through calculation. Data loss does not occur.

    [0073] Similarly, assuming that at a time T2, the storage server 3 is restored and joins the RAID again, but the storage server 2 is permanently out of service, B1 is lost. In this case, A1, C1, D1, P1, and Q1 are stored in the stripe, and B1 can still be obtained through calculation. Data loss does not occur either.

    [0074] Therefore, for the case in which (N+M)>X, and N+M is not equal to a multiple of X, when a type of a RAID is RAID 6, and the RAID includes two check units, if two storage servers are transiently out of service, two replacements need to be selected for each storage server.

    [0075] With reference to the foregoing descriptions of the case in which N+M=X or the case in which (N+M)>X and N+M is equal to a multiple of X, when multiple storage servers 20 need to be selected as replacements, a quantity of replacements needs to be Y+1, where Y=M-(┌(N+M)/X┐-1), ┌(N+M)/X┐ represents performing rounding up on (N+M)/X, N represents a quantity of data units, M represents a quantity of check units, and X represents a quantity of storage servers 20.

    [0076] In conclusion, when the storage system 10 does not include a hot spare server 30, in a case in which (N+M)>X, and N+M is not equal to a multiple of X, a storage server in which a quantity of stored members of a stripe is less than (N+M)/X may be preferentially selected as a replacement of a transiently out-of-service storage server. In this case, only one replacement is needed. Alternatively, storage servers in which quantities of stored members of a stripe are greater than (N+M)/X are selected as replacements of a transiently out-of-service storage server. In this case, Y+1 replacements are needed. In a case in which N+M=X or in a case in which (N+M)>X and N+M is equal to a multiple of X, because each storage server 20 stores an equal quantity of members, a storage server in which a quantity of stored members of a stripe is less than (N+M)/X cannot be selected as a replacement of a transiently out-of-service storage server. In this case, Y+1 replacements need to be selected.

    [0077] The above description is also applicable to the scenario 3 (as shown in FIG. 4). A difference lies in that, for the scenario 3, the N data units and the M check units are stored in the disks 60. X represents a quantity of disks forming the RAID. Similarly, for the scenario 3, when a hot spare disk is not included, in the case in which (N+M)>X and N+M is not equal to a multiple of X, a disk 60 in which a quantity of stored members of the stripe is less than (N+M)/X may be preferentially selected as a replacement of a transiently out-of-service disk 60. In this case, only one replacement is needed. Alternatively, disks 60 in which quantities of stored members of the stripe are greater than (N+M)/X are selected as replacements of a transiently out-of-service disk 60. In this case, Y+1 replacements are needed. In the case in which N+M=X or in the case in which (N+M) >X and N+M is equal to a multiple of X, because each disk 60 stores an equal quantity of members, a disk 60 in which a quantity of stored members of the stripe is less than (N+M)/X cannot be selected as a replacement of a transiently out-of-service disk 60. In this case, Y+1 replacements need to be selected.

    [0078] The following describes a method for writing data into a storage system according to an embodiment of the present invention with reference to FIG. 6. As shown in FIG. 6, the method may be applied to the storage system 10 in FIG. 2 or FIG. 4. The storage system 10 includes at least one RAID, and the RAID includes a control device and X storage devices. The method is performed by the control device.

    [0079] It should be noted that, when the method is applied to the storage system 10 shown in FIG. 2, the X storage devices refer to the storage servers 20 in FIG. 2, and the control device refers to any storage server 20 in FIG. 2 or a primary storage server 20 of the X storage servers 20.

    [0080] In addition, when the method is applied to the storage system 10 shown in FIG. 4, the X storage devices refer to the disks 60 in FIG. 4, and the control device refers to the controller 50 in FIG. 4. Therefore, a body for executing the following steps is a processor 518 in the controller 50.

    [0081] Step S601: Receive a first data object sent by a host 40, and separately send a data unit and a check unit that are included in the first data object to each storage device.

    [0082] Specifically, after receiving the first data object, a control device may divide the first data object into N data units according to a type of the RAID and perform calculation on the N data units, so as to generate M check units. The N data units and the M check units form one data stripe stripe, and each data unit or check unit is a member of the stripe, where N>=2, M>=1, and N+M>=X.

    [0083] In addition, after obtaining members of the stripe by means of dividing or generating, the control device may allocate an address to each member according to a preset rule. The address is used to represent a location, in which the member is to be stored, of a storage device. The control device may then send, according to the address allocated to each member, each member to a storage device corresponding to the address. In this embodiment, the control device may further save the address allocated to each member, an ID of the stripe, and a correspondence between members.

    [0084] Step S602: Determine that at least one first storage device is out of service.

    [0085] Optionally, in an implementation manner, the control device periodically sends a detection signal to each storage device. After receiving the detection signal, each storage device feeds back information of each stripe member stored in each storage device to the control device. The control device determines whether each storage device is in a normal working state.

    [0086] Optionally, in another implementation manner, when the host 40 sends a read data request to a control device, because to-be-read data required by the read data request is stored in each storage device as a stripe, the control device needs to send a read instruction to each storage device. If one storage device is out of service, data fed back by the storage device is certainly invalid data. In such a manner, the control device may also determine whether each storage device is in a normal working state.

    [0087] In this embodiment, there may be one or more out-of-service storage devices. When the type of the RAID is RAID 5, there is one out-of-service storage device, and one member is stored in the out-of-service storage device. When the type of the RAID is RAID 6, there may be one out-of-service storage device, and two members are stored in the out-of-service storage device, or there are two out-of-service storage devices, and one member is stored in each out-of-service storage device.

    [0088] Step S603: When N+M>=X, select Y+1 second storage devices as replacements of the first storage device, where Y=Y=M-(┌(N+M)/X┐-1).

    [0089] N+M>=X herein may be specifically N+M=X; or N+M>X, and N+M is equal to a multiple of X; or N+M>X, and N+M is not equal to a multiple of X. Selecting Y+1 second storage devices as replacements of the first storage device can ensure that after the first storage device joins the storage system 10 again, when another storage device is permanently out of service, provided that a quantity of members stored in the permanently out-of-service storage device does not exceed a quantity of out-of-service members that is allowed by the RAID, data loss does not occur. For a specific analysis process, refer to an example in FIG. 5C, FIG. 5E, or FIG. 5H, and details are not described herein again. It should be noted that, when N+M=X, the type of the RAID may be RAID 5 or RAID 6; when N+M>X, the type of the RAID is RAID 6.

    [0090] Step S604: Receive a second data object sent by the host 40, to obtain a member with which a member stored in the first storage device is updated.

    [0091] The second data object is a data object that is used to update the first data object and has a same stripe ID as the first data object. For example, after the control device receives the second data object, the control device may divide the second data object into N data units in the same way described in step S601, perform calculation on the N data units, so as to generate M check units, and moreover, allocate an address to each member according to the preset rule. When an address allocated to one or more members is the same as an address of a member stored in the first storage device, the one or more members having the same address are members with which the member stored in the first storage device is updated.

    [0092] It should be noted that, there is no order between step S604 and step S603.

    [0093] Step S605: Write the updated member into the second storage devices.

    [0094] A main task of the second storage device, as a replacement of the first storage device, is to receive, in place of the first storage device, data that is originally to be written into the first storage device.

    [0095] Referring to FIG. 7, FIG. 7 shows another implementation manner of the foregoing embodiment.

    [0096] In the implementation manner shown in FIG. 7, when N+M>X, and N+M is not equal to a multiple of X, in a preferred implementation manner, step S603 may be replaced with step S606, and the other steps are the same as the steps in the implementation manner shown in FIG. 6.

    [0097] Step S606: Select second storage devices, where a quantity of members stored in the second storage device is less than (N+M)/X. In this case, even if a second storage device is selected as a replacement of the first storage device, when another storage device is permanently out of service after the first storage device joins the storage system 10 again, provided that a quantity of members stored in the permanently out-of-service storage device does not exceed a quantity of out-of-service members that is allowed by the RAID, data loss does not occur. For a specific analysis process, refer to an example in FIG. 5F, and details are not described herein again. Alternatively, in an optional implementation manner, the second storage device is a storage device of the X storage devices that stores the fewest members.

    [0098] It can be seen that, compared with the implementation manner shown in FIG. 6, in the implementation manner shown in FIG. 7, fewer replacements may be selected for a transiently out-of-service storage device, thereby saving more resources to an extent.

    [0099] It should be noted that, the implementation manner shown in step S606 is applicable to the RAID 6.

    [0100] According to this embodiment of the present invention, after a first storage device is transiently out of service, a proper replacement may be selected for the transiently out-of-service first storage device, so that when another storage device is permanently out of service after the first storage device joins a storage system again, provided that a quantity of members stored in the permanently out-of-service storage device does not exceed a quantity of out-of-service members that is allowed by the RAID, data loss does not occur, thereby ensuring data reliability.

    [0101] An embodiment of the present invention further provides a computer program product for data processing, including a computer readable storage medium that stores program code, where an instruction included in the program code is used to perform the method procedures of the foregoing method embodiments.

    [0102] A person of ordinary skill in the art may understand that the foregoing storage medium includes any non-transitory (non-transitory) computer-readable medium that can store program code, such as a USB flash drive, a removable hard disk, a magnetic disk, an optical disc, a random access memory (Random-Access Memory, RAM), a solid state disk (Solid State Disk, SSD), or a non-volatile memory (non-volatile memory).

    [0103] Finally, it should be noted that the foregoing embodiments are merely intended for describing the technical solutions of the present invention, but not for limiting the present invention.


    Claims

    1. A method for writing data into a storage system, wherein the storage system comprises a redundant array of independent disks, RAID, the RAID comprises a control device (50) and X storage devices (60), a data stripe is stored in the RAID, and the data stripe comprises (N+M) members, N standing for a quantity of data units in the members, M standing for a quantity of check units generated based on the N data units, N>=2, M=2, and the RAID is RAID 6 with N+M=X or N+M=2X or (N+M)>X, wherein when (N+M)>X and (N+M) is not equal to a multiple of X, each storage device stores one or two members of the stripe; and the method is performed by the control device and comprises:

    determining (S602) that at least one first storage device of the X storage devices is out of service, wherein at least one member of the data stripe is stored in the first storage device;

    the method being characterized by:

    determining that a quantity of out-of-service members reaches a quantity of out-of-service members that is tolerable to the RAID 6;

    updating the members of the data stripe stored on the remaining not out of service storage devices by writing new data to the members; and

    writing (S603) target data into (Y+1) second storage devices of the X storage devices, wherein Y=M-(┌(N+M)/X┐-1), wherein the target data is a data unit or a check unit used to update the at least one member that is stored in the first storage device, and wherein ┌(N + M)/X┐ represents performing rounding up on (N+M)/X, and wherein the target data is obtained through calculation by using the updated members of the data stripe stored on the remaining not out of service storage devices.


     
    2. The method according to claim 1, further comprising: determining that the target data is the data unit or the check unit used to update the at least one member that is stored in the first storage device.
     
    3. A storage system (10), wherein the storage system (10) comprises a redundant array of independent disks, RAID, the RAID comprises a control device (50) and X storage devices (60), a data stripe is stored in the RAID, and the data stripe comprises (N+M) members, N standing for a quantity of data units in the members, M standing for a quantity of check units generated based on the N data units, N>=2, M=2, and the RAID is RAID 6 with N+M=X, or N+M=2X or (N+M)>X, wherein when (N+M)>X and (N+M) is not equal to a multiple of X, each storage device stores one or two members of the stripe;
    wherein each of the X storage devices is configured to store one of the (N+M) members; and
    the control device (50) is configured to:

    determine (S602) that at least one first storage device of the X storage devices is out of service, wherein at least one member of the data stripe is stored in the first storage device;

    and the storage system being characterized in that the control device (50) is configured to:

    determine that a quantity of out-of-service members reaches a quantity of out-of-service members that is tolerable to the RAID 6;

    update the members of the data stripe stored on the remaining not out of service storage devices by writing new data to the members; and

    write (S603) target data into (Y+1) second storage devices of the X storage devices, wherein Y=M- (┌(N+M)/X┐-1), wherein the target data is a data unit or a check unit used to update the at least one member of the data stripe that is stored in the first storage device, and wherein ┌(N+M)/X┐ represents performing rounding up on (N+M)/X, and wherein the target data is obtained through calculation by using the updated members of the data stripe stored on the remaining not out of service storage devices.


     
    4. The system according to claim 3, wherein
    the control device (50) is further configured to determine that the target data is the data unit or the check unit used to update the at least one member that is stored in the first storage device.
     


    Ansprüche

    1. Verfahren zum Schreiben von Daten in ein Speichersystem, wobei das Speichersystem ein redundantes Array unabhängiger Platten (Redundant Array of Independent Disks, RAID) umfasst, wobei das RAID eine Steuervorrichtung (50) und X Speichervorrichtungen (60) umfasst, ein Datenstreifen in dem RAID gespeichert ist und der Datenstreifen (N+M) Elemente umfasst, wobei N eine Quantität von Dateneinheiten in den Elementen steht, M eine Quantität von Prüfeinheiten, die auf der Basis der N Dateneinheiten generiert werden, ist, N>=2 und M=2 ist und ein Typ des RAID RAID 6 mit N+M=X oder N+M=2X oder (N+M)>X ist, wobei, wenn (N+M)>X ist und (N+M) ungleich einem Vielfachen von X ist, jede Speichervorrichtung ein oder zwei Elemente des Streifens speichert; und das Verfahren von der Steuervorrichtung durchgeführt wird und umfasst:

    Feststellen (S602), dass mindestens eine Speichervorrichtung der X Speichervorrichtungen außer Betrieb ist, wobei mindestens ein Element des Datenstreifens in der ersten Speichervorrichtung gespeichert ist;

    wobei das Verfahren gekennzeichnet ist durch:

    Feststellen, dass eine Quantität außer Betrieb befindlicher Elemente eine Quantität von außer Betrieb befindlichen Elementen erreicht, die für das RAID6 annehmbar ist;

    Aktualisieren der Elemente des Datenstreifens, der auf den verbleibenden, nicht außer Betrieb befindlichen Speichervorrichtungen gespeichert ist, durch Schreiben neuer Daten zu den Elementen; und

    Schreiben (S603) von Zieldaten in (Y+1) zweite Speichervorrichtungen der X Speichervorrichtungen, mit Y=M-(┌(N+M)/X┐-1), wobei die Zieldaten eine Dateneinheit oder eine Prüfeinheit sind, die zum Aktualisieren des mindestens einen Elements des Datenstreifens, der in der ersten Speichervorrichtung gespeichert ist, verwendet werden, und wobei ┌(N+M)/X┐ die Durchführung einer Abrundung von (N+M)/X bezeichnet, und wobei die Zieldaten durch Berechnung unter Verwendung der aktualisierten Elemente des Datenstreifens, der auf den verbleibenden, nicht außer Betrieb befindlichen Speichervorrichtungen gespeichert ist, erhalten werden.


     
    2. Verfahren nach Anspruch 1, ferner umfassend: Feststellen, dass die Zieldaten die Dateneinheit oder die Prüfeinheit sind, die zum Aktualisieren des mindestens einen Elements verwendet wird, das in der ersten Speichervorrichtung gespeichert ist.
     
    3. Speichersystem (10), wobei das Speichersystem (10) ein redundantes Array unabhängiger Platten, RAID, umfasst, wobei das RAID eine Steuervorrichtung (50) und X Speichervorrichtungen (60) umfasst, ein Datenstreifen in dem RAID gespeichert wird und der Datenstreifen (N+M) Elemente umfasst, wobei N eine Quantität von Dateneinheiten in den Elementen ist, M eine Quantität von Prüfeinheiten ist, die auf der Basis der N Dateneinheiten generiert werden, N>=2 und M=2 ist und ein Typ des RAID RAID 6 mit N+M=X oder N+M=2X oder (N+M)>X ist, wobei, wenn (N+M)>X ist und (N+M) ungleich einem Vielfachen von X ist, jede Speichervorrichtung ein oder zwei Elemente des Streifens speichert;
    wobei jede der X Speichervorrichtungen konfiguriert ist, eines der (N+M) Elemente zu speichern; und
    die Steuervorrichtung (50) konfiguriert ist:

    festzustellen (S602), dass mindestens eine erste Speichervorrichtung der X Speichervorrichtungen außer Betrieb ist, wobei mindestens ein Element des Datenstreifens in der ersten Speichervorrichtung gespeichert ist;

    und wobei das Speichersystem dadurch gekennzeichnet ist, dass die Steuervorrichtung (50) konfiguriert ist:

    festzustellen, dass eine Quantität außer Betrieb befindlicher Elemente eine Quantität von außer Betrieb befindlichen Elementen erreicht, die für das RAID 6 annehmbar ist;

    Elemente des Datenstreifens, der auf den verbleibenden, nicht außer Betrieb befindlichen Speichervorrichtungen gespeichert ist, durch Schreiben neuer Daten zu den Elementen zu aktualisieren; und

    Zieldaten in (Y+1) zweiten Speichervorrichtungen der X Speichervorrichtungen zu schreiben (S603), wobei Y=M-(┌(N+M)/X┐-1) ist, wobei die Zieldaten eine Dateneinheit oder eine Prüfeinheit sind, die zum Aktualisieren des mindestens einen Elements des Datenstreifens, der in der ersten Speichervorrichtung gespeichert ist, verwendet werden, und wobei ┌(N+M)/X┐ die Durchführung einer Abrundung von (N+M)/X bezeichnet, und wobei die Zieldaten durch Berechnung unter Verwendung der aktualisierten Elemente des Datenstreifens, der auf den verbleibenden, nicht außer Betrieb befindlichen Speichervorrichtungen gespeichert ist, erhalten werden.


     
    4. System nach Anspruch 3, wobei
    die Steuervorrichtung (50) ferner konfiguriert ist, festzustellen, dass die Zieldaten die Dateneinheit oder die Prüfeinheit sind, die zum Aktualisieren des mindestens einen Elements des Datenstreifens, der auf der ersten Speichervorrichtung gespeichert ist, verwendet werden.
     


    Revendications

    1. Procédé d'écriture de données dans un système de stockage, dans lequel le système de stockage comprend un réseau redondant de disques indépendants, RAID, le RAID comprend un dispositif de commande (50) et X dispositifs de stockage (60), une bande de données est stockée dans le RAID, et la bande de données comprend (N+M) éléments, N représentant une quantité d'unités de données dans les éléments, M représentant une quantité d'unités de vérification générées sur la base des N unités de données, N ≥ 2, M = 2, et le RAID est un RAID 6 avec N+M = X ou N+M = 2X ou (N+M) > X, dans lequel, quand (N+M) > X et (N+M) n'est pas égal à un multiple de X, chaque dispositif de stockage stocke un ou deux éléments de la bande ; et le procédé est effectué par le dispositif de commande et comprend :

    la détermination (S602) qu'au moins un premier dispositif de stockage parmi les X dispositifs de stockage est hors service, au moins un élément de la bande de données étant stocké dans le premier dispositif de stockage ;

    le procédé étant caractérisé par :

    la détermination qu'une quantité d'éléments hors service atteint une quantité d'éléments hors service qui est tolérable pour le RAID 6 ;

    la mise à jour des éléments de la bande de données stockés sur les dispositifs de stockage non hors service restants par écriture de nouvelles données sur les éléments ; et

    l'écriture (S603) de données cibles dans (Y+1) deuxièmes dispositifs de stockage parmi les X dispositifs de stockage, dans lequel Y= M - (┌(N+M)/X┐-1), dans lequel les données cibles constituent une unité de données ou une unité de vérification utilisée pour mettre à jour l'au moins un élément qui est stocké dans le premier dispositif de stockage, et dans lequel ┌(N+M)/X┐ représente la réalisation d'un arrondi sur (N+M)/X, et dans lequel les données cibles sont obtenues par calcul en utilisant les éléments mis à jour de la bande de données stockés sur les dispositifs de stockage non hors service restants.


     
    2. Procédé selon la revendication 1, comprenant en outre : la détermination que les données cibles constituent l'unité de données ou l'unité de vérification utilisée pour mettre à jour l'au moins un élément qui est stocké dans le premier dispositif de stockage.
     
    3. Système de stockage (10), le système de stockage (10) comprenant un réseau redondant de disques indépendants, RAID, le RAID comprenant un dispositif de commande (50) et X dispositifs de stockage (60), une bande de données étant stockée dans le RAID, et la bande de données comprenant (N+M) éléments, N représentant une quantité d'unités de données dans les éléments, M représentant une quantité d'unités de vérification générées sur la base des N unités de données, N ≥ 2, M = 2, et le RAID étant un RAID 6 avec N+M = X ou N+M = 2X ou (N+M) > X, dans lequel, quand (N+M) > X et (N+M) n'est pas égal à un multiple de X, chaque dispositif de stockage stocke un ou deux éléments de la bande ;
    dans lequel chacun des X dispositifs de stockage est configuré pour stocker un des (N+M) éléments ; et
    le dispositif de commande (50) est configuré pour :

    déterminer (S602) qu'au moins un premier dispositif de stockage parmi les X dispositifs de stockage est hors service, au moins un élément de la bande de données étant stocké dans le premier dispositif de stockage ;

    et le système de stockage étant caractérisé en ce que le dispositif de commande (50) est configuré pour :

    déterminer qu'une quantité d'éléments hors service atteint une quantité d'éléments hors service qui est tolérable pour le RAID 6 ;

    mettre à jour les éléments de la bande de données stockés sur les dispositifs de stockage non hors service restants en écrivant de nouvelles données sur les éléments ; et

    écrire (S603) des données cibles dans (Y+1) deuxièmes dispositifs de stockage parmi les X dispositifs de stockage, dans lequel Y= M - (┌(N+M)/X┐-1), dans lequel les données cibles constituent une unité de données ou une unité de vérification utilisée pour mettre à jour l'au moins un élément de la bande de données qui est stocké dans le premier dispositif de stockage, et dans lequel ┌(N+M)/X┐ représente la réalisation d'un arrondi sur (N+M)/X, et dans lequel les données cibles sont obtenues par calcul en utilisant les éléments mis à jour de la bande de données stockés sur les dispositifs de stockage non hors service restants.


     
    4. Système selon la revendication 3, dans lequel
    le dispositif de commande (50) est également configuré pour déterminer que les données cibles constituent l'unité de données ou l'unité de vérification utilisée pour mettre à jour l'au moins un élément qui est stocké dans le premier dispositif de stockage.
     




    Drawing

































    REFERENCES CITED IN THE DESCRIPTION



    This list of references cited by the applicant is for the reader's convenience only. It does not form part of the European patent document. Even though great care has been taken in compiling the references, errors or omissions cannot be excluded and the EPO disclaims all liability in this regard.

    Patent documents cited in the description