CN112395264B - Processing method for mapping between logical targets and volumes in distributed storage system - Google Patents
Processing method for mapping between logical targets and volumes in distributed storage system Download PDFInfo
- Publication number
- CN112395264B CN112395264B CN202011352601.0A CN202011352601A CN112395264B CN 112395264 B CN112395264 B CN 112395264B CN 202011352601 A CN202011352601 A CN 202011352601A CN 112395264 B CN112395264 B CN 112395264B
- Authority
- CN
- China
- Prior art keywords
- target
- logical
- mapping
- volume
- client
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000013507 mapping Methods 0.000 title claims abstract description 111
- 238000003672 processing method Methods 0.000 title abstract description 8
- 238000000034 method Methods 0.000 claims abstract description 27
- 230000007246 mechanism Effects 0.000 claims abstract description 14
- 230000008569 process Effects 0.000 claims abstract description 13
- 230000008859 change Effects 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims description 11
- 238000012986 modification Methods 0.000 claims description 4
- 230000004048 modification Effects 0.000 claims description 4
- 238000007726 management method Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 238000013500 data storage Methods 0.000 description 4
- 239000003999 initiator Substances 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000013475 authorization Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/18—File system types
- G06F16/182—Distributed file systems
- G06F16/1824—Distributed file systems implemented using Network-attached Storage [NAS] architecture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0604—Improving or facilitating administration, e.g. storage management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0662—Virtualisation aspects
- G06F3/0665—Virtualisation aspects at area level, e.g. provisioning of virtual or logical volumes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/067—Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a processing method of mapping between logical targets and volumes in a distributed storage system, which comprises the following steps: s1, storing target mapping information in a distributed storage system, wherein the target mapping information comprises a mapping relation between a gateway node and a logic target, a mapping relation between the logic target and a volume and a mapping relation between the logic target and a client; s2, loading and exposing the logic target to the outside through the SCSI gateway based on the target mapping information so as to process the access request sent by the client; s3, subscribing the SCSI gateway to change notification of the target mapping information and/or the configuration information in the distributed storage system based on a subscription notification mechanism; notifying a SCSI gateway subscribed to the change notification when the user modifies the target mapping information and/or the configuration information; and S4, when the SCSI gateway receives the change notification, reloading the metadata mapping table maintained in the storage cluster of the distributed storage system, and updating the mapping relation between the corresponding logic target and the volume based on the latest metadata mapping table.
Description
Technical Field
The invention relates to the field of data storage management, in particular to a processing method for mapping between logical targets and volumes in a distributed storage system.
Background
The rapid development of science and technology makes data exponentially grow, people pay more attention to the safety and reliability and the read-write efficiency of the data, and meanwhile, the traditional single-medium data storage mode cannot meet the requirement of large data processing. The distributed storage system with the characteristics of safety, reliability, read-write efficiency, expandability, low cost and the like is derived, and the system architecture consists of a group of computer nodes which communicate through a network and coordinate to complete common tasks. In a distributed storage system, a plurality of data nodes and gateway nodes are typically established. The data node is used for data storage; the gateway node is used for providing an interface, such as SCSI, FC, etc., to the outside, and the external device can access the data node to access the data by connecting the gateway node. The distributed storage has significantly improved performance, high reliability, easy expansion, low cost and the like compared with the traditional storage, but at the same time, various difficulties are brought to the proposal, such as message notification and information synchronization among multiple nodes, volume mapping and volume mounting management and the like.
Disclosure of Invention
The invention mainly aims to solve the problems of message notification and information synchronization among multiple nodes and the problems of mapping between a logic target and a volume among multiple node targets in the existing distributed storage system, and provides a processing method of mapping between the logic target and the volume in the distributed storage system so as to solve the problems of the existing distributed storage system.
In order to achieve the above purpose, the invention adopts the following technical scheme:
A processing method of mapping between logical objects and volumes in a distributed storage system includes the following steps: s1, storing target mapping information in a distributed storage system, wherein the target mapping information comprises a mapping relation between a gateway node and a logic target, a mapping relation between the logic target and a volume and a mapping relation between the logic target and a client; s2, loading and exposing the logic target to the outside through a target device on the SCSI gateway based on the target mapping information so as to process an access request sent by the client; s3, based on a subscription notification mechanism, subscribing the target device to change notification of the target mapping information and/or configuration information in the distributed storage system; notifying a target device which has subscribed to the change notification when a user modifies target mapping information and/or configuration information; and S4, after the target device receives the notification about the user modification target mapping information and/or configuration information, reloading the metadata mapping table maintained in the storage cluster of the distributed storage system, and updating the mapping relation between the corresponding logic target and the volume based on the latest metadata mapping table.
The invention has the beneficial effects that: the client accesses the logic target associated with the node to access the volume associated with the logic target through the gateway node, and after the logic target is associated with the volume, the metadata information associated with the logic target and the volume is pushed to all gateway nodes associated with the logic target by utilizing a subscription notification mechanism of the distributed storage system, so that the problem of message synchronization among a plurality of gateway nodes is solved; on the other hand, through reasonable metadata management, the metadata is more reliable and efficient in adding, deleting, modifying and querying, and the client can access the correct volume in a huge and complex distributed storage system.
Drawings
FIG. 1 is a schematic diagram of interactions between a client, a target, and a storage cluster in a distributed storage system;
FIG. 2 is a schematic diagram of a process for mapping volumes to logical targets;
FIG. 3 is a logical target creation flow diagram;
FIG. 4 is a flow chart of a logical target associated with a volume;
fig. 5 is a flow chart of a logical target associated with a client.
Detailed Description
The invention will be further described with reference to the drawings and the detailed description.
The abbreviations, english terms and other technical terms appearing in the present embodiment are explained first.
SCSI, smallComputerSystemInterface, small computer system interface.
ISCSI, internetSmallComputerSystemInterface, small computer System interface over the Internet. In distributed storage, the iSCSI architecture defines the provider of the storage service as iSCSItgt, the storage server, for converting SCSI commands and data in TCP/IP packets; while the user of the storage service is defined as iSCSIinitiator for generating SCSI requests and encapsulating SCSI commands and data into TCP/IP packets to be sent to the IP network, i.e., the storage client. And the storage server side and the storage client side communicate based on TCP, and the storage server side maps the block storage equipment into volumes to be provided for the storage client side, so that the remote block storage service is realized.
The target (Linuxtargetframework, tgt) is an architecture proposed for creating and maintaining storage-server drives, the target is a logical target stored in tgt, and the target is indirectly integrated into the SCSI middle layer. tgt is a process running independently and takes the role of an iSCSI server. After the storage server creates the target, the relevant target and volume mapping information can be saved in the target. The target may receive and process the request initiated by the storage client and feed back the processing result to the storage client. The iSCSI client may access its target through tgt to access the associated volume at the target. And creating and starting a target service process on the gateway node, receiving and processing an iSCSI instruction initiated by the client, storing target and volume mapping information sent by the storage server, and transmitting IO (input and output of data) to the storage server to complete data reading and writing.
And (3) roll mounting: a volume (lun) is a storage area on a hard disk, and a drive formats the volume using a file system (e.g., FAT or NTFS) and assigns it a drive number; mounting refers to attaching a device (typically a storage device) to a directory and accessing the mounted device through the directory. In a distributed storage system, a data writing end and a data storage end are often not directly connected, namely, data to be written and a volume to be written are submitted at a client, a server is notified in a network communication mode, and then data writing is completed at the server. Therefore, the mounted volume is a precondition for data reading and writing in the distributed storage.
The watch/notify mechanism subscribes to the notification mechanism, subscribes to messages through the watch, and publishes messages through notify. The distributed storage system provides a watch/notify mechanism that solves the problem of communication between multiple gateway nodes. The client registers the watch object with the OSD (objectstoragedevice, object store daemon) and maintains a session connection with the main OSD. The client can send notification messages and message content to all clients (also called watchers) that have registered watch objects and receive notifications when the watchers receive the notifications, which allows the client to use any object as a synchronous communication channel. For example, three clients register a watch object with the OSD respectively, and keep session connection with the OSD, when one client pushes a message to the OSD, the OSD pushes the message to all clients registered with the watch object after receiving the message.
The cluster records and maintains metadata information of target mapping, including target information, mapping volume information, mapping relation between gateway node and target, and mapping relation between target and volume. These metadata information are saved into the four types of objects of the metadata map tables target.nodes.map.list, target.lus.map.list, node.targets.list and target.list in fig. 1, it should be understood that the node1, node2, target.list in fig. 1 are only node.targets.list corresponding to two nodes distinguished by numerals 1, 2; as does the target. Meanwhile, the cluster provides interfaces for adding, deleting, modifying and checking the four objects to finish updating the metadata.
The gateway node, namely the SCSI gateway in the invention, namely the node where tgt is located, is a bridge for connecting communication between the client and the storage cluster. And the notification and the data synchronization of the messages are completed between the tgt and the storage clusters through a watch/notify mechanism, so that when the tgt is started, a watch object is established by taking the name of a node plus ". Tgt.watch.list" as the name. Thereafter, the cluster need only issue a message to the object notify to complete the notification of the cluster to tgt. And each time the metadata information is modified, the configuration tool calls a notify method to issue modified contents to the nodes tgt, and after the notification is received, the metadata mapping table is reloaded, and the corresponding volume mapping relation is updated based on the latest metadata mapping table. In order to avoid the failure of the watch/notify mechanism, the gateway node periodically reads the metadata mapping table, and keeps the metadata information recorded in the memory consistent with the metadata information recorded in the distributed storage. the tgt and the client end complete interaction through the iSCSI protocol, so that the tgt has the capability of analyzing and processing the iSCSI protocol, and when the tgt interacts with the client end, the tgt directly returns to the metadata mapping table stored in the memory of the tgt. In the distributed storage system, the interaction relationship among an initiator (client), a tgt (target) and a cluster (storage cluster) is shown in fig. 1, the initiator directly interacts with the target tgt created on a gateway node (node), the target receives and processes an iSCSI request initiated by the client, receives and stores information of target and volume mapping pushed by the cluster, and issues an IO to the storage cluster.
The client, i.e. the stored user, completes the interaction with tgt through iSCSI protocol: and acquiring a target list maintained in tgt, and accessing the associated volume under the target by adding access control authority to the target. The same initiator can authorize access to a plurality of targets, and for an initiator without authorization, luns on the targets cannot be accessed, so that control of lun access authority is realized through the logical targets, and the effect of isolating luns is achieved. Finally, the client accesses the associated volume under the target, i.e. the lun mask (volume mount) process, through the target, an exemplary volume mount flow is shown in fig. 2, and pool is a logical pool; an image is defined in the logic pool, and the image is a logic unit for storing data corresponding to the internal storage lun; luns are externally exposed logical volumes that define more structures and interfaces to manipulate images.
In the invention, the storage server combines the application of the iSCSI technology and the tgt technology to develop the target service program, and the target works in the gateway node. In order to ensure message notification and data synchronization between gateway nodes, nodes and storage clusters, a watch/notify mechanism provided by ceph (i.e., a distributed storage system) is used, i.e., a watch object is registered at each node and storage cluster, and message notification is completed by notify to the watch object.
The embodiment of the invention provides a processing method of mapping between targets and volumes in a distributed storage system, which is used for solving the problem of target and volume mapping among multi-node targets in the distributed storage system, and particularly shows the problem of 1, message synchronization: the client accesses the target associated with the target through the gateway node to access the volume associated with the target, so after the target and the volume are associated, the metadata information associated with the target and the volume is pushed to all gateway nodes associated with the target; 2. mapping management difficulties: there are often thousands of gateway nodes, volumes, and clients in a distributed storage system, and how to ensure that clients access the correct volumes requires a good management scheme to be established.
The processing method for mapping between the target and the volume in the distributed storage system provided by the embodiment comprises the following steps:
S1, storing target mapping information in a distributed storage system, wherein the mapping information comprises a mapping relation between a gateway node and a logic target, a mapping relation between the logic target and a volume and a mapping relation between the logic target and a client;
s2, loading and exposing a logic target externally through a target device on the SCSI gateway based on the target mapping information so as to process an access request sent by the client;
S3, based on a subscription notification mechanism, subscribing a target device on the SCSI gateway to change notification of the target mapping information and/or configuration information in the distributed storage system; notifying a target device which has subscribed to the change notification when a user modifies target mapping information and/or configuration information;
And S4, after the target device receives the notification about the user modification target mapping information and/or configuration information, reloading the metadata mapping table maintained in the storage cluster of the distributed storage system, and updating the mapping relation between the corresponding logic target and the volume based on the latest metadata mapping table.
For ease of description of the process, the present invention assumes that the customer needs to mount a volume to access the data within the volume, and a series of preparatory actions need to be performed prior to mounting, including: ① Creating a target; ② create a volume; ③ target is associated with volume (volume map); ④ the target is associated with the client.
① Creating a target: the mapping of the volume is that the volume is actually mapped to the target, and the client side accesses the target through a command to mount the volume, so that the target needs to be created first. the target creation flow is shown in fig. 3, and includes:
The user sends a target creation instruction through a configuration tool at the client; information indicating a target name and at least one access gateway is needed in the instruction;
Before executing the instruction, the configuration tool checks validity of the target name and whether the current target list already contains the target to be created or not: if the target name is illegal or the target to be created is already contained in the current target list, the target creation instruction is not executed and the information of failure execution is returned; if the target name is legal and the target to be created is not contained in the current target list, the configuration tool directly calls a target creation interface externally provided by the cluster to complete the creation of the target. When in creation, the created target information is written into the target-gateway node mapping table object target.nodes.map.list, wherein the target information comprises a target name, a type, a read-write attribute, creation time and an access node, the information of the target in the metadata information is stored in a key-value pair form, a key item is the target name, and the value comprises the target name, the read-write attribute, the target type, the creation time and the access node.
After the target is created, the configuration tool pushes an update message to all targets of SCSI gateways associated with the created logical target, specifically, the configuration tool pushes a message about the target update to the main OSD through a Notify method, and the main OSD pushes an update message to all targets on the SCSI gateway registered with the watch object. And after receiving the update message, the target on the SCSI gateway reloads the metadata mapping table, and updates the mapping relation between the corresponding logic target and the volume based on the latest metadata mapping table.
② Creating a volume: creating a volume refers to creating an empty volume, and this process only records volume information, such as volume name, logical pool to which it belongs, and volume size, and does not actually allocate storage space.
③ Target is associated with volume (volume map): the action of associating a target with a volume, which may also be referred to as mapping of a volume, is shown in fig. 4, and includes:
The user issues an associated instruction of the target and the volume through the configuration tool, and the associated target name and the volume name need to be indicated in the instruction;
Before the configuration tool executes the association instruction, it is checked whether the target and volume to be associated have been created and whether they have been associated: only when the target and the volume to be associated are created and are not associated, the configuration tool executes the association instruction of the target and the volume, namely directly calls an association interface externally provided by the cluster to complete the association of the target and the volume; otherwise, the configuration tool does not execute the target and volume association instruction and returns the execution failure information. During association, writing lun information (key is a target name, value is a logical pool to which luns belong, lun-id and a list container consisting of snapshot names) into a target.luns.MAP.list object; creating a target. List object and updating information of all volumes associated with the target.
After the association of the target and the volume is completed, the configuration tool pushes update messages to all the targets of the SCSI gateways associated with the target, specifically, the configuration tool pushes messages about target mapping relation update to the main OSD through a Notify method, and the main OSD pushes update messages to all the targets on the SCSI gateways registered with the watch object. And after receiving the update message, the target on the SCSI gateway reloads the metadata mapping table, and updates the mapping relation between the corresponding logic target and the volume based on the latest metadata mapping table.
④ Target is associated with the client: before the target is associated with the client, the client needs to initiate an iSCSI scanning action to the gateway node where tgt is located, so that tgt "knows" the information of the client, and the association of the target and the client can be performed after the scanning is completed. The mode of initiating the scan is: the user uses iscsiadm scanning command at the client, and inputs iscsiadm-mdiscovery-tst-p < ip >, which is the ip address of the gateway node to be scanned. the flow of associating the target with the client is shown in fig. 5, and includes:
the user issues an association instruction of the target and the client through the configuration tool, wherein the association instruction needs to indicate the target name and the client name to be associated;
Before the configuration tool executes the instruction, it is checked whether the target to be associated has been created and whether the target has been associated with the client: only when a target to be associated is created and is not associated with a client, the configuration tool executes an associated instruction of the target and the client, namely directly calls an associated interface provided outside the storage cluster to complete the association of the target and the client; otherwise, the configuration tool does not execute the associated instruction of the target and the client and returns the information of the execution failure. When the target is associated, the client information associated with the target is written into the target.
After the association of the target and the client is completed, the configuration tool pushes update messages to all targets of the SCSI gateways associated with the target, specifically, the configuration tool pushes messages about target mapping relation update to the main OSD through a Notify method, and the main OSD pushes update messages to all targets on the SCSI gateways registered with the watch object. And after receiving the update message, the target on the SCSI gateway reloads the metadata mapping table, and updates the mapping relation between the corresponding logic target and the client based on the latest metadata mapping table.
The association of the client side to the target and the association of the target to the volume are completed, and the client can access the volume associated under the target only by adding access control authority to the target, namely, the volume mounting is completed. The process of adding access control rights to the target is also called login, and the login mode is as follows: the client uses iscsiadm command to input iscsiadm-mnode-T < iqn:target > -l, the iqn:target is a character string spliced by iqn as prefix and target name, and after the target is associated with the client, the client executes scanning command iscsiadm-mdiscovery-tst-p < ip >, initiates scanning to SCSI gateway node, and obtains target list on the gateway node. After successful login, the client establishes a session with tgt, and the session is used when the associated volume under the target is read and written.
The foregoing embodiments of the present invention provide a reasonable metadata management mechanism for metadata management such as target information, volume information, a mapping relationship between a target and a volume, a mapping relationship between a target and a gateway node, and a mapping relationship between a target and a client in a distributed storage system, so that metadata can be added, deleted, modified, and queried more reliably and efficiently. Meanwhile, a switch/notify mechanism of ceph is used to solve the problems of message synchronization and communication about the change of the mapping relationship between the targets of multiple nodes and between the targets and the storage clusters in the distributed storage system.
The foregoing is a further detailed description of the invention in connection with the preferred embodiments, and it is not intended that the invention be limited to the specific embodiments described. It will be apparent to those skilled in the art that several equivalent substitutions and obvious modifications can be made without departing from the spirit of the invention, and the same should be considered to be within the scope of the invention.
Claims (10)
1. A method for processing a mapping between logical objects and volumes in a distributed storage system, comprising the steps of:
s1, storing target mapping information in a distributed storage system, wherein the target mapping information comprises a mapping relation between a gateway node and a logic target, a mapping relation between the logic target and a volume and a mapping relation between the logic target and a client;
S2, loading and exposing the logic target to the outside through a target device on the SCSI gateway based on the target mapping information so as to process an access request sent by the client;
S3, based on a subscription notification mechanism, subscribing the target device to change notification of the target mapping information and/or configuration information in the distributed storage system; notifying a target device which has subscribed to the change notification when a user modifies target mapping information and/or configuration information;
And S4, after the target device receives the notification about the user modification target mapping information and/or configuration information, reloading the metadata mapping table maintained in the storage cluster of the distributed storage system, and updating the mapping relation between the corresponding logic target and the volume based on the latest metadata mapping table.
2. The method for processing the mapping between logical objects and volumes in the distributed storage system according to claim 1, wherein in step S3: in order to avoid the failure of the subscription notification mechanism, the target on the SCSI gateway is configured to periodically read the metadata mapping table, so that metadata information recorded in the memory of the SCSI gateway is consistent with metadata information recorded in the metadata mapping table.
3. The method of claim 1, wherein the logical object to volume mapping is established by creating a logical object, creating a volume, and associating the volume with the logical object.
4. The method for processing the mapping between logical objects and volumes in the distributed storage system according to claim 3, wherein creating the logical objects comprises:
The user issues a target creation instruction through a configuration tool; the target creation instruction comprises a logic target name and information of at least one access gateway;
The configuration tool checks the validity of the name of the logic target and whether the logic target to be created is contained in the current target list: if the logical object name is illegal or the current object list contains the logical object to be created, not executing the object creation instruction and returning information of execution failure; if the logical target name is legal and the current target list does not contain the logical target to be created, the configuration tool directly calls a target creation interface provided outside the storage cluster to complete the creation of the logical target;
After the creation of the logical target is completed, the configuration tool pushes update messages to all the targets of the SCSI gateway associated with the created logical target;
And after receiving the update message, the SCSI gateway reloads the metadata mapping table and updates the mapping relation between the corresponding logical target and the volume based on the latest metadata mapping table.
5. The method of claim 4, wherein the configuration tool checks validity of the logical object name and whether the logical object to be created is already included in the current object list by acquiring metadata from the storage cluster.
6. The method of claim 4, wherein the configuration tool, when invoking the storage cluster to create a logical object for an externally provided object creation interface, writes logical object information to the object-gateway node mapping table object, the logical object information including a name, a type, a read-write attribute, a creation time, and an access node of the logical object.
7. The method of processing a mapping between logical objects and volumes in a distributed storage system of claim 3, wherein associating volumes with logical objects comprises:
the user issues an associated instruction of the logic target and the volume through a configuration tool;
The configuration tool checks whether a logical target and volume to be associated have been created and associated: only when the logic target and the volume to be associated are created and are not associated, the configuration tool executes the association instruction of the logic target and the volume, and directly invokes an association interface provided outside the storage cluster to complete the association of the logic target and the volume; otherwise, the configuration tool does not execute the associated instruction of the logical object and the volume and returns information of execution failure;
After the association of the logical target with the volume is completed, the configuration tool pushes update messages to all of the targets of the SCSI gateways associated with the logical target;
And after receiving the update message, the SCSI gateway reloads the metadata mapping table and updates the mapping relation between the corresponding logical target and the volume based on the latest metadata mapping table.
8. The method of processing mappings between logical objects and volumes in a distributed storage system of claim 7, wherein the configuration tool checks whether logical objects and volumes to be associated have been created and associated by retrieving metadata from a storage cluster.
9. The method for processing the mapping between the logical object and the volume in the distributed storage system according to claim 1, wherein the mapping relationship between the logical object and the client is obtained by associating the logical object with the client, and the association between the logical object and the client comprises:
The user issues an association instruction of the logic target and the client through the configuration tool, wherein the association instruction needs to indicate the name of the logic target to be associated and the name of the client;
the configuration tool checks whether a logical object to be associated has been created and whether the logical object has been associated with the client: only when a logic target to be associated is created and is not associated with a client, the configuration tool executes an association instruction of the logic target and the client, and directly invokes an association interface provided outside the storage cluster to complete association of the logic target and the client; otherwise, the configuration tool does not execute the associated instruction of the logic target and the client and returns the information of failure execution;
After the association of the logical object with the client is completed, the configuration tool pushes update messages to all the targets of the SCSI gateway associated with the logical object;
And after receiving the update message, the SCSI gateway reloads the metadata mapping table, and updates the mapping relation between the corresponding logic target and the client based on the latest metadata mapping table.
10. The method for processing the mapping between the logical object and the volume in the distributed storage system according to claim 1, wherein after the association between the logical object and the client and the association between the logical object and the volume are completed, the user can access the volume associated under the logical object by adding the access control authority to the logical object, i.e. complete the volume mount.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011352601.0A CN112395264B (en) | 2020-11-26 | 2020-11-26 | Processing method for mapping between logical targets and volumes in distributed storage system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011352601.0A CN112395264B (en) | 2020-11-26 | 2020-11-26 | Processing method for mapping between logical targets and volumes in distributed storage system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112395264A CN112395264A (en) | 2021-02-23 |
| CN112395264B true CN112395264B (en) | 2024-05-28 |
Family
ID=74604548
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011352601.0A Active CN112395264B (en) | 2020-11-26 | 2020-11-26 | Processing method for mapping between logical targets and volumes in distributed storage system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112395264B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113489784B (en) * | 2021-07-05 | 2024-05-17 | 深圳市杉岩数据技术有限公司 | Method and system for realizing multipath access of asymmetric logic unit of distributed storage |
| CN113630450B (en) * | 2021-07-26 | 2024-03-15 | 深圳市杉岩数据技术有限公司 | Access control method of distributed storage system and distributed storage system |
| CN113721849B (en) * | 2021-08-23 | 2024-04-12 | 深圳市杉岩数据技术有限公司 | Data copying and unloading method based on distributed storage and terminal equipment |
| CN113746641B (en) * | 2021-11-05 | 2022-02-18 | 深圳市杉岩数据技术有限公司 | ODX protocol processing method based on distributed storage |
| CN114461388B (en) * | 2022-01-13 | 2024-01-12 | 苏州浪潮智能科技有限公司 | Block storage service metadata configuration method, device, equipment and medium |
| CN114564153B (en) * | 2022-02-28 | 2023-08-18 | 苏州浪潮智能科技有限公司 | Volume mapping relieving method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7281062B1 (en) * | 2002-04-22 | 2007-10-09 | Cisco Technology, Inc. | Virtual SCSI bus for SCSI-based storage area network |
| CN109672714A (en) * | 2017-10-17 | 2019-04-23 | 中移(苏州)软件技术有限公司 | A kind of data processing method and distributed memory system of distributed memory system |
| CN109992433A (en) * | 2019-04-11 | 2019-07-09 | 苏州浪潮智能科技有限公司 | A kind of distribution tgt communication optimization method, apparatus, equipment and storage medium |
| CN111273869A (en) * | 2020-01-20 | 2020-06-12 | 苏州浪潮智能科技有限公司 | Distributed storage system performance optimization method, system, electronic device and medium |
| CN111464622A (en) * | 2020-03-30 | 2020-07-28 | 星辰天合（北京）数据科技有限公司 | Volume mapping processing method and device in distributed storage system |
-
2020
- 2020-11-26 CN CN202011352601.0A patent/CN112395264B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7281062B1 (en) * | 2002-04-22 | 2007-10-09 | Cisco Technology, Inc. | Virtual SCSI bus for SCSI-based storage area network |
| CN109672714A (en) * | 2017-10-17 | 2019-04-23 | 中移(苏州)软件技术有限公司 | A kind of data processing method and distributed memory system of distributed memory system |
| CN109992433A (en) * | 2019-04-11 | 2019-07-09 | 苏州浪潮智能科技有限公司 | A kind of distribution tgt communication optimization method, apparatus, equipment and storage medium |
| CN111273869A (en) * | 2020-01-20 | 2020-06-12 | 苏州浪潮智能科技有限公司 | Distributed storage system performance optimization method, system, electronic device and medium |
| CN111464622A (en) * | 2020-03-30 | 2020-07-28 | 星辰天合（北京）数据科技有限公司 | Volume mapping processing method and device in distributed storage system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112395264A (en) | 2021-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112395264B (en) | Processing method for mapping between logical targets and volumes in distributed storage system | |
| KR100350141B1 (en) | An application interface to a media server and a method of implementing the same | |
| US10732836B2 (en) | Remote one-sided persistent writes | |
| US7783737B2 (en) | System and method for managing supply of digital content | |
| US20100299306A1 (en) | Storage system having file change notification interface | |
| US10127054B2 (en) | Bootstrapping server using configuration file stored in server-managed storage | |
| US11386015B2 (en) | Methods for managing storage systems with dualport solid-state disks accessible by multiple hosts and devices thereof | |
| US7818390B2 (en) | Method for transferring data between terminal apparatuses in a transparent computation system | |
| US10872036B1 (en) | Methods for facilitating efficient storage operations using host-managed solid-state disks and devices thereof | |
| US20090006619A1 (en) | Directory Snapshot Browser | |
| CN114265814B (en) | Data lake file system based on object storage | |
| CN113746641B (en) | ODX protocol processing method based on distributed storage | |
| WO2024082857A1 (en) | Data migration method and system, and related apparatus | |
| CN114365109A (en) | RDMA-enabled key-value store | |
| CN114490540B (en) | Data storage method, medium, device and computing equipment | |
| JP2007287180A (en) | Distributed file system, distributed file system server, and method for accessing distributed file system | |
| WO2023097229A1 (en) | Fast database scaling utilizing a decoupled storage and compute architecture | |
| US20230169093A1 (en) | Fast database scaling utilizing a decoupled storage and compute architecture | |
| CN113377714A (en) | Target renaming method and device based on distributed storage system | |
| US11537597B1 (en) | Method and system for streaming data from portable storage devices | |
| JP2006185463A (en) | Gateway device | |
| JP3143919B2 (en) | Communication parameter management method | |
| CN115102972A (en) | Method, device, equipment and medium for storing NFS (network file system) file | |
| CN116662264A (en) | Data management method, device, equipment and storage medium thereof | |
| CN118132205A (en) | Management method and device of desktop cloud virtual machine, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |