KR20150061314A - Method and System for recovery of iSCSI storage system used network distributed file system - Google Patents

Abstract

The present invention relates to a method and a system capable of effectively recovering a fault occurring in an asymmetric cluster distributed file system using an iSCSI storage system. The present invention relates to a method for recovering a fault of an iSCSI storage system using a network distributed file system, which comprises: a first step where a block layout manager records at least one of read and write type information, data size information, and LUN information when a specific iSCSI initiator processes an iSCSI block read and write request of a specific iSCSI target that belongs to a specific gateway; a second step where the block layout manager transmits at least one information, among the read and write type information, data size information, and LUN information, to an iSCSI session manager; a third step where the iSCSI session manager counts the information by each iSCSI gateway; a fourth step where the iSCSI session manager updates iSCSI gateway ranking indexes in the information aggregated by each iSCSI gateway; a fifth step where the iSCSI session manager monitors whether or not each iSCSI gateway has a fault through an agent installed in each iSCSI gateway; and a sixth step of distributing and generating all iSCSI targets that belong to a faulty iSCSI gateway to a normal iSCSI gateway when the iSCSI session manager determines that a certain iSCSI gateway has a fault.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to a method and system for recovering from a network distributed file system based on an iSCSI storage system,

The present invention relates to a method and system for effectively recovering a failure in an asymmetric cluster distributed file system based iSCSI storage system.

In recent years, with the rapid development of the Internet technology, the transmission of multimedia data such as photographs and moving images has been dramatically increased. Therefore, a company providing a multimedia data transmission service using the Internet has generated a very large amount of data. Therefore, it is urgent to introduce a system capable of effectively distributing and managing a large amount of data.

Recently, advances in storage system or file system technology have greatly improved the scalability and performance of storage systems. In terms of the file system structure, some systems are trying to build a so-called asymmetric cluster file system that separates the data input / output path of the file and the metadata management path of the file, thereby improving the scalability and performance of the distributed storage system.

This structure allows the client system to directly access the storage devices and also increases storage scalability by avoiding bottlenecks caused by frequent file accesses. For example, IBM's StorageTank and Panasas 'ActiveScale Storage Cluster, Cluster Filesystems' Luster, Hadoop's DFS, and Google's Google Filesystem were developed based on this architecture.

In such a network-based distributed file system environment, an application server, a metadata server, and a data server communicate with each other via a network to provide data input / output. In order for the application server to access a specific file, the metadata server obtains the location information of the block in which the actual data of the file is stored, accesses the data server storing the actual data using the location information, Data is obtained.

However, in order to perform block data input / output service using an iSCSI protocol based on an asymmetric distributed file system, a module (iSCSI gateway) for creating an iSCSI target and connecting the storage area of the distributed file system is required. One unit iSCSI gateway generates an iSCSI target based on a plurality of ISCN (iSCSI Qualified Names) and provides block data input / output services to a plurality of clients, that is, an iSCSI initiator on the application server. However, some of the iSCSI gateways may be shut down due to hardware failures such as CPU, memory, network card, and power supply. Therefore, all iSCSI targets of failed iSCSI gateways must be able to be transferred to the normal iSCSI gateways so that block data I / O services can continue to be maintained even in the event of failure of some iSCSI gateways.

Therefore, the present invention is applicable to a case where a failure occurs in some iSCSI gateways such as a part of a plurality of iSCSI gateways due to a hardware failure of a CPU, a memory, a network card, a power supply, And to provide an effective method for transferring all the iSCSI targets of an iSCSI gateway to a normal iSCSI gateway.

A method for failover of a network distributed file system based iSCSI storage system driven by including a metadata server (M), a data server (D), and an application server (0)

The iSCSI storage system utilizes the metadata server M and the data server D as a block I / O storage space to process SCSI (Small Computers System Interface) commands based on iSCSI (Internet Small Computer System Interface) Further comprising an iSCSI storage system including an iSCSI gateway, an iSCSI control server, and an iSNS server,

The iSCSI gateway includes a SCSI target core serving as a standard interface for block data input / output requested outside the network-based storage, SCSI middleware for supporting the iSCSI interface in the distributed file system, And a block layout manager (Block Layout Manager) for managing distributed data block information, wherein the control server comprises an iSCSI volume manager for configuring an iSCSI volume using a storage space of a distributed file system and controlling a plurality of iSCSI gateways, Lt; RTI ID = 0.0 > iSCSI < / RTI > session manager,

The block layout manager may include at least one of read and write type information, data size information, and LUN information when a specific iSCSI initiator processes iSCSI block read and write requests of a specific iSCSI target belonging to a specific iSCSI gateway A first step of recording;

A second step of transferring at least one of read and write type information, data size information and LUN information to the iSCSI session manager;

A third step of the iSCSI session manager aggregating the information for each iSCSI gateway;

The iSCSI session manager updating an iSCSI gateway rank index from the information aggregated for each iSCSI gateway;

The iSCSI session manager monitors the presence or absence of failure of each iSCSI gateway through an agent installed in each iSCSI gateway. And

And a sixth step of distributing to the normal iSCSI gateway all the iSCSI targets belonging to the iSCSI gateway when the iSCSI session manager determines that the specific iSCSI gateway has failed.

In addition, the method may further include a pre-step in which the iSCSI control server records the IQN information and the portal information of the specific iSCSI target in the iSNS server prior to the first step.

In this case, in the pre-processing step, the iSCSI volume manager creates an iSCSI volume on a file basis through the metadata server M, and the iSCSI volume manager performs iSCSI Storing the volume name information and the size information; and the iSCSI volume manner is configured to determine, from at least one of the iSCSI gateway ID, the IQN information, the TPG (Target Portal Group), the LUN, creating an iSCSI target in an iSCSI gateway, the iSCSI volume manager recording at least one of iSCSI gateway ID, IQN information, TPG, LUN, portal and ACL information to a DB located in an iSCSI control server; The manager mapping (connecting) the iSCSI volume to the LUN of the iSCSI target, recording the iSCSI volume usage information in the DB of the iSCSI control server, The SI volume manager may further include notifying the iSCSI session manager of the iSCSI volume usage information.

In addition, in the second step, it is preferable that the transmission of the information is repeatedly performed for each of the pre-selected reporting periods.

In addition, if the information is successfully transferred in the second step, the block layout manager may further include initializing the stored information.

In the second step, the block layout manager may further include accumulating at least one of read and write type information, data size information, and LUN information until a "reporting period ".

In the fourth step, the iSCSI session manager updates the iSCSI gateway rank index based on a value obtained by multiplying the read and write-specific data size information by a randomly set " read weight "and a" write weight ".

In the sixth step, the iSCSI gateway index index excluding the failed iSCSI gateway index, the iSCSI target rank index, the iSCSI volume manager, the iSCSI gateway having the lowest index, And a step of generating a duplicate.

The sixth step may further include deleting the iSNS server information corresponding to the iSCSI target of the specific iSCSI gateway determined as the failure, that is, the IQN information and the portal information.

In addition, the step of creating the iSCSI target rank index may include: pre-defined read weights and write weights in the data size information by read and write accumulated for each iSCSI target in the iSCSI target list belonging to the failed iSCSI gateway stored in the DB of the iSCSI control server It is preferable to be based on the values obtained by multiplying the weights by the respective weights.

The sixth step may further include recording the IQN information and the portal information of the iSCSI target in the iSNS server when the replication of the iSCSI target is successful and deleting the corresponding iSCSI target in the iSCSI target ranking index desirable.

The method may further include updating the iSCSI gateway rank index excluding the failed iSCSI gateway.

Also, the method preferably repeats the sixth step until all the iSCSI gateway rank index items are deleted.

When the iSCSI target belonging to the failed iSCSI gateway is restored, the iSCSI target connects to the iSCSI target. In the iSCSI initiator using the block data input / output service, the iSCSI target is searched again through the iSNS server, And providing a data input / output service.

According to the present invention, even if some iSCSI gateways fail due to a hardware failure such as a CPU, memory, network card, or power supply, some of the iSCSI gateways can not be used for all iSCSI targets Can be transferred to a normal iSCSI gateway, so that the block data input / output service can be continuously maintained.

FIG. 1 is a diagram showing a schematic configuration of an iSCSI storage system and a network distributed file system using the storage system according to a preferred embodiment of the present invention.
2 is a schematic diagram illustrating an iSCSI Volume formation procedure for supporting Block IO.
Fig. 3 is a view schematically showing a procedure of processing data data read in block IO.
Fig. 4 is a view schematically showing a procedure of processing data write (Data Write) in block IO.
5 is a diagram schematically showing a procedure in which IQN information and portal information of an iSCSI target are recorded.
6 is a diagram schematically showing a procedure for recovering the failure of the iSCSI gateway.

A preferred embodiment of a failure recovery method in a network distributed file system based iSCSI storage system according to a preferred embodiment of the present invention will be described with reference to the accompanying drawings.

The network distributed file system based iSCSI storage system according to the present embodiment is a storage system that generates a logical iSCSI volume (LUN) and provides it to an iSCSI initiator through an iSCSI target to process a block IO.

Also, according to a preferred embodiment of the present invention, the expansion of the storage capacity is provided in the form of adding nodes of the distributed file system.

Also, according to a preferred embodiment of the present invention, the overall input / output bandwidth expansion is provided in the form of adding an iSCSI target of a gateway type.

According to a preferred embodiment of the present invention, more than two iSCSI gateways are used for ensuring storage availability and fail-over is automatically provided to other iSCSI gateways when an iSCSI gateway fails.

FIG. 1 is a diagram showing a schematic configuration of an iSCSI storage system and a network distributed file system using the storage system according to a preferred embodiment of the present invention. 1, a network distributed file system according to a preferred embodiment of the present invention includes a metadata server M, a data server D, and an application server (hereinafter, referred to as " 0).

Specifically, the metadata server M performs a control path function in the distributed file system. In addition, the metadata server M manages meta information (file attributes, path, path list of data pieces on the data server D, whether or not to replicate) in the file.

The data server D also functions as a data path in the distributed file system. That is, when the data server D separates a file into data fragments by the metadata server M, the data server D performs a function of distributing substantially separated data fragments and a function of distributing separated fragments of data.

The distributed file system according to the preferred embodiment of the present invention is a system for processing SCSI commands based on an iSCSI interface by utilizing the metadata server M and the data server D as block input / output storage spaces.

In addition, the application server 0 is a server using storage, and an iSCSI initiator is formed and connected to the iSCSI gateway through Ethernet.

The network distributed file system according to the preferred embodiment of the present invention further includes an expandable iSCSI storage system. The scalable iSCSI storage system according to the present embodiment utilizes a metadata server M and a data server D, which virtualize large-scale physical storage resources as a single storage volume, as a block I / O storage space, Based system.

The scalable iSCSI storage system according to the present embodiment includes a plurality of iSCSI gateways 1, an iSCSI control server 2 and an iSNS server 3 and is provided with a metadata server M, a data server D, For example, Ethernet (ethernet) to the server (0) to provide a block input / output service to a plurality of iSCSI initiators in a scalable manner.

According to a preferred embodiment of the present invention, the metadata server M and the data server D, which are used as a base storage of the scalable iSCSI storage system, support distributed data processing for each iSCSI gateway 1, It is desirable to provide scalability. In addition, the iSCSI gateway 1 is composed of a plurality of iSCSI initiators in order to meet performance requirements of a plurality of iSCSI initiators using block data input / output services.

The iSCSI gateway 1 according to the preferred embodiment of the present invention includes an iSCSI target core 1-1, a SCSI middleware 1-2 and a block layout manager 1-3 Specifically, the following functions are performed.

First, the iSCSI target core 1-1 functions as a standard interface for block data input / output requested outside the Ethernet network-based storage. Specifically, the iSCSI target core 1-1 includes iSCSI target management, network portal management, target portal group management, LUN mapping, iSCSI authentication management based on Challenge Handshake Authentication Protocol (CHAP) ) Management, an iSCSI protocol data unit (PDU), and a command processing function. On the other hand, the mapping between the iSCSI volume (LUN) on the UCS-FS and the target is achieved by controlling the iSCSI target core of the iSCSI volume manager.

Meanwhile, the iSCSI interface function encapsulates the CDB to generate a PDU in order to exchange SCSI commands and parameters encapsulated in the form of Ethernet-based TCP / IP, and transmits the promised It provides only the role of delivering according to the procedure. Therefore, in order to support the iSCSI interface to the distributed file system, a file-based solution, a module that processes SCSI CDB is essential. The SCSI middleware 1-2 decodes the CDB as a module configured according to this purpose and processes the corresponding command in accordance with the standard of the corresponding SCSI command. The SCSI command can largely be classified into a data input / output command and a non-input / output command, and the interlocking with the block layout manager 1-3 is determined according to the above-mentioned classification. The data input / output instruction is interlocked with the block layout manager. When the processing of the SCSI command is completed, the processed result is encapsulated in the CDB format and transferred to the iSCSI target core.

The block layout manager 1-3 is a block for managing data block information distributed in a plurality of physical disk spaces. The storage space on the distributed file system is physically divided into data servers and stored in chunks of data. The set of data fragments is mapped to a single "file" on the distributed file system. The meta information of the file managed by the metadata server of the distributed file system includes a file name, a directory structure, a list of data fragments constituting the file, and location information on the data server. The iSCSI volume (LUN) of the scalable iSCSI storage system corresponds to one file specified in the storage space of the distributed file system. Therefore, in order to link the file and the iSCSI target (LUN mapping), the block layout manager 1-3 for managing the meta information of the iSCSI volume connected to the iSCSI target that the iSCSI gateway itself is servicing is essential. The block layout manager manages the location, the storage unit, and the number of the file chunks constituting the iSCSI volume through the metadata server M of the distributed file system according to need and manages them in the internal storage. And performs block data input / output by mapping the information and the block address and input / output size information, which are parameters of the block input / output received from the SCSI middleware side.

Also, according to a preferred embodiment of the present invention, the iSCSI control server 2 performs control and monitoring of the iSCSI gateway 1. Specifically, the iSCSI control server 2 is a block that configures an iSCSI volume using the storage space of the distributed file system and controls a plurality of iSCSI gateways 1-1.

According to a preferred embodiment of the present invention, the iSCSI control server 2 comprises an iSCSI volume manager 2-1 and an iSCSI session manager 2-1.

First, the iSCSI volume manager 2-1 configures an iSCSI volume using the storage space of the UCS-FS and controls a plurality of iSCSI target cores 1-1. The iSCSI volume manager 2-1 generates a file corresponding to the iSCSI volume on the UCS-FS through the interface provided by the UCS-FS and transfers the iSCSI target via the interface provided by the iSCSI target core 1-1 Management control, network portal management control, target portal group management control, LUN mapping control, and iSCSI authentication management control.

The iSCSI session manager 2-2 integrally manages and monitors basic session functions operating individually in a plurality of iSCSI target cores. The iSCSI session manager 2-2 updates the connection information of the iSCSI target of each iSCSI gateway by interworking with the standard iSNS server 3.

Also, the iSNS server 3 functions as a repository for storing information such as portals and entities related to the currently activated iSCSI node. Where the node may be an initiator, a target, or a managed node. Also, the iSNS server 3 registers an initiator and an object, and the initiator queries a list of available objects in the iSNS server 3.

In addition, the iSNS server 3 functions as a dynamic database of iSCSI devices and related information available in the current network, and provides an iSCSI search function to the iSCSI initiator of the network. In addition, the iSNS server 3 can further provide a search domain service. That is, an administrator can assign an iSCSI node and a portal to one or more groups called search domains. In addition, the search domain provides an area specifying function that enables the iSCSI initiator to search only the corresponding iSCSI target sharing at least one search domain.

block IO To To support iSCSI  Volume formation procedure

The iSCSI volume formation procedure for supporting the block IO will be described in detail below with reference to FIG.

First, the iSCSI management server 2 requests the metadata server M to create an iSCSI volume. (ISCSI volume name / size)

Next, the metadata server M allocates the ID of the iSCSI volume to be created and assigns a chunk to be stored in the data server D distributed on the network to the size (chunk ID, chunk position, Or not).

Next, when the metadata server M returns the iSCSI volume ID information to the iSCSI management server 2, the returned iSCSI volume ID information is transmitted to the block layout manager 1-3 associated with the iSCSI volume, The iSCSI volume creation procedure to support < RTI ID = 0.0 >

block IO  : Data reading process

The procedure for processing data reading in the block IO will be described below with reference to Fig.

First, the application server 0 requests the iSCSI gateway 1 to read SCSI block data in the iSCSI standard system.

Then, the iSCSI target core 1-1 analyzes the iSCSI PDU, decomposes it, and transfers the SCSI CDB to the iSCSI middleware 1-2.

Then, the iSCSI middleware 1-2 analyzes the SCSI command and transfers the logical block address (LBA) of the block to be read and the size information of the data to be read to the block layout manager 1-3.

Then, the block layout manager 1-3 calculates the chunk ID and offset constituting the iSCSI volume using the LBA address, and transmits the size of the data to be read to the metadata server M. [

Then, based on the chunk ID, the offset, and the size information of the data to be read, which are transmitted to the metadata server M, all the related chunk file location lists of the data server (D) (1-3).

Then, the block layout manager 1-3 reads the data from the offset of the first chunk file to the last chunk file based on the chunk file location list and reads the data by the size of the data to be stored in the buffer located in the block layout manager 1-3 Record the data.

Then, the block layout manager 1-3 transfers the location of the buffer on the memory to the iSCSI middleware 1-2, and the iSCSI middleware 1-2 generates the SCSI CDB containing the contents of the buffer.

Then, the generated SCSI CDB is delivered to the iSCSI target core 1-1, the iSCSI target core 1-1 generates an iSCSI PDU including the SCSI CDB, and then transmits the generated iSCSI PDU to the application To the server (0).

block IO  : Write data ( Write ) Processing

A procedure for processing data write in the block IO will be described below with reference to FIG.

First, the application server 0 requests the iSCSI gateway 1 to write SCSI block data in the iSCSI standard manner.

Then, the iSCSI target core 1-1 analyzes the iSCSI PDU, decomposes it, and transfers the SCSI CDB to the iSCSI middleware 1-2.

Then, the iSCSI middleware 1-2 analyzes the SCSI command and transfers the logical block address (LBA) of the block to be written and the size information of the data writing to the block layout manager 1-3.

Then, the block layout manager 1-3 calculates the chunk ID and offset constituting the corresponding iSCSI volume by using the LBA address, and transfers the size of the data write to the metadata server M. [

Then, based on the chunk ID, offset, and size of data write information transmitted to the metadata server M, it is determined whether all relevant chunk files in the data server (D) area distributed on the network exist. If there is no chunk file A chunk is generated at the assigned position, and the chunk position list is sorted in the ID order and transmitted to the block layout manager 1-3.

Then, the block layout manager 1-3 writes data to the buffer located in the block layout manager 1-3 by the amount of data writing from the offset of the first chunk file to the last chunk file based on the chunk file location list.

Subsequently, the block layout manager 1-3 transmits the information on which data writing has been completed to the iSCSI middleware 1-2, and the iSCSI middleware 1-2 includes information on the completion of data writing Create a SCSI CDB.

Then, the generated SCSI CDB is delivered to the iSCSI target core 1-1, the iSCSI target core 1-1 generates an iSCSI PDU including the SCSI CDB, and then transmits the generated iSCSI PDU to the application To the server (0).

Standard iSNS  Applies to server (3) iSCSI Target IQN  Procedure for recording information and portal information

The procedure for recording the IQN information and the portal information of the iSCSI target will be described with reference to FIG.

First, the iSCSI volume manager 2-1 creates an iSCSI volume on a file basis via the metadata server M. Then, the iSCSI volume manager 2-1 stores iSCSI volume name information and size information in the DB located in the iSCSI control server 2 with respect to the created iSCSI volume.

The iSCSI volume manager 2-1 can control for iSCSI target creation through a plurality of iSCSI gateway target cores 1-1. The iSCSI volume manager 2-1 inputs iSCSI gateway ID, IQN information, TPG (Target Portal Group), LUN, Portal, and ACL information through a user interface (UI) And creates an iSCSI target in the iSCSI gateway 1. When an iSCSI target is created, the iSCSI volume manager (2-1) records the iSCSI gateway ID, IQN information, TPG, LUN, portal, and ACL information in the DB located in the iSCSI control server (2).

Then, the iSCSI volume manager 2-1 maps the iSCSI volume to the LUN of the iSCSI target created previously, and records the iSCSI volume usage information in the DB of the iSCSI control server 2. When the above process is completed, the iSCSI volume manager 2-1 notifies the iSCSI session manager 2-2 of this, and the iSCSI session manager 2-2 transmits the IQN information of the iSCSI target to the standard iSNS server 3, Record the portal information.

iSCSI  Procedures for recovering from a gateway failure

Next, the procedure for recovering the failure of the iSCSI gateway will be described with reference to FIG.

The application server (0) accesses the iSNS server (3) through the iSCSI initiator, searches for the iSCSI target, and logs in the iSCSI target based on the IQN information and the portal information. The above process can be repeatedly performed in a plurality of iSCSI gateways and application servers (0).

The block layout manager 1-3 determines whether the specific iSCSI initiator is capable of reading and writing type information, data size information (i. E., Data size information) when processing iSCSI block read and write requests of a specific iSCSI target belonging to a specific iSCSI gateway And LUN information.

In addition, the block layout manager 1-3 accumulates the read and write type and data size information per LUN up to the "reporting period ". Then, in the "reporting cycle ", the block layout manager 1-3 delivers the read and write type information, the data size information and the LUN information to the iSCSI session manager 2-2. If the transfer is successful, the block layout manager 1 -3) initializes the stored information.

In addition, the iSCSI session manager 2-2 having received the information transmits read and write type and data size information per LUN to the DB of the iSCSI control server 2 using read and write type information, data size information and LUN information Accumulate. Also, the cumulative result is divided by the "revaluation value" for each "reevaluation period" set.

In addition, the iSCSI session manager 2-2 aggregates the accumulated information for each iSCSI gateway. For example, the iSCSI session manager 2 - 2 can aggregate the sum of the data size information for each of the LUNs of the iSCSI target belonging to the iSCSI gateway.

In addition, the iSCSI session manager 2-2 calculates the iSCSI gateway rank index based on the sum of the read weight and the write weight multiplied by arbitrarily set data size information for read and write in the information aggregated for each iSCSI gateway Update. In this case, "1" represents the iSCSI gateway with the highest load and represents iSCSI gateway with relatively low load increasing by one.

In addition, the iSCSI session manager 2-2 monitors the presence or absence of failure of each iSCSI gateway 1 through an agent installed in each iSCSI gateway 1.

In addition, when the iSCSI session manager 2-2 determines that a specific iSCSI gateway has failed, all of the iSCSI targets belonging to the iSCSI gateway are generated and distributed to the normal iSCSI gateway. The process is as follows.

1. Delete the information of the iSNS server corresponding to the iSCSI target of the specific iSCSI gateway determined as the failure, that is, the IQN information and the portal information.

2. Update the iSCSI gateway rank index except for the failed iSCSI gateway.

3. The sum of the "read weights" and "write weights" multiplied by the read and write data size information accumulated for each iSCSI target in the iSCSI target list belonging to the failed iSCSI gateway stored in the DB of the iSCSI control server (2) And creates an iSCSI target rank index based on the iSCSI target rank index.

4. The iSCSI volume manager (2-1) accesses the iSCSI target having the highest (smallest) rank index in the iSCSI gateway having the lowest (highest number) rank index as the corresponding (iSCSI) target stored in the DB of the iSCSI control server Create a copy using the information of the iSCSI target.

5. If the replication of the iSCSI target is successful, the iSNS server 3 records the IQN information and the portal information of the iSCSI target and deletes the corresponding iSCSI target from the iSCSI target ranking index.

6. Update the iSCSI gateway rank index except the failed iSCSI gateway.

7. Repeat steps 4 to 6 until all iSCSI gateway rank index entries are deleted.

If the iSCSI targets belonging to the failed iSCSI gateway are recovered in the above process, the iSCSI target using the block data input / output service is connected to the iSCSI target and the iSCSI target is re-discovered through the iSNS server 3, Block data input / output service can be provided.

The method for recovering the failure in the network distributed file system based iSCSI storage system according to the preferred embodiment of the present invention has been described in detail. However, it will be understood by those skilled in the art that various modifications and variations can be made in the present invention. Accordingly, the scope of the present invention is limited only by the claims that follow.

Claims (15)

A method for failover of a network distributed file system based iSCSI storage system driven by including a metadata server (M), a data server (D), and an application server (0)
The iSCSI storage system utilizes the metadata server M and the data server D as a block I / O storage space to process SCSI (Small Computers System Interface) commands based on iSCSI (Internet Small Computer System Interface) Further comprising an iSCSI storage system including an iSCSI gateway, an iSCSI control server, and an iSNS server,
The iSCSI gateway includes a SCSI target core serving as a standard interface for block data input / output requested outside the network-based storage, SCSI middleware for supporting the iSCSI interface in the distributed file system, And a block layout manager (Block Layout Manager) for managing distributed data block information, wherein the control server comprises an iSCSI volume manager for configuring an iSCSI volume using a storage space of a distributed file system and controlling a plurality of iSCSI gateways, Lt; RTI ID = 0.0 > iSCSI < / RTI > session manager,
The block layout manager may include at least one of read and write type information, data size information, and LUN information when a specific iSCSI initiator processes iSCSI block read and write requests of a specific iSCSI target belonging to a specific iSCSI gateway A first step of recording;
A second step of transferring at least one of read and write type information, data size information and LUN information to the iSCSI session manager;
A third step of the iSCSI session manager aggregating the information for each iSCSI gateway;
The iSCSI session manager updating an iSCSI gateway rank index from the information aggregated for each iSCSI gateway;
The iSCSI session manager monitors the presence or absence of failure of each iSCSI gateway through an agent installed in each iSCSI gateway. And
When the iSCSI session manager determines that a specific iSCSI gateway has failed, a sixth step of allocating all the iSCSI targets belonging to the iSCSI gateway to the normal iSCSI gateway
The method comprising the steps of: (a) 2. The method of claim 1, wherein the iSCSI control server further comprises a pre-step of recording IQN information and portal information of a specific iSCSI target to the iSNS server prior to the first step. How to recover from a system failure. The method according to claim 2,
The iSCSI volume manager creates an iSCSI volume on a file basis through a metadata server M, and the iSCSI volume manager stores iSCSI volume name information and size information in a DB located in the iSCSI control server for the generated iSCSI volume , The iSCSI volume manager generates an iSCSI target from a specific iSCSI gateway from at least one of iSCSI gateway ID, IQN information, TPG (Target Portal Group), LUN, Portal and ACL information Wherein the iSCSI volume manager records at least one of iSCSI gateway ID, IQN information, TPG, LUN, portal and ACL information to a DB located in an iSCSI control server, mapping (connecting) the iSCSI volume, recording the iSCSI volume usage information to the DB of the iSCSI control server, and iSCSI volume manager performing the iSCSI session It said the manager of the steps to notify the iSCSI network volume usage information further comprises a distributed file system-based disaster recovery method of iSCSI storage system. The method according to any one of claims 1 to 3, wherein, in the second step, the transfer of the information is repeatedly performed for each pre-selected reporting period. The method as claimed in any one of claims 1 to 3, wherein, in the second step, if the transfer of the information is successful, the block layout manager initializes the stored information. How to recover from a system failure. The method as claimed in any one of claims 1 to 3, wherein, in the second step, the block layout manager further includes accumulating at least one of read and write type information, data size information, and LUN information until a specific reporting period Wherein the failure recovery method is based on a network distributed file system. The method as claimed in any one of claims 1 to 3, wherein, in the fourth step, the iSCSI session manager multiplies data size information for each read and write by "read weight" and "write weight" And updating the gateway rank index. The method as claimed in any one of claims 1 to 3, wherein, in the sixth step, the iSCSI gateway index index excluding the failed iSCSI gateway is created, the iSCSI target rank index is created, and the iSCSI volume manager includes iSCSI Generating a copy of an iSCSI target having a highest rank index in the gateway. The method of any one of claims 1 to 3, wherein the sixth step further comprises deleting the information of the iSNS server corresponding to the iSCSI target of the specific iSCSI gateway determined as the failure, that is, the IQN information and the portal information The method comprising the steps of: (a) determining a failure of a network distributed file system based iSCSI storage system; The method as claimed in claim 8, wherein the step of creating the iSCSI target rank index comprises: pre-defined reading of read and write data size information accumulated for each iSCSI target in an iSCSI target list belonging to a failed iSCSI gateway stored in a DB of the iSCSI control server Wherein the data is created based on the sum of the weights and the write weights. The method as claimed in any one of claims 1 to 3, wherein, in the sixth step, if the replication of the iSCSI target is successful, IQN information and portal information of the iSCSI target are recorded in the iSNS server, Further comprising the step of deleting the target. ≪ Desc / Clms Page number 24 > The method of any one of claims 1 to 3, wherein the method further comprises updating an iSCSI gateway rank index excluding a failed iSCSI gateway. The method according to any one of claims 1 to 3, wherein the step of repeating step (6) is repeated until all iSCSI gateway rank index entries are deleted. . The method as claimed in any one of claims 1 to 3, wherein when the iSCSI targets belonging to the failed iSCSI gateway are restored, the iSCSI target connecting the iSCSI target and the iSCSI initiator using the block data input / And a seventh step of providing an existing block data input / output service through a re-login process and a re-login process. A network distributed file system for implementing a failure recovery method of an iSCSI storage system based on a network distributed file system according to any one of claims 1 to 3,
The network distributed file system utilizes the metadata server M, the data server D, the application server 0 and the metadata server M and the data server D as a block I / And an iSCSI storage system including a plurality of iSCSI gateways, an iSCSI control server, and an iSNS server for processing a Computers System Interface (iSCSI) command based on an Internet Small Computer System Interface (iSCSI)
The iSCSI gateway includes a SCSI target core serving as a standard interface for block data input / output requested outside the network-based storage, SCSI middleware for supporting the iSCSI interface in the distributed file system, And a block layout manager (Block Layout Manager) for managing distributed data block information, wherein the control server comprises an iSCSI volume manager for configuring an iSCSI volume using a storage space of a distributed file system and controlling a plurality of iSCSI gateways, And an iSCSI session manager for managing a session function of the iSCSI target core of the iSCSI target core.

Images