CN111897486A - Intelligent unified storage system based on software definition - Google Patents
Intelligent unified storage system based on software definition Download PDFInfo
- Publication number
- CN111897486A CN111897486A CN202010512470.1A CN202010512470A CN111897486A CN 111897486 A CN111897486 A CN 111897486A CN 202010512470 A CN202010512470 A CN 202010512470A CN 111897486 A CN111897486 A CN 111897486A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- storage
- file
- storage system
- 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.)
- Pending
Links
Images
Classifications
-
- 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
- G06F3/0626—Reducing size or complexity of storage systems
-
- 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
- G06F3/0655—Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices
- G06F3/0656—Data buffering arrangements
-
- 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)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides an intelligent unified storage system based on software definition, which integrates SAN and NAS storage architectures and realizes unified access of file-level, block-level and object-level data. By the cluster of the distributed file system on a plurality of nodes, a uniform management point, a faster file access speed and extremely high availability are provided for large-scale content storage, and the total bandwidth and EB capacity of 100GB/S can be exceeded at most. Due to the adoption of a unique algorithm to carry out block-level splitting on the files spanning multiple storage nodes in the cluster, the fully distributed design is easy to improve the storage performance, the expandability, the usability and the manageability.
Description
Technical Field
The invention belongs to the technical field of information storage, and particularly relates to an intelligent unified storage system based on software definition.
Background
With the rapid development of the information industry, the data volume generated by various industries also shows explosive growth. How to effectively use the related storage technology to store the mass data for a long time and further discover the data value in the mass data is a problem which is urgently needed to be solved by the data storage industry. In addition, the 4V characteristics of large data (large data size, many types, low cost density, and high speed) illustrate the increased demands on the performance of storage systems (large capacity, high performance, easy expansion, ease of use, etc.) from the side.
In the past, the storage architecture is mainly centered on a server, a storage device is directly connected to a server host, then the server is connected to a network, and any client wishing to access the resource on the storage device must pass through the server. Since all data streams must be forwarded through the server, the server is burdened and the performance of the whole system is prone to problems. As the demand of data storage is increasing and the demand of clients for the performance and capacity of servers is increasing, the innovation of storage technology is developing to be inevitable, and as people in the development industry of network technology consider to separate storage from application servers for centralized management, a storage network mode begins to appear. The storage network is mainly implemented in two ways: SAN storage and NAS storage. SAN (storage Area networks) storage Area networks are a private network built specifically for storage independent of the TCP/IP network. And a network Channel (FC) technology is adopted, and the FC switch is used for connecting the storage array and the server host to establish a regional network special for data storage. NAS (network attached storage) network access storage is a mechanism for realizing data storage by adopting special equipment directly connected with a network medium, and each application server uses the same file management system through network sharing protocols (such as NFS and CIFS), so that reliable file-level data integration can be provided, and the high efficiency and the safety are realized. However, such a method cannot adapt to different storage requirements, once the device is damaged, the performance of the system is greatly reduced, the normal use of storage is affected, meanwhile, the unified management and flexible scheduling of resources cannot be achieved, and the phenomenon of low storage utilization rate is easily caused. Thus, the presence of different stores affects the ease of use and utilization of the stores.
With the rapid development of enterprises, businesses and departments are gradually increased, and the IT architecture deployment and application of the enterprises become more and more complicated. Most enterprises have not only database-based applications but also file-based access requirements. In the past, IT management departments needed to deploy SAN and NAS storage devices separately to meet access requirements for different traffic types. Enterprises face the problems of IT architecture deployment, high operation cost, difficult operation and maintenance management and the like; in addition, with the rapid development of applications such as big data, cloud computing, cloud storage, etc., different types of data are rapidly expanding, and the storage requirement of data volume is more and more widely concerned by the industry, so enterprises need to deal with the challenges of low utilization rate of storage resources, poor performance of storage devices, difficulty in upgrading, etc.
The intelligent unified storage technology based on software definition provides a unified management point, a faster file access speed and extremely high availability for large-scale content storage through a cluster of a distributed file system on a plurality of nodes, and the maximum total bandwidth can exceed 100GB/S and EB capacity. Because a unique algorithm is adopted to carry out block-level splitting on files spanning a plurality of storage nodes in the cluster, the design completely belongs to a distributed design, and unprecedented high-efficiency storage performance and expandability can be brought. The design of the unified storage technology architecture is a mode of defining storage through software, wherein a functional module can provide file, object and block storage services upwards, supports various standard protocols of CIFS, NFS, iSCSI, S3 and UDFS to manage storage, and is far higher than the expansibility, reliability and performance of a common NAS/SAN system. Meanwhile, the intelligent volume management provides functions of file management, information statistics, metadata monitoring and the like, and the usability and the safety of the system are further improved.
Object of the Invention
The invention aims to focus on the difficult problems of information storage in the prior art, and provides an intelligent unified storage system based on software definition, which has the characteristics of high elasticity, high intelligence and easy management. The intelligent unified storage of the invention integrates SAN and NAS architectures, realizes unified access of file level, block level and object level data, and provides a unified, elastic, intelligent and simple information storage solution for users with excellent design performance, good storage efficiency and abundant software function modules.
Disclosure of Invention
The invention provides an intelligent unified storage system based on software definition, which integrates SAN and NAS storage architectures and comprises the following components:
the system comprises a shared interface access module, a distributed storage management module, a storage resource pooling module, a storage cache module, a storage security group module and a physical storage resource module; the intelligent unified storage system provides file, object and block storage services to the outside in a software defined storage mode, and supports CIFS, NFS, iSCSI, S3 and UDFS standard protocol management storage.
The sharing interface access module comprises a file sharing module, an object sharing module and a block sharing module, supports CIFS, NFS, iSCSI, S3 and UDFS standard protocols, supports the mutual access of NAS and S3 data, and enables a user to select different protocols to access the data according to service requirements.
The distributed storage management module comprises a client module, a server module and an intelligent volume management module; file retrieval and file statistics are carried out by managing file metadata, wherein the file statistics comprise type statistics, file quantity statistics and file distribution statistics; health scoring is carried out on the clustered results, and the files can be guaranteed to be cured after being damaged; the intelligent unified storage system comprises a client module, a server module and a server module, wherein the client module is used for receiving a request of a user, the server module is used for receiving a request of the user, the request of the user is received by the server module, and the server module is used for receiving a request of the user and providing a data storage function of a volume.
The storage resource pooling module integrates the independent storage resources provided by the security group module into a resource pool through a resource pooling technology, so that management, capacity expansion and resource allocation are facilitated.
The storage cache module accelerates mass storage by using a flash disk such as SSD or NVMe as a read-write cache (writeback mode) or a read cache (writethrough or writeearound mode), thereby greatly improving the storage bandwidth and IOPS.
The security group module is used for changing a plurality of physical disks into a redundant disk array. Multiple independent hard disk drives are combined using virtualized storage technology to improve performance, capacity, and reliability.
The physical storage resource module provides basic data storage function for the final data carrier.
Drawings
FIG. 1 is an architecture diagram of the intelligent unified storage system of the present invention.
Fig. 2 is a schematic diagram of a shared interface access module.
FIG. 3 is a schematic diagram of a distributed storage management module.
FIG. 4 is a schematic diagram of a storage resource pooling module.
FIG. 5 is a schematic diagram of a store cache module.
FIG. 6 is a memory security group module diagram.
FIG. 7 is a diagram of a physical storage resource module architecture.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings.
FIG. 1 is an architecture diagram of the intelligent unified storage system of the present invention. The storage system integrates two storage architectures of SAN and NAS, and comprises the following components: the system comprises a shared interface access module, a distributed storage management module, a storage resource pooling module, a storage cache module, a storage security group module and a physical storage resource module; the intelligent unified storage system provides file, object and block storage services to the outside in a software defined storage mode, and supports CIFS, NFS, iSCSI, S3 and UDFS standard protocol management storage.
Example 1
In this embodiment, the intelligent unified storage system includes a shared interface access module, a distributed storage management module, a storage resource pooling module, a storage cache module, a storage security group module, and a physical storage resource module, where the shared access interface layer is used to provide access interfaces such as NAS, SAN, S3, and the like, the distributed storage module performs pooling and unified management after virtualization of file system resources through software, the storage resource pooling module forms a resource pool with multiple security groups through a resource pooling technology to perform unified management, the storage cache module performs cache acceleration on the resource pool through VNMe and SSD, the security group module integrates physical storage resources into a disk array through a RAID technology to provide longitudinal pool security, and the physical storage resource module provides a basic data storage function for a final carrier of data.
Fig. 2 is a schematic diagram of a sharing interface access module, which includes a file access module, an object access module, and a block access module, where the file access module is used to provide a file access interface, the object access module is used to provide a block access interface, and the block access module is used to provide a block access interface.
The NAS framework used by the file interface access module supports NFS and CIFS protocols, has good expansibility, is easy to manage, has low price and is convenient for user data sharing.
The block interface access module uses SAN architecture, supports IPSAN, uses iSCSI protocol, uses independent SAN network, and provides higher IOPS and storage bandwidth.
The object access interface module uses Minio object storage service, compatible amazon S3 cloud storage service interface, and is well suited for storing large volumes of unstructured data, such as pictures, videos, log files, backup data, container/virtual machine images, etc., while an object file may be any size, varying from a few kb to a maximum of 5T.
Fig. 3 shows a schematic diagram of a distributed storage management module, which is divided into a client module, a server module and an intelligent volume management module, wherein the client module is used for processing data input by the sharing module, and the server module is used for managing data blocks, handling data requests from other components and providing data storage functions of volumes.
The distributed storage management uses a glusterfs composition distributed file management system, the client module uses a glusterfs-client module, a glusterfs volume is mounted to a mounting point and provided for a POSIX file access interface of a sharing interface standard, and the object access interface and the file access interface simultaneously access the POSIX interface, so that mutual conversion between file storage and object storage is achieved, and the space utilization rate of storage is improved.
The server module uses the glusterfs-server module to manage the cluster, volume, snapshot and other modules, and receives the data of the client and writes the data into the storage block to provide the data storage function.
And the intelligent volume management module monitors the change of the file metadata of the server data block by using the kernel inotify module, writes the file metadata into the mongodb database, provides an interface for a user index file, and solves the problem of low traversal operation efficiency of the glusterfs directory.
Fig. 4 is a schematic diagram of a storage resource pooling module, where the resource pooling module initializes a plurality of security groups into Physical volumes by a lvm technology and integrates the security groups into one Volume Group, provides data block storage for a distributed storage module by dividing the Logical volumes, and supports a Thin Logical Volume to provide mechanisms such as copy-on-write and snapshot.
Fig. 5 is a schematic diagram of a storage cache module, which uses the Bcache technology, uses an NVMe or SSD device as cache disks of multiple security groups, supports three caching strategies, namely, writeback, writethrough, and writeearoud, provides dynamic modification, provides a power-off protection mechanism, and does not return that writing is completed before data does not fall into stable storage, and after power-off of a server, dirty data continues to write cache data into stable storage after a point is added.
Fig. 6 is a diagram of a storage security group module, where the security group module constructs physical resources into a plurality of disk arrays to increase storage bandwidth and IOPS, and provides multiple security redundancy mechanisms such as RAID0, RAID1, RAID5, RAID10, and RAID50 to protect longitudinal pool security of users, and provides functions such as caching and pre-reading to increase storage bandwidth and IOPS.
Fig. 7 is a structural diagram of a physical storage resource module, which is composed of a magnetic disk device and provides a basic data storage function as a final carrier of data.
The user service accesses data through a file sharing access interface, a block sharing access interface and an object sharing access interface.
The shared access interface accesses the client module in the distributed file system module through POSIX.
And the client module in the distributed file system submits the data to the server module in the distributed file system in the forms of Hash, copy, erasure codes and the like.
The server module submits the data to the resource pool module, and the resource pool module sorts the data and submits the data to the storage cache module.
The cache module firstly classifies data types, judges whether the data is random IO or sequential IO, sequences the data firstly if the data is random IO, then writes the data into the SSD or NVMe, and then submits the data in the SSD or NVMe to the security group module by the back-end process, and directly submits the data to the security group module without sequencing if the data is sequential IO.
The safety group module simultaneously reads a plurality of disks in the safety group by carrying out striping, mirroring and parity check on the data on the disks in the physical storage resource module, reduces the mechanical seek time of the disks, improves the data storage speed and realizes the redundancy protection of the data.
And the physical storage resource module writes the data into the hard disk and stores the data.
The invention has the advantages of
The intelligent unified storage system based on software definition provided by the invention integrates two storage architectures of SAN and NAS, and realizes unified access of file-level, block-level and object-level data. By the cluster of the distributed file system on a plurality of nodes, a uniform management point, a faster file access speed and extremely high availability are provided for large-scale content storage, and the total bandwidth and EB capacity of 100GB/S can be exceeded at most. Due to the adoption of a unique algorithm to carry out block-level splitting on the files spanning multiple storage nodes in the cluster, the fully distributed design is easy to improve the storage performance, the expandability, the usability and the manageability.
Compared with the traditional storage mode, the invention has the following advantages:
1. through the cluster of the distributed file system on a plurality of nodes, a uniform management point, a faster file access speed and extremely high availability are provided for large-scale content storage.
2. The distributed storage system based on software definition uniformly provides file, block and object services to the outside after virtualizing storage resources in the whole cluster.
3. Supporting CIFS, NFS, iSCSI, S3, UDFS multiple standard protocols
4. The method can be used for searching massive files, counting file types, counting file quantity and counting file distribution, can be used for scoring the health of the cluster, and can be used for healing damaged files.
Therefore, the invention can effectively solve the problems of low efficiency, low storage utilization rate and the like of the traditional storage mode, and can realize that the user freely allocates the storage to meet the requirements of the application environment on the storage of different protocols. The intelligent distributed storage function of horizontal and longitudinal bidirectional expansion can be realized, and the method is a fully self-developed storage technology which not only has the elastic on-demand service capability of a distributed architecture, but also meets the key business requirements of enterprises. The system can provide block storage, object storage and file storage resources for upper-layer applications, and provide excellent performance and rich enterprise-level characteristics; the system can provide efficient, reliable and intelligent unified storage service and easily meet the requirement of quick access of large-scale data in the intelligent era.
Claims (10)
1. An intelligent unified storage system based on software definition, which merges storage architectures of SAN and NAS, the intelligent unified storage system comprising:
the system comprises an intelligent volume management module, a remote volume copying module, a snapshot management module, a sharing management module, a security group module, an EC erasure code module, a data local recovery module and a transverse/longitudinal bidirectional elastic expansion module;
by means of software defined storage, the intelligent unified storage system provides file, object and block storage services for the outside and supports CIFS, NFS, iSCSI, S3 and UDFS standard protocol management storage.
2. The intelligent unified storage system based on software definition according to claim 1, wherein the intelligent volume management module performs file retrieval and file statistics by managing file metadata, the file statistics including type statistics, file quantity statistics, and file distribution statistics; health scoring is carried out on the clustered results, and the files can be guaranteed to be cured after being damaged; by designing a graphical monitoring management interface, an operation monitoring alarm is provided, so that a user can monitor the state of the intelligent unified storage system in real time.
3. The intelligent unified storage system based on software definition according to claim 1, wherein the remote volume replication module synchronizes data among a plurality of data centers through a local area network, a wide area network, and the internet, and the remote volume replication module can perform disaster recovery backup on the data to prevent data loss.
4. The intelligent unified storage system based on software definition according to claim 1, wherein the snapshot management module supports a file/directory-based snapshot technology, creates file images at multiple time points for the same file or directory, realizes content preservation for snapshot files/directories, and can perform data recovery when an application failure or file damage occurs to a storage device, so as to restore data to a state at a certain available time point, thereby ensuring data security; in addition, it can be used as a data source for volume creation.
5. The intelligent unified storage system based on software definition according to claim 1, wherein the shared management module supports CIFS, NFS, iSCSI, S3, UDFS standard protocols, supports mutual access of NAS and S3 data, and enables a user to select different protocols for data writing and reading according to service requirements.
6. The intelligent unified storage system based on software definition according to claim 1, wherein the security group module comprises a plurality of security group units connected with the resource pool, the security group provides 4 levels of data redundancy of stripe, mirror, single check and double check for the resource pool; when a bad block of data is detected, the security group module will extract the correct data from the other redundant copy and replace the incorrect data with the correct data; in the security group unit, a plurality of independent physical hard disks are combined into a logic hard disk in different modes, so that the read-write performance and the data security of the hard disks are improved.
7. The intelligent unified storage system based on software definition according to claim 1, wherein the EC erasure code module comprises a plurality of EC erasure code units connected with a storage space, the storage space refers to a logical hard disk combined by a plurality of separate physical hard disks in different ways; the EC erasure code module improves the reliability of the intelligent unified storage system by tolerating node faults, and when a node in a redundancy range is disconnected, data can still be acquired from other service nodes; with the expansion of the nodes, the method can be automatically adjusted to obtain higher storage space utilization rate; when partial nodes are damaged, the whole data of the intelligent unified storage system can still be calculated through the other undamaged nodes, and the safety of the data is ensured.
8. The intelligent unified storage system based on software definition according to claim 1, wherein said data local recovery module can calculate and recover data through algorithm when a certain disk is bad or abnormal.
9. The intelligent unified storage system based on software definition according to claim 8, wherein, through the data local recovery module, the intelligent unified storage system can implement automatic recovery of data within a resource pool group without going through a cluster; when a certain disk in the security group module is invalid, replacing the invalid disk with another normal standby disk in the security group under the condition of not interfering the normal use of the current security group, so as to realize the data protection of the system; when the hard disk fails, the copy is lost, the data local recovery module automatically starts data reconstruction, and data reconstruction is performed from data blocks in other different disks.
10. The intelligent unified storage system based on software definition according to claim 1, wherein the horizontal/vertical bidirectional elastic expansion module supports interconnection of a plurality of x86 and home-made servers into a parallel distributed file system through a network in a TCP/IP manner; storage capacity to support several EBs; support thousands of clients; by using the elastic hash algorithm, the expansion can be carried out at any time according to requirements, and the longitudinal expansion of the single-node resource pool is realized; each logical volume can be adjusted according to the use condition, the hard disk space is fully utilized, and the storage performance of a single node is improved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010512470.1A CN111897486A (en) | 2020-06-08 | 2020-06-08 | Intelligent unified storage system based on software definition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010512470.1A CN111897486A (en) | 2020-06-08 | 2020-06-08 | Intelligent unified storage system based on software definition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111897486A true CN111897486A (en) | 2020-11-06 |
Family
ID=73206583
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010512470.1A Pending CN111897486A (en) | 2020-06-08 | 2020-06-08 | Intelligent unified storage system based on software definition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111897486A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114185490A (en) * | 2021-12-06 | 2022-03-15 | 深圳市瑞驰信息技术有限公司 | Method for realizing data exchange between glusterfs file system and object storage s3 |
| CN114895856A (en) * | 2022-07-12 | 2022-08-12 | 创云融达信息技术(天津)股份有限公司 | Distributed storage system based on high-density storage hardware |
| CN116431596A (en) * | 2023-06-12 | 2023-07-14 | 青岛诺亚信息技术有限公司 | Case-level-oriented cross-platform distributed file system and implementation method |
-
2020
- 2020-06-08 CN CN202010512470.1A patent/CN111897486A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114185490A (en) * | 2021-12-06 | 2022-03-15 | 深圳市瑞驰信息技术有限公司 | Method for realizing data exchange between glusterfs file system and object storage s3 |
| CN114895856A (en) * | 2022-07-12 | 2022-08-12 | 创云融达信息技术(天津)股份有限公司 | Distributed storage system based on high-density storage hardware |
| CN114895856B (en) * | 2022-07-12 | 2022-09-16 | 创云融达信息技术(天津)股份有限公司 | Distributed storage system based on high-density storage hardware |
| CN116431596A (en) * | 2023-06-12 | 2023-07-14 | 青岛诺亚信息技术有限公司 | Case-level-oriented cross-platform distributed file system and implementation method |
| CN116431596B (en) * | 2023-06-12 | 2023-09-01 | 青岛诺亚信息技术有限公司 | Case-level-oriented cross-platform distributed file system and implementation method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2799973B1 (en) | A method for layered storage of enterprise data | |
| US6862609B2 (en) | Redundant storage for multiple processors in a ring network | |
| US9367395B1 (en) | Managing data inconsistencies in storage systems | |
| US20060106893A1 (en) | Incremental backup operations in storage networks | |
| US11748208B2 (en) | Persistent memory architecture | |
| US7305530B2 (en) | Copy operations in storage networks | |
| US9558068B1 (en) | Recovering from metadata inconsistencies in storage systems | |
| Kaiser et al. | Design of an exact data deduplication cluster | |
| US11861169B2 (en) | Layout format for compressed data | |
| US10242012B1 (en) | Managing truncation of files of file systems | |
| CN111897486A (en) | Intelligent unified storage system based on software definition | |
| US20180275907A1 (en) | Composite aggregate architecture | |
| US11822520B2 (en) | Freeing pages within persistent memory | |
| US7472307B2 (en) | Recovery operations in storage networks | |
| US20230139582A1 (en) | Forwarding operations to bypass persistent memory | |
| US11960448B2 (en) | Unified object format for retaining compression and performing additional compression for reduced storage consumption in an object store | |
| US20240128984A1 (en) | Additional compression for existing compressed data | |
| US20240137329A1 (en) | Shared storage model for high availability within cloud environments | |
| Thomasian | RAID Organizations for Improved Reliability and Performance: A Not Entirely Unbiased Tutorial (1st revision) | |
| Ren | Architecture and performance evaluation of data storage systems |
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 |