CN103902479A - Quick reconstruction mechanism for metadata cache on basis of metadata log - Google Patents
Quick reconstruction mechanism for metadata cache on basis of metadata log Download PDFInfo
- Publication number
- CN103902479A CN103902479A CN201410117821.3A CN201410117821A CN103902479A CN 103902479 A CN103902479 A CN 103902479A CN 201410117821 A CN201410117821 A CN 201410117821A CN 103902479 A CN103902479 A CN 103902479A
- Authority
- CN
- China
- Prior art keywords
- metadata
- daily record
- cache
- data server
- meta data
- 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
Abstract
The invention discloses a quick reconstruction mechanism for a metadata cache on the basis of metadata log. The quick reconstruction mechanism comprises three major modules including a metadata log accessor, a metadata memory and the metadata cache. The quick reconstruction mechanism for the metadata cache has the advantages that the metadata operation log which is previously recorded can be utilized in metadata server failure recovery procedures, so that the pre-failure metadata cache can be quickly loaded into an internal memory, the metadata cache can be quickly reconstructed, and pre-failure-recovery cache scenes can be quickly recovered; data in the cache can be directly utilized to continue to process metadata requests after metadata server failure is recovered, accordingly, the metadata processing efficiency can be improved, and the integral work efficiency of a system can be improved.
Description
Technical field
The present invention relates to Computer Storage field, be specifically related in cluster storage, daily record algorithm, cache algorithm and the recovery mechanism of meta data server.
Background technology
Along with developing rapidly of network application, network information data amount is increasing, and the mass data storage of PB rank becomes more and more important.The file system of traditional sense can not meet the requirements such as the large capacity, high reliability, high-performance of existing application, and for meeting these new demands, distributed file system application has obtained extensive attention.The research of existing distributed file system is mainly divided into metadata and actual data storage separate management, in file system, metadata request occupies the more than 50% of all requests, therefore, metadata management problem becomes an important research direction in distributed file system research.
Metadata is of paramount importance characteristic information in file system, and realizing high speed metadata access is the effective way that improves file system performance.In distributed file system, user needs prior accesses meta-data to any operation of data object, and any change that data object is made all must be recorded in metadata, and visible user is very frequently to the access of metadata.Therefore, improve the speed of metadata access, extremely important to the performance of lifting file system.
For the data of frequent access, adopt caching technology can improve the performance of file system.The visiting frequency of metadata is very high, and may be repeatedly to access same data, and buffer memory can greatly reduce the inner mutual number of times of metadata management system.The meta data server (mds) of the distributed file system of main flow has substantially all possessed metadata cache mechanism at present.
In traditional meta data server, because buffer memory is to be stored in the middle of the internal memory of meta data server, therefore, once meta data server power down or restart data cached will loss.Subsequently, after meta data server is resumed work, in internal memory without any data cached, need to be along with the processing of client-requested, progressively metadata about load from metadata store equipment, and then realize the recovery of metadata cache scene.This mode is in the firm start-up course of meta data server, can produce the data access request for metadata repository in a large number, and client also needs to wait for after these data access request complete and could carry out normal metadata operation, thereby affected the whole efficiency of system.
Summary of the invention
The present invention is directed to the weak point that prior art exists, fully utilize the daily record technology of Metadata Service, a kind of Fast Reconstruction mechanism of metadata cache is provided.
The invention discloses a kind of metadata cache Fast Reconstruction mechanism based on metadata daily record, its technical scheme that solve the technical problem employing is as follows: described metadata cache Fast Reconstruction mechanism comprises three large modules: metadata log access device, metadata repository and metadata cache, wherein:
(1) metadata log access device is responsible for the access of metadata daily record, metadata daily record is read and write with the form of entry, metadata log access device is responsible for ignoring the preservation mechanism of the concrete metadata daily record of bottom, and a metadata daily record read-write interface based on entry is upwards provided.
(2) metadata repository is the equipment of actual storage metadata, searching using index of metadata node as key word is provided conventionally, creates, modification and deletion action.
(3) metadata cache is a region in meta data server internal memory, is responsible for a part of content in cache metadata storer, and this partial content has close relationship with the metadata request of processing or just completing at present processing conventionally.
By the metadata cache Fast Reconstruction mechanism based on metadata daily record of the present invention, in the failover procedure of meta data server, can utilize the metadata operation daily record of precedence record, fast the metadata cache before fault is loaded in internal memory, rebuilds the metadata cache information before fault.
The beneficial effect of the metadata cache Fast Reconstruction mechanism based on metadata daily record disclosed by the invention is: by described metadata cache Fast Reconstruction mechanism, carry out in the process of fault recovery at meta data server, do not need the content playback in metadata daily record in metadata repository, need to from metadata repository, not load a large amount of metadata informations in buffer memory yet, therefore, reduce the access load of metadata repository, accelerate the speed of metadata fault recovery, can rebuild fast metadata cache, return to rapidly the buffer memory scene before fault recovery, and complete after fault recovery at meta data server, can directly utilize the data in buffer memory to continue process metadata request, improve the treatment effeciency of metadata, improve the work efficiency of entire system.
Accompanying drawing explanation
Accompanying drawing 1 is the schematic diagram of the described metadata cache Fast Reconstruction mechanism based on metadata daily record.
Embodiment
Below in conjunction with accompanying drawing, the metadata cache Fast Reconstruction mechanism based on metadata daily record disclosed in this invention is described in further details.
A kind of metadata cache Fast Reconstruction mechanism based on metadata daily record that the present invention proposes, in the failure process of meta data server, utilize the metadata operation daily record of precedence record, fast the metadata cache before fault is loaded in internal memory, rebuild the metadata cache information before fault.This metadata cache Fast Reconstruction mechanism mainly comprises metadata log access device, metadata repository and the large module of metadata cache three; Below this three large module is explained as follows in detail:
(1) metadata log access device: this module is responsible for the access of metadata daily record, metadata daily record is read and write with the form of entry, metadata log access device is responsible for ignoring the preservation mechanism of the concrete metadata daily record of bottom, and a metadata daily record read-write interface based on entry is upwards provided;
(2) metadata repository: the equipment of actual storage metadata, conventionally provides searching using index of metadata node as key word, creates, modification and deletion action;
(3) metadata cache: a region in meta data server internal memory, be responsible for a part of content in cache metadata storer, this partial content has close relationship with the metadata request of processing or just completing at present processing conventionally.
The concrete enforcement of the metadata cache Fast Reconstruction mechanism based on metadata daily record that the present invention proposes comprises three steps: the dump of metadata request processing, metadata daily record and metadata cache are rebuild.Respectively the enforcement of these three steps is elaborated below:
One, metadata request treatment scheme
In the time that meta data server is received the metadata request of client, can carry out following steps and complete the operation of request:
(1) structure metadata journal entries, meta data server is according to the type of request, the journal entries data corresponding to information structuring such as data item and the operation that will carry out of request;
(2) submit to metadata entry to metadata log access device, metadata log access device is responsible for journal entries to be written on daily record equipment;
(3) upgrade metadata cache, metadata log access device completes after writing of daily record, notice meta data server, meta data server is received after the report that daily record write, understand metadata updates operation and completed persistence, can upgrade memory cache, so that apply metadata operation;
(4) complete after buffer update, meta data server completes to clients report metadata request.
Two, the dump of metadata daily record
Meta data server can, according to dump strategy, be dumped to the content metadata recording in metadata daily record in metadata repository;
Before executive dumping operation, meta data server can be first according to the pressure of current system, comprises the information such as CPU, network, request waiting list length, and whether judgement is applicable to executive dumping operation at present, if metadata log manager finds that current system pressure is larger, postpone dump;
Dump operation does not need again to read daily record, only needs the data of buffer memory in metadata cache to be saved in metadata repository;
Dump operation also needs to record a dumping log in metadata daily record, and before mark dumping log, metadata daily record, all to complete dump, does not need the metadata daily record before playback dumping log in the start-up course of meta data server.
Three, metadata cache is rebuild flow process
Can draw according to step 1, two implementation process:
1. in metadata daily record, preserve the metadata operation of nearest execution, can from these journal entries, get related metadata item.According to lru algorithm, these metadata items are all focus metadata items, very possible as the required metadata item of using in next step client requests.And more approach the journal entries at metadata daily record end, the temperature of the metadata item of wherein using is higher.
2. the playback of metadata daily record need to be using some dumping logs as starting point, the consistance of guarantee metadata like this.
According to above 2 points, in the startup or failover procedure of meta data server, will carry out following operation and rebuild metadata cache, as shown in Figure 1:
(1) (initial) position of confirmation (metadata) daily record playback: meta data server will, by metadata log access device, travel through metadata daily record after starting from back to front one by one, while often traversing a metadata operation daily record, carry out following operation:
If a) this journal entries is metadata operation daily record, add up the number of the metadata item that this daily record relates to, statistics is joined in global statistics data;
If b) this journal entries is a dumping log, judge whether the global statistics data of current metadata item have reached threshold value, if reach threshold value, this dumping log is designated as the reference position of metadata daily record playback, traversal finishes; If do not reach threshold value, continue traversal forward;
(2) carry out playback (metadata) journalizing, confirming after the reference position of metadata daily record playback, from this position, travel through successively backward and playback metadata journal entries, in the process of playback journal entries, according to the metadata operation requirement in journal entries, from metadata repository, load relevant metadata item in metadata cache;
Complete after above two steps, in metadata cache, reconstruct metadata delay machine or restart before cache contents.
Remove outside feature technology of the present invention, be the known technology of those skilled in the art.
Claims (6)
1. the metadata cache Fast Reconstruction mechanism based on metadata daily record, is characterized in that, described metadata cache Fast Reconstruction mechanism comprises three large modules: metadata log access device, metadata repository and metadata cache; Wherein:
(1) metadata log access device is responsible for the access of metadata daily record, and metadata daily record is read and write with the form of entry, and metadata log access device is responsible for upwards providing a metadata daily record read-write interface based on entry;
(2) metadata repository is the equipment of actual storage metadata, for searching using index of metadata node as key word is provided, create, modification and deletion action;
(3) metadata cache is a region in meta data server internal memory, is responsible for content in cache metadata storer;
By the described metadata cache Fast Reconstruction mechanism based on metadata daily record, in the failover procedure of meta data server, can utilize the metadata operation daily record of precedence record, metadata cache before fault is loaded in meta data server internal memory, rebuilds the metadata cache information before fault.
2. the metadata cache Fast Reconstruction mechanism based on metadata daily record according to claim 1, it is characterized in that, the concrete enforcement of the described metadata cache Fast Reconstruction mechanism based on metadata daily record comprises three steps: the dump of metadata request processing, metadata daily record and metadata cache are rebuild.
3. the metadata cache Fast Reconstruction mechanism based on metadata daily record according to claim 2, is characterized in that the operating process of described metadata request processing:
In the time that meta data server is received the metadata request of client, meta data server is constructed corresponding metadata journal entries according to type, the data item of request and the operation information that will carry out of request;
Then metadata entry is submitted to metadata log access device, by metadata log access device, journal entries is written on daily record equipment;
Metadata log access device completes after writing of daily record, notice meta data server, meta data server is received after the report that daily record write, and upgrades meta data server memory cache, and last meta data server completes to clients report metadata request.
4. the metadata cache Fast Reconstruction mechanism based on metadata daily record according to claim 3, is characterized in that the dump of described metadata daily record:
Meta data server can, according to dump strategy, be dumped to the content metadata recording in metadata daily record in metadata repository;
Before executive dumping operation, meta data server, first according to the pressure of current system, comprises CPU, network, request waiting list length information, and whether judgement is applicable to executive dumping operation at present, if metadata log manager finds that current system pressure is larger, postpone dump;
Dump operation only needs the data of buffer memory in metadata cache to be saved in metadata repository.
5. the metadata cache Fast Reconstruction mechanism based on metadata daily record according to claim 4, it is characterized in that, described dump operation also needs to record a dumping log in metadata daily record, before mark dumping log, metadata daily record has all completed dump, in the start-up course of meta data server, does not need the metadata daily record before playback dumping log.
6. the metadata cache Fast Reconstruction mechanism based on metadata daily record according to claim 4, is characterized in that, the idiographic flow that described metadata cache is rebuild:
(1) reference position of confirmation metadata daily record playback: meta data server will, by metadata log access device, travel through metadata daily record after starting from back to front one by one, while often traversing a metadata operation daily record, carry out following operation:
If this journal entries is metadata operation daily record, add up the number of the metadata item that this daily record relates to, statistics is joined in global statistics data;
If this journal entries is a dumping log, judge whether the global statistics data of current metadata item have reached threshold value, if reach threshold value, this dumping log is designated as the reference position of metadata daily record playback, traversal finishes; If do not reach threshold value, continue traversal forward;
(2) carry out playback metadata journalizing, confirming after the reference position of metadata daily record playback, from this position, travel through successively backward and playback metadata journal entries, in the process of playback journal entries, according to the metadata operation requirement in journal entries, from metadata repository, load relevant metadata item in metadata cache.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410117821.3A CN103902479A (en) | 2014-03-27 | 2014-03-27 | Quick reconstruction mechanism for metadata cache on basis of metadata log |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410117821.3A CN103902479A (en) | 2014-03-27 | 2014-03-27 | Quick reconstruction mechanism for metadata cache on basis of metadata log |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103902479A true CN103902479A (en) | 2014-07-02 |
Family
ID=50993812
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410117821.3A Pending CN103902479A (en) | 2014-03-27 | 2014-03-27 | Quick reconstruction mechanism for metadata cache on basis of metadata log |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103902479A (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105302691A (en) * | 2015-10-20 | 2016-02-03 | 浪潮(北京)电子信息产业有限公司 | Metadata performance monitoring method and system |
| CN105302488A (en) * | 2015-10-27 | 2016-02-03 | 浪潮(北京)电子信息产业有限公司 | Data writing method and system for storage system |
| WO2017177752A1 (en) * | 2016-04-14 | 2017-10-19 | 杭州海康威视数字技术股份有限公司 | File storage method and device |
| CN108153804A (en) * | 2017-11-17 | 2018-06-12 | 极道科技（北京）有限公司 | A kind of metadata daily record update method of symmetric distributed file system |
| CN108427728A (en) * | 2018-02-13 | 2018-08-21 | 百度在线网络技术（北京）有限公司 | Management method, equipment and the computer-readable medium of metadata |
| CN108900337A (en) * | 2018-06-29 | 2018-11-27 | 郑州云海信息技术有限公司 | A kind of fault recovery method of Metadata Service, server, client and system |
| CN109032536A (en) * | 2018-08-31 | 2018-12-18 | 郑州云海信息技术有限公司 | Date storage method, device, system and equipment based on distributed cluster system |
| CN109508148A (en) * | 2018-11-09 | 2019-03-22 | 浪潮电子信息产业股份有限公司 | A kind of metadata method for reconstructing, device and computer readable storage medium |
| CN109669814A (en) * | 2018-12-10 | 2019-04-23 | 浪潮(北京)电子信息产业有限公司 | A kind of restoration methods of Metadata Service, device, equipment and readable storage medium storing program for executing |
| CN109669632A (en) * | 2018-12-10 | 2019-04-23 | 浪潮电子信息产业股份有限公司 | Metadata wiring method, device and medium based on distributed objects storage system |
| CN109828862A (en) * | 2017-11-23 | 2019-05-31 | 成都华为技术有限公司 | A kind of method and apparatus playing back log |
| CN110046132A (en) * | 2019-04-15 | 2019-07-23 | 苏州浪潮智能科技有限公司 | A kind of metadata request processing method, device, equipment and readable storage medium storing program for executing |
| CN112000623A (en) * | 2020-08-07 | 2020-11-27 | 北京浪潮数据技术有限公司 | Metadata access method and device and computer readable storage medium |
| CN112667149A (en) * | 2020-12-04 | 2021-04-16 | 北京浪潮数据技术有限公司 | Data heat sensing method, device, equipment and medium |
| CN115657956A (en) * | 2022-11-02 | 2023-01-31 | 中国科学院空间应用工程与技术中心 | Metadata consistency writing method and system for handling cache data loss |
| CN117348809A (en) * | 2023-10-08 | 2024-01-05 | 中电云计算技术有限公司 | Read cache method and system based on log writing |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5193162A (en) * | 1989-11-06 | 1993-03-09 | Unisys Corporation | Cache memory with data compaction for use in the audit trail of a data processing system having record locking capabilities |
| CN101089857A (en) * | 2007-07-24 | 2007-12-19 | 中兴通讯股份有限公司 | Internal store data base transaction method and system |
| CN101286127A (en) * | 2008-05-08 | 2008-10-15 | 华中科技大学 | Multi-fork diary memory continuous data protecting and restoration method |
| CN102089746A (en) * | 2008-05-13 | 2011-06-08 | 微软公司 | Flash recovery employing transaction log |
| CN103516549A (en) * | 2013-09-27 | 2014-01-15 | 浪潮电子信息产业股份有限公司 | File system metadata log mechanism based on shared object storage |
-
2014
- 2014-03-27 CN CN201410117821.3A patent/CN103902479A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5193162A (en) * | 1989-11-06 | 1993-03-09 | Unisys Corporation | Cache memory with data compaction for use in the audit trail of a data processing system having record locking capabilities |
| CN101089857A (en) * | 2007-07-24 | 2007-12-19 | 中兴通讯股份有限公司 | Internal store data base transaction method and system |
| CN101286127A (en) * | 2008-05-08 | 2008-10-15 | 华中科技大学 | Multi-fork diary memory continuous data protecting and restoration method |
| CN102089746A (en) * | 2008-05-13 | 2011-06-08 | 微软公司 | Flash recovery employing transaction log |
| CN103516549A (en) * | 2013-09-27 | 2014-01-15 | 浪潮电子信息产业股份有限公司 | File system metadata log mechanism based on shared object storage |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105302691B (en) * | 2015-10-20 | 2018-04-24 | 浪潮(北京)电子信息产业有限公司 | A kind of metadata method for monitoring performance and system |
| CN105302691A (en) * | 2015-10-20 | 2016-02-03 | 浪潮(北京)电子信息产业有限公司 | Metadata performance monitoring method and system |
| CN105302488A (en) * | 2015-10-27 | 2016-02-03 | 浪潮(北京)电子信息产业有限公司 | Data writing method and system for storage system |
| CN105302488B (en) * | 2015-10-27 | 2018-05-01 | 浪潮(北京)电子信息产业有限公司 | The method for writing data and system of a kind of storage system |
| WO2017177752A1 (en) * | 2016-04-14 | 2017-10-19 | 杭州海康威视数字技术股份有限公司 | File storage method and device |
| CN108153804A (en) * | 2017-11-17 | 2018-06-12 | 极道科技（北京）有限公司 | A kind of metadata daily record update method of symmetric distributed file system |
| CN108153804B (en) * | 2017-11-17 | 2021-03-16 | 极道科技（北京）有限公司 | Metadata log updating method for symmetric distributed file system |
| CN109828862A (en) * | 2017-11-23 | 2019-05-31 | 成都华为技术有限公司 | A kind of method and apparatus playing back log |
| CN109828862B (en) * | 2017-11-23 | 2023-08-22 | 成都华为技术有限公司 | Method and device for replaying log |
| CN108427728A (en) * | 2018-02-13 | 2018-08-21 | 百度在线网络技术（北京）有限公司 | Management method, equipment and the computer-readable medium of metadata |
| CN108900337A (en) * | 2018-06-29 | 2018-11-27 | 郑州云海信息技术有限公司 | A kind of fault recovery method of Metadata Service, server, client and system |
| CN108900337B (en) * | 2018-06-29 | 2021-07-16 | 郑州云海信息技术有限公司 | Fault recovery method, server, client and system for metadata service |
| CN109032536A (en) * | 2018-08-31 | 2018-12-18 | 郑州云海信息技术有限公司 | Date storage method, device, system and equipment based on distributed cluster system |
| CN109032536B (en) * | 2018-08-31 | 2021-08-10 | 郑州云海信息技术有限公司 | Data storage method, device, system and equipment based on distributed cluster system |
| CN109508148B (en) * | 2018-11-09 | 2021-08-10 | 浪潮电子信息产业股份有限公司 | Metadata reconstruction method and device and computer readable storage medium |
| CN109508148A (en) * | 2018-11-09 | 2019-03-22 | 浪潮电子信息产业股份有限公司 | A kind of metadata method for reconstructing, device and computer readable storage medium |
| CN109669814A (en) * | 2018-12-10 | 2019-04-23 | 浪潮(北京)电子信息产业有限公司 | A kind of restoration methods of Metadata Service, device, equipment and readable storage medium storing program for executing |
| CN109669632A (en) * | 2018-12-10 | 2019-04-23 | 浪潮电子信息产业股份有限公司 | Metadata wiring method, device and medium based on distributed objects storage system |
| CN110046132A (en) * | 2019-04-15 | 2019-07-23 | 苏州浪潮智能科技有限公司 | A kind of metadata request processing method, device, equipment and readable storage medium storing program for executing |
| CN110046132B (en) * | 2019-04-15 | 2022-04-22 | 苏州浪潮智能科技有限公司 | Metadata request processing method, device, equipment and readable storage medium |
| CN112000623A (en) * | 2020-08-07 | 2020-11-27 | 北京浪潮数据技术有限公司 | Metadata access method and device and computer readable storage medium |
| CN112667149A (en) * | 2020-12-04 | 2021-04-16 | 北京浪潮数据技术有限公司 | Data heat sensing method, device, equipment and medium |
| CN112667149B (en) * | 2020-12-04 | 2023-12-29 | 北京浪潮数据技术有限公司 | Data heat sensing method, device, equipment and medium |
| CN115657956A (en) * | 2022-11-02 | 2023-01-31 | 中国科学院空间应用工程与技术中心 | Metadata consistency writing method and system for handling cache data loss |
| CN115657956B (en) * | 2022-11-02 | 2023-08-22 | 中国科学院空间应用工程与技术中心 | Metadata consistency writing method and system for coping with cache data loss |
| CN117348809A (en) * | 2023-10-08 | 2024-01-05 | 中电云计算技术有限公司 | Read cache method and system based on log writing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103902479A (en) | Quick reconstruction mechanism for metadata cache on basis of metadata log | |
| US10503423B1 (en) | System and method for cache replacement using access-ordering lookahead approach | |
| US9710535B2 (en) | Object storage system with local transaction logs, a distributed namespace, and optimized support for user directories | |
| US10339017B2 (en) | Methods and systems for using a write cache in a storage system | |
| CN106484906B (en) | Distributed object storage system flash-back method and device | |
| CN102014158B (en) | Cloud storage service client high-efficiency fine-granularity data caching system and method | |
| US9817865B2 (en) | Direct lookup for identifying duplicate data in a data deduplication system | |
| US9772949B2 (en) | Apparatus, system and method for providing a persistent level-two cache | |
| CN107179878B (en) | Data storage method and device based on application optimization | |
| KR100979750B1 (en) | Apparatus and method for managing file in distributed storage system | |
| CN105183839A (en) | Hadoop-based storage optimizing method for small file hierachical indexing | |
| CN108021717B (en) | Method for implementing lightweight embedded file system | |
| CN103595797B (en) | Caching method for distributed storage system | |
| CN103516549B (en) | A kind of file system metadata log mechanism based on shared object storage | |
| US20130297969A1 (en) | File management method and apparatus for hybrid storage system | |
| CN107368608A (en) | The HDFS small documents buffer memory management methods of algorithm are replaced based on ARC | |
| CN104657461A (en) | File system metadata search caching method based on internal memory and SSD (Solid State Disk) collaboration | |
| US9189408B1 (en) | System and method of offline annotation of future accesses for improving performance of backup storage system | |
| US8612717B2 (en) | Storage system | |
| CN110704431A (en) | Hierarchical storage management method for mass data | |
| WO2017023709A1 (en) | Object storage system with local transaction logs, a distributed namespace, and optimized support for user directories | |
| CN110134551B (en) | Continuous data protection method and device | |
| CN109521957A (en) | A kind of data processing method and device | |
| US20210132824A1 (en) | Information processing apparatus and recording medium storing information processing program | |
| Tchaye-Kondi et al. | Hadoop perfect file: a fast access container for small files with direct in disc metadata access |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20140702 |