CN105760519B - Cluster file system and file lock distribution method thereof - Google Patents
Cluster file system and file lock distribution method thereof Download PDFInfo
- Publication number
- CN105760519B CN105760519B CN201610108914.9A CN201610108914A CN105760519B CN 105760519 B CN105760519 B CN 105760519B CN 201610108914 A CN201610108914 A CN 201610108914A CN 105760519 B CN105760519 B CN 105760519B
- Authority
- CN
- China
- Prior art keywords
- file
- file lock
- locking
- client
- lock
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/18—File system types
- G06F16/182—Distributed file systems
- G06F16/1824—Distributed file systems implemented using Network-attached Storage [NAS] architecture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/17—Details of further file system functions
- G06F16/176—Support for shared access to files; File sharing support
- G06F16/1767—Concurrency control, e.g. optimistic or pessimistic approaches
- G06F16/1774—Locking methods, e.g. locking methods for file systems allowing shared and concurrent access to files
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (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 discloses a cluster file system and a file lock distribution method thereof, wherein the cluster file system comprises: the agent module acquires a file lock for a file from the file lock module and receives a plurality of first locking requests of a plurality of service clients for the file; establishing a waiting queue for the first locking requests according to a time sequence, sequentially responding to the first locking requests according to the sequence of the waiting queue, and distributing the file lock to a corresponding service client for holding; when all the service clients do not hold the file lock any more, the waiting queue is empty, and a new first locking request is not received within a subsequent preset time, releasing the file lock; under the state that the agent module does not hold the file lock, the file lock module receives a second locking request from the repair client and distributes the file lock to the repair client for holding; the invention ensures that the front-end service is not influenced when the data is repaired, ensures the performance of the front-end service, fully reuses and utilizes hardware resources and reduces the cost of users.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a cluster file system and a file lock allocation method thereof.
Background
The cluster file system is a file system which runs on a plurality of computers and is communicated with each other in a certain mode so as to integrate and virtualize all storage space resources in a cluster and provide file access service for the outside. The method is different from the purposes of local file systems such as NTFS, EXT and the like, wherein the former is used for expandability, and the latter is operated in a single machine environment and is used for purely managing mapping between blocks and files and file attributes. The cluster file system has the characteristic of high availability, namely that the cluster file system can still provide normal file access within a certain limit when suffering from human misoperation, natural fault and the like, copy or erasure technology is generally adopted to protect data, and data synchronization is required after disaster redundant data is degraded; in the process of file access and data synchronous repair, a file lock mechanism is applied, that is, a file can only be accessed by a user with a file lock.
When the existing cluster file system performs data restoration of files, data restoration and front-end services are generally physically isolated by dividing network segments, although bandwidth conflict of front-end service data is eliminated, process pressure conflict between the front-end services and the data restoration cannot be avoided, so that read-write requests of the front-end services can be affected during the data restoration, and a user needs to add a physical link for the data restoration with low probability, so that hardware cost and management operation cost are increased undoubtedly.
Disclosure of Invention
In view of the above, an object of the present invention is to provide a cluster file system and a file lock allocation method thereof, so that a front-end service is not affected when data is repaired, the performance of the front-end service is ensured, the high availability characteristic of the cluster file system is reflected, hardware resources are fully reused, and further, user cost is reduced.
Based on the above object, the present invention provides a file lock allocation method for a cluster file system, where the cluster file system includes: a file lock module and an agent module; the method comprises the following steps:
the agent module acquires a file lock for a file from the file lock module and receives a plurality of first locking requests of a plurality of service clients for the file;
the agent module establishes a waiting queue for the first locking requests according to a time sequence, sequentially responds to the first locking requests according to the sequence of the waiting queue, and distributes the file lock to a corresponding service client for holding;
the agent module monitors the state of the file lock, and releases the file lock when all the service clients do not hold the file lock any more, the waiting queue is empty and a new first locking request is not received in the subsequent preset time;
and under the state that the agent module does not hold the file lock, the file lock module receives a second locking request from the repair client and distributes the file lock to the repair client for holding.
Preferably, after the file lock module allocates the file lock to the repair client for holding, the method further includes the following steps:
and the file lock module monitors the progress of file repair of the file lock held by the repair client, and when the repair data reaches a preset word length, the repair client releases the file lock held by the repair client.
Preferably, the preset word length is 128 k.
Preferably, the proxy module establishes a waiting queue for the first locking requests according to a time sequence, sequentially responds to the first locking requests according to the sequence of the waiting queue, and allocates the file lock to a corresponding service client for holding, and then further includes:
the agent module judges whether a locking interval of a service client currently holding a file lock conflicts with a locking interval required by a next first locking request in the waiting queue, and if so, the next first locking request is kept in the waiting queue; and if not, responding to the next first locking request.
Preferably, the preset time period is as follows: 0-10 s.
In another aspect, the present invention further provides a cluster file system applying the method as described in any one of the above, including a file lock module for allocating a file lock, further including:
the proxy module is used for acquiring a file lock of a file from the file lock module and receiving a plurality of first locking requests of a plurality of service clients to the file; establishing a waiting queue for the first locking requests according to a time sequence, sequentially responding to the first locking requests according to the sequence of the waiting queue, and distributing the file lock to a corresponding service client for holding; monitoring the state of a file lock, and releasing the file lock when all business clients do not hold the file lock any more, the waiting queue is empty and a new first locking request is not received within a subsequent preset time;
the file lock module is further used for receiving a second locking request from the repair client under the state that the agent module does not hold the file lock, and distributing the file lock to the repair client for holding.
Preferably, the file lock module is further configured to: and monitoring the progress of file repair of the file lock held by the repair client, and when the repair data reaches a preset word length, enabling the repair client to release the file lock held by the repair client.
Preferably, the preset word length is 128 k.
Preferably, the agent module is further configured to: judging whether a locking interval of a service client currently holding a file lock conflicts with a locking interval required by a next first locking request in the waiting queue, if so, keeping the next first locking request in the waiting queue; and if not, responding to the next first locking request.
Preferably, the preset time period is as follows: 0-10 s.
As can be seen from the above description, the cluster file system and the file lock allocation method thereof according to the present invention logically isolate the front-end service process from the data repair process, so that the front-end service is not affected during data repair, and specifically have the following advantages:
(1) when the front-end service client has an access request, the back-end data synchronous repair waits.
(2) The method and the system ensure the safety of the service data, reduce the influence of data synchronization on the front-end service, and reduce the hardware cost and the operation management cost.
(3) The back end can automatically utilize the idle time period of the front end access or the time period with smaller access pressure to carry out data synchronous restoration, and the time window of the data synchronous restoration is shortened as much as possible while the front end service is not influenced, thereby improving the data safety.
(4) Professional engineers are not needed to intervene, and the operation and maintenance cost is reduced.
(5) The data synchronization repair can be logically isolated from the front-end service, and the influence of IO conflict on the performance of the front-end service is avoided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flowchart of a file lock allocation method of a cluster file system according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a cluster file system according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to specific embodiments and the accompanying drawings.
It should be noted that all expressions using "first" and "second" in the embodiments of the present invention are used for distinguishing two entities with the same name but different names or different parameters, and it should be noted that "first" and "second" are merely for convenience of description and should not be construed as limitations of the embodiments of the present invention, and they are not described in any more detail in the following embodiments.
The embodiment of the invention provides a cluster file system and a file lock distribution method thereof. The existing cluster file system generally comprises a file lock module used for distributing file locks, and specifically distributes the file locks to corresponding client sides for holding according to the locking requests of the client sides for certain files; after the client finishes the predetermined work, the file lock is released, and the file lock can be distributed to other clients. In the embodiment of the present invention, the file locks used may be read-write locks or mutual exclusion locks, and the use of different types of file locks does not affect the technical effect of the implementation of the present invention, and the specific functions of the above-mentioned types of file locks are the prior art, and are not described in detail in the specification. The clients generally include a service client and a repair client. The service client is generally positioned at the front end of the system, is used by a user and carries out a front-end service process through the service client; the repair client is generally located at the back end of the system, and is used for performing a data repair process of the file.
In this embodiment, the cluster file system includes: the file locking module and the proxy module. Wherein, the file lock module is the same as the prior art, and the user distributes the file lock; the proxy module is a proprietary module of the present invention, and is used for performing distribution management on a locking request (in this embodiment, a first locking request) from a service client. Specifically, the file lock allocation method for the cluster file system in this embodiment includes the following steps:
the agent module acquires a file lock for a file from the file lock module and receives a plurality of first locking requests of a plurality of service clients for the file;
the agent module establishes a waiting queue for the first locking requests according to a time sequence, sequentially responds to the first locking requests according to the sequence of the waiting queue, and distributes the file lock to a corresponding service client for holding;
the agent module monitors the state of the file lock, and releases the file lock when all the service clients do not hold the file lock any more, the waiting queue is empty and a new first locking request is not received in the subsequent preset time;
and under the state that the agent module does not hold the file lock, the file lock module receives a second locking request from the repair client and distributes the file lock to the repair client for holding.
It can be seen from the foregoing embodiments that, in the file lock allocation method for a cluster file system according to the present invention, a first locking request from a service client and a second locking request from a self-repair client are logically isolated, so that the priority of the first locking request is higher than that of the second locking request; in effect, when the front-end service has an access request, the data synchronous repair process can avoid; if the front end has no service access, the back end data synchronous repair process can be almost performed as full as possible. Furthermore, through the setting of the preset duration, the locking priority of the service client and the repair client is flexibly adjusted, and the synchronization speed of the repair client is controlled, so that the repair client can multiplex a physical link, and the user cost is saved. In addition, the method of the invention can also be applied to various data protection algorithms, such as redundant copies, erasure code technology and the like; but also other backend synchronization requirements such as hierarchical storage, data rebalancing, etc.
Referring to fig. 1, a flowchart of a file lock allocation method of a cluster file system according to an embodiment of the present invention is shown.
As a more specific embodiment, the file lock allocation method of the cluster file system includes the following steps:
For a certain file in the cluster file system, the locking request of the service client for the file generally refers to a locking request for different data intervals of the file sent by the same service client and a locking request for the file sent by different service clients, and the locking request is referred to as a first locking request in this embodiment.
In this step, the agent module first obtains the file lock from the file lock module. And under the state that the agent module holds the file lock, first locking requests from the service client are all sent to the agent module for processing.
102, the agent module establishes a waiting queue for the first locking requests according to a time sequence, responds to the first locking requests in sequence according to the waiting queue, and allocates the file lock to a corresponding service client for holding.
For the received first locking requests, a waiting queue is firstly established according to the time sequence of the first locking requests, and the first locking requests are sequentially arranged in the waiting queue according to the time sequence from early to late. And then, sequentially responding according to a plurality of first locking requests in the waiting queue, and further distributing the file lock to the corresponding business client to hold. That is, after the current service client that holds the file lock completes the work and releases the file lock, the file lock does not provide equal acquisition opportunities to all other locking request issuing ends, but the file lock is allocated to the next service client that issues the first locking request in the waiting queue according to the waiting queue.
103, the agent module judges whether a locking interval of the current business client holding the file lock conflicts with a locking interval required by the next first locking request in the waiting queue, if yes, step 104 is executed; if not, go to step 105.
In this step, under the condition that one service client currently holds the file lock, it is further determined whether a locking interval required by a next first locking request in the waiting queue conflicts with a locking interval of the service client currently holding the file lock. The locking interval refers to a file interval which is required to be locked by a first locking request sent by different service clients, and the conflict existing in the locking interval refers to the overlapping part existing in the locking intervals of the two business clients; the fact that the locking intervals are not in conflict means that the locking intervals of the two business clients are not in overlapped parts, and under the condition that the locking intervals are not in overlapped parts, the file locks can be simultaneously distributed to the corresponding two business clients to be held at the same time, and when the two business clients finish respective file data access work, conflict cannot be generated.
And when the locking interval of the service client currently holding the file lock conflicts with the locking area required by the next first locking request in the waiting queue, keeping the next first locking request in the waiting queue, and after the service client currently holding the file lock releases the file lock, distributing the file lock to the service client sending the next first locking request in the waiting queue.
And step 105, responding to the next first locking request.
And when the locking interval of the service client currently holding the file lock does not conflict with the locking interval required by the next first locking request in the waiting queue, responding to the next first locking request in the waiting queue, and simultaneously distributing the file lock to the service client sending the next first locking request.
And 106, monitoring the state of the file lock by the agent module, and releasing the file lock when all the service clients do not hold the file lock any more, the waiting queue is empty and a new first locking request is not received in the subsequent preset time.
In this step, the state of the file lock is continuously monitored, and when it is monitored that the file locks held by all the service clients are released and the waiting queue is empty, the file lock is further released when it is continuously monitored that a new first locking request is received and added to the waiting queue within a subsequent preset time period. Specifically, the selectable range of the preset duration is as follows: 0-10 s; the preferred preset duration is set to 1 s.
And step 107, in the state that the agent module does not hold the file lock, the file lock module receives a second locking request from the repair client and distributes the file lock to the repair client for holding.
After the file lock is released by the agent module, the file lock module can receive and respond to a second locking request from the repair client, the file lock is distributed to the repair client to hold according to the second locking request, and the data synchronization repair of the file is started after the repair client holds the file lock.
In the process that a file lock is distributed to a repair client to hold, and the repair client holds the file lock to perform data synchronous repair on the file, the progress of file repair of the file lock held by the repair client is monitored, and when the repair data reaches a preset word length, an instruction is immediately sent out to enable the repair client to release the file lock held by the repair client. Preferably, the preset word length is 128 k.
Through the step, the time length for the file lock held by the repair client to carry out data synchronous repair is limited, and when the repair client wants to continue data synchronous repair, the second locking request needs to be sent again, so that the file lock is held by the service client as much as possible, and service data processing is preferably carried out.
Fig. 2 is a schematic diagram of a cluster file system according to an embodiment of the present invention.
On the other hand, the embodiment of the present invention further provides a cluster file system, where the cluster file system applies the file lock allocation method described in the above embodiment. The cluster file system includes, in addition to a file lock module 201 for allocating file locks: the agent module 202.
In this embodiment, the agent module 202 is configured to obtain a file lock for a file from the file lock module 201 and receive a plurality of first locking requests for the file from a plurality of service clients 203; establishing a waiting queue for the first locking requests according to a time sequence, sequentially responding to the first locking requests according to the sequence of the waiting queue, and distributing the file lock to a corresponding service client 203 for holding; monitoring the state of the file lock, and releasing the file lock when all the service clients 203 do not hold the file lock any more, the waiting queue is empty and a new first locking request is not received within a subsequent preset time;
in addition, in this embodiment, the file lock module 201 is further configured to receive a second locking request from the repairing client 204 in a state that the proxy module 202 does not hold a file lock, and allocate the file lock to the repairing client 204.
In a preferred embodiment, the file lock module 201 is further configured to: monitoring the progress of file repair of the file lock held by the repair client 204, and when the repair data reaches a preset word length, enabling the repair client 204 to release the file lock held by the repair client 204. Wherein the preset word length is 128 k.
In a preferred embodiment, the agent module 202 is further configured to: judging whether a locking interval of the service client 203 currently holding the file lock conflicts with a locking interval required by the next first locking request in the waiting queue, if so, keeping the next first locking request in the waiting queue; and if not, responding to the next first locking request. Wherein the preset duration is: 0-10 s; preferably, the preset time period is 1 s.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to these examples; within the idea of the invention, also features in the above embodiments or in different embodiments may be combined, steps may be implemented in any order, and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity. Therefore, any omissions, modifications, substitutions, improvements and the like that may be made without departing from the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (8)
1. A file lock allocation method of a cluster file system is characterized in that the cluster file system comprises the following steps: the system comprises a file lock module used for distributing file locks, and an agent module used for distributing and managing a first locking request from a service client; the method comprises the following steps:
the agent module acquires a file lock for a file from the file lock module and receives a plurality of first locking requests of a plurality of service clients for the file;
the agent module establishes a waiting queue for the first locking requests according to a time sequence, sequentially responds to the first locking requests according to the sequence of the waiting queue, and distributes the file lock to a corresponding service client for holding;
the agent module monitors the state of the file lock, and releases the file lock when all the service clients do not hold the file lock any more, the waiting queue is empty and a new first locking request is not received in the subsequent preset time;
under the state that the agent module does not hold the file lock, the file lock module receives a second locking request from a repair client and distributes the file lock to the repair client;
after the file lock module allocates a file lock to the repair client for holding, the method further comprises the following steps:
and the file lock module monitors the progress of file repair of the file lock held by the repair client, and when the repair data reaches a preset word length, the repair client releases the file lock held by the repair client.
2. The method of claim 1, wherein the predetermined word size is 128 k.
3. The method according to claim 1, wherein the agent module establishes a waiting queue for the first locking requests according to a time sequence, sequentially responds to the first locking requests according to the sequence of the waiting queue, and after allocating the file lock to a corresponding service client for holding, further comprises:
the agent module judges whether a locking interval of a service client currently holding a file lock conflicts with a locking interval required by a next first locking request in the waiting queue, and if so, the next first locking request is kept in the waiting queue; and if not, responding to the next first locking request.
4. The method of claim 1, wherein the preset duration is: 0-10 s.
5. A cluster file system applying the method of any one of claims 1 to 4, comprising a file lock module for assigning a file lock, further comprising:
the proxy module is used for acquiring a file lock of a file from the file lock module and receiving a plurality of first locking requests of a plurality of service clients to the file; establishing a waiting queue for the first locking requests according to a time sequence, sequentially responding to the first locking requests according to the sequence of the waiting queue, and distributing the file lock to a corresponding service client for holding; monitoring the state of a file lock, and releasing the file lock when all business clients do not hold the file lock any more, the waiting queue is empty and a new first locking request is not received within a subsequent preset time;
the file lock module is further used for receiving a second locking request from the repair client under the state that the agent module does not hold the file lock, and distributing the file lock to the repair client;
the file lock module is further to: and monitoring the progress of file repair of the file lock held by the repair client, and when the repair data reaches a preset word length, enabling the repair client to release the file lock held by the repair client.
6. The clustered file system of claim 5 wherein the preset word size is 128 k.
7. The clustered file system of claim 5, wherein the proxy module is further configured to: judging whether a locking interval of a service client currently holding a file lock conflicts with a locking interval required by a next first locking request in the waiting queue, if so, keeping the next first locking request in the waiting queue; and if not, responding to the next first locking request.
8. The clustered file system of claim 5 wherein the preset duration is: 0-10 s.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610108914.9A CN105760519B (en) | 2016-02-26 | 2016-02-26 | Cluster file system and file lock distribution method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610108914.9A CN105760519B (en) | 2016-02-26 | 2016-02-26 | Cluster file system and file lock distribution method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105760519A CN105760519A (en) | 2016-07-13 |
| CN105760519B true CN105760519B (en) | 2020-08-28 |
Family
ID=56331374
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610108914.9A Active CN105760519B (en) | 2016-02-26 | 2016-02-26 | Cluster file system and file lock distribution method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105760519B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107181789A (en) * | 2017-03-31 | 2017-09-19 | 北京奇艺世纪科技有限公司 | A kind of distributed lock implementation method and device |
| CN107016094B (en) * | 2017-04-06 | 2020-11-17 | 深圳创维－Rgb电子有限公司 | Project shared file multi-person collaborative development method, device and system |
| CN107423454B (en) * | 2017-09-22 | 2021-01-12 | 苏州浪潮智能科技有限公司 | Method, device and equipment for processing file lock in distributed file system |
| CN110008031B (en) * | 2018-01-05 | 2022-04-15 | 北京金山云网络技术有限公司 | Device operation method, cluster system, electronic device and readable storage medium |
| CN110968563B (en) * | 2018-09-29 | 2023-11-17 | 华为技术有限公司 | Data storage method, metadata server and client |
| CN109408477A (en) * | 2018-10-09 | 2019-03-01 | 郑州云海信息技术有限公司 | A kind of method, system and associated component that setting group document is locked |
| CN109412891B (en) * | 2018-10-19 | 2022-04-22 | 郑州云海信息技术有限公司 | Method and device for detecting client state |
| CN109743366B (en) * | 2018-12-21 | 2022-04-05 | 苏宁易购集团股份有限公司 | Resource locking method, device and system for multi-living scene |
| CN113760369A (en) * | 2020-09-29 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Concurrent thread processing method, concurrent thread processing device, electronic equipment and storage medium |
| CN114116639B (en) * | 2022-01-27 | 2022-04-29 | 苏州浪潮智能科技有限公司 | Method, device, equipment and medium for setting cluster file lock |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103488526A (en) * | 2013-09-02 | 2014-01-01 | 用友软件股份有限公司 | System and method for locking business resource in distributed system |
| CN103514298A (en) * | 2013-10-16 | 2014-01-15 | 浪潮(北京)电子信息产业有限公司 | Method for achieving file lock and metadata server |
| CN103795801A (en) * | 2014-02-12 | 2014-05-14 | 浪潮电子信息产业股份有限公司 | Metadata group design method based on real-time application group |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5828876A (en) * | 1996-07-31 | 1998-10-27 | Ncr Corporation | File system for a clustered processing system |
| CN100432940C (en) * | 2006-10-19 | 2008-11-12 | 华为技术有限公司 | Method for distributing shared resource lock in computer cluster system and cluster system |
| CN104484236B (en) * | 2014-11-28 | 2017-11-03 | 曙光云计算集团有限公司 | A kind of HA accesses adaptive method |
-
2016
- 2016-02-26 CN CN201610108914.9A patent/CN105760519B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103488526A (en) * | 2013-09-02 | 2014-01-01 | 用友软件股份有限公司 | System and method for locking business resource in distributed system |
| CN103514298A (en) * | 2013-10-16 | 2014-01-15 | 浪潮(北京)电子信息产业有限公司 | Method for achieving file lock and metadata server |
| CN103795801A (en) * | 2014-02-12 | 2014-05-14 | 浪潮电子信息产业股份有限公司 | Metadata group design method based on real-time application group |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105760519A (en) | 2016-07-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105760519B (en) | Cluster file system and file lock distribution method thereof | |
| US9189268B2 (en) | Limiting simultaneous data transfers and efficient throttle management | |
| EP3567829B1 (en) | Resource management method and apparatus | |
| CN110941481A (en) | Resource scheduling method, device and system | |
| JP5510556B2 (en) | Method and system for managing virtual machine storage space and physical hosts | |
| US8352434B2 (en) | Performing scheduled backups of a backup node associated with a plurality of agent nodes | |
| US8850156B2 (en) | Method and system for managing virtual machine storage space and physical host | |
| US10778750B2 (en) | Server computer management system for supporting highly available virtual desktops of multiple different tenants | |
| US9319281B2 (en) | Resource management method, resource management device, and program product | |
| US11888933B2 (en) | Cloud service processing method and device, cloud server, cloud service system and storage medium | |
| US20130282795A1 (en) | Method And Apparatus for Web Based Storage On Demand | |
| US9104501B2 (en) | Preparing parallel tasks to use a synchronization register | |
| KR101714412B1 (en) | Method and apparatus for organizing database system in cloud environment | |
| CN111694658A (en) | CPU resource allocation method, device, electronic equipment and storage medium | |
| US7219345B2 (en) | System and method for terminating processes in a distributed computing system | |
| CN108352995B (en) | SMB service fault processing method and storage device | |
| WO2018010603A1 (en) | Storage mode upgrade method, apparatus and system based on video cloud storage system | |
| CN110046138B (en) | iSCSI target multi-instance processing method and distributed storage system | |
| CN114172903B (en) | Node capacity expansion method, device, equipment and medium of slm scheduling system | |
| CN111857548B (en) | Data reading method, device and system | |
| CN116112499B (en) | Construction method of data acquisition system and data acquisition method | |
| CN117668010A (en) | Task processing method, electronic device and storage medium | |
| US20230393882A1 (en) | Management of virtual machine shutdowns in a computing environment based on resource locks | |
| CN117993922A (en) | Method and device for determining ticket number and electronic equipment | |
| CN110737489A (en) | intelligent high-performance computing centers |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210902 Address after: 271024 Taishan science and Technology Industrial Park, high tech Zone, Tai'an City, Shandong Province Patentee after: Shandong whale shark Information Technology Co.,Ltd. Address before: 100195 Room 101, 1st floor, building 31, yuquanhuigu, No.3 minzhuang Road, Yuquanshan, Haidian District, Beijing Patentee before: PERABYTES TECHNOLOGY Co.,Ltd. |
|
| TR01 | Transfer of patent right |