CN109213571A - A kind of internal memory sharing method, Container Management platform and computer readable storage medium - Google Patents
A kind of internal memory sharing method, Container Management platform and computer readable storage medium Download PDFInfo
- Publication number
- CN109213571A CN109213571A CN201811006390.8A CN201811006390A CN109213571A CN 109213571 A CN109213571 A CN 109213571A CN 201811006390 A CN201811006390 A CN 201811006390A CN 109213571 A CN109213571 A CN 109213571A
- Authority
- CN
- China
- Prior art keywords
- container
- address space
- access
- virtual address
- semaphore
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/54—Interprogram communication
- G06F9/544—Buffers; Shared memory; Pipes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/45583—Memory management, e.g. access or allocation
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This application discloses a kind of internal memory sharing method, Container Management platform and computer readable storage mediums, the described method includes: creating one piece of virtual address space on the host where at least two containers, the at least two containers label having the same, makes virtual address space described in the memory sharing of at least two container;The state of the container of virtual address space described in test access;When the container delay machine of access, the operation address of semaphore and the container of access in virtual address space is sent to the container with the container accessed with same label, the semaphore is used to control the synchronization and mutual exclusion of data access between container.The state that the application passes through the container of test access virtual address space, and in the container delay machine of access, semaphore and its operation address are sent to other containers, under the premise of reduction front end is repeatedly distributed, shared drive between multiple Memcached server nodes is realized, to solve the problems, such as the Single Point of Faliure of Memcached cluster.
Description
Technical field
The present invention relates to, but not limited to field of computer technology more particularly to a kind of internal memory sharing method, container tube to pat
Platform and computer readable storage medium.
Background technique
Memcached is a kind of high performance distributed memory target cache system, for dynamic web page (Web) application with
Mitigate database loads, inquired from initial database retrieval, scientific research field big data analysis till now, application range is got over
Come wider.But due to not having between the Memcached server in Memcached cluster and others Memcached server
There is any communication, and without any data backup, so when any one Memcached server node breaks down
When, it may appear that loss of data and reconnection, and then influence the stability of Memcached service.
The prior art is by increasing proxy server before Memcached server node, by proxy server to more
Platform Memcached server node carries out data and synchronizes, and ensures data integrity;Or by Memcached server section
Increase mcrouter (a kind of Memcached protocol router) before point, is turned by the tracking of mcrouter realizing route, heartbeat failure
Move etc..
But above two mode not only introduces additional component, improves the complexity of system, and more importantly
Data needs are constantly copied, and are considerably increased the cost of system maintenance, are reduced efficiency.
Summary of the invention
The embodiment of the invention provides a kind of internal memory sharing method, Container Management platform and computer readable storage medium,
It can realize under the premise of reduction front end data repeatedly copies and share message between multiple Memcached server nodes.
In order to reach the object of the invention, the technical solution of the embodiment of the present invention is achieved in that
The embodiment of the invention provides a kind of internal memory sharing methods, comprising:
One piece of virtual address space is created on the host where at least two containers, at least two container has
Identical label makes virtual address space described in the memory sharing of at least two container;
The state of the container of virtual address space described in test access;
When the container delay machine of the access, by semaphore and the container of the access in the virtual address space
Operation address is sent to the container for having same label with the container of the access, and the semaphore is for controlling number between container
According to the synchronization and mutual exclusion of access.
In one embodiment, include: before the method
A memory type block file is mapped on the host to the process address space;
By the address of the process address space of memory type block file mapping and the virtual address space phase of the creation
Association.
In one embodiment, the method also includes:
The quantity for inspecting periodically the container currently survived, when the quantity for the container currently survived is less than preset value
When, restart the container of delay machine.
In one embodiment, the load distribution strategy of at least two container is poll pattern or client-based meeting
Talk about holding mode.
The embodiment of the invention also provides a kind of computer readable storage medium, the computer-readable recording medium storage
Have one or more program, one or more of programs can be executed by one or more processor, with realize such as with
The step of upper described in any item internal memory sharing methods.
The embodiment of the invention also provides a kind of Container Management platforms, including processor and memory, in which:
The processor is for executing the memory sharing program stored in memory, to realize as described in any of the above item
The step of internal memory sharing method.
The embodiment of the invention also provides a kind of Container Management platforms, including setup module and first detection module, in which:
Setup module, on the host where at least two containers create one piece of virtual address space, it is described extremely
Few two container labels having the same, make virtual address space described in the memory sharing of at least two container;
First detection module, the state of the container for virtual address space described in test access, when the appearance of the access
When device delay machine, the operation address of semaphore and the container of the access in the virtual address space is sent to and the visit
The container asked has the container of same label, and the semaphore is used to control the synchronization and mutual exclusion of data access between container.
In one embodiment, the setup module is also used to:
A memory type block file is mapped on the host to the process address space;
By the address of the process address space of memory type block file mapping and the virtual address space phase of the creation
Association.
In one embodiment, the Container Management platform further includes the second detection module, in which:
Second detection module is used for: the quantity for the container currently survived is inspected periodically, when the institute currently survived
When stating the quantity of container less than preset value, the container of delay machine is restarted.
In one embodiment, the load distribution strategy of at least two container is poll pattern or client-based meeting
Talk about holding mode.
The technical solution of the embodiment of the present invention, has the following beneficial effects:
Internal memory sharing method, Container Management platform and computer readable storage medium provided in an embodiment of the present invention, pass through
The state of the container of test access virtual address space, and in the container delay machine of access, semaphore and its operation address are sent out
It send to other containers, under the premise of reduction front end data repeatedly copies, realizes between multiple Memcached server nodes
Shared drive, to solve the problems, such as the Single Point of Faliure of Memcached cluster.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is a kind of flow diagram of internal memory sharing method of the embodiment of the present invention;
Fig. 2 is a kind of kubernetes aggregated structure schematic diagram of the embodiment of the present invention;
Fig. 3 is a kind of label selector operation principle schematic diagram of the embodiment of the present invention;
Fig. 4 is a kind of address mapped theory schematic diagram of the embodiment of the present invention;
Fig. 5 is a kind of structural schematic diagram of Container Management platform of the embodiment of the present invention;
Fig. 6 is the structural schematic diagram of another Container Management platform of the embodiment of the present invention;
Fig. 7 is the structural schematic diagram of another Container Management platform of the embodiment of the present invention.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to the present invention
Embodiment be described in detail.It should be noted that in the absence of conflict, in the embodiment and embodiment in the application
Feature can mutual any combination.
As shown in Figure 1, a kind of internal memory sharing method according to an embodiment of the present invention, includes the following steps:
Step 101: one piece of virtual address space of creation on the host where at least two containers, described at least two
Container label having the same makes virtual address space described in the memory sharing of at least two container;
In an example of the present embodiment, the host where at least two container is Kubernetes working node
(Worker Node)。
Kubernetes is that Google corporate team was initiated simultaneously in 2014 based on internal cluster management system Borg open source
The open source container cluster management system of maintenance supports such as Docker container technique, and using it, user easily can build and manage
Manage a privately owned container cloud.As shown in Fig. 2, Kubernetes cluster includes management (Master) component and working node
(Worker Node) component.Master component provides all operations relevant to management, such as scheduling, monitoring, support to resource
Operation etc., it inspects periodically managed node (Node) resource by Node Controller (Node Controller)
Health status completes the life cycle management of Node.The relevant one group of process of cluster management is run on Master node: being answered
With routine interface server (API server), control manager (Controller Manager) and scheduler
(Scheduler), these processes realize the resource management of entire cluster, beanpod (Pod) scheduling, elastic telescopic, security control,
The functions such as system monitoring.
Worker Node component can be virtual machine or physical machine, in creation Kubernetes colonization process,
Worker Node needs to pre-install some necessary softwares to respond the management of Master.On Worker Node,
The minimum running unit of Kubernetes management is Pod, runs kubelet, kube-proxy service processes thereon, these clothes
Business process such as is responsible for the creation of Pod, starting, monitors, restarts at the functions.
Kubernetes has as the indispensable a part of the existing function of cloud platform instantly without additional deployment and dimension
The innate advantage of shield.As shown in Fig. 2, the application is by operating in multiple Docker (a kind of application container engine)
Memcached service shared drive mode realize message synchronization function (rather than as the prior art in Memcached server
Increase message distribution or automatic synchronization software before node), it ensure that due to part of Memcached service fault, generate
The problem of service is unstable or information drop-out.
Before the internal memory sharing method of application the application, it is necessary first to which the Docker mirror image for making Memcached (can be with
Memcached software is first installed in Docker, then constructs mirror image with Dockerfile;Or directly it is packaged into complete mirror
Picture), and mirror site is uploaded to, it is used to create service.Then cluster items necessary resource is created, such as kube-proxy, Pod
Deng, and service (Service) is configured, Service is considered as mono- significant components of Kubernetes, a Service
It is the Outside Access interface of the Pod of one group of offer same services, wherein the configuration of Service includes:
1, the entry address of a Service is defined, i.e. ClusterIP, front end applications can by this entry address
To access the cluster being made of Pod, even if the IP address of rear end Pod, which changes, will not influence to use;For in Service
Port (Port) configures specific port numbers, such as 11211.
2, it is to be passed through by label selector (Label Selector) come what is defined which Pod Service, which acts on,
The Label that all Pod in Label Selector configuration rear end possess is Memcached.As shown in figure 3, kupe-proxy into
Journey selects corresponding Pod by the Label Selector of Service.By label Selector, client can facilitate
One group of resource object of identification and selection.
It 3, is all Pod configuration load distribution policies.
In the present embodiment, the load distribution strategy of at least two container is poll pattern or client-based session
Holding mode.
Kubernetes provides two kinds of load distribution strategies: poll (Round Robin) mode and based on client ip
The session of location keeps (Session Affinity) mode, in which:
Round Robin: it is forwarded requests on the Pod of rear end according to poll framework;
Session Affinity: the request for for the first time initiating some client is forwarded on some Pod of rear end, it
The request that all clients are initiated afterwards will be all forwarded on the identical Pod in rear end.
If not having to both modes of Round Robin or Session Affinity, oneself can also formulate corresponding
Load distribution strategy.
Finally the security strategy of the Pod on node (Security Policy) is configured, Pod security strategy is by setting
It sets and strategy forms, they can control the security feature of Pod access, and configure the container in all Pod for running the services
(Container) identical memory is accessed, increases proxy server for message distribution to each Memcached without front end in this way
Caching can be realized and share message between multiple Memcached server nodes, wherein the configuration method of shared drive is as follows:
1, one piece of virtual address space is created on the host where at least two containers.
In the present embodiment, before the method further include:
A memory type block file is mapped on the host to the process address space;
By the address of the process address space of memory type block file mapping and the virtual address space phase of the creation
Association.
Memory type block file is mapped in the process address space herein, it can be understood as be application shared memory space
One reference, is used to write-back, it is ensured that data are not lost.
For example, as shown in figure 4, by Mmap system function call by memory type block file (such as ramdisk), be mapped into
Journey address space determines address space by parameters such as addr, len, offset, and accesses.
It should be noted that Mmap is the memory mapping function that Unix/Linux is provided, file content can be mapped to
On one section of memory (virtual memory).Mmap itself provides a kind of unusual file read-write mode, and process can be as read-write
Memory equally operates ordinary file.Mmap system function prototype are as follows: mmap (void*addr, size_t len, int
Prot, int flags, int fd, off_t offset), wherein each parameter declaration is as follows:
Addr: the initial address of specified mapping is typically set to NULL, is specified by system;
Length: it is mapped to the file size of memory;
Prot: the protected mode of mapping may is that map section can be performed (PROT_EXEC), map section can be read
(PROT_READ), map section can be written into (PROT_WRITE), map section cannot access (PROT_NONE);
Flags: the characteristic of map section, may is that MAP_SHARED (write-in map section data can replicate back into file, and
Allow the process of other mapping this documents shared), MAP_PRIVATE (map section can be generated to the write operation of map section
Duplication, the modification made to this region will not write back original);
Fd: the filec descriptor returned by open represents the file to be mapped;
Offset: the offset at file beginning, it is necessary to it is the integral multiple of paging size, usually 0, it indicates from file header
Start to map.
2, the kernel parameter for modifying each Memcached Container (increases the realization interface of Mmap, then compiles again
Translate kernel), so that the memory sharing previous step of each Memcached Container is created that the virtual address space come;
Shared drive is the most useful interprocess communication mode, and most fast interprocess communication (Inter-Process
Communication, IPC) form.Purpose using shared drive is exactly that all services use same memory, different Pod
On the data that use of same services be consistent, achieve the purpose that distribute without client and can reach data synchronization.Using
The benefit of this kind of form be exactly it is high-efficient, under specific synchronization mechanism, process can not be needed data and be copied with direct read/write memory
Shellfish.
3, by realizing Mmap system function interface, the memory address called each time is recorded, by using semaphore control
The synchronization and mutual exclusion of data access between container.
In the present embodiment, semaphore includes two states: locking and unlocked, when semaphore is locking, removes and currently visit
Outside the container for asking the shared virtual address space, other containers cannot access the shared virtual address space;Work as letter
Number amount be unlocked state when, receive the accessible shared virtual address space of container of the semaphore.
In an example of the present embodiment, the mapping of the state of the semaphore is realized by calling Munmap function, from
And realize the mutual exclusion of data access between each container.
Memory mapping function Mmap is responsible for file content or other objects being mapped to the virtual memory space of process,
By the reading and modification to this section of memory, to realize the reading and modification to file, without recalling reading (read), writing
(write) operation such as.Munmap executes the operation opposite with Mmap, deletes the object mapping in particular address region
Step 102: the state of the container of virtual address space described in test access;
In the present embodiment, pass through virtual address space described in a kind of Pacemaker (cluster resource manager) test access
Container state or by Pacemaker come the Memcached inside the container of virtual address space described in snoop accesses
Service state.
Pacemaker is a cluster resource manager.The message and member management that it utilizes cluster basic component to provide
Ability detects and restores from the failure of node or resource class, and the maximum to realize cluster service (also known as resource) is available
Property.
Step 103: when the container delay machine of the access, by semaphore and the container of the access in the virtual address
Operation address in space is sent to the container for having same label with the container of the access, and the semaphore holds for controlling
The synchronization and mutual exclusion of data access between device.
In the present embodiment, the Memcached service down inside the container delay machine of the access or the container falls
When, the data such as memory address called using Pacemaker script by semaphore, currently are sent to other Memcached services
The container of normal operation, the container of the data such as reception semaphore and the memory address currently called is according to the data shared interior
Corresponding information is retrieved in depositing, to guarantee the normal operation of service.
In the present embodiment, the method also includes:
The quantity for inspecting periodically the container currently survived, when the quantity for the container currently survived is less than preset value
When, restart the container of delay machine.
In an example of the present embodiment, a copy controller (Replication Controller, RC) is defined
Number of copies be 3 (other numerical value can also be defined as), be submitted to Kubernetes, the Controller on Master component
Manager will be notified, and the Pod quantity of regular visit current system survival guarantees the Pod quantity currently survived and definition
Number of copies be consistent, by make full use of Kubernetes RC strategy, guarantee service high availability, further strengthen
The continuous availability of service.
The embodiment of the invention also provides a kind of computer readable storage medium, the computer-readable recording medium storage
Have one or more program, one or more of programs can be executed by one or more processor, with realize such as with
The step of upper described in any item internal memory sharing methods.
As shown in figure 5, a kind of Container Management platform according to an embodiment of the present invention, including processor 501 and memory
502, in which:
The processor 501 is for executing the memory sharing program stored in memory 502, to realize such as any of the above item
The step of described internal memory sharing method.
As shown in fig. 6, a kind of Container Management platform according to an embodiment of the present invention, including setup module 601 and the first inspection
Survey module 602, in which:
Setup module 601, it is described for creating one piece of virtual address space on the host where at least two containers
At least two containers label having the same makes virtual address space described in the memory sharing of at least two container;
First detection module 602, the state of the container for virtual address space described in test access, when the access
When container delay machine, by the operation address of semaphore and the container of the access in the virtual address space be sent to it is described
The container of access has the container of same label, and the semaphore is used to control the synchronization and mutual exclusion of data access between container.
In an example of the present embodiment, the host where at least two container is Kubernetes Worker
Node。
In the present embodiment, the setup module 601 is also used to:
A memory type block file is mapped on the host to the process address space;
By the address of the process address space of memory type block file mapping and the virtual address space phase of the creation
Association.
For example, as shown in figure 4, by Mmap system function call by memory type block file (such as ramdisk), be mapped into
Journey address space determines address space by parameters such as addr, len, offset, and accesses.
The container for accessing the virtual address space records the memory address called each time, and by using semaphore control
The synchronization and mutual exclusion of data access between container.
In the present embodiment, the load distribution strategy of at least two container is poll pattern or client-based session
Holding mode.
In the present embodiment, the first detection module 602 passes through virtual address space described in Pacemaker test access
The state of container is taken by Pacemaker come the Memcached inside the container of virtual address space described in snoop accesses
Business state uses when the Memcached service down inside the container delay machine of the access or the container falls
The data such as the memory address that Pacemaker script is called by semaphore, currently are sent to other Memcached services and operate normally
Container, the container for receiving the data such as semaphore and the memory address that currently calls retrieves in shared drive according to the data
To corresponding information, to guarantee the normal operation of service.
In the present embodiment, the first detection module 602 be arranged on Kubernetes Worker Node node or
In the container of Kubernetes Worker Node intra-node.
In the present embodiment, as shown in fig. 7, the Container Management platform further includes the second detection module 603, second inspection
Module 603 is surveyed to be used for:
The quantity for inspecting periodically the container currently survived, when the quantity for the container currently survived is less than preset value
When, restart the container of delay machine.
In the present embodiment, second detection module 603 is arranged on Kubernetes Master node.
In an example of the present embodiment, a copy controller (Replication Controller, RC) is defined
Number of copies be 3 (other numerical value can also be defined as), be submitted to Kubernetes, the Controller on Master component
Manager will be notified, and the Pod quantity of regular visit current system survival guarantees the Pod quantity currently survived and definition
Number of copies be consistent, by make full use of Kubernetes RC strategy, guarantee service high availability, further strengthen
The continuous availability of service.
Frame of the application based on Kubernetes is sufficiently carried in conjunction with the advantage of Docker rapid deployment, lightweight
Memcached service, reaches the memory sharing strategy between multiple Pod by Mmap technology, realizes multiple Memcached services
Message is shared between device node, without increasing the additional component distribution such as magent in the front end of Memcached server node
Message synchronization between multiple Memcached server nodes can be realized in message.
Those of ordinary skill in the art will appreciate that all or part of the steps in the above method can be instructed by program
Related hardware is completed, and described program can store in computer readable storage medium, such as read-only memory, disk or CD
Deng.Optionally, one or more integrated circuits also can be used to realize, accordingly in all or part of the steps of above-described embodiment
Ground, each module/unit in above-described embodiment can take the form of hardware realization, can also use the shape of software function module
Formula is realized.The present invention is not limited to the combinations of the hardware and software of any particular form.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of internal memory sharing method characterized by comprising
One piece of virtual address space is created on the host where at least two containers, at least two container has identical
Label, make virtual address space described in the memory sharing of at least two container;
The state of the container of virtual address space described in test access;
When the container delay machine of the access, by the operation of semaphore and the container of the access in the virtual address space
Address is sent to the container for having same label with the container of the access, and the semaphore is visited for controlling data between container
The synchronization and mutual exclusion asked.
2. the method according to claim 1, wherein including: before the method
A memory type block file is mapped on the host to the process address space;
The address of the process address space of memory type block file mapping is associated with the virtual address space of the creation.
3. the method according to claim 1, wherein the method also includes:
The quantity for inspecting periodically the container currently survived, when the quantity for the container currently survived is less than preset value,
Restart the container of delay machine.
4. the method according to claim 1, wherein the load distribution strategy of at least two container is poll
Mode or client-based session keep mode.
5. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage have one or
Multiple programs, one or more of programs can be executed by one or more processor, to realize such as Claims 1-4
Any one of described in internal memory sharing method the step of.
6. a kind of Container Management platform, which is characterized in that including processor and memory, in which:
The processor is for executing the memory sharing program stored in memory, to realize such as any one of claims 1 to 4
The step of described internal memory sharing method.
7. a kind of Container Management platform, which is characterized in that including setup module and first detection module, in which:
Setup module, on the host where at least two containers create one piece of virtual address space, described at least two
A container label having the same, makes virtual address space described in the memory sharing of at least two container;
First detection module, the state of the container for virtual address space described in test access, when the container of the access is delayed
When machine, the operation address of semaphore and the container of the access in the virtual address space is sent to and the access
Container has the container of same label, and the semaphore is used to control the synchronization and mutual exclusion of data access between container.
8. Container Management platform according to claim 7, which is characterized in that the setup module is also used to:
A memory type block file is mapped on the host to the process address space;
The address of the process address space of memory type block file mapping is associated with the virtual address space of the creation.
9. Container Management platform according to claim 7, which is characterized in that further include the second detection module, in which:
Second detection module is used for: the quantity for the container currently survived is inspected periodically, when the appearance currently survived
When the quantity of device is less than preset value, the container of delay machine is restarted.
10. Container Management platform according to claim 7, which is characterized in that the load distribution of at least two container
Strategy is that poll pattern or client-based session keep mode.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811006390.8A CN109213571B (en) | 2018-08-30 | 2018-08-30 | Memory sharing method, container management platform and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811006390.8A CN109213571B (en) | 2018-08-30 | 2018-08-30 | Memory sharing method, container management platform and computer readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109213571A true CN109213571A (en) | 2019-01-15 |
CN109213571B CN109213571B (en) | 2020-12-29 |
Family
ID=64986468
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811006390.8A Active CN109213571B (en) | 2018-08-30 | 2018-08-30 | Memory sharing method, container management platform and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109213571B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109831500A (en) * | 2019-01-30 | 2019-05-31 | 无锡华云数据技术服务有限公司 | The synchronous method of configuration file and Pod in Kubernetes cluster |
CN109933312A (en) * | 2019-03-25 | 2019-06-25 | 南京邮电大学 | A method of containerization relevant database I/O consumption is effectively reduced |
CN110334069A (en) * | 2019-07-10 | 2019-10-15 | 中国民航信息网络股份有限公司 | Data sharing method and relevant apparatus between multi-process |
CN113366802A (en) * | 2019-01-24 | 2021-09-07 | 瑞典爱立信有限公司 | State controller operating in KUBERNETES system and method for operating the same |
CN114546598A (en) * | 2022-02-25 | 2022-05-27 | 北京小佑网络科技有限公司 | Control method for processes, files and network access in container |
CN116204269A (en) * | 2021-11-30 | 2023-06-02 | 慧与发展有限责任合伙企业 | Management cluster with integrated services for deploying and managing services in tenant clusters |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120102135A1 (en) * | 2010-10-22 | 2012-04-26 | Netapp, Inc. | Seamless takeover of a stateful protocol session in a virtual machine environment |
CN102662777A (en) * | 2012-04-28 | 2012-09-12 | 浪潮电子信息产业股份有限公司 | High speed communication method between clients based on kernel-based virtual machine (KVM) |
CN103019889A (en) * | 2012-12-21 | 2013-04-03 | 曙光信息产业(北京)有限公司 | Distributed file system and failure processing method thereof |
CN104899126A (en) * | 2015-06-12 | 2015-09-09 | 北京奇虎科技有限公司 | Method, device and system for performing local real-time monitoring on containers in host |
CN106445637A (en) * | 2016-09-29 | 2017-02-22 | 中国银联股份有限公司 | Container management scheduling system |
CN107158705A (en) * | 2017-05-18 | 2017-09-15 | 腾讯科技(深圳)有限公司 | The update method and device of service |
CN107589972A (en) * | 2017-08-03 | 2018-01-16 | 北京天云融创软件技术有限公司 | A kind of method that Pod in Kubernetes shares IPC NameSpaces |
-
2018
- 2018-08-30 CN CN201811006390.8A patent/CN109213571B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120102135A1 (en) * | 2010-10-22 | 2012-04-26 | Netapp, Inc. | Seamless takeover of a stateful protocol session in a virtual machine environment |
CN102662777A (en) * | 2012-04-28 | 2012-09-12 | 浪潮电子信息产业股份有限公司 | High speed communication method between clients based on kernel-based virtual machine (KVM) |
CN103019889A (en) * | 2012-12-21 | 2013-04-03 | 曙光信息产业(北京)有限公司 | Distributed file system and failure processing method thereof |
CN104899126A (en) * | 2015-06-12 | 2015-09-09 | 北京奇虎科技有限公司 | Method, device and system for performing local real-time monitoring on containers in host |
CN106445637A (en) * | 2016-09-29 | 2017-02-22 | 中国银联股份有限公司 | Container management scheduling system |
CN107158705A (en) * | 2017-05-18 | 2017-09-15 | 腾讯科技(深圳)有限公司 | The update method and device of service |
CN107589972A (en) * | 2017-08-03 | 2018-01-16 | 北京天云融创软件技术有限公司 | A kind of method that Pod in Kubernetes shares IPC NameSpaces |
Non-Patent Citations (1)
Title |
---|
YI REN 等: "Shared-Memory Optimizations for Inter-Virtual-Machine Communication", 《ACM COMPUTING SURVEYS》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113366802A (en) * | 2019-01-24 | 2021-09-07 | 瑞典爱立信有限公司 | State controller operating in KUBERNETES system and method for operating the same |
CN113366802B (en) * | 2019-01-24 | 2024-03-15 | 瑞典爱立信有限公司 | State controller operating in kubrennetes system and method of operating the same |
CN109831500A (en) * | 2019-01-30 | 2019-05-31 | 无锡华云数据技术服务有限公司 | The synchronous method of configuration file and Pod in Kubernetes cluster |
CN109933312A (en) * | 2019-03-25 | 2019-06-25 | 南京邮电大学 | A method of containerization relevant database I/O consumption is effectively reduced |
CN109933312B (en) * | 2019-03-25 | 2021-06-01 | 南京邮电大学 | Method for effectively reducing I/O consumption of containerized relational database |
CN110334069A (en) * | 2019-07-10 | 2019-10-15 | 中国民航信息网络股份有限公司 | Data sharing method and relevant apparatus between multi-process |
CN110334069B (en) * | 2019-07-10 | 2022-02-01 | 中国民航信息网络股份有限公司 | Data sharing method among multiple processes and related device |
CN116204269A (en) * | 2021-11-30 | 2023-06-02 | 慧与发展有限责任合伙企业 | Management cluster with integrated services for deploying and managing services in tenant clusters |
CN114546598A (en) * | 2022-02-25 | 2022-05-27 | 北京小佑网络科技有限公司 | Control method for processes, files and network access in container |
CN114546598B (en) * | 2022-02-25 | 2022-10-21 | 北京小佑网络科技有限公司 | Control method for processes, files and network access in container |
Also Published As
Publication number | Publication date |
---|---|
CN109213571B (en) | 2020-12-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109213571A (en) | A kind of internal memory sharing method, Container Management platform and computer readable storage medium | |
US11809753B2 (en) | Virtual disk blueprints for a virtualized storage area network utilizing physical storage devices located in host computers | |
US20190342229A1 (en) | Multi-cluster resource management | |
CN106027647B (en) | The cluster distributed document storage system of LXPFS | |
CN107566533B (en) | Internal and external network file sharing system based on NAS (network attached storage) | |
CN110377395B (en) | Pod migration method in Kubernetes cluster | |
EP3647966B1 (en) | Scalable distributed storage architecture | |
US8108623B2 (en) | Poll based cache event notifications in a distributed cache | |
JP6607783B2 (en) | Distributed cache cluster management | |
JP2023532947A (en) | Data transfer method, proxy server, storage medium and electronic device | |
US20110131318A1 (en) | High availability enabler | |
Junior et al. | Stateful container migration in geo-distributed environments | |
US11223519B2 (en) | Storage system for network information | |
CN111147274B (en) | System and method for creating a highly available arbitration set for a cluster solution | |
CN111966482B (en) | Edge computing system | |
JP7361989B2 (en) | COS service discovery across multiple COS clusters based on Container Orchestration (COS) Cluster Domain Name System | |
CN111459619A (en) | Method and device for realizing service based on cloud platform | |
CN105468643B (en) | The access method and system of distributed file system | |
US11397711B1 (en) | Proxy-based database scaling | |
US20210067599A1 (en) | Cloud resource marketplace | |
CN114172917B (en) | Distributed cache system and deployment method thereof | |
CN115510018A (en) | Database cluster capacity expansion method and system | |
Bekas et al. | Cross-layer management of a containerized NoSQL data store | |
CN116760913B (en) | Method and system for issuing k8s cluster protocol conversion platform configuration | |
US20240086368A1 (en) | System and method for object store federation |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |