CN109213446A - Switching method, device, equipment and the readable storage medium storing program for executing of write buffer mode - Google Patents
Switching method, device, equipment and the readable storage medium storing program for executing of write buffer mode Download PDFInfo
- Publication number
- CN109213446A CN109213446A CN201810966987.0A CN201810966987A CN109213446A CN 109213446 A CN109213446 A CN 109213446A CN 201810966987 A CN201810966987 A CN 201810966987A CN 109213446 A CN109213446 A CN 109213446A
- Authority
- CN
- China
- Prior art keywords
- cluster
- node
- state
- write buffer
- mode
- 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
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0614—Improving the reliability of storage systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0655—Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices
- G06F3/0656—Data buffering arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/067—Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Memory System Of A Hierarchy Structure (AREA)
- Techniques For Improving Reliability Of Storages (AREA)
Abstract
The invention discloses a kind of switching methods of write buffer mode in HA cluster, comprising: the state of each node in monitoring HA cluster；Judge whether the quantity for the node being online in HA cluster is greater than predetermined quantity；If so, being WB mode by the write buffer mode setting of HA cluster；If it is not, being then WT mode by the write buffer mode setting of HA cluster.As it can be seen that in the present solution, writing data into caching using WB mode, writing speed is very fast if the quantity of line node is more than the predetermined quantity in HA cluster；If online quantity is no more than the predetermined quantity, caching and rule are write data into using WT mode, although writing speed is slower, high reliablity；By the switching to two write buffer modes, so that improving system data reliability while safeguards system performance；The invention also discloses switching device, equipment and the readable storage medium storing program for executing of a kind of write buffer mode, are equally able to achieve above-mentioned technical effect.
Description
Technical field
The present invention relates to storage server system technical fields, more specifically to write buffer mould in a kind of HA cluster
Switching method, device, equipment and the computer readable storage medium of formula.
Background technique
Currently, data storage needs more harsh reliability and more efficient I O process in cloud computing era
Can, caching is wherein play important role.For the efficient access for ensureing data, the processing of host IO and backend resources are balanced
Ability, storage system will use a large amount of memories to buffer IO；A variety of write buffer modes are developed also for storage system feature, such as
WB (WriteBack) mode/WT (WriteThrough) mode.Heritage storage system is to ensure that performance will use WB mode, should
Mode feature is that caching is first written in data, and writing speed is fast, when caching lower brush just can rule, the disadvantage is that the data power down in caching
It loses, especially to single node storage system；WT mode then needs write buffer and disk, and writing speed is slower, but reliable
Property it is high.Therefore in HA cluster (High Available Cluster, high-availability cluster), two or more node is generally comprised,
Reasonable employment cache mode can improve system performance when system is normal, ensure data reliability in system exception.
Therefore, how according to both write buffer modes, guarantee the high availability of cluster, be those skilled in the art's needs
It solves the problems, such as.
Summary of the invention
The purpose of the present invention is to provide switching method, device, equipment and the calculating of write buffer mode in a kind of HA cluster
Machine readable storage medium storing program for executing, to improve system data reliability while safeguards system performance.
To achieve the above object, the embodiment of the invention provides following technical solutions:
The switching method of write buffer mode in a kind of HA cluster, comprising:
Monitor the state of each node in HA cluster；The state includes: presence and off-line state；
Judge whether the quantity for the node being online in the HA cluster is greater than predetermined quantity；
If so, being WriteBack mode by the write buffer mode setting of the HA cluster；
If it is not, being then WriteThrough mode by the write buffer mode setting of the HA cluster.
Wherein, judge whether the quantity for the node being online in the HA cluster is greater than predetermined quantity, comprising:
Judge whether the quantity for the node being online in the HA cluster is greater than one.
Wherein, the state for monitoring each node in HA cluster, comprising:
Real-time detection whether there is the node that cluster is added or the node for leaving cluster；
The node of cluster is added if it exists, then the state that the node of addition cluster is arranged is presence；It leaves if it exists
The node of cluster, then it is off-line state that the state of the node of cluster is left in setting.
Wherein, in the monitoring HA cluster after the state of each node, further includes:
Judge in the quantity of node and the quantity of the node in off-line state that are online, if exist at least
One quantity is updated；
If it exists, then execute the quantity for judging the node being online in the HA cluster whether be greater than it is predetermined
The step of quantity.
Wherein, the write buffer mode setting by the HA cluster is after WriteThrough mode, further includes:
The state for generating only one node is the early warning information of presence.
The switching device of write buffer mode in a kind of HA cluster, comprising:
Node state detection module, for monitoring the state of each node in HA cluster；The state includes: presence
And off-line state；
Quantity judgment module, for judging it is predetermined whether the quantity for the node being online in the HA cluster is greater than
Quantity；
The quantity of first setup module, the node for being online in the HA cluster is greater than predetermined quantity
When, it is WriteBack mode by the write buffer mode setting of the HA cluster；
The quantity of second setup module, the node for being online in the HA cluster is not more than predetermined quantity
When, it is WriteThrough mode by the write buffer mode setting of the HA cluster.
Wherein, the node state detection module, comprising:
Detection unit whether there is the node that cluster is added or the node for leaving cluster for real-time detection；
First state setting unit, for there is the node that cluster is added, then the state that the node of addition cluster is arranged is
Presence；
Second state set unit, for there is the node for leaving cluster, then the state for the node that cluster is left in setting is
Off-line state.
Wherein, this programme further include:
Cue module, for being generation after WriteThrough mode by the write buffer mode setting of the HA cluster
The state of only one node is the early warning information of presence.
The switching equipment of write buffer mode in a kind of HA cluster, comprising:
Memory, for storing computer program；
Processor realizes the switching method of write buffer mode in above-mentioned HA cluster when for executing the computer program
Step.
A kind of computer readable storage medium is stored with computer program on the computer readable storage medium, described
The step of switching method of write buffer mode in above-mentioned HA cluster is realized when computer program is executed by processor.
By above scheme it is found that in a kind of HA cluster provided in an embodiment of the present invention write buffer mode switching method,
It include: the state for monitoring each node in HA cluster；The state includes: presence and off-line state；Judge the HA collection
Whether the quantity for the node being online in group is greater than predetermined quantity；If so, by the write buffer mode of the HA cluster
It is set as WriteBack mode；If it is not, being then WriteThrough mode by the write buffer mode setting of the HA cluster.
As it can be seen that this programme in the write buffer mode for determining HA cluster, presets a predetermined quantity, if HA cluster
The quantity of middle line node is more than the predetermined quantity, then uses WriteBack mode, write data into caching, writing speed compared with
Fastly；WriteThrough mode is used if online quantity is no more than the predetermined quantity, writes data into caching and rule, though
Right writing speed is slower, but high reliablity；By the switching to two write buffer modes, so that in the same of safeguards system performance
When, improve system data reliability；
The invention also discloses switching device, equipment and the computer-readable storage mediums of write buffer mode in a kind of HA cluster
Matter is equally able to achieve above-mentioned technical effect.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the switching method flow diagram of write buffer mode in a kind of HA cluster disclosed by the embodiments of the present invention；
Fig. 2 is the switching method flow diagram of write buffer mode in another kind HA cluster disclosed by the embodiments of the present invention；
Fig. 3 is the switching device structural schematic diagram of write buffer mode in a kind of HA cluster disclosed by the embodiments of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
The embodiment of the invention discloses switching method, device, equipment and the computers of write buffer mode in a kind of HA cluster
Readable storage medium storing program for executing, to improve system data reliability while safeguards system performance.
Referring to Fig. 1, the switching method of write buffer mode in a kind of HA cluster provided in an embodiment of the present invention, comprising:
The state of each node in S101, monitoring HA cluster；The state includes: presence and off-line state；
Wherein, the state for monitoring each node in HA cluster, comprising:
Real-time detection whether there is the node that cluster is added or the node for leaving cluster；
The node of cluster is added if it exists, then the state that the node of addition cluster is arranged is presence；It leaves if it exists
The node of cluster, then it is off-line state that the state of the node of cluster is left in setting.
Specifically, switching method in the present embodiment is applied to storage server system, which is HA cluster (High
Available Cluster, high-availability cluster), there are two and more than two node in the cluster.This programme by controlling more
The high-availability cluster characteristic of storage system MCS maintenance, to realize trouble shooting and failure transfer (including write buffer pattern switching)
Automation, specifically include that failure Auto-Sensing (Auto-Detect), automatic switchover/failure transfer (FailOver) and automatically
Restore (FailBack).
In S101, failure Auto-Sensing is mainly realized, more controlled storage system MCS can pass through in HA cluster management
Cluster state online_nodes identifies the state of line node, and system can change section when node joins and departs cluster
Dotted state, to trigger corresponding logical process, which includes the pattern switching of logical volume write buffer, it may be assumed that storage system
WT mode, safeguards system data reliability are used in system when only one node；Two and the above node survive when use WB mode
It is handled, ensures efficient data processing ability.
S102, judge whether the quantity for the node being online in the HA cluster is greater than predetermined quantity；If so,
Execute S103；If it is not, then executing S104；
Wherein, judge whether the quantity for the node being online in the HA cluster is greater than predetermined quantity, comprising: sentence
Whether the quantity of the node being online in the HA cluster of breaking is greater than one.
Predetermined quantity in this programme can be preset, and in the present embodiment, which is preferably 1,
That is judging whether the quantity for the node being online is greater than 1, if it is greater than one, then S103 is executed；In threadiness
When the quantity of the node of state is 1, then S104 is executed.
S103, by the write buffer mode setting of the HA cluster be WriteBack mode；
S104, by the write buffer mode setting of the HA cluster be WriteThrough mode.
In the present solution, S102-S104 mainly realizes failure transfer and automatic restores, that is to say, that being saved in cluster
The online_nodes of point is judged, when there is node to leave in cluster, and when only one node of online node, illustrates this
A node needs to automatically switch (FailOver), the tupe of logical volume write buffer can be changed to WT by WB.When node restores
After cluster is added, line node quantity is greater than one at this time, will do it automatic restore (FailBack) at this time and handles, by write buffer
Mode is from WT switchback WB.
It is specifically, main when storage system program is realized including the following steps:
(1) when more controlled storage system clusters create or after node addition, need to change cluster online_nodes, it should
Value is the vector value of 32-bit, can highest support the state of 32 nodes to indicate；
(2), can be according to node state when creating logical volume in storage system, to select write buffer mode, more control systems are
WB, single control system WT, the attribute as volume are saved；
(3) when failover occurs for node, WT mode is automatically switched to；
(4) after failback occurs for node, logical volume write buffer pattern switching is returned into WB automatically.
As can be seen that the write buffer mode for this guarantee cluster high availability that this programme proposes carries out self-adaptive processing side
Method, by the HA cluster management of more controlled storage system MCS, triggered according to the variation of clustered node presence logical volume write it is slow
The pattern switching deposited ensures that storage system is able to use WB mode when normal and plays maximum I O process performance, in abnormal cluster
In preferentially select WT mode, make the timely rule of data, ensure storing data safety, system is reliable, makes system under different scenes
Selection switching is carried out to write buffer mode, changes the event of storage system reply different scenes and the processing capacity of data in due course.
Referring to fig. 2, in another kind HA cluster provided in an embodiment of the present invention write buffer mode switching method, comprising:
The state of each node in S201, monitoring HA cluster；The state includes: presence and off-line state；
In the quantity of node and the quantity of the node in off-line state that S202, judgement are online, if deposit
It is updated at least one quantity；
If it exists, then S203 is executed；If it does not exist, then S201 is executed；
S203, judge whether the quantity for the node being online in the HA cluster is greater than predetermined quantity；If so,
Execute S204；If it is not, then executing S205；
S204, by the write buffer mode setting of the HA cluster be WriteBack mode；
S205, by the write buffer mode setting of the HA cluster be WriteThrough mode.
Specifically, in the present solution, judging whether the number of nodes being online in HA cluster is greater than predetermined quantity
When, it can be by way of real-time detection, it can also the mode through this embodiment, it may be assumed that the node being online
Quantity and the node in off-line state quantity in there are at least one quantity to be updated, at this moment can trigger S203 come to
Line number of nodes is judged that this mode can find the change of node state compared with the mode of real-time detection in time, also
System process performance can be saved.
Further, this programme is by the write buffer mode setting of HA cluster for after WriteThrough mode, further includes: raw
State at only one node is the early warning information of presence.Due to only one section of node online in cluster
At this moment point influences the read-write of data in order to avoid node failure, produces an early warning information, at this moment to mention
Show that line node is only one in administrative staff's cluster, to execute the operation such as malfunction elimination in time.
As can be seen that the present invention controls storage management software by using MCS to provide HA cluster management, to cache module more
Write buffer pattern switching event be provided support that write buffer mode switches over according to the state of cluster, can effectively play more
The caching performance of control system can also ensure the data safety of storage system when the system failure is unstable.The present invention with before
Single write buffer mode is compared, and adaptive mechanism can more improve product reliability and processing capacity, promotes product competitiveness；When
So, storage system is other than supporting automatic switching method described in this programme, and also support user is settable manually, thus to use
Family provides good user experience.
Switching device provided in an embodiment of the present invention is introduced below, switching device and above description described below
Switching method can be cross-referenced.
Referring to Fig. 3, the switching device of write buffer mode in a kind of HA cluster provided in an embodiment of the present invention, comprising:
Node state detection module 100, for monitoring the state of each node in HA cluster；The state includes: online
State and off-line state；
Quantity judgment module 200, for judging whether the quantity for the node being online in the HA cluster is greater than
Predetermined quantity；
The quantity of first setup module 300, the node for being online in the HA cluster is greater than predetermined number
It is WriteBack mode by the write buffer mode setting of the HA cluster when amount；
Second setup module 400, the quantity of the node for being online in the HA cluster is no more than predetermined
It is WriteThrough mode by the write buffer mode setting of the HA cluster when quantity.
Wherein, the node state detection module, comprising:
Detection unit whether there is the node that cluster is added or the node for leaving cluster for real-time detection；
First state setting unit, for there is the node that cluster is added, then the state that the node of addition cluster is arranged is
Presence；
Second state set unit, for there is the node for leaving cluster, then the state for the node that cluster is left in setting is
Off-line state.
Wherein, this programme further include:
Cue module, for being generation after WriteThrough mode by the write buffer mode setting of the HA cluster
The state of only one node is the early warning information of presence.
Wherein, the quantity judgment module, specifically for the number for the node for judging to be online in the HA cluster
Whether amount is greater than one.
Wherein, this programme further include:
Update condition judgment module, the quantity of the node for judging to be online and the node in off-line state
Quantity in, if there are at least one quantity to be updated；
The quantity judgment module determines the quantity for the node being online for the update condition judgment module
In the quantity of the node in off-line state, after being updated there are at least one quantity, judge to be in the HA cluster
Whether the quantity of the node of linear state is greater than predetermined quantity.
The embodiment of the present invention also provides a kind of switching equipment of write buffer mode in HA cluster, comprising:
Memory, for storing computer program；
Processor is realized when for executing the computer program in above-mentioned any means HA cluster as described in the examples
The step of switching method of write buffer mode.
The embodiment of the present invention also provides a kind of computer readable storage medium, stores on the computer readable storage medium
There is computer program, the computer program realizes above-mentioned any means HA cluster as described in the examples when being executed by processor
The step of switching method of middle write buffer mode.
Wherein, the storage medium may include: USB flash disk, mobile hard disk, read-only memory (Read-Only Memory,
ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. are various can store program
The medium of code.
To sum up, this programme is directed to the characteristics of write buffer mode, by using the line node of storage system HA cluster
State, to judge which kind of write buffer mode carrying out caching I O process using.While safeguards system performance, storage system is improved
Data reliability.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with other
The difference of embodiment, the same or similar parts in each embodiment may refer to each other.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest scope of cause.
Claims (10)
1. the switching method of write buffer mode in a kind of HA cluster characterized by comprising
Monitor the state of each node in HA cluster；The state includes: presence and off-line state；
Judge whether the quantity for the node being online in the HA cluster is greater than predetermined quantity；
If so, being WriteBack mode by the write buffer mode setting of the HA cluster；
If it is not, being then WriteThrough mode by the write buffer mode setting of the HA cluster.
2. switching method according to claim 1, which is characterized in that judge the section being online in the HA cluster
Whether the quantity of point is greater than predetermined quantity, comprising:
Judge whether the quantity for the node being online in the HA cluster is greater than one.
3. switching method according to claim 1, which is characterized in that the state of each node in the monitoring HA cluster,
Include:
Real-time detection whether there is the node that cluster is added or the node for leaving cluster；
The node of cluster is added if it exists, then the state that the node of addition cluster is arranged is presence；Cluster is left if it exists
Node, then setting leave cluster node state be off-line state.
4. switching method according to claim 3, which is characterized in that it is described monitoring HA cluster in each node state it
Afterwards, further includes:
Judge in the quantity of node and the quantity of the node in off-line state that are online, if there are at least one
Quantity is updated；
If it exists, then execute whether the quantity for judging the node being online in the HA cluster is greater than predetermined quantity
The step of.
5. switching method as claimed in any of claims 1 to 4, which is characterized in that described by the HA cluster
Write buffer mode setting is after WriteThrough mode, further includes:
The state for generating only one node is the early warning information of presence.
6. the switching device of write buffer mode in a kind of HA cluster characterized by comprising
Node state detection module, for monitoring the state of each node in HA cluster；The state include: presence and from
Linear state；
Quantity judgment module, for judging whether the quantity for the node being online in the HA cluster is greater than predetermined number
Amount；
First setup module will when the quantity of the node for being online in the HA cluster is greater than predetermined quantity
The write buffer mode setting of the HA cluster is WriteBack mode；
Second setup module, when the quantity of the node for being online in the HA cluster is not more than predetermined quantity,
It is WriteThrough mode by the write buffer mode setting of the HA cluster.
7. switching device according to claim 6, which is characterized in that the node state detection module, comprising:
Detection unit whether there is the node that cluster is added or the node for leaving cluster for real-time detection；
First state setting unit, for there is the node that cluster is added, then it is online that the state of the node of addition cluster, which is arranged,
State；
Second state set unit, for there is the node for leaving cluster, then the state for the node that cluster is left in setting is offline
State.
8. switching device according to claim 6 or 7, which is characterized in that further include:
Cue module, for by the write buffer mode setting of the HA cluster be WriteThrough mode after, generation only has
The state of one node is the early warning information of presence.
9. the switching equipment of write buffer mode in a kind of HA cluster characterized by comprising
Memory, for storing computer program；
Processor is realized when for executing the computer program such as write buffer mould in claim 1 to the 5 one HA cluster
The step of switching method of formula.
10. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium
Program is realized when the computer program is executed by processor such as write buffer mode in claim 1 to the 5 one HA cluster
Switching method the step of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810966987.0A CN109213446B (en) | 2018-08-23 | 2018-08-23 | Write cache mode switching method, device and equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810966987.0A CN109213446B (en) | 2018-08-23 | 2018-08-23 | Write cache mode switching method, device and equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109213446A true CN109213446A (en) | 2019-01-15 |
| CN109213446B CN109213446B (en) | 2022-03-22 |
Family
ID=64989612
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810966987.0A Active CN109213446B (en) | 2018-08-23 | 2018-08-23 | Write cache mode switching method, device and equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109213446B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6662219B1 (en) * | 1999-12-15 | 2003-12-09 | Microsoft Corporation | System for determining at subgroup of nodes relative weight to represent cluster by obtaining exclusive possession of quorum resource |
| CN1558321A (en) * | 2003-07-02 | 2004-12-29 | 普安科技股份有限公司 | Storage virtualization computer system and external controller therefor |
| CN102200949A (en) * | 2011-05-16 | 2011-09-28 | 浪潮(北京)电子信息产业有限公司 | Device and method for realizing controller fault protection of multi-controller memory system |
| CN103605618A (en) * | 2013-11-20 | 2014-02-26 | 浪潮电子信息产业股份有限公司 | Non-write-back mirror image and direct write switching method for cache mirror image system |
| US20150286438A1 (en) * | 2014-04-03 | 2015-10-08 | Lsi Corporation | System, Method and Computer-Readable Medium for Dynamically Configuring an Operational Mode in a Storage Controller |
| CN105068768A (en) * | 2015-08-26 | 2015-11-18 | 华为技术有限公司 | Write policy control method and apparatus |
| US20170115894A1 (en) * | 2015-10-26 | 2017-04-27 | Netapp, Inc. | Dynamic Caching Mode Based on Utilization of Mirroring Channels |
| CN107436727A (en) * | 2016-05-26 | 2017-12-05 | 中兴通讯股份有限公司 | The memory space management and device of simplification volume |
| CN107766181A (en) * | 2017-09-12 | 2018-03-06 | 中国电子科技集团公司第五十二研究所 | A kind of dual controller storage High Availabitity subsystem based on PCIe non-transparent bridges |
| CN108334401A (en) * | 2018-01-31 | 2018-07-27 | 武汉噢易云计算股份有限公司 | Realize that logical volume dynamically distributes and supports the system and method for dynamic migration of virtual machine |
-
2018
- 2018-08-23 CN CN201810966987.0A patent/CN109213446B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6662219B1 (en) * | 1999-12-15 | 2003-12-09 | Microsoft Corporation | System for determining at subgroup of nodes relative weight to represent cluster by obtaining exclusive possession of quorum resource |
| CN1558321A (en) * | 2003-07-02 | 2004-12-29 | 普安科技股份有限公司 | Storage virtualization computer system and external controller therefor |
| CN102200949A (en) * | 2011-05-16 | 2011-09-28 | 浪潮(北京)电子信息产业有限公司 | Device and method for realizing controller fault protection of multi-controller memory system |
| CN103605618A (en) * | 2013-11-20 | 2014-02-26 | 浪潮电子信息产业股份有限公司 | Non-write-back mirror image and direct write switching method for cache mirror image system |
| US20150286438A1 (en) * | 2014-04-03 | 2015-10-08 | Lsi Corporation | System, Method and Computer-Readable Medium for Dynamically Configuring an Operational Mode in a Storage Controller |
| CN105068768A (en) * | 2015-08-26 | 2015-11-18 | 华为技术有限公司 | Write policy control method and apparatus |
| US20170115894A1 (en) * | 2015-10-26 | 2017-04-27 | Netapp, Inc. | Dynamic Caching Mode Based on Utilization of Mirroring Channels |
| CN107436727A (en) * | 2016-05-26 | 2017-12-05 | 中兴通讯股份有限公司 | The memory space management and device of simplification volume |
| CN107766181A (en) * | 2017-09-12 | 2018-03-06 | 中国电子科技集团公司第五十二研究所 | A kind of dual controller storage High Availabitity subsystem based on PCIe non-transparent bridges |
| CN108334401A (en) * | 2018-01-31 | 2018-07-27 | 武汉噢易云计算股份有限公司 | Realize that logical volume dynamically distributes and supports the system and method for dynamic migration of virtual machine |
Non-Patent Citations (2)
| Title |
|---|
| HAO LIU: "RWT: Suppressing Write-Through Cost When Coherence is Not Needed", 《IEEE》 * |
| 林伟等: "众核处理器中使用写掩码实现混合写回/写穿透策略", 《计算机学报》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109213446B (en) | 2022-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107526546B (en) | Spark distributed computing data processing method and system | |
| CN202798798U (en) | High availability system based on cloud computing technology | |
| EP3620905B1 (en) | Method and device for identifying osd sub-health, and data storage system | |
| US8069191B2 (en) | Method, an apparatus and a system for managing a snapshot storage pool | |
| CN110008149B (en) | Fusion memory device and method of operating the same | |
| US8321622B2 (en) | Storage system with multiple controllers and multiple processing paths | |
| US20140006687A1 (en) | Data Cache Apparatus, Data Storage System and Method | |
| CN103907097A (en) | Intelligence for controlling virtual storage appliance storage allocation | |
| US11544093B2 (en) | Virtual machine replication and migration | |
| US9390010B2 (en) | Cache management | |
| US11809252B2 (en) | Priority-based battery allocation for resources during power outage | |
| CN105095094A (en) | Memory management method and equipment | |
| CN103765373A (en) | Data storage method, data storage device, and storage equipment | |
| CN102207830A (en) | Cache dynamic allocation management method and device | |
| CN110780811B (en) | Data protection method, device and storage medium | |
| CN104298574A (en) | Data high-speed storage processing system | |
| CN106874103B (en) | Heartbeat implementation method and device | |
| CN105095495A (en) | Distributed file system cache management method and system | |
| CN109189739B (en) | Cache space recovery method and device | |
| US9298397B2 (en) | Nonvolatile storage thresholding for ultra-SSD, SSD, and HDD drive intermix | |
| CN111857540A (en) | Data access method, device and computer program product | |
| CN104460938B (en) | System-wide power conservation method and system using memory cache | |
| CN105103139B (en) | Method and apparatus for improving the performance across the semaphore supervisory sequence of coherent bus | |
| CN112214161B (en) | Memory system and method of operating the same | |
| CN105446913A (en) | Data access method and apparatus |
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 |