CN107645421A - A kind of ISCSI protocol implementing methods of distributed storage - Google Patents
A kind of ISCSI protocol implementing methods of distributed storage Download PDFInfo
- Publication number
- CN107645421A CN107645421A CN201711098193.9A CN201711098193A CN107645421A CN 107645421 A CN107645421 A CN 107645421A CN 201711098193 A CN201711098193 A CN 201711098193A CN 107645421 A CN107645421 A CN 107645421A
- Authority
- CN
- China
- Prior art keywords
- iscsi
- node
- service
- memory
- memory node
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The invention discloses a kind of ISCSI protocol implementing methods of distributed storage, comprise the following steps：ISCSI service clusters carry out fault detect by heartbeat acknowledgement mechanism, and complete malfunctioning node ruling and configuration by master memory nodes；ISCSI service clusters carry out ISCSI Service Source migration operations after memory node dynamic change.The unified management ISCSI services of ISCSI service clusters, automatic monitoring node state, realize that service fault migrates, and ensure the continuity of upper-layer service I/O operation.Found by malfunctioning node and resource migration both sides designs the availability and reliability for ensureing service.The functions such as service fault migration are realized using raft consistency algorithms, develop domain name access function, it is thus identified that validity and availability of the ISCSI clusters to distributed storage.
Description
Technical field
The present invention relates to technical field of distributed memory, the ISCSI protocol implementing methods of especially a kind of distributed storage.
Background technology
In distributed memory system, ISCSI (the ISCSI Internet Small Computer of master-slave back-up mode
System Interface Internet small computer system interfaces) service arrangement can not make full use of distributed storage
The advantage brought.First, the joint behavior of distributed memory system management is different, and it is substantial amounts of that a certain node is not enough to support
ISCSI is serviced, and easily causes the frequent failure of ISCSI service nodes；Secondly, it is impossible to node resource is made full use of, so as to realize
Weighing apparatus load.However, being directed to distributed storage array, industry still provides the ISCSI services that master-slave back-up mode is realized.
The content of the invention
It is an object of the invention to provide a kind of ISCSI protocol implementing methods of distributed storage, set using distributed thought
Count and realize ISCSI service clusters, ISCSI services are evenly distributed on each memory node, be managed collectively ISCSI service,
Automatic monitoring node state, service fault migration.
To achieve the above object, the present invention uses following technical proposals：
A kind of ISCSI protocol implementing methods of distributed storage, comprise the following steps：
ISCSI service clusters carry out fault detect by heartbeat acknowledgement mechanism, and complete failure by master memory nodes
Node decides and configuration；
ISCSI service clusters carry out ISCSI Service Source migration operations after memory node dynamic change.
Further, in addition to, ISCSI service clusters carry out ISCSI service arrangements according to node selection strategy, realize
ISCSI services the equiblibrium mass distribution on each memory node.
Further, the ISCSI service clusters carry out ISCSI service arrangements according to node selection strategy, including：
The poll since lowest number memory node, if the memory node is malfunctioning node, select next effective
Node；Effective node of ISCSI connection minimum numbers is selected, if the ISCSI quantitys of service of each memory node are identical, is selected
Select the minimum memory node of numbering and carry out ISCSI service arrangements.
Further, it is described that malfunctioning node ruling and configuration are completed by master memory nodes, including：
In setting time, some memory node is reported as exception by memory nodes more than half, then master storages section
Point thinks the memory node for malfunctioning node and kicks out of ISCSI storage clusters, while updates ISCSI storage clusters node state letter
Data result after renewal is sent and is synchronized on each memory node by breath, master memory nodes.
Further, the ISCSI service clusters carry out ISCSI Service Source migrations after memory node dynamic change
Operation, including：ISCSI service clusters carry out ISCSI Service Source migration operations after judging memory node for malfunctioning node；
When memory node adds ISCSI service clusters again, ISCSI Service Source migrations are carried out.
Further, the ISCSI Service Sources migration operation, including：
The ISCSI service profiles of memory node to be migrated are obtained, are mapped to Ceph block devices according to configuration file
Healthy node；Memory node cluster after renewal redeploys ISCSI services；Carry out IP address migration.
The effect provided in the content of the invention is only the effect of embodiment, rather than whole effects that invention is all, above-mentioned
A technical scheme in technical scheme has the following advantages that or beneficial effect：
The present invention makes full use of the node resource of distributed storage, there is provided ISCSI services sets under distributed storage environment
Group, ISCSI clusters carry out ISCSI service arrangements in service arrangement and migration according to node selection strategy (poll/connection number),
So as to which ISCSI is serviced into equiblibrium mass distribution to memory node, indivedual memory node load too high are avoided.ISCSI service clusters are united
One management ISCSI services, automatic monitoring node state, realize that service fault migrates, and ensure the continuous of upper-layer service I/O operation
Property.Found by malfunctioning node and resource migration both sides designs the availability and reliability for ensureing service.Using raft mono-
Cause property algorithm realizes the functions such as service fault migration, develops domain name access function, it is thus identified that ISCSI clusters are to distributed storage
Validity and availability.
Brief description of the drawings
Fig. 1 is ISCSI distributed type assemblies configuration diagrams；
Fig. 2 is the ISCSI protocol implementing method flow charts of distributed storage of the present invention.
Embodiment
For the technical characterstic for illustrating this programme can be understood, below by embodiment, and its accompanying drawing is combined, to this hair
It is bright to be described in detail.Following disclosure provides many different embodiments or example is used for realizing the different knots of the present invention
Structure.In order to simplify disclosure of the invention, hereinafter the part and setting of specific examples are described.In addition, the present invention can be with
Repeat reference numerals and/or letter in different examples.This repetition is that for purposes of simplicity and clarity, itself is not indicated
Relation between various embodiments are discussed and/or set.It should be noted that part illustrated in the accompanying drawings is not necessarily to scale
Draw.Present invention omits the description to known assemblies and treatment technology and process to avoid being unnecessarily limiting the present invention.
As shown in figure 1, ISCSI service clusters are designed and Implemented using distributed thought.The ISCSI clusters that the present invention designs
Node resource is made full use of, ISCSI services are evenly distributed in each memory node, ISCSI service clusters are exactly to realize
The set of memory node existing for one group of actual hardware of ISCSI agreements；ISCSI service clusters and storage cluster are all based on together
Two kinds of services that the storage hardware equipment of sample provides, because the only distributed memory space of storage cluster offer is, it is necessary to make
Storage service is externally provided with ISCSI agreements.
As shown in Fig. 2 a kind of ISCSI protocol implementing methods of distributed storage, comprise the following steps：
S1, ISCSI service cluster carry out ISCSI service arrangements according to node selection strategy, realize ISCSI services each
Equiblibrium mass distribution on memory node；
S2, ISCSI service cluster carry out fault detect by heartbeat acknowledgement mechanism, and complete event by master memory nodes
Hinder node ruling and configuration；
S3, ISCSI service cluster carry out ISCSI Service Source migration operations after memory node dynamic change.
In step S1, ISCSI service clusters carry out ISCSI service arrangements according to node selection strategy, including：
The poll since lowest number memory node, if i is the node of last time ISCSI service arrangement, select i=(i+
1) mod n are as service arrangement node, if the memory node is malfunctioning node, select next effective node；Select
Effective node of ISCSI connection minimum numbers, if the ISCSI quantitys of service of each memory node are identical, selection numbering is most
Small memory node carries out ISCSI service arrangements.
In step S2, malfunctioning node ruling and configuration are completed by master memory nodes, including：
In setting time (such as 60 seconds), some memory node is by half (N/2+1 node) node report stored above
Accuse as exception, then master memory nodes think the memory node for malfunctioning node and kick out of ISCSI storage clusters, update simultaneously
Data result after renewal is sent and is synchronized to each storage by ISCSI storage cluster node status informations, master memory nodes
On node.Due to the authority of master nodes, the change of ISCSI cluster configuration datas of the invention can only all pass through master
Node makes requests on.Meanwhile the data result of change is sent by master nodes and is synchronized on each node.Master only has
After ensuring that data are synchronized and being written to (N/2+1) individual node disk, i.e., after can ensureing data consistency, it can just return to behaviour
Succeed.
In step S3, ISCSI service clusters carry out ISCSI Service Source migration operations after memory node dynamic change,
Including：ISCSI service clusters carry out ISCSI Service Source migration operations after judging memory node for malfunctioning node；Storage section
When point adds ISCSI service clusters again, ISCSI Service Source migrations are carried out.
In step S3, ISCSI Service Source migration operations, including：
The ISCSI service profiles of memory node to be migrated are obtained, are mapped to Ceph block devices according to configuration file
Healthy node；Memory node cluster after renewal redeploys ISCSI services；Carry out IP address migration.
Although above-mentioned the embodiment of the present invention is described with reference to accompanying drawing, model not is protected to the present invention
The limitation enclosed, one of ordinary skill in the art should be understood that on the basis of technical scheme those skilled in the art are not
Need to pay various modifications or deformation that creative work can make still within protection scope of the present invention.
Claims (6)
1. a kind of ISCSI protocol implementing methods of distributed storage, it is characterized in that, comprise the following steps：
ISCSI service clusters carry out fault detect by heartbeat acknowledgement mechanism, and complete malfunctioning node by master memory nodes
Ruling and configuration；
ISCSI service clusters carry out ISCSI Service Source migration operations after memory node dynamic change.
2. a kind of ISCSI protocol implementing methods of distributed storage as claimed in claim 1, it is characterized in that, in addition to,
ISCSI service clusters carry out ISCSI service arrangements according to node selection strategy, realize ISCSI services on each memory node
Equiblibrium mass distribution.
3. a kind of ISCSI protocol implementing methods of distributed storage as claimed in claim 2, it is characterized in that, the ISCSI clothes
Cluster be engaged according to node selection strategy progress ISCSI service arrangements, including：
The poll since lowest number memory node, if the memory node is malfunctioning node, select next effective node；
Effective node of ISCSI connection minimum numbers is selected, if the ISCSI quantitys of service of each memory node are identical, selection is compiled
Number minimum memory node carries out ISCSI service arrangements.
4. a kind of ISCSI protocol implementing methods of distributed storage as claimed in claim 1, it is characterized in that, it is described by
Master memory nodes complete malfunctioning node ruling and configuration, including：
In setting time, some memory node is reported as exception by memory nodes more than half, then master memory nodes are recognized
It is malfunctioning node for the memory node and kicks out of ISCSI storage clusters, while updates ISCSI storage cluster node status informations,
Data result after renewal is sent and is synchronized on each memory node by master memory nodes.
5. a kind of ISCSI protocol implementing methods of distributed storage as claimed in claim 1, it is characterized in that, the ISCSI clothes
Cluster be engaged in after memory node dynamic change, carries out ISCSI Service Source migration operations, including：ISCSI service clusters are judging
Memory node is progress ISCSI Service Source migration operations after malfunctioning node；
When memory node adds ISCSI service clusters again, ISCSI Service Source migrations are carried out.
6. a kind of ISCSI protocol implementing methods of distributed storage as claimed in claim 1, it is characterized in that, the ISCSI clothes
Business resource migration operation, including：
The ISCSI service profiles of memory node to be migrated are obtained, Ceph block devices are mapped to by health according to configuration file
Node；Memory node cluster after renewal redeploys ISCSI services；Carry out IP address migration.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711098193.9A CN107645421A (en) | 2017-11-09 | 2017-11-09 | A kind of ISCSI protocol implementing methods of distributed storage |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711098193.9A CN107645421A (en) | 2017-11-09 | 2017-11-09 | A kind of ISCSI protocol implementing methods of distributed storage |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107645421A true CN107645421A (en) | 2018-01-30 |
Family
ID=61125708
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711098193.9A Pending CN107645421A (en) | 2017-11-09 | 2017-11-09 | A kind of ISCSI protocol implementing methods of distributed storage |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107645421A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846064A (en) * | 2018-06-06 | 2018-11-20 | 南京群顶科技有限公司 | Dynamic chain type storage cluster implementation method based on ceph |
| CN109151028A (en) * | 2018-08-23 | 2019-01-04 | 郑州云海信息技术有限公司 | A kind of distributed memory system disaster recovery method and device |
| CN113596195A (en) * | 2021-08-23 | 2021-11-02 | 重庆紫光华山智安科技有限公司 | Public IP address management method, device, main node and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1554055A (en) * | 2001-07-23 | 2004-12-08 | �Ƚ�װ�ù�˾ | High-availability cluster virtual server system |
| CN1852502A (en) * | 2006-05-29 | 2006-10-25 | 杭州华为三康技术有限公司 | Method for realizing load uniform in clustering system, system and storage controller |
| CN101819545A (en) * | 2010-04-09 | 2010-09-01 | 济南银泉科技有限公司 | Method for realizing platform migration by using virtualization technology |
| CN102594861A (en) * | 2011-12-15 | 2012-07-18 | 杭州电子科技大学 | Cloud storage system with balanced multi-server load |
| WO2014209270A1 (en) * | 2013-06-24 | 2014-12-31 | Hitachi, Ltd. | Method and an apparatus to a cloud management system allocating dynamic wan optimizing function resources |
| CN105281949A (en) * | 2015-09-09 | 2016-01-27 | 浪潮(北京)电子信息产业有限公司 | Host fence method and fence device in mixed storage mode |
-
2017
- 2017-11-09 CN CN201711098193.9A patent/CN107645421A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1554055A (en) * | 2001-07-23 | 2004-12-08 | �Ƚ�װ�ù�˾ | High-availability cluster virtual server system |
| CN1852502A (en) * | 2006-05-29 | 2006-10-25 | 杭州华为三康技术有限公司 | Method for realizing load uniform in clustering system, system and storage controller |
| CN101819545A (en) * | 2010-04-09 | 2010-09-01 | 济南银泉科技有限公司 | Method for realizing platform migration by using virtualization technology |
| CN102594861A (en) * | 2011-12-15 | 2012-07-18 | 杭州电子科技大学 | Cloud storage system with balanced multi-server load |
| WO2014209270A1 (en) * | 2013-06-24 | 2014-12-31 | Hitachi, Ltd. | Method and an apparatus to a cloud management system allocating dynamic wan optimizing function resources |
| CN105281949A (en) * | 2015-09-09 | 2016-01-27 | 浪潮(北京)电子信息产业有限公司 | Host fence method and fence device in mixed storage mode |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846064A (en) * | 2018-06-06 | 2018-11-20 | 南京群顶科技有限公司 | Dynamic chain type storage cluster implementation method based on ceph |
| CN108846064B (en) * | 2018-06-06 | 2021-07-23 | 南京群顶科技有限公司 | Method for realizing dynamic chained storage cluster based on ceph |
| CN109151028A (en) * | 2018-08-23 | 2019-01-04 | 郑州云海信息技术有限公司 | A kind of distributed memory system disaster recovery method and device |
| CN113596195A (en) * | 2021-08-23 | 2021-11-02 | 重庆紫光华山智安科技有限公司 | Public IP address management method, device, main node and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10177994B2 (en) | Fault tolerant federation of computing clusters | |
| US10805406B2 (en) | Zone redundant computing services using multiple local services in distributed computing systems | |
| US11700300B2 (en) | Cluster resource management in distributed computing systems | |
| WO2019119311A1 (en) | Data storage method, device, and system | |
| US20170060689A1 (en) | Varying rebuild task priorities | |
| US11595474B2 (en) | Accelerating data replication using multicast and non-volatile memory enabled nodes | |
| CN107645421A (en) | A kind of ISCSI protocol implementing methods of distributed storage | |
| US9378078B2 (en) | Controlling method, information processing apparatus, storage medium, and method of detecting failure | |
| CN102983996A (en) | Dynamic allocation method and system for high-availability cluster resource management | |
| US11397629B1 (en) | Automated resolution engine | |
| CN108063787A (en) | The method that dual-active framework is realized based on distributed consensus state machine | |
| CN106874142A (en) | A kind of real time data fault-tolerance processing method and system | |
| CN108733307B (en) | Storage management method, apparatus and computer readable medium | |
| CN104052799B (en) | A kind of method that High Availabitity storage is realized using resource ring | |
| CN103336721B (en) | Method, device and system for allocating database operation request | |
| CN111866210A (en) | Virtual IP balance distribution method, system, terminal and storage medium | |
| WO2016206433A1 (en) | Method and apparatus for balancing server load | |
| CN115878047B (en) | Data consistency verification method, device, equipment and storage medium | |
| CN109218465A (en) | A kind of server node sequence number report method, device, equipment and storage medium | |
| CN112433842B (en) | Method and equipment for distributing master node and slave node in service cluster | |
| US11556361B2 (en) | Monitoring and managing of complex multi-role applications | |
| CN117234433B (en) | Data migration method and device, RAID storage device, storage medium and electronic device | |
| US10360107B2 (en) | Modifying allocation of storage resources in a dispersed storage network | |
| CN108270831A (en) | A kind of arbitrator's cluster implementation method and device | |
| Xue | Automated cloud bursting on a hybrid cloud platform |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180130 |