CN101630236B - Method and system for processing business data as well as storing device and application server - Google Patents

Method and system for processing business data as well as storing device and application server Download PDF

Info

Publication number
CN101630236B
CN101630236B CN2009100915014A CN200910091501A CN101630236B CN 101630236 B CN101630236 B CN 101630236B CN 2009100915014 A CN2009100915014 A CN 2009100915014A CN 200910091501 A CN200910091501 A CN 200910091501A CN 101630236 B CN101630236 B CN 101630236B
Authority
CN
China
Prior art keywords
information
logical block
module
application server
storage system
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN2009100915014A
Other languages
Chinese (zh)
Other versions
CN101630236A (en
Inventor
马草飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chengdu Huawei Technology Co Ltd
Original Assignee
Huawei Symantec Technologies Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Huawei Symantec Technologies Co Ltd filed Critical Huawei Symantec Technologies Co Ltd
Priority to CN2009100915014A priority Critical patent/CN101630236B/en
Publication of CN101630236A publication Critical patent/CN101630236A/en
Application granted granted Critical
Publication of CN101630236B publication Critical patent/CN101630236B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Abstract

The embodiment of the invention discloses a method and a system for processing business data as well as a storing device and an application server, wherein the method comprises the following steps: sampling data input and output by a logic unit of a storing system which corresponds to the application server according to a preset sampling strategy, and acquiring sampling information; analyzing the sampling information, and acquiring analyzing result information; generating storing configuration information of the logic unit according to the analyzing result information; and storing the business data of the application server according to the storing configuration information. The storing device comprises an input and output sampling strategy module, an input and output characteristic analysis module, an information generating module and a processing module. The application server comprises an input and output sampling strategy module, an input and output characteristic analysis module and an information generating module. The processing system of the business data comprises the application server and the storing device. The embodiment of the invention ensures that the performance optimization of the storing system can be realized under different application scenes.

Description

The disposal route of business datum, system, memory device and application server
Technical field
The present invention relates to computer memory technical, relate in particular to a kind of disposal route, system, memory device and application server of business datum.
Background technology
Universal day by day along with computer utility, the user improves gradually to computing velocity and performance demands, and the performance of data storage device and speed directly have influence on the overall performance of computer system.In order to improve hard disk speed, raid-array (Redundant Array of Independent Disk; Hereinafter to be referred as: RAID) technology has constantly developed into low-end market by the server high-end market at present, the RAID technology can be given full play to the advantage of polylith hard disk, the any head and shoulders above independent hard disk of its speed and handling capacity, but also have good fault-tolerant ability, when any hard disk corruptions, all can work on.In addition, be deployed in multipath (the Multiple Path of application server end; Hereinafter to be referred as: MP) software is except being used for by making of redundant path the reliability of elevator system, also can avoid the service disconnection that causes because of Single Point of Faliure, improves the handling capacity of system.
In the disk array in the prior art, MP software is installed in the application server based on AIX/Linux/Windows, utilize MP software to realize management to redundant path between server and the memory device, after having guaranteed that a paths interrupts therein, business can be switched on other safe paths online.In addition, because the RAID technology can be divided into several different ranks, and different speed, security and cost performances is provided respectively, the user can be configured according to the RAID rank of business demand to disk array, as when reliability requirement is higher, can use RAID0; When handling capacity is had relatively high expectations, can use RAID1; Performance requirement is higher and need have certain fault-tolerance the time when reading, and can use RAID5.
Yet, the difference of the handled application of computing machine is increasing in the practical application, the behavior of application software also has nothing in common with each other, concerning storage system, different application has different performances and demand, temporal correlation as some application is bigger, and some application need is handled I/O request at random, and some is used then needs processing sequence I/O request.Configuration attributes different in the disk array can produce great performance difference in response to the difference with scene, therefore, need carry out reasonable configuration to the association attributes in the disk array, and domestic consumer is difficult to provide the allocation plan of a concrete storage system, even can finish the attribute configuration to storage system, but the allocation plan of this static state can not satisfy the requirement of using continuous variation.
Summary of the invention
The embodiment of the invention is to provide a kind of disposal route, system, memory device and application server of business datum, realizes the attribute information of configure storage system adaptively, makes storage system can all realize the optimization of performance under the different application scene.
To achieve these goals, the embodiment of the invention provides a kind of disposal route of business datum, comprising:
Sample according to the inputoutput data in the logical block of the storage system of default sampling policy application server correspondence, and obtain sample information, wherein, described logical block is the inputoutput data of an application server employed logical block when storing on storage system;
Described sample information is analyzed, obtained analysis result information;
Generate the store configuration information of described logical block according to described analysis result information;
According to described store configuration information described storage system is configured, and under the storage system of described store configuration information configuration, the business datum of described application server is carried out stores processor;
Add up the loading condition of described logical block;
Adjust the home control device of logical block according to described loading condition.
The embodiment of the invention also provides a kind of memory device, comprising:
Input and output sampling policy module, be used for sampling according to the inputoutput data of the logical block of the storage system of default sampling policy application server correspondence, and obtain sample information, wherein, described logical block is the inputoutput data of an application server employed logical block when storing on storage system;
The input-output characteristic analysis module is used for the described sample information that described input and output sampling policy module is obtained is analyzed, and obtains analysis result information;
Information generating module is used for generating according to the described analysis result information that described input-output characteristic analysis module obtains the store configuration information of described logical block;
Processing module is used for according to the described store configuration information that described information generating module generates described storage system being configured, and under the storage system of described store configuration information configuration the business datum of described application server is carried out stores processor;
Statistical module is used to add up the loading condition of described logical block;
Adjusting module is used for the home control device according to the described loading condition adjustment logical block of described statistical module counts.
The embodiment of the invention also provides a kind of application server, comprising:
Input and output sampling policy module, be used for the inputoutput data of logical block being sampled according to default sampling policy, and obtain sample information, wherein, described logical block is the inputoutput data of application server employed logical block when storing on storage system;
The input-output characteristic analysis module is used for the described sample information that described input and output sampling policy module is obtained is analyzed, and obtains analysis result information;
Information generating module, be used for generating the store configuration information of described logical block according to the described analysis result information that described input-output characteristic analysis module obtains, so that storage system is configured, and under the storage system of described store configuration information configuration, the business datum of described application server is carried out stores processor;
Statistical module is used to add up the loading condition of described logical block;
Adjusting module is used for the home control device according to the described loading condition adjustment logical block of described statistical module counts.
The embodiment of the invention also provides a kind of disposal system of business datum, comprising:
Application server is deployed with multi-path software, and described application server is used for issuing inputoutput data to memory device;
Memory device, be used for the inputoutput data of the logical block of the storage system of described application server correspondence being sampled according to default sampling policy, the described sample information of obtaining is analyzed, generate the store configuration information of described logical block according to the described analysis result information that obtains, and described storage system is configured according to described store configuration information, and under the storage system of described store configuration information configuration, the business datum of described application server is carried out stores processor, add up the loading condition of described logical block, adjust the home control device of logical block according to described loading condition, wherein, described logical block is the inputoutput data of an application server employed logical block when storing on storage system.
The disposal route of a kind of business datum that the embodiment of the invention provides, system, memory device and application server, according to different sample information different stored configuration schemes is set, make and at different professional situations and application scenarios different stored configuration schemes to be set, overcome the defective that the system performance that the static stored configuration scheme that is provided with is brought in the prior art reduces, realize the attribute information of configure storage system adaptively, made storage system can under the different application scene, all realize the optimization of performance.
Description of drawings
In order to be illustrated more clearly in the present invention or technical scheme of the prior art, to do to introduce simply to the accompanying drawing of required use in embodiment or the description of the Prior Art below, apparently, accompanying drawing in describing below only is some embodiments of the present invention, for those of ordinary skills, under the prerequisite of not paying creative work, can also obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the process flow diagram of disposal route one embodiment of business datum of the present invention;
Fig. 2 is the process flow diagram of another embodiment of disposal route of business datum of the present invention;
Fig. 3 is the application scenarios synoptic diagram of the disk array among another embodiment of disposal route of business datum of the present invention;
Fig. 4 is the contrast of the route diversion among another embodiment of disposal route of business datum of the present invention synoptic diagram;
Fig. 5 is the structural drawing of memory device one embodiment of the present invention;
Fig. 6 is the structural drawing of another embodiment of memory device of the present invention;
Fig. 7 is the structural drawing of application server embodiment of the present invention;
Fig. 8 is the structural drawing of the disposal system embodiment of business datum of the present invention.
Embodiment
Below in conjunction with the accompanying drawing among the present invention, the technical scheme among the present invention is clearly and completely described, obviously, described embodiment only is the present invention's part embodiment, rather than whole embodiment.Based on the embodiment among the present invention, the every other embodiment that those of ordinary skills are obtained under the prerequisite of not making creative work belongs to the scope of protection of the invention.
Below by drawings and Examples, technical scheme of the present invention is described in further detail.
Fig. 1 is the process flow diagram of disposal route one embodiment of business datum of the present invention, and as shown in Figure 1, present embodiment has offered a kind of disposal route of business datum, can specifically comprise the steps:
Step 101 is sampled according to the inputoutput data in the logical block of the storage system of default sampling policy application server correspondence, and is obtained sample information;
Step 102 is analyzed sample information, obtains analysis result information;
Step 103 generates the store configuration information of the logical block of storage system according to analysis result information;
Step 104 is carried out stores processor according to the business datum of store configuration information application server.
Sampling policy default in the present embodiment can be the strategy of user according to the acquiescence execution of the actual operating position setting of business, the user can utilize user's configuration tool that sampling policy is set in client, the employing strategy that is provided with can be information such as concrete sampling time section, sampling period, as logical block (the Logic Unit Number to the storage system of appointment application server correspondence 2 o'clock to 5 o'clock every afternoon; Hereinafter to be referred as: I/O data LUN) are sampled.Employed LUN when the LUN of the storage system of application server correspondence can store on storage system for the I/O data of application server herein.Present embodiment is sampled by the I/O data on the LUN of the storage system of certain sampling policy application server correspondence, and utilize corresponding analysis module that the sample information that gets access to is carried out analyzing and processing, utilize analysis result information to generate the store configuration information of LUN of the storage system of this application server correspondence, this store configuration information can be specially the RAID configuration of storage system, buffer memory (Cache) strategy, home control device configuration information of LUN or the like, according to the store configuration information that generates storage system is configured, the store configuration information of the optimum under the different sampling policies is provided for storage system, and under the storage system of this store configuration information configuration, the business datum of application server is carried out stores processor.
This enforcement provides a kind of disposal route of business datum, according to different sample information different stored configuration schemes is set, make and at different professional situations and application scenarios different stored configuration schemes to be set, overcome the defective that the system performance that the static stored configuration scheme that is provided with is brought in the prior art reduces, realized the attribute information of configure storage system adaptively, make storage system can under the different application scene, all realize the optimization of performance, simultaneously, the user only needs to import corresponding enter factor by configuration tool, carry out the judgement of stored configuration scheme and need not user oneself according to professional situation, for the user provides a great convenience.
Fig. 2 is the process flow diagram of another embodiment of disposal route of business datum of the present invention, and as shown in Figure 2, present embodiment provides a kind of disposal route of business datum, can comprise the steps:
Step 201, I/O sampling policy module is sampled according to the inputoutput data in the logical block of the storage system of default sampling policy application server correspondence, and obtains sample information.
This step can be specially I/O sampling policy module and according to the sampling policy of user preset the I/O data on the LUN of the storage system of the application server correspondence of appointment be sampled, when application server carries out the stores processor of I/O data, the I/O data are passed through host bus adaptor (Host BusAdapter; After being issued in the disk array in the storage system hereinafter to be referred as: driving HBA), object machine in the disk array is distributed the I/O data that receive, and data are sent to small computer system interface (Small Computer System Interface; Hereinafter to be referred as: SCSI) module or RAID module the time, the I/O data are also sent to I/O sampling policy module.I/O sampling policy module is carried out the sampling of I/O data according to the sampling policy of user preset, wherein, sampling policy can be the strategy of user according to the acquiescence execution of the actual operating position setting of business, the user can utilize user's configuration tool that sampling policy is set in client, the employing strategy that is provided with can be information such as concrete sampling time section, sampling period, as sampling policy is to carry out the sampling of I/O data 2 o'clock every afternoons to 5 property dot cycle ground, and obtains sample information according to sampled result.The user can set sampling policy according to the real needs and the professional operation conditions of business, for the time stronger correlativity is arranged as some business, in certain special time period, may need to handle more I/O request, then need the I/O that handles to ask less relatively at another special time period, then the user can be set at these two certain period of time the sampling time section in the sampling policy, promptly in these two time periods the I/O data is sampled.Particularly, sample information can comprise the logical address of I/O data, the size information of I/O data, the receiving time information of I/O data, the destination logical unit information of I/O data and the controller information of I/O data process.It is pointed out that the sample information that gets access to by this step includes but not limited to above-mentioned information, sample information can also be other relevant informations of I/O data, can select according to the concrete configuration situation of storage system.Being I/O sampling policy module periodically carries out sample record to the characteristic of the I/O data on the LUN of the storage system of given server correspondence in the sampling time section of setting, with the logical address that gets access to above-mentioned I/O data, the sample information such as size information of I/O data.
Step 202, I/O specificity analysis module is analyzed sample information, obtains analysis result information.
Finish the sampling of I/O data in I/O sampling policy module, and after getting access to sample information, the logical address of I/O data, the sample information such as size information of I/O data can be sent to I/O specificity analysis module, by I/O specificity analysis module the sample information that gets access to is analyzed, and got access to analysis result information.Particularly, the analysis result information in this step can comprise the size information of the area information, I/O data write request percent information of the size information of I/O packet, the focus visit of percent information, the I/O data of I/O data and sequential I/O data at random, the maximum I/O data that receive, the size information of the minimum I/O data that receive.Wherein, the size information of I/O packet can be the percent information of big I/O and little I/O, and big I/O data correspond to the bigger I/O data of data volume, and little I/O data correspond to the less I/O data of data volume.It is to be noted, the analysis result information of obtaining by this step includes but not limited to above-mentioned analysis result information, can also get access to other analysis result information according to sample information, as the processing time of disk array to the I/O data, disk array is in I/O data and this I/O size of data of the system optimal performance of sampling time section processing, disk array is in system that the sampling time section is handled I/O data and this I/O size of data of the poorest performance, the I/O data of the poorest performance correspondence of system the formation of process and the time loss of in formation, waiting for, the strategy of Cache and corresponding hit rate etc.
Step 203 is set the weight rank of each information in the analysis result information respectively.
After over-sampling and analytic process get access to analysis result information, the user can carry out other setting of weight level to each information in the analysis result information according to the practical business situation.As some application and time stronger correlativity is arranged, may need to handle more I/O request by day as this business, then relatively more idle at night, then correspondingly can the weight rank that big I/O data are corresponding with the percent information of little I/O data be provided with higherly.And some application need is handled a large amount of requests of I/O at random, and as the data library software, some is used then needs to handle a large amount of sequential I/O requests, and then correspondingly inciting somebody to action at random, the I/O data weight rank corresponding with the percent information of sequential I/O data is provided with higherly.
Step 204 is according to the weight rank of each information correspondence and the store configuration information of analysis result information formation logic unit.
After each information in the analysis result information being carried out other setting of weight level, specifically according to analysis result information and wherein the weight rank of each information correspondence generate the store configuration information of LUN of the storage system of application server correspondence, promptly when generating store configuration information, the weight rank of each information correspondence in the analysis result information is taken into account, to obtain more reasonably store configuration information, the row that is configured into of storage system is further optimized.I/O data on the LUN of the storage system of specifying the application server correspondence are being sampled, and after the sample information that gets access to carried out analyzing and processing, generate the store configuration information of LUN of the storage system of this application server correspondence according to the analysis result information that gets access to, revise the relevant configured parameter of storage system according to this store configuration information, be provided with or the like as the configuration of RAID grade, the strategy of Cache, the home control device of LUN.Be illustrated in figure 3 as the application scenarios synoptic diagram of the disk array among another embodiment of disposal route of business datum of the present invention, because this store configuration information is to obtain according to the characteristic sampling analysis of the I/O data in the current slot, therefore, this store configuration information is a store configuration information more excellent under the current state, and the storage system that disposes according to this store configuration information can obtain its optimum characteristic in current slot.
Further, the disposal route of the business datum that present embodiment provides can also comprise the steps: to generate analytical statement according to sample information and store configuration information, and analytical statement is sent to far-end server.Obtaining sample information by I/O sampling policy module samples, obtain analysis result information by I/O specificity analysis module analysis, and generate the more excellent store configuration information of storage system by analysis result information after, can further generate analytical statement according to the store configuration information of the correspondence in sample information in the current sampling time section and the current sampling time section, this analytical statement is sent in the far-end server by network communication interface, the user can get access to this analytical statement by far-end server, carry out manual analysis or backup, the reference frame when making amendment for the user as follow-up store configuration information to storage system.
Further, the disposal route of the business datum that provides of present embodiment can also comprise the steps: to write down and obtain the historical performance information of storage system; According to historical storage configuration information and historical performance information store configuration information is adjusted.Wherein, the historical storage configuration information can in a last sampling time section through over-sampling, analyze the store configuration information of the storage system obtain, historical performance information is configured the performance information of back storage system to storage system for the historical configuration information that obtains according to a last sampling time section, it is the overall performance situation of storage system, backup all preserved in the information record that present embodiment obtained each stage, prepares against the follow-up reference of carrying out.Since in the present embodiment to the periodic samples that is sampled as of I/O data, and after each sampling period finishes, to relevant sample information, store configuration information and system performance information all write down and preserve, interim when the next sampling period, when continuation is sampled to the I/O data and is analyzed, also with reference to the data of historical record, as historical storage configuration information and historical performance information, set historical storage configuration information and historical performance information are adjusted the store configuration information that generates in this sampling period, so that more reasonably stored configuration scheme to be provided.
Step 205 is carried out stores processor according to the business datum of store configuration information application server.
After generating more excellent store configuration information according to analysis result information, according to this store configuration information storage system is disposed accordingly, utilize the business datum of the storage system application server after disposing to carry out stores processor.
On the basis of the foregoing description, the disposal route of the business datum that present embodiment provides can also comprise the steps: the loading condition of statistic logic unit; Adjust the home control device of each logical block according to loading condition.In the present embodiment, storage system provides the storage space of data for each application on the application server, in storage system, comprise at least two LUN, when the LUN resource that disk array is provided when application server conducted interviews, application server used the home control device of this LUN correspondence to carry out corresponding I/O operation.For improving the I/O access performance, MP software is set in application server usually, the home control device that adopts storage system to be provided with in layoutprocedure is shared the I/O request, and adopt the static mode that is provided with to come the home control device of LUN is provided with in the prior art usually, be easy to cause a large amount of I/O business to be concentrated like this and be distributed on same controller or the same paths by MP software, thus the overall performance of reduction system.The defective that present embodiment is brought for the home control device that solves the static state setting that exists in the prior art, earlier the loading condition of all LUN in the storage system is added up, the loading condition of different LUN has nothing in common with each other, the load of some LUN is more, and the load of some LUN is less, loading condition according to LUN comes the home control device of each LUN is adjusted, the LUN that load is more adjusts on the home control device of the less LUN of load, be illustrated in figure 4 as the route diversion contrast synoptic diagram among another embodiment of disposal route of business datum of the present invention, as can be seen from Figure 4, originally at least two application servers carried out at least two I/O operations on a controller, after adjusting, at least two I/O operation of application server is balancedly shared at least two controllers, and after the change of home control device, make that the employed optimal path of MP software in the application server also changes simultaneously.Present embodiment is more balancedly shared the I/O data of two application servers on different controllers or the different path at least, solved I/O the blocking up on a controller or a paths of at least two application servers, and the relatively more idle defective in other controllers or path, the home control device of LUN is dynamically adjusted in realization according to the I/O loading condition of all LUN in the storage system.
The disposal route that it is pointed out that the business datum that present embodiment provides goes for storage area network (Storsge Area Network; Hereinafter to be referred as: SAN) the SAN equipment of networking can also be applicable to network attached storage (Network Attached Storage; Hereinafter to be referred as: NAS) the NAS memory device of networking, concrete technical scheme is all identical, just on the sampled data source, there are differences, wherein, because SAN equipment externally provides the visit of piece level, and NAS equipment externally provides the visit of file-level, therefore, the sampled data source of SAN equipment is the I/O data of piece level, and the sampled data source of NAS equipment is the I/O data of file-level.And no matter be SAN networking (mode) or NAS networking, its communication interface modules all goes for optical-fibre channel (Fibre Channel; Hereinafter to be referred as: FC) interface, serial SCSI (serial attached SCSI; Hereinafter to be referred as: SAS) interface and IP interface.
This enforcement provides a kind of disposal route of business datum, I/O sampling policy module is sampled to the I/O data of the LUN of given server correspondence according to default sampling policy, by I/O specificity analysis module the sample information of obtaining is analyzed, and acquisition analysis result information, according to analysis result information the stored configuration scheme of different application in the different time sections correspondence is set, make and at different professional situations and application scenarios different stored configuration schemes to be set, overcome the defective that the system performance that the static stored configuration scheme that is provided with is brought in the prior art reduces.And self-learning capability by software, by the store configuration information that generates further being adjusted in conjunction with history information, constantly dynamically adjust the configuration information of storage system, for the stored configuration that the user is provided under the different scenes is advised, the user only needs to import corresponding enter factor by configuration tool, carry out the judgement of stored configuration scheme and need not user oneself according to professional situation, for the user provides a great convenience, make total system under the application scenarios of long-time scope and complexity, all can have excellent performance.In addition, I/O loading condition according to all LUN in the storage system, dynamically adjust the home control device of LUN, the I/O data of at least two application servers are more balancedly shared on different controllers or the different path, solved I/O the blocking up on a controller or a paths of at least two application servers, and the relatively more idle defective in other controllers or path, the home control device of LUN is dynamically adjusted in realization according to the I/O loading condition of all LUN in the storage system.
Fig. 5 is the structural drawing of memory device one embodiment of the present invention, and as shown in Figure 5, present embodiment provides a kind of memory device, can specifically comprise I/O sampling policy module 501, I/O specificity analysis module 502, information generating module 503 and processing module 504.Wherein, I/O sampling policy module 501 is used for sampling according to the inputoutput data of the logical block of the storage system of default sampling policy application server correspondence, and obtains sample information.I/O specificity analysis module 502 is used for the described sample information that I/O sampling policy module 501 is obtained is analyzed, and obtains analysis result information.Information generating module 503 is used for the store configuration information according to the analysis result information formation logic unit of I/O specificity analysis module 502 acquisitions.Processing module 504 is used for carrying out stores processor according to the business datum of the store configuration information application server of information generating module 503 generations.
Further, be illustrated in figure 6 as the structural drawing of another embodiment of memory device of the present invention, on the basis of above-mentioned embodiment shown in Figure 5, the memory device that present embodiment provides can also comprise: report generation module 601, be used for the described store configuration information that the described sample information obtained according to I/O sampling policy module 501 and information generating module 503 generate and generate analytical statement, and described analytical statement is sent to far-end server.Particularly, can comprise at least two object informations in analysis result information, then information generating module 503 specifically comprises setup unit 513 and generation unit 523.Wherein, setup unit 513 is used for setting the corresponding respectively weight rank of at least two object informations of analysis result information; Generation unit 523 is used for the store configuration information according to the logical block of the storage system of the weight rank of at least two object information correspondences of setup unit 513 settings and analysis result information generation application server correspondence.
Further, the memory device that present embodiment provides can also comprise: logging modle 602 and information adjusting module 603, and wherein, logging modle 602 is used to write down and obtain the historical performance information of storage system; Information adjusting module 603 is used for according to the described historical performance information of historical storage configuration information and logging modle 602 records described store configuration information being adjusted.
In addition, the memory device that provides of present embodiment can also comprise statistical module 604 and adjusting module 605.Wherein, statistical module 604 is used for the loading condition of statistic logic unit; Adjusting module 605 is used for adjusting according to the described loading condition of statistical module 604 statistics the home control device of each described logical block.
This enforcement provides a kind of memory device, by I/O sampling policy module is set, I/O specificity analysis module, information generating module and processing module, according to different sample information different stored configuration schemes is set, make and at different professional situations and application scenarios different stored configuration schemes to be set, overcome the defective that the system performance that the static stored configuration scheme that is provided with is brought in the prior art reduces, realized the attribute information of configure storage system adaptively, make storage system can under the different application scene, all realize the optimization of performance, simultaneously, the user only needs to import corresponding enter factor by configuration tool, carry out the judgement of stored configuration scheme and need not user oneself according to professional situation, for the user provides a great convenience.
Fig. 7 is the structural drawing of application server embodiment of the present invention, as shown in Figure 7, present embodiment provides a kind of application server, in the present embodiment, when if desired certain application server being carried out special I/O analysis, each module that memory device one side can be comprised is implanted in application server one side, and therefore, the application server that provides in the present embodiment can specifically comprise I/O sampling policy module 701, I/O specificity analysis module 702 and information generating module 703.Wherein, I/O sampling policy module 701 is used for according to default sampling policy the inputoutput data of logical block being sampled, and obtains sample information; I/O specificity analysis module 702 is used for the described sample information that I/O sampling policy module 701 is obtained is analyzed, and obtains analysis result information; Information generating module 703 is used for generating according to the described analysis result information that I/O specificity analysis module 702 obtains the store configuration information of described logical block.In the above-described embodiments, I/O sampling policy module 701 and I/O specificity analysis module 702 all are arranged on memory device one side, in the present embodiment, I/O sampling policy module 701 and I/O specificity analysis module 702 all are arranged on application server one side, make and to carry out the analysis of special I/O data to specifying application server, and only need in memory device one side and application server one side by the privately owned communication protocol realization of formulating communicating by letter each other.
This enforcement provides a kind of application server, by I/O sampling policy module is set, I/O specificity analysis module and information generating module, according to different sample information different stored configuration schemes is set, make and at different professional situations and application scenarios different stored configuration schemes to be set, overcome the defective that the system performance that the static stored configuration scheme that is provided with is brought in the prior art reduces, realized the attribute information of configure storage system adaptively, make storage system can under the different application scene, all realize the optimization of performance, simultaneously, the user only needs to import corresponding enter factor by configuration tool, carry out the judgement of stored configuration scheme and need not user oneself according to professional situation, for the user provides a great convenience.
Fig. 8 is the structural drawing of the disposal system embodiment of business datum of the present invention, as shown in Figure 8, present embodiment provides a kind of disposal system of business datum, and the disposal system of the business datum that present embodiment provides can specifically comprise application server 801 and memory device 802.Wherein, be deployed with multi-path software in the application server 801, be used for issuing inputoutput data to memory device 802.Memory device 802 is used for sampling according to the inputoutput data of the logical block of default sampling policy application server 801 correspondences, the described sample information of obtaining is analyzed, according to the store configuration information of the analysis result information formation logic unit that obtains, and carry out stores processor according to the business datum of described store configuration information application server 801.
This enforcement provides a kind of disposal system of business datum, by application server and memory device are set, according to different sample information different stored configuration schemes is set, make and at different professional situations and application scenarios different stored configuration schemes to be set, overcome the defective that the system performance that the static stored configuration scheme that is provided with is brought in the prior art reduces, realized the attribute information of configure storage system adaptively, make storage system can under the different application scene, all realize the optimization of performance, simultaneously, the user only needs to import corresponding enter factor by configuration tool, carry out the judgement of stored configuration scheme and need not user oneself according to professional situation, for the user provides a great convenience.
It should be noted that at last: above embodiment only in order to technical scheme of the present invention to be described, is not intended to limit; Although with reference to previous embodiment the present invention is had been described in detail, those of ordinary skill in the art is to be understood that: it still can be made amendment to the technical scheme that previous embodiment is put down in writing, and perhaps part technical characterictic wherein is equal to replacement; And these modifications or replacement do not make the essence of appropriate technical solution break away from the spirit and scope of embodiment of the invention technical scheme.

Claims (10)

1. the disposal route of a business datum is characterized in that, comprising:
Sample according to the inputoutput data in the logical block of the storage system of default sampling policy application server correspondence, and obtain sample information, wherein, described logical block is the inputoutput data of an application server employed logical block when storing on storage system;
Described sample information is analyzed, obtained analysis result information;
Generate the store configuration information of described logical block according to described analysis result information;
According to described store configuration information described storage system is configured, and under the storage system of described store configuration information configuration, the business datum of described application server is carried out stores processor;
Add up the loading condition of described logical block;
Adjust the home control device of logical block according to described loading condition.
2. method according to claim 1 is characterized in that, also comprises: generate analytical statement according to described sample information and described store configuration information, and described analytical statement is sent to far-end server.
3. method according to claim 2 is characterized in that, comprises at least two object informations in the described analysis result information;
The described store configuration information that generates described logical block according to described analysis result information comprises:
Set the weight rank of at least two object informations described in the described analysis result information respectively;
The store configuration information that generates described logical block according to the weight rank and the described analysis result information of described at least two object informations.
4. method according to claim 1 is characterized in that, also comprises:
Write down and obtain the historical performance information of described storage system;
According to historical storage configuration information and described historical performance information described store configuration information is adjusted.
5. a memory device is characterized in that, comprising:
Input and output sampling policy module, be used for sampling according to the inputoutput data of the logical block of the storage system of default sampling policy application server correspondence, and obtain sample information, wherein, described logical block is the inputoutput data of an application server employed logical block when storing on storage system;
The input-output characteristic analysis module is used for the described sample information that described input and output sampling policy module is obtained is analyzed, and obtains analysis result information;
Information generating module is used for generating according to the described analysis result information that described input-output characteristic analysis module obtains the store configuration information of described logical block;
Processing module is used for according to the described store configuration information that described information generating module generates described storage system being configured, and under the storage system of described store configuration information configuration the business datum of described application server is carried out stores processor;
Statistical module is used to add up the loading condition of described logical block;
Adjusting module is used for the home control device according to the described loading condition adjustment logical block of described statistical module counts.
6. memory device according to claim 5 is characterized in that, also comprises:
The report generation module is used for the described store configuration information that the described sample information obtained according to described input and output sampling policy module and described information generating module generate and generates analytical statement, and described analytical statement is sent to far-end server.
7. memory device according to claim 6 is characterized in that, comprises at least two object informations in the described analysis result information;
Described information generating module comprises:
Setup unit is used for setting respectively the weight rank of at least two object informations described in the described analysis result information;
Generation unit is used for the weight rank of described at least two object informations of setting respectively according to described setup unit and the store configuration information that described analysis result information generates described logical block.
8. memory device according to claim 5 is characterized in that, also comprises:
Logging modle is used to write down and obtain the historical performance information of described storage system;
The information adjusting module is used for according to the described historical performance information of historical storage configuration information and described logging modle record described store configuration information being adjusted.
9. an application server is characterized in that, comprising:
Input and output sampling policy module, be used for the inputoutput data of logical block being sampled according to default sampling policy, and obtain sample information, wherein, described logical block is the inputoutput data of application server employed logical block when storing on storage system;
The input-output characteristic analysis module is used for the described sample information that described input and output sampling policy module is obtained is analyzed, and obtains analysis result information;
Information generating module, be used for generating the store configuration information of described logical block according to the described analysis result information that described input-output characteristic analysis module obtains, so that storage system is configured, and under the storage system of described store configuration information configuration, the business datum of described application server is carried out stores processor;
Statistical module is used to add up the loading condition of described logical block;
Adjusting module is used for the home control device according to the described loading condition adjustment logical block of described statistical module counts.
10. the disposal system of a business datum is characterized in that, comprising:
Application server is deployed with multi-path software, and described application server is used for issuing inputoutput data to memory device;
Memory device, be used for the inputoutput data of the logical block of the storage system of described application server correspondence being sampled according to default sampling policy, the described sample information of obtaining is analyzed, generate the store configuration information of described logical block according to the described analysis result information that obtains, and described storage system is configured according to described store configuration information, and under the storage system of described store configuration information configuration, the business datum of described application server is carried out stores processor, add up the loading condition of described logical block, adjust the home control device of logical block according to described loading condition, wherein, described logical block is the inputoutput data of an application server employed logical block when storing on storage system.
CN2009100915014A 2009-08-24 2009-08-24 Method and system for processing business data as well as storing device and application server Active CN101630236B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN2009100915014A CN101630236B (en) 2009-08-24 2009-08-24 Method and system for processing business data as well as storing device and application server

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN2009100915014A CN101630236B (en) 2009-08-24 2009-08-24 Method and system for processing business data as well as storing device and application server

Publications (2)

Publication Number Publication Date
CN101630236A CN101630236A (en) 2010-01-20
CN101630236B true CN101630236B (en) 2011-11-09

Family

ID=41575357

Family Applications (1)

Application Number Title Priority Date Filing Date
CN2009100915014A Active CN101630236B (en) 2009-08-24 2009-08-24 Method and system for processing business data as well as storing device and application server

Country Status (1)

Country Link
CN (1) CN101630236B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103095784B (en) * 2011-11-08 2016-04-20 北京捷通华声科技股份有限公司 A kind of cloud user mapped system and method
CN104346353A (en) * 2013-07-29 2015-02-11 国际商业机器公司 Method and system for asynchronous access
CN106686082B (en) * 2016-12-29 2020-09-11 华为技术有限公司 Storage resource adjusting method and management node
CN107861691B (en) * 2017-11-22 2021-04-27 北京腾凌科技有限公司 Load balancing method and device of multi-control storage system
CN111538987B (en) * 2020-04-26 2022-02-01 浙江荃润信息技术有限公司 Information security storage system based on big data

Also Published As

Publication number Publication date
CN101630236A (en) 2010-01-20

Similar Documents

Publication Publication Date Title
US9436389B2 (en) Management of shared storage I/O resources
CN102770848B (en) The dynamic management of the task that produces in memory controller
US8738975B2 (en) Runtime dynamic performance skew elimination
US7415582B2 (en) Storage system construction managing device and construction management method
EP1768014B1 (en) Storage control apparatus, data management system and data management method
US7594083B2 (en) Storage system and storage control device
EP1657630A1 (en) Storage device and storage device data life cycle control method
US20080301332A1 (en) Method for using host and storage controller port information to configure paths between a host and storage controller
CN103250143A (en) Data storage method and storage device
US7702962B2 (en) Storage system and a method for dissolving fault of a storage system
US8250257B1 (en) Techniques for balancing system I/O load
CN102609215B (en) Data processing method and device
CN101393536A (en) Storage system
CN101630236B (en) Method and system for processing business data as well as storing device and application server
US7188166B2 (en) Storage system, storage control device, and control method for storage system
JP6955159B2 (en) Storage systems, storage controllers and programs
US20070266218A1 (en) Storage system and storage control method for the same
US9747040B1 (en) Method and system for machine learning for write command selection based on technology feedback
US9298493B1 (en) Managing system I/O load
Lumb et al. D-SPTF: Decentralized request distribution in brick-based storage systems
US7958324B2 (en) Computer system and command execution frequency control method
US20090006738A1 (en) Host adaptive seek technique environment
US9135191B1 (en) Techniques for storage network bandwidth management
US7418530B2 (en) Storage device and method for controlling storage device packet size
US20060112301A1 (en) Method and computer program product to improve I/O performance and control I/O latency in a redundant array

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
C56 Change in the name or address of the patentee

Owner name: HUAWEI DIGITAL TECHNOLOGY (CHENGDU) CO., LTD.

Free format text: FORMER NAME: CHENGDU HUAWEI SYMANTEC TECHNOLOGIES CO., LTD.

CP01 Change in the name or title of a patent holder

Address after: 611731 Chengdu high tech Zone, Sichuan, West Park, Qingshui River

Patentee after: HUAWEI DIGITAL TECHNOLOGIES (CHENG DU) Co.,Ltd.

Address before: 611731 Chengdu high tech Zone, Sichuan, West Park, Qingshui River

Patentee before: CHENGDU HUAWEI SYMANTEC TECHNOLOGIES Co.,Ltd.

TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20220907

Address after: No. 1899 Xiyuan Avenue, high tech Zone (West District), Chengdu, Sichuan 610041

Patentee after: Chengdu Huawei Technologies Co.,Ltd.

Address before: 611731 Qingshui River District, Chengdu hi tech Zone, Sichuan, China

Patentee before: HUAWEI DIGITAL TECHNOLOGIES (CHENG DU) Co.,Ltd.