CN104216758A - Read and write operation performance optimization method and device - Google Patents
Read and write operation performance optimization method and device Download PDFInfo
- Publication number
- CN104216758A CN104216758A CN201410419211.9A CN201410419211A CN104216758A CN 104216758 A CN104216758 A CN 104216758A CN 201410419211 A CN201410419211 A CN 201410419211A CN 104216758 A CN104216758 A CN 104216758A
- Authority
- CN
- China
- Prior art keywords
- virtual machine
- mark
- processor
- read
- module
- 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
Landscapes
- Memory System Of A Hierarchy Structure (AREA)
Abstract
The invention discloses a read and write operation performance optimization method and a device. The method comprises receiving a read and write request sent by a processor in a processor cluster, which comprises the identification of the processor, querying a configuration table by taking the identification of the processor as a basis, so as to obtain an identification of a virtual machine operated by the processor currently, which comprises a mapping relation between the identification of the processor and the identification of the virtual machine operated by the processor currently, sending the identification of the virtual machine to equipment, and performing performance optimization processing on read and write operation according to the identification of the virtual machine operated by the processor currently. By adopting the scheme, the identification of the virtual machine sending the read and write request can be obtained, so as to perform optimization processing on read and write operation according to the identification of the virtual machine.
Description
Technical field
The present invention relates to processor, particularly relate to a kind of read-write operation performance optimization method and device.
Background technology
Intel Virtualization Technology is a very important technology in computer technology, by Intel Virtualization Technology, can run multiple virtual machine on same computer hardware simultaneously, and each virtual machine runs an operating system.Each operating system can run oneself application program independently of each other, makes mutual not perception between operating system.But, when the number ratio of virtual machine is more, different virtual machine will influence each other to the performance that cache buffer (Cache) carries out read-write operation, because Cache needs the read-write requests processing multiple virtual machine simultaneously, and the access of these virtual machines differs from one another.Such as, the size of the application program run in virtual machine A to the distribution of Cache is very sensitive, if be assigned to more Cache for virtual machine A, then the performance of read-write operation that shows of virtual machine A is better; The size of the application program run in virtual machine B to the distribution of Cache is insensitive, even if the Cache distributed for virtual machine B is many again, the read-write operation performance that virtual machine B shows still does not have any change, thus the Cache giving virtual machine B even is on the contrary many, causing the Cache that can distribute to as the virtual machine of this Cache magnitude to distributing of virtual machine A to tail off, having influence on the read-write operation performance of the virtual machine of this Cache magnitude to distributing of picture virtual machine A.
So if can identify virtual machine, the feature of the read-write requests sent according to virtual machine carries out performance optimization process, then can greatly improve the performance of Cache being carried out to read-write operation., in the prior art, can only identify at most read-write requests is that certain processor sends.But on the one hand for small virtual machine, virtual machine may operate in processor 1 in a upper time period, may operate in processor 2 in the next time period, on the other hand, for large-scale virtual machine, virtual machine may operate in multiple processor simultaneously.So it is that prior art cannot identify what send read-write requests for which virtual machine.
Summary of the invention
Embodiment of the present invention technical matters to be solved is, provide a kind of virtual machine sign acquiring method, device and equipment, can know the mark of the virtual machine sending read-write requests, the mark according to virtual machine is optimized read-write operation.
The application's first aspect provides a kind of read-write operation performance optimization method, and described method comprises: receive the read-write requests that the processor that is positioned at processor bunch sends, wherein, described read-write requests contains the mark of described processor; Foundation is designated with described processor, query configuration table is to obtain the mark of the current virtual machine run of described processor, wherein, described allocation list contains the mapping relations of the mark of described processor and the mark of the current virtual machine run of described processor; To the mark sending described virtual machine from equipment, described in making, according to the mark of the described processor current virtual machine run, performance optimization process is carried out to read-write operation from equipment.
In conjunction with first aspect, in the first possible embodiment of the application's first aspect, before receiving the read-write requests that the processor that is positioned at processor bunch sends, described method also comprises: the mark being obtained the current virtual machine run of described processor that described processor sends by operating system; Set up the mapping relations between the mark of described processor and the mark of the current virtual machine run of described processor; Mapping relations between the mark of described processor and the mark of the current virtual machine run of described processor are loaded in allocation list.
In conjunction with first aspect, in the embodiment that the second of the application's first aspect is possible, describedly from equipment, property optimized handling method is carried out to described virtual machine and be specially: obtain according to the mark of described virtual machine described virtual machine to carry out read-write operation rule to cache buffer from equipment by described, and according to described rule before receiving next virtual machine read-write requests, in advance data are got cache buffer.
In conjunction with first aspect, in the third possible embodiment of the application's first aspect, comprise by carrying out performance optimization process from equipment according to the mark of the current virtual machine run of described processor: if run scanning class method in described virtual machine, be then restricted to described virtual machine and distribute cache buffer.
In conjunction with first aspect, in 4th kind of possible embodiment of the application's first aspect, comprise by carrying out performance optimization process from equipment according to the mark of the current virtual machine run of described processor: the described virtual machine that is designated according to described virtual machine distributes road, wherein, described road is a structural units of cache buffer, and at least part of virtual machine is assigned to different described roads respectively.
The application's second aspect provides a kind of read-write operation performance optimization method, described method comprises: the mark receiving the current described virtual machine run of processor that interconnecting module sends, wherein, the mark of described virtual machine is inquired about by described interconnecting module the allocation list be stored in described interconnecting module and is obtained, and described allocation list contains the mapping relations of the mark of described processor and the mark of the current virtual machine run of described processor; Mark according to the current virtual machine run of described processor carries out performance optimization process.
In conjunction with second aspect, in the first possible embodiment of the application's second aspect, mark according to the current virtual machine run of described processor carries out performance optimization process, comprise: obtain according to the mark of described virtual machine described virtual machine to carry out read-write operation rule to cache buffer, and according to described rule before receiving next virtual machine read-write requests, in advance institute's visit data is got cache buffer.
In conjunction with second aspect, in the embodiment that the second of the application's second aspect is possible, mark according to the current virtual machine run of described processor carries out performance optimization process, comprise: if run scanning class method in described virtual machine, be then restricted to described virtual machine and distribute cache buffer.
In conjunction with second aspect, in the third possible embodiment of the application's second aspect, carry out performance optimization process according to the mark of the current virtual machine run of described processor to comprise: the described virtual machine that is designated according to described virtual machine distributes road, wherein, described road is a structural units of cache buffer, and at least part of virtual machine is assigned to different described roads respectively.
The application's third aspect provides a kind of read-write operation performance optimization device, described device comprises: receiver module, enquiry module and sending module, the read-write requests that described receiver module sends for receiving the processor that is positioned at processor bunch, wherein, described read-write requests contains the mark of described processor, and the mark of described processor is sent to described enquiry module by described receiver module; Described enquiry module is for receiving the mark of described processor, foundation is designated with described processor, query configuration table is to obtain the mark of the current virtual machine run of described processor, wherein, described allocation list contains the mapping relations of the mark of described processor and the mark of the current virtual machine run of described processor, and described enquiry module is used for the mark of described virtual machine to send to described sending module; Described sending module, for receiving the mark of described virtual machine, to the mark sending described virtual machine from equipment, carries out performance optimization process according to the mark of the current virtual machine run of described processor to read-write operation from equipment described in making.
In conjunction with the third aspect, in the first possible embodiment of the application's third aspect, described device also comprises: acquisition module, set up module and load-on module, described acquisition module is used for obtaining by operating system the mark of the current virtual machine run of described processor that described processor sends, and the mark of the mark of described processor and described virtual machine sends to by described acquisition module describedly sets up module; Describedly set up the mark of module for the mark and described virtual machine that receive described processor, set up the mapping relations between the mark of described processor and the mark of the current virtual machine run of described processor, described mapping relations are sent to described load-on module by described module of setting up; Mapping relations between the mark of described processor and the mark of the current virtual machine run of described processor, for receiving described mapping relations, are loaded in allocation list by described load-on module.
In conjunction with the third aspect, in the embodiment that the second of the application's third aspect is possible, obtain according to the mark of described virtual machine described virtual machine to carry out read-write operation rule to cache buffer from equipment by described, and according to described rule before receiving next virtual machine read-write requests, in advance institute's visit data is got cache buffer.
In conjunction with the third aspect, in the third possible embodiment of the application's third aspect, if run scanning class method in described virtual machine, then by from device-restrictive being described virtual machine distribution cache buffer.
In conjunction with the third aspect, in 4th kind of possible embodiment of the application's third aspect, road is distributed according to the described virtual machine that is designated of described virtual machine by from equipment, wherein, described road is a structural units of cache buffer, and at least part of virtual machine is assigned to different described roads respectively.
The application's fourth aspect provides a kind of read-write operation performance optimization device, described device comprises: receiver module and optimization module, the mark of the processor current described virtual machine that running of described receiver module for receiving interconnecting module and sending, wherein, the mark of described virtual machine is inquired about by described interconnecting module the allocation list be stored in described interconnecting module and is obtained, described allocation list contains the mapping relations of the mark of described processor and the mark of the current virtual machine run of described processor, the mark of described virtual machine is sent to described optimization module by described receiver module, described optimization module is used for carrying out performance optimization process according to the mark of the current virtual machine run of described processor.
In conjunction with fourth aspect, in the first possible embodiment of the application's fourth aspect, described optimization module also to carry out the rule of read-write operation to cache buffer for obtaining described virtual machine according to the mark of described virtual machine, and according to described rule before receiving next virtual machine read-write requests, in advance institute's visit data is got cache buffer.
In conjunction with fourth aspect, in the embodiment that the second of the application's fourth aspect is possible, when described optimization module also for running scanning class method in described virtual machine, being restricted to described virtual machine and distributing cache buffer.
In conjunction with fourth aspect, in the third possible embodiment of the application's fourth aspect, described optimization module also distributes road for the described virtual machine that is designated according to described virtual machine, wherein, described road is a structural units of cache buffer, and at least part of virtual machine is assigned to different described roads respectively.
In above-mentioned scheme, after receiving the read-write requests that the processor that is positioned at processor bunch sends, according to the identified query allocation list of processor to obtain the mark of the current virtual machine run of processor, then, then according to the mark of the processor current virtual machine run read-write operation is optimized.By implementing the embodiment of the present invention, the mark of the virtual machine sending read-write requests can be known according to query configuration table, know the feature of the read-write requests that virtual machine sends according to the mark of virtual machine, the feature of the read-write requests then sent according to virtual machine is optimized read-write operation.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the process flow diagram of read-write operation performance optimization method one embodiment of the present invention;
Fig. 2 is processor and the Organization Chart from equipment in read-write operation performance optimization method of the present invention;
Fig. 3 is the process flow diagram of another embodiment of read-write operation performance optimization method of the present invention;
Fig. 4 is the process flow diagram of the another embodiment of read-write operation performance optimization method of the present invention;
Fig. 5 is the structural representation of read-write operation performance optimization device one embodiment of the present invention;
Fig. 6 is the structural representation of another embodiment of read-write operation performance optimization device of the present invention;
Fig. 7 is the structural representation of the another embodiment of read-write operation performance optimization device of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
It should be noted that, the term used in embodiments of the present invention is only for the object describing specific embodiment, and not intended to be limiting the present invention." one ", " described " and " being somebody's turn to do " of the singulative used in the embodiment of the present invention and appended claims is also intended to comprise most form, unless context clearly represents other implications.It is also understood that term "and/or" used herein refer to and comprise one or more project of listing be associated any or all may combine.
See the process flow diagram that Fig. 1, Fig. 1 are read-write operation performance optimization method one embodiments of the present invention.The read-write operation performance optimization method of present embodiment comprises:
110: receive the read-write requests that the processor that is positioned at processor bunch sends.
Particularly, see also Fig. 2, as shown in Figure 2 in a multi-processor system, 16 processors are divided into 4 processors bunches of 210,4 processors bunches 210 and are respectively processor bunch Cluster0 ~ Cluster3.Each processor bunches 210 comprises 4 processors, 211,4 processors 211 and is respectively processor CPU0 ~ CPU3.In interconnecting module 220, be each processor bunch 210 generations allocation list 222, so, there are allocation list 0 ~ 3 totally 4 allocation lists 222.The mark of the virtual machine that allocation list 222 is running for the processor 211 recorded in alignment processing device bunches 210.Interconnecting module 220 is also connected from equipment 240 with multiple by system bus 230.Wherein, from equipment 240 can be Cache etc.Processor bunches 210, interconnecting module 220, system bus 230 and be all integrated in same chip from equipment 240.
When the processor 211 in processor bunches 210 will carry out read-write operation to Cache, the processor 211 being positioned at processor bunches 210 outwards will send read-write requests, and wherein, described read-write requests contains the mark of processor 211.The read-write requests that processor 211 sends will receive by interconnecting module 220.
120: be designated foundation with processor, query configuration table is to obtain the mark of the current virtual machine run of processor, and wherein, described allocation list contains the mapping relations of the mark of processor and the mark of the current virtual machine run of processor.
Particularly, interconnecting module 220 is designated foundation with processor 211, and query configuration table 222 is to obtain the mark of the current virtual machine run of processor 211.Such as, processor CPU0 in processor bunch Cluster0 have issued read-write requests, then interconnecting module 220 removes query configuration table 0 according to the mark of the processor CPU0 in processor bunch Cluster0, and obtains the virtual identifying VMID0 of the virtual machine run in the processor CPU0 in processor bunch Cluster0.
130: to the mark sending virtual machine from equipment, make to carry out performance optimization process according to the mark of the current virtual machine run of processor to read-write operation from equipment.
Particularly, after the virtual identifying VMID0 inquiring about the virtual machine run in the processor CPU0 obtained in processor bunch Cluster0, sent to from equipment 240 by system bus 230, make to carry out performance optimization process according to the mark of the current virtual machine run of processor to read-write operation from equipment 240.
Be understandable that, in other implementations, processor bunches 210, interconnecting module 220, system bus 230 and also can not be integrated in same chip from equipment 240, but independently hardware device mutually.
The quantity of the processor in processor bunch can be 1, and can be multiple, the application do concrete restriction yet.
In above-mentioned scheme, after receiving the read-write requests that the processor that is positioned at processor bunch sends, according to the identified query allocation list of processor to obtain the mark of the current virtual machine run of processor, then, then according to the mark of the processor current virtual machine run read-write operation is optimized.By implementing the embodiment of the present invention, the mark of the virtual machine sending read-write requests can be known according to query configuration table, know the feature of the read-write requests that virtual machine sends according to the mark of virtual machine, the feature of the read-write requests then sent according to virtual machine is optimized read-write operation.
See the process flow diagram that Fig. 3, Fig. 3 are another embodiments of read-write operation performance optimization method of the present invention.The read-write operation performance optimization method of present embodiment comprises:
310: create allocation list.
Particularly, please again consult Fig. 2, as shown in Figure 2 in a multi-processor system, 16 processors are divided into 4 processors bunches of 210,4 processors bunches 210 and are respectively processor bunch Cluster0 ~ Cluster3.Each processor bunches 210 comprises 4 processors, 211,4 processors 211 and is respectively processor CPU0 ~ CPU3.In interconnecting module 220, be each processor bunch 210 generations allocation list 222, so, there are allocation list 0 ~ 3 totally 4 allocation lists 222.The mark of the virtual machine that allocation list 222 is running for the processor 211 recorded in alignment processing device bunches 210.Interconnecting module 220 is also connected from equipment 240 with multiple by system bus 230.Wherein, from equipment 240 can be Cache etc.Processor bunches 210, interconnecting module 220, system bus 230 and be all integrated in same chip from equipment 240.
Interconnecting module 220 obtains the mark of the current virtual machine run of processor 211 that processor 211 sends by operating system.Then, interconnecting module 220 sets up the mapping relations between the mark of processor 211 and the mark of the current virtual machine run of processor 211.Finally, the mapping relations between the mark of processor 211 and the mark of the current virtual machine run of processor 211 are loaded in allocation list 222.
Be understandable that, interconnecting module 220 can be each processor bunch 210 generations allocation list 222, also can be multiple processor bunch 210 generations allocation list 222, not do concrete restriction herein.
320: receive the read-write requests that the processor that is positioned at processor bunch sends.
Particularly, when the processor 211 in processor bunches 210 will carry out read-write operation to Cache, the processor 211 being positioned at processor bunches 210 outwards will send read-write requests, and wherein, described read-write requests contains the mark of processor 211.The read-write requests that processor 211 sends will receive by interconnecting module 220.
330: be designated foundation with processor, query configuration table is to obtain the mark of the current virtual machine run of processor, and wherein, described allocation list contains the mapping relations of the mark of processor and the mark of the current virtual machine run of processor.
Particularly, interconnecting module 220 is designated foundation with processor 211, and query configuration table 222 is to obtain the mark of the current virtual machine run of processor 211.Such as, processor CPU0 in processor bunch Cluster0 have issued read-write requests, then interconnecting module 220 removes query configuration table 0 according to the mark of the processor CPU0 in processor bunch Cluster0, and obtains the virtual identifying VMID0 of the virtual machine run in the processor CPU0 in processor bunch Cluster0.
340: to the mark sending virtual machine from equipment, make to carry out performance optimization process according to the mark of the current virtual machine run of processor to read-write operation from equipment.
Particularly, after the virtual identifying VMID0 inquiring about the virtual machine run in the processor CPU0 obtained in processor bunch Cluster0, sent to from equipment 240 by system bus 230, make to carry out performance optimization process according to the mark of the current virtual machine run of processor 211 to read-write operation from equipment 240.Have a variety of according to the mark of the current virtual machine run of processor 211 to the mode that read-write operation carries out performance optimization process from equipment 240, such as, (1) read-write operation rule is carried out by obtaining virtual machine from equipment according to the mark of virtual machine, and according to rule before receiving next virtual machine read-write requests, in advance institute's visit data is got Cache.Such as, virtual identifying be the virtual machine of VMID0 when carrying out read-write operation for carry out read-write operation by even rule to block address, then press even rule to block address 0 from equipment, 2,4,6 carry out read-write operation, and can before next virtual machine read-write requests, be that the data in advance of the address space of 8 gets cache buffer in advance by block address, thus improve the speed of read-write operation.(2) if run scanning class method in virtual machine, because scanning class method is for the first time to after wherein some data blocks carry out read-write operation, seldom again read-write operation is carried out to this data block, so, be restricted to virtual machine and distribute cache buffer, use to other virtual machine to save memory headroom.(3) distribute road (way) by from equipment according to the described virtual machine that is designated of virtual machine, wherein, way is a structural units of cache buffer, and at least part of virtual machine is assigned to different way.When space is enough, each virtual machine can be made to take separately one or more way.But, when insufficient space, multiple virtual machine also can be made to share a way.Such as, virtual machine 1 and virtual machine 2 share way1, and virtual machine 3 and virtual machine 4 share way2.Or virtual machine 1 monopolizes way1, virtual machine 1 and virtual machine 2 share way2, and virtual machine 2 monopolizes way3 etc.
Be understandable that, the quantity of the processor in processor bunch can be 1, and can be multiple, the application do concrete restriction yet.
See the process flow diagram that Fig. 4, Fig. 4 are the another embodiments of read-write operation performance optimization method of the present invention.The read-write operation performance optimization method of present embodiment comprises:
410: the mark receiving the current virtual machine run of processor that interconnecting module sends.Wherein, the mark of virtual machine is inquired about by interconnecting module the allocation list be stored in interconnecting module and is obtained, and allocation list contains the mapping relations of the mark of described processor and the mark of the current virtual machine run of described processor.
Particularly, by the embodiment shown in Fig. 1 and Fig. 3, interconnecting module obtains the mark of the current virtual machine run of processor, and sends to from equipment.From the mark of the current virtual machine run of processor that equipment corresponding reception interconnecting module sends.
420: the mark according to the current virtual machine run of processor carries out performance optimization process.
Particularly, have a variety of according to the mark of the current virtual machine run of processor to the mode that read-write operation carries out performance optimization process from equipment, such as, (1) read-write operation rule is carried out by obtaining virtual machine from equipment according to the mark of virtual machine, and according to rule before receiving next virtual machine read-write requests, in advance data are got Cache.Such as, virtual identifying be the virtual machine of VMID0 when carrying out read-write operation for carry out read-write operation by even rule to block address, then press even rule to block address 0 from equipment, 2,4,6 carry out read-write operation, and can before next virtual machine read-write requests, be that the data in advance of the address space of 8 gets cache buffer in advance by block address, thus improve the speed of read-write operation.(2) if run scanning class method in virtual machine, for the first time to after wherein some data blocks carry out read-write operation, seldom again read-write operation is carried out to this data block, so, be restricted to virtual machine and distribute cache buffer, use to other virtual machine to save memory headroom.(3) distribute road (way) by from equipment according to the described virtual machine that is designated of virtual machine, wherein, way is a structural units of cache buffer, and at least part of virtual machine is assigned to different way.When space is enough, each virtual machine can be made to take separately one or more way.But, when insufficient space, multiple virtual machine also can be made to share a way.Such as, virtual machine 1 and virtual machine 2 share way1, and virtual machine 3 and virtual machine 4 share way2.Or virtual machine 1 monopolizes way1, virtual machine 1 and virtual machine 2 share way2, and virtual machine 2 monopolizes way3 etc.
In above-mentioned scheme, after receiving the read-write requests that the processor that is positioned at processor bunch sends, according to the identified query allocation list of processor to obtain the mark of the current virtual machine run of processor, then, then according to the mark of the processor current virtual machine run read-write operation is optimized.By implementing the embodiment of the present invention, the mark of the virtual machine sending read-write requests can be known according to query configuration table, know the feature of the read-write requests that virtual machine sends according to the mark of virtual machine, the feature of the read-write requests then sent according to virtual machine is optimized read-write operation.
The above-mentioned method illustrating the embodiment of the present invention, below for the ease of implementing the such scheme of the embodiment of the present invention better, correspondingly, is also provided for coordinating the relevant device implementing such scheme below.
Refer to Fig. 5, Fig. 5 is the structural representation of read-write operation performance optimization device one embodiment of the present invention.The read-write operation performance optimization device 500 of present embodiment comprises: receiver module 510, enquiry module 520 and sending module 530.
The read-write requests that described receiver module 510 sends for receiving the processor that is positioned at processor bunch, wherein, described read-write requests contains the mark of described processor, and the mark of described processor is sent to described enquiry module 520 by described receiver module 510.
Described enquiry module 520 is for receiving the mark of described processor, foundation is designated with described processor, query configuration table is to obtain the mark of the current virtual machine run of described processor, wherein, described allocation list contains the mapping relations of the mark of described processor and the mark of the current virtual machine run of described processor, and described enquiry module 520 is for sending to described sending module 530 by the mark of described virtual machine.
Described sending module 530, for receiving the mark of described virtual machine, to the mark sending described virtual machine from equipment, carries out performance optimization process according to the mark of the current virtual machine run of described processor to read-write operation from equipment described in making.
Device shown in Fig. 5 can perform each step of the method shown in Fig. 1, specifically refers to Fig. 1 and associated description, no longer launches to describe herein.
Consult Fig. 6, read-write operation performance optimization device 600 also comprises: acquisition module 540, set up module 550 and load-on module 560.
The mark of the current virtual machine run of described processor that described acquisition module 540 is sent for being obtained described processor by operating system, the mark of the mark of described processor and described virtual machine sends to by described acquisition module 540 describedly sets up module 550.
Describedly set up the mark of module 550 for the mark and described virtual machine that receive described processor, set up the mapping relations between the mark of described processor and the mark of the current virtual machine run of described processor, described mapping relations are sent to described load-on module 560 by described module 550 of setting up.
Mapping relations between the mark of described processor and the mark of the current virtual machine run of described processor, for receiving described mapping relations, are loaded in allocation list by described load-on module 560.
Alternatively, obtain according to the mark of described virtual machine described virtual machine to carry out read-write operation rule to cache buffer from equipment by described, and according to described rule before receiving next virtual machine read-write requests, in advance institute's visit data is got cache buffer.
Alternatively, if run scanning class method in described virtual machine, then by from device-restrictive being described virtual machine distribution cache buffer.
Alternatively, distribute road by from equipment according to the described virtual machine that is designated of described virtual machine, wherein, described road is a structural units of cache buffer, and at least part of virtual machine is assigned to different described roads respectively.
Device shown in Fig. 6 can perform each step of the method shown in Fig. 1 and Fig. 3, specifically refers to Fig. 1, Fig. 3 and associated description, no longer launches to describe herein.
In above-mentioned scheme, after receiving the read-write requests that the processor that is positioned at processor bunch sends, according to the identified query allocation list of processor to obtain the mark of the current virtual machine run of processor, then, then according to the mark of the processor current virtual machine run read-write operation is optimized.By implementing the embodiment of the present invention, the mark of the virtual machine sending read-write requests can be known according to query configuration table, know the feature of the read-write requests that virtual machine sends according to the mark of virtual machine, the feature of the read-write requests then sent according to virtual machine is optimized read-write operation.
Refer to Fig. 7, Fig. 7 is the structural representation of read-write operation performance optimization device one embodiment of the present invention.The read-write operation performance optimization device 700 of present embodiment comprises: receiver module 710 and optimization module 720.
The mark of the processor current described virtual machine that running of described receiver module 710 for receiving interconnecting module and sending, wherein, the mark of described virtual machine is inquired about by described interconnecting module the allocation list be stored in described interconnecting module and is obtained, described allocation list contains the mapping relations of the mark of described processor and the mark of the current virtual machine run of described processor, and the mark of described virtual machine is sent to described optimization module 720 by described receiver module 710.
Described optimization module 720 is for carrying out performance optimization process according to the mark of the current virtual machine run of described processor.
Alternatively, described optimization module 720 also to carry out the rule of read-write operation to cache buffer for obtaining described virtual machine according to the mark of described virtual machine, and according to described rule before receiving next virtual machine read-write requests, in advance data are got cache buffer.
Alternatively, when described optimization module 720 also for running scanning class method in described virtual machine, being restricted to described virtual machine and distributing cache buffer.
Alternatively, described optimization module 720 also distributes road for the described virtual machine that is designated according to described virtual machine, and wherein, described road is a structural units of cache buffer, and at least part of virtual machine is assigned to different described roads respectively.
Device shown in Fig. 7 can perform each step of the method shown in Fig. 4, specifically refers to Fig. 4 and associated description, no longer launches to describe herein.
In above-mentioned scheme, after receiving the read-write requests that the processor that is positioned at processor bunch sends, according to the identified query allocation list of processor to obtain the mark of the current virtual machine run of processor, then, then according to the mark of the processor current virtual machine run read-write operation is optimized.By implementing the embodiment of the present invention, the mark of the virtual machine sending read-write requests can be known according to query configuration table, know the feature of the read-write requests that virtual machine sends according to the mark of virtual machine, the feature of the read-write requests then sent according to virtual machine is optimized read-write operation.
One of ordinary skill in the art will appreciate that all or part of flow process realized in above-described embodiment method, that the hardware that can carry out instruction relevant by computer program has come, described program can be stored in a computer read/write memory medium, this program, when performing, can comprise the flow process of the embodiment as above-mentioned each side method.Wherein, described storage medium can be magnetic disc, CD, read-only store-memory body (Read-Only Memory, ROM) or random store-memory body (Random Access Memory, RAM) etc.
Above disclosedly be only a kind of preferred embodiment of the present invention, certainly the interest field of the present invention can not be limited with this, one of ordinary skill in the art will appreciate that all or part of flow process realizing above-described embodiment, and according to the equivalent variations that the claims in the present invention are done, still belong to the scope that invention is contained.
Claims (18)
1. a read-write operation performance optimization method, is characterized in that, described method comprises:
Receive the read-write requests that the processor that is positioned at processor bunch sends, wherein, described read-write requests contains the mark of described processor;
Foundation is designated with described processor, query configuration table is to obtain the mark of the current virtual machine run of described processor, wherein, described allocation list contains the mapping relations of the mark of described processor and the mark of the current virtual machine run of described processor;
To the mark sending described virtual machine from equipment, described in making, according to the mark of the described processor current virtual machine run, performance optimization process is carried out to read-write operation from equipment.
2. method according to claim 1, is characterized in that, before receiving the read-write requests that the processor that is positioned at processor bunch sends, described method also comprises:
The mark of the current virtual machine run of described processor that described processor sends is obtained by operating system;
Set up the mapping relations between the mark of described processor and the mark of the current virtual machine run of described processor;
Mapping relations between the mark of described processor and the mark of the current virtual machine run of described processor are loaded in allocation list.
3. method according to claim 1, is characterized in that, describedly carries out property optimized handling method from equipment to described virtual machine and is specially:
Obtain according to the mark of described virtual machine described virtual machine to carry out read-write operation rule to cache buffer, and according to described rule before receiving next virtual machine read-write requests, in advance institute's visit data is got cache buffer.
4. method according to claim 1, is characterized in that, comprises by carrying out performance optimization process from equipment according to the mark of the current virtual machine run of described processor:
If run scanning class method in described virtual machine, be then restricted to described virtual machine and distribute cache buffer.
5. method according to claim 1, is characterized in that, comprises by carrying out performance optimization process from equipment according to the mark of the current virtual machine run of described processor:
The described virtual machine that is designated according to described virtual machine distributes road, and wherein, described road is a structural units of cache buffer, and at least part of virtual machine is assigned to different described roads respectively.
6. a read-write operation performance optimization method, is characterized in that, described method comprises:
Receive the mark of the current described virtual machine run of processor that interconnecting module sends, wherein, the mark of described virtual machine is inquired about by described interconnecting module the allocation list be stored in described interconnecting module and is obtained, and described allocation list contains the mapping relations of the mark of described processor and the mark of the current virtual machine run of described processor;
Mark according to the current virtual machine run of described processor carries out performance optimization process.
7. method according to claim 6, is characterized in that, the mark according to the current virtual machine run of described processor carries out performance optimization process, comprising:
Obtain according to the mark of described virtual machine described virtual machine to carry out read-write operation rule to cache buffer, and according to described rule before receiving next virtual machine read-write requests, in advance institute's visit data is got cache buffer.
8. method according to claim 6, is characterized in that, the mark according to the current virtual machine run of described processor carries out performance optimization process, comprising:
If run scanning class method in described virtual machine, be then restricted to described virtual machine and distribute cache buffer.
9. method according to claim 6, is characterized in that, carries out performance optimization process comprise according to the mark of the current virtual machine run of described processor:
The described virtual machine that is designated according to described virtual machine distributes road, and wherein, described road is a structural units of cache buffer, and at least part of virtual machine is assigned to different described roads respectively.
10. a read-write operation performance optimization device, is characterized in that, described device comprises: receiver module, enquiry module and sending module:
The read-write requests that described receiver module sends for receiving the processor that is positioned at processor bunch, wherein, described read-write requests contains the mark of described processor, and the mark of described processor is sent to described enquiry module by described receiver module;
Described enquiry module is for receiving the mark of described processor, foundation is designated with described processor, query configuration table is to obtain the mark of the current virtual machine run of described processor, wherein, described allocation list contains the mapping relations of the mark of described processor and the mark of the current virtual machine run of described processor, and described enquiry module is used for the mark of described virtual machine to send to described sending module;
Described sending module, for receiving the mark of described virtual machine, to the mark sending described virtual machine from equipment, carries out performance optimization process according to the mark of the current virtual machine run of described processor to read-write operation from equipment described in making.
11. devices according to claim 10, is characterized in that, described device also comprises: acquisition module, set up module and load-on module:
Described acquisition module is used for obtaining by operating system the mark of the current virtual machine run of described processor that described processor sends, and the mark of the mark of described processor and described virtual machine sends to by described acquisition module describedly sets up module;
Describedly set up the mark of module for the mark and described virtual machine that receive described processor, set up the mapping relations between the mark of described processor and the mark of the current virtual machine run of described processor, described mapping relations are sent to described load-on module by described module of setting up;
Mapping relations between the mark of described processor and the mark of the current virtual machine run of described processor, for receiving described mapping relations, are loaded in allocation list by described load-on module.
12. devices according to claim 10, is characterized in that,
Obtain according to the mark of described virtual machine described virtual machine to carry out read-write operation rule to cache buffer from equipment by described, and according to described rule before receiving next virtual machine read-write requests, in advance institute's visit data is got cache buffer.
13. devices according to claim 10, is characterized in that, if run scanning class method in described virtual machine, then by from device-restrictive being described virtual machine distribution cache buffer.
14. devices according to claim 10, it is characterized in that, distribute road by from equipment according to the described virtual machine that is designated of described virtual machine, wherein, described road is a structural units of cache buffer, and at least part of virtual machine is assigned to different described roads respectively.
15. 1 kinds of read-write operation performance optimization devices, it is characterized in that, described device comprises: receiver module and optimization module:
The mark of the processor current described virtual machine that running of described receiver module for receiving interconnecting module and sending, wherein, the mark of described virtual machine is inquired about by described interconnecting module the allocation list be stored in described interconnecting module and is obtained, described allocation list contains the mapping relations of the mark of described processor and the mark of the current virtual machine run of described processor, and the mark of described virtual machine is sent to described optimization module by described receiver module;
Described optimization module is used for carrying out performance optimization process according to the mark of the current virtual machine run of described processor.
16. devices according to claim 15, is characterized in that,
Described optimization module also to carry out the rule of read-write operation to cache buffer for obtaining described virtual machine according to the mark of described virtual machine, and according to described rule before receiving next virtual machine read-write requests, in advance institute's visit data is got cache buffer.
17. devices according to claim 15, is characterized in that,
When described optimization module also for running scanning class method in described virtual machine, being restricted to described virtual machine and distributing cache buffer.
18. devices according to claim 15, is characterized in that,
Described optimization module also distributes road for the described virtual machine that is designated according to described virtual machine, and wherein, described road is a structural units of cache buffer, and at least part of virtual machine is assigned to different described roads respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410419211.9A CN104216758B (en) | 2014-08-22 | 2014-08-22 | A kind of read-write operation performance optimization method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410419211.9A CN104216758B (en) | 2014-08-22 | 2014-08-22 | A kind of read-write operation performance optimization method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104216758A true CN104216758A (en) | 2014-12-17 |
| CN104216758B CN104216758B (en) | 2018-05-04 |
Family
ID=52098286
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410419211.9A Active CN104216758B (en) | 2014-08-22 | 2014-08-22 | A kind of read-write operation performance optimization method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104216758B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090077550A1 (en) * | 2007-09-13 | 2009-03-19 | Scott Rhine | Virtual machine schedular with memory access control |
| CN101561769A (en) * | 2009-05-25 | 2009-10-21 | 北京航空航天大学 | Process migration tracking method based on multi-core platform virtual machine |
| CN102483718A (en) * | 2009-08-25 | 2012-05-30 | 国际商业机器公司 | Cache partitioning in virtualized environments |
| CN103902352A (en) * | 2012-12-28 | 2014-07-02 | 华为技术有限公司 | Method and device for acquiring request data in multi-core virtual machine system |
-
2014
- 2014-08-22 CN CN201410419211.9A patent/CN104216758B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090077550A1 (en) * | 2007-09-13 | 2009-03-19 | Scott Rhine | Virtual machine schedular with memory access control |
| CN101561769A (en) * | 2009-05-25 | 2009-10-21 | 北京航空航天大学 | Process migration tracking method based on multi-core platform virtual machine |
| CN102483718A (en) * | 2009-08-25 | 2012-05-30 | 国际商业机器公司 | Cache partitioning in virtualized environments |
| CN103902352A (en) * | 2012-12-28 | 2014-07-02 | 华为技术有限公司 | Method and device for acquiring request data in multi-core virtual machine system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104216758B (en) | 2018-05-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105993009B (en) | The method and apparatus that MSI-X is interrupted are transmitted by computing resource of the non-transparent bridge into PCIe cluster | |
| KR101994021B1 (en) | File manipulation method and apparatus | |
| CN102819497B (en) | A kind of memory allocation method, Apparatus and system | |
| CN105283855B (en) | A kind of addressing method and device | |
| US9430391B2 (en) | Managing coherent memory between an accelerated processing device and a central processing unit | |
| CN102831069B (en) | Internal memory processing method, memory management equipment | |
| US20160232640A1 (en) | Resource management | |
| CN104461958A (en) | Storage resource access method supporting SR-IOV, storage controller and storage equipment | |
| KR20150091663A (en) | System comprising multi channel memory and operating method for the same | |
| CN102053800A (en) | Data access method, message receiving resolver and system | |
| CN102708060A (en) | Method, device and system for accessing image files | |
| CN104636186A (en) | Virtual machine memory management method, physical host, PCIE equipment, configuration method thereof and migration management equipment | |
| US9817754B2 (en) | Flash memory management | |
| CN104169891A (en) | Method and device for accessing memory | |
| CN105335309A (en) | Data transmission method and computer | |
| CN109299190A (en) | The method and device of the metadata dealt with objects in distributed memory system | |
| CN104657224A (en) | Inter-process communication method and device | |
| US10062137B2 (en) | Communication between integrated graphics processing units | |
| CN103488523A (en) | Page access method, page access device and server | |
| CN104407990B (en) | A kind of disk access method and device | |
| US20180157605A1 (en) | Configuration of a memory controller for copy-on-write | |
| CN108615077B (en) | Cache optimization method and device applied to deep learning network | |
| JP2005208999A5 (en) | ||
| CN102521163A (en) | Method and device for replacing directory | |
| CN109992451A (en) | Nonvolatile memory and volatile ram mixed management method and its system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |