CN106843906A - The method and server of a kind of adjustment system page-size - Google Patents
The method and server of a kind of adjustment system page-size Download PDFInfo
- Publication number
- CN106843906A CN106843906A CN201710098007.5A CN201710098007A CN106843906A CN 106843906 A CN106843906 A CN 106843906A CN 201710098007 A CN201710098007 A CN 201710098007A CN 106843906 A CN106843906 A CN 106843906A
- Authority
- CN
- China
- Prior art keywords
- page
- size
- application program
- distribution
- big
- 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
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000009826 distribution Methods 0.000 claims abstract description 50
- 238000012544 monitoring process Methods 0.000 claims abstract description 50
- 230000008569 process Effects 0.000 claims description 25
- 230000004048 modification Effects 0.000 claims description 15
- 238000012986 modification Methods 0.000 claims description 15
- 239000003550 marker Substances 0.000 claims description 13
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 3
- 238000003860 storage Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013519 translation Methods 0.000 description 3
- 230000014616 translation Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/451—Execution arrangements for user interfaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5011—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals
- G06F9/5016—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals the resource being the memory
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Memory System Of A Hierarchy Structure (AREA)
Abstract
The embodiment of the invention discloses the method and server of a kind of adjustment system page-size, system page-size is set for dynamic, improves the performance of server.Present invention method includes:If application program runtime system page-size is system default value, page monitoring mark is set, the page monitoring mark is for monitoring page faults number of times;Determine that the application program has the big memory requirements of distribution;Mark is monitored according to the page to judge whether to meet the preset condition for distributing big internal memory;If so, then changing the system page-size.The embodiment of the present invention additionally provides a kind of server, and the embodiment of the present invention can dynamically set system page-size, improve the performance of server.
Description
Technical field
The present invention relates to server field, and in particular to the method and server of a kind of adjustment system page-size.
Background technology
With the continuous increase for calculating demand size, application program is also increasing to the demand of internal memory.
In order to realize virtual memory management mechanism, operating system carries out paging management to internal memory.From internal memory " Paging system "
The beginning of proposition, the default size of memory pages is just arranged to 4096 bytes, i.e. 4KB, although memory pages size is in principle
Configurable, but most of operating system is still using the 4KB pages of acquiescence.
The page of 4KB sizes is rational when " Paging system " is proposed, because memory size at that time is only several
Ten Mbytes, then when physical memory capacity rises to several G even tens G, page-size remains 4KB.For example exist
On (SuSE) Linux OS during the larger application program of running memory demand, because its default page size for using is 4KB,
Page can be a lot, and the array of managing internal memory page can consume internal memory, while translation lookahead or look-aside buffer than larger
The size of (Translation Lookside Buffera, TLB) is fixed, thus can produce more TLB Miss and skip leaf
Interrupt, so as to largely effect on the performance of application program.
The content of the invention
The method and server of a kind of adjustment system page-size are the embodiment of the invention provides, system is set for dynamic
System page-size, improves the performance of server.
On the one hand the embodiment of the present invention provides a kind of method of adjustment system page-size, specifically includes:
If application program runtime system page-size is system default value, page monitoring mark, the page monitoring are set
Indicate for monitoring page faults number of times;
Determine that the application program has the big memory requirements of distribution;
Mark is monitored according to the page to judge whether to meet the preset condition for distributing big internal memory;
If so, then changing the system page-size.
On the other hand the embodiment of the present invention provides a kind of server, specifically includes:
Setting unit, if application program runtime system page-size is system default value, for setting page monitoring mark
Will, the page monitoring mark is for monitoring page faults number of times;
Determining unit, for determining that the application program has the big memory requirements of distribution;
Judging unit, judges whether to meet the preset condition for distributing big internal memory for monitoring mark according to the page;
Modification unit, if so, being then used to change the system page-size.
As can be seen from the above technical solutions, the embodiment of the present invention has advantages below:If application program runtime system
Page-size is system default value, then set page monitoring mark, and the page monitoring mark is for monitoring page faults number of times;It is true again
The fixed application program has the big memory requirements of distribution;Determine that application program has after the big memory requirements of distribution to be monitored according to the page to mark
Will judges whether the condition of the big internal memory of distribution for meeting preset;If meeting the condition of the preset big internal memory of distribution, modification is described
System page-size.In the embodiment of the present invention, system page-size is then changed when the condition of the preset big internal memory of distribution is met,
Dynamic sets page-size, improves the performance of server.
Brief description of the drawings
Fig. 1 is a Paging system schematic diagram in the embodiment of the present invention;
Fig. 2 is method one embodiment schematic diagram of adjustment system page-size in the embodiment of the present invention;
Fig. 3 .1 are another embodiment schematic diagram of method of adjustment system page-size in the embodiment of the present invention;
Fig. 3 .2 are a TLB caching schematic diagram in the embodiment of the present invention;
Fig. 4 is one embodiment schematic diagram of server in the embodiment of the present invention;
Fig. 5 is another embodiment schematic diagram of server in the embodiment of the present invention;
Fig. 6 is another embodiment schematic diagram of server in the embodiment of the present invention.
Specific embodiment
A kind of method of adjustment system page-size is the embodiment of the invention provides, it is big to set the system page for dynamic
It is small, improve the performance of server.
In order that those skilled in the art more fully understand the present invention program, below in conjunction with the embodiment of the present invention
Accompanying drawing, is clearly and completely described to the technical scheme in the embodiment of the present invention, it is clear that described embodiment is only
The embodiment of a part of the invention, rather than whole embodiments.Based on the embodiment in the present invention, ordinary skill people
The every other embodiment that member is obtained under the premise of creative work is not made, should all belong to the model of present invention protection
Enclose.
Term " first ", " second ", " the 3rd ", " in description and claims of this specification and above-mentioned accompanying drawing
Four " etc. (if present) is for distinguishing similar object, without for describing specific order or precedence.Should manage
The data that solution is so used can be exchanged in the appropriate case, so that the embodiments described herein can be with except illustrating herein
Or the order beyond the content of description is implemented.Additionally, term " including " or " having " and its any deformation, it is intended that covering is not
Exclusive includes, for example, the process, method, system, product or the equipment that contain series of steps or unit be not necessarily limited to it is clear
Those steps for listing or unit, but may include not list clearly or for these processes, method, product or set
Standby intrinsic other steps or unit.
In storage allocation, due to the indefinite length of section, it may occur that the clear area in internal memory is less than small loading
Section, or clear area is far longer than the section to be loaded.In the previous case, it is necessary to find suitable clear area in addition;
In the case of the latter, distribution can succeed, but too waste.In view of this, introduce Paging system and complete virtual address to thing
Manage the process of address conversion.It is as shown in Figure 1 Paging system schematic diagram, the linear address that processor is produced is virtual address, its
Middle linear address includes catalogue, the page and page bias internal.Cr3 registers specify the physical address of page directory, page directory to specify institute
There is the physical address of page table, and each page table indicates the physical address of included page, by page directory entry and page table entry
Conversion, gets the page of operating system access.
For ease of understanding, the idiographic flow in the embodiment of the present invention is described below, refers to Fig. 2, the present invention is real
A kind of method one embodiment of adjustment system page-size includes in applying example:
The 201st, page monitoring mark is set;
When application program is run, if application program uses system default value as system page-size, page is set
Monitoring mark, for monitoring page faults number of times, wherein page faults are the operating system page to be accessed to page monitoring mark
Do not conducted interviews again after hosting, it is necessary to operating system is called in main memory.
202nd, determine that application program has the big memory requirements of distribution;
After page monitoring mark is set, it is considered to the characteristics of application program big memory requirements, determine that application program has distribution imperial palace
Deposit demand.
203rd, monitor mark according to page to judge whether to meet the preset condition for distributing big internal memory, if so, then performing step
204;
After determining application program and having the big memory requirements of distribution, mark is monitored according to page and judges whether to meet preset distribution big
The condition of internal memory, if so, meeting the condition of the preset big internal memory of distribution, then performs step 204, if it is not, then performing step
205。
204th, system page-size is changed;
After the condition of the big internal memory of distribution for determining to meet preset according to page monitoring mark, system page-size is changed.
205th, other steps are performed.
After the condition of the big internal memory of distribution for determining to be unsatisfactory for preset according to page monitoring mark, run with default interface size
The process that application program is operationally generated.
In the embodiment of the present invention, if application program runtime system page-size is system default value, page monitoring is set
Mark, the page monitoring mark is for monitoring page faults number of times;Determine that the application program has the big memory requirements of distribution again;Really
Determine application program and have after the big memory requirements of distribution to monitor mark according to the page and judge whether to meet the preset big internal memory of distribution
Condition;If meeting the condition of the preset big internal memory of distribution, the system page-size is changed.In the embodiment of the present invention, when full
System page-size is then changed during the condition of the preset big internal memory of distribution of foot, dynamic sets page-size, improves server
Performance.
For ease of understanding, below to the embodiment of the present invention in a kind of method of adjustment system page-size retouched in detail
State, specific to refer to Fig. 3 .1 as shown in Fig. 3 .1, the method bag of another adjustment system page-size in the embodiment of the present invention
Include:
301st, process is created;
302nd, judge whether to set page-size, if so, then performing step 303;If it is not, then performing step 304;
Application program run when generate process, in process creation, application program can according to big memory requirements the characteristics of
Page-size or the page-size using system default, such as 4KB are directly set.
Server judge current page-size whether be system default page-size, if the page of system default is big
Small, then application program is not provided with page-size, that is, perform step 304;If server judgement is not the page-size of system default,
Then perform step 303.
303rd, process is run with the page-size;
If server judges that the current page-size of application program is not that the page-size of system default, i.e. application program set
Page-size is put, then process is run with the page-size.
The 304th, page monitoring mark is set;
If server judges that the current page-size of application program is the page-size of system default, wherein, system default
Page-size be generally 4KB, then the interface of the settable process of server monitors mark using page.When the page monitors flag set
When, can monitoring process trigger page faults occur the frequency.
305th, judge whether the value of each page table effective marker position is all 1, if so, then performing step 306;If it is not, then performing
Step 307;
During by Paging system completion virtual address to physical address translations, each in page table has a page
Table effective marker position, if the value of page table effective marker position is 0, it is invalid to represent, i.e. not in internal memory, processor needs to visit page data
Ask data storage device;If the value of page table effective marker position is 1, represent effective, i.e., in internal memory, processor can be direct for page data
Access.The value that server passes through each page table effective marker position in the corresponding page table entry of virtual memory for judging application program operation
Whether it is all 1 to determine whether application program has the big memory requirements of distribution, if so, then performing step 306;If it is not, then performing step
Rapid 307.
306th, determine that application program has the big memory requirements of distribution;
If the value of each page table effective marker position in the corresponding page table entry of virtual memory of application program operation is all 1,
Server determines that application program has the big memory requirements of distribution.
307th, process is run with default page size;
If the value of each page table effective marker position in the corresponding page table entry of virtual memory of application program operation is not all 1,
Then server judges that application program does not distribute big memory requirements, will application program when running the process that generates with default page
Size is run.
308th, the number of times of Sentinel surveillance page faults is monitored by page;
When page monitors flag bit set, server monitors the number of times that Sentinel surveillance obtains page faults by this page, with
Number of times according to the page faults determines whether the situation of page faults is frequent.
309th, whether the number of times of page monitoring Mark Detection page faults is judged more than the first preset value, if so, then performing step
Rapid 310;If it is not, then performing step 311;
After page monitors the number of times that Sentinel surveillance obtains page faults, server judges whether the number of times of page faults is big
In default first preset value, if being more than, step 310 is performed, if being less than, perform step 311.
310th, determine to meet the preset condition for distributing big internal memory;
If server judges the number of times of page faults more than default first preset value, server thinks that page faults are sent out
Raw number of times frequently, that is, meets the condition of the preset big internal memory of distribution.
It should be noted that in practical application, when server judges that TLB occurs to be shaken, also can determine that and meet preset
Distribute the condition of big internal memory.As shown in Figure 3 .2, to accelerate conversion of the virtual address to physical address, processor is using smaller more
Fast TLB cachings, the list item that the part in housing page table in TLB cachings accesses recently.If it is virtual that processor is accessed
When address realm is very wide, TLB does not have the virtual address, then the list item in the middle of a page table at a slow speed can be produced to copy to
The process of TLB cachings, if the number of times that the process occurs is more than the second preset value, then it is assumed that TLB shakes occur.Therefore, it is preset
The content that is included of condition of the big internal memory of distribution do not limit herein specifically.
311st, process is run with default page size;
In the embodiment of the present invention, step 311 is similar with step 307, and specific here is omitted.
312nd, the page size in allocated big internal memory page table entry and modification page directory entry is merged;
After server determines the condition of the big internal memory of distribution for meeting preset, allocated big internal memory page table entry is merged
Treatment, and the page in page directory entry is dimensioned to the big page so that follow-up big Memory Allocation uses the big page.
The 313rd, system page-size is set.
Server modifies the page-size of acquiescence, is allowed to meet the demand of the big internal memory of application program.It is appreciated that
, the value of amended system page-size is the index times of 2KB, such as 512KB, or 1MB etc., is not limited herein specifically
It is fixed.
It should be noted that server adds page table entry process in being cached by the number of times or TLB of page faults is sent out
Raw number of times judges whether to meet the condition of the preset big internal memory of distribution, in practical application, can divide scarce by being classified
The number of times or TLB that page is interrupted add the number of times that the process of page table entry occurs in caching, for example, judging the number of times of page faults
When, if the number of times is more than the first preset value, less than the 3rd preset value, then the value of corresponding modification system page-size is A, if should
Number of times is more than the 3rd preset value, and less than the 4th preset value, then the value of corresponding modification system page-size is B, if the number of times is big
In the 4th preset value, then the value of corresponding modification system page-size is C.Therefore, set system page-size mode it is specific this
Place does not limit.
In the embodiment of the present invention, if application program runtime system page-size is system default value, page monitoring is set
Mark, the page monitoring mark is for monitoring page faults number of times;Determine that the application program has the big memory requirements of distribution again;Really
Determine application program and have after the big memory requirements of distribution to monitor mark according to the page and judge whether to meet the preset big internal memory of distribution
Condition;If meeting the condition of the preset big internal memory of distribution, the system page-size is changed.In the embodiment of the present invention, when full
System page-size is then changed during the condition of the preset big internal memory of distribution of foot, dynamic sets page-size, improves server
Performance.
The method to the adjustment system page-size in the embodiment of the present invention is described above, below to of the invention real
The server applied in example is described, and refers to Fig. 4, and the server in the embodiment of the present invention includes:
Setting unit 401, if application program runtime system page-size is system default value, for setting page monitoring
Mark, page monitoring mark is for monitoring page faults number of times;
Determining unit 402, for determining that application program has the big memory requirements of distribution;
Judging unit 403, judges whether to meet the preset condition for distributing big internal memory for monitoring mark according to page;
Modification unit 404, if so, being then used to change system page-size.
In the embodiment of the present invention, if application program runtime system page-size is system default value, setting unit sets
Page monitoring mark is put, page monitoring mark is for monitoring page faults number of times;Determining unit determines that application program has distribution imperial palace again
Deposit demand;Determine that application program has after the big memory requirements of distribution to monitor mark according to the page and judge whether to meet preset distribution
The condition of big internal memory;If meeting the condition of the preset big internal memory of distribution, modification unit modification system page-size.It is of the invention real
Apply in example, system page-size is then changed when the condition of the preset big internal memory of distribution is met, dynamic sets page-size, improves
The performance of server.
For ease of understanding, the server in the embodiment of the present invention is described in detail below, the basis shown in above-mentioned Fig. 4
On, 5 are referred to, it is another embodiment schematic diagram of server in the embodiment of the present invention, determining unit 502 can include:
Whether the first judge module 5021, the value for judging each page table effective marker position is all 1, page table effective marker position
It is contained in the corresponding page table entry of the virtual memory of application program;
First determining module 5022, if so, being then used to determine that application program has the big memory requirements of distribution.
Wherein, judging unit 503 can include:
Monitoring modular 5031, the number of times for monitoring Sentinel surveillance page faults by page;
Second judge module 5032, for judging the number of times of page faults whether more than the first preset value;
Second determining module 5033, if so, being then used to determine to meet the preset condition for distributing big internal memory;
Wherein, monitoring modular 5031, can be also used for monitoring the process of addition page table entry in back of the body buffer TLB after conversion
The number of times of generation;
Second judging unit 5032, can be also used for judging the number of times that the process for adding page table entry in TLB occurs
Whether the second preset value is more than;
Second determining module 5033, if can be also used for, it is determined that meet the condition of the preset big internal memory of distribution.
And, modification unit 504 also includes:
Merging module 5041, for merging allocated big internal memory page table entry and changing the page size in page directory entry;
Setup module 5042, for setting system page-size.
In the embodiment of the present invention, server also includes:
Setup unit 505, for setting system page-size when application program is run.
The angle of above-mentioned Fig. 4 to Fig. 5 slave modules functional entity is retouched in detail to the server in the embodiment of the present invention
State, the server in the embodiment of the present invention is described in detail from the angle of hardware handles below, refer to Fig. 6.Fig. 6 is this
A kind of server that inventive embodiments are provided, the server 600 can be because of configuration or performance is different and the larger difference of producing ratio, can
With including one or more central processing units (central processing units, CPU) 622 (for example, one or one
Individual above processor) and memory 632, one or more store the storage medium 630 of application programs 642 or data 644
(such as one or more mass memory units).Wherein, memory 632 and storage medium 630 can be it is of short duration storage or
Persistently storage.The program stored in storage medium 630 can include one or more modules (diagram is not marked), each mould
Block can be included to the series of instructions operation in server.Further, central processing unit 622 could be arranged to and storage
Medium 630 is communicated, and the series of instructions operation in storage medium 630 is performed in opening device 600.
Server 600 can also include one or more power supplys 626, one or more wired or wireless networks
Interface 650, one or more input/output interfaces 658, and/or, one or more operating systems 641, for example
Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM etc..
Step in above-described embodiment as performed by server can be based on the server architecture shown in the Fig. 6.
It is apparent to those skilled in the art that, for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, may be referred to the corresponding process in preceding method embodiment, will not be repeated here.
In several embodiments provided herein, it should be understood that disclosed system, apparatus and method can be with
Realize by another way.For example, device embodiment described above is only schematical, for example, the unit
Divide, only a kind of division of logic function there can be other dividing mode when actually realizing, for example multiple units or component
Can combine or be desirably integrated into another system, or some features can be ignored, or do not perform.It is another, it is shown or
The coupling each other for discussing or direct-coupling or communication connection can be the indirect couplings of device or unit by some interfaces
Close or communicate to connect, can be electrical, mechanical or other forms.
The unit that is illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part for showing can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be according to the actual needs selected to realize the mesh of this embodiment scheme
's.
In addition, during each functional unit in each embodiment of the invention can be integrated in a processing unit, it is also possible to
It is that unit is individually physically present, it is also possible to which two or more units are integrated in a unit.Above-mentioned integrated list
Unit can both be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.
If the integrated unit is to realize in the form of SFU software functional unit and as independent production marketing or use
When, can store in a computer read/write memory medium.Based on such understanding, technical scheme is substantially
The part for being contributed to prior art in other words or all or part of the technical scheme can be in the form of software products
Embody, the computer software product is stored in a storage medium, including some instructions are used to so that a computer
Equipment (can be personal computer, server, or network equipment etc.) performs the complete of each embodiment methods described of the invention
Portion or part steps.And foregoing storage medium includes:USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), magnetic disc or CD etc. are various can store journey
The medium of sequence code.
The above, the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although with reference to preceding
Embodiment is stated to be described in detail the present invention, it will be understood by those within the art that:It still can be to preceding
State the technical scheme described in each embodiment to modify, or equivalent is carried out to which part technical characteristic;And these
Modification is replaced, and does not make the spirit and scope of the essence disengaging various embodiments of the present invention technical scheme of appropriate technical solution.
Claims (10)
1. a kind of method of adjustment system page-size, it is characterised in that including:
If application program runtime system page-size is system default value, page monitoring mark, the page monitoring mark are set
For monitoring page faults number of times;
Determine that the application program has the big memory requirements of distribution;
Mark is monitored according to the page to judge whether to meet the preset condition for distributing big internal memory;
If so, then changing the system page-size.
2. method according to claim 1, it is characterised in that determine that the application program has the big memory requirements bag of distribution
Include:
Judge whether the value of each page table effective marker position is all 1, the page table effective marker position is contained in the application program
In the corresponding page table entry of virtual memory;
If, it is determined that the application program has the big memory requirements of distribution.
3. method according to claim 1, it is characterised in that mark is monitored according to the page and judges whether to meet preset
The condition for distributing big internal memory includes:
The number of times of Sentinel surveillance page faults is monitored by the page;
Judge the number of times of the page faults whether more than the first preset value;
If, it is determined that meet the condition of the preset big internal memory of distribution;Or,
It is determined that the number of times that the process of page table entry occurs is added in back of the body buffer TLB after conversion;
Judge whether the number of times that the process that page table entry is added in TLB occurs is more than the second preset value;
If, it is determined that meet the condition of the preset big internal memory of distribution.
4. method according to claim 1, it is characterised in that the modification system page-size includes:
Merge the page size in allocated big internal memory page table entry and modification page directory entry;
The system page-size is set.
5. method according to any one of claim 1 to 4, it is characterised in that if described in when the application program is run
System page-size is not system default value, and methods described also includes:
The system page-size is set when the application program is run.
6. a kind of server, it is characterised in that including:
Setting unit, if application program runtime system page-size is system default value, for setting page monitoring mark, institute
Page monitoring mark is stated for monitoring page faults number of times;
Determining unit, for determining that the application program has the big memory requirements of distribution;
Judging unit, judges whether to meet the preset condition for distributing big internal memory for monitoring mark according to the page;
Modification unit, if so, being then used to change the system page-size.
7. server according to claim 6, it is characterised in that the determining unit includes:
Whether the first judge module, the value for judging each page table effective marker position is all 1, and the page table effective marker position includes
In the corresponding page table entry of virtual memory of the application program;
First determining module, if so, being then used to determine that the application program has the big memory requirements of distribution.
8. server according to claim 6, it is characterised in that the judging unit includes:
Monitoring modular, the number of times for monitoring Sentinel surveillance page faults by the page;
Second judge module, for judging the number of times of the page faults whether more than the first preset value;
Second determining module, if so, being then used for the condition for determining to meet the preset big internal memory of distribution;Or,
The monitoring modular adds the number of times that the process of page table entry occurs in being additionally operable to monitor back of the body buffer TLB after conversion;
Whether second judge module is additionally operable to judge number of times that the process that page table entry is added in TLB occurs more than the
Two preset values;
If so, then second determining module is additionally operable to the condition for determining to meet the preset big internal memory of distribution.
9. server according to claim 6, it is characterised in that the modification unit includes:
Merging module, for merging allocated big internal memory page table entry and changing the page size in page directory entry;
Setup module, for setting the system page-size.
10. the server according to any one of claim 6 to 9, it is characterised in that the server also includes:
Setup unit, for setting the system page-size when the application program is run.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710098007.5A CN106843906B (en) | 2017-02-22 | 2017-02-22 | Method and server for adjusting system page size |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710098007.5A CN106843906B (en) | 2017-02-22 | 2017-02-22 | Method and server for adjusting system page size |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106843906A true CN106843906A (en) | 2017-06-13 |
CN106843906B CN106843906B (en) | 2021-02-02 |
Family
ID=59135009
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710098007.5A Active CN106843906B (en) | 2017-02-22 | 2017-02-22 | Method and server for adjusting system page size |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106843906B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110955495A (en) * | 2019-11-26 | 2020-04-03 | 网易(杭州)网络有限公司 | Management method, device and storage medium of virtualized memory |
CN111382087A (en) * | 2018-12-28 | 2020-07-07 | 华为技术有限公司 | Memory management method and electronic equipment |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120246436A1 (en) * | 2011-03-21 | 2012-09-27 | Microsoft Corporation | Combining memory pages having identical content |
CN103984599A (en) * | 2014-04-14 | 2014-08-13 | 北京大学 | Method for improving utilization rate of large pages of operating system |
CN105159838A (en) * | 2015-08-27 | 2015-12-16 | 华为技术有限公司 | Memory access method and computer system |
-
2017
- 2017-02-22 CN CN201710098007.5A patent/CN106843906B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120246436A1 (en) * | 2011-03-21 | 2012-09-27 | Microsoft Corporation | Combining memory pages having identical content |
CN103984599A (en) * | 2014-04-14 | 2014-08-13 | 北京大学 | Method for improving utilization rate of large pages of operating system |
CN105159838A (en) * | 2015-08-27 | 2015-12-16 | 华为技术有限公司 | Memory access method and computer system |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111382087A (en) * | 2018-12-28 | 2020-07-07 | 华为技术有限公司 | Memory management method and electronic equipment |
CN110955495A (en) * | 2019-11-26 | 2020-04-03 | 网易(杭州)网络有限公司 | Management method, device and storage medium of virtualized memory |
CN110955495B (en) * | 2019-11-26 | 2022-08-05 | 网易(杭州)网络有限公司 | Management method, device and storage medium of virtualized memory |
Also Published As
Publication number | Publication date |
---|---|
CN106843906B (en) | 2021-02-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Dahlin et al. | Cooperative caching: Using remote client memory to improve file system performance | |
CN107636625A (en) | Method and apparatus for the virtualization control of shared system cache | |
CN113906399B (en) | Connection bandwidth based throttling of memory as a service | |
CN108509014B (en) | Computing device and method of distributing power to multiple cores in each computing device | |
CN1327196A (en) | Information processing system and distribution method of storage device | |
CN102985910A (en) | GPU support for garbage collection | |
US6925546B2 (en) | Memory pool configuration system | |
CN105335308B (en) | To access information treating method and apparatus, the system of storage device | |
CN103631537B (en) | The management method of a kind of virtual disk and device | |
US11126553B2 (en) | Dynamic allocation of memory between containers | |
WO2017181895A1 (en) | Cache-coherence management method and node controller | |
Smolyar et al. | Ioctopus: Outsmarting nonuniform dma | |
CN106843906A (en) | The method and server of a kind of adjustment system page-size | |
US11928061B2 (en) | Cache management method and apparatus | |
CN113994313A (en) | Memory as a service based distributed computing | |
Wang et al. | Rerec: In-reram acceleration with access-aware mapping for personalized recommendation | |
CN115904212A (en) | Data processing method and device, processor and hybrid memory system | |
Akbari Bengar et al. | A page replacement algorithm based on a fuzzy approach to improve cache memory performance | |
CN113906396A (en) | Memory Management Unit (MMU) for accessing borrowed memory | |
US11593273B2 (en) | Management of cache use requests sent to remote cache devices | |
Bender et al. | Paging and the address-translation problem | |
CN104461941A (en) | Memory system structure and management method | |
WO2023000696A1 (en) | Resource allocation method and device | |
CN109690501A (en) | Mixed design/output correlation write-in | |
CN114675959A (en) | Memory recovery method and related device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20201229 Address after: Building 9, No.1, guanpu Road, Guoxiang street, Wuzhong Economic Development Zone, Wuzhong District, Suzhou City, Jiangsu Province Applicant after: SUZHOU LANGCHAO INTELLIGENT TECHNOLOGY Co.,Ltd. Address before: Room 1601, floor 16, 278 Xinyi Road, Zhengdong New District, Zhengzhou City, Henan Province Applicant before: ZHENGZHOU YUNHAI INFORMATION TECHNOLOGY Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |