CN107766123A - A kind of JVM tunings method - Google Patents
A kind of JVM tunings method Download PDFInfo
- Publication number
- CN107766123A CN107766123A CN201710942079.3A CN201710942079A CN107766123A CN 107766123 A CN107766123 A CN 107766123A CN 201710942079 A CN201710942079 A CN 201710942079A CN 107766123 A CN107766123 A CN 107766123A
- Authority
- CN
- China
- Prior art keywords
- space
- jvm
- new generation
- heap
- information
- 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 52
- 230000015654 memory Effects 0.000 claims abstract description 54
- 238000005457 optimization Methods 0.000 claims abstract description 46
- 230000008569 process Effects 0.000 claims abstract description 26
- 230000009183 running Effects 0.000 claims abstract description 6
- 230000008859 change Effects 0.000 claims description 9
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 230000010429 evolutionary process Effects 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000004088 simulation Methods 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
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
-
- 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
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/45591—Monitoring or debugging support
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Devices For Executing Special Programs (AREA)
Abstract
A kind of JVM tunings method, comprises the following steps：Commending system obtains the process number of destination service, to get corresponding JVM examples；The JVM environment scan tools that system combination JDK environment provides, the spatial information and log information of timing acquisition destination service, the spatial information includes the daily record of JVM garbage reclamations and JVM running log information including JVM heap space, space of new generation, old age for space and forever for memory information, the log information；The information got is stored in database, and mean operation is carried out for space and forever for internal memory to JVM heap space, space of new generation, old age respectively, generates optimum results；The JVM parameters in optimization system are adjusted according to optimum results.The present invention is by by JVM evolutionary process vague generalization, so that the evolutionary process of specialty is become into simple and easy, while reducing a large amount of work of staff.
Description
Technical field
The present invention relates to a kind of computer runtime optimization method, more particularly to a kind of JVM tunings method.
Background technology
In IT services, the mentality of designing of software is converted into program code by programmer using certain programming language, in crowd
In more programming languages, Java language is very important one kind, and java applet is operated on Java Virtual Machine JVM.JVM is Java
Program provides memory management and runtime environment.Under normal circumstances, in order to which the service for allowing a Java language to develop is realized faster
Speed is more stably run, and developer is needed according to JVM parameters are adjusted the characteristics of program, as Memory Allocation and garbage object reclaim
Processing, if it is possible to optimization JVM parameters well, it will obtain very big performance boost.
JVM tunings are a rings critically important in service optimization.Common practice is, technical staff is according to the operation feelings of service
Condition does the observation of a period of time, and according to the meaning of each parameters of JVM, exploratory provides JVM tuning schemes；One section of service operation
After time, check whether the program is reasonable, when unreasonable or when still needing to optimization, then provide new adjusting and optimizing scheme.So
Repeatedly so as to obtaining tuning result.
Under this prior art pattern, although by constantly debugging, optimum results can be finally obtained.But exist and lack
Falling into includes, and first, it is necessary to which staff has very deep understanding to JVM, it is necessary to grasp the meaning that each parameters of JVM are acted on tuning
Justice；Second, it is also necessary to which professional does prolonged tracking and maintenance to service, scheme change, retries.The presence of above mentioned problem,
It all can undoubtedly increase manpower, time and the cost in work.
The content of the invention
The invention provides a kind of JVM tunings method, for solving to optimize operating process more for JVM in the prior art
The problem of numerous and diverse, by setting automatic Optimization Steps so as to efficiently obtaining tuning result.
The present invention is achieved by the following technical programs：
A kind of JVM tunings method, comprises the following steps：
Commending system obtains the process number of destination service, to get corresponding JVM examples；
The JVM environment scan tools that system combination JDK environment provides, the spatial information of timing acquisition destination service and daily record
Information, the spatial information include JVM heap space, space of new generation, old age for space and forever for memory information, the daily record
Information includes the daily record of JVM garbage reclamations and JVM running log information；
The information got is stored in database, and respectively to JVM heap space, space of new generation, old age for space and forever
Mean operation is carried out for internal memory long, generates optimum results；
The JVM parameters in optimization system are adjusted according to optimum results.
A kind of JVM tunings method as described above, the space allocation stride a of optimum results scope is 20~60%, when
When the amplitude of variation in space is more than a, then the amount of original value is increased or decreased according to optimum results, otherwise, JVM parameter is kept not
Become.
A kind of JVM tunings method as described above, JVM according to the interval time b of setting, by the spatial information collected with
Information data in the interval time b of setting does mean operation, and optimization system will regenerate optimum results.
A kind of JVM tunings method as described above, the JVM heap space optimization process include：Obtain heap space information and
Log information；Determine whether forever for internal memory overflow error；If any then increasing forever for memory headroom, such as nothing, then terminate.
A kind of JVM tunings method as described above, the old age include for space optimization process：Obtain old age makes for internal memory
With rate；Judge whether memory usage continues a high position, in this way, then increase is old for space, then terminates, if not, under
One step judges whether old age continues low level for memory usage, in this way, then reduces old age for space, then terminates, if not, logical
Old age is spent before and after acquisition Full GC for space utilization rate situation of change, is judged in interval time b utilization rate differences of new generation twice
Whether fall in the range of space allocation stride a, in this way, then increase space of new generation, then terminate, such as otherwise directly terminate.
A kind of JVM tunings method as described above, the space optimization process of new generation include：Obtaining internal memory of new generation makes
With rate；Judge whether memory usage continues a high position, in this way, then increase space of new generation, then terminate, if not, under
One step judges whether memory usage of new generation continues low level, in this way, then reduces space of new generation, then terminates, if not, logical
Cross and obtain utilization rate situation of change in space of new generation before and after Minor GC, judge in interval time b utilization rate differences of new generation twice
Whether fall in the range of space allocation stride a, in this way, then increase space of new generation, then terminate, such as otherwise directly terminate.
A kind of JVM tunings method as described above, the JVM heap space optimization process be additionally provided with space of new generation with it is old
Age space ratio Optimization Steps, including heap space information is obtained, heap memory overflow error is judged whether, in this way, is then increased
Then raft memory size terminates, if not, determining whether heap memory utilization rate difference falls twice in interval time b
In the range of space allocation stride a, then increase heap memory size in this way and then terminate, if not, before obtaining heap memory spilling
Full GC results, judge whether space utilization rate of new generation is less than setting value C, if not, increase heap memory size and then knot
Beam, in this way, then directly terminate.
A kind of JVM tunings method as described above, the space optimization process of new generation are additionally provided with age threshold optimization
Step, including obtain blob information before and after Minor GC and count, judge whether object living always be present, if not, directly
Binding beam, in this way, obtain GC number of Minor in setting time section, obtain the age parameter that JVM objects enter old generation, so
Judge that old age is less than space allocation stride a for space average utilization rate, such as utilization rate in interval time b afterwards, then reduce age ginseng
Number, as utilization rate is more than space allocation stride a, then age parameter is improved, is then terminated.
A kind of JVM tunings method as described above, the space optimization process of new generation, which is additionally provided with, directly carries out old age
For blob information before and after object size threshold values Optimization Steps, including acquisition Minor GC and count, judge whether exist always
Object living, if not, directly terminate, in this way, during obtaining in size A, the interval time b of largest object Full GC twice
It is old for space utilization rate, when utilization rate is more than space allocation stride a, then directly terminate, when utilization rate is less than space allocation step
Width a, then the object size parameter P for being directly entered old generation is further obtained, then by P and A to being compared, as P is more than A
Then directly terminate, assign A value to P if P is less than A, then terminate.
Compared with prior art, it is an advantage of the invention that：
The present invention is by by JVM evolutionary process vague generalization, so that the evolutionary process of specialty is become into simple and easy, subtracting simultaneously
A large amount of work of few staff.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described.
Fig. 1 is the system flow chart of the present invention；
Fig. 2 is JVM heap space optimization flow chart in Fig. 1；
Fig. 3 is Fig. 1 person in middle and old age for space optimization flow chart；
Fig. 4 is Fig. 1 Middle Cenozoic space optimization flow charts；
Fig. 5 is Fig. 1 Middle Cenozoics space and old age for space ratio Optimizing Flow figure；
Fig. 6 is age threshold optimization flow chart in Fig. 1；
Fig. 7 is that old age is directly entered in Fig. 1 for object size threshold optimization flow chart.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
Part of the embodiment of the present invention, rather than whole embodiments.
Wherein, the technical term implication being related to is as follows：
1. JVM is Java Virtual Machine (Java Virtual Machine) abbreviation, JVM is a kind of to be used for computing device
Specification, be by the computer of reality analogue simulation various computer functions realize.Java Virtual Machine includes a set of
Byte code instruction collection, one group of register, a stack, a heap and a storage method domain.
2. space of new generation is a part in JVM heap space, the object being newly created that in JVM runnings is deposited
Storage space is put
3. old is the another part in JVM heap space for space, for coordinating recovery algorithm will multiple local garbage reclamation
The object so survived is appointed to preserve to the region
4. Minor GC are JVM once small garbage reclamation actions, for reclaiming object invalid in space of new generation.
Minor GC actions trigger in insufficient space of new generation.
5. Full GC are once full heap garbage reclamations of the JVM to heap space, trigger, reclaim when old age is for insufficient space
Invalidated object in heap space.Full GC efficiency is more much lower than Minor GC.
As shown in Fig. 1-Fig. 7, a kind of JVM tunings method of the present embodiment, comprise the following steps：
Commending system obtains the process number of destination service, to get corresponding JVM examples；System combination JDK environment carries
The JVM environment scan tools of confession, the spatial information and log information of timing acquisition destination service, the spatial information include JVM
Heap space, space of new generation, old age include JVM garbage reclamation daily records for space and forever for memory information, the log information
With JVM running log information；The information got is stored in database, and respectively to JVM heap space, space of new generation, old age
Mean operation is carried out for space and forever for internal memory, generates optimum results；According to optimum results to the JVM parameters in optimization system
It is adjusted.
Specifically, JVM tunings mostly occur in the adjustment of following parameter；JVM heap memory size, JVM is most in raft
Size, JVM Cenozoic memory sizes are deposited, JVM personated old man is directly entered personated old man for object size threshold value, and JVM for age threshold
Forever for memory size.Based on this situation, this method obtains relevant parameter by timing inquiry JVM states, then passes through cluster
Analysis, the excursion for the value that gets parms, and then draw JVM tuning schemes.Tuning scheme is applied in instantiation by user,
Tuning scheme makes new adjustment according to the change of time, is recommended for user is further.
The present embodiment is a kind of service based on Web technologies, and system deployment is on the node where JVM examples to be optimized.
Sent and asked to commending system by HTTP modes.
Specific deployment way is as follows：Program JVM parameters to be optimized are set, the JVM examples is exported garbage reclamation daily record；Open
Program to be optimized is moved, starts JVM tuning commending systems；Program process number to be optimized is obtained, and obtains its daily record outgoing route；Will
Process number and daily record outgoing route are input to JVM tuning commending systems；, should by recommendation results after waiting commending system to provide recommendation
Program JVM to be optimized is used, restarts the JVM, waits Operation Optimization Systerm to provide recommendation again.Until meet that user requires.
Commending system obtains the process number of destination service, that is, gets corresponding JVM examples；System combination JDK environment carries
The instruments such as JVM environment scan tools jmap, jstack, jps of confession, the JVM heap memory size of timing acquisition destination service are newborn
For spatial variations situation, old age is for information, permanent internal storage information and JVM garbage reclamation daily records, JVM running log information；Will
The information deposit database got.And five minutes durations are unit, by the information in the information collected and other five minutes
Do mean operation.The interval time b that the present embodiment is set is 5 minute, i.e., every 5 minutes, optimization system will regenerate optimization
As a result；According to the information generation optimum results in time period.The adjustment stride a in space is set as that 25% is defined.Even optimize
As a result it is increase or reduction, then the amount of original value 25% is increased or decreased according to optimum results, otherwise, parameter keeps constant.
Further, the process of JVM heap space optimization described in the present embodiment includes：Obtain heap space information and daily record letter
Breath；Determine whether forever for internal memory overflow error；If any then increasing forever for memory headroom, such as nothing, then terminate.
Further, old age described in the present embodiment includes for space optimization process：Old age is obtained for memory usage；Sentence
Whether disconnected memory usage continues a high position, and in this way, then increase is old for space, then terminates, judges in next step if not, entering
It is old whether to continue low level for memory usage, in this way, then reduce old age for space, then terminate, if not, passing through acquisition
Old age for space utilization rate situation of change, judges whether utilization rate difference of new generation falls twice in interval time b before and after Full GC
In the range of space allocation stride a, in this way, then increase space of new generation, then terminate, such as otherwise directly terminate.
Further, space optimization process of new generation includes described in the present embodiment：Obtain memory usage of new generation；Sentence
Whether disconnected memory usage continues a high position, in this way, then increases space of new generation, then terminates, and judges in next step if not, entering
Whether memory usage of new generation continues low level, in this way, then reduces space of new generation, then terminates, if not, by obtaining
Utilization rate situation of change in space of new generation before and after Minor GC, judge interval time b twice utilization rate difference of new generation whether
Fall in the range of space allocation stride a, in this way, then increase space of new generation, then terminate, such as otherwise directly terminate.
Further, the process of JVM heap space optimization described in the present embodiment is additionally provided with space of new generation and old generation is empty
Between ratio Optimization Steps, including obtain heap space information, judge whether heap memory overflow error, in this way, then increase heap in
Deposit size and then terminate, if not, determining whether heap memory utilization rate difference falls in space tune twice in interval time b
In the range of synchronizing width a, then increase heap memory size in this way and then terminate, tied if not, obtaining Full GC before heap memory overflows
Fruit, judges whether space utilization rate of new generation is less than setting value C, if not, then increase heap memory size terminates, in this way, then
Directly terminate.
Further, space optimization process of new generation is additionally provided with age threshold Optimization Steps described in the present embodiment, bag
Include and obtain blob information before and after Minor GC and count, judge whether object living always be present, if not, directly terminate,
In this way, obtain GC number of Minor in setting time section, obtain the age parameter that JVM objects enter old generation, then judge
Old age is less than space allocation stride a for space average utilization rate, such as utilization rate in interval time b, then reduces age parameter, such as make
It is more than space allocation stride a with rate, then improves age parameter, then terminate.
Further, it is old big for object to be additionally provided with directly progress for space optimization process of new generation described in the present embodiment
Small threshold values Optimization Steps, including obtain blob information before and after Minor GC and count, judge whether object living always be present,
If not, directly terminate, in this way, old age is for space during obtaining in size A, the interval time b of largest object Full GC twice
Utilization rate, when utilization rate is more than space allocation stride a, then directly terminate, when utilization rate is less than space space allocation stride a, then
The object size parameter P for being directly entered old generation is further obtained, then by P and A to being compared, as P is direct more than if A
Terminate, assign A value to P if P is less than A, then terminate.
The technology contents of the not detailed description of the present invention are known technology.
Claims (9)
- A kind of 1. JVM tunings method, it is characterised in that comprise the following steps：Commending system obtains the process number of destination service, to get corresponding JVM examples；The JVM environment scan tools that system combination JDK environment provides, the spatial information of timing acquisition destination service and daily record letter Breath, the spatial information include JVM heap space, space of new generation, old age for space and forever for memory information, the daily record letter Breath includes the daily record of JVM garbage reclamations and JVM running log information；The information got is stored in database, and respectively to JVM heap space, space of new generation, old age for space and permanent generation Internal memory carries out mean operation, generates optimum results；The JVM parameters in optimization system are adjusted according to optimum results.
- 2. a kind of JVM tunings method according to claim 1, it is characterised in that the space allocation stride a's of optimum results Scope is 20~60%, when the amplitude of variation in space is more than a, then the amount of original value is increased or decreased according to optimum results, no Then, JVM parameter is kept constant.
- 3. a kind of JVM tunings method according to claim 2, it is characterised in that JVM, will according to the interval time b of setting The spatial information collected does mean operation with the information data in the interval time b of setting, and optimization system will regenerate excellent Change result.
- A kind of 4. JVM tunings method according to claim 3, it is characterised in that the JVM heap space optimization process bag Include：Obtain heap space information and log information；Determine whether forever for internal memory overflow error；If any then in increase forever generation Space is deposited, such as nothing, is then terminated.
- 5. a kind of JVM tunings method according to claim 3, it is characterised in that the old age is for space optimization process bag Include：Old age is obtained for memory usage；Judge whether memory usage continues a high position, in this way, then increase is old for space, then Terminate, if not, into judge in next step it is old whether continue low level for memory usage, in this way, then reduce old age for space, Then terminate, if not, being judged by old age before and after obtaining Full GC for space utilization rate situation of change in interval time b two Whether secondary utilization rate difference of new generation falls in the range of space allocation stride a, in this way, then increases space of new generation, Ran Houjie Beam, such as otherwise directly terminate.
- A kind of 6. JVM tunings method according to claim 3, it is characterised in that the space optimization process bag of new generation Include：Obtain memory usage of new generation；Judge whether memory usage continues a high position, in this way, then increase space of new generation, then Terminate, if not, into judging whether memory usage of new generation continues low level in next step, in this way, then reduce space of new generation, Then terminate, if not, by obtaining utilization rate situation of change in space of new generation before and after Minor GC, judge in interval time b two Whether secondary utilization rate difference of new generation falls in the range of space allocation stride a, in this way, then increases space of new generation, Ran Houjie Beam, such as otherwise directly terminate.
- 7. a kind of JVM tunings method according to claim 4, it is characterised in that the JVM heap space optimization process is also set Space of new generation is equipped with old for space ratio Optimization Steps, including obtains heap space information, judges whether heap memory Overflow error, in this way, then increase and heap memory size and then terminate, if not, determining whether in interval time b heap memories twice Whether utilization rate difference falls in the range of space allocation stride a, then increases heap memory size in this way and then terminates, if not, Full GC results before heap memory overflows are obtained, judge whether space utilization rate of new generation is less than setting value C, if not, increase heap Then memory size terminates, in this way, then directly terminate.
- 8. a kind of JVM tunings method according to claim 6, it is characterised in that the space optimization process of new generation is also It is provided with age threshold Optimization Steps, including obtains blob information before and after Minor GC and count, judges whether exist always Object living, if not, directly terminating, in this way, obtain GC number of Minor in setting time section, obtain the entrance of JVM objects The age parameter in old generation, then judge that old age is less than space allocation for space average utilization rate, such as utilization rate in interval time b Stride a, then reduce age parameter, as utilization rate is more than space allocation stride a, then improves age parameter, then terminates.
- 9. a kind of JVM tunings method according to claim 6, it is characterised in that the space optimization process of new generation is also It is provided with and directly carries out old age for blob information before and after object size threshold values Optimization Steps, including acquisition Minor GC and unite Meter, judge whether object living always be present, if not, directly terminating, in this way, obtain size A, the interval time of largest object Old age for space utilization rate, when utilization rate is more than space allocation stride a, then directly terminates during Full GC twice in b, when making Be less than space space allocation stride a with rate, then further obtain and be directly entered the object size parameter P in old generation, then by P and A to being compared, directly terminate if P is more than A, assign A value to P if P is less than A, then terminate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710942079.3A CN107766123B (en) | 2017-10-11 | 2017-10-11 | JVM (JVM) tuning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710942079.3A CN107766123B (en) | 2017-10-11 | 2017-10-11 | JVM (JVM) tuning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107766123A true CN107766123A (en) | 2018-03-06 |
| CN107766123B CN107766123B (en) | 2020-10-27 |
Family
ID=61267073
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710942079.3A Active CN107766123B (en) | 2017-10-11 | 2017-10-11 | JVM (JVM) tuning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107766123B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109144671A (en) * | 2018-08-21 | 2019-01-04 | 郑州云海信息技术有限公司 | The management method and device of virtual machine in cloud data system |
| CN109597676A (en) * | 2018-10-25 | 2019-04-09 | 平安科技（深圳）有限公司 | Monitoring and early warning method, apparatus and storage medium based on JVM |
| CN111352698A (en) * | 2020-02-25 | 2020-06-30 | 北京奇艺世纪科技有限公司 | JVM parameter adjusting method and device |
| CN111427667A (en) * | 2020-04-03 | 2020-07-17 | 帆软软件有限公司 | JVM load quantification and optimization method |
| CN111831467A (en) * | 2020-07-21 | 2020-10-27 | 北京思特奇信息技术股份有限公司 | Method, system and electronic equipment for java process memory overflow self-fusing |
| CN111949377A (en) * | 2020-08-25 | 2020-11-17 | 深圳市广通软件有限公司 | JVM parameter optimization method, device, server and storage medium for WEB middleware |
| CN112000471A (en) * | 2020-08-10 | 2020-11-27 | 海信电子科技(武汉)有限公司 | Memory optimization method and device |
| CN112000428A (en) * | 2020-07-30 | 2020-11-27 | 杭州安恒信息技术股份有限公司 | JVM (JVM) tuning method and device based on machine learning and electronic device |
| CN112579259A (en) * | 2020-12-14 | 2021-03-30 | 中国科学院软件研究所 | GC self-adaptive adjusting method and device for big data processing framework |
| CN112751591A (en) * | 2019-10-29 | 2021-05-04 | 联发科技（新加坡）私人有限公司 | Method and device for supporting JMAP and CMAP transmission |
| CN112905418A (en) * | 2021-03-02 | 2021-06-04 | 湖南快乐阳光互动娱乐传媒有限公司 | JVM (JVM) tuning method and device |
| CN113608798A (en) * | 2021-08-06 | 2021-11-05 | 中航金网(北京)电子商务有限公司 | Method and device for configuring resources used by non-JAVA application and cloud-native application |
| CN113778740A (en) * | 2021-11-10 | 2021-12-10 | 中航金网(北京)电子商务有限公司 | Exception handling method and device based on garbage collection log |
| CN114281483A (en) * | 2021-12-28 | 2022-04-05 | 中国电信股份有限公司 | Memory area tuning method and device, storage medium and processor |
| CN114816760A (en) * | 2022-05-13 | 2022-07-29 | 兰考堌阳医院有限公司 | Interactive nursing billboard system and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080134172A1 (en) * | 2006-11-30 | 2008-06-05 | International Business Machines Corporation | JVM System Scope Initializer |
| US20110271276A1 (en) * | 2010-04-28 | 2011-11-03 | International Business Machines Corporation | Automated tuning in a virtual machine computing environment |
| CN103186412A (en) * | 2011-12-31 | 2013-07-03 | 北京新媒传信科技有限公司 | Performance optimization method based on JVM (java virtual machine) server |
| CN103870315A (en) * | 2014-03-26 | 2014-06-18 | 中国联合网络通信集团有限公司 | JVM energy consumption control method and device |
| CN104346255A (en) * | 2014-10-21 | 2015-02-11 | 浪潮集团有限公司 | Method for automatically monitoring service conditions of process memories in cloud computation |
-
2017
- 2017-10-11 CN CN201710942079.3A patent/CN107766123B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080134172A1 (en) * | 2006-11-30 | 2008-06-05 | International Business Machines Corporation | JVM System Scope Initializer |
| US20110271276A1 (en) * | 2010-04-28 | 2011-11-03 | International Business Machines Corporation | Automated tuning in a virtual machine computing environment |
| CN103186412A (en) * | 2011-12-31 | 2013-07-03 | 北京新媒传信科技有限公司 | Performance optimization method based on JVM (java virtual machine) server |
| CN103870315A (en) * | 2014-03-26 | 2014-06-18 | 中国联合网络通信集团有限公司 | JVM energy consumption control method and device |
| CN104346255A (en) * | 2014-10-21 | 2015-02-11 | 浪潮集团有限公司 | Method for automatically monitoring service conditions of process memories in cloud computation |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109144671A (en) * | 2018-08-21 | 2019-01-04 | 郑州云海信息技术有限公司 | The management method and device of virtual machine in cloud data system |
| CN109597676A (en) * | 2018-10-25 | 2019-04-09 | 平安科技（深圳）有限公司 | Monitoring and early warning method, apparatus and storage medium based on JVM |
| CN112751591A (en) * | 2019-10-29 | 2021-05-04 | 联发科技（新加坡）私人有限公司 | Method and device for supporting JMAP and CMAP transmission |
| CN112751591B (en) * | 2019-10-29 | 2023-09-19 | 联发科技（新加坡）私人有限公司 | Method and device for supporting JMAP and CMAP transmission |
| CN111352698A (en) * | 2020-02-25 | 2020-06-30 | 北京奇艺世纪科技有限公司 | JVM parameter adjusting method and device |
| CN111352698B (en) * | 2020-02-25 | 2023-12-22 | 北京奇艺世纪科技有限公司 | JVM parameter adjusting method and device |
| CN111427667A (en) * | 2020-04-03 | 2020-07-17 | 帆软软件有限公司 | JVM load quantification and optimization method |
| CN111831467A (en) * | 2020-07-21 | 2020-10-27 | 北京思特奇信息技术股份有限公司 | Method, system and electronic equipment for java process memory overflow self-fusing |
| CN112000428A (en) * | 2020-07-30 | 2020-11-27 | 杭州安恒信息技术股份有限公司 | JVM (JVM) tuning method and device based on machine learning and electronic device |
| CN112000428B (en) * | 2020-07-30 | 2024-03-22 | 杭州安恒信息技术股份有限公司 | JVM optimization method and device based on machine learning and electronic device |
| CN112000471A (en) * | 2020-08-10 | 2020-11-27 | 海信电子科技(武汉)有限公司 | Memory optimization method and device |
| CN112000471B (en) * | 2020-08-10 | 2023-10-27 | Vidaa(荷兰)国际控股有限公司 | Memory optimization method and device |
| CN111949377A (en) * | 2020-08-25 | 2020-11-17 | 深圳市广通软件有限公司 | JVM parameter optimization method, device, server and storage medium for WEB middleware |
| CN112579259A (en) * | 2020-12-14 | 2021-03-30 | 中国科学院软件研究所 | GC self-adaptive adjusting method and device for big data processing framework |
| CN112579259B (en) * | 2020-12-14 | 2022-07-15 | 中国科学院软件研究所 | GC self-adaptive adjustment method and device for big data processing framework |
| CN112905418A (en) * | 2021-03-02 | 2021-06-04 | 湖南快乐阳光互动娱乐传媒有限公司 | JVM (JVM) tuning method and device |
| CN113608798A (en) * | 2021-08-06 | 2021-11-05 | 中航金网(北京)电子商务有限公司 | Method and device for configuring resources used by non-JAVA application and cloud-native application |
| CN113778740A (en) * | 2021-11-10 | 2021-12-10 | 中航金网(北京)电子商务有限公司 | Exception handling method and device based on garbage collection log |
| CN114281483A (en) * | 2021-12-28 | 2022-04-05 | 中国电信股份有限公司 | Memory area tuning method and device, storage medium and processor |
| CN114816760B (en) * | 2022-05-13 | 2023-04-28 | 兰考堌阳医院有限公司 | Interactive nursing billboard system and storage medium |
| CN114816760A (en) * | 2022-05-13 | 2022-07-29 | 兰考堌阳医院有限公司 | Interactive nursing billboard system and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107766123B (en) | 2020-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107766123A (en) | A kind of JVM tunings method | |
| US11620574B2 (en) | Holistic optimization for accelerating iterative machine learning | |
| US8918769B2 (en) | Application of optimization techniques to intermediate representations for code generation | |
| US7788658B2 (en) | Computer code partitioning for enhanced performance | |
| CN105283851A (en) | Cost analysis for selecting trace objectives | |
| CN105122212A (en) | Periodicity optimization in an automated tracing system | |
| US20150058316A1 (en) | Continuous Cloud-Scale Query Optimization and Processing | |
| CN1447224A (en) | Method of optimizing use of memory in computer applied program | |
| CN105122234A (en) | Deploying trace objectives using cost analyses | |
| Hertz et al. | Generating object lifetime traces with Merlin | |
| Sanchez et al. | Using machines to learn method-specific compilation strategies | |
| CN105607952B (en) | Method and device for scheduling virtualized resources | |
| US8056061B2 (en) | Data processing device and method using predesignated register | |
| CN1894664B (en) | Methods and apparatus to dynamically insert prefetch instructions based on compiler and garbage collector analysis | |
| Previti et al. | Premise set caching for enumerating minimal correction subsets | |
| US8176286B2 (en) | Memory recycling in computer systems | |
| CN105447285B (en) | A method of improving OpenCL hardware execution efficiency | |
| CN106250292A (en) | A kind of office management system performance monitoring platform | |
| Beronić et al. | Assessing Contemporary Automated Memory Management in Java–Garbage First, Shenandoah, and Z Garbage Collectors Comparison | |
| CN105302551B (en) | A kind of method and system of the Orthogonal Decomposition construction and optimization of big data processing system | |
| Lengauer et al. | Where has all my memory gone? determining memory characteristics of product variants using virtual-machine-level monitoring | |
| Nikolaidis et al. | Experience with managing technical debt in scientific software development using the exa2pro framework | |
| CN114064012A (en) | Dynamic and static combined interface code generation method and system and electronic equipment | |
| Park et al. | Multi-objective exploration for practical optimization decisions in binary translation | |
| Czibula et al. | Hierarchical clustering for software systems restructuring |
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: 20200929 Address after: 215100 No. 1 Guanpu Road, Guoxiang Street, Wuzhong Economic Development Zone, Suzhou City, Jiangsu Province Applicant after: SUZHOU LANGCHAO INTELLIGENT TECHNOLOGY Co.,Ltd. Address before: 450018 Henan province Zheng Dong New District of Zhengzhou City Xinyi Road No. 278 16 floor room 1601 Applicant before: ZHENGZHOU YUNHAI INFORMATION TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |