CN103248675A - Polling method for monitoring state of server hardware - Google Patents
Polling method for monitoring state of server hardware Download PDFInfo
- Publication number
- CN103248675A CN103248675A CN2013101418710A CN201310141871A CN103248675A CN 103248675 A CN103248675 A CN 103248675A CN 2013101418710 A CN2013101418710 A CN 2013101418710A CN 201310141871 A CN201310141871 A CN 201310141871A CN 103248675 A CN103248675 A CN 103248675A
- Authority
- CN
- China
- Prior art keywords
- priority
- hardware state
- monitoring
- state
- hardware
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention provides a polling method for monitoring a state of server hardware. The method comprises the specific polling processes as follows: the server hardware is subjected to state grading respectively, and then whether the priority of the state of the server hardware during polling is improved or not is judged according to the setting of a user and the state parameter of the server hardware; if the user sets the priority of the state of the hardware to be high, or if the difference between the state parameter of the hardware and an alarm threshold value is within the range set by the user, the priority of the state of the hardware during polling is improved, the high priority hardware state is monitored with a complete service strategy, and an ordinary priority hardware state is monitored with a limitation service strategy. Compared with the prior art, the polling method for monitoring the state of the server hardware proposes a grading strategy, so that the polling efficiency and the alarming timeliness are improved, and the inquiring of the hardware state can be rapidly and accurately completed.
Description
Technical field
The present invention relates to field of computer technology, specifically a kind of polling method of the branch fraction strategy for the monitoring server hardware state.
Background technology
Along with improving constantly with the server range of application of server performance constantly enlarges, the requirement of server stable operation is also more and more higher, server can stable operation the basis be that hardware components can stable operation, so it is for the server hardware state, just more and more important as the monitoring of hardware states such as voltage, temperature, rotation speed of the fan.
Along with the continuous upgrading of hardware, need the hardware state monitored also more and more on the server, on a high-end server, may have hundreds of even thousands of hardware states needs monitoring.Monitor at so many state, adopt the simple method of poll successively that hardware state is gathered, the method of judging and handling can cause the warning that can not handle some hardware states timely, as in the 1st hardware state of poll, even if its state parameter has soon approached threshold value, but think that still it is normal, continue poll then, when being polled to the 10th hardware state, the 1st hardware state parameter may surpass threshold value, but simple polling mode successively can't be handled, it can continue poll, until whole hardware state poll one time all, when returning the 1st hardware state of poll, could report to the police to the 1st state.
From top analysis as can be seen, for the more many systems of hardware state, suppose to have N hardware state to need monitoring, adopt polling method simply successively, the monitoring time delay T=N*T of each hardware state
D(T
DIt is the time of each hardware state cost of poll).
At this problem, the polling method that this patent has proposed branch fraction strategy comes the server hardware state to monitor.
Summary of the invention
Technical assignment of the present invention is to solve the deficiencies in the prior art, and a kind of polling method for the monitoring server hardware state is provided.
Technical scheme of the present invention realizes in the following manner, this a kind of polling method for the monitoring server hardware state, and its detailed process is:
Server hardware is carried out the state classification respectively, setting and server hardware state parameter according to the user determines whether to improve its priority in poll then: set the priority of this hardware state as the user for high, perhaps this hardware state parameter with the difference of alarm threshold value within the scope that the user sets, improve the priority of this hardware state in poll so, the full service strategy is adopted in hardware state monitoring for high priority, adopts for the hardware state monitoring of normal priority to limit service strategy.
Described server hardware state stage division is as follows: server hardware has N state, the state of its high priority has M, the hardware state of M high priority is formed a monitoring formation, this monitoring formation is high-priority queue, described M span is 0≤M≤N, corresponding, the hardware state of normal priority has N-M.
Described full service strategy refers to for high-priority queue, must monitor after M the hardware state in this formation, forwards the formation of monitoring normal priority again to and goes to carry out monitoring.
Described restriction service strategy refers to for the normal priority formation, only monitors K hardware state at every turn; After the monitoring that executes this K hardware state, get back to high-priority queue and carry out monitoring, after high-priority queue monitoring finishes, get back to the normal priority formation again, continue remaining hardware state in the formation of monitoring normal priority, after being finished, forward high-priority queue again to, switch so repeatedly, the span of described K is 1≤K≤N-M.
The beneficial effect that the present invention compared with prior art produces is:
A kind of polling method for the monitoring server hardware state of the present invention guarantees the server data stable transfer, has proposed the polling method of branch fraction strategy, has improved the efficient of poll and the promptness of warning, can finish the inquiry of hardware state fast and accurately.
Embodiment
A kind of polling method for the monitoring server hardware state by having proposed the polling method of branch fraction strategy, has improved the efficient of poll and the promptness of warning, and its concrete polling procedure is as follows:
Suppose that server has N hardware state to need monitoring.
The control parameter of user's input mainly comprises two:
Whether 1, set its priority at each hardware state is high.
2, the hardware state parameter can not surpass the percentage of setting threshold.
Supposing has M at the hardware state of some moment high priorities, the hardware state of this M high priority is formed a monitoring formation, be called high-priority queue, span 0≤M≤N of M, namely may not have the hardware state of high priority to need monitoring, also hardware state that might be all becomes high priority.The hardware state of normal priority has N-M, and these hardware states are formed a monitoring formation, are called the normal priority formation.
For the strategy of high-priority queue employing full service, namely must monitor after M the hardware state in this formation, forward the formation of monitoring normal priority again to and go to carry out monitoring.
For the normal priority formation, employing be the strategy that limits service, namely only monitor K hardware state at every turn; After the monitoring that executes this K hardware state, get back to high-priority queue and carry out monitoring, after high-priority queue monitoring finishes, get back to the normal priority formation again, continue remaining hardware state in the formation of monitoring normal priority, still only monitor K hardware state, after being finished, forward high-priority queue again to, switch so repeatedly.
Here the value of K is 1≤K≤N-M.
For specific an application, the N value is fixed, and the M value can change according to the hardware state parameter, and its span is 0≤M≤N; The efficient of choosing for this method of K value has crucial effect.
In the method, suppose that each execution cycle is microcycle (MP), the MP=high-priority queue is carried out the time (T of full service
HW)+Low Priority Queuing is carried out the time (T of the service of restriction
LK).After each microcycle is finished, upgrade the K value.
For a hardware state of high-priority queue, its service time delay is:
From computing formula as can be seen, the time delay maximum of high priority is
This is that all hardware states all join the situation in the high-priority queue, in actual use, generally this situation can not occur, so pass through the polling mode of this minute fraction strategy, has improved the promptness to the hardware state monitoring alarm.
For a hardware state of normal priority formation, its service time delay is:
(when K can be divided exactly by N-M)
From computing formula, the service time delay of the hardware state of the normal priority formation time delay put down of poll more successively increases to some extent, and according to the value difference of K, this time delay also is different.
Through after the microperiodic monitoring once, according to the hardware state parameter, upgrade the M value.This moment, N value and M value were all determined.
For
, in the span of K value, the K value is more little, and its time delay is more little; For
, then be that the K value is more little, its time delay is more big.So according to a suitable K value, make
With
And (be designated as
) can get minimum value.
Calculate through formula
(when K can not be divided exactly by N-M)
From formula as can be seen, a proportional relationship about K (high priority) and an inversely prroportional relationship about K (low priority).Under the situation of given N and M, obtain the K value and make
The value minimum.
In practical operation, at first set up a hardware state watch-list, the method that proposes according to this patent requires to change watch-list then provides following input item to get final product at each state:
Whether this hardware state is high priority; The threshold value of hardware state parameter (upper and lower bound); The hardware state parameter can not surpass the percentage of setting threshold.
Claims (4)
1. polling method that is used for the monitoring server hardware state, it is characterized in that: concrete polling procedure is: server hardware is carried out the state classification respectively, setting and server hardware state parameter according to the user determines whether to improve its priority in poll then: set the priority of this hardware state as the user for high, perhaps this hardware state parameter with the difference of alarm threshold value within the scope that the user sets, improve the priority of this hardware state in poll so, the full service strategy is adopted in hardware state monitoring for high priority, adopts for the hardware state monitoring of normal priority to limit service strategy.
2. a kind of polling method for the monitoring server hardware state according to claim 1, it is characterized in that: described server hardware state stage division is as follows: server hardware has N state, the state of its high priority has M, the hardware state of M high priority is formed a monitoring formation, this monitoring formation is high-priority queue, described M span is 0≤M≤N, and is corresponding, and the hardware state of normal priority has N-M.
3. a kind of polling method for the monitoring server hardware state according to claim 2, it is characterized in that: described full service strategy refers to for high-priority queue, must monitor after M the hardware state in this formation, forward the formation of monitoring normal priority again to and go to carry out monitoring.
4. a kind of polling method for the monitoring server hardware state of stating according to claim 3, it is characterized in that: described restriction service strategy refers to for the normal priority formation, only monitors K hardware state at every turn; After the monitoring that executes this K hardware state, get back to high-priority queue and carry out monitoring, after high-priority queue monitoring finishes, get back to the normal priority formation again, continue remaining hardware state in the formation of monitoring normal priority, after being finished, forward high-priority queue again to, switch so repeatedly, the span of described K is 1≤K≤N-M.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013101418710A CN103248675A (en) | 2013-04-23 | 2013-04-23 | Polling method for monitoring state of server hardware |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013101418710A CN103248675A (en) | 2013-04-23 | 2013-04-23 | Polling method for monitoring state of server hardware |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103248675A true CN103248675A (en) | 2013-08-14 |
Family
ID=48927896
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2013101418710A Pending CN103248675A (en) | 2013-04-23 | 2013-04-23 | Polling method for monitoring state of server hardware |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103248675A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105591816A (en) * | 2015-12-10 | 2016-05-18 | 北京合力思腾科技股份有限公司 | Detection method for detecting running state of IT operation server |
| CN106130824A (en) * | 2016-07-22 | 2016-11-16 | 杨志军 | Integration of three networks broadband access priority polling control method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2292479A1 (en) * | 1997-06-27 | 1999-01-07 | Motorola, Inc. | System, device, and method for providing low access delay for time-sensitive applications in a shared medium network |
| CN102183768A (en) * | 2011-02-24 | 2011-09-14 | 航天东方红卫星有限公司 | Satellite fault rapid positioning system based on bus monitoring |
-
2013
- 2013-04-23 CN CN2013101418710A patent/CN103248675A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2292479A1 (en) * | 1997-06-27 | 1999-01-07 | Motorola, Inc. | System, device, and method for providing low access delay for time-sensitive applications in a shared medium network |
| CN102183768A (en) * | 2011-02-24 | 2011-09-14 | 航天东方红卫星有限公司 | Satellite fault rapid positioning system based on bus monitoring |
Non-Patent Citations (1)
| Title |
|---|
| 熊家龙: "两级轮询传感器网络在森林防火中的应用", 《林业实用技术》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105591816A (en) * | 2015-12-10 | 2016-05-18 | 北京合力思腾科技股份有限公司 | Detection method for detecting running state of IT operation server |
| CN106130824A (en) * | 2016-07-22 | 2016-11-16 | 杨志军 | Integration of three networks broadband access priority polling control method and system |
| CN106130824B (en) * | 2016-07-22 | 2019-04-30 | 杨志军 | Integration of three networks broadband access priority polling control method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA3104806C (en) | Method for scheduling a task, resource sharing use method and system based on preemptive scheduling, scheduler, device, and storage medium | |
| CN110096353B (en) | Task scheduling method and device | |
| CN103164279A (en) | Method and system for distributing cloud computing resources | |
| CN107370667B (en) | Multithreading parallel processing method and device, readable medium and storage controller | |
| Thinakaran et al. | Phoenix: A constraint-aware scheduler for heterogeneous datacenters | |
| US20180004568A1 (en) | Distributed task system and service processing method based on internet of things | |
| CN101840353B (en) | Dynamic timing method for real-time embedded operating system | |
| US10157155B2 (en) | Operating system-managed interrupt steering in multiprocessor systems | |
| CN103365729A (en) | Dynamic MapReduce dispatching method and system based on task type | |
| US9256506B1 (en) | System and method for performing operations on target servers | |
| WO2012037760A1 (en) | Method, server and system for improving alarm processing efficiency | |
| US9641431B1 (en) | System and methods for utilization-based balancing of traffic to an information retrieval system | |
| US20160202933A1 (en) | Impact-based migration scheduling | |
| CN103346902B (en) | The method and system of data acquisition scheduling | |
| CN101246438A (en) | Process and interrupt processing method and device for symmetrical multiprocessing system | |
| KR20110080735A (en) | Computing system and method | |
| CN102270156A (en) | Method for managing real-time embedded system timers | |
| CN104714838A (en) | Task scheduling method and device | |
| US20170048352A1 (en) | Computer-readable recording medium, distributed processing method, and distributed processing device | |
| CN108983946A (en) | A kind of server energy consumption control method, system and equipment | |
| CN103995742A (en) | Embedded type real-time scheduling control device and method based on MCU | |
| CN105242954A (en) | Mapping method between virtual CPUs (Central Processing Unit) and physical CPUs, and electronic equipment | |
| CN103248675A (en) | Polling method for monitoring state of server hardware | |
| CN103293967A (en) | Multi-task control method for intelligent meter reading terminal | |
| US9298652B2 (en) | Moderated completion signaling |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130814 |
|
| WD01 | Invention patent application deemed withdrawn after publication |