CN108848002A - A kind of dynamic GSLB processing method based on business delay - Google Patents
A kind of dynamic GSLB processing method based on business delay Download PDFInfo
- Publication number
- CN108848002A CN108848002A CN201810570528.0A CN201810570528A CN108848002A CN 108848002 A CN108848002 A CN 108848002A CN 201810570528 A CN201810570528 A CN 201810570528A CN 108848002 A CN108848002 A CN 108848002A
- Authority
- CN
- China
- Prior art keywords
- gslb
- data center
- business
- slb1
- processing method
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0852—Delays
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/04—Processing captured monitoring data, e.g. for logfile generation
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Data Mining & Analysis (AREA)
- Computer And Data Communications (AREA)
- Debugging And Monitoring (AREA)
Abstract
The present invention discloses a kind of dynamic GSLB processing method based on business delay, wherein adjust the rate that GSLB responds the data center in time by using metric algorithm, to solve because client caused by server service is busy accesses slow and solves because of the service fail for causing partial service link to be operating abnormally generation after server long-play, such as RAM leakage, database is too fat to move etc., such case business is accessible but low-response, the situation of time-out often occurs.
Description
Technical field
The invention belongs to technical field of the computer network more particularly to a kind of GSLB processing methods.
Background technique
In entire GSLB multiple data centers solution, GSLB manufacturer solutions all at present is all, according to strong
The series of algorithms such as health inspection, geographical location respond DNS request.It cannot really combine with business, really apply
In, the business of SLB load since a variety of situations such as portfolio is big, system longtime running, network cause cause business access slower,
Such case is problem to be solved of the present invention.
Therefore the technical solution for needing one kind new is to solve the above problems.
Summary of the invention
Goal of the invention:Solve the problems, such as because server service it is busy caused by client access it is slow, also solve because service
The problem of causing partial service link to be operating abnormally the service fail generated after device long-play.
Technical solution:In order to achieve the above objectives, following technical solution can be used in the present invention:
A kind of dynamic GSLB processing method based on business delay:
The delay of data center SLB1 device real-time monitoring record traffic, the business are delayed corresponding business to visit from client
VIP is asked, then goes to the whole process of rear end real server by VIP;
Assuming that the address date of business VIP1 is m1;Data center's SLB2 behavior and data center SLB1 are consistent, false
If the address date of business VIP2 is m2;M1 and m2 is by SLB dynamic acquisition and retains the numerical value of nearest several groups, covering operation;
It is respectively vip1=m1 that GSLB, which is detected by agreement and collected corresponding service condition in all data center apparatus,;
Vip2=m2, SLB timing take several groups data to all data center apparatus;
The time-delayed safe value t1 and warning value t2 that GSLB is set according to oneself are measured, and metric algorithm is:
(1) calculating data center and fetching the average value of several groups data is m;
(2) if m<T1 is then considered safe range, the DNS response rate of the GSLB normal response data center, it is assumed that
Rate is s1;
(3) if t1<m<T2 then thinks bounds, and dynamic adjusts GSLB and responds the rate of data center SLB1 as original
The half of some s1, i.e. s1/2;
Two period ms of continuous probe still fall within the range, continue to adjust the rate that GSLB responds data center SLB1
For last half, i.e. s1/4;
Two period ms of continuous probe still fall within the range again, continue to adjust the speed that GSLB responds data center SLB1
Rate is last half, i.e. s1/8;
Continue two period ms of continuous probe and still fall within the range, GSLB will no longer respond the DNS of data center SLB1
Request;
(4) if m>T2 then thinks abnormal ranges, and GSLB will no longer respond the DNS request of data center SLB1.
It further, further include Restoration Mechanism in step (3), i.e. m<t1.
Further, it is characterised in that:SLB timing takes five groups of data to data center's SLB equipment, it is assumed that is m1_1, m1_
2, m1_3, m1_4, m1_5 are all fetched when five groups discontented.
Further, this method is suitable for multiple data centers, and GSLB has been associated with health examination algorithm in this method.
Beneficial effect:The rate that GSLB responds the data center is adjusted by using metric algorithm in the present invention in time, with
It solves because client caused by server service is busy accesses slow and solves because leading to part industry after server long-play
Link of being engaged in is operating abnormally the service fail generated, and such as RAM leakage, database is too fat to move etc., and such case business is accessible but rings
The situation of time-out often should occur slowly.
Specific embodiment
The present embodiment discloses a kind of processing method applied in the dynamic GSLB based on business delay of multiple data centers, should
The precondition of processing method:
1GSLB has been associated with health examination algorithm
2 multiple data centers
Realization and principle explanation:
1, VIP is accessed from client in data center SLB1 device real-time monitoring record traffic, then by VIP to go to rear end true
The business of the whole process of real server is delayed, it is assumed that business VIP1 is m1;Data center's SLB2 behavior and data center SLB1
It is consistent, it is assumed that business VIP2 is m2;M1 and m2 retains nearest 5 groups of numerical value, covering operation by SLB dynamic acquisition;
2, GSLB passes through corresponding business shape in agreement detection, collection (actively and Passive Mode) data center's SLB equipment
State is respectively vip1=m1;Vip2=m2, SLB timing to data center's SLB equipment take five groups of data, it is assumed that for m1_1, m1_2,
M1_3, m1_4, m1_5 are all fetched when five groups discontented,
3, the time-delayed safe value t1 and warning value t2 that GSLB is set according to oneself are measured, and metric algorithm is:
(1) calculating data center and fetching the average value of data m1_1 to m1_5 is m
(2) if m<T1 is then considered safe range, the DNS response rate of the GSLB normal response data center, it is assumed that
Rate is s1
(3) if t1<m<T2 then thinks bounds, and dynamic adjusts GSLB and responds the rate of data center SLB1 as original
The half of some s1, i.e. s1/2;
Two period ms of continuous probe still fall within the range, continue to adjust the rate that GSLB responds data center SLB1
For last general, i.e. s1/4;
Two period ms of continuous probe still fall within the range again, continue to adjust the speed that GSLB responds data center SLB1
Rate is last general, i.e. s1/8;
Continue two period ms of continuous probe and still fall within the range, GSLB will no longer respond the DNS of data center SLB1
Request
Restoration Mechanism:m<t1
(4) if m>T2 then thinks abnormal ranges, and GSLB will no longer respond the DNS request of data center SLB1.
In addition, there are many concrete methods of realizing and approach of the invention, the above is only a preferred embodiment of the present invention.
It should be pointed out that for those skilled in the art, without departing from the principle of the present invention, can also do
Several improvements and modifications out, these modifications and embellishments should also be considered as the scope of protection of the present invention.What is be not known in the present embodiment is each
The available prior art of component part is realized.
Claims (5)
1. a kind of dynamic GSLB processing method based on business delay, it is characterised in that:
The delay of data center SLB1 device real-time monitoring record traffic, the business are delayed corresponding business to be accessed from client
VIP, then go to by VIP the whole process of rear end real server;
Assuming that the address date of business VIP1 is m1;Data center's SLB2 behavior and data center SLB1 are consistent, it is assumed that industry
The address date of business VIP2 is m2;M1 and m2 is by SLB dynamic acquisition and retains the numerical value of nearest several groups, covering operation;
It is respectively VIP1=m1 that GSLB, which is detected by agreement and collected corresponding service condition in all data center apparatus,;VIP2
=m2, GSLB timing take several groups data to all data center apparatus;
The time-delayed safe value t1 and warning value t2 that GSLB is set according to oneself are measured, and metric algorithm is:
(1) calculating data center and fetching the average value of several groups data is m;
(2) if m<T1 is then considered safe range, the DNS response rate of the GSLB normal response data center, it is assumed that rate
For s1;
(3) if t1<m<T2 then thinks bounds, and it is original that dynamic, which adjusts GSLB and responds the rate of data center SLB1,
The half of s1, i.e. s1/2;
Two period ms of continuous probe still fall within the range, and it is upper for continuing to adjust GSLB to respond the rate of data center SLB1
Primary half, i.e. s1/4;
Two period ms of continuous probe still fall within the range again, continue to adjust GSLB responding the rate of data center SLB1 and be
Last half, i.e. s1/8;
Continue two period ms of continuous probe and still fall within the range, GSLB asks the DNS for no longer responding data center SLB1
It asks;
(4) if m>T2 then thinks abnormal ranges, and GSLB will no longer respond the DNS request of data center SLB1.
2. processing method according to claim 1, it is characterised in that:Step further includes Restoration Mechanism in (3), i.e. m<t1.
3. processing method according to claim 1, it is characterised in that:SLB timing takes five groups of industry to data center's SLB equipment
Business status data, it is assumed that be m1_1, m1_2, m1_3, m1_4, m1_5, all fetched when five groups discontented.
4. processing method according to claim 1 or 2 or 3, it is characterised in that:Suitable for multiple data centers.
5. processing method according to claim 1, it is characterised in that:GSLB has been associated with health examination algorithm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810570528.0A CN108848002B (en) | 2018-06-05 | 2018-06-05 | Dynamic GSLB processing method based on service delay |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810570528.0A CN108848002B (en) | 2018-06-05 | 2018-06-05 | Dynamic GSLB processing method based on service delay |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108848002A true CN108848002A (en) | 2018-11-20 |
CN108848002B CN108848002B (en) | 2021-07-16 |
Family
ID=64210376
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810570528.0A Active CN108848002B (en) | 2018-06-05 | 2018-06-05 | Dynamic GSLB processing method based on service delay |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108848002B (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7096263B2 (en) * | 2000-05-26 | 2006-08-22 | Akamai Technologies, Inc. | Method for predicting file download time from mirrored data centers in a global computer network |
CN101146022A (en) * | 2006-09-11 | 2008-03-19 | 思华科技(上海)有限公司 | Node overlapping content distribution network |
CN102207891A (en) * | 2011-06-10 | 2011-10-05 | 浙江大学 | Method for achieving dynamic partitioning and load balancing of data-partitioning distributed environment |
CN102763375A (en) * | 2009-12-23 | 2012-10-31 | 思杰***有限公司 | Systems and methods for gslb spillover |
CN102891804A (en) * | 2012-10-16 | 2013-01-23 | 中兴通讯股份有限公司南京分公司 | Control strategy adjustment method and system |
CN104022891A (en) * | 2013-02-28 | 2014-09-03 | 杭州华三通信技术有限公司 | Global load balancing equipment business coordination method and device |
US9032488B2 (en) * | 2012-04-17 | 2015-05-12 | Salesforce.Com, Inc. | Cross instance user authentication architecture |
CN105262857A (en) * | 2015-11-04 | 2016-01-20 | 北京汉柏科技有限公司 | DNS relay function acceleration method and device |
CN105704708A (en) * | 2014-11-25 | 2016-06-22 | 中兴通讯股份有限公司 | Mobile network content distribution method, device and system |
CN106657201A (en) * | 2015-11-03 | 2017-05-10 | 中兴通讯股份有限公司 | Data processing method and device for GSLB scheduling system |
-
2018
- 2018-06-05 CN CN201810570528.0A patent/CN108848002B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7096263B2 (en) * | 2000-05-26 | 2006-08-22 | Akamai Technologies, Inc. | Method for predicting file download time from mirrored data centers in a global computer network |
CN101146022A (en) * | 2006-09-11 | 2008-03-19 | 思华科技(上海)有限公司 | Node overlapping content distribution network |
CN102763375A (en) * | 2009-12-23 | 2012-10-31 | 思杰***有限公司 | Systems and methods for gslb spillover |
CN102207891A (en) * | 2011-06-10 | 2011-10-05 | 浙江大学 | Method for achieving dynamic partitioning and load balancing of data-partitioning distributed environment |
US9032488B2 (en) * | 2012-04-17 | 2015-05-12 | Salesforce.Com, Inc. | Cross instance user authentication architecture |
CN102891804A (en) * | 2012-10-16 | 2013-01-23 | 中兴通讯股份有限公司南京分公司 | Control strategy adjustment method and system |
CN104022891A (en) * | 2013-02-28 | 2014-09-03 | 杭州华三通信技术有限公司 | Global load balancing equipment business coordination method and device |
CN105704708A (en) * | 2014-11-25 | 2016-06-22 | 中兴通讯股份有限公司 | Mobile network content distribution method, device and system |
CN106657201A (en) * | 2015-11-03 | 2017-05-10 | 中兴通讯股份有限公司 | Data processing method and device for GSLB scheduling system |
CN105262857A (en) * | 2015-11-04 | 2016-01-20 | 北京汉柏科技有限公司 | DNS relay function acceleration method and device |
Non-Patent Citations (2)
Title |
---|
JÖRG JUNG,ET AL.,: ""Self-adapting load balancing for DNS"", 《 INTERNATIONAL SYMPOSIUM ON PERFORMANCE EVALUATION OF COMPUTER AND TELECOMMUNICATION SYSTEMS (SPECTS 2014)》 * |
徐玲,: ""CDN网络中负载均衡的研究"", 《中国优秀硕士学位论文全文数据库-信息科技辑》 * |
Also Published As
Publication number | Publication date |
---|---|
CN108848002B (en) | 2021-07-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20140149533A1 (en) | Data storage based on content popularity | |
CN107426206A (en) | A kind of protector and method to web server | |
US7657779B2 (en) | Client assisted autonomic computing | |
US20050256935A1 (en) | System and method for managing a network | |
CN107707631B (en) | Data acquisition method and device | |
CN109787827B (en) | CDN network monitoring method and device | |
CN104836819A (en) | Dynamic load balancing method and system, and monitoring and dispatching device | |
CA2810823A1 (en) | Method, system and apparatus for accessing and managing a plurality of wind turbines via a network | |
JP6220625B2 (en) | Delay monitoring system and delay monitoring method | |
CN108270778A (en) | A kind of DNS domain name abnormal access detection method and device | |
US10581902B1 (en) | Methods for mitigating distributed denial of service attacks and devices thereof | |
US20190164067A1 (en) | Method and device for monitoring a process of generating metric data for predicting anomalies | |
CN112104752B (en) | Hot spot balancing method and system for cache nodes of content distribution network | |
CN106656636A (en) | Cloud platform fault detection method and device | |
US10754722B1 (en) | Method for remotely clearing abnormal status of racks applied in data center | |
CN108848002A (en) | A kind of dynamic GSLB processing method based on business delay | |
US20200305301A1 (en) | Method for remotely clearing abnormal status of racks applied in data center | |
WO2018035765A1 (en) | Method and apparatus for detecting network abnormity | |
CN103297480B (en) | A kind of application service automatic checkout system and method | |
CN108366077A (en) | Fission formula attack protection network access system | |
CN106789335A (en) | A kind of method and system for processing information | |
CN107612755A (en) | The management method and its device of a kind of cloud resource | |
CN115277080B (en) | Content distribution network cache pollution defense method based on merck tree | |
CN103731365A (en) | Bottleneck-free load balancing network server system and establishment method thereof | |
CN113452691B (en) | Service flow detection method and device, server and storage medium |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |