CN104468302B - A kind of processing method and processing device of token - Google Patents
A kind of processing method and processing device of token Download PDFInfo
- Publication number
- CN104468302B CN104468302B CN201410550612.8A CN201410550612A CN104468302B CN 104468302 B CN104468302 B CN 104468302B CN 201410550612 A CN201410550612 A CN 201410550612A CN 104468302 B CN104468302 B CN 104468302B
- Authority
- CN
- China
- Prior art keywords
- token
- loop
- node
- message processing
- processing cluster
- 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.)
- Active
Links
Landscapes
- Small-Scale Networks (AREA)
Abstract
The present invention is applied to network technique field, there is provided a kind of processing method of token, device and Message Processing cluster, methods described include:Token loop is established in the application layer of Message Processing cluster;When node adds or exits token loop, token is produced or destroyed using simple majority Voting Algorithm;In the transmittance process of token, monitor the timestamp of each node last outflow token in token loop, if monitoring, the timestamp of node last outflow token and the time difference of current time beyond the winding time of setting, initiate route finding process, rebuild token loop.The present invention, avoid the token loop for occurring 2 or more than 2 in Message Processing cluster;In addition, being monitored to the token winding time of each node, solve prior art, while the loss of token such as can not supervise at the problem in token loop, substantially increase the reliability of distributed cluster system.
Description
Technical field
The invention belongs to network technique field, more particularly to a kind of processing method of token, device and Message Processing cluster.
Background technology
With the continuous extension of network size, distributed system is widely used, while also brings Distributed Coordination one
The problem of cause property.Consistency problem is mainly shown as data consistency, logical consistency and temporal consistency, solves uniformity and asks
, can be harmonious when topic is mainly to ensure that distributed system accesses and controlled at the same time a resource, ensure the correct of access
Property (deadlock freedom and without hunger phenomenon).Mutual exclusion is the key that distributed system solves consistency problem.Usual distributed system makes
Mutually exclusive algorithm has:Centralized algorithm, distributed algorithm and token ring algorithm.
Centralized algorithm selects a process as telegon, for coordinating the entrance of critical zone.
Feature:Telegon only allows a process to enter critical zone in the same time, therefore can guarantee that mutual exclusion.Because request disappears
Breath is that decision queue obtains, and is not in " hungry to death " phenomenon.But single telegon is its bottleneck.
The thought of distributed algorithm is:To wanting that the process into critical zone initially sets up a message, the message includes treating
Critical zone name, process name and the timestamp of entrance.After one process receives message, following operation is had:If not critical
In area and it is not desired to then reply a message into critical zone;Do not replied message if in critical zone, request message is put into
Queue, if not in critical zone, but want to enter critical zone, then compare the timestamp want into the process of critical zone, timestamp is small
Process enter critical zone.
Feature:Algorithm is complicated, " hungry to death " phenomenon easily occurs, and system is not healthy and strong;But it theoretically indicates algorithm
Feasibility, practicable algorithm will be developed.
The thought of token ring algorithm is:Whole system only has one piece of token, and only owner of a token just has into critical
The qualification in area.When process i is connected to token from process i-1, it, which is checked whether, wants to enter critical zone, if it is, into treating
After it is released, process i+1 is passed token to;If being not desired to enter, directly token is transmitted downwards.
Feature:First, token is easy to be lost, it is highly difficult in fact to detect token lost;Second, easily there is process event
Barrier, and process failure ratio less easily recovers.
The content of the invention
The embodiments of the invention provide a kind of processing method of token, device and Message Processing cluster, it is intended to solves existing
The mutually exclusive algorithm that technology provides, the problem of token lost is difficult to monitor, process collapse is difficult to recover.
On the one hand, there is provided a kind of processing method of token, methods described include:
Token loop is established in the application layer of Message Processing cluster;
When node adds or exits token loop, token is produced or destroyed using simple majority Voting Algorithm;
In the transmittance process of token, the timestamp of each node last outflow token in token loop is monitored, if prison
The timestamp of node last outflow token and the time difference of current time are measured beyond the winding time of setting, then initiates route
Discovery procedure, rebuild token loop.
Further, the simple majority Voting Algorithm produces or destroyed token and includes:
Number of nodes in presetting message processing cluster is N, and N is the integer more than or equal to 1;
When the token loop for monitoring to be made up of N number of node in Message Processing cluster node addition or exit described
During token loop, the number of nodes P described in dynamic calculation in token loop;
When P, which is more than the house tail of (N+2)/2, rounds value, if automatically generating new token without token in token loop;
If having token in token loop, former token is maintained;
When P, which is less than or equal to the house tail of (N+2)/2, rounds value, if having token in token loop, the token is destroyed.
Further, described when P gives up tail less than or equal to (N+2)/2 and rounds value, in addition to:
If being hung up in token loop without token, system, new node is waited to add in the Message Processing cluster.
Further, the node in the Message Processing cluster includes ballot tiny node, common tiny node and monitoring station section
Point.
On the other hand, there is provided a kind of processing unit of token, described device include:
Token loop establishes unit, for establishing token loop in the application layer of Message Processing cluster;
Token produces or destroyed unit, for when node adds or exits token loop, being thrown using simple majority
Ticket algorithm produces or destroyed token;
Token winding time supervision unit, in the transmittance process of token, monitoring each node in token loop
Last time spreads out of the timestamp of token, if monitoring, the timestamp of node last outflow token and the time difference of current time exceed
The winding time of setting, then route finding process is initiated, rebuild token loop.
Further, the token produces or destroyed unit and includes:
Number of nodes presetting module, the number of nodes handled for presetting message in cluster are N, and N is whole more than or equal to 1
Number;
Number of nodes statistical module, it is made up of for working as to monitor to be added by node N number of node in Message Processing cluster
Token loop or when exiting the token loop, the number of nodes P described in dynamic calculation in token loop;
Token generation module, for when P is more than (N+2)/2 and gives up tail and round value, if without token in token loop, automatically
Produce new token;
Token maintenance module, if for having token in token loop, maintain former token;
Token destroy module, for when P be less than or equal to (N+2)/2 give up tail round value when, if having token in token loop,
Destroy the token.
Further, the token produces or destroyed unit and also includes:
Node, which adds, waits module, if for being hung up in token loop without token, system, waits new node to add institute
State in Message Processing cluster.
Further, described device is built in the respective nodes in Message Processing cluster, in the Message Processing cluster
Node include ballot tiny node, common tiny node and monitoring tiny node.
Another further aspect, there is provided a kind of Message Processing cluster, the Message Processing cluster include vote tiny node, ormal station
Node and monitoring tiny node, the processing dress of token as described above is built-in with the respective nodes in the Message Processing cluster
Put.
In the embodiment of the present invention, after the application layer of Message Processing cluster establishes token loop, when node addition or move back
When going out the token loop, token is produced or destroyed using simple majority Voting Algorithm, avoids and occurs 2 in Message Processing cluster
Or the token loop of more than 2;In addition, monitored to the token winding time of each node, to find that token is in time
No loss, and in token lost, token loop is rebuild, solve prior art, the loss of token can not supervise in token loop
While the problems such as pipe, the reliability of distributed cluster system is substantially increased.
Brief description of the drawings
Fig. 1 is the implementation process figure of the processing method for the token that the embodiment of the present invention one provides;
Fig. 2 is the implementation process figure for the route finding process that the embodiment of the present invention one provides;
Fig. 3 is the implementation process figure for the route synchronization process that the embodiment of the present invention one provides;
Fig. 4 is the implementation process figure for the token checking process that the embodiment of the present invention one provides;
Fig. 5 is the implementation process figure that the token that the embodiment of the present invention one provides produces process;
Fig. 6 is the implementation process figure for the alternative space process that the embodiment of the present invention one provides;
Fig. 7 is the structured flowchart of the processing unit for the token that the embodiment of the present invention two provides.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
In embodiments of the present invention, token loop is established in the application layer of Message Processing cluster;When node adds or moves back
When going out token loop, token is produced or destroyed using simple majority Voting Algorithm;In the transmittance process of token, token ring is monitored
In road each node last outflow token timestamp, if monitor node last outflow token timestamp with it is current when
Between time difference beyond the winding time of setting, then initiate route finding process, rebuild token loop.
It is described in detail below in conjunction with realization of the specific embodiment to the present invention:
Embodiment one
Fig. 1 shows the implementation process of the processing method for the token that the embodiment of the present invention one provides, and details are as follows:
In step S101, token loop is established in the application layer of Message Processing cluster.
In step s 102, when node adds or when exiting token loop, produced using simple majority Voting Algorithm or
Destroy token.
In embodiments of the present invention, in order to avoid logical loops that Message Processing cluster is split into two or more
Serialize " fissure " phenomenon of work, therefore automatically generate and destroy using the Voting Algorithm of " simple majority of (N+2)/2 "
Token, the algorithm of simple majority Voting Algorithm are as follows:
Number of nodes in presetting message processing cluster be N, and N is the integer more than or equal to 1, when having monitored node addition
The token loop that is made up of N number of node in Message Processing cluster or when exiting the token loop, order described in dynamic calculation
Number of nodes P in board loop, when P, which is more than the house tail of (N+2)/2, rounds value, if being automatically generated in token loop without token
New token;If having token in token loop, former token is maintained;When P, which is less than or equal to the house tail of (N+2)/2, rounds value, if order
There is token in board loop, then destroy the token, if being hung up in token loop without token, system, wait new node to add institute
State in Message Processing cluster.
According to majority voting algorithm briefly above, even number platform main frame of odd number platform main frame (node) redundancy ability than odd number+1
Also it is eager to excel, so in actual deployment typically using odd number platform main frame composition Message Processing cluster.For 3 Message Processing clusters
Can 1 mechanical disorder of disaster tolerance, 5 Message Processing clusters can hold 1 failure or 2 simultaneous faults, by that analogy, this simple majority
Voting Algorithm only holds the disaster and failure of a small number of machine nodes, but for relative unit, improves reliability.Individually below with 3
Platform, 5, the fault rate of Message Processing cluster is calculated exemplified by 7.
Premise:
1), the probability of the failure of all node hosts is roughly the same, i.e., fault rate is q.
2), assuming that 1 failure occurred in 100 days in main frame, then the fault rate q for calculating the main frame is 1%, the like.
3), assume that the fault rate q of All hosts is no more than 10%, i.e., occur being less than 1 failure in 10 days.
1 fault rate Q (1)=q
3 fault rate Q (3)=3q2(1-q)+q3=3q2-2q3
5 fault rate Q (5)=10q3(1-q)2+5q4(1-q)+q5=10q3-15q4+6q5
7 fault rate Q (7)=35q4(1-q)3+21q5(1-q)2+7q6(1-q)+q7=35q4-84q5+70q6-20q7
3 principals and subordinates arbitrate fault rate Q (secondary)=2q2(1-q)+q3=2q2-q3
Table 1 shows the fault rate of Message Processing cluster:
Q(1) | Q(3) | Q(5) | Q(7) | Q (secondary) |
0.1 | 0.028 | 0.00856 | 0.002728 | 0.018 |
0.01 | 0.000298 | 9.8506E-06 | 3.4167E-07 | 0.000198 |
0.001 | 0.000002998 | 9.98501E-09 | 3.49161E-11 | 0.000001998 |
Table 1
In terms of above-mentioned Message Processing clustering fault rate, fault rate declines quickly, and MPU global reliabilities can be lifted
99.97%~99.999999%.
Wherein, all nodes in Message Processing cluster have unified planning coding, and static configuration has website class
Type.Mode, the quantity of different type website, the function description of different type website and difference caused by different types of website
The flow that types of sites is participated in refers to the table 2 in step S102, and as shown in Table 2, the generation of token is by throwing with destroying work
Ticket station, ormal station and monitoring station, which coordinate, to be completed.
In step s 103, in the transmittance process of token, each node last outflow token in token loop is monitored
Timestamp, if monitor node last outflow token timestamp and current time time difference beyond setting winding
Between, then route finding process is initiated, rebuilds token loop.
In embodiments of the present invention, the transitive dependency of token in established between each node it is unique, stably, efficient token
Loop.Management to token loop includes node discovery, route synchronization, token inspection, token generation, alternative space, winding prison
The combination process such as election, node depending on grade basic procedure and monitoring station are dynamically added, node dynamic exits.Message Processing cluster
Interior each node is divided into monitoring station, ormal station, polling station by the management responsibility to token.
Table 2 shows the Functional division of each node
Table 2
Token loop management algorithm is built upon carries out unified planning coding to all nodes in Message Processing cluster
On the basis of and static configuration type of site.
The foundation of token loop is completed on route discovery, route synchronization the two basic handling flows, token
The foundation of loop, the addition of node, the exiting of node, monitoring station election etc. follow route discovery, route synchronization, the two bases
This flow.
Table 3 shows the promoter of the route discovery of token loop, route synchronization, initiates condition and the content of execution
Description:
Table 3
Specifically, route discovery flow is as shown in Fig. 2 comprise the following steps:
<1>, new entrant, find that node abnormal node occurs, do not received order in each route discovery winding time
Board and receive system control rerouting order, then initiate route discovery instruction.
<2>, promoter according to cluster global configuration according to it is incremented by successively from its adjacent node begin attempt to connect searching can
Use succession.
<3>If, attempt connection it is failed, the node hang up, wait other nodes add.
<4>, such as connect succession success, update routing table itself.
<5>, promoter send route discovery instruction, pass to succession.
<6>, succession compare route discovery instruction in promoter ID and self ID.
<7>If, promoter ID>Self ID, route discovery instruction stop, and initiate new route discovery instruction.
<8>If, promoter ID<Self ID, the life cycle during route discovery is instructed subtract 1, if still above 0, press
Step<2>-<8>Continue to transmit route discovery instruction, otherwise terminate and transmit.
<9>If, promoter's ID=self IDs, illustrate that a circle has been transmitted in route discovery instruction, route instruction terminates, renewal
Its routing table, the node are cluster monitoring station.
Route synchronization flow is as shown in figure 3, comprise the following steps:
<1>, route discovery instruction normal termination and instruct the maximum sequence number of serial number present node issue, monitored by MPU
Stand and initiate route synchronization instruction.
<2>, succession receive route synchronization instruction after, the relation of discrimination instruction promoter ID and self ID.
<3>If, promoter ID>Self ID, the transmission of the route synchronization is terminated, initiating route synchronization again by the node refers to
Order.
<4>If, promoter ID<Self ID, itself routing table and monitoring station information are updated, the life during route synchronization is instructed
The life cycle subtracts 1, and step is pressed if still above 0<2>-><5>Continue to transmit, otherwise terminate and transmit.
<5>If, promoter's ID=self IDs, illustrate that a circle has been transmitted in route synchronization instruction, instruction terminates.
Table 4 shows the maintenance description of token loop:
Table 4
Token work management includes token inspection, token generation, alternative space, token winding time monitoring and token
Can monitoring.
Table 5 shows the interaction content in token work management flow:
Table 5
Wherein, token check process is as shown in figure 4, comprise the following steps:
<1>, token inspection instruction is initiated by monitoring station, and pass to its successor.
<2>, succession receive token inspection instruction, the relation of discrimination instruction promoter ID and self ID.
<3>If, promoter ID>Self ID, the transmission of token inspection instruction is terminated, token inspection is initiated by the node again
Look into instruction.
<4>If, promoter ID<Self ID, the token mark in being instructed according to the inspection of self-operating status update token, and
Life cycle in instruction is subtracted 1, step is pressed if still above 0<1>-<5>) continue to transmit instruction, otherwise terminate and transmit.
<5>If, promoter's ID=self IDs, illustrate to check that a circle has been transmitted in instruction, instruction terminates.
<6>, monitoring station is by the token mark in the token inspection that receives instruction, and initiate time and last time
The time of token is received, differentiates in Message Processing cluster and whether there is token.
Wherein, token produces flow as shown in figure 5, comprising the following steps:
<1>, monitoring station initiate token check process, and differentiate that token is not present in token loop.
<2>, judge that effective number of nodes exceedes half in routing table.
<3>, monitoring station initiates maximum sequence number to all polling stations and inquires.
<4>, monitoring station Receive sequence number inquiry result, maximum sequence number M is taken in all response results, and increase on this basis
Add certain radix, form all nodes * maximum token step-lengths of start sequence number N=M+ of new token.
<5>, monitoring station produces new token, and issues token update notification to all polling stations.
Wherein, alternative space flow is as shown in fig. 6, comprise the following steps:
<1>, node after the token of transmission is received, the mark for the machine being possessed token is set to true, while response is returned
Return.
<2>, node is when possessing token, to serializing in sending the instruction that token step-length is not more than in buffering area,
Combine simultaneously and carry out multicast transmission.
<3>, when the instruction of sequence of tokens reach token step-length or send buffering area without waiting to send instructions, then update token letter
Cease and pass to its successor, the node enters armed state, and records the timestamp into armed state.
<4>, alternative space to succession when, if occur repeatedly transmit failure after, the succession the machine routing table
State be changed to ' N ' down state, and a route discovery instruction is triggered, further according to the enabled node in routing table after renewal
Whether number reaches minimum working host quantity, if stopping transmitting less than the value token, and sends alarm.
<5>, node in armed state, prefetch service order and monitor whether the stand-by period exceedes the winding time, if exceeding
Then stop prefetching service order and enter suspended state, while trigger a route discovery and instruct.
Specifically, the monitoring of token refers to monitor the operation conditions of token in token loop, including token winding
Time monitoring and this two parts of token performance monitoring.Token winding time monitoring refers to that each node in Message Processing cluster is equal
The timestamp of last time outflow token is recorded, monitoring station timing differentiates whether the time difference of the timestamp and current time exceeds setting
The winding time, if exceeding, need to initiate route finding process again, rebuild token loop.
Token performance monitoring be by the monitoring station delay enclosed of monitoring alternative space one and handling capacity, monitoring result with token and
Transmit.
It by monitoring of the monitoring station to the token winding time, can monitor whether token is lost, if lost, rebuild
Token loop, new token is produced, solve prior art, the loss of token such as can not supervise at the same of problem in token loop
When, substantially increase the reliability of distributed cluster system.
The present embodiment, with reference to token-ring network principle, after the application layer of Message Processing cluster establishes token loop, work as node
When adding or exit the token loop, token is produced or destroyed using simple majority Voting Algorithm, avoids Message Processing collection
Occurs the token loop of 2 or more than 2 in group;In addition, the token winding time of each node is monitored, with timely
It was found that whether token is lost, and in token lost, token loop is rebuild, solves prior art, token in token loop
While loss such as can not supervise at the problem, the reliability of distributed cluster system is substantially increased.
Can one of ordinary skill in the art will appreciate that realizing that all or part of step in the various embodiments described above method is
To instruct the hardware of correlation to complete by program, corresponding program can be stored in a computer read/write memory medium
In, described storage medium, such as ROM/RAM, disk or CD.
Embodiment two
Fig. 7 shows the concrete structure block diagram of the processing unit for the token that the embodiment of the present invention two provides, for the ease of saying
It is bright, it illustrate only the part related to the embodiment of the present invention.Message Processing cluster include vote tiny node, common tiny node and
Tiny node is monitored, the processing unit of the token, the place of the token are built-in with the respective nodes in the Message Processing cluster
Reason device 7 includes:Token loop establishes unit 71, token produces or destroys unit 72 and token winding time supervision unit
73。
Wherein, token loop establishes unit 71, for establishing token loop in the application layer of Message Processing cluster;
Token produces or destroyed unit 72, for adding or when exiting token loop when node, using simple majority
Voting Algorithm produces or destroyed token;
Token winding time supervision unit 73, in the transmittance process of token, monitoring each section in token loop
The timestamp of point last time outflow token, if monitoring, the timestamp of node last outflow token and the time difference of current time surpass
Go out the winding time of setting, then initiate route finding process, rebuild token loop.
Include specifically, the token produces or destroyed unit 72:
Number of nodes presetting module, it is N to handle the number of nodes in cluster for presetting message;
Number of nodes statistical module, it is made up of for working as to monitor to be added by node N number of node in Message Processing cluster
Token loop or when exiting the token loop, the number of nodes P described in dynamic calculation in token loop;
Token generation module, for when P is more than (N+2)/2 and gives up tail and round value, if without token in token loop, automatically
Produce new token;
Token maintenance module, if for having token in token loop, maintain former token;
Token destroy module, for when P be less than or equal to (N+2)/2 give up tail round value when, if having token in token loop,
Destroy the token.
Further, the token produces or destroyed unit 72 and also includes:
Node, which adds, waits module, if for being hung up in token loop without token, system, waits new node to add institute
State in Message Processing cluster.
Further, described device 7 is built in the respective nodes in Message Processing cluster, in the Message Processing cluster
Node include ballot tiny node, common tiny node and monitoring tiny node.
The processing unit of token provided in an embodiment of the present invention can be applied in foregoing corresponding embodiment of the method one, in detail
Feelings will not be repeated here referring to the description of above-described embodiment one.
It is worth noting that, in the processing unit embodiment of above-mentioned token, included unit is simply according to function
What logic was divided, but above-mentioned division is not limited to, as long as corresponding function can be realized;In addition, each function
The specific name of unit is also only to facilitate mutually distinguish, the protection domain being not intended to limit the invention.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement made within refreshing and principle etc., should be included in the scope of the protection.
Claims (6)
1. a kind of processing method of token, it is characterised in that methods described includes:
Token loop is established in the application layer of Message Processing cluster;
When node adds or exits token loop, token is produced or destroyed using simple majority Voting Algorithm;
In the transmittance process of token, the timestamp of each node last outflow token in token loop is monitored, if monitoring
There are the timestamp of node last outflow token and the time difference of current time to exceed the winding time of setting, then initiate route discovery
Process, rebuild token loop;
The simple majority Voting Algorithm, which produces or destroyed token, to be included:
Number of nodes in presetting message processing cluster is N, and N is the integer more than or equal to 1;
When the token loop for monitoring to be made up of N number of node in Message Processing cluster node addition or exit the token
During loop, the number of nodes P described in dynamic calculation in token loop;
When P, which is more than the house tail of (N+2)/2, rounds value, if automatically generating new token without token in token loop;
If having token in token loop, former token is maintained;
When P, which is less than or equal to the house tail of (N+2)/2, rounds value, if having token in token loop, the token is destroyed.
2. the method as described in claim 1, it is characterised in that described when P gives up tail less than or equal to (N+2)/2 and rounds value,
Also include:
If being hung up in token loop without token, system, new node is waited to add in the Message Processing cluster.
3. the method as described in claim 1, it is characterised in that the node in the Message Processing cluster saves including polling station
Point, common tiny node and monitoring tiny node.
4. a kind of processing unit of token, it is characterised in that described device includes:
Token loop establishes unit, for establishing token loop in the application layer of Message Processing cluster;
Token produces or destroyed unit, for when node adds or exits token loop, being voted and being calculated using simple majority
Method produces or destroyed token;
Token winding time supervision unit, in the transmittance process of token, monitoring each node last in token loop
The timestamp of token is spread out of, the timestamp of node last outflow token and the time difference of current time exceed setting if monitoring
The winding time, then initiate route finding process, rebuild token loop;
The token, which produces or destroyed unit, to be included:
Number of nodes presetting module, the number of nodes handled for presetting message in cluster are N, and N is the integer more than or equal to 1;
Number of nodes statistical module, for when the order for monitoring to be made up of N number of node in Message Processing cluster node addition
Board loop or when exiting the token loop, the number of nodes P described in dynamic calculation in token loop;
Token generation module, for when P is more than the house tail of (N+2)/2 and rounds value, if token loop is interior without token, automatically generating
New token;
Token maintenance module, if for having token in token loop, maintain former token;
Token destroys module, for when P gives up tail less than or equal to (N+2)/2 and rounds value, if having token in token loop, destroying
The token.
5. device as claimed in claim 4, it is characterised in that the token, which produces or destroyed unit, also to be included:
Node, which adds, waits module, if for being hung up in token loop without token, system, waits and disappearing described in new node addition
In breath processing cluster.
6. device as claimed in claim 4, it is characterised in that described device is built in the respective nodes in Message Processing cluster
In, the node in the Message Processing cluster includes ballot tiny node, common tiny node and monitoring tiny node.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410550612.8A CN104468302B (en) | 2014-10-16 | 2014-10-16 | A kind of processing method and processing device of token |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410550612.8A CN104468302B (en) | 2014-10-16 | 2014-10-16 | A kind of processing method and processing device of token |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104468302A CN104468302A (en) | 2015-03-25 |
CN104468302B true CN104468302B (en) | 2018-03-30 |
Family
ID=52913709
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410550612.8A Active CN104468302B (en) | 2014-10-16 | 2014-10-16 | A kind of processing method and processing device of token |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104468302B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107306289B (en) * | 2016-04-21 | 2020-11-27 | 中国移动通信集团重庆有限公司 | Load balancing method and device based on cloud computing |
US10572376B2 (en) * | 2016-12-30 | 2020-02-25 | Intel Corporation | Memory ordering in acceleration hardware |
US11200186B2 (en) | 2018-06-30 | 2021-12-14 | Intel Corporation | Apparatuses, methods, and systems for operations in a configurable spatial accelerator |
CN109614403B (en) * | 2018-10-24 | 2020-03-06 | 北京三快在线科技有限公司 | Data consistency checking method and device for cluster service node |
US11907713B2 (en) | 2019-12-28 | 2024-02-20 | Intel Corporation | Apparatuses, methods, and systems for fused operations using sign modification in a processing element of a configurable spatial accelerator |
CN112131012B (en) * | 2020-11-26 | 2021-07-20 | 九州华兴集成电路设计(北京)有限公司 | Token processing method, token processing device and computer readable storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH06112964A (en) * | 1992-09-30 | 1994-04-22 | Yokokawa Denshi Kiki Kk | Loop controller and its automatic changeover method in token loop lan |
CN1649319A (en) * | 2005-02-04 | 2005-08-03 | 西安电子科技大学 | Token transfer and manage method for Ad Hoc network |
CN1964353A (en) * | 2006-12-05 | 2007-05-16 | 上海大学 | A protocol stack facing wireless industrial control network |
CN103533661A (en) * | 2013-10-23 | 2014-01-22 | 中国舰船研究设计中心 | Wireless channel access control method based on virtual token |
-
2014
- 2014-10-16 CN CN201410550612.8A patent/CN104468302B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH06112964A (en) * | 1992-09-30 | 1994-04-22 | Yokokawa Denshi Kiki Kk | Loop controller and its automatic changeover method in token loop lan |
CN1649319A (en) * | 2005-02-04 | 2005-08-03 | 西安电子科技大学 | Token transfer and manage method for Ad Hoc network |
CN1964353A (en) * | 2006-12-05 | 2007-05-16 | 上海大学 | A protocol stack facing wireless industrial control network |
CN103533661A (en) * | 2013-10-23 | 2014-01-22 | 中国舰船研究设计中心 | Wireless channel access control method based on virtual token |
Also Published As
Publication number | Publication date |
---|---|
CN104468302A (en) | 2015-03-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104468302B (en) | A kind of processing method and processing device of token | |
WO2018072618A1 (en) | Method for allocating stream computing task and control server | |
WO2016107172A1 (en) | Post-cluster brain split quorum processing method and quorum storage device and system | |
CN106790694A (en) | The dispatching method of destination object in distributed system and distributed system | |
CN102308559B (en) | Voting arbitration method and apparatus for cluster computer system | |
CN103780432B (en) | Parking lot O&M method, Carriageway controlling machine, server, mobile terminal and system | |
CN103995868B (en) | The global transaction manager and transaction methods of Based on Distributed system | |
CN104391777B (en) | Cloud platform and its operation and monitoring method and device based on (SuSE) Linux OS | |
CN111949444A (en) | Data backup and recovery system and method based on distributed service cluster | |
WO2017107827A1 (en) | Method and apparatus for isolating environment | |
CN106487486A (en) | Method for processing business data centring system | |
CN107659948B (en) | Method and device for controlling access of AP (access point) | |
CN103036719A (en) | Cross-regional service disaster method and device based on main cluster servers | |
CN107769943A (en) | A kind of method and apparatus of active and standby cluster switching | |
CN110990200A (en) | Flow switching method and device based on multi-activity data center | |
CN107347084A (en) | The method, apparatus and system of distributed lock management | |
CN107360025A (en) | A kind of distributed memory system cluster monitoring method and apparatus | |
CN110119325A (en) | Server failure processing method, device, equipment and computer readable storage medium | |
CN105072386A (en) | Video networking system based on multicast technologies and state monitoring method | |
CN103345439A (en) | Method and device for monitoring health states of full links in information system | |
CN109165122B (en) | Method for improving disaster recovery capability of application system same city multi-park deployment realized based on block chain technology | |
CN102387210B (en) | Distribution type file system monitoring method based on rapid synchronization network | |
CN108445857A (en) | A kind of 1+N redundancy scheme design methods of SCADA system | |
CN101778091B (en) | Expandable security server alternate system | |
CN107239235A (en) | A kind of many RAID synchronous method living of many controls and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |