CN105515912A - Detecting and processing method for validity of link among multiple nodes - Google Patents
Detecting and processing method for validity of link among multiple nodes Download PDFInfo
- Publication number
- CN105515912A CN105515912A CN201510970908.XA CN201510970908A CN105515912A CN 105515912 A CN105515912 A CN 105515912A CN 201510970908 A CN201510970908 A CN 201510970908A CN 105515912 A CN105515912 A CN 105515912A
- Authority
- CN
- China
- Prior art keywords
- time
- link
- heartbeat
- node
- recovery
- 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
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/08—Testing, supervising or monitoring using real traffic
-
- 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
- H04L43/0805—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability
- H04L43/0811—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability by checking connectivity
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/02—Traffic management, e.g. flow control or congestion control
- H04W28/0289—Congestion control
Abstract
The invention discloses a detecting and processing method for validity of a link among multiple nodes, and belongs to the field of multi-node link transmission of a TETRA digital trunking system. A multi-node data mutual transmission link generally has multiple phenomena, including, long-term validity, link long-term disconnection, link recovery after disconnection, disconnection in link validity process, and alternate link disconnection and recovery. Due to the phenomena, various abnormal conditions for applications are aroused in a practical running process. The detecting and processing method for validity of the link among multiple nodes comprises the steps of calculating time when a heartbeat request is sent at each time; dispersing the time on a time grid; detecting the validity of the link in a preset period; and performing detection for link recovery by adopting a hypothetical recovery strategy in a link recovery process. Through the ways mentioned above, feedback of the validity of the link is added, and accurate guarantee is provided for link selection of the applications.
Description
Technical field
The present invention relates to TETRA digital cluster system Multi-node link transmission field, especially relate to linkage availability between a kind of multinode and detect and processing method.
Background technology
In digital cluster system, switching center can regard with base station the node intercomed mutually as, is communicated, and require between each node that the link between two nodes has the requirement of reliability between each node by selected communication protocol.Under the link circuit condition of reality, the state of link may have that link is permanently effective, link disconnects for a long time, link first disconnects rear recovery, link effective procedure breaks, link disconnects and recover the phenomenons such as alternately appearance.When complex network quality, unstable transmission system can on the function of Digital Clustering produce various expection less than impact, such as cause the delay of call setup, call setup failure etc.Detect the stability of link, degree of jitter anticipation is carried out to the situation of the link in future, to the function of digital cluster system, there is very great meaning.
In order to detect these states, the mode that prior art adopts N continuous time heartbeat detection all not receive the other side's response message usually detects, this detection mode can detect above phenomenon to a certain extent, but in practice process, the value of N decides the speed degree of testing result, the too small detection of N value can be very fast, but the tolerance of link is too low; And N value is excessive, detecting can be very slow, but the tolerance of link can be very high.N continuous time heartbeat detection disconnects link and recovers to replace the condition detection occurred and can lose efficacy in addition, sometimes also can bring the possibility of continuous Link State alarm.
Along with increasing of number of nodes, a node needs the quantity of the node connected also increasing, and will bring the requirement of single node and Multi-node link high concurrency like this, also detects the too much puzzlement of required timer for reliability between node detects to cause simultaneously.Meeting like this, node is more, more to the consumption of resource, leaves the resource of data packets between node for fewer.
Summary of the invention
Technical problem to be solved by this invention is: provide link congestion, shaking detection and processing method between a kind of switching center and base station site.In Digital Clustering field, the real-time of digital cluster system be ensured, a kind of stable link must be provided between switching center and base station, in the face of the more serious link of shake will provide alarm in time, and can recover timely when link-recovery.Carrying out that also can be intelligent in the face of more complicated dither cycle is predicted and judges, to ensure that between switching control center and base station, data can correctly, in real time transmit.
Object of the present invention is achieved through the following technical solutions: linkage availability detection method between a kind of multinode, comprises the following steps:
S1: set up internodal network and connect, Link State corresponding for each node is initialized as Link down status;
S2: source node sends heartbeat request message respectively to each peer node, the time that record heartbeat request message sends, and according to heartbeat response wait time, calculate each nodes heart beat time-out time;
S3: source node waits for the message that each peer node sends within the current preset cycle, if the message receiving that peer node sends, record receives the time of message, and the state upgrading this link is effective; If do not receive the message that peer node sends, judge that whether this link is effective, the record heartbeat timeout time according to slow detection; Wherein, message comprises heartbeat response message or heartbeat request message;
S4: calculate the time that each node sends heartbeat request message next time respectively, and when corresponding node is placed in layout; Wherein, described time layout is: timeline is divided into same intervals, timeline between two adjacent spaces is as layout when one, time layout internal memory put the heartbeat affairs that will complete in this time interval, heartbeat affairs comprise: nodes heart beat initiates affairs and nodes heart beat time-out affairs, and the heartbeat affairs of each node are on average disperseed then in layout;
S5: according to each node heartbeat response wait time next time, calculates each node heartbeat timeout time next time, and when corresponding node is placed in layout;
S6: enter next predetermined period, using next predetermined period as the current preset cycle, performs S3.
Wherein, the slow detection of the basis described in S3 judges that whether this link is effective, is specially: N continuous time transmission heartbeat request message, and accumulative appearance does not receive heartbeat response message number of times and reaches predetermined threshold value, then Link down; Otherwise link is effective; Wherein, N is natural number.
Wherein, N is 6, and predetermined threshold value is 3.
Wherein, described in S4, calculate the time that each node sends heartbeat request message next time respectively, be specially:
T
Heatbeat=MAX{T
HeartbeatExpiry,T
DataConfirm,T
DataIndication,T
HeartbeatRSP}+T
Period;
Wherein: T
heartbeat: present node sends the time of heartbeat request message next time; T
heartbeatExpiry: the time of the last nodes heart beat time-out of present node; T
dataConfirm: the time that the last node data bag of present node confirms; T
dataHeartRSP: the time of the last nodes heart beat response of present node; T
dataIndcation: the present node the last time receiving node data bag; T
period: heartbeat request message sends the cycle.
Wherein, described in S5 according to each node heartbeat response wait time next time, calculate each node heartbeat timeout time next time, be specially:
T
Expiry=T
Heartbeat+T
Wait,
Wherein: T
expiry: present node is the heartbeat timeout time next time; T
heartbeat: present node sends the time of heartbeat request message next time; T
wait: present node is heartbeat response wait time next time.
A recovery detection method for link exception between multinode, comprises the following steps:
(1) if current ink is invalid, recovery policy hypothetical is fast adopted to carry out current ink recovery;
(2) judge that whether recovery policy is successful, if success, process ends; If failure, then think that current ink is shaken, adopt slow Restoration Mechanism to judge that whether current ink is effective.
Wherein, described recovery policy hypothetical is fast specially: when link is in disarmed state for a long time, if link receives heartbeat response, this link-recovery.
Wherein, described slow Restoration Mechanism is specially: the packet loss in statistics setting-up time carrys out anticipation Link State, when packet loss is greater than upper threshold value, and judges Link down; When packet loss is less than lower threshold value, then judge that link is effective; When packet loss ratio is positioned at threshold interval, then by same Packet Generation twice.
Wherein, described threshold interval is: 1% ~ 3%.
Compared with prior art, the advantage of the inventive method is:
(1) break-make anticipation accurately and effectively can be reached on IP link and carries out data transmission.
(2) can be in digital cluster system, between multiple node, data transmission provides very intelligent bearing capacity.Can describe with following word: link is stablized, and normally works; Link is obstructed, timely alarm; The little shake of link, strengthens transmission channel; The large shake of link, timely alarm.
Accompanying drawing explanation
Fig. 1 is time lattice structure figure of the present invention;
Layout process chart when Fig. 2 is of the present invention;
Fig. 3 be the present invention under Link down status, heartbeat process chart;
Fig. 4 be the present invention under Link up status, heartbeat process chart.
Embodiment
Below in conjunction with accompanying drawing, the method for the invention is described in further detail.
The situation of link is generally divided into following several situation: link is unimpeded, link delay is large, link has packet loss once in a while, link randomness packet loss, isl cycle packet loss, a large amount of packet loss of link, link are obstructed.These all have a significant impact the performance of digital cluster system.The inventive method by adopting the mechanism of message echo between switching control center and base station, and calculates echo delay, to analyze and draws the situation of current ink, and carry out anticipation to the link stability in future according to the data of a period of time to link condition.
Link is unimpeded, link delay is large, link this several situation obstructed can directly just can be reached a conclusion by the response of echo, and these conclusions directly can as the direct feedback of the situation of link.In link flapping i.e. link, have detection when packet loss to need to analyze the echo feedback in a period of time interval, packet loss ratio in the analystal section time, and packet loss trend, carry out anticipation to the link condition in future.In the face of packet loss ratio is at the link of threshold value (1% ~ 3%), the mode of same Packet Generation twice is adopted to increase the transmission success rate of data, in the face of packet loss ratio will stop the transmission of data at the link of threshold value more than 3%, and produce warning information, inform that engineering staff carries out looking into of link and repaiies.
The method that between multinode, linkage availability detects, comprises the following steps:
S1: set up internodal network according to communication requirement and connect, Link State corresponding for each node is initialized as link down state;
Embodiment: switching center and base station are regarded as identical transmission node, is connected by IP network.In node, set up the storage area of the information of multiple node, the information of each node is stored in independent region, and is initialized as link down state to Link State corresponding to each node.
S2: source node sends heartbeat request message respectively to each peer node, the time that record heartbeat request message sends;
S3: source node waits for the message that each peer node sends within the current preset cycle, if the message receiving that peer node sends, record receives the time of message, and the state upgrading this link is effective; If do not receive the message that peer node sends, judge that whether this link is effective, the record heartbeat timeout time according to slow detection; Wherein, message comprises heartbeat response message or heartbeat request message;
Embodiment: after system starts, node sends heartbeat message respectively to multiple peer node, then heartbeat response message is waited for, if receive heartbeat response message or peer node to send and the heartbeat message that comes, the state upgrading this link is available, and notifying correlation module, this link can be used, and can send packet on this link;
If do not receive heartbeat response message or peer node to send and the heartbeat message that comes, then the continuous heartbeat request message that send for 6 times, accumulative appearance does not receive heartbeat response message for 3 times, then Link down; Otherwise link is effective.As shown in Figure 4.
S4: calculate the time that each node sends heartbeat request message next time respectively, and when corresponding node is placed in layout;
Embodiment: when sending heartbeat message, sending packet or receiving the data packet message of Correspondent Node, the following information of real time record record: the time that heartbeat sends, the time receiving heartbeat response, the heartbeat timeout time, send packet time, receive packet receive response time, response package time-out time, receive Correspondent Node packet time; Calculated the time of heartbeat next time by these temporal informations above, and this time be placed on plan in advance time layout in.
Described time layout is: timeline is divided into same intervals, timeline between two adjacent spaces is as layout when one, time layout internal memory put the heartbeat affairs that will complete in this time interval, heartbeat affairs comprise: nodes heart beat initiates affairs and nodes heart beat time-out affairs, and the heartbeat affairs of each node are on average disperseed then in layout.As shown in Figure 1.
After system starts, first prepare to send heartbeat message to each node, when being placed on corresponding by these affairs, the nodes heart beat of layout is initiated in affairs; Then according to first processing node heartbeat timeout affairs, affairs when reprocessing nodes heart beat initiates the order pair of affairs in layout process.Time layout in transaction complete after, when waiting for next, the arrival of layout, carries out the transaction of layout during the next one.As shown in Figure 2.
Each node sends the time of heartbeat request message next time, is specially:
T
Heatbeat=MAX{T
HeartbeatExpiry,T
DataConfirm,T
DataIndication,T
HeartbeatRSP}+T
Period;
Wherein: T
heartbeat: present node sends the time of heartbeat request message next time; T
heartbeatExpiry: the time of the last nodes heart beat time-out of present node; T
dataConfirm: the time that the last node data bag of present node confirms; T
dataHeartRSP: the time of the last nodes heart beat response of present node; T
dataIndcation: the present node the last time receiving node data bag; T
period: heartbeat request message sends the cycle.
In this way, oriented peer node time of sending heartbeat be just distributed on timeline equably, avoid synchronization and send the network congestion that a large amount of heartbeat message causes.
S5: according to each node heartbeat response wait time next time, calculates each node heartbeat timeout time next time, and when corresponding node is placed in layout; Be specially:
T
Expiry=T
Heartbeat+T
Wait,
Wherein: T
expiry: present node is the heartbeat timeout time next time; T
heartbeat: present node sends the time of heartbeat request message next time; T
wait: present node is heartbeat response wait time next time.
S6: enter next predetermined period, using next predetermined period as the current preset cycle, performs S3.
When Fig. 3 is Link down, carry out the flow chart of link-recovery.A restoration methods for link exception between multinode, comprises the following steps:
(1) if current ink is invalid, recovery policy hypothetical is fast adopted to carry out current ink recovery;
(2) judge that whether recovery policy is successful, if success, process ends; If failure, then think that current ink is shaken, adopt slow Restoration Mechanism to judge that whether current ink is effective.
Embodiment: when link judges obstructed, adopts recovery policy hypothetical fast to carry out linkup notification.Be specially: when link is in disarmed state for a long time, if link receives heartbeat response, this link-recovery.
By the notice that the mechanism of fast quick-recovery may bring alternately link to disconnect and recover, very large impact will certainly be caused like this to transfer of data, here by accumulation study mechanism within a certain period of time, link disconnection alternately and recovery are more than 2 times, by adopting the slow mechanism recovered, link-recovery mechanism next time judges that this link-recovery is normal.
Slow recovery wisdom is specially: link adopts the mode of packet loss statistics to carry out anticipation to Link State, and the packet of transmission or heartbeat message can not get being designated as packet loss, and the packet loss added up in nearest a period of time carrys out anticipation Link State:
When packet loss continues to increase, be increased to more than 3%, unavailable to application module report link immediately;
When packet loss is reduced to less than 1%, then can use to application module report link;
In the face of packet loss ratio is positioned at the link of 1% ~ 3%, the mode of same Packet Generation twice is adopted to increase the transmission success rate of data, in the face of packet loss ratio will stop the transmission of data at the link of threshold value more than 3%, and produce warning information, inform that engineering staff carries out looking into of link and repaiies.
The congestion state of link can be notified application module timely in this way, obtain good effect.
Claims (9)
1. a linkage availability detection method between multinode, is characterized in that, comprise the following steps:
S1: set up internodal network and connect, Link State corresponding for each node is initialized as Link down status;
S2: source node sends heartbeat request message respectively to each peer node, the time that record heartbeat request message sends, and according to heartbeat response wait time, calculate each nodes heart beat time-out time;
S3: source node waits for the message that each peer node sends within the current preset cycle, if the message receiving that peer node sends, record receives the time of message, and the state upgrading this link is effective; If do not receive the message that peer node sends, judge that whether this link is effective, the record heartbeat timeout time according to slow detection; Wherein, message comprises heartbeat response message or heartbeat request message;
S4: calculate the time that each node sends heartbeat request message next time respectively, and when corresponding node is placed in layout; Wherein, described time layout is: timeline is divided into same intervals, timeline between two adjacent spaces is as layout when one, time layout internal memory put the heartbeat affairs that will complete in this time interval, heartbeat affairs comprise: nodes heart beat initiates affairs and nodes heart beat time-out affairs, and the heartbeat affairs of each node are on average disperseed then in layout;
S5: according to each node heartbeat response wait time next time, calculates each node heartbeat timeout time next time, and when corresponding node is placed in layout;
S6: enter next predetermined period, using next predetermined period as the current preset cycle, performs S3.
2. between a kind of multinode according to claim 1, linkage availability detects and processing method, it is characterized in that: the slow detection of the basis described in S3 judges that whether this link is effective, be specially: N continuous time sends heartbeat request message, accumulative appearance does not receive heartbeat response message number of times and reaches predetermined threshold value, then Link down; Otherwise link is effective; Wherein, N is natural number.
3. between a kind of multinode according to claim 2, linkage availability detects and processing method, and it is characterized in that: N is 6, predetermined threshold value is 3.
4. between a kind of multinode according to claim 1, linkage availability detects and processing method, it is characterized in that: calculate the time that each node sends heartbeat request message next time respectively described in S4, is specially:
T
Heatbeat=MAX{T
HeartbeatExpiry,T
DataConfirm,T
DataIndication,T
HeartbeatRSP}+T
Period;
Wherein: T
heartbeat: present node sends the time of heartbeat request message next time; T
heartbeatExpiry: the time of the last nodes heart beat time-out of present node; T
dataConfirm: the time that the last node data bag of present node confirms; T
dataHeartRSP: the time of the last nodes heart beat response of present node; T
dataIndcation: the present node the last time receiving node data bag; T
period: heartbeat request message sends the cycle.
5. between a kind of multinode according to claim 1 linkage availability detect and processing method, it is characterized in that: described in S5 according to each node heartbeat response wait time next time, calculate each node heartbeat timeout time next time, be specially:
T
Expiry=T
Heartbeat+T
Wait,
Wherein: T
expiry: present node is the heartbeat timeout time next time; T
heartbeat: present node sends the time of heartbeat request message next time; T
wait: present node is heartbeat response wait time next time.
6. the recovery detection method of link exception between multinode, is characterised in that, comprises the following steps:
(1) if current ink is invalid, recovery policy hypothetical is fast adopted to carry out current ink recovery;
(2) judge that whether recovery policy is successful, if success, process ends; If failure, then think that current ink is shaken, adopt slow Restoration Mechanism to judge that whether current ink is effective.
7. the recovery detection method of link exception between a kind of multinode according to claim 6, be characterised in that: described recovery policy hypothetical is fast specially: when link is in disarmed state for a long time, if link receives heartbeat response, this link-recovery.
8. the recovery detection method of link exception between a kind of multinode according to claim 6, be characterised in that: described slow Restoration Mechanism is specially: the packet loss in statistics setting-up time carrys out anticipation Link State, when packet loss is greater than upper threshold value, and judge Link down; When packet loss is less than lower threshold value, then judge that link is effective; When packet loss ratio is positioned at threshold interval, then by same Packet Generation twice.
9. the restoration methods of link exception between a kind of multinode according to claim 8, is characterised in that: described threshold interval is: 1% ~ 3%.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510970908.XA CN105515912B (en) | 2015-12-22 | 2015-12-22 | Linkage availability detection and processing method between a kind of multinode |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510970908.XA CN105515912B (en) | 2015-12-22 | 2015-12-22 | Linkage availability detection and processing method between a kind of multinode |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105515912A true CN105515912A (en) | 2016-04-20 |
CN105515912B CN105515912B (en) | 2018-10-16 |
Family
ID=55723571
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510970908.XA Active CN105515912B (en) | 2015-12-22 | 2015-12-22 | Linkage availability detection and processing method between a kind of multinode |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105515912B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107360012A (en) * | 2016-05-10 | 2017-11-17 | 大唐移动通信设备有限公司 | A kind of Link State processing method and apparatus for network node |
CN107659951A (en) * | 2016-07-26 | 2018-02-02 | 华为技术有限公司 | Link restoring method, device and equipment |
WO2018121353A1 (en) * | 2016-12-27 | 2018-07-05 | 北京奇虎科技有限公司 | Method of testing data channel, test server, and test system |
CN109104338A (en) * | 2018-11-12 | 2018-12-28 | 北京天融信网络安全技术有限公司 | Link intelligent detection method, storage medium and computer equipment |
CN109803024A (en) * | 2019-01-28 | 2019-05-24 | 北京中科晶上科技股份有限公司 | A method of for cluster node network |
CN112272110A (en) * | 2020-10-16 | 2021-01-26 | 苏州浪潮智能科技有限公司 | Connection jitter processing method, system and device for storage cluster controller node |
WO2021207960A1 (en) * | 2020-04-15 | 2021-10-21 | 云图技术有限公司 | Data processing method, apparatus, device and system for implementing disconnected network reconnection |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090262643A1 (en) * | 2008-04-16 | 2009-10-22 | Hangzhou H3C Technologies Co., Ltd. | Method for implementing intersecting ring network with arbitrary topology, node and intersecting ring network |
CN101640629A (en) * | 2008-07-29 | 2010-02-03 | 华为技术有限公司 | Method for monitoring link packet loss and bidirectional forwarding detector |
CN101695171A (en) * | 2009-10-16 | 2010-04-14 | 中兴通讯股份有限公司 | Method utilizing stream control transmission protocol to measure network transmission quality and device thereof |
CN103685248A (en) * | 2013-12-02 | 2014-03-26 | 许继电气股份有限公司 | Process layer tri-play message transport real-time scheduling method |
CN104933132A (en) * | 2015-06-12 | 2015-09-23 | 广州巨杉软件开发有限公司 | Distributed database weighted voting method based on operating sequence number |
-
2015
- 2015-12-22 CN CN201510970908.XA patent/CN105515912B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090262643A1 (en) * | 2008-04-16 | 2009-10-22 | Hangzhou H3C Technologies Co., Ltd. | Method for implementing intersecting ring network with arbitrary topology, node and intersecting ring network |
CN101640629A (en) * | 2008-07-29 | 2010-02-03 | 华为技术有限公司 | Method for monitoring link packet loss and bidirectional forwarding detector |
CN101695171A (en) * | 2009-10-16 | 2010-04-14 | 中兴通讯股份有限公司 | Method utilizing stream control transmission protocol to measure network transmission quality and device thereof |
CN103685248A (en) * | 2013-12-02 | 2014-03-26 | 许继电气股份有限公司 | Process layer tri-play message transport real-time scheduling method |
CN104933132A (en) * | 2015-06-12 | 2015-09-23 | 广州巨杉软件开发有限公司 | Distributed database weighted voting method based on operating sequence number |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107360012A (en) * | 2016-05-10 | 2017-11-17 | 大唐移动通信设备有限公司 | A kind of Link State processing method and apparatus for network node |
CN107659951A (en) * | 2016-07-26 | 2018-02-02 | 华为技术有限公司 | Link restoring method, device and equipment |
CN107659951B (en) * | 2016-07-26 | 2020-10-09 | 华为技术有限公司 | Link recovery method, device and equipment |
US10932140B2 (en) | 2016-07-26 | 2021-02-23 | Huawei Technologies Co., Ltd. | Link restoration method and apparatus, and device |
WO2018121353A1 (en) * | 2016-12-27 | 2018-07-05 | 北京奇虎科技有限公司 | Method of testing data channel, test server, and test system |
CN109104338A (en) * | 2018-11-12 | 2018-12-28 | 北京天融信网络安全技术有限公司 | Link intelligent detection method, storage medium and computer equipment |
CN109104338B (en) * | 2018-11-12 | 2020-10-16 | 北京天融信网络安全技术有限公司 | Link intelligent detection method, storage medium and computer equipment |
CN109803024A (en) * | 2019-01-28 | 2019-05-24 | 北京中科晶上科技股份有限公司 | A method of for cluster node network |
CN109803024B (en) * | 2019-01-28 | 2021-12-21 | 北京中科晶上科技股份有限公司 | Method for cluster node network |
WO2021207960A1 (en) * | 2020-04-15 | 2021-10-21 | 云图技术有限公司 | Data processing method, apparatus, device and system for implementing disconnected network reconnection |
CN112272110A (en) * | 2020-10-16 | 2021-01-26 | 苏州浪潮智能科技有限公司 | Connection jitter processing method, system and device for storage cluster controller node |
CN112272110B (en) * | 2020-10-16 | 2022-11-18 | 苏州浪潮智能科技有限公司 | Connection jitter processing method, system and device for storage cluster controller node |
Also Published As
Publication number | Publication date |
---|---|
CN105515912B (en) | 2018-10-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105515912A (en) | Detecting and processing method for validity of link among multiple nodes | |
CN110912780B (en) | High-availability cluster detection method, system and controlled terminal | |
US9237092B2 (en) | Method, apparatus, and system for updating ring network topology information | |
EP2798782B1 (en) | Technique for handling a status change in an interconnect node | |
KR101274323B1 (en) | Method and system for network congestion management | |
CN1859371B (en) | Method for checking flow engineering link time slot state consistency | |
CN109218126B (en) | Method, device and system for monitoring node survival state | |
CN103200109B (en) | A kind of ospf neighbor relationship management method and equipment | |
CN109245926B (en) | Intelligent network card, intelligent network card system and control method | |
CN104272654A (en) | Method and apparatus for adaptive fast start in link aggregation | |
CN106844083A (en) | A kind of fault-tolerance approach and system perceived towards stream calculation system exception | |
CN105071968A (en) | Method and device for repairing hidden failures of service plane and control plane of communication device | |
CN101753397A (en) | System, method and device for rapidly self-healing Ethernet ring | |
CN104471915A (en) | Grace state and pacing in link aggregation | |
CN102404170A (en) | Detection method, device and system of message loss | |
CN109391691A (en) | The restoration methods and relevant apparatus that NAS is serviced under a kind of single node failure | |
WO2012119522A1 (en) | Method and apparatus for processing link fault | |
CN102843274B (en) | The method of a kind of multilink fault detection and device | |
CN105224550A (en) | Distributed stream computing system and method | |
CN109688017A (en) | A kind of dual star topology redundant topology architecture system and framework implementation method | |
CN105049238A (en) | Redundancy backup method and equipment for LTE (Long Term Evolution) gateway equipment exchange subsystem | |
CN109327383A (en) | A kind of fault handling method and equipment | |
CN106921532A (en) | A kind of performance management method, the device of business catenary system | |
CN103414591A (en) | Method and system for fast converging when port failure is recovered | |
CN112822283B (en) | Edge node control method and device, control node and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |