CN113872834A - Visual monitoring method and system for distributed system - Google Patents
Visual monitoring method and system for distributed system Download PDFInfo
- Publication number
- CN113872834A CN113872834A CN202111217462.5A CN202111217462A CN113872834A CN 113872834 A CN113872834 A CN 113872834A CN 202111217462 A CN202111217462 A CN 202111217462A CN 113872834 A CN113872834 A CN 113872834A
- Authority
- CN
- China
- Prior art keywords
- node
- distributed system
- sub
- graph
- fractal
- 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
Images
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
- H04L43/04—Processing captured monitoring data, e.g. for logfile generation
- H04L43/045—Processing captured monitoring data, e.g. for logfile generation for graphical visualisation of monitoring data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/3006—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/32—Monitoring with visual or acoustical indication of the functioning of the machine
- G06F11/323—Visualisation of programs or trace data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/32—Monitoring with visual or acoustical indication of the functioning of the machine
- G06F11/324—Display of status information
- G06F11/328—Computer systems status display
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/12—Discovery or management of network topologies
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Hardware Design (AREA)
- Mathematical Physics (AREA)
- Debugging And Monitoring (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
A visual monitoring method and a system of a distributed system are provided, the method comprises the following steps: acquiring a node hierarchy of the distributed system according to a node routing table of the distributed system, and representing a node hierarchy structure of the distributed system by adopting a regular polygon fractal graph, wherein one sub-fractal graph in the fractal graph corresponds to one node of the distributed system, and each sub-fractal graph is drawn by adopting a dotted line; acquiring subtask information and resource allocation information of a current task of a distributed system, acquiring an operation node corresponding to an operation resource of each subtask based on the subtask information and the resource allocation information, searching the operation node in the fractal graph, and drawing a sub-fractal graph corresponding to the operation node into a solid line graph; and acquiring monitoring information of each operating node in real time, and drawing and displaying the monitoring information on a side line of the sub-fractal graph corresponding to the operating node based on the monitoring information.
Description
Technical Field
The invention relates to the technical field of distributed system monitoring, in particular to a visual monitoring method and system for a distributed system.
Background
Distributed systems have become the core underlying framework of current cloud computing, cloud storage, and intelligent computing centers. Distributed storage and computation frameworks based on Hadoop, spark and the like can integrate a plurality of traditional complex tasks such as network transmission, load balancing, AI processing and the like, and the comprehensiveness and complexity of the bottom layer design of the distributed storage and computation frameworks are far superior to those of the previous distributed systems.
Visual monitoring of distributed systems is an important consideration in current distributed system management. At present, the visual monitoring of a distributed system mainly adopts the form of establishing 3-5 dimensional visual charts such as a ring chart, a line chart, a column chart, a bubble chart and the like to display monitoring information, the visual monitoring mode adopting a multi-chart mode can split the whole running state, not only is single chart information provided incompletely, but also operation and maintenance personnel can ignore other parts while checking one chart, and in case of abnormal states, the system can be controlled untimely, thereby causing serious consequences.
Disclosure of Invention
In view of the foregoing analysis, embodiments of the present invention provide a visual monitoring method and system for a distributed system, so as to solve the problem that the running state of the system cannot be displayed integrally because the existing distributed system adopts multiple charts to display monitoring information.
In one aspect, an embodiment of the present invention provides a visual monitoring method for a distributed system, including: acquiring a node hierarchy of the distributed system according to a node routing table of the distributed system, and representing a node hierarchy structure of the distributed system by adopting a regular polygon fractal graph, wherein one sub-fractal graph in the fractal graph corresponds to one node of the distributed system, and each sub-fractal graph is drawn by adopting a dotted line;
acquiring subtask information and resource allocation information of a current task of a distributed system, acquiring an operation node corresponding to an operation resource of each subtask based on the subtask information and the resource allocation information, searching the operation node in the fractal graph, and drawing a sub-fractal graph corresponding to the operation node into a solid line graph;
and acquiring monitoring information of each operating node in real time, and drawing and displaying the monitoring information on a side line of the sub-fractal graph corresponding to the operating node based on the monitoring information.
The beneficial effects of the above technical scheme are as follows: based on a fractal theory, when the node structure of the distributed system is infinitely expanded, the node hierarchy structure of the system and the real-time running state of various resources of each working node can be simultaneously displayed in one graph, so that the monitoring efficiency is improved, and the omission of monitoring information is avoided.
Further, representing a node hierarchy of the distributed system by adopting a regular polygon fractal graph, comprising:
adopting a positive N-edge to represent the uppermost node of the node hierarchical structure to form a zero-order sub-fractal graph;
for each positive N-polygon in the sub-fractal graph of the j-1 order, acquiring the number M of sub-nodes of a node represented by the current positive N-polygon according to the node routing table, averagely dividing an inscribed circle of the positive N-polygon into M fan-shaped areas by adopting dividing lines, drawing a circle by taking the midpoint of each dividing line as the center of a circle and taking one half of each dividing line as the diameter, and drawing the positive N-polygon in the circle to form the sub-fractal graph of the j order; the circle is an inscribed circle of the regular N-edge;
the N value is determined according to the monitoring dimension of the distributed system, and T represents the node level number of the distributed system; j-1, 2, … T-1.
The beneficial effects of the above technical scheme are as follows: the fractal graph can be generated quickly, the structure is simple and clear, and monitoring personnel can check the fractal graph conveniently.
Further, the monitoring dimension includes a CPU resource, a memory resource, a disk resource, and a GPU resource, and the monitoring information includes an occupancy rate of the resource and a state of the resource.
The beneficial effects of the above technical scheme are as follows: the multidimensional resource occupation condition and the working state of the distributed system can be monitored conveniently and rapidly, so that missing information is avoided.
Further, based on the monitoring information, the step of drawing and displaying the monitoring information on an edge line of the sub-fractal graph corresponding to the operating node includes:
searching a sub-fractal graph corresponding to the operating node in the regular polygon fractal graph based on a graph index;
and drawing the monitoring information display line at the side line position of the sub-fractal graph corresponding to the resource by taking the side length of the sub-fractal graph multiplied by the occupancy rate of the resource as the length of the monitoring information display line and the color corresponding to the state grade of the resource as the color of the monitoring information display line.
The beneficial effects of the above technical scheme are as follows: each side of the regular polygon corresponds to one monitoring dimension, a plurality of monitoring dimensions can be displayed in one regular polygon at the same time, and monitoring information can be comprehensively displayed by adopting different colors and lengths to represent the monitoring information.
Further, drawing the fractal graph by adopting OpenGL or DirectX graphics API.
On the other hand, the embodiment of the invention provides a visual monitoring system of a distributed system, which comprises the following modules:
the initial fractal graph generating module is used for acquiring the node hierarchy of the distributed system according to the node routing table of the distributed system, and representing the node hierarchy structure of the distributed system by adopting a regular polygon fractal graph, wherein one sub-fractal graph in the fractal graph corresponds to one node of the distributed system, and each sub-fractal graph is drawn by adopting a dotted line;
the operation state display module is used for acquiring subtask information and resource allocation information of a current task of the distributed system, acquiring an operation node corresponding to an operation resource of each subtask based on the subtask information and the resource allocation information, searching the operation node in the fractal graph, and drawing a sub fractal graph corresponding to the operation node into a solid line graph;
and the monitoring information display module is used for acquiring the monitoring information of each operation node in real time, and drawing and displaying the monitoring information on the side line of the sub-fractal graph corresponding to the operation node based on the monitoring information.
Further, the initial fractal graph generating module generates a regular polygon fractal graph by adopting the following method:
adopting a positive N-edge to represent the uppermost node of the node hierarchical structure to form a zero-order sub-fractal graph;
for each positive N-polygon in the sub-fractal graph of the j-1 order, acquiring the number M of sub-nodes of a node represented by the current positive N-polygon according to the node routing table, averagely dividing an inscribed circle of the positive N-polygon into M fan-shaped areas by adopting dividing lines, drawing a circle by taking the midpoint of each dividing line as the center of a circle and taking one half of each dividing line as the diameter, and drawing the positive N-polygon in the circle to form the sub-fractal graph of the j order; the circle is an inscribed circle of the regular N-edge;
the N value is determined according to the monitoring dimension of the distributed system, and T represents the node level number of the distributed system; j-1, 2, … T-1.
Further, the monitoring dimension includes a CPU resource, a memory resource, a disk resource, and a GPU resource, and the monitoring information includes an occupancy rate of the resource and a state of the resource.
Further, the monitoring information display module displays the monitoring information by adopting the following steps:
searching a sub-fractal graph corresponding to the operating node in the regular polygon fractal graph based on a graph index;
and drawing the monitoring information display line at the side line position of the sub-fractal graph corresponding to the resource by taking the side length of the sub-fractal graph multiplied by the occupancy rate of the resource as the length of the monitoring information display line and the color corresponding to the state grade of the resource as the color of the monitoring information display line.
Further, drawing the fractal graph by adopting OpenGL or DirectX graphics API.
In the invention, the technical schemes can be combined with each other to realize more preferable combination schemes. Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
Drawings
The drawings are only for purposes of illustrating particular embodiments and are not to be construed as limiting the invention, wherein like reference numerals are used to designate like parts throughout.
Fig. 1 is a flowchart of a visual monitoring method for a distributed system according to an embodiment of the present invention;
fig. 2 is a block diagram of a visual monitoring system of a distributed system according to an embodiment of the present invention;
fig. 3 is a fractal diagram provided in an embodiment of the present invention.
Detailed Description
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate preferred embodiments of the invention and together with the description, serve to explain the principles of the invention and not to limit the scope of the invention.
Distributed systems have become the core underlying framework of current cloud computing, cloud storage, and intelligent computing centers. Distributed storage and computation frameworks based on Hadoop, spark and the like can integrate a plurality of traditional complex tasks such as network transmission, load balancing, AI processing and the like, and the comprehensiveness and complexity of the bottom layer design of the distributed storage and computation frameworks are far superior to those of the previous distributed systems.
Visual monitoring of distributed systems is an important consideration in current distributed system management. At present, the visual monitoring of a distributed system mainly adopts the form of establishing 3-5 dimensional visual charts such as a ring chart, a line chart, a column chart, a bubble chart and the like to display monitoring information, the visual monitoring mode adopting a multi-chart mode can fracture the whole running state, not only single chart information is not provided completely, but also a user can ignore other parts while observing 1 chart, and in case of abnormal states, the system can be controlled untimely, thereby causing serious consequences.
Based on this, a specific embodiment of the present application discloses a visual monitoring method for a distributed system, which uses a fractal graph to display monitoring information of the distributed system in a graph in an integrated manner, so as to not only display the dependency relationship between nodes, but also comprehensively display the running state of each node of the distributed system, thereby facilitating monitoring personnel to monitor the system and finding out abnormal states of the system in time. As shown in fig. 1, the method comprises the steps of:
s1, obtaining the node hierarchy of the distributed system according to the node routing table of the distributed system, representing the node hierarchy structure of the distributed system by adopting a regular polygon fractal graph, wherein one sub-fractal graph in the fractal graph corresponds to one node of the distributed system, and each sub-fractal graph is drawn by adopting a dotted line.
The distributed system usually adopts a master-slave structure, which may be a two-layer structure or a multi-layer structure, and the master node of the distributed system maintains the information of the subordinate slave nodes thereof, so that the information of the subordinate slave nodes thereof is obtained according to the routing information table of the master node, thereby obtaining the node hierarchy structure of the whole distributed system.
The part of the fractal graph has a certain similarity relation with the whole fractal graph, namely the structure of the parent image is similar to that of the child image, but the child image is a part of the parent image. By means of recursion, the fractal graph can be drawn in an infinite hierarchy mode theoretically, and therefore the fractal graph is suitable for representing a node hierarchy structure of a distributed system. Each sub-fractal in the fractal graph corresponds to a node of the distributed system. The subordinate levels of the nodes can be clearly represented through the parent-child fractal graph, each sub-graph has a similar structure with the parent graph, the information dimension which can be displayed by each sub-graph is the same as that of the parent graph, and all monitoring information can be displayed in one graph because the sub-graph is one part of the parent graph, so that the running state of the distributed system can be integrally monitored, and the problem of monitoring omission caused by splitting and displaying the monitoring information is avoided.
Specifically, the number of edges of the regular polygon is determined according to the monitored dimension. Generally, the monitoring dimension of the distributed system includes CPU resources, memory resources, disk resources, and GPU resources, and the monitoring information that can be obtained by monitoring these resources includes the occupancy rate of the resources and the status of the resources. The monitoring dimension may also include other dimensions, such as network resources, JVM resources, and the like, and corresponding monitoring information is obtained according to the difference of the monitoring dimension.
The main stream distributed system comprises a monitoring interface, and the monitoring information can be obtained through the monitoring interface. Such as the http monitor port or JMX port of Hadoop. Monitoring information may also be obtained through a monitoring interface provided by a third party monitoring tool, such as a ganglia tool. Each side of the regular polygon corresponds to one monitoring dimension, and the acquired monitoring information can be displayed as side line information of the regular polygon, so that the monitoring information of multiple dimensions is displayed in one graph.
Adopting a positive N-edge to represent the uppermost node of the node hierarchical structure to form a zero-order sub-fractal graph;
for each positive N-polygon in the sub-fractal graph of the j-1 order, acquiring the number M of sub-nodes of a node represented by the current positive N-polygon according to the node routing table, averagely dividing an inscribed circle of the positive N-polygon into M fan-shaped areas by adopting dividing lines, drawing a circle by taking the midpoint of each dividing line as the center of a circle and taking one half of each dividing line as the diameter, and drawing the positive N-polygon in the circle to form the sub-fractal graph of the j order; the circle is an inscribed circle of the positive N deformation;
the N value is determined according to the monitoring dimension of the distributed system, and T represents the node level number of the distributed system; j-1, 2, … T-1.
For example, 4 monitoring dimensions are taken as an example for illustration. Firstly, drawing a positive quadrangle on a monitoring interface, and representing the uppermost main node of the distributed system by the positive quadrangle to form a zero-order sub-fractal graph. And recording the graph index of the positive quadrilateral graph and the corresponding node information thereof.
If the uppermost layer main node has 5 slave nodes, the inscribed circle of the regular quadrangle of the zero-order sub-fractal graph is averagely divided into 5 fan-shaped areas, the middle point of each dividing line is taken as the center of a circle, the diameter of the middle point of the length of the dividing line is taken as the diameter, a small circle is drawn, the small circle is taken as the inscribed circle, the regular quadrangle is drawn, the first-order sub-fractal graph is formed, and in the implementation process, the small circle can also be taken as the circumscribed circle to draw the regular quadrangle. Each positive quadrangle of the first-order fractal graph represents a slave node, and the graph index and the corresponding node information of each positive quadrangle are recorded.
And forming a fractal graph representing the static structure of the distributed system by analogy with the steps. The reason why the structure is static is that although a plurality of nodes are configured in the distributed system, each task is divided into a plurality of subtasks, the subtasks are distributed and run on different nodes, and for one distributed task, not all nodes are running their subtasks, so in step S1, all the sub-fractal graphs in the fractal graph are drawn as dotted lines to represent a state where the node has not run the subtasks. And after the subtasks are distributed in the nodes, drawing the sub-graphs corresponding to the nodes as solid lines, thereby clearly displaying the node task running conditions of the distributed system.
In implementation, the fractal graph can be drawn by adopting OpenGL or DirectX graphics API.
S2, subtask information and resource allocation information of a current task of the distributed system are obtained, an operation node corresponding to an operation resource of each subtask is obtained based on the subtask information and the resource allocation information, the operation node is searched in the fractal graph, and a sub fractal graph corresponding to the operation node is drawn into a solid line graph.
In the distributed system, a task is divided into subtasks, the subtasks are distributed to run on different nodes according to a distribution scheduling strategy, and one subtask may run on a plurality of nodes. The task scheduling management center of the distributed system maintains the partition information and the node allocation information of each task. For example, a certain subtask of a certain task runs on a certain node(s). Data for a subtask may be stored on one node, but computation may be performed on another node, i.e., two or more nodes cooperate to perform a subtask. When a task is operated, subtask information and node distribution information of the current task of the task scheduling management center are obtained, and accordingly an operation node corresponding to each subtask is obtained. And inquiring a sub-fractal graph corresponding to the operating node in the fractal graph according to the graph index and the node information, and drawing the sub-fractal graph as a solid line so as to represent that the node is required to operate the task. Therefore, monitoring personnel can conveniently and clearly and completely see which nodes in the system are running tasks, and the monitoring personnel can monitor the nodes.
During implementation, the operation nodes corresponding to different subtasks can be filled with different colors, so that monitoring personnel can conveniently monitor the operation nodes, and the filling colors are different from the colors representing monitoring information.
And S3, acquiring the monitoring information of each operation node in real time, and drawing and displaying the monitoring information on the side line of the sub-fractal graph corresponding to the operation node based on the monitoring information.
Specifically, the monitoring information of each running node can be acquired through a monitoring interface or a third-party monitoring tool of the distributed system.
And searching a sub-fractal graph corresponding to the operating node in the regular polygon fractal graph based on a graph index.
And drawing the monitoring information display line at the side line position of the sub-fractal graph corresponding to the resource by taking the side length of the sub-fractal graph multiplied by the occupancy rate of the resource as the length of the monitoring information display line and the color corresponding to the state grade of the resource as the color of the monitoring information display line.
Specifically, the information of the sub-fractal graph corresponding to the operating node can be queried according to the graph index, for example, information such as vertex coordinates and side lengths of the sub-fractal graph is obtained. For example, if the lowest edge of the quadrangle represents a disk resource, as shown in fig. 3, the length of the side of the fractal graph P1 multiplied by the occupancy rate of the disk is used as the length of the monitoring information display line, and the color corresponding to the status level of the disk is used as the color of the monitoring information display line, the status of the disk can be classified into different levels according to the actual monitoring requirement, for example, into normal, warning, and alert according to the level of the number of bad tracks of the disk, which are respectively represented by green, yellow, and red. The ratio of the memory read-write rate to the comparative normal value determines the status level, which the GPU and CPU can determine according to the number of their queued (polled) processing tasks. For example, 10 threads may be queued in the forwarding state and more than 100 threads may be queued in the alert state.
During implementation, the highest-level abnormality can be expressed in a high-frequency flashing mode, and the flashing frequency is the reciprocal of the time difference (measured in minutes) from the time when the primary signal is sent to the current time, so that the longer the abnormality is, the higher the flashing frequency is, namely, a certain frequency draws the monitoring information display line into different colors, thereby helping monitoring personnel to find abnormal information in time and further ensuring that the system can operate stably.
If the node monitoring information in each subgroup needs to be checked, the local image can be enlarged by rolling the mouse, so that the monitoring information can be checked conveniently.
Based on the fractal theory, when the node structure of the distributed system is infinitely expanded, the running states of the network structure, the working groups and various resources of each working node can be simultaneously displayed in one graph, and the monitoring capability of an operator on the real-time state of the system is enhanced.
On the other hand, the embodiment of the invention provides a visual monitoring system of a distributed system, which comprises the following modules:
the initial fractal graph generating module is used for acquiring the node hierarchy of the distributed system according to the node routing table of the distributed system, and representing the node hierarchy structure of the distributed system by adopting a regular polygon fractal graph, wherein one sub-fractal graph in the fractal graph corresponds to one node of the distributed system, and each sub-fractal graph is drawn by adopting a dotted line;
the operation state display module is used for acquiring subtask information and resource allocation information of a current task of the distributed system, acquiring an operation node corresponding to an operation resource of each subtask based on the subtask information and the resource allocation information, searching the operation node in the fractal graph, and drawing a sub fractal graph corresponding to the operation node into a solid line graph;
and the monitoring information display module is used for acquiring the monitoring information of each operation node in real time, and drawing and displaying the monitoring information on the side line of the sub-fractal graph corresponding to the operation node based on the monitoring information.
Preferably, the initial fractal graph generating module generates the regular polygon fractal graph by the following method:
adopting a positive N-edge to represent the uppermost node of the node hierarchical structure to form a zero-order sub-fractal graph;
for each positive N-polygon in the sub-fractal graph of the j-1 order, acquiring the number M of sub-nodes of a node represented by the current positive N-polygon according to the node routing table, averagely dividing an inscribed circle of the positive N-polygon into M fan-shaped areas by adopting dividing lines, drawing a circle by taking the midpoint of each dividing line as the center of a circle and taking one half of each dividing line as the diameter, and drawing the positive N-polygon in the circle to form the sub-fractal graph of the j order; the circle is an inscribed circle of the regular N-edge;
the N value is determined according to the monitoring dimension of the distributed system, and T represents the node level number of the distributed system; j-1, 2, … T-1.
Preferably, the monitoring dimension includes CPU resources, memory resources, disk resources, and GPU resources, and the monitoring information includes occupancy rates of the resources and states of the resources.
Preferably, the monitoring information display module displays the monitoring information by adopting the following steps:
searching a sub-fractal graph corresponding to the operating node in the regular polygon fractal graph based on a graph index;
and drawing the monitoring information display line at the side line position of the sub-fractal graph corresponding to the resource by taking the side length of the sub-fractal graph multiplied by the occupancy rate of the resource as the length of the monitoring information display line and the color corresponding to the state grade of the resource as the color of the monitoring information display line.
Preferably, the fractal graph is drawn by adopting OpenGL or DirectX graphics API.
The method embodiment and the system embodiment are based on the same principle, and related parts can be referenced mutually, and the same technical effect can be achieved. For a specific implementation process, reference is made to the foregoing embodiments, which are not described herein again.
Those skilled in the art will appreciate that all or part of the flow of the method implementing the above embodiments may be implemented by a computer program, which is stored in a computer readable storage medium, to instruct related hardware. The computer readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention.
Claims (10)
1. A visual monitoring method of a distributed system is characterized by comprising the following steps:
acquiring a node hierarchy of the distributed system according to a node routing table of the distributed system, and representing a node hierarchy structure of the distributed system by adopting a regular polygon fractal graph, wherein one sub-fractal graph in the fractal graph corresponds to one node of the distributed system, and each sub-fractal graph is drawn by adopting a dotted line;
acquiring subtask information and resource allocation information of a current task of a distributed system, acquiring an operation node corresponding to an operation resource of each subtask based on the subtask information and the resource allocation information, searching the operation node in the fractal graph, and drawing a sub-fractal graph corresponding to the operation node into a solid line graph;
and acquiring monitoring information of each operating node in real time, and drawing and displaying the monitoring information on a side line of the sub-fractal graph corresponding to the operating node based on the monitoring information.
2. The visual monitoring method of the distributed system according to claim 1, wherein the representing of the node hierarchy of the distributed system by a regular polygon fractal comprises:
adopting a positive N-edge to represent the uppermost node of the node hierarchical structure to form a zero-order sub-fractal graph;
for each positive N-polygon in the sub-fractal graph of the j-1 order, acquiring the number M of sub-nodes of a node represented by the current positive N-polygon according to the node routing table, averagely dividing an inscribed circle of the positive N-polygon into M fan-shaped areas by adopting dividing lines, drawing a circle by taking the midpoint of each dividing line as the center of a circle and taking one half of each dividing line as the diameter, and drawing the positive N-polygon in the circle to form the sub-fractal graph of the j order; the circle is an inscribed circle of the regular N-edge;
the N value is determined according to the monitoring dimension of the distributed system, and T represents the node level number of the distributed system; j-1, 2, … T-1.
3. The visual monitoring method of the distributed system according to claim 2, wherein the monitoring dimensions include CPU resources, memory resources, disk resources, and GPU resources, and the monitoring information includes occupancy rates of resources and states of resources.
4. The visual monitoring method of the distributed system according to claim 3, wherein the step of drawing and displaying the monitoring information on an edge line of the sub-fractal graph corresponding to the operating node based on the monitoring information comprises:
searching a sub-fractal graph corresponding to the operating node in the regular polygon fractal graph based on a graph index;
and drawing the monitoring information display line at the side line position of the sub-fractal graph corresponding to the resource by taking the side length of the sub-fractal graph multiplied by the occupancy rate of the resource as the length of the monitoring information display line and the color corresponding to the state grade of the resource as the color of the monitoring information display line.
5. The visual monitoring method of the distributed system according to claim 1, wherein the fractal graph is drawn by using OpenGL or DirectX graphic API.
6. A visual monitoring system of a distributed system comprises the following modules:
the initial fractal graph generating module is used for acquiring the node hierarchy of the distributed system according to the node routing table of the distributed system, and representing the node hierarchy structure of the distributed system by adopting a regular polygon fractal graph, wherein one sub-fractal graph in the fractal graph corresponds to one node of the distributed system, and each sub-fractal graph is drawn by adopting a dotted line;
the operation state display module is used for acquiring subtask information and resource allocation information of a current task of the distributed system, acquiring an operation node corresponding to an operation resource of each subtask based on the subtask information and the resource allocation information, searching the operation node in the fractal graph, and drawing a sub fractal graph corresponding to the operation node into a solid line graph;
and the monitoring information display module is used for acquiring the monitoring information of each operation node in real time, and drawing and displaying the monitoring information on the side line of the sub-fractal graph corresponding to the operation node based on the monitoring information.
7. The visual monitoring system of the distributed system according to claim 6, wherein the initial fractal map generation module generates the regular polygon fractal map by:
adopting a positive N-edge to represent the uppermost node of the node hierarchical structure to form a zero-order sub-fractal graph;
for each positive N-polygon in the sub-fractal graph of the j-1 order, acquiring the number M of sub-nodes of a node represented by the current positive N-polygon according to the node routing table, averagely dividing an inscribed circle of the positive N-polygon into M fan-shaped areas by adopting dividing lines, drawing a circle by taking the midpoint of each dividing line as the center of a circle and taking one half of each dividing line as the diameter, and drawing the positive N-polygon in the circle to form the sub-fractal graph of the j order; the circle is an inscribed circle of the regular N-edge;
the N value is determined according to the monitoring dimension of the distributed system, and T represents the node level number of the distributed system; j-1, 2, … T-1.
8. The visual monitoring system of the distributed system according to claim 7, wherein the monitoring dimensions include CPU resources, memory resources, disk resources, and GPU resources, and the monitoring information includes occupancy rates of resources and states of resources.
9. The visual monitoring system of the distributed system according to claim 8, wherein the monitoring information display module displays the monitoring information by the following steps:
searching a sub-fractal graph corresponding to the operating node in the regular polygon fractal graph based on a graph index;
and drawing the monitoring information display line at the side line position of the sub-fractal graph corresponding to the resource by taking the side length of the sub-fractal graph multiplied by the occupancy rate of the resource as the length of the monitoring information display line and the color corresponding to the state grade of the resource as the color of the monitoring information display line.
10. The visual monitoring system of the distributed system according to claim 6, wherein the fractal graph is drawn by using OpenGL or DirectX graphics API.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111217462.5A CN113872834B (en) | 2021-10-19 | 2021-10-19 | Visual monitoring method and system for distributed system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111217462.5A CN113872834B (en) | 2021-10-19 | 2021-10-19 | Visual monitoring method and system for distributed system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113872834A true CN113872834A (en) | 2021-12-31 |
CN113872834B CN113872834B (en) | 2023-05-23 |
Family
ID=79000436
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111217462.5A Active CN113872834B (en) | 2021-10-19 | 2021-10-19 | Visual monitoring method and system for distributed system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113872834B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101470711A (en) * | 2007-12-25 | 2009-07-01 | 国际商业机器公司 | Data visualization method and apparatus for layered graph structure |
CN105426499A (en) * | 2015-11-25 | 2016-03-23 | 成都数联铭品科技有限公司 | Implementation method of data visualization |
CN105488130A (en) * | 2015-11-25 | 2016-04-13 | 成都数联铭品科技有限公司 | Associated data visualization display method |
CN105573824A (en) * | 2014-10-10 | 2016-05-11 | 腾讯科技(深圳)有限公司 | Monitoring method and system of distributed computing system |
CN107168847A (en) * | 2017-04-21 | 2017-09-15 | 国家电网公司 | The full link application monitoring method and device of a kind of support distribution formula framework |
-
2021
- 2021-10-19 CN CN202111217462.5A patent/CN113872834B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101470711A (en) * | 2007-12-25 | 2009-07-01 | 国际商业机器公司 | Data visualization method and apparatus for layered graph structure |
CN105573824A (en) * | 2014-10-10 | 2016-05-11 | 腾讯科技(深圳)有限公司 | Monitoring method and system of distributed computing system |
CN105426499A (en) * | 2015-11-25 | 2016-03-23 | 成都数联铭品科技有限公司 | Implementation method of data visualization |
CN105488130A (en) * | 2015-11-25 | 2016-04-13 | 成都数联铭品科技有限公司 | Associated data visualization display method |
CN107168847A (en) * | 2017-04-21 | 2017-09-15 | 国家电网公司 | The full link application monitoring method and device of a kind of support distribution formula framework |
Also Published As
Publication number | Publication date |
---|---|
CN113872834B (en) | 2023-05-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8013859B2 (en) | Graphical display for illustrating effectiveness of resource management and resource balancing | |
US8621032B2 (en) | Method and apparatus for intuitively administering networked computer systems | |
CN108804383B (en) | Support point parallel enumeration method and device based on measurement space | |
CN107305518A (en) | The display methods and device of warning information | |
CN109063838B (en) | Knowledge model servization and flow customization system | |
US7571088B2 (en) | Simulation of connected devices | |
US20130289945A1 (en) | System and Method for Space Utilization Optimization and Visualization | |
CN113904941B (en) | Method, system and electronic device for generating topological graph | |
CN113287153A (en) | Dynamic front-end driven generation of HLOD trees | |
CN105827678B (en) | Communication means and node under a kind of framework based on High Availabitity | |
US10038589B1 (en) | Network link capacity determination | |
WO2016106590A1 (en) | Method and apparatus for presenting device load state in cloud computing network | |
CN115169634A (en) | Task allocation optimization processing method and device | |
Chen et al. | A resilience-oriented evaluation and identification of critical thresholds for traffic congestion diffusion | |
CN102819533B (en) | The warehouse compartment information processing method in visualization warehouse and device | |
US10891319B2 (en) | Easy clustering of graphs of nodes preserving node relationships | |
CN113872834B (en) | Visual monitoring method and system for distributed system | |
Goldin et al. | Georouting and delta-gathering: Efficient data propagation techniques for geosensor networks | |
CN114968227A (en) | Intelligent combat simulation platform and data processing method thereof | |
Park et al. | Visualization of urban air pollution with cloud computing | |
CN114169521A (en) | Knowledge graph construction method based on fault mode and influence analysis information | |
KR20230053328A (en) | Method and system for monitoring facilities using 3D virtual model | |
CN111901156A (en) | Method and device for monitoring fault | |
JP2000020428A (en) | Network management system | |
CN108363756A (en) | A kind of intelligent transportation big data processing system |
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 |