Fengshen-Performance Capacity Analysis Report

Introduction to Fengshen-Analysis Report | Performance Capacity

1. Function introduction

The performance overview of each product of the cloud platform needs to be viewed by logging in to the corresponding operation and maintenance tool. When providing relevant reports and summaries, it will take a long time. The performance capacity report provides evaluation and analysis of important indicators of all products on the cloud platform, which can help the operation Maintenance can quickly locate problems and provide offline reports on related performance, which greatly reduces operation and maintenance costs.

1.1 Data source

Conferred God Database

1.2 Solve the problem

①Provide full product performance analysis charts to improve the speed of problem location;

②Provide capacity analysis of the entire cloud platform;

③Support downloading offline reports.

2. Development Architecture

2.1 Architecture description

The performance capacity report is integrated in the Fengshen monitoring system. The data comes from the monitoring data of the Fengshen database. The performance capacity data is regularly analyzed and recorded and recorded into the database. The front-end display and offline reports read the corresponding data and display them in the form of graph visualization. As shown below.

figure 1

2.2 Features

1. The function is integrated in the Fengshen system and has no impact on the production environment;
2. Analyze the overall operating status of the current cloud platform and give optimization suggestions;
3. Visually display the instance status of each product to improve operation and maintenance efficiency;
4. Provide offline data report and full data download of instance performance.

2.3 Functional structure and product list

<span class = "Lake-fontSize-. 11"> Tab </ span>	<span class = "Lake-fontSize-. 11"> Product </ span>
< span class="lake-fontsize-11">Overview</span>	<span class="lake-fontsize-11">Resource capacity, number of instances/hosts, number of alarms</span>
<span class="lake-fontsize-11">Basic</span>	<span class="lake-fontsize-11"> Space-based, ecs, oss, slb, Pangu</span>
<span class ="lake-fontsize-11">Middleware</span>	<span class="lake-fontsize-11">mq</span><span class="lake-fontsize-11">, edas, schx </span>
<span class="lake-fontsize-11">Database</span>	<span class="lake-fontsize-11">rds</span ><span class="lake-fontsize-11">, drds, minirds, ots, ads</span>
<span class="lake-fontsize-11">big data</span>	< span class="lake-fontsize-11">dataworks</span><span class="lake-fontsize-11">, odps</span>
<span class="lake-fontsize-11"> Base</span>	<span class="lake-fontsize-11">docker</span><span class="lake-fontsize-11">, ops, otsinner, ftp-server, minirds, slb, vpc </span>

## 3. Function details The performance capacity report is displayed and classified according to the overall overview, basic components, middleware, database, big data, and base (see section 2.3 for details). The main display types include graphs, bar charts, pie charts, heat maps, and tables, and Analyze the visual content, give suggestions, and support time retrieval or download offline reports; #### 3.1 Pie chart performance analysis 1. The figure shows the overall performance of ECS products, which clearly shows the ECS resource usage of the current cloud platform; 2. Click the "Search" button in the upper right corner of the figure to search according to the time range of the required data; 3. The red text box in the figure is an analysis suggestion. Most of the ECS performance utilization rate is below 30%. It can be seen that the current cloud platform ECS is relatively idle and needs to be appropriately scaled down to recover resources. Figure 2 #### 3.2 Curve performance analysis 1. The picture shows the Pangu water level usage of each product on the cloud platform, which can show the Pangu water level trend within a fixed time frame; 2. As shown in the figure, the current cloud platform Pangu water level utilization rate hardly exceeds 30%, and no optimization is required. Figure 3 #### 3.3 Columnar performance analysis 1. The picture shows the comparison between the number of CPU resources of all docker hosts on the cloud platform and the number of allocated CPU resources; 2. As shown in the figure, the CPU resources of the docker host in the current environment are oversold. Figure 4 #### 3.4 Thermal performance analysis 1. The picture shows the single CPU usage of all docker hosts on the cloud platform, which can be compared and analyzed in conjunction with Figure (3-3); 2. The number in the box is the CPU usage rate of the corresponding kernel on the x-axis. Hovering one of the kernels with the mouse will display the corresponding kernel's mount container; 3. When there is CPU migration work during the operation and maintenance process, you can refer to this heat map and select the host of the same group of ASW for migration. Figure 5 #### 3.5 Table capacity analysis 1. The following figure shows the overall resource usage analysis of the current cloud platform; 2. The figure shows the total number of resources and the number of used resources, as well as the forecast of resource use. Figure 6 The above examples are several typical visual display methods in the report. Each cloud product is composed of different charts and corresponding analysis suggestions. We are the Alibaba Cloud Intelligent Global Technical Service-SRE team. We are committed to becoming a technology-based, service-oriented, and high-availability engineer team of business systems; providing professional and systematic SRE services to help customers make better use of the cloud 、Build a more stable and reliable business system based on the cloud to improve business stability. We hope to share more technologies that help enterprise customers go to the cloud, make good use of the cloud, and make their business operations on the cloud more stable and reliable. You can scan the QR code below to join the Alibaba Cloud SRE Technical Institute Dingding circle, and more The multi-cloud master communicates about those things about the cloud platform. > Copyright Statement: content of this article is contributed spontaneously by Alibaba Cloud real-name registered users, and the copyright belongs to the original author. The Alibaba Cloud Developer Community does not own the copyright, and does not bear the corresponding legal responsibility. For specific rules, please refer to the "Alibaba Cloud Developer Community User Service Agreement" and the "Alibaba Cloud Developer Community Intellectual Property Protection Guidelines". If you find suspected plagiarism in this community, fill in the infringement complaint form to report it. Once verified, the community will immediately delete the suspected infringing content.