Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

support monitoring opensuse os metrics #997

Merged
merged 1 commit into from
May 30, 2023
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
394 changes: 394 additions & 0 deletions manager/src/main/resources/define/app-opensuse.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,394 @@
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

# The monitoring type category:service-application service monitoring db-database monitoring custom-custom monitoring os-operating system monitoring
# 监控类型所属类别:service-应用服务监控 db-数据库监控 custom-自定义监控 os-操作系统监控 cn-云原生cloud native network-网络监控
category: os
# The monitoring type eg: linux windows tomcat mysql aws...
# 监控类型 eg: linux windows tomcat mysql aws...
app: opensuse
# The monitoring i18n name
# 监控类型国际化名称
name:
zh-CN: OpenSUSE
en-US: OpenSUSE
# 监控所需输入参数定义(根据定义渲染页面UI)
# Input params define for monitoring(render web ui by the definition)
params:
# field-param field key
# field-变量字段标识符
- field: host
# name-param field display i18n name
# name-参数字段显示名称
name:
zh-CN: 主机Host
en-US: Host
# type-param field type(most mapping the html input type)
# type-字段类型,样式(大部分映射input标签type属性)
type: host
# required-true or false
# required-是否是必输项 true-必填 false-可选
required: true
# field-param field key
# field-变量字段标识符
- field: port
# name-param field display i18n name
# name-参数字段显示名称
name:
zh-CN: 端口
en-US: Port
# type-param field type(most mapping the html input type)
# type-字段类型,样式(大部分映射input标签type属性)
type: number
# when type is number, range is required
# 当type为number时,用range表示范围
range: '[0,65535]'
# required-true or false
# required-是否是必输项 true-必填 false-可选
required: true
# default value
# 默认值
defaultValue: 22
# field-param field key
# field-变量字段标识符
- field: timeout
# name-param field display i18n name
# name-参数字段显示名称
name:
zh-CN: 超时时间(ms)
en-US: Timeout(ms)
# type-param field type(most mapping the html input type)
# type-字段类型,样式(大部分映射input标签type属性)
type: number
# when type is number, range is required
# 当type为number时,用range表示范围
range: '[400,200000]'
# required-true or false
# required-是否是必输项 true-必填 false-可选
required: false
# default value
# 默认值
defaultValue: 6000
# field-param field key
# field-变量字段标识符
- field: username
# name-param field display i18n name
# name-参数字段显示名称
name:
zh-CN: 用户名
en-US: Username
# type-param field type(most mapping the html input type)
# type-字段类型,样式(大部分映射input标签type属性)
type: text
# when type is text, use limit to limit string length
# 当type为text时,用limit表示字符串限制大小
limit: 20
# required-true or false
# required-是否是必输项 true-必填 false-可选
required: true
# field-param field key
# field-变量字段标识符
- field: password
# name-param field display i18n name
# name-参数字段显示名称
name:
zh-CN: 密码
en-US: Password
# type-param field type(most mapping the html input tag)
# type-字段类型,样式(大部分映射input标签type属性)
type: password
# required-true or false
# required-是否是必输项 true-必填 false-可选
required: false
# field-param field key
# field-变量字段标识符
- field: privateKey
# name-param field display i18n name
# name-参数字段显示名称
name:
zh-CN: 私钥
en-US: PrivateKey
# type-param field type(most mapping the html input type)
# type-字段类型,样式(大部分映射input标签type属性)
type: textarea
# required-true or false
# required-是否是必输项 true-必填 false-可选
required: false
# hide param-true or false
# 是否隐藏字段 true or false
hide: true
# collect metrics config list
# 采集指标组配置列表
metrics:
# metrics - basic, inner monitoring metrics (responseTime - response time)
# 监控指标组 - basic, 内置监控指标有 (responseTime - 响应时间)
- name: basic
# 指标组调度优先级(0-127)越小优先级越高,优先级低的指标组会等优先级高的指标组采集完成后才会被调度,相同优先级的指标组会并行调度采集
# metrics group scheduling priority(0->127)->(high->low), metrics with the same priority will be scheduled in parallel
# priority 0's metrics group is availability metrics, it will be scheduled first, only availability metrics collect success will the scheduling continue
# 指标组调度优先级(0->127)->(优先级高->低) 优先级低的指标组会等优先级高的指标组采集完成后才会被调度, 相同优先级的指标组会并行调度采集
# 优先级为0的指标组为可用性指标组,即它会被首先调度,采集成功才会继续调度其它指标组,采集失败则中断调度
priority: 0
# collect metrics content
# 具体监控指标列表
fields:
# field-metric name, type-metric type(0-number,1-string), unit-metric unit('%','ms','MB'), instance-if is metrics group unique identifier
# field-指标名称, type-指标类型(0-number数字,1-string字符串), unit-指标单位('%','ms','MB'), instance-是否是指标集合唯一标识符字段
- field: hostname
type: 1
instance: true
- field: version
type: 1
- field: uptime
type: 1
# the protocol used for monitoring, eg: sql, ssh, http, telnet, wmi, snmp, sdk
protocol: ssh
# the config content when protocol is ssh
ssh:
# ssh host: ipv4 ipv6 domain
host: ^_^host^_^
# ssh port
port: ^_^port^_^
# ssh username
username: ^_^username^_^
# ssh password
password: ^_^password^_^
# ssh private key
privateKey: ^_^privateKey^_^
timeout: ^_^timeout^_^
# ssh run collect script
script: (uname -r ; hostname ; uptime | awk -F "," '{print $1}' | sed "s/ //g") | sed ":a;N;s/\n/^/g;ta" | awk -F '^' 'BEGIN{print "version hostname uptime"} {print $1, $2, $3}'
# ssh response data parse type: oneRow, multiRow
parseType: multiRow

- name: cpu
priority: 1
fields:
- field: info
type: 1
- field: cores
type: 0
- field: interrupt
type: 0
- field: load
type: 1
- field: context_switch
type: 0
- field: usage
type: 0
unit: '%'
# (optional)metrics field alias name, it is used as an alias field to map and convert the collected data and metrics field
# (可选)监控指标别名, 做为中间字段与采集数据字段和指标字段映射转换
aliasFields:
- info
- cores
- load
- interrupt
- context_switch
- idle
# mapping and conversion expressions, use these and aliasField above to calculate metrics value
# (可选)指标映射转换计算表达式,与上面的别名一起作用,计算出最终需要的指标值
# eg: cores=core1+core2, usage=usage, waitTime=allTime-runningTime
calculates:
- info=info
- cores=cores
- load=load
- interrupt=interrupt
- context_switch=context_switch
- usage=100-idle
protocol: ssh
ssh:
host: ^_^host^_^
port: ^_^port^_^
username: ^_^username^_^
password: ^_^password^_^
privateKey: ^_^privateKey^_^
timeout: ^_^timeout^_^
script: "LANG=C lscpu | awk -F: '$1==\"Model name\" {print $2}';awk '/processor/{core++} END{print core}' /proc/cpuinfo;uptime | sed 's/,/ /g' | awk '{for(i=NF-2;i<=NF;i++)print $i }' | xargs;vmstat 1 1 | awk 'NR==3{print $11}';vmstat 1 1 | awk 'NR==3{print $12}';vmstat 1 2 | awk 'NR==4{print $15}'"
parseType: oneRow

- name: memory
priority: 2
fields:
- field: total
type: 0
unit: Mb
- field: used
type: 0
unit: Mb
- field: free
type: 0
unit: Mb
- field: buff_cache
type: 0
unit: Mb
- field: available
type: 0
unit: Mb
- field: usage
type: 0
unit: '%'
aliasFields:
- total
- used
- free
- buff_cache
- available
calculates:
- total=total
- used=used
- free=free
- buff_cache=buff_cache
- available=available
- usage=(used / total) * 100
protocol: ssh
ssh:
host: ^_^host^_^
port: ^_^port^_^
username: ^_^username^_^
password: ^_^password^_^
privateKey: ^_^privateKey^_^
timeout: ^_^timeout^_^
script: free -m | awk 'BEGIN{print "total used free buff_cache available"} NR==2{print $2,$3,$4,$6,$7}'
parseType: multiRow

- name: disk
priority: 3
fields:
- field: disk_num
type: 0
unit: 'block'
- field: partition_num
type: 0
- field: block_write
type: 0
unit: 'block'
- field: block_read
type: 0
unit: 'block'
- field: write_rate
type: 0
unit: iops
protocol: ssh
ssh:
host: ^_^host^_^
port: ^_^port^_^
username: ^_^username^_^
password: ^_^password^_^
privateKey: ^_^privateKey^_^
timeout: ^_^timeout^_^
script: vmstat -D | awk 'NR==1{print $1}';vmstat -D | awk 'NR==2{print $1}';vmstat 1 1 | awk 'NR==3{print $10}';vmstat 1 1 | awk 'NR==3{print $9}';vmstat 1 1 | awk 'NR==3{print $16}'
parseType: oneRow

- name: interface
priority: 4
fields:
- field: interface_name
type: 1
instance: true
- field: receive_bytes
type: 0
unit: byte
- field: transmit_bytes
type: 0
unit: byte
protocol: ssh
ssh:
host: ^_^host^_^
port: ^_^port^_^
username: ^_^username^_^
password: ^_^password^_^
privateKey: ^_^privateKey^_^
timeout: ^_^timeout^_^
script: cat /proc/net/dev | tail -n +3 | awk 'BEGIN{ print "interface_name receive_bytes transmit_bytes"} {print $1,$2,$10}'
parseType: multiRow

- name: disk_free
priority: 5
fields:
- field: filesystem
type: 1
- field: used
type: 0
unit: Mb
- field: available
type: 0
unit: Mb
- field: usage
type: 0
unit: '%'
- field: mounted
type: 1
instance: true
protocol: ssh
ssh:
host: ^_^host^_^
port: ^_^port^_^
username: ^_^username^_^
password: ^_^password^_^
privateKey: ^_^privateKey^_^
timeout: ^_^timeout^_^
script: df -m | tail -n +2 | awk 'BEGIN{ print "filesystem used available usage mounted"} {print $1,$3,$4,$5,$6}'
parseType: multiRow

- name: top_cpu_process
priority: 6
fields:
- field: pid
type: 1
instance: true
- field: cpu_usage
type: 0
unit: '%'
- field: mem_usage
type: 0
unit: '%'
- field: command
type: 1
protocol: ssh
ssh:
host: ^_^host^_^
port: ^_^port^_^
username: ^_^username^_^
password: ^_^password^_^
privateKey: ^_^privateKey^_^
timeout: ^_^timeout^_^
script: ps -aux | sort -k3nr | awk 'BEGIN{ print "pid cpu_usage mem_usage command" } {print $2, $3, $4, $11}'| head -n 10
parseType: multiRow

- name: top_mem_process
priority: 7
fields:
- field: pid
type: 1
instance: true
- field: cpu_usage
type: 0
unit: '%'
- field: mem_usage
type: 0
unit: '%'
- field: command
type: 1
protocol: ssh
ssh:
host: ^_^host^_^
port: ^_^port^_^
username: ^_^username^_^
password: ^_^password^_^
privateKey: ^_^privateKey^_^
timeout: ^_^timeout^_^
script: ps -aux | sort -k4nr | awk 'BEGIN{ print "pid cpu_usage mem_usage command" } {print $2, $3, $4, $11}'| head -n 10
parseType: multiRow