Prometheus与SNMP对接监控

[Unit]

Description=SNMP Exporter

After=network-online.target

# This assumes you are running snmp_exporter under the user "prometheus"

[Service]

Type=simple

Restart=on-failure

ExecStart=/usr/local/snmp_exporter/snmp_exporter --config.file=/usr/local/snmp_exporter/snmp.yml

RestartSec=5

[Install]

WantedBy=multi-user.target

modules:

test:

walk:

- 1.3.6.1.2.1.25.3.3.1.1

version: 2

auth:

community: public

- job_name: 'snmp'

scrape_interval: 10s

static_configs:

- targets:

- 172.16.0.167 # 交换机IP地址

metrics_path: /snmp

params:

module: [test] #generator.yml或SNMP_EXRORTER配置文件中对应的模块

relabel_configs:

- source_labels: [__address__]

target_label: __param_target

- source_labels: [__param_target]

target_label: instance

- target_label: __address__

replacement: 172.16.0.112:9116 # snmp_exporter 服务IP地址

modules:

genesys:

walk:

- servers

- genericServer

- gsCleanupTimeout

- gServersTable

- gServersEntry

- gServerId

- gServerName

- gServerStatus

- gServerType

- gServerVersion

- gServerWorkDir

- gServerCommandLine

- gServerPID

- gServerCommand

- gServerDeleteClient

- gServerControlTable

- gServerControlEntry

- gsCtrlServerID

- gsCtrlTableID

- gsCtrlRefreshStatus

- gsCtrlLastRefreshed

- gsCtrlAutomaticRefresh

- gsCtrlRowStatus

- gsInfoTable

- gsInfoEntry

- gsClientsExistNum

- gsClientsTotalNum

- gsServerConfigFile

- gsLogTable

- gsLogEntry

- gsPollingTable

- gsPollingEntry

- gsPollingStatus

- gsPollingInterval

- gsPollingID

- gsPollingLastTrap

- gsClientTable

- gsClientEntry

- gsClientSocket

- gsClientAppName

- gsClientAuthorized

- gsClientType

- gsClientGotEvents

- gsClientSentReqs

- specificServer

- tServer

- tsInfoTable

- tsInfoEntry

- tsCallsExistNum

- tsCallsTotalNum

- tsLinksCommand

- tsLastChangedLinkStatus

- tsCallTable

- tsCallEntry

- callInstanceID

- callConnID

- callState

- callCallID

- callType

- callReferenceID

- callTimeStamp

- callDNIS

- callANI

- callNumParties

- callPartiesList

- callCustomerID

- callFirstTransferLocation

- callFirstTransferDN

- callLastTransferLocation

- callLastTransferDN

- tsDtaTable

- tsDtaEntry

- tsDtaInstanceID

- tsDtaDigits

- tsDtaMode

- tsDtaState

- tsDtaType

- tsLinkTable

- tsLinkEntry

- tsLinkID

- tsLinkName

- tsLinkStatus

- tsLinkProtocol

- tsLinkSocket

- tsLinkPID

- tsLinkDelay

- tsLinkPort

- tsLinkAddress

- tsLinkX25LocalAddress

- tsLinkMode

- tsLinkX25Device

- tsLinkDTEClass

- tsLinkTemplate

- tsCallFilterTable

- tsCallFilterEntry

- fltCallCreatedBefore

- fltCallCreatedAfter

- fltCallUpdatedBefore

- fltCallUpdatedAfter

- fltClearCallByConnId

- tsCallInfoTable

- tsCallInfoEntry

- callInfoInstanceID

- callInfoConnID

- callInfoType

- callInfoCreationTimestamp

- callInfoLastUpdatedTimestamp

- callInfoInternalParties

- tsLinkStatsTable

- tsLinkStatsEntry

- linkId

- timeElapsedSec

- numberMessagesTx

- rateMessagesTx

- numberMessagesRx

- rateMessagesRx

- hosts

- hostsTable

- hostsEntry

- hostId

- hostName

- hostStatus

- hostIPAddress

- hostOSType

- hostLCAPort

- solutions

- solutionsTable

- solutionsEntry

- solutionId

- solutionName

- solutionType

- solutionStatus

- solutionControlServer

- solutionsComponentsTable

- solutionsComponentsEntry

- componentId

- componentName

- notifications

- gsAlarm

- gsMLAlarm

- gsServerUpTrap

- gsServerDownTrap

- gsPollingSignal

- tsLinkStatusTrap

- genesysmibConformance

- genesysmibGroups

- gServersListGroup

- genericServerControlGroup

- genericServerInfoGroup

- genericServerLogGroup

- genericServerPollingGroup

- genericServerClientGroup

- tServerInfoGroup

- tServerCallGroup

- tServerDtaGroup

- tServerLinkGroup

- genericAlarmObjectGroup

- specificAlarmObjectGroup

- hostsGroup

- solutionsGroup

- solutionsComponentsGroup

- notificationGroup

- tServerCallFilterGroup

- tServerCallInfoGroup

- genesysmibCompliances

- genesysmibCompliance

version: 2

auth:

community: public

- job_name: 'snmp'

scrape_interval: 10s

static_configs:

- targets:

- 172.16.5.51 # genesys地址

metrics_path: /snmp

params:

module: [genesys] #generator.yml或SNMP_EXRORTER配置文件中对应的模块

relabel_configs:

- source_labels: [__address__]

target_label: __param_target

- source_labels: [__param_target]

target_label: instance

- target_label: __address__

replacement: 172.16.0.112:9116 # snmp_exporter 服务IP地址

vi conf/defaults.ini

#################################### SMTP / Emailing #####################

[smtp]

enabled = true

host = smtp.163.com:25

user = 15188257614@163.com

# If the password contains # or ; you have to wrap it with triple quotes. Ex """#password;"""

password = JPLGFRGKFPVJIXGU

cert_file =

key_file =

skip_verify = false

from_address = 15188257614@163.com

from_name = Grafana

ehlo_identity =

startTLS_policy =

[emails]

welcome_email_on_sign_up = false

templates_pattern = emails/*.html

vim gs_check_snmp.sh

#!/bin/bash

gs_snmp_ip=172.16.5.51

gs_server_id=`snmpwalk -v 2c -m GENESYS-SML-MIB-G71 -c public $gs_snmp_ip |grep SIPServer |grep "is UP" |awk -F . '{print$15}' |tail -n1`

gs_run_count=`snmpwalk -v 2c -m GENESYS-SML-MIB-G71 -c public $gs_snmp_ip |grep SIPServer |grep "is UP" |wc -l`

gs_conf_count=`snmpwalk -v 2c -m GENESYS-SML-MIB-G71 -c public $gs_snmp_ip gsCtrlRowStatus |grep -v "gsCtrlRowStatus = No Such Object available on this agent at this OID"|wc -l`

###判断gs sipserver是否正常运行

if [ "$gs_run_count" -eq "0" ];then

echo -e "\033[32m sipserver 服务未运行 \033[0m"

else

if [ "$gs_conf_count" -eq "0" ];then

echo -e "\033[32m gs_snmp 配置中 \033[0m"

for i in {1,2,4,5,6,7,8,9,10};do snmpset -c private -v 2c $gs_snmp_ip 1.3.6.1.4.1.1729.100.1.3.1.6.$gs_server_id.$i i 4;done

echo -e "\033[32m gs_snmp 配置成功 \033[0m"

else

echo -e "\033[32m gs_snmp 无需配置 \033[0m"

exit 1

fi

fi

#删除操作

#snmpset -c private -v 2c 172.16.5.51 1.3.6.1.4.1.1729.100.1.3.1.6.116.8 i 6

######状态栏列对象有6个定义值：

#active（1），表明状态行是可用的

#notInService（2），表明行存在但不可用

#notReady（3），表明存在，但因为缺少必要的信息而不能用

#createAndGo（4），有管理者设置，表明希望创建一个概念行并设置该行的状态列对象为active

#createAndWait（5），有管理者设置，表明希望创建一个概念行，但不可用

#destroy（6），删除行

cat > /usr/lib/systemd/system/pushgateway.service <<EOF

[Unit]

Description=pushgateway

Documentation=https://github.com/prometheus/pushgateway

After=network.target

[Service]

ExecStart=/usr/local/pushgateway/pushgateway

Restart=on-failure

[Install]

WantedBy=multi-user.target

EOF

LOGCONF:

level: info

format: text

director: logs

link-name: current.log

TrapServer:

ip: "172.16.5.51"

port: 161

version: "v2c" #v1, v2c, v3

community: "public"

timeout: 2 #seconds

maxoids: 60

mib_map_file: "miblist.txt"

ApiServer:

api_port: 8070 # apiserver的监听端口

api_read_timeout: 5 #apiserver读请求超时时间， 秒

api_write_timeout: 5 # apiserver写请求超时时间，秒

api_web_root: "./webapp"

sender:

pushgateway_url: "http://172.16.0.167:9091"

job_name: "snmp_trap"

# zabbix_host: "10.187.32.8"

# zabbix_port: 10051

# zbx_itme_key: "snmptraper.fallback"

# sender_dir: "./zabbix_sender.exe"

senders:

# - "zabbix"

- "pushgateway"

process_names:

- name: "{{.Matches}}"

cmdline:

- 'ces-wd.jar'

- name: "{{.Matches}}"

cmdline:

- 'freeswitch'

[Unit]

Description=process_exporter

After=network.target

[Service]

User=root

Type=simple

ExecStart=/usr/local/process-exporter/process-exporter -config.path /usr/local/process-exporter/process-name.yaml

Restart=on-failure

[Install]

WantedBy=multi-user.target

- job_name: 'process'

static_configs:

-targets: ['172.**.**.**:9256']

…..

- job_name: 'process'

scrape_interval: 2m

scrape_timeout: 120s

static_configs:

file_sd_configs:

- files:

- /data/prometheus/config/process_exporter.json

…..

[root@harbor config]# cat process_exporter.json

[

{

"labels": {

"desc": "ces-wd",

"group": "ces-wd.jar",

"host_ip": "172.16.1.254",

"hostname": "abc_baidu"

},

"targets": [

"172.16.1.254:9256"

]

},

{

"labels": {

"desc": "freeswitch",

"group": "freeswitch",

"host_ip": "172.16.1.254",

"hostname": "abc_baidu"

},

"targets": [

"172.16.1.254:9256"

]

}

]

groups:

- name: dol_alert_process_rule

rules:

- alert: Dolphinscheduler Alert ProcessDown # 告警名称

expr: (namedprocess_namegroup_num_procs{groupname="map[:alertlib]"}) == 0

for: 1m # 满足告警条件持续时间多久后，才会发送告警

labels: #标签项

severity: error

annotations: # 解析项，详细解释告警信息

summary: "dolphinscheduler Alert {{ $labels.instance }} has been down for more than 1 minutes"

description: "dolphinscheduler Alert has been down, This requires immediate action!"

./promtool check config prometheus.yml

systemctl reload prometheus.service

yum install https://download.postgresql.org/pub/repos/yum/reporpms/EL-7-x86_64/pgdg-redhat-repo-latest.noarch.rpm

yum install postgresql12-server postgresql12

初始化数据库，初始化数据库命令会在 /var/lib/pgsql 目录下创建名称为12文件夹，11为数据库版本，如果安装的是其他版本，对应的是其版本号（9.4、9.5）

/usr/pgsql-12/bin/postgresql-12-setup initdb

设置开机启动并启动

systemctl enable postgresql-12 && systemctl start postgresql-12

安装完成后，默认会创建一个名为postgres的linux登录用户

默认postgresql不允许远程连接，修改配置，使远程用户可以连接

vim /var/lib/pgsql/12/data/postgresql.conf

listen_addresses = '*'

vim /var/lib/pgsql/12/data/pg_hba.conf

# IPv4 local connections:

host all all 0.0.0.0/0 md5

重启生效

systemctl restart postgresql-12

修改数据库用户密码

使用postgres用户登录，并设置postgres用户密码

su – postgres

postgres=# ALTER USER postgres WITH PASSWORD 'pgsql123';

psqlpostgres=# select usename,passwd from pg_shadow;

postgres=# SELECT datname FROM pg_database;

使用\q可以退出终端

访问测试

bash-4.2$ psql -d postgres -U postgres -h 172.16.1.111

Password for user postgres:

psql (9.2.24, server 12.11)

WARNING: psql version 9.2, server version 12.0.

Some psql features might not work.

Type "help" for help.

postgres=#

wget https://github.com/wrouesnel/postgres_exporter/releases/download/v0.5.1/postgres_exporter_v0.5.1_linux-amd64.tar.gz

mkdir /usr/local/postgres_exporter && tar -zxvf postgres_exporter_v0.5.1_linux-amd64.tar.gz -C /usr/local/postgres_exporter

cd /usr/local/postgres_exporter && mv postgres_exporter_v0.5.1_linux-amd64/* ./ &&

rm -fr postgres_exporter_v0.5.1_linux-amd64/

vim postgres_exporter.env

DATA_SOURCE_NAME="postgresql://postgres:pgsql123@172.16.1.111:5432/?sslmode=disable"

vim /etc/systemd/system/postgres_exporter.service

[Unit]

Description=Prometheus exporter for Postgresql

Wants=network-online.target

After=network-online.target

[Service]

User=postgres

Group=postgres

WorkingDirectory=/usr/local/postgres_exporter

EnvironmentFile=/usr/local/postgres_exporter/postgres_exporter.env

ExecStart=/usr/local/postgres_exporter/postgres_exporter

Restart=always

[Install]

WantedBy=multi-user.target

服务启动

systemctl start postgres_exporter.service

systemctl enable postgres_exporter.service

systemctl status postgres_exporter.service

访问测试

curl http://172.16.1.111:9187/metrics

普罗米修斯配置

- job_name: 'postgres'

static_configs:

- targets: ['172.16.1.111:9187']

labels:

instance: postgresdb1

# 如果有其他postgres_exporter如下添加：

# - targets: ['10.10.xxx.56:9287']

# labels:

# instance: db2

重启后加载curl -X POST 172.16.1.84:9090/-/reload

grafanaid:

9628

455

警报规则

vi /data/prometheus/conf/rules/postgres.rules

groups:

- name: postgresql-监控告警

rules:

- alert: 警报！Postgresql宕机

expr: pg_up == 0

for: 0m

labels:

severity: 严重告警

annotations:

summary: "{{$labels.instance}} Postgresql down"

description: "Postgresql instance is down\n 当前值={{ $value }}"

- alert: 警报！Postgresql被重启

expr: time() - pg_postmaster_start_time_seconds < 60

for: 0m

labels:

severity: 严重告警

annotations:

summary: "{{$labels.instance}} Postgresql restarted"

description: "Postgresql restarted\n 当前值={{ $value }}"

- alert: 警报！PostgresqlExporterError

expr: pg_exporter_last_scrape_error > 0

for: 0m

labels:

severity: 严重告警

annotations:

summary: "{{$labels.instance}} Postgresql exporter error"

description: "Postgresql exporter is showing errors. A query may be buggy in query.yaml\n 当前值={{ $value }}"

- alert: 警报！Postgresql主从复制不同步

expr: pg_replication_lag > 30 and ON(instance) pg_replication_is_replica == 1

for: 0m

labels:

severity: 严重告警

annotations:

summary: "{{$labels.instance}} Postgresql replication lag"

description: "PostgreSQL replication lag is going up (> 30s)\n 当前值={{ $value }}"

- alert: 警报！PostgresqlTableNotVaccumed

expr: time() - pg_stat_user_tables_last_autovacuum > 60 * 60 * 24

for: 0m

labels:

severity: 一般告警

annotations:

summary: "{{$labels.instance}} Postgresql table not vaccumed"

description: "Table has not been vaccum for 24 hours\n 当前值={{ $value }}"

- alert: 警报！PostgresqlTableNotAnalyzed

expr: time() - pg_stat_user_tables_last_autoanalyze > 60 * 60 * 24

for: 0m

labels:

severity: 一般告警

annotations:

summary: "{{$labels.instance}} Postgresql table not analyzed"

description: "Table has not been analyzed for 24 hours\n 当前值={{ $value }}"

- alert: 警报！Postgresql连接数太多

expr: sum by (datname) (pg_stat_activity_count{datname!~"template.*|postgres"}) > pg_settings_max_connections * 0.8

for: 2m

labels:

severity: 一般告警

annotations:

summary: "{{$labels.instance}} Postgresql too many connections"

description: "PostgreSQL instance has too many connections (> 80%).\n 当前值={{ $value }}"

- alert: 警报！Postgresql连接数太少

expr: sum by (datname) (pg_stat_activity_count{datname!~"template.*|postgres"}) < 5

for: 2m

labels:

severity: 一般告警

annotations:

summary: "{{$labels.instance}} Postgresql not enough connections"

description: "PostgreSQL instance should have more connections (> 5)\n 当前值={{ $value }}"

- alert: 警报！Postgresql死锁

expr: increase(pg_stat_database_deadlocks{datname!~"template.*|postgres"}[1m]) > 5

for: 0m

labels:

severity: 一般告警

annotations:

summary: "{{$labels.instance}} Postgresql dead locks"

description: "PostgreSQL has dead-locks\n 当前值={{ $value }}"

- alert: 警报！Postgresql慢查询

expr: pg_slow_queries > 0

for: 2m

labels:

severity: 一般告警

annotations:

summary: "{{$labels.instance}} Postgresql slow queries"

description: "PostgreSQL executes slow queries\n 当前值={{ $value }}"

- alert: 警报！Postgresql回滚率高

expr: rate(pg_stat_database_xact_rollback{datname!~"template.*"}[3m]) / rate(pg_stat_database_xact_commit{datname!~"template.*"}[3m]) > 0.02

for: 0m

labels:

severity: 一般告警

annotations:

summary: "{{$labels.instance}} Postgresql high rollback rate"

description: "Ratio of transactions being aborted compared to committed is > 2 %\n 当前值={{ $value }}"

- alert: 警报！Postgresql提交率低

expr: rate(pg_stat_database_xact_commit[1m]) < 10

for: 2m

labels:

severity: 严重告警

annotations:

summary: "{{$labels.instance}} Postgresql commit rate low"

description: "Postgres seems to be processing very few transactions\n 当前值={{ $value }}"

- alert: 警报！PostgresqlLowXidConsumption

expr: rate(pg_txid_current[1m]) < 5

for: 2m

labels:

severity: 一般告警

annotations:

summary: "{{$labels.instance}} Postgresql low XID consumption"

description: "Postgresql seems to be consuming transaction IDs very slowly\n 当前值={{ $value }}"

- alert: 警报！PostgresqllowXlogConsumption

expr: rate(pg_xlog_position_bytes[1m]) < 100

for: 2m

labels:

severity: 一般告警

annotations:

summary: "{{$labels.instance}} Postgresqllow XLOG consumption"

description: "Postgres seems to be consuming XLOG very slowly\n 当前值={{ $value }}"

- alert: 警报！PostgresqlWaleReplicationStopped

expr: rate(pg_xlog_position_bytes[1m]) == 0

for: 0m

labels:

severity: 严重告警

annotations:

summary: "{{$labels.instance}} Postgresql WALE replication stopped"

description: "WAL-E replication seems to be stopped\n 当前值={{ $value }}"

- alert: 警报！PostgresqlHighRateStatementTimeout

expr: rate(postgresql_errors_total{type="statement_timeout"}[1m]) > 3

for: 0m

labels:

severity: 严重告警

annotations:

summary: "{{$labels.instance}} Postgresql high rate statement timeout"

description: "Postgres transactions showing high rate of statement timeouts\n 当前值={{ $value }}"

- alert: 警报！PostgresqlHighRateDeadlock

expr: increase(postgresql_errors_total{type="deadlock_detected"}[1m]) > 1

for: 0m

labels:

severity: 严重告警

annotations:

summary: "{{$labels.instance}} Postgresql high rate deadlock"

description: "Postgres detected deadlocks\n 当前值={{ $value }}"

- alert: 警报！PostgresqlReplicationLagBytes

expr: (pg_xlog_position_bytes and pg_replication_is_replica == 0) - on(environment) group_right(instance) (pg_xlog_position_bytes and pg_replication_is_replica == 1) > 1e+09

for: 0m

labels:

severity: 严重告警

annotations:

summary: "{{$labels.instance}} Postgresql replication lag bytes"

description: "Postgres Replication lag (in bytes) is high\n 当前值={{ $value }}"

- alert: 警报！PostgresqlUnusedReplicationSlot

expr: pg_replication_slots_active == 0

for: 1m

labels:

severity: 一般告警

annotations:

summary: "{{$labels.instance}} Postgresql unused replication slot"

description: "Unused Replication Slots\n 当前值={{ $value }}"

- alert: 警报！PostgresqlTooManyDeadTuples

expr: ((pg_stat_user_tables_n_dead_tup > 10000) / (pg_stat_user_tables_n_live_tup + pg_stat_user_tables_n_dead_tup)) >= 0.1 unless ON(instance) (pg_replication_is_replica == 1)

for: 2m

labels:

severity: 一般告警

annotations:

summary: "{{$labels.instance}} Postgresql too many dead tuples"

description: "PostgreSQL dead tuples is too large\n 当前值={{ $value }}"

- alert: 警报！PostgresqlSplitBrain

expr: count(pg_replication_is_replica == 0) != 1

for: 0m

labels:

severity: 严重告警

annotations:

summary: "{{$labels.instance}} Postgresql split brain"

description: "Split Brain, too many primary Postgresql databases in read-write mode\n 当前值={{ $value }}"

- alert: 警报！PostgresqlPromotedNode

expr: pg_replication_is_replica and changes(pg_replication_is_replica[1m]) > 0

for: 0m

labels:

severity: 一般告警

annotations:

summary: "{{$labels.instance}} Postgresql promoted node"

description: "Postgresql standby server has been promoted as primary node\n 当前值={{ $value }}"

- alert: 警报！PostgresqlSslCompressionActive

expr: sum(pg_stat_ssl_compression) > 0

for: 0m

labels:

severity: 严重告警

annotations:

summary: "{{$labels.instance}} Postgresql SSL compression active"

description: "Database connections with SSL compression enabled. This may add significant jitter in replication delay. Replicas should turn off SSL compression via `sslcompression=0` in `recovery.conf`.\n 当前值={{ $value }}"

- alert: 警报！PostgresqlTooManyLocksAcquired

expr: ((sum (pg_locks_count)) / (pg_settings_max_locks_per_transaction * pg_settings_max_connections)) > 0.20

for: 2m

labels:

severity: 严重告警

annotations:

summary: "{{$labels.instance}} Postgresql too many locks acquired"

description: "Too many locks acquired on the database. If this alert happens frequently, we may need to increase the postgres setting max_locks_per_transaction.\n 当前值={{ $value }}"

asterisk –rvv执行命令进入cli

sip show peers 显示所有已定义的SIP peer

sip show peers

No such command 'sip show peers' (type 'core show help sip show' for other possible commands)

解决方法

module load chan_sip.so

module reload chan_sip.so

sip show peers

sip show channels 显示所有活动的SIP通道

git clone https://github.com/robinmarechal/asterisk_exporter.git

cd asterisk_exporter

vim main.go

enableAgentsCollector = kingpin.Flag("collector.agents", "Enable agents collector").Default("false").Bool()

将默认的main.go文件进行修改，将agents改为关闭，Asterisk16版本中没有这个查询指标，如果启动会导致采集服务失败

make

./asterisk_exporter <flags>

./asterisk_exporter –h

注意事项，make时需要go语言支持，且需要执行下面配置，否则提示/bin/promu无改命令

touch /root/go/bin/promu

ln -s /root/go/bin/promu /bin/promu

rm -f /root/go/bin/promu

vim asterisk_exporter.service

[Unit]

Description=Asterisk call center system exporter for Prometheus

After=network.target

[Service]

User=asterisk

Group=asterisk

Type=simple

ExecStart=/usr/local/asterisk_exporter/asterisk_exporter \

--web.listen-address=":9815" \

--web.telemetry-path="/metrics" \

--metrics.prefix="asterisk" \

--asterisk.path="/usr/sbin/asterisk" \

--collector.core \

--collector.sip \

--collector.bridges \

--collector.calendars \

--collector.confbridges \

--collector.modules

Restart=always

RestartSec=1

[Install]

WantedBy=multi-user.target

服务启动

cp asterisk_exporter.service /usr/lib/systemd/system/asterisk_exporter.service

systemctl enable asterisk_exporter

systemctl start asterisk_exporter

systemctl status asterisk_exporter

以上如果启动不了可以尝试修改下面参数

ExecStart=/usr/local/asterisk_exporter/asterisk_exporter --asterisk.path=/usr/sbin/asterisk --collector.core --collector.sip --collector.bridges --collector.calendars --collector.confbridges --collector.modules

cd /usr/local

mkdir jvm_exporter

wget https://repo1.maven.org/maven2/io/prometheus/jmx/jmx_prometheus_javaagent/0.12.0/jmx_prometheus_javaagent-0.12.0.jar

vim simple-config.yml

---

wercaseOutputLabelNames: true

lowercaseOutputName: true

whitelistObjectNames: ["java.lang:type=OperatingSystem"]

rules:

- pattern: 'java.lang<type=OperatingSystem><>((?!process_cpu_time)\w+):'

name: os_$1

type: GAUGE

attrNameSnakeCase: true

或者使用下面配置

--   
lowercaseOutputLabelNames: true
lowercaseOutputName: true
whitelistObjectNames: ["java.lang:type=OperatingSystem"]
blacklistObjectNames: []
rules:
  - pattern: 'java.lang<type=OperatingSystem><>(committed_virtual_memory|free_physical_memory|free_swap_space|total_physical_memory|total_swap_space)_size:'
    name: os_$1_bytes
    type: GAUGE
    attrNameSnakeCase: true
  - pattern: 'java.lang<type=OperatingSystem><>((?!process_cpu_time)\w+):'
    name: os_$1
    type: GAUGE
    attrNameSnakeCase: true -

比如我有一个rms的java应用，启动方式为：

java -jar /data/rms/RMS.jar

使用JMX Exporter插件收集数据，需要改成这样：

java -javaagent:/usr/local/jmx_exporter/jmx_prometheus_javaagent-0.12.0.jar=3010:/usr/local/jmx_exporter/simple-config.yml -jar /data/rms/RMS.jar

注意：3010是代理端口，可以随意指定。

或者下面已遵义公积金ivr流程为例

java -javaagent:/usr/local/jvm_exporter/jmx_prometheus_javaagent-0.12.0.jar=3310:/usr/local/jvm_exporter/simple-config.yml -jar ./laihu-ivr-zygjj.jar

modules:

module_name: # The module name. You can have as many modules as you want.

walk: # List of OIDs to walk. Can also be SNMP object names or specific instances.

- 1.3.6.1.2.1.2 # Same as "interfaces"

- sysUpTime # Same as "1.3.6.1.2.1.1.3"

- 1.3.6.1.2.1.31.1.1.1.6.40 # Instance of "ifHCInOctets" with index "40"

version: 2 # SNMP version to use. Defaults to 2.

# 1 will use GETNEXT, 2 and 3 use GETBULK.

max_repetitions: 25 # How many objects to request with GET/GETBULK, defaults to 25.

# May need to be reduced for buggy devices.

retries: 3 # How many times to retry a failed request, defaults to 3.

timeout: 5s # Timeout for each individual SNMP request, defaults to 5s.

auth:

# Community string is used with SNMP v1 and v2. Defaults to "public".

community: public

# v3 has different and more complex settings.

# Which are required depends on the security_level.

# The equivalent options on NetSNMP commands like snmpbulkwalk

# and snmpget are also listed. See snmpcmd(1).

username: user # Required, no default. -u option to NetSNMP.

security_level: noAuthNoPriv # Defaults to noAuthNoPriv. -l option to NetSNMP.

# Can be noAuthNoPriv, authNoPriv or authPriv.

password: pass # Has no default. Also known as authKey, -A option to NetSNMP.

# Required if security_level is authNoPriv or authPriv.

auth_protocol: MD5 # MD5, SHA, SHA224, SHA256, SHA384, or SHA512. Defaults to MD5. -a option to NetSNMP.

# Used if security_level is authNoPriv or authPriv.

priv_protocol: DES # DES, AES, AES192, or AES256. Defaults to DES. -x option to NetSNMP.

# Used if security_level is authPriv.

priv_password: otherPass # Has no default. Also known as privKey, -X option to NetSNMP.

# Required if security_level is authPriv.

context_name: context # Has no default. -n option to NetSNMP.

# Required if context is configured on the device.

lookups: # Optional list of lookups to perform.

# The default for `keep_source_indexes` is false. Indexes must be unique for this option to be used.

# If the index of a table is bsnDot11EssIndex, usually that'd be the label

# on the resulting metrics from that table. Instead, use the index to

# lookup the bsnDot11EssSsid table entry and create a bsnDot11EssSsid label

# with that value.

- source_indexes: [bsnDot11EssIndex]

lookup: bsnDot11EssSsid

drop_source_indexes: false # If true, delete source index labels for this lookup.

# This avoids label clutter when the new index is unique.

overrides: # Allows for per-module overrides of bits of MIBs

metricName:

ignore: true # Drops the metric from the output.

regex_extracts:

Temp: # A new metric will be created appending this to the metricName to become metricNameTemp.

- regex: '(.*)' # Regex to extract a value from the returned SNMP walks's value.

value: '$1' # The result will be parsed as a float64, defaults to $1.

Status:

- regex: '.*Example'

value: '1' # The first entry whose regex matches and whose value parses wins.

- regex: '.*'

value: '0'

type: DisplayString # Override the metric type, possible types are:

# gauge: An integer with type gauge.

# counter: An integer with type counter.

# OctetString: A bit string, rendered as 0xff34.

# DateAndTime: An RFC 2579 DateAndTime byte sequence. If the device has no time zone data, UTC is used.

# DisplayString: An ASCII or UTF-8 string.

# PhysAddress48: A 48 bit MAC address, rendered as 00:01:02:03:04:ff.

# Float: A 32 bit floating-point value with type gauge.

# Double: A 64 bit floating-point value with type gauge.

# InetAddressIPv4: An IPv4 address, rendered as 1.2.3.4.

# InetAddressIPv6: An IPv6 address, rendered as 0102:0304:0506:0708:090A:0B0C:0D0E:0F10.

# InetAddress: An InetAddress per RFC 4001. Must be preceded by an InetAddressType.

# InetAddressMissingSize: An InetAddress that violates section 4.1 of RFC 4001 by

# not having the size in the index. Must be preceded by an InetAddressType.

# EnumAsInfo: An enum for which a single timeseries is created. Good for constant values.

# EnumAsStateSet: An enum with a time series per state. Good for variable low-cardinality enums.

# Bits: An RFC 2578 BITS construct, which produces a StateSet with a time series per bit.

vi /etc/snmp/snmptrapd.conf

authCommunity log,execute,net public

# systemctl start snmptrapd

# systemctl enable snmptrapd

或者

snmptrapd -C -c /etc/snmp/snmptrapd.conf -Lf /var/log/net-snmptrap.log

netstat -nlp|grep 162

pkill -9 snmptrapd

现在您已经设置好了，让我们抛出一个 SNMP 陷阱来测试脚本是否运行。

当指定 linkDown 的 OID 时就是这种情况。

snmptrap -v 2c -c public 127.0.0.1 '' .1.3.6.1.6.3.1.1.5.3

然后我们再去我们的日志查看

cat/var/log/snmptrap/snmptrap.log

prometheus配置：

说明：14，18，19为三个不同的中继接口。当使用率大于80%后报警。

报警公式： pstn_channel_use / (pstn_channel_idle + pstn_channel_use) > 0.8 

######################

- job_name: snmp

  honor_timestamps: true

  scrape_interval: 30s

  scrape_timeout: 10s

  metrics_path: /snmp

  scheme: http

  static_configs:

  - targets:

    - "14"

    - "18"

    - "19"

  relabel_configs:

  - source_labels: [__address__]

    separator: ;

    regex: (.*)

    target_label: __param_target

    replacement: $1

    action: replace

  - source_labels: [__param_target]

    separator: ;

    regex: (.*)

    target_label: instance

    replacement: $1

    action: replace

  - separator: ;

    regex: (.*)

    target_label: __address__

    replacement: 192.168.185.85:9116

    action: replace

##################################