[Debian] 使用 Telegraf, InfluxDB and Grafana 監控網路狀態
#Step: 01 – Grafana 安裝在 Debian 10 上
說明 #Step: 02 – influxdb 安裝在 Debian 10 上
說明 #Step: 03 – telegraf 安裝在 Debian 10 上
說明 #Step: 04 – telegraf 設定檔
說明 #Step: 05 – Grafana 監控SNMP 設備
說明
說明
apt update
安裝資料庫
apt install mariadb-server
修改 root 使用密碼登入方式
USE mysql;
UPDATE user SET plugin='mysql_native_password' WHERE user='root';
FLUSH PRIVILEGES;
exit;
mysql_secure_installation
#
CREATE DATABASE grafana CHARACTER SET UTF8 COLLATE UTF8_BIN;
CREATE USER 'grafana'@'%' IDENTIFIED BY 'Oscar123wu123';
GRANT ALL PRIVILEGES ON grafana.* TO 'grafana'@'%';
quit;
#
sudo apt-get install -y apt-transport-https
sudo apt-get install -y software-properties-common wget
wget -q -O - https://packages.grafana.com/gpg.key | sudo apt-key add -
# Alternatively you can add the beta repository, see in the table above
sudo add-apt-repository "deb https://packages.grafana.com/oss/deb stable main"
sudo apt-get update
sudo apt-get install grafana
OR
sudo apt-get install -y adduser libfontconfig1
wget https://dl.grafana.com/oss/release/grafana_7.0.1_amd64.deb
sudo dpkg -i grafana_7.0.1_amd64.deb
#
vi /etc/grafana/grafana.ini
=====================================================================
[database]
type = mysql
host = 127.0.0.1:3306
name = grafana
user = grafana
password = Oscar123wu123
[session]
provider = mysql
provider_config = `grafana:Oscar123wu123@tcp(127.0.0.1:3306)/grafana`
=====================================================================
service grafana-server start
systemctl enable --now grafana-server
systemctl status grafana-server
#
說明
mkdir /downloads
cd /downloads
wget https://dl.influxdata.com/influxdb/releases/influxdb_1.8.0_amd64.deb
dpkg -i influxdb_1.8.0_amd64.deb
systemctl enable --now influxdb
systemctl status influxdb
說明
mkdir /downloads
cd /downloads
wget https://dl.influxdata.com/telegraf/releases/telegraf_1.14.3-1_amd64.deb
dpkg -i telegraf_1.14.3-1_amd64.deb
systemctl enable --now telegraf
確認服務
systemctl status telegraf
設定基本設定
vi /etc/telegraf/telegraf.conf
================================================
[global_tags]
[agent]
interval = "10s"
round_interval = true
metric_batch_size = 1000
metric_buffer_limit = 10000
collection_jitter = "0s"
flush_interval = "10s"
flush_jitter = "0s"
precision = ""
hostname = ""
omit_hostname = false
[[outputs.influxdb]]
[[inputs.cpu]]
percpu = true
totalcpu = true
collect_cpu_time = false
report_active = false
[[inputs.disk]]
ignore_fs = ["tmpfs", "devtmpfs", "devfs", "iso9660", "overlay", "aufs", "squashfs"]
[[inputs.diskio]]
[[inputs.kernel]]
[[inputs.mem]]
[[inputs.processes]]
[[inputs.swap]]
[[inputs.system]]
================================================
設定監控主機
vi /etc/telegraf/telegraf.d/monitor-linux-snmp.conf
================================================
[[inputs.snmp]]
agents = [ "172.31.41.29:161"]
version = 2
community = "GokuBlack"
name = "snmp"
[[inputs.snmp.field]]
name = "hostname"
oid = "RFC1213-MIB::sysName.0"
is_tag = true
[[inputs.snmp.table]]
name = "snmp"
inherit_tags = [ "hostname" ]
oid = "IF-MIB::ifXTable"
[[inputs.snmp.table.field]]
name = "ifName"
oid = "IF-MIB::ifName"
is_tag = true
=====================================================
重啟 telegraf
service telegraf restart
##
1. 安裝 snmpd 服務
# apt-get install snmpd snmp
2. 修改 /etc/snmp/snmpd.conf 設定檔
# sed -i 's/#rocommunity public localhost/rocommunity public localhost/' /etc/snmp/snmpd.conf
3. 讓其它的 IP 可以讀取 snmp 相關資訊
# sed -i 's/127.0.0.1/0.0.0.0/' /etc/snmp/snmpd.conf
或
# sed -i 's/agentAddress udp:127.0.0.1:161/#agentAddress udp:127.0.0.1:161/' /etc/snmp/snmpd.conf
# sed -i 's/#agentAddress udp:161/agentAddress udp:161/' /etc/snmp/snmpd.conf
或
# echo 'rocommunity public' > /etc/snmp/snmpd.conf
# chmod 600 /etc/snmp/snmpd.conf
4. 啟動 snmpd 服務
# /etc/init.d/snmpd start
Starting network management services: snmpd.
5. 檢查 snmpd 是否有正常啟動
# netstat -anulp | grep 161
udp 0 0 0.0.0.0:161 0.0.0.0:* 4540/snmpd
6. 讀取 snmpd 資訊
# snmpwalk -v 1 -c public localhost | less
# snmpwalk -v 2c -c public localhost | less
7. 在防火牆設定限制
# iptabels -A INPUT -u udp -s x.x.x.x --dport 161 -m state --state NEW -j ACCEPT
調整吐出來的資訊完整度 , default 可改成 host ip (正面表列)
rocommunity修改成如下
#rocommunity6 public default -V systemonly
#rocommunity public default -V systemonly
rocommunity public default
service snmpd restart
說明
vi /etc/telegraf/telegraf.conf
[global_tags]
[agent]
interval = "10s"
round_interval = true
metric_batch_size = 1000
metric_buffer_limit = 10000
collection_jitter = "0s"
flush_interval = "10s"
flush_jitter = "0s"
precision = ""
hostname = ""
omit_hostname = false
[[outputs.influxdb]]
[[inputs.cpu]]
percpu = true
totalcpu = true
collect_cpu_time = false
report_active = false
[[inputs.disk]]
ignore_fs = ["tmpfs", "devtmpfs", "devfs", "iso9660", "overlay", "aufs", "squashfs"]
[[inputs.diskio]]
[[inputs.kernel]]
[[inputs.mem]]
[[inputs.processes]]
[[inputs.swap]]
[[inputs.system]]
vi /etc/telegraf/telegraf.d/monitor-linux-snmp.conf
[[inputs.snmp]]
agents = [ "127.0.0.1:161"]
version = 2
community = "public"
name = "snmp"
[[inputs.snmp.field]]
name = "hostname"
oid = "RFC1213-MIB::sysName.0"
is_tag = true
[[inputs.snmp.table]]
name = "snmp"
inherit_tags = [ "hostname" ]
oid = "IF-MIB::ifXTable"
[[inputs.snmp.table.field]]
name = "ifName"
oid = "IF-MIB::ifName"
is_tag = true
=========================
service telegraf restart
telegraf -config /etc/telegraf/telegraf.d/monitor-linux-snmp.conf --test
influx
> use telegraf
Using database telegraf
> show measurements
name: measurements
name
----
cpu
disk
diskio
interface
kernel
mem
processes
snmp
swap
system
> select * from snmp limit 2
name: snmp
time agent_host host hostname ifConnectorPresent ifCounterDiscontinuityTime ifHCInBroadcastPkts ifHCInMulticastPkts ifHCInOctets ifHCInUcastPkts ifHCOutBroadcastPkts ifHCOutMulticastPkts ifHCOutOctets ifHCOutUcastPkts ifHighSpeed ifInBroadcastPkts ifInMulticastPkts ifName ifOutBroadcastPkts ifOutMulticastPkts ifPromiscuousMode
---- ---------- ---- -------- ------------------ -------------------------- ------------------- ------------------- ------------ --------------- -------------------- -------------------- ------------- ---------------- ----------- ----------------- ----------------- ------ ------------------ ------------------ -----------------
1590563960000000000 127.0.0.1 Debian10-4-InfluxDB-Telegraf-Grafana-02 Debian10-4-InfluxDB-Telegraf-Grafana-02 1 0 0 0 163832728 117733 0 0 14911617 57903 10000 0 0 ens192 0 0 2
1590563960000000000 127.0.0.1 Debian10-4-InfluxDB-Telegraf-Grafana-02 Debian10-4-InfluxDB-Telegraf-Grafana-02 2 0 0 0 6058851 35460 0 0 6058851 35460 10 0 0 lo 0
說明
Grafana Monitoring SNMP Device
要修改相對應的主機名稱和網卡
SELECT non_negative_derivative(mean("ifHCInOctets"), 1s) *8 AS "In" FROM "snmp" WHERE ("hostname" = 'Debian10-4-InfluxDB-Telegraf-Grafana-02' AND "ifName" = 'ens192') AND $timeFilter GROUP BY time($__interval), "hostname", "ifName" fill(null)
SELECT non_negative_derivative(mean("ifHCOutOctets"), 1s) *8 AS "Out" FROM "snmp" WHERE ("hostname" = 'Debian10-4-InfluxDB-Telegraf-Grafana-02' AND "ifName" = 'ens192') AND $timeFilter GROUP BY time($__interval), "hostname", "ifName" fill(null)
說明
當前3種最佳解決方法是：
使用 name_override，name_suffix 或 name_prefix 配置選項將名稱放在輸入端的測量之前，然後使用namepass路由到輸出，範例如下：
這邊使用 name_prefix 方式施作
=============================================================
[[inputs.exec]]
# ...
name_prefix = "exec1_"
[[inputs.exec]]
# ...
name_prefix = "exec2_"
# this influxdb will only get exec1
[[outputs.influxdb]]
# ...
namepass = "exec1_*"
# this will only get exec2
[[outputs.influxdb]]
# ...
namepass = "exec2_*"
# 輸入如下:
[[inputs.snmp]]
# ...
name_prefix = "exec1_"
agents = [ "192.168.1.250:161" ]
version = 2
community = "public"
name = "snmp"
[[inputs.snmp.field]]
name = "hostname"
oid = "RFC1213-MIB::sysName.0"
is_tag = true
[[inputs.snmp.table]]
name = "snmp"
inherit_tags = [ "hostname" ]
oid = "IF-MIB::ifXTable"
[[inputs.snmp.table.field]]
name = "ifName"
oid = "IF-MIB::ifName"
is_tag = true
[[inputs.snmp]]
# ...
name_prefix = "exec2_"
agents = [ "192.168.10.100:161" ]
version = 2
community = "load_public"
name = "snmp"
[[inputs.snmp.field]]
name = "hostname"
oid = "RFC1213-MIB::sysName.0"
is_tag = true
[[inputs.snmp.table]]
name = "snmp"
inherit_tags = [ "hostname" ]
oid = "IF-MIB::ifXTable"
[[inputs.snmp.table.field]]
name = "ifName"
oid = "IF-MIB::ifName"
is_tag = true
輸出如下:
[outputs]
[outputs.influxdb]
#.....
namepass = ["exec1_*"]
# The full HTTP endpoint URL for your InfluxDB instance
url = "http://localhost:8086"
# The target database for metrics. Telegraf will create the DB 1 if it does not exist
database = "exec1_telegraf"
[outputs]
[outputs.influxdb]
#.....
namepass = ["exec2_*"]
# The full HTTP endpoint URL for your InfluxDB instance
url = "http://localhost:8086"
# The target database for metrics. Telegraf will create the DB 2 if it does not exist
database = "exec2_telegraf"
==========================================================================
可以寫入道不同資料庫方式 要注意 name 會改變 變成 exec3_snmp 顯示如下
####################################
> show measurements
name: measurements
name
----
exec3_snmp
select * from exec3_snmp limit 2
####################################
[[inputs.snmp]]
name_prefix = "exec3_"
agents = ["xxx.xxx.xxx.xxx"]
version = 2
community = "public"
interval = "60s"
timeout = "10s"
retries = 3
name = "snmp"
[[inputs.snmp.field]]
name = "hostname"
oid = "RFC1213-MIB::sysName.0"
is_tag = true
[[inputs.snmp.field]]
name = "pool_client_connections"
oid = "F5-BIGIP-LOCAL-MIB::ltmPoolStatServerCurConns.15.47.67.111.109.109.111.110.47.71.87.95.112.111.111.108"
[[inputs.snmp.field]]
name = "F5_client_connections"
oid = "F5-BIGIP-SYSTEM-MIB::sysStatClientCurConns.0"
[outputs]
[outputs.influxdb]
#.....
namepass = ["exec3_*"]
# The full HTTP endpoint URL for your InfluxDB instance
url = "http://localhost:8086"
# The target database for metrics. Telegraf will create the DB 3 if it does not exist
database = "exec3_telegraf"
==========================================================================
使用標籤，標籤放置，標籤傳遞路由
運行多個Telegraf進程。
##
#配合ID 928 Templated dashboard for telegraf + influxdb. 設定檔
# Global tags can be specified here in key="value" format.
[global_tags]
# dc = "us-east-1" # will tag all metrics with dc=us-east-1
# rack = "1a"
## Environment variables can be used as tags, and throughout the config file
# user = "$USER"
# Configuration for telegraf agent
[agent]
interval = "10s"
round_interval = true
metric_batch_size = 1000
metric_buffer_limit = 10000
collection_jitter = "0s"
flush_interval = "10s"
flush_jitter = "0s"
precision = ""
debug = false
quiet = false
hostname = ""
omit_hostname = false
###############################################################################
# OUTPUTS #
###############################################################################
# Configuration for influxdb server to send metrics to
[[outputs.influxdb]]
#urls = ["http://your_host:8086"]
urls = ["http://localhost:8086"]
database = "telegraf_metrics"
## Retention policy to write to. Empty string writes to the default rp.
retention_policy = ""
## Write consistency (clusters only), can be: "any", "one", "quorum", "all"
write_consistency = "any"
## Write timeout (for the InfluxDB client), formatted as a string.
## If not provided, will default to 5s. 0s means no timeout (not recommended).
timeout = "5s"
# username = "telegraf"
# password = "2bmpiIeSWd63a7ew"
## Set the user agent for HTTP POSTs (can be useful for log differentiation)
# user_agent = "telegraf"
## Set UDP payload size, defaults to InfluxDB UDP Client default (512 bytes)
# udp_payload = 512
###############################################################################
# INPUTS #
###############################################################################
# Read metrics about cpu usage
[[inputs.cpu]]
## Whether to report per-cpu stats or not
percpu = true
## Whether to report total system cpu stats or not
totalcpu = true
## Comment this line if you want the raw CPU time metrics
fielddrop = ["time_*"]
# Read metrics about disk usage by mount point
[[inputs.disk]]
## By default, telegraf gather stats for all mountpoints.
## Setting mountpoints will restrict the stats to the specified mountpoints.
# mount_points = ["/"]
## Ignore some mountpoints by filesystem type. For example (dev)tmpfs (usually
## present on /run, /var/run, /dev/shm or /dev).
ignore_fs = ["tmpfs", "devtmpfs", "devfs", "iso9660", "overlay", "aufs", "squashfs"]
# Read metrics about disk IO by device
[[inputs.diskio]]
## By default, telegraf will gather stats for all devices including
## disk partitions.
## Setting devices will restrict the stats to the specified devices.
# devices = ["sda", "sdb"]
## Uncomment the following line if you need disk serial numbers.
# skip_serial_number = false
[[inputs.io]]
# Get kernel statistics from /proc/stat
[[inputs.kernel]]
# no configuration
# Read metrics about memory usage
[[inputs.mem]]
# no configuration
# Get the number of processes and group them by status
[[inputs.processes]]
# no configuration
# Read metrics about swap memory usage
[[inputs.swap]]
# no configuration
# Read metrics about system load & uptime
[[inputs.system]]
# no configuration
# Read metrics about network interface usage
[[inputs.net]]
# collect data only about specific interfaces
# interfaces = ["eth0"]
[[inputs.netstat]]
# no configuration
[[inputs.interrupts]]
# no configuration
[[inputs.linux_sysctl_fs]]
# no configuration
########################
沒有留言:
張貼留言