架构:yarn+flink+supervisor+pushgateway+prometheus+node_exporter+grafana
下载如下离线包,安装
grafana-enterprise-9.2.3.linux-amd64.tar.gz
node_exporter-1.4.0.linux-amd64.tar.gz
prometheus-2.39.1.linux-amd64.tar.gz
pushgateway-1.4.3.linux-amd64.tar.gz
在supervisor中配置上面组件的启动文件
[baiyun@hadoop102 supervisord.d]$ ll
总用量 16
-rw-rw-r–. 1 baiyun baiyun 371 11月 2 23:32 grafana.ini
-rw-rw-r–. 1 baiyun baiyun 276 11月 3 00:57 node_exporter.ini
-rw-rw-r–. 1 baiyun baiyun 448 11月 3 00:02 prometheus.ini
-rw-rw-r–. 1 baiyun baiyun 293 11月 3 00:01 pushgateway.ini
grafana.ini
[baiyun@hadoop102 supervisord.d]$ cat grafana.ini
[program:grafana]
command=/home/baiyun/my_soft/grafana/bin/grafana-server --homepath /home/baiyun/my_soft/grafana web
user=root
autostart=true
autorestart=true
startsecs=10
exitcodes=0
redirect_stderr=true
stdout_logfile=/home/baiyun/my_soft/grafana/log/grafana.log
stdout_logfile_backups=5
node_exporter.ini
[baiyun@hadoop102 supervisord.d]$ cat node_exporter.ini
[program:node_exporter]
command=/home/baiyun/my_soft/node_exporter/node_exporter
user=root
autostart=true
autorestart=true
startsecs=10
exitcodes=0
redirect_stderr=true
stdout_logfile=/home/baiyun/my_soft/node_exporter/log/node_exporter.log
stdout_logfile_backups=5
prometheus.ini
[baiyun@hadoop102 supervisord.d]$ cat prometheus.ini
[program:prometheus]
command=/home/baiyun/my_soft/prometheus/prometheus --config.file=/home/baiyun/my_soft/prometheus/prometheus.yml --storage.tsdb.path /home/baiyun/my_soft/prometheus/data --storage.tsdb.retention.time 1d --enable-feature=promql-at-modifier
user=root
autostart=true
autorestart=true
startsecs=10
exitcodes=0
redirect_stderr=true
stdout_logfile=/home/baiyun/my_soft/prometheus/log/prometheus.log
stdout_logfile_backups=5
pushgateway.ini
[baiyun@hadoop102 supervisord.d]$ cat pushgateway.ini
[program:pushgateway]
command=/home/baiyun/my_soft/pushgateway/pushgateway --web.listen-address :9091
user=root
autostart=true
autorestart=true
startsecs=10
exitcodes=0
redirect_stderr=true
stdout_logfile=/home/baiyun/my_soft/pushgateway/log/pushgateway.log
stdout_logfile_backups=5
supervisord.conf
[baiyun@hadoop102 my_etc]$ cat supervisord.conf
; Sample supervisor config file.
;
; For more information on the config file, please see:
; http://supervisord.org/configuration.html
;
; Notes:
; - Shell expansion ("~" or "$HOME") is not supported. Environment
; variables can be expanded using this syntax: "%(ENV_HOME)s".
; - Quotes around values are not supported, except in the case of
; the environment= options as shown below.
; - Comments must have a leading space: "a=b ;comment" not "a=b;comment".
; - Command will be truncated if it looks like a config file comment, e.g.
; "command=bash -c 'foo ; bar'" will truncate to "command=bash -c 'foo ".
;
; Warning:
; Paths throughout this example file use /tmp because it is available on most
; systems. You will likely need to change these to locations more appropriate
; for your system. Some systems periodically delete older files in /tmp.
; Notably, if the socket file defined in the [unix_http_server] section below
; is deleted, supervisorctl will be unable to connect to supervisord.
[unix_http_server]
file=/var/run/supervisor/supervisor.sock ; the path to the socket file
;chmod=0700 ; socket file mode (default 0700)
;chown=nobody:nogroup ; socket file uid:gid owner
;username=user ; default is no username (open server)
;password=123 ; default is no password (open server)
; Security Warning:
; The inet HTTP server is not enabled by default. The inet HTTP server is
; enabled by uncommenting the [inet_http_server] section below. The inet
; HTTP server is intended for use within a trusted environment only. It
; should only be bound to localhost or only accessible from within an
; isolated, trusted network. The inet HTTP server does not support any
; form of encryption. The inet HTTP server does not use authentication
; by default (see the username= and password= options to add authentication).
; Never expose the inet HTTP server to the public internet.
[inet_http_server] ; inet (TCP) server disabled by default
port=0.0.0.0:9001 ; ip_address:port specifier, *:port for all iface
;username=user ; default is no username (open server)
;password=123 ; default is no password (open server)
[supervisord]
logfile=/var/log/supervisor/supervisord.log ; main log file; default $CWD/supervisord.log
logfile_maxbytes=50MB ; max main logfile bytes b4 rotation; default 50MB
logfile_backups=10 ; # of main logfile backups; 0 means none, default 10
loglevel=info ; log level; default info; others: debug,warn,trace
pidfile=/var/run/supervisord.pid ; supervisord pidfile; default supervisord.pid
nodaemon=false ; start in foreground if true; default false
silent=false ; no logs to stdout if true; default false
minfds=1024 ; min. avail startup file descriptors; default 1024
minprocs=200 ; min. avail process descriptors;default 200
;umask=022 ; process file creation umask; default 022
;user=supervisord ; setuid to this UNIX account at startup; recommended if root
;identifier=supervisor ; supervisord identifier, default is 'supervisor'
;directory=/tmp ; default is not to cd during start
;nocleanup=true ; don't clean up tempfiles at start; default false
;childlogdir=/tmp ; 'AUTO' child log dir, default $TEMP
;environment=KEY="value" ; key value pairs to add to environment
;strip_ansi=false ; strip ansi escape codes in logs; def. false
; The rpcinterface:supervisor section must remain in the config file for
; RPC (supervisorctl/web interface) to work. Additional interfaces may be
; added by defining them in separate [rpcinterface:x] sections.
[rpcinterface:supervisor]
supervisor.rpcinterface_factory = supervisor.rpcinterface:make_main_rpcinterface
; The supervisorctl section configures how supervisorctl will connect to
; supervisord. configure it match the settings in either the unix_http_server
; or inet_http_server section.
[supervisorctl]
serverurl=unix:///var/run/supervisor/supervisor.sock ; use a unix:// URL for a unix socket
;serverurl=http://127.0.0.1:9001 ; use an http:// url to specify an inet socket
;username=chris ; should be same as in [*_http_server] if set
;password=123 ; should be same as in [*_http_server] if set
;prompt=mysupervisor ; cmd line prompt (default "supervisor")
;history_file=~/.sc_history ; use readline history if available
; The sample program section below shows all possible program subsection values.
; Create one or more 'real' program: sections to be able to control them under
; supervisor.
;[program:theprogramname]
;command=/bin/cat ; the program (relative uses PATH, can take args)
;process_name=%(program_name)s ; process_name expr (default %(program_name)s)
;numprocs=1 ; number of processes copies to start (def 1)
;directory=/tmp ; directory to cwd to before exec (def no cwd)
;umask=022 ; umask for process (default None)
;priority=999 ; the relative start priority (default 999)
;autostart=true ; start at supervisord start (default: true)
;startsecs=1 ; # of secs prog must stay up to be running (def. 1)
;startretries=3 ; max # of serial start failures when starting (default 3)
;autorestart=unexpected ; when to restart if exited after running (def: unexpected)
;exitcodes=0 ; 'expected' exit codes used with autorestart (default 0)
;stopsignal=QUIT ; signal used to kill process (default TERM)
;stopwaitsecs=10 ; max num secs to wait b4 SIGKILL (default 10)
;stopasgroup=false ; send stop signal to the UNIX process group (default false)
;killasgroup=false ; SIGKILL the UNIX process group (def false)
;user=chrism ; setuid to this UNIX account to run the program
;redirect_stderr=true ; redirect proc stderr to stdout (default false)
;stdout_logfile=/a/path ; stdout log path, NONE for none; default AUTO
;stdout_logfile_maxbytes=1MB ; max # logfile bytes b4 rotation (default 50MB)
;stdout_logfile_backups=10 ; # of stdout logfile backups (0 means none, default 10)
;stdout_capture_maxbytes=1MB ; number of bytes in 'capturemode' (default 0)
;stdout_events_enabled=false ; emit events on stdout writes (default false)
;stdout_syslog=false ; send stdout to syslog with process name (default false)
;stderr_logfile=/a/path ; stderr log path, NONE for none; default AUTO
;stderr_logfile_maxbytes=1MB ; max # logfile bytes b4 rotation (default 50MB)
;stderr_logfile_backups=10 ; # of stderr logfile backups (0 means none, default 10)
;stderr_capture_maxbytes=1MB ; number of bytes in 'capturemode' (default 0)
;stderr_events_enabled=false ; emit events on stderr writes (default false)
;stderr_syslog=false ; send stderr to syslog with process name (default false)
;environment=A="1",B="2" ; process environment additions (def no adds)
;serverurl=AUTO ; override serverurl computation (childutils)
; The sample eventlistener section below shows all possible eventlistener
; subsection values. Create one or more 'real' eventlistener: sections to be
; able to handle event notifications sent by supervisord.
;[eventlistener:theeventlistenername]
;command=/bin/eventlistener ; the program (relative uses PATH, can take args)
;process_name=%(program_name)s ; process_name expr (default %(program_name)s)
;numprocs=1 ; number of processes copies to start (def 1)
;events=EVENT ; event notif. types to subscribe to (req'd)
;buffer_size=10 ; event buffer queue size (default 10)
;directory=/tmp ; directory to cwd to before exec (def no cwd)
;umask=022 ; umask for process (default None)
;priority=-1 ; the relative start priority (default -1)
;autostart=true ; start at supervisord start (default: true)
;startsecs=1 ; # of secs prog must stay up to be running (def. 1)
;startretries=3 ; max # of serial start failures when starting (default 3)
;autorestart=unexpected ; autorestart if exited after running (def: unexpected)
;exitcodes=0 ; 'expected' exit codes used with autorestart (default 0)
;stopsignal=QUIT ; signal used to kill process (default TERM)
;stopwaitsecs=10 ; max num secs to wait b4 SIGKILL (default 10)
;stopasgroup=false ; send stop signal to the UNIX process group (default false)
;killasgroup=false ; SIGKILL the UNIX process group (def false)
;user=chrism ; setuid to this UNIX account to run the program
;redirect_stderr=false ; redirect_stderr=true is not allowed for eventlisteners
;stdout_logfile=/a/path ; stdout log path, NONE for none; default AUTO
;stdout_logfile_maxbytes=1MB ; max # logfile bytes b4 rotation (default 50MB)
;stdout_logfile_backups=10 ; # of stdout logfile backups (0 means none, default 10)
;stdout_events_enabled=false ; emit events on stdout writes (default false)
;stdout_syslog=false ; send stdout to syslog with process name (default false)
;stderr_logfile=/a/path ; stderr log path, NONE for none; default AUTO
;stderr_logfile_maxbytes=1MB ; max # logfile bytes b4 rotation (default 50MB)
;stderr_logfile_backups=10 ; # of stderr logfile backups (0 means none, default 10)
;stderr_events_enabled=false ; emit events on stderr writes (default false)
;stderr_syslog=false ; send stderr to syslog with process name (default false)
;environment=A="1",B="2" ; process environment additions
;serverurl=AUTO ; override serverurl computation (childutils)
; The sample group section below shows all possible group values. Create one
; or more 'real' group: sections to create "heterogeneous" process groups.
;[group:thegroupname]
;programs=progname1,progname2 ; each refers to 'x' in [program:x] definitions
;priority=999 ; the relative start priority (default 999)
; The [include] section can just contain the "files" setting. This
; setting can list multiple files (separated by whitespace or
; newlines). It can also contain wildcards. The filenames are
; interpreted as relative to this file. Included files *cannot*
; include files themselves.
[include]
prometheus.yml
[baiyun@hadoop102 prometheus]$ cat prometheus.yml
# my global config
global:
scrape_interval: 30s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
# scrape_timeout is set to the global default (10s).
# Alertmanager configuration
alerting:
alertmanagers:
- static_configs:
- targets:
# - alertmanager:9093
# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files:
# - "first_rules.yml"
# - "second_rules.yml"
# A scrape configuration containing exactly one endpoint to scrape:
# Here it's Prometheus itself.
scrape_configs:
- job_name: "prometheus"
static_configs:
- targets: ["localhost:9090"]
- job_name: 'pushgateway'
static_configs:
- targets: ['localhost:9091']
labels:
instance: pushgateway
- job_name: 'node exporter'
static_configs:
- targets: ['localhost:9100']
flink-conf.yaml
classloader.check-leaked-classloader: false
##### 与Prometheus集成配置 #####
metrics.reporter.promgateway.class: org.apache.flink.metrics.prometheus.PrometheusPushGatewayReporter
## PushGateway的主机名与端口号
metrics.reporter.promgateway.host: xxx
metrics.reporter.promgateway.port: 9091
## Flink metric在前端展示的标签(前缀)与随机后缀
metrics.reporter.promgateway.jobName: flink-metrics
metrics.reporter.promgateway.randomJobNameSuffix: true
metrics.reporter.promgateway.deleteOnShutdown: false
metrics.reporter.promgateway.interval: 30 SECONDS