locust（二）配置prometheus和grafana

一、Prometheus介绍

Prometheus是一个开源的系统监控和报警系统，在kubernetes容器管理系统中，通常会搭配prometheus进行监控，同时也支持多种exporter采集数据，还支持pushgateway进行数据上报，Prometheus性能足够支撑上万台规模的集群。

二、grafana介绍

Prometheus的重要组件之一，提供监控仪表盘，可视化监控数据的功能

三、locust介绍

Locust 是一个开源负载测试工具,使用的‘协程’方式,有webui图形界面、无图形界面、分布式等多种运行方式。

为啥要使用Prometheus和grafana,locust 自带检测结果太丑，数据无法持久化

具体操作

1.先参考官网提供的prometheus_exporter.py

# coding: utf8

import six
from itertools import chain

from flask import request, Response
from locust import stats as locust_stats, runners as locust_runners
from locust import User, task, events
from prometheus_client import Metric, REGISTRY, exposition

# This locustfile adds an external web endpoint to the locust master, and makes it serve as a prometheus exporter.
# Runs it as a normal locustfile, then points prometheus to it.
# locust -f prometheus_exporter.py --master

# Lots of code taken from [mbolek's locust_exporter](https://github.com/mbolek/locust_exporter), thx mbolek!


class LocustCollector(object):
    registry = REGISTRY

    def __init__(self, environment, runner):
        self.environment = environment
        self.runner = runner

    def collect(self):
        # collect metrics only when locust runner is spawning or running.
        runner = self.runner

        if runner and runner.state in (locust_runners.STATE_SPAWNING, locust_runners.STATE_RUNNING):
            stats = []
            for s in chain(locust_stats.sort_stats(runner.stats.entries), [runner.stats.total]):
                stats.append({
                    "method": s.method,
                    "name": s.name,
                    "num_requests": s.num_requests,
                    "num_failures": s.num_failures,
                    "avg_response_time": s.avg_response_time,
                    "min_response_time": s.min_response_time or 0,
                    "max_response_time": s.max_response_time,
                    "current_rps": s.current_rps,
                    "median_response_time": s.median_response_time,
                    "ninetieth_response_time": s.get_response_time_percentile(0.9),
                    # only total stats can use current_response_time, so sad.
                    #"current_response_time_percentile_95": s.get_current_response_time_percentile(0.95),
                    "avg_content_length": s.avg_content_length,
                    "current_fail_per_sec": s.current_fail_per_sec
                })

            # perhaps StatsError.parse_error in e.to_dict only works in python slave, take notices!
            errors = [e.to_dict() for e in six.itervalues(runner.stats.errors)]

            metric = Metric('locust_user_count', 'Swarmed users', 'gauge')
            metric.add_sample('locust_user_count', value=runner.user_count, labels={})
            yield metric
            
            metric = Metric('locust_errors', 'Locust requests errors', 'gauge')
            for err in errors:
                metric.add_sample('locust_errors', value=err['occurrences'],
                                  labels={'path': err['name'], 'method': err['method'],
                                          'error': err['error']})
            yield metric

            is_distributed = isinstance(runner, locust_runners.MasterRunner)
            if is_distributed:
                metric = Metric('locust_slave_count', 'Locust number of slaves', 'gauge')
                metric.add_sample('locust_slave_count', value=len(runner.clients.values()), labels={})
                yield metric

            metric = Metric('locust_fail_ratio', 'Locust failure ratio', 'gauge')
            metric.add_sample('locust_fail_ratio', value=runner.stats.total.fail_ratio, labels={})
            yield metric

            metric = Metric('locust_state', 'State of the locust swarm', 'gauge')
            metric.add_sample('locust_state', value=1, labels={'state': runner.state})
            yield metric

            stats_metrics = ['avg_content_length', 'avg_response_time', 'current_rps', 'current_fail_per_sec',
                             'max_response_time', 'ninetieth_response_time', 'median_response_time', 'min_response_time',
                             'num_failures', 'num_requests']

            for mtr in stats_metrics:
                mtype = 'gauge'
                if mtr in ['num_requests', 'num_failures']:
                    mtype = 'counter'
                metric = Metric('locust_stats_' + mtr, 'Locust stats ' + mtr, mtype)
                for stat in stats:
                    # Aggregated stat's method label is None, so name it as Aggregated
                    # locust has changed name Total to Aggregated since 0.12.1
                    if 'Aggregated' != stat['name']:
                        metric.add_sample('locust_stats_' + mtr, value=stat[mtr],
                                          labels={'path': stat['name'], 'method': stat['method']})
                    else:
                        metric.add_sample('locust_stats_' + mtr, value=stat[mtr],
                                          labels={'path': stat['name'], 'method': 'Aggregated'})
                yield metric


@events.init.add_listener
def locust_init(environment, runner, **kwargs):
    print("locust init event received")
    if environment.web_ui and runner:
        @environment.web_ui.app.route("/export/prometheus")
        def prometheus_exporter():
            registry = REGISTRY
            encoder, content_type = exposition.choose_encoder(request.headers.get('Accept'))
            if 'name[]' in request.args:
                registry = REGISTRY.restricted_registry(request.args.get('name[]'))
            body = encoder(registry)
            return Response(body, content_type=content_type)
        REGISTRY.register(LocustCollector(environment, runner))


class Dummy(User):
    @task(20)
    def hello(self):
        pass

使用方式两种，

a、直接修改改文件，将自己的压测类替换Dummy类，当启动压测，自动会启动ip:/export/prometheus的服务，该服务的数据就是我们需要收集的数据

b、以master启动该脚本，压测脚本以worker形式启动，指向master为启动该脚本的地址

b优势在于，监听服务可以永远启动，第一种方式只有压测时才启动

调用/export/prometheus的截图:

2.上面图有内容，说明locust-explorer已经搞定，继续安装Prometheus和grafana 。。。此处省略一万字

3.启动Prometheus后,浏览器输入服务器ip:9090即可打开页面,表示启动正常

4.配置Prometheus.yml,增加数据源为上面的接口地址

- job_name: locust

    metrics_path: '/export/prometheus'
    static_configs:
      - targets: ['slave机ip:8089']
        labels:
          instance: locust

配置后重启prometheus服务，然后再刷新页面：