背景说明
服务部署在阿里云的k8s上，配置了基于prometheus的grafana监控。原本用的是自定义的metrics接口统计，上报一些字段，后面发现prometheus自带的监控非常全面好用，适合直接抓取统计，所以做了一些改变。
python prometheus-client 安装
pip install prometheus-client
python封装
# encoding: utf-8
from prometheus_client import counter, gauge, summary
from prometheus_client.core import collectorregistry
from prometheus_client.exposition import choose_encoder
class monitor:
def __init__(self):
# 注册收集器&最大耗时map
self.collector_registry = collectorregistry(auto_describe=false)
self.request_time_max_map = {}
# 接口调用summary统计
self.http_request_summary = summary(name="http_server_requests_seconds",
documentation="num of request time summary",
labelnames=("method", "code", "uri"),
registry=self.collector_registry)
# 接口最大耗时统计
self.http_request_max_cost = gauge(name="http_server_requests_seconds_max",
documentation="number of request max cost",
labelnames=("method", "code", "uri"),
registry=self.collector_registry)
# 请求失败次数统计
self.http_request_fail_count = counter(name="http_server_requests_error",
documentation="times of request fail in total",
labelnames=("method", "code", "uri"),
registry=self.collector_registry)
# 模型预测耗时统计
self.http_request_predict_cost = counter(name="http_server_requests_seconds_predict",
documentation="seconds of prediction cost in total",
labelnames=("method", "code", "uri"),
registry=self.collector_registry)
# 图片下载耗时统计
self.http_request_download_cost = counter(name="http_server_requests_seconds_download",
documentation="seconds of download cost in total",
labelnames=("method", "code", "uri"),
registry=self.collector_registry)
# 获取/metrics结果
def get_prometheus_metrics_info(self, handler):
encoder, content_type = choose_encoder(handler.request.headers.get('accept'))
handler.set_header("content-type", content_type)
handler.write(encoder(self.collector_registry))
self.reset_request_time_max_map()
# summary统计
def set_prometheus_request_summary(self, handler):
self.http_request_summary.labels(handler.request.method, handler.get_status(), handler.request.path).observe(handler.request.request_time())
self.set_prometheus_request_max_cost(handler)
# 自定义summary统计
def set_prometheus_request_summary_customize(self, method, status, path, cost_time):
self.http_request_summary.labels(method, status, path).observe(cost_time)
self.set_prometheus_request_max_cost_customize(method, status, path, cost_time)
# 失败统计
def set_prometheus_request_fail_count(self, handler, amount=1.0):
self.http_request_fail_count.labels(handler.request.method, handler.get_status(), handler.request.path).inc(amount)
# 自定义失败统计
def set_prometheus_request_fail_count_customize(self, method, status, path, amount=1.0):
self.http_request_fail_count.labels(method, status, path).inc(amount)
# 最大耗时统计
def set_prometheus_request_max_cost(self, handler):
requset_cost = handler.request.request_time()
if self.check_request_time_max_map(handler.request.path, requset_cost):
self.http_request_max_cost.labels(handler.request.method, handler.get_status(), handler.request.path).set(requset_cost)
self.request_time_max_map[handler.request.path] = requset_cost
# 自定义最大耗时统计
def set_prometheus_request_max_cost_customize(self, method, status, path, cost_time):
if self.check_request_time_max_map(path, cost_time):
self.http_request_max_cost.labels(method, status, path).set(cost_time)
self.request_time_max_map[path] = cost_time
# 预测耗时统计
def set_prometheus_request_predict_cost(self, handler, amount=1.0):
self.http_request_predict_cost.labels(handler.request.method, handler.get_status(), handler.request.path).inc(amount)
# 自定义预测耗时统计
def set_prometheus_request_predict_cost_customize(self, method, status, path, cost_time):
self.http_request_predict_cost.labels(method, status, path).inc(cost_time)
# 下载耗时统计
def set_prometheus_request_download_cost(self, handler, amount=1.0):
self.http_request_download_cost.labels(handler.request.method, handler.get_status(), handler.request.path).inc(amount)
# 自定义下载耗时统计
def set_prometheus_request_download_cost_customize(self, method, status, path, cost_time):
self.http_request_download_cost.labels(method, status, path).inc(cost_time)
# 校验是否赋值最大耗时map
def check_request_time_max_map(self, uri, cost):
if uri not in self.request_time_max_map:
return true
if self.request_time_max_map[uri] < cost:
return true
return false
# 重置最大耗时map
def reset_request_time_max_map(self):
for key in self.request_time_max_map:
self.request_time_max_map[key] = 0.0
调用
import tornado
import tornado.ioloop
import tornado.web
import tornado.gen
from datetime import datetime
from tools.monitor import monitor
global g_monitor
class classifierhandler(tornado.web.requesthandler):
def post(self):
# todo something you need
# work....
# 统计summary，包括请求次数和每次耗时
g_monitor.set_prometheus_request_summary(self)
self.write("ok")
class pinghandler(tornado.web.requesthandler):
def head(self):
print('info', datetime.now(), "/ping head.")
g_monitor.set_prometheus_request_summary(self)
self.write("ok")
def get(self):
print('info', datetime.now(), "/ping get.")
g_monitor.set_prometheus_request_summary(self)
self.write("ok")
class metricshandler(tornado.web.requesthandler):
def get(self):
print('info', datetime.now(), "/metrics get.")
g_monitor.set_prometheus_request_summary(self)
# 通过metrics接口返回统计结果
g_monitor.get_prometheus_metrics_info(self)
def make_app():
return tornado.web.application([
(r"/ping?", pinghandler),
(r"/metrics?", metricshandler),
(r"/work?", classifierhandler)
])
if __name__ == "__main__":
g_monitor = monitor()
app = make_app()
app.listen(port)
tornado.ioloop.ioloop.current().start()
metrics返回结果实例
到此这篇关于详解python prometheus_client使用方式的文章就介绍到这了,更多相关python prometheus_client内容请搜索www.887551.com以前的文章或继续浏览下面的相关文章希望大家以后多多支持www.887551.com！
黄山市民网：https://www.huangshanshimin.com/
