首页 文章

普罗米修斯为Tensorflow服务

提问于
浏览
0

使用Prometheus导出器进行Tensorflow服务的步骤是什么?根据1.11 TF服务支持prometheus指标:https://github.com/tensorflow/serving/releases/tag/1.11.0

我正在从示例https://www.tensorflow.org/serving/docker开始一个docker以及以下内容:

docker run -p 8501:8501 -p 8500:8500 \ --mount type = bind,\ source = / tmp / tfserving / serving / tensorflow_serving / servables / tensorflow / testdata / saved_model_half_plus_two_cpu,\ target = / models / half_plus_two \ -e MODEL_NAME = half_plus_two -t tensorflow / serving&

Prometheus配置文件:global:scrape_interval:10s evaluation_interval:10s external_labels:monitor:'tf-serving-monitor'

scrape_configs: - job_name:'tensorflow'scrape_interval:5s static_configs: - targets:['localhost:8501']

但prometheus未能找到服务公开的指标 . 我应该在docker上打开一个特定的端口,还是应该传递给TF服务的一些参数?

1 回答

  • 1

    According to the release notes you linked to TensorFlow导出 /monitoring/prometheus/metrics 处的Prometheus指标(与Prometheus的默认 /metrics 相反) . 所以至少你需要在配置中添加 metrics_path

    scrape_configs:
      - job_name: 'tensorflow'
        scrape_interval: 5s
        metrics_path: '/monitoring/prometheus/metrics'
        static_configs:
          - targets: ['localhost:8501']
    

    但首先请确保您可以在浏览器中查看http://localhost:8501/monitoring/prometheus/metrics处导出的指标 . 其他人(使用您的浏览器)直到找到正确的URL(并在您的配置中反映出来) .

相关问题