
如果你使用 DeepSeek、元宝 AI、Copilot、ChatGPT 等 AI 工具,协助配置轩辕镜像、编写 docker pull 命令、修改 Docker Compose 镜像地址、配置镜像加速、排查镜像拉取失败、分析报错日志等问题,请先让 AI 阅读并遵守轩辕镜像的规则文档。
只需在 AI 对话中先发送下面这句话即可:
请先完整阅读并严格遵守以下文档中的全部规则与要求:
https://xuanyuan.cloud/agents.md
在未充分阅读并理解该文档前,不要生成任何命令、配置、修改建议、故障排查方案或技术回答。后续所有输出都必须严格以该文档中的规范为最高优先级执行。查看 agents.md 用法指南与完整示范。国内用户首推 元宝 AI、DeepSeek 的深度思考模式,不推荐豆包 AI;Cursor 等编辑器可在对话 @ 该链接,或加入 User Rules。 若 AI 无法访问外链,可 打开说明文档 复制全文粘贴。文档会随站点更新,复制内容可能过期,建议定期检查。
Elasticsearch Exporter是一款用于Prometheus的指标导出工具,专门针对大型Elasticsearch集群设计。它能够从Elasticsearch集群收集各类指标并转换为Prometheus兼容格式,同时提供灵活的配置选项以避免因指标过多导致Prometheus服务器过载。该导出器支持指标过滤、单位转换、自动元数据更新及指标生命周期管理,适用于需要精细化监控Elasticsearch集群的场景。
/metrics页面服务,提高稳定性exporter_allow_zero_metrics控制)_bytes和_seconds后缀transport_actions_cluster:monitor/nodes/info[n]_requests_count→transport_actions_cluster_monitor_nodes_info:n:_requests_count)vin_cluster_version等命名空间标签,便于集群版本间指标对比vin_cluster_version标签实现不同版本集群指标对比基础运行命令:
bashdocker run --network=host -it vinted/elasticsearch_exporter --elasticsearch_url=http://IP:PORT
抓取节点统计子系统(thread_pool)指标
bashdocker run --network=host -it vinted/elasticsearch_exporter \ --elasticsearch_url=http://IP:PORT \ --exporter_metrics_enabled="nodes_stats=true" \ --elasticsearch_path_parameters="nodes_stats=thread_pool"
同时抓取thread_pool和fs子系统指标
bashdocker run --network=host -it vinted/elasticsearch_exporter \ --elasticsearch_url=http://IP:PORT \ --exporter_metrics_enabled="nodes_stats=true" \ --elasticsearch_path_parameters="nodes_stats=thread_pool,fs"
| 配置标志 | 描述 |
|---|---|
exporter_include_labels | 配置要包含的标签 |
exporter_skip_labels | 配置要跳过的标签 |
exporter_skip_metrics | 配置要跳过的指标 |
elasticsearch_global_timeout | 全局请求超时时间 |
exporter_poll_default_interval | 默认指标轮询间隔 |
exporter_poll_intervals | 按指标设置轮询间隔 |
exporter_metrics_enabled | 启用的指标类型 |
exporter_metadata_refresh_interval | 元数据刷新间隔 |
/_cat子系统:
/_cluster子系统:
/_nodes子系统:
/_stats子系统:
该导出器自身也会暴露监控指标,包括:
# HELP elasticsearch_subsystem_request_duration_seconds Elasticsearch子系统请求延迟(秒) # TYPE elasticsearch_subsystem_request_duration_seconds histogram elasticsearch_subsystem_request_duration_seconds_bucket{cluster="devnull",subsystem="/_nodes/os",le="0.005"} 0 elasticsearch_subsystem_request_duration_seconds_sum{cluster="devnull",subsystem="/nodes_stats"} 0.130069193 elasticsearch_subsystem_request_duration_seconds_count{cluster="devnull",subsystem="/nodes_stats"} 1 # HELP http_request_duration_seconds HTTP请求延迟(秒) # TYPE http_request_duration_seconds histogram http_request_duration_seconds_bucket{handler="/metrics",le="0.005"} 1 http_request_duration_seconds_sum{handler="/metrics"} 0.004372555 http_request_duration_seconds_count{handler="/metrics"} 1 # 进程指标 process_cpu_seconds_total 0.24 process_max_fds 1024 process_open_fds 16 process_resident_memory_bytes 25006080 process_start_time_seconds 1605894185.46 process_virtual_memory_bytes 1345773568
日志级别:info,warn,error,debug,trace
bashexport RUST_LOG=info,reqwest=debug
bashexport RUST_LOG=trace
MIT
您可以使用以下命令拉取该镜像。请将 <标签> 替换为具体的标签版本。如需查看所有可用标签版本,请访问 标签列表页面。


来自真实用户的反馈,见证轩辕镜像的优质服务