elastic/elasticsearch

we should add monitor about whether the netty worker thread pool are busy or not

Open

#80,340 创建于 2021年11月4日

在 GitHub 查看
 (13 评论) (0 反应) (0 负责人)Java (76,700 star) (25,882 fork)batch import
:Distributed/Network>enhancementTeam:Distributedhelp wanted

描述

We find the took in response is smaller than the external statistics timeout in product, part of the reason is that some threads of worker thread pool are relatively busy, the search requests are pending on the worker queue. Yet there is not available api, to get the statistics of worker queue, we have to add metrics and build the source code, If fact, There is a serious queuing here: 97, 64, 68, 108, 133, 61, 62, 123, 70, 66, 118, 110, 65, 52, 95, each number represents one of the worker threads's pending tasks.

If we can add api to get those metrics.

贡献者指南

技术栈
java
领域
backendobservability
议题类型
feature
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
3
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
1-2 days
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
stale
清晰度议题是否清楚说明期望改动、验收标准和下一步。
clear
前置要求
JavaElasticsearch architectureNetty thread pool
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
25
研究方向
Investigate the Netty thread pool usage in Elasticsearch, particularly in the transport netty4 module. Look at existing metrics endpoints like / nodes/stats to understand the pattern for exposing new metrics. Review the issue comments for any prior discussion or pointers.