第1.9章 elasticsearch Nodes hot_threads

亦凉 2022-02-17 10:14 159阅读 0赞

[Nodes hot\_threads][Nodes hot_threads]，根据官方描述`_nodes/hot_threads`获取集群中每个节点当前热线程，我执行后的返回的结果信息很长，那么该怎么解读呢？  
很容易推理出，hot\_threads在哪里，那么哪里就是性能优化的地方。  
185上面并没有热的线程与下图top监控的指标是吻合的。

::: {bwhs185}{0l0BABnLTfKt4NBEI8uuUA}{V0Ycx2FaS_OUM9Z9jbCLMg}{10.101.3.185}{10.101.3.185:9300}{ml.max_open_jobs=10, ml.enabled=true}
       Hot threads at 2019-04-19T01:52:34.843Z, interval=500ms, busiestThreads=3, ignoreIdleThreads=true:

![1][]  
从下面的快照，可以看到3个get线程占用了资源,但是这个指标能解决什么问题，暂无头绪。

::: {bwhs184}{0CnTTaSaRt-X5m5hj-Oqdw}{OjqrxRmCQfKIjwOHA-Mheg}{10.101.3.184}{10.101.3.184:9300}{ml.max_open_jobs=10, ml.enabled=true}
       Hot threads at 2019-04-19T02:01:14.806Z, interval=500ms, busiestThreads=3, ignoreIdleThreads=true:
       
       16.4% (81.7ms out of 500ms) cpu usage by thread 'elasticsearch[bwhs184][get][T#4]'
         8/10 snapshots sharing following 2 elements
           java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
           java.lang.Thread.run(Thread.java:748)
       
       16.0% (80ms out of 500ms) cpu usage by thread 'elasticsearch[bwhs184][get][T#3]'
         5/10 snapshots sharing following 2 elements
           java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
           java.lang.Thread.run(Thread.java:748)
       
       10.0% (50ms out of 500ms) cpu usage by thread 'elasticsearch[bwhs184][get][T#1]'
         4/10 snapshots sharing following 2 elements
           java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
           java.lang.Thread.run(Thread.java:748)

[Nodes hot_threads]: https://www.elastic.co/guide/en/elasticsearch/reference/5.6/cluster-nodes-hot-threads.html
[1]: /images/20220217/f9850b5c1fbb46e591fd0a47a4fb6dc5.png