gpt4 book ai didi

Hadoop reduce 停止运行

转载 作者:可可西里 更新时间:2023-11-01 14:15:38 27 4
gpt4 key购买 nike

我现在有一个可怕的问题。当我在 hadoop 中运行作业时, map 进程正常,达到 100%,没有发生任何故障。然而,当reduce进程运行时,它在达到67%时停止了。这很奇怪。我是hadoop的新手,在网上搜索了很多资料,但现在仍然很困惑。下面是一段输出。

13/10/25 21:40:00 INFO input.FileInputFormat: Total input paths to process : 2
13/10/25 21:40:01 INFO mapred.JobClient: Running job: job_201310252001_0003
13/10/25 21:40:02 INFO mapred.JobClient: map 0% reduce 0%
13/10/25 21:40:30 INFO mapred.JobClient: map 1% reduce 0%
13/10/25 21:40:37 INFO mapred.JobClient: map 2% reduce 0%
13/10/25 21:40:39 INFO mapred.JobClient: map 3% reduce 0%
13/10/25 21:40:40 INFO mapred.JobClient: map 4% reduce 0%
13/10/25 21:40:42 INFO mapred.JobClient: map 5% reduce 0%
13/10/25 21:40:43 INFO mapred.JobClient: map 6% reduce 0%
13/10/25 21:40:45 INFO mapred.JobClient: map 7% reduce 0%
13/10/25 21:40:46 INFO mapred.JobClient: map 9% reduce 0%
13/10/25 21:40:48 INFO mapred.JobClient: map 10% reduce 0%
13/10/25 21:40:49 INFO mapred.JobClient: map 11% reduce 0%
13/10/25 21:40:52 INFO mapred.JobClient: map 14% reduce 0%
13/10/25 21:40:55 INFO mapred.JobClient: map 17% reduce 0%
13/10/25 21:40:58 INFO mapred.JobClient: map 19% reduce 0%
13/10/25 21:41:01 INFO mapred.JobClient: map 22% reduce 0%
13/10/25 21:41:04 INFO mapred.JobClient: map 23% reduce 0%
13/10/25 21:41:05 INFO mapred.JobClient: map 24% reduce 0%
13/10/25 21:41:07 INFO mapred.JobClient: map 26% reduce 0%
13/10/25 21:41:08 INFO mapred.JobClient: map 27% reduce 0%
13/10/25 21:41:10 INFO mapred.JobClient: map 28% reduce 0%
13/10/25 21:41:11 INFO mapred.JobClient: map 29% reduce 0%
13/10/25 21:41:13 INFO mapred.JobClient: map 30% reduce 0%
13/10/25 21:41:14 INFO mapred.JobClient: map 31% reduce 0%
13/10/25 21:41:16 INFO mapred.JobClient: map 32% reduce 0%
13/10/25 21:41:20 INFO mapred.JobClient: map 34% reduce 0%
13/10/25 21:41:23 INFO mapred.JobClient: map 35% reduce 0%
13/10/25 21:41:26 INFO mapred.JobClient: map 36% reduce 0%
13/10/25 21:41:34 INFO mapred.JobClient: map 37% reduce 0%
13/10/25 21:41:39 INFO mapred.JobClient: map 38% reduce 0%
13/10/25 21:41:43 INFO mapred.JobClient: map 40% reduce 0%
13/10/25 21:41:44 INFO mapred.JobClient: map 40% reduce 6%
13/10/25 21:41:46 INFO mapred.JobClient: map 42% reduce 6%
13/10/25 21:41:49 INFO mapred.JobClient: map 43% reduce 6%
13/10/25 21:41:51 INFO mapred.JobClient: map 44% reduce 6%
13/10/25 21:41:52 INFO mapred.JobClient: map 45% reduce 6%
13/10/25 21:41:55 INFO mapred.JobClient: map 46% reduce 6%
13/10/25 21:41:57 INFO mapred.JobClient: map 47% reduce 6%
13/10/25 21:41:58 INFO mapred.JobClient: map 48% reduce 9%
13/10/25 21:42:01 INFO mapred.JobClient: map 51% reduce 12%
13/10/25 21:42:04 INFO mapred.JobClient: map 54% reduce 12%
13/10/25 21:42:07 INFO mapred.JobClient: map 56% reduce 12%
13/10/25 21:42:10 INFO mapred.JobClient: map 58% reduce 12%
13/10/25 21:42:13 INFO mapred.JobClient: map 60% reduce 12%
13/10/25 21:42:16 INFO mapred.JobClient: map 61% reduce 12%
13/10/25 21:42:19 INFO mapred.JobClient: map 62% reduce 15%
13/10/25 21:42:22 INFO mapred.JobClient: map 63% reduce 15%
13/10/25 21:42:23 INFO mapred.JobClient: map 65% reduce 15%
13/10/25 21:42:26 INFO mapred.JobClient: map 66% reduce 15%
13/10/25 21:42:28 INFO mapred.JobClient: map 67% reduce 15%
13/10/25 21:42:29 INFO mapred.JobClient: map 68% reduce 15%
13/10/25 21:42:32 INFO mapred.JobClient: map 69% reduce 15%
13/10/25 21:42:34 INFO mapred.JobClient: map 70% reduce 18%
13/10/25 21:42:35 INFO mapred.JobClient: map 72% reduce 18%
13/10/25 21:42:38 INFO mapred.JobClient: map 75% reduce 18%
13/10/25 21:42:41 INFO mapred.JobClient: map 77% reduce 18%
13/10/25 21:42:44 INFO mapred.JobClient: map 80% reduce 18%
13/10/25 21:42:47 INFO mapred.JobClient: map 82% reduce 18%
13/10/25 21:42:50 INFO mapred.JobClient: map 85% reduce 18%
13/10/25 21:42:53 INFO mapred.JobClient: map 87% reduce 18%
13/10/25 21:42:56 INFO mapred.JobClient: map 88% reduce 18%
13/10/25 21:42:59 INFO mapred.JobClient: map 89% reduce 18%
13/10/25 21:43:02 INFO mapred.JobClient: map 90% reduce 18%
13/10/25 21:43:05 INFO mapred.JobClient: map 91% reduce 18%
13/10/25 21:43:18 INFO mapred.JobClient: map 94% reduce 21%
13/10/25 21:43:21 INFO mapred.JobClient: map 97% reduce 21%
13/10/25 21:43:24 INFO mapred.JobClient: map 99% reduce 27%
13/10/25 21:43:27 INFO mapred.JobClient: map 100% reduce 30%
13/10/25 21:43:30 INFO mapred.JobClient: map 100% reduce 67%

最佳答案

这里的症状是你的代码在你的 reduce 阶段被“卡住了”,要么是因为无限循环,要么只是收到了可笑的数据量,或者其他原因(也许发布你的 reduce 代码?)。

以下是百分比在 reducer 中的工作方式:

  1. 0-33% 是洗牌。这是数据从映射器移动到缩减器(查看它是如何在映射器完成之前开始的)。
  2. 33%-67% 是那种。这只能在映射器完成后开始(查看映射器达到 100% 后它如何从 30% 变为 67%)。
  3. 67%-100% 是您正在运行的实际 reduce 代码。每次 reduce task 完成时,这个百分比都会增加。您的 reduce 任务均未完成。

在 JobTracker 界面中,查看您的作业并查看 reducer 接收了多少数据。如果 reducer 中的记录数量增加,则意味着您可能有太多数据进入 reducer。如果该数字保持不变,您可能会遇到某种无限循环。

关于Hadoop reduce 停止运行,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/19592744/

27 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com