<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>question Hash join node no-child time is much bigger than the sum of all breakdown costs in Archives of Support Questions (Read Only)</title>
    <link>https://community.cloudera.com/t5/Archives-of-Support-Questions/Hash-join-node-no-child-time-is-much-bigger-than-the-sum-of/m-p/37018#M17819</link>
    <description>&lt;P&gt;Hi&lt;/P&gt;&lt;P&gt;Can any one help to explain what's going on in this hash join node. The non-child time is 5s326ms. However, if I sum up all the breakdown costs, i.e., build time, probe time, build partition time and etc, it is&amp;nbsp;not equal to the execution time of this node, i.e., non-child time. So what part of the execution time is missing from this profile?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;The full profile is attached in the link below. We are&amp;nbsp;using&amp;nbsp;&lt;SPAN&gt;CDH4.5.8 Impala 2.2.&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;HASH_JOIN_NODE (id=2):(Total: 8s009ms, non-child: &lt;FONT color="#FF0000"&gt;5s326ms&lt;/FONT&gt;, % non-child: 66.51%)&lt;BR /&gt;ExecOption: Build Side Codegen Enabled, Probe Side Codegen Enabled, Join Build-Side Prepared Asynchronously&lt;BR /&gt;- BuildPartitionTime: &lt;FONT color="#FF0000"&gt;246.892ms&lt;/FONT&gt;&lt;BR /&gt;- BuildRows: 1.50M (1504350)&lt;BR /&gt;- BuildRowsPartitioned: 1.50M (1504350)&lt;BR /&gt;- BuildTime: &lt;FONT color="#FF0000"&gt;205.22ms&lt;/FONT&gt;&lt;BR /&gt;- GetNewBlockTime: &lt;FONT color="#FF0000"&gt;2.107ms&lt;/FONT&gt;&lt;BR /&gt;- HashBuckets: 4.19M (4194304)&lt;BR /&gt;- LargestPartitionPercent: 6 (6)&lt;BR /&gt;- MaxPartitionLevel: 0 (0)&lt;BR /&gt;- NumRepartitions: 0 (0)&lt;BR /&gt;- PartitionsCreated: 16 (16)&lt;BR /&gt;- PeakMemoryUsage: 451.02 MB (472932352)&lt;BR /&gt;- PinTime: 0ns&lt;BR /&gt;- ProbeRows: 2.50M (2502844)&lt;BR /&gt;- ProbeRowsPartitioned: 0 (0)&lt;BR /&gt;- ProbeTime: &lt;FONT color="#FF0000"&gt;860.379ms&lt;/FONT&gt;&lt;BR /&gt;- RowsReturned: 417.52K (417520)&lt;BR /&gt;- RowsReturnedRate: 52.13 K/sec&lt;BR /&gt;- SpilledPartitions: 0 (0)&lt;BR /&gt;- UnpinTime: &lt;FONT color="#FF0000"&gt;997ns&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;A href="https://my.syncplicity.com/share/knuknsvjyz1kzyu/profile" target="_blank"&gt;https://my.syncplicity.com/share/knuknsvjyz1kzyu/profile&lt;/A&gt;&lt;/P&gt;&lt;P&gt;password: 123456&lt;/P&gt;</description>
    <pubDate>Fri, 16 Sep 2022 10:02:05 GMT</pubDate>
    <dc:creator>epstvxj</dc:creator>
    <dc:date>2022-09-16T10:02:05Z</dc:date>
    <item>
      <title>Hash join node no-child time is much bigger than the sum of all breakdown costs</title>
      <link>https://community.cloudera.com/t5/Archives-of-Support-Questions/Hash-join-node-no-child-time-is-much-bigger-than-the-sum-of/m-p/37018#M17819</link>
      <description>&lt;P&gt;Hi&lt;/P&gt;&lt;P&gt;Can any one help to explain what's going on in this hash join node. The non-child time is 5s326ms. However, if I sum up all the breakdown costs, i.e., build time, probe time, build partition time and etc, it is&amp;nbsp;not equal to the execution time of this node, i.e., non-child time. So what part of the execution time is missing from this profile?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;The full profile is attached in the link below. We are&amp;nbsp;using&amp;nbsp;&lt;SPAN&gt;CDH4.5.8 Impala 2.2.&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;HASH_JOIN_NODE (id=2):(Total: 8s009ms, non-child: &lt;FONT color="#FF0000"&gt;5s326ms&lt;/FONT&gt;, % non-child: 66.51%)&lt;BR /&gt;ExecOption: Build Side Codegen Enabled, Probe Side Codegen Enabled, Join Build-Side Prepared Asynchronously&lt;BR /&gt;- BuildPartitionTime: &lt;FONT color="#FF0000"&gt;246.892ms&lt;/FONT&gt;&lt;BR /&gt;- BuildRows: 1.50M (1504350)&lt;BR /&gt;- BuildRowsPartitioned: 1.50M (1504350)&lt;BR /&gt;- BuildTime: &lt;FONT color="#FF0000"&gt;205.22ms&lt;/FONT&gt;&lt;BR /&gt;- GetNewBlockTime: &lt;FONT color="#FF0000"&gt;2.107ms&lt;/FONT&gt;&lt;BR /&gt;- HashBuckets: 4.19M (4194304)&lt;BR /&gt;- LargestPartitionPercent: 6 (6)&lt;BR /&gt;- MaxPartitionLevel: 0 (0)&lt;BR /&gt;- NumRepartitions: 0 (0)&lt;BR /&gt;- PartitionsCreated: 16 (16)&lt;BR /&gt;- PeakMemoryUsage: 451.02 MB (472932352)&lt;BR /&gt;- PinTime: 0ns&lt;BR /&gt;- ProbeRows: 2.50M (2502844)&lt;BR /&gt;- ProbeRowsPartitioned: 0 (0)&lt;BR /&gt;- ProbeTime: &lt;FONT color="#FF0000"&gt;860.379ms&lt;/FONT&gt;&lt;BR /&gt;- RowsReturned: 417.52K (417520)&lt;BR /&gt;- RowsReturnedRate: 52.13 K/sec&lt;BR /&gt;- SpilledPartitions: 0 (0)&lt;BR /&gt;- UnpinTime: &lt;FONT color="#FF0000"&gt;997ns&lt;/FONT&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;A href="https://my.syncplicity.com/share/knuknsvjyz1kzyu/profile" target="_blank"&gt;https://my.syncplicity.com/share/knuknsvjyz1kzyu/profile&lt;/A&gt;&lt;/P&gt;&lt;P&gt;password: 123456&lt;/P&gt;</description>
      <pubDate>Fri, 16 Sep 2022 10:02:05 GMT</pubDate>
      <guid>https://community.cloudera.com/t5/Archives-of-Support-Questions/Hash-join-node-no-child-time-is-much-bigger-than-the-sum-of/m-p/37018#M17819</guid>
      <dc:creator>epstvxj</dc:creator>
      <dc:date>2022-09-16T10:02:05Z</dc:date>
    </item>
    <item>
      <title>Re: Hash join node no-child time is much bigger than the sum of all breakdown costs</title>
      <link>https://community.cloudera.com/t5/Archives-of-Support-Questions/Hash-join-node-no-child-time-is-much-bigger-than-the-sum-of/m-p/37049#M17820</link>
      <description>&lt;P&gt;This is apperently a bug that has been fixed in more recent versions:&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;A href="https://issues.cloudera.org/browse/IMPALA-2075" target="_blank"&gt;https://issues.cloudera.org/browse/IMPALA-2075&lt;/A&gt;&lt;/P&gt;</description>
      <pubDate>Thu, 04 Feb 2016 19:17:17 GMT</pubDate>
      <guid>https://community.cloudera.com/t5/Archives-of-Support-Questions/Hash-join-node-no-child-time-is-much-bigger-than-the-sum-of/m-p/37049#M17820</guid>
      <dc:creator>jbapple</dc:creator>
      <dc:date>2016-02-04T19:17:17Z</dc:date>
    </item>
    <item>
      <title>Re: Hash join node no-child time is much bigger than the sum of all breakdown costs</title>
      <link>https://community.cloudera.com/t5/Archives-of-Support-Questions/Hash-join-node-no-child-time-is-much-bigger-than-the-sum-of/m-p/37052#M17821</link>
      <description>&lt;P&gt;Thanks. Does this affect the final execution time listed in the Timeline part of the profile, do I have to substract the additional time recored in the hash join part to get the correct query execution time?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Thu, 04 Feb 2016 19:25:22 GMT</pubDate>
      <guid>https://community.cloudera.com/t5/Archives-of-Support-Questions/Hash-join-node-no-child-time-is-much-bigger-than-the-sum-of/m-p/37052#M17821</guid>
      <dc:creator>epstvxj</dc:creator>
      <dc:date>2016-02-04T19:25:22Z</dc:date>
    </item>
    <item>
      <title>Re: Hash join node no-child time is much bigger than the sum of all breakdown costs</title>
      <link>https://community.cloudera.com/t5/Archives-of-Support-Questions/Hash-join-node-no-child-time-is-much-bigger-than-the-sum-of/m-p/37054#M17822</link>
      <description>No, it does not affect the timeline.</description>
      <pubDate>Thu, 04 Feb 2016 20:50:55 GMT</pubDate>
      <guid>https://community.cloudera.com/t5/Archives-of-Support-Questions/Hash-join-node-no-child-time-is-much-bigger-than-the-sum-of/m-p/37054#M17822</guid>
      <dc:creator>jbapple</dc:creator>
      <dc:date>2016-02-04T20:50:55Z</dc:date>
    </item>
  </channel>
</rss>

