Grokbase › Groups › Hadoop › common-user › December 2009
FAQ
When I run the balancer, it says it's moving 10G, but after those 10G are moved, it's reported that only ~ 1G is moved.

What could be causing this discrepancy?

Thanks so much in advance for your help.

--jake

2009-12-21 21:53:25,967 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: 1 over utilized nodes: 172.18.141.95:50010
2009-12-21 21:53:25,967 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: 0 under utilized nodes:
2009-12-21 21:53:25,967 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: Need to move 292.74 GB bytes to make the cluster balanced.
2009-12-21 21:53:25,968 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: Decided to move 10 GB bytes from 172.18.141.95:50010 to 172.18.141.98:50010
2009-12-21 21:53:25,968 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: Will move 10 GBbytes in this iteration

..... moving blocks .....

2009-12-21 22:15:56,249 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: 1 over utilized nodes: 172.18.141.95:50010
2009-12-21 22:15:56,249 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: 0 under utilized nodes:
2009-12-21 22:15:56,249 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: Need to move 291.4 GB bytes to make the cluster balanced.
2009-12-21 22:15:56,249 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: Decided to move 10 GB bytes from 172.18.141.95:50010 to 172.18.141.96:50010
2009-12-21 22:15:56,249 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: Will move 10 GBbytes in this iteration

Search Discussions

  • Jacob Olsen at Dec 21, 2009 at 10:48 pm ⇧
    And indeed, I verify only ~1G of data has been moved. Any ideas?

    --jake
    On 12/21/09 2:18 PM, Jacob Olsen wrote:
    When I run the balancer, it says it's moving 10G, but after those 10G are moved, it's reported that only ~ 1G is moved.

    What could be causing this discrepancy?

    Thanks so much in advance for your help.

    --jake

    2009-12-21 21:53:25,967 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: 1 over utilized nodes: 172.18.141.95:50010
    2009-12-21 21:53:25,967 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: 0 under utilized nodes:
    2009-12-21 21:53:25,967 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: Need to move 292.74 GB bytes to make the cluster balanced.
    2009-12-21 21:53:25,968 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: Decided to move 10 GB bytes from 172.18.141.95:50010 to 172.18.141.98:50010
    2009-12-21 21:53:25,968 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: Will move 10 GBbytes in this iteration

    ..... moving blocks .....

    2009-12-21 22:15:56,249 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: 1 over utilized nodes: 172.18.141.95:50010
    2009-12-21 22:15:56,249 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: 0 under utilized nodes:
    2009-12-21 22:15:56,249 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: Need to move 291.4 GB bytes to make the cluster balanced.
    2009-12-21 22:15:56,249 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: Decided to move 10 GB bytes from 172.18.141.95:50010 to 172.18.141.96:50010
    2009-12-21 22:15:56,249 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: Will move 10 GBbytes in this iteration
  • Jacob Olsen at Dec 22, 2009 at 12:13 am ⇧
    Answering my own questions here:

    But, after a few stops/starts and WARNS:

    On 12/21/09 2:48 PM, Jacob Olsen wrote:
    And indeed, I verify only ~1G of data has been moved. Any ideas?

    --jake
    On 12/21/09 2:18 PM, Jacob Olsen wrote:
    When I run the balancer, it says it's moving 10G, but after those 10G are moved, it's reported that only ~ 1G is moved.

    What could be causing this discrepancy?

    Thanks so much in advance for your help.

    --jake

    2009-12-21 21:53:25,967 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: 1 over utilized nodes: 172.18.141.95:50010
    2009-12-21 21:53:25,967 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: 0 under utilized nodes:
    2009-12-21 21:53:25,967 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: Need to move 292.74 GB bytes to make the cluster balanced.
    2009-12-21 21:53:25,968 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: Decided to move 10 GB bytes from 172.18.141.95:50010 to 172.18.141.98:50010
    2009-12-21 21:53:25,968 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: Will move 10 GBbytes in this iteration

    ..... moving blocks .....

    2009-12-21 22:15:56,249 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: 1 over utilized nodes: 172.18.141.95:50010
    2009-12-21 22:15:56,249 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: 0 under utilized nodes:
    2009-12-21 22:15:56,249 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: Need to move 291.4 GB bytes to make the cluster balanced.
    2009-12-21 22:15:56,249 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: Decided to move 10 GB bytes from 172.18.141.95:50010 to 172.18.141.96:50010
    2009-12-21 22:15:56,249 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: Will move 10 GBbytes in this iteration
  • Jacob Olsen at Dec 22, 2009 at 4:35 am ⇧
    Answering my own question here.

    Make sure your dfs.balance.bandwidthPerSec is the same on all of your
    datanodes, or else, you will observe the "funkiness".

    --jake
    On 12/21/09 3:41 PM, Jacob Olsen wrote:
    Answering my own questions here:

    But, after a few stops/starts and WARNS:

    On 12/21/09 2:48 PM, Jacob Olsen wrote:
    And indeed, I verify only ~1G of data has been moved. Any ideas?

    --jake
    On 12/21/09 2:18 PM, Jacob Olsen wrote:
    When I run the balancer, it says it's moving 10G, but after those 10G are moved, it's reported that only ~ 1G is moved.

    What could be causing this discrepancy?

    Thanks so much in advance for your help.

    --jake

    2009-12-21 21:53:25,967 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: 1 over utilized nodes: 172.18.141.95:50010
    2009-12-21 21:53:25,967 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: 0 under utilized nodes:
    2009-12-21 21:53:25,967 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: Need to move 292.74 GB bytes to make the cluster balanced.
    2009-12-21 21:53:25,968 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: Decided to move 10 GB bytes from 172.18.141.95:50010 to 172.18.141.98:50010
    2009-12-21 21:53:25,968 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: Will move 10 GBbytes in this iteration

    ..... moving blocks .....

    2009-12-21 22:15:56,249 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: 1 over utilized nodes: 172.18.141.95:50010
    2009-12-21 22:15:56,249 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: 0 under utilized nodes:
    2009-12-21 22:15:56,249 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: Need to move 291.4 GB bytes to make the cluster balanced.
    2009-12-21 22:15:56,249 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: Decided to move 10 GB bytes from 172.18.141.95:50010 to 172.18.141.96:50010
    2009-12-21 22:15:56,249 INFO org.apache.hadoop.hdfs.server.balancer.Balancer: Will move 10 GBbytes in this iteration

Related Discussions

Discussion Navigation
viewthread | post
Discussion Overview
groupcommon-user @
categorieshadoop
postedDec 21, '09 at 10:19p
activeDec 22, '09 at 4:35a
posts4
users1
websitehadoop.apache.org...
irc#hadoop

1 user in discussion

Jacob Olsen: 4 posts

Content

People

Support

Translate

site design / logo © 2022 Grokbase