[jira] [Created] (HDFS-12601) Implement new hdfs balancer's threshold units

["Ruslan Dautkhanov (JIRA)" <ji...@apache.org>]

Ruslan Dautkhanov created HDFS-12601:
----------------------------------------

             Summary: Implement new hdfs balancer's threshold units
                 Key: HDFS-12601
                 URL: https://issues.apache.org/jira/browse/HDFS-12601
             Project: Hadoop HDFS
          Issue Type: Improvement
          Components: balancer & mover
    Affects Versions: 3.0.0-alpha3, 2.7.4, 2.6.5
            Reporter: Ruslan Dautkhanov


Balancer threshold unit is inappropriate in most cases for new clusters, that have a lot of capacity and small used%. 

For example, in one of our new clusters HDFS capacity is *2.2 Pb* and only *160Tb* used (across all DNs). So 1% threshold equals to *0.55* Tb (there are 40 nodes in this cluster) for `hdfs balancer -threshold` parameter. 
Now we have some DNs that have as low as *3.5*Tb 
and other DNs as high as *4.6* Tb. 

So the actual disbalance is more like *24%*.
`hdfs balancer -threshold *1*` command says there is nothing to balance (and I can't put smaller value than 1).
Balancer now thinks that the disbalance is less than 1% (based on full capacity), 
when it's actually 24%. 

We see that those nodes with more data actually getting more processing tasks 
(because of data locality).

It would be great to introduce a suffix for -threshold balancer parameter:
* 10c ('c' for `c`apacity) would mean 10% from DN's capacity (current behavior, will default to 'c' if not specified so this change is backward compatible);
* 10u ('u' for `u`sed space variance across all DNs) would be measured as %min_used / %max_used. For the example above, the cluster would get rebalanced correctly as current disbalance is 24%.






--
This message was sent by Atlassian JIRA
(v6.4.14#64029)

---------------------------------------------------------------------
To unsubscribe, e-mail: hdfs-dev-unsubscribe@hadoop.apache.org
For additional commands, e-mail: hdfs-dev-help@hadoop.apache.org