[ 
https://issues.apache.org/jira/browse/HDFS-7435?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15025772#comment-15025772
 ] 

Mingliang Liu commented on HDFS-7435:
-------------------------------------

In {{NNThroughputBenchmark}} class, the change
{code}
     void formBlockReport() {
       // fill remaining slots with blocks that do not exist
-      for(int idx = blocks.size()-1; idx >= nrBlocks; idx--)
-        blocks.set(idx, new Block(blocks.size() - idx, 0, 0));
-      blockReportList = new BlockListAsLongs(blocks).getBlockListAsLongs();
+      for (int idx = blocks.size()-1; idx >= nrBlocks; idx--) {
+        Block block = new Block(blocks.size() - idx, 0, 0);
+        blocks.set(idx, new BlockReportReplica(block));
+      }
+      blockReportList = BlockListAsLongs.EMPTY;
{code}

Why the last line is not building the {{blockReportList}} using {{blocks}} 
field as following?
{code}
      blockReportList = BlockListAsLongs.encode(blocks);
{code}

I may need more context to understand this patch, while my goal is to work on 
{{NNThroughputBenchmark}}. Thanks.

> PB encoding of block reports is very inefficient
> ------------------------------------------------
>
>                 Key: HDFS-7435
>                 URL: https://issues.apache.org/jira/browse/HDFS-7435
>             Project: Hadoop HDFS
>          Issue Type: Improvement
>          Components: datanode, namenode
>    Affects Versions: 2.0.0-alpha, 3.0.0
>            Reporter: Daryn Sharp
>            Assignee: Daryn Sharp
>            Priority: Critical
>             Fix For: 2.7.0
>
>         Attachments: HDFS-7435.000.patch, HDFS-7435.001.patch, 
> HDFS-7435.002.patch, HDFS-7435.patch, HDFS-7435.patch, HDFS-7435.patch, 
> HDFS-7435.patch, HDFS-7435.patch, HDFS-7435.patch, HDFS-7435.patch, 
> HDFS-7435.patch, HDFS-7435.patch
>
>
> Block reports are encoded as a PB repeating long.  Repeating fields use an 
> {{ArrayList}} with default capacity of 10.  A block report containing tens or 
> hundreds of thousand of longs (3 for each replica) is extremely expensive 
> since the {{ArrayList}} must realloc many times.  Also, decoding repeating 
> fields will box the primitive longs which must then be unboxed.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Reply via email to