[
https://issues.apache.org/jira/browse/HDFS-4979?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13718557#comment-13718557
]
Suresh Srinivas commented on HDFS-4979:
---------------------------------------
Here is a quick bench mark I did to test the impact of retryCache on namenode
operation. RetryCache has the most impact on create() call. That is what I have
used in the tests:
Command run:
{noformat}
bin/hadoop jar share/hadoop/hdfs/hadoop-hdfs-3.0.0-SNAPSHOT-tests.jar
org.apache.hadoop.hdfs.server.namenode.NNThroughputBenchmark -op create
-threads 100 -files 10000
{noformat}
I ran three iterations (100 threads creating 10K files):
With retry cache (Elapsed time and Ops per second): (3101ms,
3224.766204450177), (3133ms, 3191.828917969997), (3253, 3074.085459575776)
Without retry cache (Elapsed time and Ops per second): (3236ms,
3090.234857849196), (3124ms, 3201.024327784891), (3119, 3206.155819172812)
As expected, look up and adding of entry to a hashmap, outside the namesystem
lock does not have significant impact on the operational throughput of the
namenode.
> Implement retry cache on the namenode
> -------------------------------------
>
> Key: HDFS-4979
> URL: https://issues.apache.org/jira/browse/HDFS-4979
> Project: Hadoop HDFS
> Issue Type: Sub-task
> Components: namenode
> Reporter: Suresh Srinivas
> Assignee: Suresh Srinivas
> Attachments: HDFS-4979.10.patch, HDFS-4979.1.patch,
> HDFS-4979.2.patch, HDFS-4979.3.patch, HDFS-4979.4.patch, HDFS-4979.5.patch,
> HDFS-4979.6.patch, HDFS-4979.7.patch, HDFS-4979.8.patch, HDFS-4979.9.patch,
> HDFS-4979.patch
>
>
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira
