[jira] [Commented] (HDFS-14084) Need for more stats in DFSClient

["Pranay Singh (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/HDFS-14084?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16708010#comment-16708010 ] 

Pranay Singh commented on HDFS-14084:
-------------------------------------

[~stevel@apache.org] I went through the code and found that the StorageStatistics is already implemented in DistributedFileSystem.java, but the problem with StorageStatistics is that it just records the frequency of a particular operation and not it's latency. It appears that though the stats are collected but they are only used by the test programs perhaps for verification purpose like TestDistributedFileSystem.java, StorageStatisticsTracker.java. The other problem is how to display it, I tried printing the stats through the Iterator on the log but that is too verbose.

[~elgoiri] I saw the usage of rpcMetrics(RpcMetrics) in Server.java, which has a function updateMetrics() that records the RPC latency via addRpcProcessingTime() which is called in ProtobufRpcEngine.java at the end RPC call (server side) perhaps similar implementation can be done in client side calling protobuf RPC methods. Please let me know your thoughts on that. This would use the generic Metric interface for publishing the result hence would be more usable.

 

> Need for more stats in DFSClient
> --------------------------------
>
>                 Key: HDFS-14084
>                 URL: https://issues.apache.org/jira/browse/HDFS-14084
>             Project: Hadoop HDFS
>          Issue Type: Improvement
>    Affects Versions: 3.0.0
>            Reporter: Pranay Singh
>            Assignee: Pranay Singh
>            Priority: Minor
>         Attachments: HDFS-14084.001.patch
>
>
> The usage of HDFS has changed from being used as a map-reduce filesystem, now it's becoming more of like a general purpose filesystem. In most of the cases there are issues with the Namenode so we have metrics to know the workload or stress on Namenode.
> However, there is a need to have more statistics collected for different operations/RPCs in DFSClient to know which RPC operations are taking longer time or to know what is the frequency of the operation.These statistics can be exposed to the users of DFS Client and they can periodically log or do some sort of flow control if the response is slow. This will also help to isolate HDFS issue in a mixed environment where on a node say we have Spark, HBase and Impala running together. We can check the throughput of different operation across client and isolate the problem caused because of noisy neighbor or network congestion or shared JVM.
> We have dealt with several problems from the field for which there is no conclusive evidence as to what caused the problem. If we had metrics or stats in DFSClient we would be better equipped to solve such complex problems.
> List of jiras for reference:
> -------------------------
>  HADOOP-15538 HADOOP-15530 ( client side deadlock)



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

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