hadoop-common-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Steve Loughran (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HADOOP-13065) Add a new interface for retrieving FS and FC Statistics
Date Tue, 03 May 2016 08:58:13 GMT

    [ https://issues.apache.org/jira/browse/HADOOP-13065?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15268386#comment-15268386

Steve Loughran commented on HADOOP-13065:

Related to this, I've come across some details about how the reflection-based {{AtomicLongFieldUpdater}}
is going to become a lot closer to non-atomic {{volatile long ++}} calls: http://shipilev.net/blog/2015/faster-atomic-fu/

This argues in favour of using this operation for updating metrics directly...it'd mean that
the variables could just be simple {{volatile long}}, with a static {{AtomicLongFieldUpdater}}
used to update them all

public final class readMetrics {

private static final AtomicLongFieldUpdater bytesReadUpdater = AtomicLongFieldUpdater.newUpdater(Cell.class,
private volatile long bytesRead;

public long incBytesRead(long count) {
  return bytesReadUpdater.addAndGet(count);

HBase uses this in {{org.apache.hadoop.hbase.util.Counter}}, where it's described as "High
scalable counter. Thread safe."

> Add a new interface for retrieving FS and FC Statistics
> -------------------------------------------------------
>                 Key: HADOOP-13065
>                 URL: https://issues.apache.org/jira/browse/HADOOP-13065
>             Project: Hadoop Common
>          Issue Type: Improvement
>          Components: fs
>            Reporter: Ram Venkatesh
>            Assignee: Mingliang Liu
>         Attachments: HADOOP-13065-007.patch, HDFS-10175.000.patch, HDFS-10175.001.patch,
HDFS-10175.002.patch, HDFS-10175.003.patch, HDFS-10175.004.patch, HDFS-10175.005.patch, HDFS-10175.006.patch,
> Currently FileSystem.Statistics exposes the following statistics:
> BytesRead
> BytesWritten
> ReadOps
> LargeReadOps
> WriteOps
> These are in-turn exposed as job counters by MapReduce and other frameworks. There is
logic within DfsClient to map operations to these counters that can be confusing, for instance,
mkdirs counts as a writeOp.
> Proposed enhancement:
> Add a statistic for each DfsClient operation including create, append, createSymlink,
delete, exists, mkdirs, rename and expose them as new properties on the Statistics object.
The operation-specific counters can be used for analyzing the load imposed by a particular
job on HDFS. 
> For example, we can use them to identify jobs that end up creating a large number of
> Once this information is available in the Statistics object, the app frameworks like
MapReduce can expose them as additional counters to be aggregated and recorded as part of
job summary.

This message was sent by Atlassian JIRA

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

View raw message