[
https://issues.apache.org/jira/browse/HBASE-8868?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Wei-Chiu Chuang updated HBASE-8868:
-----------------------------------
Status: Patch Available (was: Open)
Expose file system level read metrics for RegionServer.
If the HBase RS runs on top of HDFS, calculate the aggregation of
ReadStatistics of each HdfsFileInputStream. These metrics include:
(1) total number of bytes read from HDFS.
(2) total number of bytes read from local DataNode.
(3) total number of bytes read locally through short-circuit read.
(4) total number of bytes read locally through zero-copy read.
Because HDFS ReadStatistics is calculated per input stream, it is not
feasible to update the aggregated number in real time. Instead, the
metrics are updated when an input stream is closed.
Let me know if this approach makes sense.
> add metric to report client shortcircuit reads
> ----------------------------------------------
>
> Key: HBASE-8868
> URL: https://issues.apache.org/jira/browse/HBASE-8868
> Project: HBase
> Issue Type: Improvement
> Components: metrics, regionserver
> Affects Versions: 0.95.1, 0.94.8
> Reporter: Viral Bajaria
> Assignee: Wei-Chiu Chuang
> Priority: Minor
> Attachments: HBASE-8868.master.001.patch
>
>
> With the availability of shortcircuit reads, when the feature is enabled
> there is no metric which exposes how many times the regionserver was able to
> shortcircuit the read and not make a IPC to the datanode.
> It will be great to add the metric and expose it via Ganglia.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
