[
https://issues.apache.org/jira/browse/HADOOP-13028?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Steve Loughran updated HADOOP-13028:
------------------------------------
Attachment:
org.apache.hadoop.fs.s3a.scale.TestS3AInputStreamPerformance-output.txt
Performance run for Patch 004. Notice the inferred detail
{code}
An open() call has the equivalent duration of reading 686,641 bytes
{code}
That effectively defines the forward range I should have on my local system if
I want to use the US landsat datasets as a source of data...it's faster to skip
half a megabyte of data than it is to break the link to S3 and set it up again
> add low level counter metrics for S3A; use in read performance tests
> --------------------------------------------------------------------
>
> Key: HADOOP-13028
> URL: https://issues.apache.org/jira/browse/HADOOP-13028
> Project: Hadoop Common
> Issue Type: Sub-task
> Components: fs/s3, metrics
> Affects Versions: 2.8.0
> Reporter: Steve Loughran
> Assignee: Steve Loughran
> Attachments: HADOOP-13028-001.patch, HADOOP-13028-002.patch,
> org.apache.hadoop.fs.s3a.scale.TestS3AInputStreamPerformance-output.txt,
> org.apache.hadoop.fs.s3a.scale.TestS3AInputStreamPerformance-output.txt
>
>
> against S3 (and other object stores), opening connections can be expensive,
> closing connections may be expensive (a sign of a regression).
> S3A FS and individual input streams should have counters of the # of
> open/close/failure+reconnect operations, timers of how long things take. This
> can be used downstream to measure efficiency of the code (how often
> connections are being made), connection reliability, etc.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
