[
https://issues.apache.org/jira/browse/HADOOP-17250?focusedWorklogId=485754&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-485754
]
ASF GitHub Bot logged work on HADOOP-17250:
-------------------------------------------
Author: ASF GitHub Bot
Created on: 17/Sep/20 14:01
Start Date: 17/Sep/20 14:01
Worklog Time Spent: 10m
Work Description: snvijaya commented on pull request #2307:
URL: https://github.com/apache/hadoop/pull/2307#issuecomment-694256719
> Sneha,
> What are the likely times to
>
> 1. negotiate a new HTTPS connection
> 2. read 4MB in a single ranged GET request
> 3. read less that 4MB in a single ranged GET request, e.g. 2MB.
>
> If there's a fixed latency for the GET irrespective of size, then small
reads are very inefficient per byte, reading the whole buffer would be
justifiable.
>
> Also: which makes for the simplest code to write. review and maintain?
Let's not ignore that little detail, especially given my experience of shipping
a broken implementation of this in S3AInputStream.
Hi Steve, I get your inputs and agree that observations from above points
can validate a better config setting for readaheadrange. Let me try to see if I
can measure up the points 1-3. Request you to give me a couple of days to get
back.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
Issue Time Tracking
-------------------
Worklog Id: (was: 485754)
Time Spent: 1.5h (was: 1h 20m)
> ABFS: Allow random read sizes to be of buffer size
> --------------------------------------------------
>
> Key: HADOOP-17250
> URL: https://issues.apache.org/jira/browse/HADOOP-17250
> Project: Hadoop Common
> Issue Type: Sub-task
> Components: fs/azure
> Affects Versions: 3.3.0
> Reporter: Sneha Vijayarajan
> Assignee: Sneha Vijayarajan
> Priority: Major
> Labels: abfsactive, pull-request-available
> Time Spent: 1.5h
> Remaining Estimate: 0h
>
> ADLS Gen2/ABFS driver is optimized to read only the bytes that are requested
> for when the read pattern is random.
> It was observed in some spark jobs that though the reads are random, the next
> read doesn't skip by a lot and can be served by the earlier read if read was
> done in buffer size. As a result the job triggered a higher count of read
> calls and resulted in higher job runtime.
> When these jobs were run against Gen1 which always reads in buffer size , the
> jobs fared well.
> In this Jira we try to provide a control over config on random read to be of
> requested size or buffer size.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
