[
https://issues.apache.org/jira/browse/HADOOP-11867?focusedWorklogId=657332&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-657332
]
ASF GitHub Bot logged work on HADOOP-11867:
-------------------------------------------
Author: ASF GitHub Bot
Created on: 29/Sep/21 15:42
Start Date: 29/Sep/21 15:42
Worklog Time Spent: 10m
Work Description: steveloughran commented on pull request #3499:
URL: https://github.com/apache/hadoop/pull/3499#issuecomment-930298150
Quick review.
* needs filesystem spec
* and a contract test
* test to include
-overlapping ranges
-beyond file length
-negative values
-on heap and off heap buffers
* be good to have a PoC of the s3a one, so that we can happy the API xfers
to the store
* and some ORC/parquet branch which shows it can be used
* is there any API we'd want, e.g an fs command which does a single async
ranged get
```
hadoop fs ranged -start 0 -end 345 -out output.txt s3a://file
```
would be good for QE tests
* and we should have a path capability. Anything which supports seek will
also do this (so ftp won't)
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
Issue Time Tracking
-------------------
Worklog Id: (was: 657332)
Time Spent: 7h (was: 6h 50m)
> FS API: Add a high-performance vectored Read to FSDataInputStream API
> ---------------------------------------------------------------------
>
> Key: HADOOP-11867
> URL: https://issues.apache.org/jira/browse/HADOOP-11867
> Project: Hadoop Common
> Issue Type: New Feature
> Components: fs, fs/azure, fs/s3, hdfs-client
> Affects Versions: 3.0.0
> Reporter: Gopal Vijayaraghavan
> Assignee: Owen O'Malley
> Priority: Major
> Labels: performance, pull-request-available
> Time Spent: 7h
> Remaining Estimate: 0h
>
> The most significant way to read from a filesystem in an efficient way is to
> let the FileSystem implementation handle the seek behaviour underneath the
> API to be the most efficient as possible.
> A better approach to the seek problem is to provide a sequence of read
> locations as part of a single call, while letting the system schedule/plan
> the reads ahead of time.
> This is exceedingly useful for seek-heavy readers on HDFS, since this allows
> for potentially optimizing away the seek-gaps within the FSDataInputStream
> implementation.
> For seek+read systems with even more latency than locally-attached disks,
> something like a {{readFully(long[] offsets, ByteBuffer[] chunks)}} would
> take of the seeks internally while reading chunk.remaining() bytes into each
> chunk (which may be {{slice()}}ed off a bigger buffer).
> The base implementation can stub in this as a sequence of seeks + read() into
> ByteBuffers, without forcing each FS implementation to override this in any
> way.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
