[
https://issues.apache.org/jira/browse/HADOOP-18528?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17633911#comment-17633911
]
ASF GitHub Bot commented on HADOOP-18528:
-----------------------------------------
steveloughran commented on PR #5134:
URL: https://github.com/apache/hadoop/pull/5134#issuecomment-1313985228
where do you test it?
+ @snvijaya @anmolanmol1234 @pranavsaxena-microsoft
what do you all think? this is us disabling the readahead so we can get on
with the real fix without being in a rush and really trying to get the tests
together. that should include taking the AbfsInputStream test, have it create
real CSV rows (use my mkcsv code as a foundation) and then have use the
mapreduce TextInputFormat code to read it back across multiple threads, just
have hive and spark do
> ABFS: Disable readAhead/prefetching by default
> ----------------------------------------------
>
> Key: HADOOP-18528
> URL: https://issues.apache.org/jira/browse/HADOOP-18528
> Project: Hadoop Common
> Issue Type: Bug
> Components: fs/azure
> Affects Versions: 3.3.4
> Reporter: Mehakmeet Singh
> Assignee: Mehakmeet Singh
> Priority: Major
> Labels: pull-request-available
>
> After the addition of HADOOP-18517, we should disable readAhead by default to
> mitigate inconsistent read results caused by ABFS prefetching, HADOOP-18521.
> As an urgent fix: Disable readAhead/prefetch, tracked for 3.3.5.
> Long-term fix: HADOOP-18521, tracked for 3.3.6.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
