[
https://issues.apache.org/jira/browse/HADOOP-18521?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17630413#comment-17630413
]
ASF GitHub Bot commented on HADOOP-18521:
-----------------------------------------
steveloughran commented on PR #5117:
URL: https://github.com/apache/hadoop/pull/5117#issuecomment-1307225146
going to have to rebase this.
i also intend to have prefetch threads update the input streams with
* gauge of active prefetches
* amount of data/duration
measuring how much data was discarded for a stream would be interesting too,
but a bit fiddlier
reader thread jsut gets iostats off the stream, casts to IOStatisticsStore
then uses it as a duration tracker and gauge stats source; straightforward
> ABFS ReadBufferManager buffer sharing across concurrent HTTP requests
> ---------------------------------------------------------------------
>
> Key: HADOOP-18521
> URL: https://issues.apache.org/jira/browse/HADOOP-18521
> Project: Hadoop Common
> Issue Type: Bug
> Components: fs/azure
> Affects Versions: 3.3.2, 3.3.3, 3.3.4
> Reporter: Steve Loughran
> Assignee: Steve Loughran
> Priority: Critical
> Labels: pull-request-available
>
> AbfsInputStream.close() can trigger the return of buffers used for active
> prefetch GET requests into the ReadBufferManager free buffer pool.
> A subsequent prefetch by a different stream in the same process may acquire
> this same buffer. This can lead to risk of corruption of its own prefetched
> data, data which may then be returned to that other thread.
> On releases without the fix for this (3.3.2 to 3.3.4), the bug can be avoided
> by disabling all prefetching
> {code}
> fs.azure.readaheadqueue.depth
> {code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: common-issues-h...@hadoop.apache.org
