[
https://issues.apache.org/jira/browse/HADOOP-19767?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18050763#comment-18050763
]
ASF GitHub Bot commented on HADOOP-19767:
-----------------------------------------
anujmodi2021 commented on code in PR #8153:
URL: https://github.com/apache/hadoop/pull/8153#discussion_r2674955845
##########
hadoop-tools/hadoop-azure/src/main/java/org/apache/hadoop/fs/azurebfs/services/AbfsInputStream.java:
##########
@@ -91,20 +92,21 @@ public abstract class AbfsInputStream extends FSInputStream
implements CanUnbuff
*/
private final boolean bufferedPreadDisabled;
// User configured size of read ahead.
- protected final int readAheadRange;
+ private final int readAheadRange;
+
+ private boolean firstRead = true;
Review Comment:
Added
> ABFS: [Read] Introduce Abfs Input Policy for detecting read patterns
> --------------------------------------------------------------------
>
> Key: HADOOP-19767
> URL: https://issues.apache.org/jira/browse/HADOOP-19767
> Project: Hadoop Common
> Issue Type: Sub-task
> Components: fs/azure
> Affects Versions: 3.4.2
> Reporter: Anuj Modi
> Assignee: Anuj Modi
> Priority: Major
> Labels: pull-request-available
>
> Since the onset of ABFS Driver, there has been a single implementation of
> AbfsInputStream. Different kinds of workloads require different heuristics to
> give the best performance for that type of workload. For example:
> # Sequential Read Workloads like DFSIO and DistCP gain performance
> improvement from prefetched
> # Random Read Workloads on other hand do not need Prefetches and enabling
> prefetches for them is an overhead and TPS heavy
> # Query Workloads involving Parquet/ORC files benefit from improvements like
> Footer Read and Small Files Reads
> To accomodate this we need to determine the pattern and accordingly create
> Input Streams implemented for that particular pattern.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
