You are viewing a plain text version of this content. The canonical link for it is here.
Posted to common-issues@hadoop.apache.org by "Sneha Vijayarajan (Jira)" <ji...@apache.org> on 2020/03/17 04:24:00 UTC
[jira] [Commented] (HADOOP-16852) ABFS: Send error back to client
for Read Ahead request failure
[ https://issues.apache.org/jira/browse/HADOOP-16852?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17060626#comment-17060626 ]
Sneha Vijayarajan commented on HADOOP-16852:
--------------------------------------------
HNS Enabled Account - East US 2
[INFO] Results:
[INFO]
[INFO] Tests run: 58, Failures: 0, Errors: 0, Skipped: 0
[WARNING] Tests run: 414, Failures: 0, Errors: 0, Skipped: 36
[WARNING] Tests run: 194, Failures: 0, Errors: 0, Skipped: 128
Non-HNS Enabled Account - East US 2
[INFO] Results:
[INFO]
[INFO] Tests run: 58, Failures: 0, Errors: 0, Skipped: 0
[WARNING] Tests run: 414, Failures: 0, Errors: 0, Skipped: 226
[WARNING] Tests run: 194, Failures: 0, Errors: 0, Skipped: 128
> ABFS: Send error back to client for Read Ahead request failure
> --------------------------------------------------------------
>
> Key: HADOOP-16852
> URL: https://issues.apache.org/jira/browse/HADOOP-16852
> Project: Hadoop Common
> Issue Type: Sub-task
> Components: fs/azure
> Affects Versions: 3.3.1
> Reporter: Sneha Vijayarajan
> Assignee: Sneha Vijayarajan
> Priority: Major
>
> Issue seen by a customer:
> The failed requests we were seeing in the AbfsClient logging actually never made it out over the wire. We have found that there’s an issue with ADLS passthrough and the 8 read ahead threads that ADLSv2 spawns in ReadBufferManager.java. We depend on thread local storage in order to get the right JWT token and those threads do not have the right information in their thread local storage. Thus, when they pick up a task from the read ahead queue they fail by throwing an AzureCredentialNotFoundException exception in AbfsRestOperation.executeHttpOperation() where it calls client.getAccessToken(). This exception is silently swallowed by the read ahead threads in ReadBufferWorker.run(). As a result, every read ahead attempt results in a failed executeHttpOperation(), but still calls AbfsClientThrottlingIntercept.updateMetrics() and contributes to throttling (despite not making it out over the wire). After the read aheads fail, the main task thread performs the read with the right thread local storage information and succeeds, but first sleeps for up to 10 seconds due to the throttling.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: common-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: common-issues-help@hadoop.apache.org